artiq_ddb_template: fixed missing separator

Otherwise artiq_compile and other uses of Core that does not access hardware/network may fail.

.gitignore

@@ -29,6 +29,7 @@ __pycache__/
 /repository/
 /results
 /last_rid.pyon
-/dataset_db.pyon
+/dataset_db.mdb
+/dataset_db.mdb-lock
 /device_db*.py
 /test*

CONTRIBUTING.rst

@@ -26,7 +26,6 @@ report if possible:
   * Operating System
   * ARTIQ version (with recent versions of ARTIQ, run ``artiq_client --version``)
   * Version of the gateware and runtime loaded in the core device (in the output of ``artiq_coremgmt -D .... log``)
-  * If using Conda, output of `conda list`
   * Hardware involved
 
 

MAJOR_VERSION

@@ -1 +0,0 @@
-7

MANIFEST.in

@@ -5,3 +5,4 @@ include versioneer.py
 include artiq/_version.py
 include artiq/coredevice/coredevice_generic.schema.json
 include artiq/compiler/kernel.ld
+include artiq/afws.pem

README.rst

@@ -13,7 +13,7 @@ ARTIQ uses FPGA hardware to perform its time-critical tasks. The `Sinara hardwar
 ARTIQ is designed to be portable to hardware platforms from different vendors and FPGA manufacturers.
 Several different configurations of a `FPGA evaluation kit <https://www.xilinx.com/products/boards-and-kits/ek-k7-kc705-g.html>`_ and of a `Zynq evaluation kit <https://www.xilinx.com/products/boards-and-kits/ek-z7-zc706-g.html>`_ are also used and supported. FPGA platforms can be combined with any number of additional peripherals, either already accessible from ARTIQ or made accessible with little effort.
 
-ARTIQ and its dependencies are available in the form of Nix packages (for Linux) and Conda packages (for Windows and Linux). See `the manual <https://m-labs.hk/experiment-control/resources/>`_ for installation instructions.
+ARTIQ and its dependencies are available in the form of Nix packages (for Linux) and MSYS2 packages (for Windows). See `the manual <https://m-labs.hk/experiment-control/resources/>`_ for installation instructions.
 Packages containing pre-compiled binary images to be loaded onto the hardware platforms are supplied for each configuration.
 Like any open source software ARTIQ can equally be built and installed directly from `source <https://github.com/m-labs/artiq>`_.
 
@@ -29,7 +29,7 @@ Website: https://m-labs.hk/artiq
 License
 =======
 
-Copyright (C) 2014-2021 M-Labs Limited.
+Copyright (C) 2014-2023 M-Labs Limited.
 
 ARTIQ is free software: you can redistribute it and/or modify
 it under the terms of the GNU Lesser General Public License as published by

RELEASE_NOTES.rst

@@ -3,39 +3,151 @@
 Release notes
 =============
 
+ARTIQ-8 (Unreleased)
+--------------------
+
+Highlights:
+
+* New hardware support:
+   - Support for Shuttler, a 16-channel 125MSPS DAC card intended for ion transport.
+     Waveform generator and user API are similar to the NIST PDQ.
+   - Implemented Phaser-servo. This requires recent gateware on Phaser.
+   - Almazny v1.2 with finer RF switch control.
+   - Metlino and Sayma support has been dropped due to complications with synchronous RTIO clocking.
+   - More user LEDs are exposed to RTIO on Kasli.
+   - Implemented Phaser-MIQRO support. This requires the proprietary Phaser MIQRO gateware
+     variant from QUARTIQ.
+   - Sampler: fixed ADC MU to Volt conversion factor for Sampler v2.2+.
+     For earlier hardware versions, specify the hardware version in the device
+     database file (e.g. ``"hw_rev": "v2.1"``) to use the correct conversion factor.
+* Support for distributed DMA, where DMA is run directly on satellites for corresponding
+  RTIO events, increasing bandwidth in scenarios with heavy satellite usage.
+* Support for subkernels, where kernels are run on satellite device CPUs to offload some
+  of the processing and RTIO operations.
+* CPU (on softcore platforms) and AXI bus (on Zynq) are now clocked synchronously with the RTIO
+  clock, to facilitate implementation of local processing on DRTIO satellites, and to slightly
+  reduce RTIO latency.
+* Support for DRTIO-over-EEM, used with Shuttler.
+* Added channel names to RTIO error messages.
+* GUI:
+   - Implemented Applet Request Interfaces which allow applets to modify datasets and set the
+     current values of widgets in the dashboard's experiment windows.
+   - Implemented a new EntryArea widget which allows argument entry widgets to be used in applets.
+   - The "Close all applets" command (shortcut: Ctrl-Alt-W) now ignores docked applets,
+     making it a convenient way to clean up after exploratory work without destroying a
+     carefully arranged default workspace.
+   - Hotkeys now organize experiment windows in the order they were last interacted with:
+      + CTRL+SHIFT+T tiles experiment windows
+      + CTRL+SHIFT+C cascades experiment windows
+* Persistent datasets are now stored in a LMDB database for improved performance.
+* Python's built-in types (such as ``float``, or ``List[...]``) can now be used in type annotations on
+  kernel functions.
+* Full Python 3.10 support.
+* MSYS2 packaging for Windows, which replaces Conda. Conda packages are still available to
+  support legacy installations, but may be removed in a future release.
+
+Breaking changes:
+
+* ``SimpleApplet`` now calls widget constructors with an additional ``ctl`` parameter for control
+  operations, which includes dataset operations. It can be ignored if not needed. For an example usage,
+  refer to the ``big_number.py`` applet.
+* ``SimpleApplet`` and ``TitleApplet`` now call ``data_changed`` with additional parameters. Derived applets
+  should change the function signature as below:
+
+::
+
+  # SimpleApplet
+  def data_changed(self, value, metadata, persist, mods)
+  # SimpleApplet (old version)
+  def data_changed(self, data, mods)
+  # TitleApplet
+  def data_changed(self, value, metadata, persist, mods, title)
+  # TitleApplet (old version)
+  def data_changed(self, data, mods, title)
+
+Accesses to the data argument should be replaced as below:
+
+::
+
+  data[key][0] ==> persist[key]
+  data[key][1] ==> value[key]
+
+* The ``ndecimals`` parameter in ``NumberValue`` and ``Scannable`` has been renamed to ``precision``. 
+  Parameters after and including ``scale`` in both constructors are now keyword-only.
+  Refer to the updated ``no_hardware/arguments_demo.py`` example for current usage.
+* Almazny v1.2 is incompatible with the legacy versions and is the default.
+  To use legacy versions, specify ``almazny_hw_rev`` in the JSON description.
+* kasli_generic.py has been merged into kasli.py, and the demonstration designs without JSON descriptions
+  have been removed. The base classes remain present in kasli.py to support third-party flows without
+  JSON descriptions.
+* Legacy PYON databases should be converted to LMDB with the script below:
+
+::
+
+  from sipyco import pyon
+  import lmdb
+
+  old = pyon.load_file("dataset_db.pyon")
+  new = lmdb.open("dataset_db.mdb", subdir=False, map_size=2**30)
+  with new.begin(write=True) as txn:
+    for key, value in old.items():
+      txn.put(key.encode(), pyon.encode((value, {})).encode())
+  new.close()
+
+* ``artiq.wavesynth`` has been removed.
+
 ARTIQ-7
 -------
 
 Highlights:
 
 * New hardware support:
-   - Kasli-SoC, a new EEM carrier based on a Zynq SoC, enabling much faster kernel execution.
+   - Kasli-SoC, a new EEM carrier based on a Zynq SoC, enabling much faster kernel execution
+     (see: https://arxiv.org/abs/2111.15290).
+   - DRTIO support on Zynq-based devices (Kasli-SoC and ZC706).
+   - DRTIO support on KC705.
    - HVAMP_8CH 8 channel HV amplifier for Fastino / Zotinos
    - Almazny mezzanine board for Mirny
+   - Phaser: improved documentation, exposed the DAC coarse mixer and ``sif_sync``, exposed upconverter calibration
+     and enabling/disabling of upconverter LO & RF outputs, added helpers to align Phaser updates to the
+     RTIO timeline (``get_next_frame_mu()``).
+   - Urukul: ``get()``, ``get_mu()``, ``get_att()``, and ``get_att_mu()`` functions added for AD9910 and AD9912.
 * Softcore targets now use the RISC-V architecture (VexRiscv) instead of OR1K (mor1kx).
+* Gateware FPU is supported on KC705 and Kasli 2.0.
 * Faster compilation for large arrays/lists.
-* Phaser:
+* Faster exception handling.
-   - Improved documentation
+* Several exception handling bugs fixed.
-   - Expose the DAC coarse mixer and ``sif_sync``
+* Support for a simpler shared library system with faster calls into the runtime. This is only used by the NAC3
-   - Exposes upconverter calibration and enabling/disabling of upconverter LO & RF outputs.
+  compiler (nac3ld) and improves RTIO output performance (test_pulse_rate) by 9-10%.
-   - Add helpers to align Phaser updates to the RTIO timeline (``get_next_frame_mu()``)
+* Moninj improvements:
-* ``get()``, ``get_mu()``, ``get_att()``, and ``get_att_mu()`` functions added for AD9910 and AD9912
+  - Urukul monitoring and frequency setting (through dashboard) is now supported.
-* On Kasli, the number of FIFO lanes in the scalable events dispatcher (SED) can now be configured in
+  - Core device moninj is now proxied via the ``aqctl_moninj_proxy`` controller.
-  the JSON hardware description file.
-* ``artiq_ddb_template`` generates edge-counter keys that start with the key of the corresponding
-  TTL device (e.g. ``"ttl_0_counter"`` for the edge counter on TTL device``"ttl_0"``)
-* ``artiq_master`` now has an ``--experiment-subdir`` option to scan only a subdirectory of the
-  repository when building the list of experiments.
 * The configuration entry ``rtio_clock`` supports multiple clocking settings, deprecating the usage
   of compile-time options.
-* DRTIO: added support for 100MHz clock.
+* Added support for 100MHz RTIO clock in DRTIO.
 * Previously detected RTIO async errors are reported to the host after each kernel terminates and a
-  warning is logged. The warning is additional to the one already printed in the core device log upon
+  warning is logged. The warning is additional to the one already printed in the core device log
-  detection of the error.
+  immediately upon detection of the error.
-* HDF5 options can now be passed when creating datasets with ``set_dataset``. This allows
+* Extended Kasli gateware JSON description with configuration for SPI over DIO.
-  in particular to use transparent compression filters as follows:
+* TTL outputs can be now configured to work as a clock generator from the JSON.
-  ``set_dataset(name, value, hdf5_options={"compression": "gzip"})``.
+* On Kasli, the number of FIFO lanes in the scalable events dispatcher (SED) can now be configured in
-* Removed worker DB warning for writing a dataset that is also in the archive
+  the JSON.
+* ``artiq_ddb_template`` generates edge-counter keys that start with the key of the corresponding
+  TTL device (e.g. ``ttl_0_counter`` for the edge counter on TTL device ``ttl_0``).
+* ``artiq_master`` now has an ``--experiment-subdir`` option to scan only a subdirectory of the
+  repository when building the list of experiments.
+* Experiments can now be submitted by-content.
+* The master can now optionally log all experiments submitted into a CSV file.
+* Removed worker DB warning for writing a dataset that is also in the archive.
+* Experiments can now call ``scheduler.check_termination()`` to test if the user
+  has requested graceful termination.
+* ARTIQ command-line programs and controllers now exit cleanly on Ctrl-C.
+* ``artiq_coremgmt reboot`` now reloads gateware as well, providing a more thorough and reliable
+  device reset (7-series FPGAs only).
+* Firmware and gateware can now be built on-demand on the M-Labs server using ``afws_client``
+  (subscribers only). Self-compilation remains possible.
+* Easier-to-use packaging via Nix Flakes.
+* Python 3.10 support (experimental).
 
 Breaking changes:
 
@@ -48,12 +160,11 @@ Breaking changes:
   generated for some configurations.
 * Phaser: fixed coarse mixer frequency configuration
 * Mirny: Added extra delays in ``ADF5356.sync()``. This avoids the need of an extra delay before
-  calling `ADF5356.init()`.
+  calling ``ADF5356.init()``.
-* DRTIO: Changed message alignment from 32-bits to 64-bits.
 * The deprecated ``set_dataset(..., save=...)`` is no longer supported.
-* The internal dataset representation was changed to support tracking HDF5 options like e.g.
+* The ``PCA9548`` I2C switch class was renamed to ``I2CSwitch``, to accommodate support for PCA9547,
-  a compression method. This requires changes to code reading the dataset persistence file
+  and possibly other switches in future. Readback has been removed, and now only one channel per
-  (``dataset_db.pyon``) and to custom applets.
+  switch is supported.
 
 
 ARTIQ-6
@@ -129,7 +240,6 @@ Breaking changes:
 * Experiment classes with underscore-prefixed names are now ignored when ``artiq_client``
   determines which experiment to submit (consistent with ``artiq_run``).
 
-
 ARTIQ-5
 -------
 

artiq/_version.py

@@ -1,13 +1,7 @@
 import os
 
+def get_rev():
+    return os.getenv("VERSIONEER_REV", default="unknown")
+
 def get_version():
-    override = os.getenv("VERSIONEER_OVERRIDE")
+    return os.getenv("VERSIONEER_OVERRIDE", default="8.0+unknown.beta")
-    if override:
-      return override
-    srcroot = os.path.join(os.path.dirname(os.path.abspath(__file__)), os.pardir)
-    with open(os.path.join(srcroot, "MAJOR_VERSION"), "r") as f:
-        version = f.read().strip()
-    version += ".unknown"
-    if os.path.exists(os.path.join(srcroot, "BETA")):
-        version += ".beta"
-    return version

artiq/applets/big_number.py

@@ -1,22 +1,96 @@
 #!/usr/bin/env python3
 
-from PyQt5 import QtWidgets
+from PyQt5 import QtWidgets, QtCore, QtGui
-
 from artiq.applets.simple import SimpleApplet
+from artiq.tools import scale_from_metadata
+from artiq.gui.tools import LayoutWidget
 
 
-class NumberWidget(QtWidgets.QLCDNumber):
+class QResponsiveLCDNumber(QtWidgets.QLCDNumber):
-    def __init__(self, args):
+    doubleClicked = QtCore.pyqtSignal()
-        QtWidgets.QLCDNumber.__init__(self)
+
-        self.setDigitCount(args.digit_count)
+    def mouseDoubleClickEvent(self, event):
+        self.doubleClicked.emit()
+
+
+class QCancellableLineEdit(QtWidgets.QLineEdit):
+    editCancelled = QtCore.pyqtSignal()
+
+    def keyPressEvent(self, event):
+        if event.key() == QtCore.Qt.Key_Escape:
+            self.editCancelled.emit()
+        else:
+            super().keyPressEvent(event)
+
+
+class NumberWidget(LayoutWidget):
+    def __init__(self, args, req):
+        LayoutWidget.__init__(self)
         self.dataset_name = args.dataset
+        self.req = req
+        self.metadata = dict()
 
-    def data_changed(self, data, mods):
+        self.number_area = QtWidgets.QStackedWidget()
+        self.addWidget(self.number_area, 0, 0)
+
+        self.unit_area = QtWidgets.QLabel()
+        self.unit_area.setAlignment(QtCore.Qt.AlignRight | QtCore.Qt.AlignTop)
+        self.addWidget(self.unit_area, 0, 1)
+
+        self.lcd_widget = QResponsiveLCDNumber()
+        self.lcd_widget.setDigitCount(args.digit_count)
+        self.lcd_widget.doubleClicked.connect(self.start_edit)
+        self.number_area.addWidget(self.lcd_widget)
+
+        self.edit_widget = QCancellableLineEdit()
+        self.edit_widget.setValidator(QtGui.QDoubleValidator())
+        self.edit_widget.setAlignment(QtCore.Qt.AlignRight | QtCore.Qt.AlignVCenter)
+        self.edit_widget.editCancelled.connect(self.cancel_edit)
+        self.edit_widget.returnPressed.connect(self.confirm_edit)
+        self.number_area.addWidget(self.edit_widget)
+
+        font = QtGui.QFont()
+        font.setPointSize(60)
+        self.edit_widget.setFont(font)
+
+        unit_font = QtGui.QFont()
+        unit_font.setPointSize(20)
+        self.unit_area.setFont(unit_font)
+
+        self.number_area.setCurrentWidget(self.lcd_widget)
+
+    def start_edit(self):
+        # QLCDNumber value property contains the value of zero
+        # if the displayed value is not a number.
+        self.edit_widget.setText(str(self.lcd_widget.value()))
+        self.edit_widget.selectAll()
+        self.edit_widget.setFocus()
+        self.number_area.setCurrentWidget(self.edit_widget)
+
+    def confirm_edit(self):
+        scale = scale_from_metadata(self.metadata)
+        val = float(self.edit_widget.text())
+        val *= scale
+        self.req.set_dataset(self.dataset_name, val, **self.metadata)
+        self.number_area.setCurrentWidget(self.lcd_widget)
+
+    def cancel_edit(self):
+        self.number_area.setCurrentWidget(self.lcd_widget)
+
+    def data_changed(self, value, metadata, persist, mods):
         try:
-            n = float(data[self.dataset_name]["value"])
+            self.metadata = metadata[self.dataset_name]
+            # This applet will degenerate other scalar types to native float on edit
+            # Use the dashboard ChangeEditDialog for consistent type casting 
+            val = float(value[self.dataset_name])
+            scale = scale_from_metadata(self.metadata)
+            val /= scale
         except (KeyError, ValueError, TypeError):
-            n = "---"
+            val = "---"
-        self.display(n)
+        
+        unit = self.metadata.get("unit", "")
+        self.unit_area.setText(unit)
+        self.lcd_widget.display(val)
 
 
 def main():

artiq/applets/image.py

@@ -7,13 +7,13 @@ from artiq.applets.simple import SimpleApplet
 
 
 class Image(pyqtgraph.ImageView):
-    def __init__(self, args):
+    def __init__(self, args, req):
         pyqtgraph.ImageView.__init__(self)
         self.args = args
 
-    def data_changed(self, data, mods):
+    def data_changed(self, value, metadata, persist, mods):
         try:
-            img = data[self.args.img]["value"]
+            img = value[self.args.img]
         except KeyError:
             return
         self.setImage(img)

artiq/applets/plot_hist.py

@@ -8,20 +8,20 @@ from artiq.applets.simple import TitleApplet
 
 
 class HistogramPlot(pyqtgraph.PlotWidget):
-    def __init__(self, args):
+    def __init__(self, args, req):
         pyqtgraph.PlotWidget.__init__(self)
         self.args = args
         self.timer = QTimer()
         self.timer.setSingleShot(True)
         self.timer.timeout.connect(self.length_warning)
 
-    def data_changed(self, data, mods, title):
+    def data_changed(self, value, metadata, persist, mods, title):
         try:
-            y = data[self.args.y]["value"]
+            y = value[self.args.y]
             if self.args.x is None:
                 x = None
             else:
-                x = data[self.args.x]["value"]
+                x = value[self.args.x]
         except KeyError:
             return
         if x is None:

artiq/applets/plot_xy.py

@@ -6,11 +6,10 @@ from PyQt5.QtCore import QTimer
 import pyqtgraph
 
 from artiq.applets.simple import TitleApplet
-from artiq.master.databases import make_dataset as empty_dataset
 
 
 class XYPlot(pyqtgraph.PlotWidget):
-    def __init__(self, args):
+    def __init__(self, args, req):
         pyqtgraph.PlotWidget.__init__(self)
         self.args = args
         self.timer = QTimer()
@@ -20,16 +19,16 @@ class XYPlot(pyqtgraph.PlotWidget):
                          'Error bars': False,
                          'Fit values': False}
 
-    def data_changed(self, data, mods, title):
+    def data_changed(self, value, metadata, persist, mods, title):
         try:
-            y = data[self.args.y]["value"]
+            y = value[self.args.y]
         except KeyError:
             return
-        x = data.get(self.args.x, empty_dataset())["value"]
+        x = value.get(self.args.x, (False, None))
         if x is None:
             x = np.arange(len(y))
-        error = data.get(self.args.error, empty_dataset())["value"]
+        error = value.get(self.args.error, (False, None))
-        fit = data.get(self.args.fit, empty_dataset())["value"]
+        fit = value.get(self.args.fit, (False, None))
 
         if not len(y) or len(y) != len(x):
             self.mismatch['X values'] = True

artiq/applets/plot_xy_hist.py

@@ -22,7 +22,7 @@ def _compute_ys(histogram_bins, histograms_counts):
 # pyqtgraph.GraphicsWindow fails to behave like a regular Qt widget
 # and breaks embedding. Do not use as top widget.
 class XYHistPlot(QtWidgets.QSplitter):
-    def __init__(self, args):
+    def __init__(self, args, req):
         QtWidgets.QSplitter.__init__(self)
         self.resize(1000, 600)
         self.setWindowTitle("XY/Histogram")
@@ -124,11 +124,11 @@ class XYHistPlot(QtWidgets.QSplitter):
                 return False
         return True
 
-    def data_changed(self, data, mods):
+    def data_changed(self, value, metadata, persist, mods):
         try:
-            xs = data[self.args.xs]["value"]
+            xs = value[self.args.xs]
-            histogram_bins = data[self.args.histogram_bins]["value"]
+            histogram_bins = value[self.args.histogram_bins]
-            histograms_counts = data[self.args.histograms_counts]["value"]
+            histograms_counts = value[self.args.histograms_counts]
         except KeyError:
             return
         if len(xs) != histograms_counts.shape[0]:

artiq/applets/progress_bar.py

@@ -0,0 +1,34 @@
+#!/usr/bin/env python3
+
+from PyQt5 import QtWidgets
+
+from artiq.applets.simple import SimpleApplet
+
+
+class ProgressWidget(QtWidgets.QProgressBar):
+    def __init__(self, args, req):
+        QtWidgets.QProgressBar.__init__(self)
+        self.setMinimum(args.min)
+        self.setMaximum(args.max)
+        self.dataset_value = args.value
+
+    def data_changed(self, value, metadata, persist, mods):
+        try:
+            val = round(value[self.dataset_value])
+        except (KeyError, ValueError, TypeError):
+            val = 0
+        self.setValue(val)
+
+
+
+def main():
+    applet = SimpleApplet(ProgressWidget)
+    applet.add_dataset("value", "counter")
+    applet.argparser.add_argument("--min", type=int, default=0,
+                                  help="minimum (left) value of the bar")
+    applet.argparser.add_argument("--max", type=int, default=100,
+                                  help="maximum (right) value of the bar")
+    applet.run()
+
+if __name__ == "__main__":
+    main()

artiq/applets/simple.py

@@ -7,14 +7,112 @@ import string
 from qasync import QEventLoop, QtWidgets, QtCore
 
 from sipyco.sync_struct import Subscriber, process_mod
+from sipyco.pc_rpc import AsyncioClient as RPCClient
 from sipyco import pyon
 from sipyco.pipe_ipc import AsyncioChildComm
 
-from artiq.master.databases import make_dataset as empty_dataset
+from artiq.language.scan import ScanObject
+
 
 logger = logging.getLogger(__name__)
 
 
+class _AppletRequestInterface:
+    def __init__(self):
+        raise NotImplementedError
+
+    def set_dataset(self, key, value, unit=None, scale=None, precision=None, persist=None):
+        """
+        Set a dataset.
+        See documentation of ``artiq.language.environment.set_dataset``.
+        """
+        raise NotImplementedError
+
+    def mutate_dataset(self, key, index, value):
+        """
+        Mutate a dataset.
+        See documentation of ``artiq.language.environment.mutate_dataset``.
+        """
+        raise NotImplementedError
+
+    def append_to_dataset(self, key, value):
+        """
+        Append to a dataset.
+        See documentation of ``artiq.language.environment.append_to_dataset``.
+        """
+        raise NotImplementedError
+
+    def set_argument_value(self, expurl, name, value):
+        """
+        Temporarily set the value of an argument in a experiment in the dashboard.
+        The value resets to default value when recomputing the argument.
+
+        :param expurl: Experiment URL identifying the experiment in the dashboard. Example: 'repo:ArgumentsDemo'.
+        :param name: Name of the argument in the experiment.
+        :param value: Object representing the new temporary value of the argument. For ``Scannable`` arguments, this parameter
+            should be a ``ScanObject``. The type of the ``ScanObject`` will be set as the selected type when this function is called. 
+        """
+        raise NotImplementedError
+
+
+class AppletRequestIPC(_AppletRequestInterface):
+    def __init__(self, ipc):
+        self.ipc = ipc
+
+    def set_dataset(self, key, value, unit=None, scale=None, precision=None, persist=None):
+        metadata = {}
+        if unit is not None:
+            metadata["unit"] = unit
+        if scale is not None:
+            metadata["scale"] = scale
+        if precision is not None:
+            metadata["precision"] = precision
+        self.ipc.set_dataset(key, value, metadata, persist)
+
+    def mutate_dataset(self, key, index, value):
+        mod = {"action": "setitem", "path": [key, 1], "key": index, "value": value}
+        self.ipc.update_dataset(mod)
+
+    def append_to_dataset(self, key, value):
+        mod = {"action": "append", "path": [key, 1], "x": value}
+        self.ipc.update_dataset(mod)
+
+    def set_argument_value(self, expurl, name, value):
+        if isinstance(value, ScanObject):
+            value = value.describe()
+        self.ipc.set_argument_value(expurl, name, value)
+
+
+class AppletRequestRPC(_AppletRequestInterface):
+    def __init__(self, loop, dataset_ctl):
+        self.loop = loop
+        self.dataset_ctl = dataset_ctl
+        self.background_tasks = set()
+
+    def _background(self, coro, *args, **kwargs):
+        task = self.loop.create_task(coro(*args, **kwargs))
+        self.background_tasks.add(task)
+        task.add_done_callback(self.background_tasks.discard)
+
+    def set_dataset(self, key, value, unit=None, scale=None, precision=None, persist=None):
+        metadata = {}
+        if unit is not None:
+            metadata["unit"] = unit
+        if scale is not None:
+            metadata["scale"] = scale
+        if precision is not None:
+            metadata["precision"] = precision
+        self._background(self.dataset_ctl.set, key, value, metadata=metadata, persist=persist)
+
+    def mutate_dataset(self, key, index, value):
+        mod = {"action": "setitem", "path": [key, 1], "key": index, "value": value}
+        self._background(self.dataset_ctl.update, mod)
+
+    def append_to_dataset(self, key, value):
+        mod = {"action": "append", "path": [key, 1], "x": value}
+        self._background(self.dataset_ctl.update, mod)
+
+
 class AppletIPCClient(AsyncioChildComm):
     def set_close_cb(self, close_cb):
         self.close_cb = close_cb
@@ -65,12 +163,30 @@ class AppletIPCClient(AsyncioChildComm):
                              exc_info=True)
                 self.close_cb()
 
-    def subscribe(self, datasets, init_cb, mod_cb):
+    def subscribe(self, datasets, init_cb, mod_cb, dataset_prefixes=[], *, loop):
         self.write_pyon({"action": "subscribe",
-                         "datasets": datasets})
+                         "datasets": datasets,
+                         "dataset_prefixes": dataset_prefixes})
         self.init_cb = init_cb
         self.mod_cb = mod_cb
-        asyncio.ensure_future(self.listen())
+        self.listen_task = loop.create_task(self.listen())
+
+    def set_dataset(self, key, value, metadata, persist=None):
+        self.write_pyon({"action": "set_dataset",
+                         "key": key,
+                         "value": value,
+                         "metadata": metadata,
+                         "persist": persist})
+
+    def update_dataset(self, mod):
+        self.write_pyon({"action": "update_dataset",
+                         "mod": mod})
+
+    def set_argument_value(self, expurl, name, value):
+        self.write_pyon({"action": "set_argument_value",
+                         "expurl": expurl,
+                         "name": name,
+                         "value": value})
 
 
 class SimpleApplet:
@@ -92,8 +208,11 @@ class SimpleApplet:
                  "for dataset notifications "
                  "(ignored in embedded mode)")
         group.add_argument(
-            "--port", default=3250, type=int,
+            "--port-notify", default=3250, type=int,
-            help="TCP port to connect to")
+            help="TCP port to connect to for notifications (ignored in embedded mode)")
+        group.add_argument(
+            "--port-control", default=3251, type=int,
+            help="TCP port to connect to for control (ignored in embedded mode)")
 
         self._arggroup_datasets = self.argparser.add_argument_group("datasets")
 
@@ -114,6 +233,9 @@ class SimpleApplet:
         self.embed = os.getenv("ARTIQ_APPLET_EMBED")
         self.datasets = {getattr(self.args, arg.replace("-", "_"))
                          for arg in self.dataset_args}
+        # Optional prefixes (dataset sub-trees) to match subscriptions against;
+        # currently only used by out-of-tree subclasses (ndscan).
+        self.dataset_prefixes = []
 
     def qasync_init(self):
         app = QtWidgets.QApplication([])
@@ -129,8 +251,21 @@ class SimpleApplet:
         if self.embed is not None:
             self.ipc.close()
 
+    def req_init(self):
+        if self.embed is None:
+            dataset_ctl = RPCClient()
+            self.loop.run_until_complete(dataset_ctl.connect_rpc(
+                self.args.server, self.args.port_control, "master_dataset_db"))
+            self.req = AppletRequestRPC(self.loop, dataset_ctl)
+        else:
+            self.req = AppletRequestIPC(self.ipc)
+
+    def req_close(self):
+        if self.embed is None:
+            self.req.dataset_ctl.close_rpc()
+
     def create_main_widget(self):
-        self.main_widget = self.main_widget_class(self.args)
+        self.main_widget = self.main_widget_class(self.args, self.req)
         if self.embed is not None:
             self.ipc.set_close_cb(self.main_widget.close)
             if os.name == "nt":
@@ -163,6 +298,14 @@ class SimpleApplet:
         self.data = data
         return data
 
+    def is_dataset_subscribed(self, key):
+        if key in self.datasets:
+            return True
+        for prefix in self.dataset_prefixes:
+            if key.startswith(prefix):
+                return True
+        return False
+
     def filter_mod(self, mod):
         if self.embed is not None:
             # the parent already filters for us
@@ -171,14 +314,19 @@ class SimpleApplet:
         if mod["action"] == "init":
             return True
         if mod["path"]:
-            return mod["path"][0] in self.datasets
+            return self.is_dataset_subscribed(mod["path"][0])
         elif mod["action"] in {"setitem", "delitem"}:
-            return mod["key"] in self.datasets
+            return self.is_dataset_subscribed(mod["key"])
         else:
             return False
 
     def emit_data_changed(self, data, mod_buffer):
-        self.main_widget.data_changed(data, mod_buffer)
+        persist = dict()
+        value = dict()
+        metadata = dict()
+        for k, d in data.items():
+            persist[k], value[k], metadata[k] = d
+        self.main_widget.data_changed(value, metadata, persist, mod_buffer)
 
     def flush_mod_buffer(self):
         self.emit_data_changed(self.data, self.mod_buffer)
@@ -193,7 +341,7 @@ class SimpleApplet:
                 self.mod_buffer.append(mod)
             else:
                 self.mod_buffer = [mod]
-                asyncio.get_event_loop().call_later(self.args.update_delay,
+                self.loop.call_later(self.args.update_delay,
                                      self.flush_mod_buffer)
         else:
             self.emit_data_changed(self.data, [mod])
@@ -203,9 +351,11 @@ class SimpleApplet:
             self.subscriber = Subscriber("datasets",
                                          self.sub_init, self.sub_mod)
             self.loop.run_until_complete(self.subscriber.connect(
-                self.args.server, self.args.port))
+                self.args.server, self.args.port_notify))
         else:
-            self.ipc.subscribe(self.datasets, self.sub_init, self.sub_mod)
+            self.ipc.subscribe(self.datasets, self.sub_init, self.sub_mod,
+                               dataset_prefixes=self.dataset_prefixes,
+                               loop=self.loop)
 
     def unsubscribe(self):
         if self.embed is None:
@@ -216,6 +366,8 @@ class SimpleApplet:
         self.qasync_init()
         try:
             self.ipc_init()
+            try:
+                self.req_init()
                 try:
                     self.create_main_widget()
                     self.subscribe()
@@ -223,6 +375,8 @@ class SimpleApplet:
                         self.loop.run_forever()
                     finally:
                         self.unsubscribe()
+                finally:
+                    self.req_close()
             finally:
                 self.ipc_close()
         finally:
@@ -252,7 +406,7 @@ class TitleApplet(SimpleApplet):
 
     def emit_data_changed(self, data, mod_buffer):
         if self.args.title is not None:
-            title_values = {k.replace(".", "/"): data.get(k, empty_dataset())["value"]
+            title_values = {k.replace(".", "/"): data.get(k, (False, None))[1]
                             for k in self.dataset_title}
             try:
                 title = self.args.title.format(**title_values)
@@ -261,4 +415,9 @@ class TitleApplet(SimpleApplet):
                 title = self.args.title
         else:
             title = None
-        self.main_widget.data_changed(data, mod_buffer, title)
+        persist = dict()
+        value = dict()
+        metadata = dict()
+        for k, d in data.items():
+            persist[k], value[k], metadata[k] = d
+        self.main_widget.data_changed(value, metadata, persist, mod_buffer, title)

artiq/browser/datasets.py

@@ -20,11 +20,46 @@ class Model(DictSyncTreeSepModel):
         DictSyncTreeSepModel.__init__(self, ".", ["Dataset", "Value"], init)
 
     def convert(self, k, v, column):
-        return short_format(v[1])
+        return short_format(v[1], v[2])
+
+
+class DatasetCtl:
+    def __init__(self, master_host, master_port):
+        self.master_host = master_host
+        self.master_port = master_port
+
+    async def _execute_rpc(self, op_name, key_or_mod, value=None, persist=None, metadata=None):
+        logger.info("Starting %s operation on %s", op_name, key_or_mod)
+        try:
+            remote = RPCClient()
+            await remote.connect_rpc(self.master_host, self.master_port,
+                                     "master_dataset_db")
+            try:
+                if op_name == "set":
+                    await remote.set(key_or_mod, value, persist, metadata)
+                elif op_name == "update":
+                    await remote.update(key_or_mod)
+                else:
+                    logger.error("Invalid operation: %s", op_name)
+                    return
+            finally:
+                remote.close_rpc()
+        except:
+            logger.error("Failed %s operation on %s", op_name,
+                        key_or_mod, exc_info=True)
+        else:
+            logger.info("Finished %s operation on %s", op_name,
+                     key_or_mod)
+
+    async def set(self, key, value, persist=None, metadata=None):
+        await self._execute_rpc("set", key, value, persist, metadata)
+
+    async def update(self, mod):
+        await self._execute_rpc("update", mod)
 
 
 class DatasetsDock(QtWidgets.QDockWidget):
-    def __init__(self, datasets_sub, master_host, master_port):
+    def __init__(self, dataset_sub, dataset_ctl):
         QtWidgets.QDockWidget.__init__(self, "Datasets")
         self.setObjectName("Datasets")
         self.setFeatures(QtWidgets.QDockWidget.DockWidgetMovable |
@@ -62,10 +97,9 @@ class DatasetsDock(QtWidgets.QDockWidget):
         self.table.addAction(upload_action)
 
         self.set_model(Model(dict()))
-        datasets_sub.add_setmodel_callback(self.set_model)
+        dataset_sub.add_setmodel_callback(self.set_model)
 
-        self.master_host = master_host
+        self.dataset_ctl = dataset_ctl
-        self.master_port = master_port
 
     def _search_datasets(self):
         if hasattr(self, "table_model_filter"):
@@ -82,30 +116,14 @@ class DatasetsDock(QtWidgets.QDockWidget):
         self.table_model_filter.setSourceModel(self.table_model)
         self.table.setModel(self.table_model_filter)
 
-    async def _upload_dataset(self, name, value,):
-        logger.info("Uploading dataset '%s' to master...", name)
-        try:
-            remote = RPCClient()
-            await remote.connect_rpc(self.master_host, self.master_port,
-                                     "master_dataset_db")
-            try:
-                await remote.set(name, value)
-            finally:
-                remote.close_rpc()
-        except:
-            logger.error("Failed uploading dataset '%s'",
-                         name, exc_info=True)
-        else:
-            logger.info("Finished uploading dataset '%s'", name)
-
     def upload_clicked(self):
         idx = self.table.selectedIndexes()
         if idx:
             idx = self.table_model_filter.mapToSource(idx[0])
             key = self.table_model.index_to_key(idx)
             if key is not None:
-                dataset = self.table_model.backing_store[key]
+                persist, value, metadata = self.table_model.backing_store[key]
-                asyncio.ensure_future(self._upload_dataset(key, dataset["value"]))
+                asyncio.ensure_future(self.dataset_ctl.set(key, value, metadata=metadata))
 
     def save_state(self):
         return bytes(self.table.header().saveState())

artiq/browser/experiments.py

@@ -10,22 +10,14 @@ import h5py
 from sipyco import pyon
 
 from artiq import __artiq_dir__ as artiq_dir
-from artiq.gui.tools import LayoutWidget, log_level_to_name, get_open_file_name
+from artiq.gui.tools import (LayoutWidget, WheelFilter, 
+                             log_level_to_name, get_open_file_name)
 from artiq.gui.entries import procdesc_to_entry
 from artiq.master.worker import Worker, log_worker_exception
 
 logger = logging.getLogger(__name__)
 
 
-class _WheelFilter(QtCore.QObject):
-    def eventFilter(self, obj, event):
-        if (event.type() == QtCore.QEvent.Wheel and
-                event.modifiers() != QtCore.Qt.NoModifier):
-            event.ignore()
-            return True
-        return False
-
-
 class _ArgumentEditor(QtWidgets.QTreeWidget):
     def __init__(self, dock):
         QtWidgets.QTreeWidget.__init__(self)
@@ -46,7 +38,7 @@ class _ArgumentEditor(QtWidgets.QTreeWidget):
         self.setStyleSheet("QTreeWidget {background: " +
                            self.palette().midlight().color().name() + " ;}")
 
-        self.viewport().installEventFilter(_WheelFilter(self.viewport()))
+        self.viewport().installEventFilter(WheelFilter(self.viewport(), True))
 
         self._groups = dict()
         self._arg_to_widgets = dict()
@@ -378,9 +370,9 @@ class _ExperimentDock(QtWidgets.QMdiSubWindow):
 
 
 class LocalDatasetDB:
-    def __init__(self, datasets_sub):
+    def __init__(self, dataset_sub):
-        self.datasets_sub = datasets_sub
+        self.dataset_sub = dataset_sub
-        datasets_sub.add_setmodel_callback(self.init)
+        dataset_sub.add_setmodel_callback(self.init)
 
     def init(self, data):
         self._data = data
@@ -389,11 +381,11 @@ class LocalDatasetDB:
         return self._data.backing_store[key][1]
 
     def update(self, mod):
-        self.datasets_sub.update(mod)
+        self.dataset_sub.update(mod)
 
 
 class ExperimentsArea(QtWidgets.QMdiArea):
-    def __init__(self, root, datasets_sub):
+    def __init__(self, root, dataset_sub):
         QtWidgets.QMdiArea.__init__(self)
         self.pixmap = QtGui.QPixmap(os.path.join(
             artiq_dir, "gui", "logo_ver.svg"))
@@ -402,11 +394,11 @@ class ExperimentsArea(QtWidgets.QMdiArea):
 
         self.open_experiments = []
 
-        self._ddb = LocalDatasetDB(datasets_sub)
+        self._ddb = LocalDatasetDB(dataset_sub)
 
         self.worker_handlers = {
             "get_device_db": lambda: {},
-            "get_device": lambda k: {"type": "dummy"},
+            "get_device": lambda key, resolve_alias=False: {"type": "dummy"},
             "get_dataset": self._ddb.get,
             "update_dataset": self._ddb.update,
         }
@@ -516,5 +508,9 @@ class ExperimentsArea(QtWidgets.QMdiArea):
         self.open_experiments.append(dock)
         return dock
 
+    def set_argument_value(self, expurl, name, value):
+        logger.warning("Unable to set argument '%s', dropping change. "
+                       "'set_argument_value' not supported in browser.", name)
+
     def on_dock_closed(self, dock):
         self.open_experiments.remove(dock)

artiq/browser/files.py

@@ -71,7 +71,7 @@ class ZoomIconView(QtWidgets.QListView):
         self._char_width = QtGui.QFontMetrics(self.font()).averageCharWidth()
         self.setViewMode(self.IconMode)
         w = self._char_width*self.default_size
-        self.setIconSize(QtCore.QSize(w, w*self.aspect))
+        self.setIconSize(QtCore.QSize(w, int(w*self.aspect)))
         self.setFlow(self.LeftToRight)
         self.setResizeMode(self.Adjust)
         self.setWrapping(True)
@@ -102,13 +102,14 @@ class Hdf5FileSystemModel(QtWidgets.QFileSystemModel):
             h5 = open_h5(info)
             if h5 is not None:
                 try:
-                    expid = pyon.decode(h5["expid"][()])
+                    expid = pyon.decode(h5["expid"][()]) if "expid" in h5 else dict()
-                    start_time = datetime.fromtimestamp(h5["start_time"][()])
+                    start_time = datetime.fromtimestamp(h5["start_time"][()]) if "start_time" in h5 else "<none>"
                     v = ("artiq_version: {}\nrepo_rev: {}\nfile: {}\n"
                          "class_name: {}\nrid: {}\nstart_time: {}").format(
-                             h5["artiq_version"][()], expid["repo_rev"],
+                             h5["artiq_version"].asstr()[()] if "artiq_version" in h5 else "<none>",
-                             expid["file"], expid["class_name"],
+                             expid.get("repo_rev", "<none>"),
-                             h5["rid"][()], start_time)
+                             expid.get("file", "<none>"), expid.get("class_name", "<none>"),
+                             h5["rid"][()] if "rid" in h5 else "<none>", start_time)
                     return v
                 except:
                     logger.warning("unable to read metadata from %s",
@@ -174,31 +175,45 @@ class FilesDock(QtWidgets.QDockWidget):
         logger.debug("loading datasets from %s", info.filePath())
         with f:
             try:
-                expid = pyon.decode(f["expid"][()])
+                expid = pyon.decode(f["expid"][()]) if "expid" in f else dict()
-                start_time = datetime.fromtimestamp(f["start_time"][()])
+                start_time = datetime.fromtimestamp(f["start_time"][()]) if "start_time" in f else "<none>"
                 v = {
-                    "artiq_version": f["artiq_version"][()],
+                    "artiq_version": f["artiq_version"].asstr()[()] if "artiq_version" in f else "<none>",
-                    "repo_rev": expid["repo_rev"],
+                    "repo_rev": expid.get("repo_rev", "<none>"),
-                    "file": expid["file"],
+                    "file": expid.get("file", "<none>"),
-                    "class_name": expid["class_name"],
+                    "class_name": expid.get("class_name", "<none>"),
-                    "rid": f["rid"][()],
+                    "rid": f["rid"][()] if "rid" in f else "<none>",
                     "start_time": start_time,
                 }
                 self.metadata_changed.emit(v)
             except:
                 logger.warning("unable to read metadata from %s",
                                info.filePath(), exc_info=True)
-            rd = dict()
+
+            rd = {}
             if "archive" in f:
-                rd = {k: (True, v[()]) for k, v in f["archive"].items()}
+                def visitor(k, v):
+                    if isinstance(v, h5py.Dataset):
+                        # v.attrs is a non-serializable h5py.AttributeManager, need to convert to dict
+                        # See https://docs.h5py.org/en/stable/high/attr.html#h5py.AttributeManager
+                        rd[k] = (True, v[()], dict(v.attrs))
+
+                f["archive"].visititems(visitor)
+
             if "datasets" in f:
-                for k, v in f["datasets"].items():
+                def visitor(k, v):
+                    if isinstance(v, h5py.Dataset):
                         if k in rd:
-                        logger.warning("dataset '%s' is both in archive and "
+                            logger.warning("dataset '%s' is both in archive "
-                                       "outputs", k)
+                                           "and outputs", k)
-                    rd[k] = (True, v[()])
+                        # v.attrs is a non-serializable h5py.AttributeManager, need to convert to dict
-            if rd:
+                        # See https://docs.h5py.org/en/stable/high/attr.html#h5py.AttributeManager
+                        rd[k] = (True, v[()], dict(v.attrs))
+
+                f["datasets"].visititems(visitor)
+
             self.datasets.init(rd)
+
         self.dataset_changed.emit(info.filePath())
 
     def list_activated(self, idx):

artiq/build_soc.py

@@ -59,7 +59,6 @@ def build_artiq_soc(soc, argdict):
     builder.software_packages = []
     builder.add_software_package("bootloader", os.path.join(firmware_dir, "bootloader"))
     is_kasli_v1 = isinstance(soc.platform, kasli.Platform) and soc.platform.hw_rev in ("v1.0", "v1.1")
-    if isinstance(soc, AMPSoC):
     kernel_cpu_type = "vexriscv" if is_kasli_v1 else "vexriscv-g"
     builder.add_software_package("libm", cpu_type=kernel_cpu_type)
     builder.add_software_package("libprintf", cpu_type=kernel_cpu_type)
@@ -69,9 +68,9 @@ def build_artiq_soc(soc, argdict):
     # If the kernel lacks FPU, then the runtime unwinder is already generated
     if not is_kasli_v1:
         builder.add_software_package("libunwind")
+    if not soc.config["DRTIO_ROLE"] == "satellite":
         builder.add_software_package("runtime", os.path.join(firmware_dir, "runtime"))
     else:
-        # Assume DRTIO satellite.
         builder.add_software_package("satman", os.path.join(firmware_dir, "satman"))
     try:
         builder.build()

artiq/compiler/asttyped.py

@@ -21,13 +21,19 @@ class scoped(object):
         set of variables resolved as globals
     """
 
+class remote(object):
+    """
+    :ivar remote_fn: (bool) whether function is ran on a remote device,
+        meaning arguments are received remotely and return is sent remotely
+    """
+
 # Typed versions of untyped nodes
 class argT(ast.arg, commontyped):
     pass
 
 class ClassDefT(ast.ClassDef):
     _types = ("constructor_type",)
-class FunctionDefT(ast.FunctionDef, scoped):
+class FunctionDefT(ast.FunctionDef, scoped, remote):
     _types = ("signature_type",)
 class QuotedFunctionDefT(FunctionDefT):
     """
@@ -58,7 +64,7 @@ class BinOpT(ast.BinOp, commontyped):
     pass
 class BoolOpT(ast.BoolOp, commontyped):
     pass
-class CallT(ast.Call, commontyped):
+class CallT(ast.Call, commontyped, remote):
     """
     :ivar iodelay: (:class:`iodelay.Expr`)
     :ivar arg_exprs: (dict of str to :class:`iodelay.Expr`)

artiq/compiler/builtins.py

@@ -38,6 +38,9 @@ class TInt(types.TMono):
     def one():
         return 1
 
+def TInt8():
+    return TInt(types.TValue(8))
+
 def TInt32():
     return TInt(types.TValue(32))
 
@@ -123,18 +126,23 @@ class TException(types.TMono):
     #  * File, line and column where it was raised (str, int, int).
     #  * Message, which can contain substitutions {0}, {1} and {2} (str).
     #  * Three 64-bit integers, parameterizing the message (numpy.int64).
+    # These attributes are prefixed with `#` so that users cannot access them,
+    # and we don't have to do string allocation in the runtime.
+    # #__name__ is now a string key in the host. TStr may not be an actual
+    # CSlice in the runtime, they might be a CSlice with length = i32::MAX and
+    # ptr = string key in the host.
 
     # Keep this in sync with the function ARTIQIRGenerator.alloc_exn.
     attributes = OrderedDict([
-        ("__name__",    TStr()),
+        ("#__name__",    TInt32()),
-        ("__file__",    TStr()),
+        ("#__file__",    TStr()),
-        ("__line__",    TInt32()),
+        ("#__line__",    TInt32()),
-        ("__col__",     TInt32()),
+        ("#__col__",     TInt32()),
-        ("__func__",    TStr()),
+        ("#__func__",    TStr()),
-        ("__message__", TStr()),
+        ("#__message__", TStr()),
-        ("__param0__",  TInt64()),
+        ("#__param0__",  TInt64()),
-        ("__param1__",  TInt64()),
+        ("#__param1__",  TInt64()),
-        ("__param2__",  TInt64()),
+        ("#__param2__",  TInt64()),
     ])
 
     def __init__(self, name="Exception", id=0):
@@ -169,7 +177,9 @@ def fn_list():
     return types.TConstructor(TList())
 
 def fn_array():
-    return types.TConstructor(TArray())
+    # numpy.array() is actually a "magic" macro that is expanded in-place, but
+    # just as for builtin functions, we do not want to quote it, etc.
+    return types.TBuiltinFunction("array")
 
 def fn_Exception():
     return types.TExceptionConstructor(TException("Exception"))
@@ -237,6 +247,12 @@ def fn_at_mu():
 def fn_rtio_log():
     return types.TBuiltinFunction("rtio_log")
 
+def fn_subkernel_await():
+    return types.TBuiltinFunction("subkernel_await")
+
+def fn_subkernel_preload():
+    return types.TBuiltinFunction("subkernel_preload")
+
 # Accessors
 
 def is_none(typ):
@@ -319,7 +335,7 @@ def get_iterable_elt(typ):
     # n-dimensional arrays, rather than the n-1 dimensional result of iterating over
     # the first axis, which makes the name a bit misleading.
     if is_str(typ) or is_bytes(typ) or is_bytearray(typ):
-        return TInt(types.TValue(8))
+        return TInt8()
     elif types._is_pointer(typ) or is_iterable(typ):
         return typ.find()["elt"].find()
     else:
@@ -335,5 +351,5 @@ def is_allocated(typ):
                   is_float(typ) or is_range(typ) or
                   types._is_pointer(typ) or types.is_function(typ) or
                   types.is_external_function(typ) or types.is_rpc(typ) or
-                  types.is_method(typ) or types.is_tuple(typ) or
+                  types.is_subkernel(typ) or types.is_method(typ) or
-                  types.is_value(typ))
+                  types.is_tuple(typ) or types.is_value(typ))

artiq/compiler/embedding.py

@@ -5,6 +5,7 @@ the references to the host objects and translates the functions
 annotated as ``@kernel`` when they are referenced.
 """
 
+import typing
 import os, re, linecache, inspect, textwrap, types as pytypes, numpy
 from collections import OrderedDict, defaultdict
 
@@ -18,6 +19,13 @@ from . import types, builtins, asttyped, math_fns, prelude
 from .transforms import ASTTypedRewriter, Inferencer, IntMonomorphizer, TypedtreePrinter
 from .transforms.asttyped_rewriter import LocalExtractor
 
+try:
+    # From numpy=1.25.0 dispatching for `__array_function__` is done via
+    # a C wrapper: https://github.com/numpy/numpy/pull/23020
+    from numpy.core._multiarray_umath import _ArrayFunctionDispatcher
+except ImportError:
+    _ArrayFunctionDispatcher = None    
+
 
 class SpecializedFunction:
     def __init__(self, instance_type, host_function):
@@ -45,8 +53,48 @@ class EmbeddingMap:
         self.object_forward_map = {}
         self.object_reverse_map = {}
         self.module_map = {}
+
+        # type_map connects the host Python `type` to the pair of associated
+        # `(TInstance, TConstructor)`s. The `used_…_names` sets cache the
+        # respective `.name`s for O(1) collision avoidance.
         self.type_map = {}
+        self.used_instance_type_names = set()
+        self.used_constructor_type_names = set()
+
         self.function_map = {}
+        self.str_forward_map = {}
+        self.str_reverse_map = {}
+
+        self.preallocate_runtime_exception_names(["RuntimeError",
+                                                  "RTIOUnderflow",
+                                                  "RTIOOverflow",
+                                                  "RTIODestinationUnreachable",
+                                                  "DMAError",
+                                                  "I2CError",
+                                                  "CacheError",
+                                                  "SPIError",
+                                                  "0:ZeroDivisionError",
+                                                  "0:IndexError",
+                                                  "UnwrapNoneError",
+                                                  "SubkernelError"])
+
+    def preallocate_runtime_exception_names(self, names):
+        for i, name in enumerate(names):
+            if ":" not in name:
+                name = "0:artiq.coredevice.exceptions." + name
+            exn_id = self.store_str(name)
+            assert exn_id == i
+
+    def store_str(self, s):
+        if s in self.str_forward_map:
+            return self.str_forward_map[s]
+        str_id = len(self.str_forward_map)
+        self.str_forward_map[s] = str_id
+        self.str_reverse_map[str_id] = s
+        return str_id
+
+    def retrieve_str(self, str_id):
+        return self.str_reverse_map[str_id]
 
     # Modules
     def store_module(self, module, module_type):
@@ -60,16 +108,6 @@ class EmbeddingMap:
 
     # Types
     def store_type(self, host_type, instance_type, constructor_type):
-        self._rename_type(instance_type)
-        self.type_map[host_type] = (instance_type, constructor_type)
-
-    def retrieve_type(self, host_type):
-        return self.type_map[host_type]
-
-    def has_type(self, host_type):
-        return host_type in self.type_map
-
-    def _rename_type(self, new_instance_type):
         # Generally, user-defined types that have exact same name (which is to say, classes
         # defined inside functions) do not pose a problem to the compiler. The two places which
         # cannot handle this are:
@@ -78,12 +116,29 @@ class EmbeddingMap:
         # Since handling #2 requires renaming on ARTIQ side anyway, it's more straightforward
         # to do it once when embedding (since non-embedded code cannot define classes in
         # functions). Also, easier to debug.
-        n = 0
+        suffix = 0
-        for host_type in self.type_map:
+        new_instance_name = instance_type.name
-            instance_type, constructor_type = self.type_map[host_type]
+        new_constructor_name = constructor_type.name
-            if instance_type.name == new_instance_type.name:
+        while True:
-                n += 1
+            if (new_instance_name not in self.used_instance_type_names
-                new_instance_type.name = "{}.{}".format(new_instance_type.name, n)
+                    and new_constructor_name not in self.used_constructor_type_names):
+                break
+            suffix += 1
+            new_instance_name = f"{instance_type.name}.{suffix}"
+            new_constructor_name = f"{constructor_type.name}.{suffix}"
+
+        self.used_instance_type_names.add(new_instance_name)
+        instance_type.name = new_instance_name
+        self.used_constructor_type_names.add(new_constructor_name)
+        constructor_type.name = new_constructor_name
+
+        self.type_map[host_type] = (instance_type, constructor_type)
+
+    def retrieve_type(self, host_type):
+        return self.type_map[host_type]
+
+    def has_type(self, host_type):
+        return host_type in self.type_map
 
     def attribute_count(self):
         count = 0
@@ -130,7 +185,22 @@ class EmbeddingMap:
                 obj_typ, _ = self.type_map[type(obj_ref)]
             yield obj_id, obj_ref, obj_typ
 
+    def subkernels(self):
+        subkernels = {}
+        for k, v in self.object_forward_map.items():
+            if hasattr(v, "artiq_embedded"):
+                if v.artiq_embedded.destination is not None:
+                    subkernels[k] = v
+        return subkernels
+
     def has_rpc(self):
+        return any(filter(
+                lambda x: (inspect.isfunction(x) or inspect.ismethod(x)) and \
+                    (not hasattr(x, "artiq_embedded") or x.artiq_embedded.destination is None),
+                self.object_forward_map.values()
+            ))
+
+    def has_rpc_or_subkernel(self):
         return any(filter(lambda x: inspect.isfunction(x) or inspect.ismethod(x),
                           self.object_forward_map.values()))
 
@@ -138,6 +208,7 @@ class EmbeddingMap:
 class ASTSynthesizer:
     def __init__(self, embedding_map, value_map, quote_function=None, expanded_from=None):
         self.source = ""
+        self.source_last_new_line = 0
         self.source_buffer = source.Buffer(self.source, "<synthesized>")
         self.embedding_map = embedding_map
         self.value_map = value_map
@@ -156,6 +227,14 @@ class ASTSynthesizer:
         return source.Range(self.source_buffer, range_from, range_to,
                             expanded_from=self.expanded_from)
 
+    def _add_iterable(self, fragment):
+        # Since DILocation points on the beginning of the piece of source
+        # we don't care if the fragment's end will overflow LLVM's limit.
+        if len(self.source) - self.source_last_new_line >= 2**16:
+            fragment = "\\\n" + fragment
+            self.source_last_new_line = len(self.source) + 2
+        return self._add(fragment)
+
     def fast_quote_list(self, value):
         elts = [None] * len(value)
         is_T = False
@@ -214,7 +293,7 @@ class ASTSynthesizer:
             for index, elt in enumerate(value):
                 elts[index] = self.quote(elt)
                 if index < len(value) - 1:
-                    self._add(", ")
+                    self._add_iterable(", ")
         return elts
 
     def quote(self, value):
@@ -265,28 +344,28 @@ class ASTSynthesizer:
                                  loc=self._add(repr(value)))
         elif isinstance(value, str):
             return asttyped.StrT(s=value, ctx=None, type=builtins.TStr(),
-                                 loc=self._add(repr(value)))
+                                 loc=self._add_iterable(repr(value)))
         elif isinstance(value, bytes):
             return asttyped.StrT(s=value, ctx=None, type=builtins.TBytes(),
-                                 loc=self._add(repr(value)))
+                                 loc=self._add_iterable(repr(value)))
         elif isinstance(value, bytearray):
-            quote_loc   = self._add('`')
+            quote_loc   = self._add_iterable('`')
-            repr_loc    = self._add(repr(value))
+            repr_loc    = self._add_iterable(repr(value))
-            unquote_loc = self._add('`')
+            unquote_loc = self._add_iterable('`')
             loc         = quote_loc.join(unquote_loc)
 
             return asttyped.QuoteT(value=value, type=builtins.TByteArray(), loc=loc)
         elif isinstance(value, list):
-            begin_loc = self._add("[")
+            begin_loc = self._add_iterable("[")
             elts = self.fast_quote_list(value)
-            end_loc   = self._add("]")
+            end_loc   = self._add_iterable("]")
             return asttyped.ListT(elts=elts, ctx=None, type=builtins.TList(),
                                   begin_loc=begin_loc, end_loc=end_loc,
                                   loc=begin_loc.join(end_loc))
         elif isinstance(value, tuple):
-            begin_loc = self._add("(")
+            begin_loc = self._add_iterable("(")
             elts = self.fast_quote_list(value)
-            end_loc   = self._add(")")
+            end_loc   = self._add_iterable(")")
             return asttyped.TupleT(elts=elts, ctx=None,
                                    type=types.TTuple([e.type for e in elts]),
                                    begin_loc=begin_loc, end_loc=end_loc,
@@ -296,7 +375,9 @@ class ASTSynthesizer:
         elif inspect.isfunction(value) or inspect.ismethod(value) or \
                 isinstance(value, pytypes.BuiltinFunctionType) or \
                 isinstance(value, SpecializedFunction) or \
-                isinstance(value, numpy.ufunc):
+                isinstance(value, numpy.ufunc) or \
+                (isinstance(value, _ArrayFunctionDispatcher) if 
+                            _ArrayFunctionDispatcher is not None else False):
             if inspect.ismethod(value):
                 quoted_self   = self.quote(value.__self__)
                 function_type = self.quote_function(value.__func__, self.expanded_from)
@@ -405,7 +486,7 @@ class ASTSynthesizer:
                 return asttyped.QuoteT(value=value, type=instance_type,
                                        loc=loc)
 
-    def call(self, callee, args, kwargs, callback=None):
+    def call(self, callee, args, kwargs, callback=None, remote_fn=False):
         """
         Construct an AST fragment calling a function specified by
         an AST node `function_node`, with given arguments.
@@ -449,7 +530,7 @@ class ASTSynthesizer:
             starargs=None, kwargs=None,
             type=types.TVar(), iodelay=None, arg_exprs={},
             begin_loc=begin_loc, end_loc=end_loc, star_loc=None, dstar_loc=None,
-            loc=callee_node.loc.join(end_loc))
+            loc=callee_node.loc.join(end_loc), remote_fn=remote_fn)
 
         if callback is not None:
             node = asttyped.CallT(
@@ -484,7 +565,7 @@ class StitchingASTTypedRewriter(ASTTypedRewriter):
                              arg=node.arg, annotation=None,
                              arg_loc=node.arg_loc, colon_loc=node.colon_loc, loc=node.loc)
 
-    def visit_quoted_function(self, node, function):
+    def visit_quoted_function(self, node, function, remote_fn):
         extractor = LocalExtractor(env_stack=self.env_stack, engine=self.engine)
         extractor.visit(node)
 
@@ -501,11 +582,11 @@ class StitchingASTTypedRewriter(ASTTypedRewriter):
         node = asttyped.QuotedFunctionDefT(
             typing_env=extractor.typing_env, globals_in_scope=extractor.global_,
             signature_type=types.TVar(), return_type=types.TVar(),
-            name=node.name, args=node.args, returns=node.returns,
+            name=node.name, args=node.args, returns=None,
             body=node.body, decorator_list=node.decorator_list,
             keyword_loc=node.keyword_loc, name_loc=node.name_loc,
             arrow_loc=node.arrow_loc, colon_loc=node.colon_loc, at_locs=node.at_locs,
-            loc=node.loc)
+            loc=node.loc, remote_fn=remote_fn)
 
         try:
             self.env_stack.append(node.typing_env)
@@ -713,7 +794,7 @@ class TypedtreeHasher(algorithm.Visitor):
         return hash(tuple(freeze(getattr(node, field_name)) for field_name in fields))
 
 class Stitcher:
-    def __init__(self, core, dmgr, engine=None, print_as_rpc=True):
+    def __init__(self, core, dmgr, engine=None, print_as_rpc=True, destination=0, subkernel_arg_types=[]):
         self.core = core
         self.dmgr = dmgr
         if engine is None:
@@ -739,11 +820,19 @@ class Stitcher:
         self.value_map = defaultdict(lambda: [])
         self.definitely_changed = False
 
+        self.destination = destination
+        self.first_call = True
+        # for non-annotated subkernels: 
+        # main kernel inferencer output with types of arguments
+        self.subkernel_arg_types = subkernel_arg_types
+
     def stitch_call(self, function, args, kwargs, callback=None):
         # We synthesize source code for the initial call so that
         # diagnostics would have something meaningful to display to the user.
         synthesizer = self._synthesizer(self._function_loc(function.artiq_embedded.function))
-        call_node = synthesizer.call(function, args, kwargs, callback)
+        # first call of a subkernel will get its arguments from remote (DRTIO)
+        remote_fn = self.destination != 0
+        call_node = synthesizer.call(function, args, kwargs, callback, remote_fn=remote_fn)
         synthesizer.finalize()
         self.typedtree.append(call_node)
 
@@ -855,6 +944,10 @@ class Stitcher:
                 return [diagnostic.Diagnostic("note",
                     "in kernel function here", {},
                     call_loc)]
+            elif fn_kind == 'subkernel':
+                return [diagnostic.Diagnostic("note",
+                    "in subkernel call here", {},
+                    call_loc)]
             else:
                 assert False
         else:
@@ -874,7 +967,7 @@ class Stitcher:
                 self._function_loc(function),
                 notes=self._call_site_note(loc, fn_kind))
             self.engine.process(diag)
-        elif fn_kind == 'rpc' and param.default is not inspect.Parameter.empty:
+        elif fn_kind == 'rpc' or fn_kind == 'subkernel' and param.default is not inspect.Parameter.empty:
             notes = []
             notes.append(diagnostic.Diagnostic("note",
                 "expanded from here while trying to infer a type for an"
@@ -893,11 +986,18 @@ class Stitcher:
                 Inferencer(engine=self.engine).visit(ast)
                 IntMonomorphizer(engine=self.engine).visit(ast)
                 return ast.type
-        else:
+        elif fn_kind == 'kernel' and self.first_call and self.destination != 0:
+            # subkernels do not have access to the main kernel code to infer
+            # arg types - so these are cached and passed onto subkernel
+            # compilation, to avoid having to annotate them fully
+            for name, typ in self.subkernel_arg_types:
+                if param.name == name:
+                    return typ
+
         # Let the rest of the program decide.
         return types.TVar()
 
-    def _quote_embedded_function(self, function, flags):
+    def _quote_embedded_function(self, function, flags, remote_fn=False):
         # we are now parsing new functions... definitely changed the type
         self.definitely_changed = True
 
@@ -996,7 +1096,7 @@ class Stitcher:
             engine=self.engine, prelude=self.prelude,
             globals=self.globals, host_environment=host_environment,
             quote=self._quote)
-        function_node = asttyped_rewriter.visit_quoted_function(function_node, embedded_function)
+        function_node = asttyped_rewriter.visit_quoted_function(function_node, embedded_function, remote_fn)
         function_node.flags = flags
 
         # Add it into our typedtree so that it gets inferenced and codegen'd.
@@ -1008,9 +1108,6 @@ class Stitcher:
         return function_node
 
     def _extract_annot(self, function, annot, kind, call_loc, fn_kind):
-        if annot is None:
-            annot = builtins.TNone()
-
         if isinstance(function, SpecializedFunction):
             host_function = function.host_function
         else:
@@ -1024,9 +1121,20 @@ class Stitcher:
         if isinstance(embedded_function, str):
             embedded_function = host_function
 
+        return self._to_artiq_type(
+            annot,
+            function=function,
+            kind=kind,
+            eval_in_scope=lambda x: eval(x, embedded_function.__globals__),
+            call_loc=call_loc,
+            fn_kind=fn_kind)
+
+    def _to_artiq_type(
+        self, annot, *, function, kind: str, eval_in_scope, call_loc: str, fn_kind: str
+    ) -> types.Type:
         if isinstance(annot, str):
             try:
-                annot = eval(annot, embedded_function.__globals__)
+                annot = eval_in_scope(annot)
             except Exception:
                 diag = diagnostic.Diagnostic(
                     "error",
@@ -1036,23 +1144,72 @@ class Stitcher:
                     notes=self._call_site_note(call_loc, fn_kind))
                 self.engine.process(diag)
 
-        if not isinstance(annot, types.Type):
+        if isinstance(annot, types.Type):
+            return annot
+
+        # Convert built-in Python types to ARTIQ ones.
+        if annot is None:
+            return builtins.TNone()
+        elif annot is numpy.int64:
+            return builtins.TInt64()
+        elif annot is numpy.int32:
+            return builtins.TInt32()
+        elif annot is float:
+            return builtins.TFloat()
+        elif annot is bool:
+            return builtins.TBool()
+        elif annot is str:
+            return builtins.TStr()
+        elif annot is bytes:
+            return builtins.TBytes()
+        elif annot is bytearray:
+            return builtins.TByteArray()
+
+        # Convert generic Python types to ARTIQ ones.
+        generic_ty = typing.get_origin(annot)
+        if generic_ty is not None:
+            type_args = typing.get_args(annot)
+            artiq_args = [
+                self._to_artiq_type(
+                    x,
+                    function=function,
+                    kind=kind,
+                    eval_in_scope=eval_in_scope,
+                    call_loc=call_loc,
+                    fn_kind=fn_kind)
+                for x in type_args
+            ]
+
+            if generic_ty is list and len(artiq_args) == 1:
+                return builtins.TList(artiq_args[0])
+            elif generic_ty is tuple:
+                return types.TTuple(artiq_args)
+
+        # Otherwise report an unknown type and just use a fresh tyvar.
+
+        if annot is int:
+            message = (
+                "type annotation for {kind}, 'int' cannot be used as an ARTIQ type. "
+                "Use numpy's int32 or int64 instead."
+            )
+            ty = builtins.TInt()
+        else:
+            message = "type annotation for {kind}, '{annot}', is not an ARTIQ type"
+            ty = types.TVar()
+
         diag = diagnostic.Diagnostic("error",
-                "type annotation for {kind}, '{annot}', is not an ARTIQ type",
+            message,
             {"kind": kind, "annot": repr(annot)},
             self._function_loc(function),
             notes=self._call_site_note(call_loc, fn_kind))
         self.engine.process(diag)
 
-            return types.TVar()
+        return ty
-        else:
-            return annot
 
     def _quote_syscall(self, function, loc):
         signature = inspect.signature(function)
 
         arg_types = OrderedDict()
-        optarg_types = OrderedDict()
         for param in signature.parameters.values():
             if param.kind != inspect.Parameter.POSITIONAL_OR_KEYWORD:
                 diag = diagnostic.Diagnostic("error",
@@ -1090,6 +1247,40 @@ class Stitcher:
         self.functions[function] = function_type
         return function_type
 
+    def _quote_subkernel(self, function, loc):
+        if isinstance(function, SpecializedFunction):
+            host_function = function.host_function
+        else:
+            host_function = function
+        ret_type = builtins.TNone()
+        signature = inspect.signature(host_function)
+            
+        if signature.return_annotation is not inspect.Signature.empty:
+            ret_type = self._extract_annot(host_function, signature.return_annotation,
+                                            "return type", loc, fn_kind='subkernel')
+        arg_types = OrderedDict()
+        optarg_types = OrderedDict()
+        for param in signature.parameters.values():
+            if param.kind != inspect.Parameter.POSITIONAL_OR_KEYWORD:
+                diag = diagnostic.Diagnostic("error",
+                    "subkernels must only use positional arguments; '{argument}' isn't",
+                    {"argument": param.name},
+                    self._function_loc(function),
+                    notes=self._call_site_note(loc, fn_kind='subkernel'))
+                self.engine.process(diag)
+
+            arg_type = self._type_of_param(function, loc, param, fn_kind='subkernel')
+            if param.default is inspect.Parameter.empty:
+                arg_types[param.name] = arg_type
+            else:
+                optarg_types[param.name] = arg_type
+
+        function_type = types.TSubkernel(arg_types, optarg_types, ret_type,
+                                   sid=self.embedding_map.store_object(host_function),
+                                   destination=host_function.artiq_embedded.destination)
+        self.functions[function] = function_type
+        return function_type
+
     def _quote_rpc(self, function, loc):
         if isinstance(function, SpecializedFunction):
             host_function = function.host_function
@@ -1149,8 +1340,18 @@ class Stitcher:
                 (host_function.artiq_embedded.core_name is None and
                  host_function.artiq_embedded.portable is False and
                  host_function.artiq_embedded.syscall is None and
+                 host_function.artiq_embedded.destination is None and
                  host_function.artiq_embedded.forbidden is False):
             self._quote_rpc(function, loc)
+        elif host_function.artiq_embedded.destination is not None and \
+            host_function.artiq_embedded.destination != self.destination:
+            # treat subkernels as kernels if running on the same device
+            if not 0 < host_function.artiq_embedded.destination <= 255:
+                diag = diagnostic.Diagnostic("error",
+                    "subkernel destination must be between 1 and 255 (inclusive)", {},
+                    self._function_loc(host_function))
+                self.engine.process(diag)
+            self._quote_subkernel(function, loc)
         elif host_function.artiq_embedded.function is not None:
             if host_function.__name__ == "<lambda>":
                 note = diagnostic.Diagnostic("note",
@@ -1174,8 +1375,13 @@ class Stitcher:
                     notes=[note])
                 self.engine.process(diag)
 
+            destination = host_function.artiq_embedded.destination
+            # remote_fn only for first call in subkernels
+            remote_fn = destination is not None and self.first_call
             self._quote_embedded_function(function,
-                                          flags=host_function.artiq_embedded.flags)
+                                          flags=host_function.artiq_embedded.flags,
+                                          remote_fn=remote_fn)
+            self.first_call = False
         elif host_function.artiq_embedded.syscall is not None:
             # Insert a storage-less global whose type instructs the compiler
             # to perform a system call instead of a regular call.

artiq/compiler/ir.py

@@ -135,6 +135,7 @@ class NamedValue(Value):
     def __init__(self, typ, name):
         super().__init__(typ)
         self.name, self.function = name, None
+        self.is_removed = False
 
     def set_name(self, new_name):
         if self.function is not None:
@@ -235,7 +236,7 @@ class Instruction(User):
         self.drop_references()
         # Check this after drop_references in case this
         # is a self-referencing phi.
-        assert not any(self.uses)
+        assert all(use.is_removed for use in self.uses)
 
     def replace_with(self, value):
         self.replace_all_uses_with(value)
@@ -370,7 +371,7 @@ class BasicBlock(NamedValue):
         self.remove_from_parent()
         # Check this after erasing instructions in case the block
         # loops into itself.
-        assert not any(self.uses)
+        assert all(use.is_removed for use in self.uses)
 
     def prepend(self, insn):
         assert isinstance(insn, Instruction)
@@ -705,6 +706,81 @@ class SetLocal(Instruction):
     def value(self):
         return self.operands[1]
 
+class GetArgFromRemote(Instruction):
+    """
+    An instruction that receives function arguments from remote 
+    (ie. subkernel in DRTIO context)
+
+    :ivar arg_name: (string) argument name
+    :ivar arg_type: argument type
+    """
+
+    """
+    :param arg_name: (string) argument name
+    :param arg_type: argument type
+    """
+    def __init__(self, arg_name, arg_type, name=""):
+        assert isinstance(arg_name, str)
+        super().__init__([], arg_type, name)
+        self.arg_name = arg_name
+        self.arg_type = arg_type
+
+    def copy(self, mapper):
+        self_copy = super().copy(mapper)
+        self_copy.arg_name = self.arg_name
+        self_copy.arg_type = self.arg_type
+        return self_copy
+
+    def opcode(self):
+        return "getargfromremote({})".format(repr(self.arg_name))
+
+class GetOptArgFromRemote(GetArgFromRemote):
+    """
+    An instruction that may or may not retrieve an optional function argument
+    from remote, depending on number of values received by firmware.
+
+    :ivar rcv_count: number of received values,
+                     determined by firmware
+    :ivar index: (integer) index of the current argument, 
+                 in reference to remote arguments
+    """
+
+    """
+    :param rcv_count: number of received valuese
+    :param index: (integer) index of the current argument, 
+                  in reference to remote arguments
+    """
+    def __init__(self, arg_name, arg_type, rcv_count, index, name=""):
+        super().__init__(arg_name, arg_type, name)
+        self.rcv_count = rcv_count
+        self.index = index
+
+    def copy(self, mapper):
+        self_copy = super().copy(mapper)
+        self_copy.rcv_count = self.rcv_count
+        self_copy.index = self.index
+        return self_copy
+
+    def opcode(self):
+        return "getoptargfromremote({})".format(repr(self.arg_name))
+
+class SubkernelAwaitArgs(Instruction):
+    """
+    A builtin instruction that takes min and max received messages as operands,
+    and a list of received types.
+
+    :ivar arg_types: (list of types) types of passed arguments (including optional)
+    """
+
+    """
+    :param arg_types: (list of types) types of passed arguments (including optional)
+    """
+
+    def __init__(self, operands, arg_types, name=None):
+        assert isinstance(arg_types, list)
+        self.arg_types = arg_types
+        super().__init__(operands, builtins.TNone(), name)
+
 class GetAttr(Instruction):
     """
     An intruction that loads an attribute from an object,
@@ -727,7 +803,7 @@ class GetAttr(Instruction):
             typ = obj.type.attributes[attr]
         else:
             typ = obj.type.constructor.attributes[attr]
-            if types.is_function(typ) or types.is_rpc(typ):
+            if types.is_function(typ) or types.is_rpc(typ) or types.is_subkernel(typ):
                 typ = types.TMethod(obj.type, typ)
         super().__init__([obj], typ, name)
         self.attr = attr
@@ -1189,14 +1265,18 @@ class IndirectBranch(Terminator):
 class Return(Terminator):
     """
     A return instruction.
+    :param remote_return: (bool) 
+        marks a return in subkernel context,
+        where the return value is sent back through DRTIO
     """
 
     """
     :param value: (:class:`Value`) return value
     """
-    def __init__(self, value, name=""):
+    def __init__(self, value, remote_return=False, name=""):
         assert isinstance(value, Value)
         super().__init__([value], builtins.TNone(), name)
+        self.remote_return = remote_return
 
     def opcode(self):
         return "return"
@@ -1245,9 +1325,9 @@ class Raise(Terminator):
         if len(self.operands) > 1:
             return self.operands[1]
 
-class Reraise(Terminator):
+class Resume(Terminator):
     """
-    A reraise instruction.
+    A resume instruction.
     """
 
     """
@@ -1261,7 +1341,7 @@ class Reraise(Terminator):
         super().__init__(operands, builtins.TNone(), name)
 
     def opcode(self):
-        return "reraise"
+        return "resume"
 
     def exception_target(self):
         if len(self.operands) > 0:
@@ -1360,14 +1440,6 @@ class LandingPad(Terminator):
     def cleanup(self):
         return self.operands[0]
 
-    def erase(self):
-        self.remove_from_parent()
-        # we should erase all clauses as well
-        for block in set(self.operands):
-            block.uses.remove(self)
-            block.erase()
-        assert not any(self.uses)
-
     def clauses(self):
         return zip(self.operands[1:], self.types)
 

artiq/compiler/kernel.ld

@@ -33,9 +33,19 @@ SECTIONS
         KEEP(*(.eh_frame_hdr))
     } : text : eh_frame
 
+    .got :
+    {
+        *(.got)
+    } : text
+
+    .got.plt :
+    {
+        *(.got.plt)
+    } : text
+
     .data :
     {
-        *(.data)
+        *(.data .data.*)
     } : data
 
     .dynamic :
@@ -51,6 +61,10 @@ SECTIONS
         _end = .;
     }
 
+    /* Kernel stack grows downward from end of memory, so put guard page after
+     * all the program contents. Note: This requires all loaded sections (at
+     * least those accessed) to be explicitly listed in the above!
+     */
     . = ALIGN(0x1000);
     _sstack_guard = .;
 }

artiq/compiler/module.py

@@ -10,7 +10,7 @@ string and infers types for it using a trivial :module:`prelude`.
 
 import os
 from pythonparser import source, diagnostic, parse_buffer
-from . import prelude, types, transforms, analyses, validators
+from . import prelude, types, transforms, analyses, validators, embedding
 
 class Source:
     def __init__(self, source_buffer, engine=None):
@@ -18,7 +18,7 @@ class Source:
             self.engine = diagnostic.Engine(all_errors_are_fatal=True)
         else:
             self.engine = engine
-        self.embedding_map = None
+        self.embedding_map = embedding.EmbeddingMap()
         self.name, _ = os.path.splitext(os.path.basename(source_buffer.name))
 
         asttyped_rewriter = transforms.ASTTypedRewriter(engine=engine,
@@ -57,7 +57,8 @@ class Module:
         constness_validator = validators.ConstnessValidator(engine=self.engine)
         artiq_ir_generator = transforms.ARTIQIRGenerator(engine=self.engine,
                                                          module_name=src.name,
-                                                         ref_period=ref_period)
+                                                         ref_period=ref_period,
+                                                         embedding_map=self.embedding_map)
         dead_code_eliminator = transforms.DeadCodeEliminator(engine=self.engine)
         local_access_validator = validators.LocalAccessValidator(engine=self.engine)
         local_demoter = transforms.LocalDemoter()
@@ -83,6 +84,8 @@ class Module:
         constant_hoister.process(self.artiq_ir)
         if remarks:
             invariant_detection.process(self.artiq_ir)
+        # for subkernels: main kernel inferencer output, to be passed to further compilations
+        self.subkernel_arg_types = inferencer.subkernel_arg_types
 
     def build_llvm_ir(self, target):
         """Compile the module to LLVM IR for the specified target."""

artiq/compiler/prelude.py

@@ -37,6 +37,7 @@ def globals():
 
         # ARTIQ decorators
         "kernel":               builtins.fn_kernel(),
+        "subkernel":            builtins.fn_kernel(),
         "portable":             builtins.fn_kernel(),
         "rpc":                  builtins.fn_kernel(),
 
@@ -54,4 +55,8 @@ def globals():
         # ARTIQ utility functions
         "rtio_log":             builtins.fn_rtio_log(),
         "core_log":             builtins.fn_print(),
+
+        # ARTIQ subkernel utility functions
+        "subkernel_await":     builtins.fn_subkernel_await(),
+        "subkernel_preload":   builtins.fn_subkernel_preload(),
     }

artiq/compiler/targets.py

@@ -74,6 +74,8 @@ class Target:
         LLVM target data layout, e.g. ``"E-m:e-p:32:32-i64:32-f64:32-v64:32-v128:32-a:0:32-n32"``
     :var features: (list of string)
         LLVM target CPU features, e.g. ``["mul", "div", "ffl1"]``
+    :var additional_linker_options: (list of string)
+        Linker options for the target in addition to the target-independent ones, e.g. ``["--target2=rel"]``
     :var print_function: (string)
         Name of a formatted print functions (with the signature of ``printf``)
         provided by the target, e.g. ``"printf"``.
@@ -83,16 +85,18 @@ class Target:
     triple = "unknown"
     data_layout = ""
     features = []
+    additional_linker_options = []
     print_function = "printf"
     now_pinning = True
 
     tool_ld = "ld.lld"
     tool_strip = "llvm-strip"
-    tool_addr2line = "llvm-addr2line"
+    tool_symbolizer = "llvm-symbolizer"
     tool_cxxfilt = "llvm-cxxfilt"
 
-    def __init__(self):
+    def __init__(self, subkernel_id=None):
         self.llcontext = ll.Context()
+        self.subkernel_id = subkernel_id
 
     def target_machine(self):
         lltarget = llvm.Target.from_triple(self.triple)
@@ -145,7 +149,8 @@ class Target:
             ir.BasicBlock._dump_loc = False
 
         type_printer = types.TypePrinter()
-        _dump(os.getenv("ARTIQ_DUMP_IR"), "ARTIQ IR", ".txt",
+        suffix = "_subkernel_{}".format(self.subkernel_id) if self.subkernel_id is not None else ""
+        _dump(os.getenv("ARTIQ_DUMP_IR"), "ARTIQ IR", suffix + ".txt",
               lambda: "\n".join(fn.as_entity(type_printer) for fn in module.artiq_ir))
 
         llmod = module.build_llvm_ir(self)
@@ -157,12 +162,12 @@ class Target:
             _dump("", "LLVM IR (broken)", ".ll", lambda: str(llmod))
             raise
 
-        _dump(os.getenv("ARTIQ_DUMP_UNOPT_LLVM"), "LLVM IR (generated)", "_unopt.ll",
+        _dump(os.getenv("ARTIQ_DUMP_UNOPT_LLVM"), "LLVM IR (generated)", suffix + "_unopt.ll",
               lambda: str(llparsedmod))
 
         self.optimize(llparsedmod)
 
-        _dump(os.getenv("ARTIQ_DUMP_LLVM"), "LLVM IR (optimized)", ".ll",
+        _dump(os.getenv("ARTIQ_DUMP_LLVM"), "LLVM IR (optimized)", suffix + ".ll",
               lambda: str(llparsedmod))
 
         return llparsedmod
@@ -181,6 +186,7 @@ class Target:
     def link(self, objects):
         """Link the relocatable objects into a shared library for this target."""
         with RunTool([self.tool_ld, "-shared", "--eh-frame-hdr"] +
+                     self.additional_linker_options +
                      ["-T" + os.path.join(os.path.dirname(__file__), "kernel.ld")] +
                      ["{{obj{}}}".format(index) for index in range(len(objects))] +
                      ["-x"] +
@@ -212,9 +218,10 @@ class Target:
         # just after the call. Offset them back to get an address somewhere
         # inside the call instruction (or its delay slot), since that's what
         # the backtrace entry should point at.
+        last_inlined = None
         offset_addresses = [hex(addr - 1) for addr in addresses]
-        with RunTool([self.tool_addr2line, "--addresses",  "--functions", "--inlines",
+        with RunTool([self.tool_symbolizer, "--addresses",  "--functions", "--inlines",
-                      "--demangle", "--exe={library}"] + offset_addresses,
+                      "--demangle", "--output-style=GNU", "--exe={library}"] + offset_addresses,
                      library=library) \
                 as results:
             lines = iter(results["__stdout__"].read().rstrip().split("\n"))
@@ -227,9 +234,11 @@ class Target:
                 if address_or_function[:2] == "0x":
                     address  = int(address_or_function[2:], 16) + 1 # remove offset
                     function = next(lines)
+                    inlined = False
                 else:
                     address  = backtrace[-1][4] # inlined
                     function = address_or_function
+                    inlined = True
                 location = next(lines)
 
                 filename, line = location.rsplit(":", 1)
@@ -240,10 +249,17 @@ class Target:
                 else:
                     line = int(line)
                 # can't get column out of addr2line D:
-                backtrace.append((filename, line, -1, function, address))
+                if inlined:
+                    last_inlined.append((filename, line, -1, function, address))
+                else:
+                    last_inlined = []
+                    backtrace.append((filename, line, -1, function, address,
+                                      last_inlined))
             return backtrace
 
     def demangle(self, names):
+        if not any(names):
+            return names
         with RunTool([self.tool_cxxfilt] + names) as results:
             return results["__stdout__"].read().rstrip().split("\n")
 
@@ -251,40 +267,43 @@ class NativeTarget(Target):
     def __init__(self):
         super().__init__()
         self.triple = llvm.get_default_triple()
-        host_data_layout = str(llvm.targets.Target.from_default_triple().create_target_machine().target_data)
+        self.data_layout = str(llvm.targets.Target.from_default_triple().create_target_machine().target_data)
 
 class RV32IMATarget(Target):
     triple = "riscv32-unknown-linux"
     data_layout = "e-m:e-p:32:32-i64:64-n32-S128"
     features = ["m", "a"]
+    additional_linker_options = ["-m", "elf32lriscv"]
     print_function = "core_log"
     now_pinning = True
 
     tool_ld = "ld.lld"
     tool_strip = "llvm-strip"
-    tool_addr2line = "llvm-addr2line"
+    tool_symbolizer = "llvm-symbolizer"
     tool_cxxfilt = "llvm-cxxfilt"
 
 class RV32GTarget(Target):
     triple = "riscv32-unknown-linux"
     data_layout = "e-m:e-p:32:32-i64:64-n32-S128"
     features = ["m", "a", "f", "d"]
+    additional_linker_options = ["-m", "elf32lriscv"]
     print_function = "core_log"
     now_pinning = True
 
     tool_ld = "ld.lld"
     tool_strip = "llvm-strip"
-    tool_addr2line = "llvm-addr2line"
+    tool_symbolizer = "llvm-symbolizer"
     tool_cxxfilt = "llvm-cxxfilt"
 
 class CortexA9Target(Target):
     triple = "armv7-unknown-linux-gnueabihf"
     data_layout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
     features = ["dsp", "fp16", "neon", "vfp3"]
+    additional_linker_options = ["-m", "armelf_linux_eabi", "--target2=rel"]
     print_function = "core_log"
     now_pinning = False
 
     tool_ld = "ld.lld"
     tool_strip = "llvm-strip"
-    tool_addr2line = "llvm-addr2line"
+    tool_symbolizer = "llvm-symbolizer"
     tool_cxxfilt = "llvm-cxxfilt"

artiq/compiler/testbench/perf_embedding.py

@@ -30,8 +30,9 @@ def main():
     device_db_path = os.path.join(os.path.dirname(sys.argv[1]), "device_db.py")
     device_mgr = DeviceManager(DeviceDB(device_db_path))
 
-    dataset_db_path = os.path.join(os.path.dirname(sys.argv[1]), "dataset_db.pyon")
+    dataset_db_path = os.path.join(os.path.dirname(sys.argv[1]), "dataset_db.mdb")
-    dataset_mgr = DatasetManager(DatasetDB(dataset_db_path))
+    dataset_db = DatasetDB(dataset_db_path)
+    dataset_mgr = DatasetManager()
 
     argument_mgr = ProcessArgumentManager({})
 
@@ -68,5 +69,7 @@ def main():
     benchmark(lambda: target.strip(elf_shlib),
               "Stripping debug information")
 
+    dataset_db.close_db()
+
 if __name__ == "__main__":
     main()

artiq/compiler/transforms/artiq_ir_generator.py

@@ -8,6 +8,7 @@ semantics explicitly.
 
 from collections import OrderedDict, defaultdict
 from functools import reduce
+from itertools import chain
 from pythonparser import algorithm, diagnostic, ast
 from .. import types, builtins, asttyped, ir, iodelay
 
@@ -61,6 +62,9 @@ class ARTIQIRGenerator(algorithm.Visitor):
         the basic block to which ``return`` will transfer control
     :ivar unwind_target: (:class:`ir.BasicBlock` or None)
         the basic block to which unwinding will transfer control
+    :ivar catch_clauses: (list of (:class:`ir.BasicBlock`, :class:`types.Type` or None))
+        a list of catch clauses that should be appended to inner try block
+        landingpad
     :ivar final_branch: (function (target: :class:`ir.BasicBlock`, block: :class:`ir.BasicBlock)
                          or None)
         the function that appends to ``block`` a jump through the ``finally`` statement
@@ -88,8 +92,9 @@ class ARTIQIRGenerator(algorithm.Visitor):
 
     _size_type = builtins.TInt32()
 
-    def __init__(self, module_name, engine, ref_period):
+    def __init__(self, module_name, engine, ref_period, embedding_map):
         self.engine = engine
+        self.embedding_map = embedding_map
         self.functions = []
         self.name = [module_name] if module_name != "" else []
         self.ref_period = ir.Constant(ref_period, builtins.TFloat())
@@ -102,10 +107,13 @@ class ARTIQIRGenerator(algorithm.Visitor):
         self.current_private_env = None
         self.current_args = None
         self.current_assign = None
+        self.current_exception = None
+        self.current_remote_fn = False
         self.break_target = None
         self.continue_target = None
         self.return_target = None
         self.unwind_target = None
+        self.catch_clauses = []
         self.final_branch = None
         self.function_map = dict()
         self.variable_map = dict()
@@ -204,7 +212,8 @@ class ARTIQIRGenerator(algorithm.Visitor):
             old_priv_env, self.current_private_env = self.current_private_env, priv_env
 
             self.generic_visit(node)
-            self.terminate(ir.Return(ir.Constant(None, builtins.TNone())))
+            self.terminate(ir.Return(ir.Constant(None, builtins.TNone()),
+                           remote_return=self.current_remote_fn))
 
             return self.functions
         finally:
@@ -287,6 +296,8 @@ class ARTIQIRGenerator(algorithm.Visitor):
             old_block, self.current_block = self.current_block, entry
 
             old_globals, self.current_globals = self.current_globals, node.globals_in_scope
+            old_remote_fn = self.current_remote_fn
+            self.current_remote_fn = getattr(node, "remote_fn", False)
 
             env_without_globals = \
                 {var: node.typing_env[var]
@@ -319,7 +330,8 @@ class ARTIQIRGenerator(algorithm.Visitor):
                 self.terminate(ir.Return(result))
             elif builtins.is_none(typ.ret):
                 if not self.current_block.is_terminated():
-                    self.current_block.append(ir.Return(ir.Constant(None, builtins.TNone())))
+                    self.current_block.append(ir.Return(ir.Constant(None, builtins.TNone()), 
+                                                        remote_return=self.current_remote_fn))
             else:
                 if not self.current_block.is_terminated():
                     if len(self.current_block.predecessors()) != 0:
@@ -338,6 +350,7 @@ class ARTIQIRGenerator(algorithm.Visitor):
             self.current_block = old_block
             self.current_globals = old_globals
             self.current_env = old_env
+            self.current_remote_fn = old_remote_fn
             if not is_lambda:
                 self.current_private_env = old_priv_env
 
@@ -360,7 +373,8 @@ class ARTIQIRGenerator(algorithm.Visitor):
             return_value = self.visit(node.value)
 
         if self.return_target is None:
-            self.append(ir.Return(return_value))
+            self.append(ir.Return(return_value, 
+                                  remote_return=self.current_remote_fn))
         else:
             self.append(ir.SetLocal(self.current_private_env, "$return", return_value))
             self.append(ir.Branch(self.return_target))
@@ -638,10 +652,10 @@ class ARTIQIRGenerator(algorithm.Visitor):
             loc_column = ir.Constant(loc.column(), builtins.TInt32())
             loc_function = ir.Constant(".".join(self.name), builtins.TStr())
 
-            self.append(ir.SetAttr(exn, "__file__", loc_file))
+            self.append(ir.SetAttr(exn, "#__file__", loc_file))
-            self.append(ir.SetAttr(exn, "__line__", loc_line))
+            self.append(ir.SetAttr(exn, "#__line__", loc_line))
-            self.append(ir.SetAttr(exn, "__col__", loc_column))
+            self.append(ir.SetAttr(exn, "#__col__", loc_column))
-            self.append(ir.SetAttr(exn, "__func__", loc_function))
+            self.append(ir.SetAttr(exn, "#__func__", loc_function))
 
             if self.unwind_target is not None:
                 self.append(ir.Raise(exn, self.unwind_target))
@@ -649,9 +663,9 @@ class ARTIQIRGenerator(algorithm.Visitor):
                 self.append(ir.Raise(exn))
         else:
             if self.unwind_target is not None:
-                self.append(ir.Reraise(self.unwind_target))
+                self.append(ir.Resume(self.unwind_target))
             else:
-                self.append(ir.Reraise())
+                self.append(ir.Resume())
 
     def visit_Raise(self, node):
         if node.exc is not None and types.is_exn_constructor(node.exc.type):
@@ -661,6 +675,9 @@ class ARTIQIRGenerator(algorithm.Visitor):
 
     def visit_Try(self, node):
         dispatcher = self.add_block("try.dispatch")
+        cleanup = self.add_block('handler.cleanup')
+        landingpad = ir.LandingPad(cleanup)
+        dispatcher.append(landingpad)
 
         if any(node.finalbody):
             # k for continuation
@@ -676,15 +693,6 @@ class ARTIQIRGenerator(algorithm.Visitor):
                 final_targets.append(target)
                 final_paths.append(block)
 
-            final_exn_targets = []
-            final_exn_paths = []
-            # raise has to be treated differently
-            # we cannot follow indirectbr for local access validation, so we
-            # have to construct the control flow explicitly
-            def exception_final_branch(target, block):
-                final_exn_targets.append(target)
-                final_exn_paths.append(block)
-
             if self.break_target is not None:
                 break_proxy = self.add_block("try.break")
                 old_break, self.break_target = self.break_target, break_proxy
@@ -704,16 +712,51 @@ class ARTIQIRGenerator(algorithm.Visitor):
                 value = return_action.append(ir.GetLocal(self.current_private_env, "$return"))
                 return_action.append(ir.Return(value))
                 final_branch(return_action, return_proxy)
+        else:
+            landingpad.has_cleanup = False
+
+        # we should propagate the clauses to nested try catch blocks
+        # so nested try catch will jump to our clause if the inner one does not
+        # match
+        # note that the phi instruction here requires some hack, see
+        # llvm_ir_generator process_function for details
+        clauses = []
+        found_catch_all = False
+        for handler_node in node.handlers:
+            if found_catch_all:
+                self.warn_unreachable(handler_node)
+                continue
+            exn_type = handler_node.name_type.find()
+            if handler_node.filter is not None and \
+                    not builtins.is_exception(exn_type, 'Exception'):
+                handler = self.add_block("handler." + exn_type.name)
+                phi = ir.Phi(builtins.TException(), 'exn')
+                handler.append(phi)
+                clauses.append((handler, exn_type, phi))
+            else:
+                handler = self.add_block("handler.catchall")
+                phi = ir.Phi(builtins.TException(), 'exn')
+                handler.append(phi)
+                clauses.append((handler, None, phi))
+                found_catch_all = True
+
+        all_clauses = clauses[:]
+        for clause in self.catch_clauses:
+            # if the last clause is accept all, do not add further clauses
+            if len(all_clauses) == 0 or all_clauses[-1][1] is not None:
+                all_clauses.append(clause)
 
         body = self.add_block("try.body")
         self.append(ir.Branch(body))
         self.current_block = body
 
-        try:
         old_unwind, self.unwind_target = self.unwind_target, dispatcher
+        old_clauses, self.catch_clauses = self.catch_clauses, all_clauses
+        try:
             self.visit(node.body)
         finally:
             self.unwind_target = old_unwind
+            self.catch_clauses = old_clauses
 
         if not self.current_block.is_terminated():
             self.visit(node.orelse)
@@ -722,95 +765,149 @@ class ARTIQIRGenerator(algorithm.Visitor):
         body = self.current_block
 
         if any(node.finalbody):
+            # if we have a final block, we should not append clauses to our
+            # landingpad or we will skip the finally block.
+            # when the finally block calls resume, it will unwind to the outer
+            # try catch block automatically
+            all_clauses = clauses
+            # reset targets
             if self.break_target:
                 self.break_target = old_break
             if self.continue_target:
                 self.continue_target = old_continue
             self.return_target = old_return
 
-            old_final_branch, self.final_branch = self.final_branch, exception_final_branch
+        if any(node.finalbody):
+            # create new unwind target for cleanup
+            final_dispatcher = self.add_block("try.final.dispatch")
+            final_landingpad = ir.LandingPad(cleanup)
+            final_dispatcher.append(final_landingpad)
 
-        cleanup = self.add_block('handler.cleanup')
+            # make sure that exception clauses are unwinded to the finally block
-        landingpad = dispatcher.append(ir.LandingPad(cleanup))
+            old_unwind, self.unwind_target = self.unwind_target, final_dispatcher
-        if not any(node.finalbody):
+
-            landingpad.has_cleanup = False
+        if any(node.finalbody):
+            # if we have a while:try/finally continue must execute finally
+            # before continuing the while
+            redirect = final_branch
+        else:
+            redirect = lambda dest, proxy: proxy.append(ir.Branch(dest))
+
+        # we need to set break/continue/return to execute end_catch
+        if self.break_target is not None:
+            break_proxy = self.add_block("try.break")
+            break_proxy.append(ir.Builtin("end_catch", [], builtins.TNone()))
+            old_break, self.break_target = self.break_target, break_proxy
+            redirect(old_break, break_proxy)
+
+        if self.continue_target is not None:
+            continue_proxy = self.add_block("try.continue")
+            continue_proxy.append(ir.Builtin("end_catch", [],
+                                             builtins.TNone()))
+            old_continue, self.continue_target = self.continue_target, continue_proxy
+            redirect(old_continue, continue_proxy)
+
+        return_proxy = self.add_block("try.return")
+        return_proxy.append(ir.Builtin("end_catch", [], builtins.TNone()))
+        old_return, self.return_target = self.return_target, return_proxy
+        old_return_target = old_return
+        if old_return_target is None:
+            old_return_target = self.add_block("try.doreturn")
+            value = old_return_target.append(ir.GetLocal(self.current_private_env, "$return"))
+            old_return_target.append(ir.Return(value))
+        redirect(old_return_target, return_proxy)
 
         handlers = []
-        for handler_node in node.handlers:
-            exn_type = handler_node.name_type.find()
-            if handler_node.filter is not None and \
-                    not builtins.is_exception(exn_type, 'Exception'):
-                handler = self.add_block("handler." + exn_type.name)
-                landingpad.add_clause(handler, exn_type)
-            else:
-                handler = self.add_block("handler.catchall")
-                landingpad.add_clause(handler, None)
 
+        for (handler_node, (handler, exn_type, phi)) in zip(node.handlers, clauses):
             self.current_block = handler
             if handler_node.name is not None:
-                exn = self.append(ir.Builtin("exncast", [landingpad], handler_node.name_type))
+                exn = self.append(ir.Builtin("exncast", [phi], handler_node.name_type))
                 self._set_local(handler_node.name, exn)
             self.visit(handler_node.body)
+            # only need to call end_catch if the current block is not terminated
+            # other possible paths: break/continue/return/raise
+            # we will call end_catch in the first 3 cases, and we should not
+            # end_catch in the last case for nested exception
+            if not self.current_block.is_terminated():
+                self.append(ir.Builtin("end_catch", [], builtins.TNone()))
             post_handler = self.current_block
+            handlers.append(post_handler)
 
-            handlers.append((handler, post_handler))
+        # branch to all possible clauses, including those from outer try catch
+        # block
+        # if we have a finally block, all_clauses will not include those from
+        # the outer block
+        for (handler, clause, phi) in all_clauses:
+            phi.add_incoming(landingpad, dispatcher)
+            landingpad.add_clause(handler, clause)
+
+        if self.break_target:
+            self.break_target = old_break
+        if self.continue_target:
+            self.continue_target = old_continue
+        self.return_target = old_return
 
         if any(node.finalbody):
             # Finalize and continue after try statement.
-            self.final_branch = old_final_branch
+            self.unwind_target = old_unwind
-
+            # Exception path
-            for (i, (target, block)) in enumerate(zip(final_exn_targets, final_exn_paths)):
+            finalizer_reraise = self.add_block("finally.resume")
-                finalizer = self.add_block(f"finally{i}")
-                self.current_block = block
-                self.terminate(ir.Branch(finalizer))
-                self.current_block = finalizer
-                self.visit(node.finalbody)
-                self.terminate(ir.Branch(target))
-
-            finalizer = self.add_block("finally")
-            self.current_block = finalizer
-
-            self.visit(node.finalbody)
-            post_finalizer = self.current_block
-
-            # Finalize and reraise. Separate from previous case to expose flow
-            # to LocalAccessValidator.
-            finalizer_reraise = self.add_block("finally.reraise")
             self.current_block = finalizer_reraise
-
             self.visit(node.finalbody)
-            self.terminate(ir.Reraise(self.unwind_target))
+            self.terminate(ir.Resume(self.unwind_target))
-
-        self.current_block = tail = self.add_block("try.tail")
-        if any(node.finalbody):
-            final_targets.append(tail)
-
-            for block in final_paths:
-                block.append(ir.Branch(finalizer))
-
-            if not body.is_terminated():
-                body.append(ir.SetLocal(final_state, "$cont", tail))
-                body.append(ir.Branch(finalizer))
-
             cleanup.append(ir.Branch(finalizer_reraise))
 
-            for handler, post_handler in handlers:
+            # Normal path
-                if not post_handler.is_terminated():
+            finalizer = self.add_block("finally")
-                    post_handler.append(ir.SetLocal(final_state, "$cont", tail))
+            self.current_block = finalizer
-                    post_handler.append(ir.Branch(finalizer))
+            self.visit(node.finalbody)
+            post_finalizer = self.current_block
+            self.current_block = tail = self.add_block("try.tail")
+            final_targets.append(tail)
 
+            # if final block is not terminated, branch to tail
             if not post_finalizer.is_terminated():
                 dest = post_finalizer.append(ir.GetLocal(final_state, "$cont"))
                 post_finalizer.append(ir.IndirectBranch(dest, final_targets))
+            # make sure proxies will branch to finalizer
+            for block in final_paths:
+                if finalizer in block.predecessors():
+                    # avoid producing irreducible graphs
+                    # generate a new finalizer
+                    self.current_block = tmp_finalizer = self.add_block("finally.tmp")
+                    self.visit(node.finalbody)
+                    if not self.current_block.is_terminated():
+                        assert isinstance(block.instructions[-1], ir.SetLocal)
+                        self.current_block.append(ir.Branch(block.instructions[-1].operands[-1]))
+                        block.instructions[-1].erase()
+                    block.append(ir.Branch(tmp_finalizer))
+                    self.current_block = tail
                 else:
+                    block.append(ir.Branch(finalizer))
+            # if no raise in body/handlers, branch to finalizer
+            for block in chain([body], handlers):
+                if not block.is_terminated():
+                    if finalizer in block.predecessors():
+                        # similar to the above case
+                        self.current_block = tmp_finalizer = self.add_block("finally.tmp")
+                        self.visit(node.finalbody)
+                        self.terminate(ir.Branch(tail))
+                        block.append(ir.Branch(tmp_finalizer))
+                        self.current_block = tail
+                    else:
+                        block.append(ir.SetLocal(final_state, "$cont", tail))
+                        block.append(ir.Branch(finalizer))
+        else:
+            self.current_block = tail = self.add_block("try.tail")
             if not body.is_terminated():
                 body.append(ir.Branch(tail))
 
-            cleanup.append(ir.Reraise(self.unwind_target))
+            cleanup.append(ir.Resume(self.unwind_target))
 
-            for handler, post_handler in handlers:
+            for handler in handlers:
-                if not post_handler.is_terminated():
+                if not handler.is_terminated():
-                    post_handler.append(ir.Branch(tail))
+                    handler.append(ir.Branch(tail))
 
     def _try_finally(self, body_gen, finally_gen, name):
         dispatcher = self.add_block("{}.dispatch".format(name))
@@ -829,7 +926,7 @@ class ARTIQIRGenerator(algorithm.Visitor):
         self.current_block = self.add_block("{}.cleanup".format(name))
         dispatcher.append(ir.LandingPad(self.current_block))
         finally_gen()
-        self.raise_exn()
+        self.terminate(ir.Resume(self.unwind_target))
 
         self.current_block = self.post_body
 
@@ -1108,7 +1205,27 @@ class ARTIQIRGenerator(algorithm.Visitor):
         finally:
             self.current_assign = old_assign
 
-        if isinstance(node.slice, ast.Index):
+        if types.is_tuple(node.value.type):
+            assert isinstance(node.slice, ast.Index), \
+                "Internal compiler error: tuple index should be an Index"
+            assert isinstance(node.slice.value, ast.Num), \
+                "Internal compiler error: tuple index should be a constant"
+
+            if self.current_assign is not None:
+                diag = diagnostic.Diagnostic("error",
+                    "cannot assign to a tuple element",
+                    {}, node.loc)
+                self.engine.process(diag)
+
+            index = node.slice.value.n
+            indexed = self.append(
+                ir.GetAttr(value, index, name="{}.e{}".format(value.name, index)),
+                loc=node.loc
+            )
+
+            return indexed
+
+        elif isinstance(node.slice, ast.Index):
             try:
                 old_assign, self.current_assign = self.current_assign, None
                 index = self.visit(node.slice.value)
@@ -2102,11 +2219,13 @@ class ARTIQIRGenerator(algorithm.Visitor):
         return phi
 
     # Keep this function with builtins.TException.attributes.
-    def alloc_exn(self, typ, message=None, param0=None, param1=None, param2=None):
+    def alloc_exn(self, typ, message=None, param0=None, param1=None,
+                  param2=None, nomsgcheck=False):
         typ = typ.find()
         name = "{}:{}".format(typ.id, typ.name)
+        name_id = self.embedding_map.store_str(name)
         attributes = [
-            ir.Constant(name,           builtins.TStr()),   # typeinfo
+            ir.Constant(name_id,        builtins.TInt32()),   # typeinfo
             ir.Constant("<not thrown>", builtins.TStr()),   # file
             ir.Constant(0,              builtins.TInt32()), # line
             ir.Constant(0,              builtins.TInt32()), # column
@@ -2115,8 +2234,16 @@ class ARTIQIRGenerator(algorithm.Visitor):
 
         if message is None:
             attributes.append(ir.Constant(typ.name, builtins.TStr()))
-        else:
+        elif isinstance(message, ir.Constant) or nomsgcheck:
             attributes.append(message)                  # message
+        else:
+            diag = diagnostic.Diagnostic(
+                "error",
+                "only constant exception messages are supported",
+                {},
+                self.current_loc if message.loc is None else message.loc
+            )
+            self.engine.process(diag)
 
         param_type = builtins.TInt64()
         for param in [param0, param1, param2]:
@@ -2404,6 +2531,33 @@ class ARTIQIRGenerator(algorithm.Visitor):
                 or types.is_builtin(typ, "at_mu"):
             return self.append(ir.Builtin(typ.name,
                                           [self.visit(arg) for arg in node.args], node.type))
+        elif types.is_builtin(typ, "subkernel_await"):
+            if len(node.args) == 2 and len(node.keywords) == 0:
+                fn = node.args[0].type
+                timeout = self.visit(node.args[1])
+            elif len(node.args) == 1 and len(node.keywords) == 0:
+                fn = node.args[0].type
+                timeout = ir.Constant(10_000, builtins.TInt64())
+            else:
+                assert False
+            if types.is_method(fn):
+                fn = types.get_method_function(fn)
+            sid = ir.Constant(fn.sid, builtins.TInt32())
+            if not builtins.is_none(fn.ret):
+                ret = self.append(ir.Builtin("subkernel_retrieve_return", [sid, timeout], fn.ret))
+            else:
+                ret = ir.Constant(None, builtins.TNone())
+            self.append(ir.Builtin("subkernel_await_finish", [sid, timeout], builtins.TNone()))
+            return ret
+        elif types.is_builtin(typ, "subkernel_preload"):
+            if len(node.args) == 1 and len(node.keywords) == 0:
+                fn = node.args[0].type
+            else:
+                assert False
+            if types.is_method(fn):
+                fn = types.get_method_function(fn)
+            sid = ir.Constant(fn.sid, builtins.TInt32())
+            return self.append(ir.Builtin("subkernel_preload", [sid], builtins.TNone()))
         elif types.is_exn_constructor(typ):
             return self.alloc_exn(node.type, *[self.visit(arg_node) for arg_node in node.args])
         elif types.is_constructor(typ):
@@ -2415,8 +2569,8 @@ class ARTIQIRGenerator(algorithm.Visitor):
                 node.loc)
             self.engine.process(diag)
 
-    def _user_call(self, callee, positional, keywords, arg_exprs={}):
+    def _user_call(self, callee, positional, keywords, arg_exprs={}, remote_fn=False):
-        if types.is_function(callee.type) or types.is_rpc(callee.type):
+        if types.is_function(callee.type) or types.is_rpc(callee.type) or types.is_subkernel(callee.type):
             func     = callee
             self_arg = None
             fn_typ   = callee.type
@@ -2431,16 +2585,51 @@ class ARTIQIRGenerator(algorithm.Visitor):
         else:
             assert False
 
-        if types.is_rpc(fn_typ):
+        if types.is_rpc(fn_typ) or types.is_subkernel(fn_typ):
-            if self_arg is None:
+            if self_arg is None or types.is_subkernel(fn_typ):
+                # self is not passed to subkernels by remote
                 args = positional
-            else:
+            elif self_arg is not None:
                 args = [self_arg] + positional
 
             for keyword in keywords:
                 arg = keywords[keyword]
                 args.append(self.append(ir.Alloc([ir.Constant(keyword, builtins.TStr()), arg],
                                                  ir.TKeyword(arg.type))))
+        elif remote_fn:
+            assert self_arg is None
+            assert len(fn_typ.args) >= len(positional)
+            assert len(keywords) == 0  # no keyword support
+            args = [None] * fn_typ.arity()
+            index = 0
+            # fill in first available args
+            for arg in positional:
+                args[index] = arg
+                index += 1
+
+            # remaining args are received through DRTIO
+            if index < len(args):
+                # min/max args received remotely (minus already filled)
+                offset = index
+                min_args = ir.Constant(len(fn_typ.args)-offset, builtins.TInt8())
+                max_args = ir.Constant(fn_typ.arity()-offset, builtins.TInt8())
+
+                arg_types = list(fn_typ.args.items())[offset:] 
+                arg_type_list = [a[1] for a in arg_types] + [a[1] for a in fn_typ.optargs.items()]
+                rcvd_count = self.append(ir.SubkernelAwaitArgs([min_args, max_args], arg_type_list))
+                # obligatory arguments
+                for arg_name, arg_type in arg_types:
+                    args[index] = self.append(ir.GetArgFromRemote(arg_name, arg_type,
+                                            name="ARG.{}".format(arg_name)))
+                    index += 1
+
+                # optional arguments
+                for optarg_name, optarg_type in fn_typ.optargs.items():
+                    idx = ir.Constant(index-offset, builtins.TInt8())
+                    args[index] = \
+                        self.append(ir.GetOptArgFromRemote(optarg_name, optarg_type, rcvd_count, idx))
+                    index += 1
+
         else:
             args = [None] * (len(fn_typ.args) + len(fn_typ.optargs))
 
@@ -2526,7 +2715,8 @@ class ARTIQIRGenerator(algorithm.Visitor):
             else:
                 assert False, "Broadcasting for {} arguments not implemented".format(len)
         else:
-            insn = self._user_call(callee, args, keywords, node.arg_exprs)
+            remote_fn = getattr(node, "remote_fn", False)
+            insn = self._user_call(callee, args, keywords, node.arg_exprs, remote_fn)
             if isinstance(node.func, asttyped.AttributeT):
                 attr_node = node.func
                 self.method_map[(attr_node.value.type.find(),
@@ -2577,11 +2767,12 @@ class ARTIQIRGenerator(algorithm.Visitor):
             old_final_branch, self.final_branch = self.final_branch, None
             old_unwind, self.unwind_target = self.unwind_target, None
 
-            exn = self.alloc_exn(builtins.TException("AssertionError"), message=msg)
+            exn = self.alloc_exn(builtins.TException("AssertionError"),
-            self.append(ir.SetAttr(exn, "__file__", file))
+                                 message=msg, nomsgcheck=True)
-            self.append(ir.SetAttr(exn, "__line__", line))
+            self.append(ir.SetAttr(exn, "#__file__", file))
-            self.append(ir.SetAttr(exn, "__col__", col))
+            self.append(ir.SetAttr(exn, "#__line__", line))
-            self.append(ir.SetAttr(exn, "__func__", function))
+            self.append(ir.SetAttr(exn, "#__col__", col))
+            self.append(ir.SetAttr(exn, "#__func__", function))
             self.append(ir.Raise(exn))
         finally:
             self.current_function = old_func
@@ -2717,14 +2908,15 @@ class ARTIQIRGenerator(algorithm.Visitor):
 
                 format_string += ")"
             elif builtins.is_exception(value.type):
-                name    = self.append(ir.GetAttr(value, "__name__"))
+                # message may not be an actual string...
-                message = self.append(ir.GetAttr(value, "__message__"))
+                # so we cannot really print it
-                param1  = self.append(ir.GetAttr(value, "__param0__"))
+                name    = self.append(ir.GetAttr(value, "#__name__"))
-                param2  = self.append(ir.GetAttr(value, "__param1__"))
+                param1  = self.append(ir.GetAttr(value, "#__param0__"))
-                param3  = self.append(ir.GetAttr(value, "__param2__"))
+                param2  = self.append(ir.GetAttr(value, "#__param1__"))
+                param3  = self.append(ir.GetAttr(value, "#__param2__"))
 
-                format_string += "%.*s(%.*s, %lld, %lld, %lld)"
+                format_string += "%ld(%lld, %lld, %lld)"
-                args += [name, message, param1, param2, param3]
+                args += [name, param1, param2, param3]
             else:
                 assert False
 

artiq/compiler/transforms/asttyped_rewriter.py

@@ -238,7 +238,7 @@ class ASTTypedRewriter(algorithm.Transformer):
             body=node.body, decorator_list=node.decorator_list,
             keyword_loc=node.keyword_loc, name_loc=node.name_loc,
             arrow_loc=node.arrow_loc, colon_loc=node.colon_loc, at_locs=node.at_locs,
-            loc=node.loc)
+            loc=node.loc, remote_fn=False)
 
         try:
             self.env_stack.append(node.typing_env)
@@ -440,7 +440,8 @@ class ASTTypedRewriter(algorithm.Transformer):
     def visit_Call(self, node):
         node = self.generic_visit(node)
         node = asttyped.CallT(type=types.TVar(), iodelay=None, arg_exprs={}, 
-                              func=node.func, args=node.args, keywords=node.keywords,
+                              remote_fn=False, func=node.func, 
+                              args=node.args, keywords=node.keywords, 
                               starargs=node.starargs, kwargs=node.kwargs,
                               star_loc=node.star_loc, dstar_loc=node.dstar_loc,
                               begin_loc=node.begin_loc, end_loc=node.end_loc, loc=node.loc)

artiq/compiler/transforms/dead_code_eliminator.py

@@ -15,13 +15,26 @@ class DeadCodeEliminator:
             self.process_function(func)
 
     def process_function(self, func):
-        modified = True
+        # defer removing those blocks, so our use checks will ignore deleted blocks
-        while modified:
+        preserve = [func.entry()]
-            modified = False
+        work_list = [func.entry()]
-            for block in list(func.basic_blocks):
+        while any(work_list):
-                if not any(block.predecessors()) and block != func.entry():
+            block = work_list.pop()
+            for succ in block.successors():
+                if succ not in preserve:
+                    preserve.append(succ)
+                    work_list.append(succ)
+
+        to_be_removed = []
+        for block in func.basic_blocks:
+            if block not in preserve:
+                block.is_removed = True
+                to_be_removed.append(block)
+                for insn in block.instructions:
+                    insn.is_removed = True
+
+        for block in to_be_removed:
             self.remove_block(block)
-                    modified = True
 
         modified = True
         while modified:
@@ -42,6 +55,8 @@ class DeadCodeEliminator:
     def remove_block(self, block):
         # block.uses are updated while iterating
         for use in set(block.uses):
+            if use.is_removed:
+                continue
             if isinstance(use, ir.Phi):
                 use.remove_incoming_block(block)
                 if not any(use.operands):
@@ -56,6 +71,8 @@ class DeadCodeEliminator:
 
     def remove_instruction(self, insn):
         for use in set(insn.uses):
+            if use.is_removed:
+                continue
             if isinstance(use, ir.Phi):
                 use.remove_incoming_value(insn)
                 if not any(use.operands):

artiq/compiler/transforms/inferencer.py

@@ -46,6 +46,7 @@ class Inferencer(algorithm.Visitor):
         self.function = None # currently visited function, for Return inference
         self.in_loop = False
         self.has_return = False
+        self.subkernel_arg_types = dict()
 
     def _unify(self, typea, typeb, loca, locb, makenotes=None, when=""):
         try:
@@ -178,7 +179,7 @@ class Inferencer(algorithm.Visitor):
                     # Convert to a method.
                     attr_type = types.TMethod(object_type, attr_type)
                     self._unify_method_self(attr_type, attr_name, attr_loc, loc, value_node.loc)
-                elif types.is_rpc(attr_type):
+                elif types.is_rpc(attr_type) or types.is_subkernel(attr_type):
                     # Convert to a method. We don't have to bother typechecking
                     # the self argument, since for RPCs anything goes.
                     attr_type = types.TMethod(object_type, attr_type)
@@ -259,7 +260,31 @@ class Inferencer(algorithm.Visitor):
 
     def visit_SubscriptT(self, node):
         self.generic_visit(node)
-        if isinstance(node.slice, ast.Index):
+
+        if types.is_tuple(node.value.type):
+            if (not isinstance(node.slice, ast.Index) or
+                not isinstance(node.slice.value, ast.Num)):
+                diag = diagnostic.Diagnostic(
+                    "error", "tuples can only be indexed by a constant", {},
+                    node.slice.loc, []
+                )
+                self.engine.process(diag)
+                return
+
+            tuple_type = node.value.type.find()
+            index = node.slice.value.n
+            if index < 0 or index >= len(tuple_type.elts):
+                diag = diagnostic.Diagnostic(
+                    "error",
+                    "index {index} is out of range for tuple of size {size}",
+                    {"index": index, "size": len(tuple_type.elts)},
+                    node.slice.loc, []
+                )
+                self.engine.process(diag)
+                return
+
+            self._unify(node.type, tuple_type.elts[index], node.loc, node.value.loc)
+        elif isinstance(node.slice, ast.Index):
             if types.is_tuple(node.slice.value.type):
                 if types.is_var(node.value.type):
                     return
@@ -1269,6 +1294,55 @@ class Inferencer(algorithm.Visitor):
             # Ignored.
             self._unify(node.type, builtins.TNone(),
                         node.loc, None)
+        elif types.is_builtin(typ, "subkernel_await"):
+            valid_forms = lambda: [
+                valid_form("subkernel_await(f: subkernel) -> f return type"),
+                valid_form("subkernel_await(f: subkernel, timeout: numpy.int64) -> f return type")
+            ]
+            if 1 <= len(node.args) <= 2:
+                arg0 = node.args[0].type
+                if types.is_var(arg0):
+                    pass  # undetermined yet
+                else:
+                    if types.is_method(arg0):
+                        fn = types.get_method_function(arg0)
+                    elif types.is_function(arg0) or types.is_subkernel(arg0):
+                        fn = arg0
+                    else:
+                        diagnose(valid_forms())
+                    self._unify(node.type, fn.ret,
+                                node.loc, None)
+                if len(node.args) == 2:
+                    arg1 = node.args[1]
+                    if types.is_var(arg1.type):
+                        pass
+                    elif builtins.is_int(arg1.type):
+                        # promote to TInt64
+                        self._unify(arg1.type, builtins.TInt64(),
+                                    arg1.loc, None)
+                    else:
+                        diagnose(valid_forms())
+            else:
+                diagnose(valid_forms())
+        elif types.is_builtin(typ, "subkernel_preload"):
+            valid_forms = lambda: [
+                valid_form("subkernel_preload(f: subkernel) -> None")
+            ]
+            if len(node.args) == 1:
+                arg0 = node.args[0].type
+                if types.is_var(arg0):
+                    pass  # undetermined yet
+                else:
+                    if types.is_method(arg0):
+                        fn = types.get_method_function(arg0)
+                    elif types.is_function(arg0) or types.is_subkernel(arg0):
+                        fn = arg0
+                    else:
+                        diagnose(valid_forms())
+                    self._unify(node.type, fn.ret,
+                                node.loc, None)
+            else:
+                diagnose(valid_forms())
         else:
             assert False
 
@@ -1307,6 +1381,7 @@ class Inferencer(algorithm.Visitor):
             typ_args    = typ.args
             typ_optargs = typ.optargs
             typ_ret     = typ.ret
+            typ_func    = typ
         else:
             typ_self    = types.get_method_self(typ)
             typ_func    = types.get_method_function(typ)
@@ -1364,12 +1439,23 @@ class Inferencer(algorithm.Visitor):
                                                     other_node=node.args[0])
                     self._unify(node.type, ret, node.loc, None)
                     return
+        if types.is_subkernel(typ_func) and typ_func.sid not in self.subkernel_arg_types:
+            self.subkernel_arg_types[typ_func.sid] = []
 
         for actualarg, (formalname, formaltyp) in \
                 zip(node.args, list(typ_args.items()) + list(typ_optargs.items())):
             self._unify(actualarg.type, formaltyp,
                         actualarg.loc, None)
             passed_args[formalname] = actualarg.loc
+            if types.is_subkernel(typ_func):
+                if types.is_instance(actualarg.type):
+                    # objects cannot be passed to subkernels, as rpc code doesn't support them
+                    diag = diagnostic.Diagnostic("error",
+                        "argument '{name}' of type: {typ} is not supported in subkernels",
+                        {"name": formalname, "typ": actualarg.type},
+                        actualarg.loc, [])
+                    self.engine.process(diag)
+                self.subkernel_arg_types[typ_func.sid].append((formalname, formaltyp))
 
         for keyword in node.keywords:
             if keyword.arg in passed_args:
@@ -1400,7 +1486,7 @@ class Inferencer(algorithm.Visitor):
             passed_args[keyword.arg] = keyword.arg_loc
 
         for formalname in typ_args:
-            if formalname not in passed_args:
+            if formalname not in passed_args and not node.remote_fn:
                 note = diagnostic.Diagnostic("note",
                     "the called function is of type {type}",
                     {"type": types.TypePrinter().name(node.func.type)},

artiq/compiler/transforms/iodelay_estimator.py

@@ -280,7 +280,7 @@ class IODelayEstimator(algorithm.Visitor):
                                   context="as an argument for delay_mu()")
             call_delay = value
         elif not types.is_builtin(typ):
-            if types.is_function(typ) or types.is_rpc(typ):
+            if types.is_function(typ) or types.is_rpc(typ) or types.is_subkernel(typ):
                 offset = 0
             elif types.is_method(typ):
                 offset = 1
@@ -288,7 +288,7 @@ class IODelayEstimator(algorithm.Visitor):
             else:
                 assert False
 
-            if types.is_rpc(typ):
+            if types.is_rpc(typ) or types.is_subkernel(typ):
                 call_delay = iodelay.Const(0)
             else:
                 delay = typ.find().delay.find()
@@ -311,6 +311,7 @@ class IODelayEstimator(algorithm.Visitor):
                         args[arg_name] = arg_node
 
                     free_vars = delay.duration.free_vars()
+                    try:
                         node.arg_exprs = {
                             arg: self.evaluate(args[arg], abort=abort,
                                             context="in the expression for argument '{}' "
@@ -318,6 +319,12 @@ class IODelayEstimator(algorithm.Visitor):
                             for arg in free_vars
                         }
                         call_delay = delay.duration.fold(node.arg_exprs)
+                    except KeyError as e:
+                        if getattr(node, "remote_fn", False):
+                            note = diagnostic.Diagnostic("note",
+                                "function called here", {},
+                                node.loc)
+                            self.abort("due to arguments passed remotely", node.loc, note)
                 else:
                     assert False
         else:

artiq/compiler/transforms/llvm_ir_generator.py

@@ -171,11 +171,26 @@ class LLVMIRGenerator:
         self.llfunction = None
         self.llmap = {}
         self.llobject_map = {}
+        self.llpred_map = {}
         self.phis = []
         self.debug_info_emitter = DebugInfoEmitter(self.llmodule)
         self.empty_metadata = self.llmodule.add_metadata([])
         self.quote_fail_msg = None
 
+        # Maximum alignment required according to the target platform ABI. As this is
+        # not directly exposed by LLVM, just take the maximum across all the "big"
+        # elementary types we use. (Vector types, should we ever support them, are
+        # likely contenders for even larger alignment requirements.)
+        self.max_target_alignment = max(map(
+            lambda t: self.abi_layout_info.get_size_align(t)[1],
+            [lli64, lldouble, llptr]
+        ))
+
+    def add_pred(self, pred, block):
+        if block not in self.llpred_map:
+            self.llpred_map[block] = set()
+        self.llpred_map[block].add(pred)
+
     def needs_sret(self, lltyp, may_be_large=True):
         if isinstance(lltyp, ll.VoidType):
             return False
@@ -200,7 +215,7 @@ class LLVMIRGenerator:
         typ = typ.find()
         if types.is_tuple(typ):
             return ll.LiteralStructType([self.llty_of_type(eltty) for eltty in typ.elts])
-        elif types.is_rpc(typ) or types.is_external_function(typ):
+        elif types.is_rpc(typ) or types.is_external_function(typ) or types.is_subkernel(typ):
             if for_return:
                 return llvoid
             else:
@@ -247,7 +262,10 @@ class LLVMIRGenerator:
             return ll.LiteralStructType([llbufferty, llshapety])
         elif builtins.is_listish(typ):
             lleltty = self.llty_of_type(builtins.get_iterable_elt(typ))
-            return ll.LiteralStructType([lleltty.as_pointer(), lli32])
+            lltyp = ll.LiteralStructType([lleltty.as_pointer(), lli32])
+            if builtins.is_list(typ):
+                lltyp = lltyp.as_pointer()
+            return lltyp
         elif builtins.is_range(typ):
             lleltty = self.llty_of_type(builtins.get_iterable_elt(typ))
             return ll.LiteralStructType([lleltty, lleltty, lleltty])
@@ -326,8 +344,8 @@ class LLVMIRGenerator:
             else:
                 value = const.value
 
-            llptr = self.llstr_of_str(const.value, linkage="private", unnamed_addr=True)
+            llptr = self.llstr_of_str(value, linkage="private", unnamed_addr=True)
-            lllen = ll.Constant(lli32, len(const.value))
+            lllen = ll.Constant(lli32, len(value))
             return ll.Constant(llty, (llptr, lllen))
         else:
             assert False
@@ -367,7 +385,9 @@ class LLVMIRGenerator:
             llty = ll.FunctionType(lli32, [], var_arg=True)
         elif name == "__artiq_raise":
             llty = ll.FunctionType(llvoid, [self.llty_of_type(builtins.TException())])
-        elif name == "__artiq_reraise":
+        elif name == "__artiq_resume":
+            llty = ll.FunctionType(llvoid, [])
+        elif name == "__artiq_end_catch":
             llty = ll.FunctionType(llvoid, [])
         elif name == "memcmp":
             llty = ll.FunctionType(lli32, [llptr, llptr, lli32])
@@ -378,6 +398,15 @@ class LLVMIRGenerator:
         elif name == "rpc_recv":
             llty = ll.FunctionType(lli32, [llptr])
 
+        elif name == "subkernel_send_message":
+            llty = ll.FunctionType(llvoid, [lli32, lli8, llsliceptr, llptrptr])
+        elif name == "subkernel_load_run":
+            llty = ll.FunctionType(llvoid, [lli32, lli1])
+        elif name == "subkernel_await_finish":
+            llty = ll.FunctionType(llvoid, [lli32, lli64])
+        elif name == "subkernel_await_message":
+            llty = ll.FunctionType(lli8, [lli32, lli64, llsliceptr, lli8, lli8])
+
         # with now-pinning
         elif name == "now":
             llty = lli64
@@ -395,7 +424,7 @@ class LLVMIRGenerator:
 
         if isinstance(llty, ll.FunctionType):
             llglobal = ll.Function(self.llmodule, llty, name)
-            if name in ("__artiq_raise", "__artiq_reraise", "llvm.trap"):
+            if name in ("__artiq_raise", "__artiq_resume", "llvm.trap"):
                 llglobal.attributes.add("noreturn")
             if name in ("rtio_log", "rpc_send", "rpc_send_async",
                         self.target.print_function):
@@ -653,6 +682,28 @@ class LLVMIRGenerator:
             self.llbuilder = ll.IRBuilder()
             llblock_map = {}
 
+            # this is the predecessor map, from basic block to the set of its
+            # predecessors
+            # handling for branch and cbranch is here, and the handling of
+            # indirectbr and landingpad are in their respective process_*
+            # function
+            self.llpred_map = llpred_map = {}
+            branch_fn = self.llbuilder.branch
+            cbranch_fn = self.llbuilder.cbranch
+            def override_branch(block):
+                nonlocal self, branch_fn
+                self.add_pred(self.llbuilder.basic_block, block)
+                return branch_fn(block)
+
+            def override_cbranch(pred, bbif, bbelse):
+                nonlocal self, cbranch_fn
+                self.add_pred(self.llbuilder.basic_block, bbif)
+                self.add_pred(self.llbuilder.basic_block, bbelse)
+                return cbranch_fn(pred, bbif, bbelse)
+
+            self.llbuilder.branch = override_branch
+            self.llbuilder.cbranch = override_cbranch
+
             if not func.is_generated:
                 lldisubprogram = self.debug_info_emitter.emit_subprogram(func, self.llfunction)
                 self.llfunction.set_metadata('dbg', lldisubprogram)
@@ -675,6 +726,10 @@ class LLVMIRGenerator:
             # Third, translate all instructions.
             for block in func.basic_blocks:
                 self.llbuilder.position_at_end(self.llmap[block])
+                old_block = None
+                if len(block.instructions) == 1 and \
+                    isinstance(block.instructions[0], ir.LandingPad):
+                    old_block = self.llbuilder.basic_block
                 for insn in block.instructions:
                     if insn.loc is not None and not func.is_generated:
                         self.llbuilder.debug_metadata = \
@@ -689,11 +744,27 @@ class LLVMIRGenerator:
                 # instruction so that the result spans several LLVM basic
                 # blocks. This only really matters for phis, which are thus
                 # using a different map (the following one).
+                if old_block is None:
                     llblock_map[block] = self.llbuilder.basic_block
+                else:
+                    llblock_map[block] = old_block
 
             # Fourth, add incoming values to phis.
             for phi, llphi in self.phis:
                 for value, block in phi.incoming():
+                    if isinstance(phi.type, builtins.TException):
+                        # a hack to patch phi from landingpad
+                        # because landingpad is a single bb in artiq IR, but
+                        # generates multiple bb, we need to find out the
+                        # predecessor to figure out the actual bb
+                        landingpad = llblock_map[block]
+                        for pred in llpred_map[llphi.parent]:
+                            if pred in llpred_map and landingpad in llpred_map[pred]:
+                                llphi.add_incoming(self.map(value), pred)
+                                break
+                        else:
+                            llphi.add_incoming(self.map(value), landingpad)
+                    else:
                         llphi.add_incoming(self.map(value), llblock_map[block])
         finally:
             self.function_flags = None
@@ -732,8 +803,19 @@ class LLVMIRGenerator:
             llalloc = self.llbuilder.alloca(lleltty, size=llsize)
             if types._is_pointer(insn.type):
                 return llalloc
+            if builtins.is_list(insn.type):
+                llvalue = self.llbuilder.alloca(self.llty_of_type(insn.type).pointee, size=1)
+                self.llbuilder.store(llalloc, self.llbuilder.gep(llvalue,
+                                                                 [self.llindex(0),
+                                                                  self.llindex(0)],
+                                                                 inbounds=True))
+                self.llbuilder.store(llsize, self.llbuilder.gep(llvalue,
+                                                                 [self.llindex(0),
+                                                                  self.llindex(1)],
+                                                                 inbounds=True))
+            else:
                 llvalue = ll.Constant(self.llty_of_type(insn.type), ll.Undefined)
-            llvalue = self.llbuilder.insert_value(llvalue, llalloc, 0, name=insn.name)
+                llvalue = self.llbuilder.insert_value(llvalue, llalloc, 0)
                 llvalue = self.llbuilder.insert_value(llvalue, llsize, 1)
             return llvalue
         elif (not builtins.is_allocated(insn.type) or ir.is_keyword(insn.type)
@@ -801,6 +883,53 @@ class LLVMIRGenerator:
             llvalue = self.llbuilder.bitcast(llvalue, llptr.type.pointee)
         return self.llbuilder.store(llvalue, llptr)
 
+    def process_GetArgFromRemote(self, insn):
+        llstackptr = self.llbuilder.call(self.llbuiltin("llvm.stacksave"), [],
+                                         name="subkernel.arg.stack")
+        llval = self._build_rpc_recv(insn.arg_type, llstackptr)
+        return llval
+
+    def process_GetOptArgFromRemote(self, insn):
+        # optarg = index < rcv_count ? Some(rcv_recv()) : None
+        llhead = self.llbuilder.basic_block
+        llrcv = self.llbuilder.append_basic_block(name="optarg.get.{}".format(insn.arg_name))
+        
+        # argument received
+        self.llbuilder.position_at_end(llrcv)
+        llstackptr = self.llbuilder.call(self.llbuiltin("llvm.stacksave"), [],
+                                         name="subkernel.arg.stack")
+        llval = self._build_rpc_recv(insn.arg_type, llstackptr)
+        llrpcretblock = self.llbuilder.basic_block  # 'return' from rpc_recv, will be needed later
+        
+        # create the tail block, needs to be after the rpc recv tail block
+        lltail = self.llbuilder.append_basic_block(name="optarg.tail.{}".format(insn.arg_name))
+        self.llbuilder.branch(lltail)
+
+        # go back to head to add a branch to the tail
+        self.llbuilder.position_at_end(llhead)
+        llargrcvd = self.llbuilder.icmp_unsigned("<", self.map(insn.index), self.map(insn.rcv_count))
+        self.llbuilder.cbranch(llargrcvd, llrcv, lltail)
+
+        # argument not received/after arg recvd
+        self.llbuilder.position_at_end(lltail)
+
+        llargtype = self.llty_of_type(insn.arg_type)
+
+        llphi_arg_present = self.llbuilder.phi(lli1, name="optarg.phi.present.{}".format(insn.arg_name))
+        llphi_arg = self.llbuilder.phi(llargtype, name="optarg.phi.{}".format(insn.arg_name))
+
+        llphi_arg_present.add_incoming(ll.Constant(lli1, 0), llhead)
+        llphi_arg.add_incoming(ll.Constant(llargtype, ll.Undefined), llhead)
+
+        llphi_arg_present.add_incoming(ll.Constant(lli1, 1), llrpcretblock)
+        llphi_arg.add_incoming(llval, llrpcretblock)
+        
+        lloptarg = ll.Constant(ll.LiteralStructType([lli1, llargtype]), ll.Undefined)
+        lloptarg = self.llbuilder.insert_value(lloptarg, llphi_arg_present, 0)
+        lloptarg = self.llbuilder.insert_value(lloptarg, llphi_arg, 1)
+
+        return lloptarg
+
     def attr_index(self, typ, attr):
         return list(typ.attributes.keys()).index(attr)
 
@@ -825,8 +954,8 @@ class LLVMIRGenerator:
     def get_global_closure_ptr(self, typ, attr):
         closure_type = typ.attributes[attr]
         assert types.is_constructor(typ)
-        assert types.is_function(closure_type) or types.is_rpc(closure_type)
+        assert types.is_function(closure_type) or types.is_rpc(closure_type) or types.is_subkernel(closure_type)
-        if types.is_external_function(closure_type) or types.is_rpc(closure_type):
+        if types.is_external_function(closure_type) or types.is_rpc(closure_type) or types.is_subkernel(closure_type):
             return None
 
         llty = self.llty_of_type(typ.attributes[attr])
@@ -938,8 +1067,14 @@ class LLVMIRGenerator:
     def process_Offset(self, insn):
         base, idx = insn.base(), insn.index()
         llelts, llidx = map(self.map, (base, idx))
-        if not types._is_pointer(base.type):
+        if builtins.is_listish(base.type):
             # This is list-ish.
+            if builtins.is_list(base.type):
+                llelts = self.llbuilder.load(self.llbuilder.gep(llelts,
+                                                                [self.llindex(0),
+                                                                 self.llindex(0)],
+                                                                inbounds=True))
+            else:
                 llelts = self.llbuilder.extract_value(llelts, 0)
         llelt = self.llbuilder.gep(llelts, [llidx], inbounds=True)
         return llelt
@@ -954,8 +1089,14 @@ class LLVMIRGenerator:
     def process_SetElem(self, insn):
         base, idx = insn.base(), insn.index()
         llelts, llidx = map(self.map, (base, idx))
-        if not types._is_pointer(base.type):
+        if builtins.is_listish(base.type):
             # This is list-ish.
+            if builtins.is_list(base.type):
+                llelts = self.llbuilder.load(self.llbuilder.gep(llelts,
+                                                                [self.llindex(0),
+                                                                 self.llindex(0)],
+                                                                inbounds=True))
+            else:
                 llelts = self.llbuilder.extract_value(llelts, 0)
         llelt = self.llbuilder.gep(llelts, [llidx], inbounds=True)
         return self.llbuilder.store(self.map(insn.value()), llelt)
@@ -1102,6 +1243,11 @@ class LLVMIRGenerator:
         lllhs, llrhs = map(self.map, (insn.lhs(), insn.rhs()))
         assert lllhs.type == llrhs.type
 
+        if isinstance(lllhs.type, ll.PointerType) and \
+                isinstance(lllhs.type.pointee, ll.LiteralStructType):
+            lllhs = self.llbuilder.load(lllhs)
+            llrhs = self.llbuilder.load(llrhs)
+
         if isinstance(lllhs.type, ll.IntType):
             return self.llbuilder.icmp_signed(op, lllhs, llrhs,
                                                 name=insn.name)
@@ -1172,6 +1318,11 @@ class LLVMIRGenerator:
                 shape = self.llbuilder.extract_value(self.map(collection),
                     self.attr_index(collection.type, "shape"))
                 return self.llbuilder.extract_value(shape, 0)
+            elif builtins.is_list(collection.type):
+                return self.llbuilder.load(self.llbuilder.gep(self.map(collection),
+                                                              [self.llindex(0),
+                                                               self.llindex(1)]))
+            else:
                 return self.llbuilder.extract_value(self.map(collection), 1)
         elif insn.op in ("printf", "rtio_log"):
             # We only get integers, floats, pointers and strings here.
@@ -1247,9 +1398,38 @@ class LLVMIRGenerator:
                 return llstore_lo
             else:
                 return self.llbuilder.call(self.llbuiltin("delay_mu"), [llinterval])
+        elif insn.op == "end_catch":
+            return self.llbuilder.call(self.llbuiltin("__artiq_end_catch"), [])
+        elif insn.op == "subkernel_await_finish":
+            llsid = self.map(insn.operands[0])
+            lltimeout = self.map(insn.operands[1])
+            return self.llbuilder.call(self.llbuiltin("subkernel_await_finish"), [llsid, lltimeout],
+                                       name="subkernel.await.finish")
+        elif insn.op == "subkernel_retrieve_return":
+            llsid = self.map(insn.operands[0])
+            lltimeout = self.map(insn.operands[1])
+            lltagptr = self._build_subkernel_tags([insn.type])
+            self.llbuilder.call(self.llbuiltin("subkernel_await_message"), 
+                                [llsid, lltimeout, lltagptr, ll.Constant(lli8, 1), ll.Constant(lli8, 1)],
+                                name="subkernel.await.message")
+            llstackptr = self.llbuilder.call(self.llbuiltin("llvm.stacksave"), [],
+                                             name="subkernel.arg.stack")
+            return self._build_rpc_recv(insn.type, llstackptr)
+        elif insn.op == "subkernel_preload":
+            llsid = self.map(insn.operands[0])
+            return self.llbuilder.call(self.llbuiltin("subkernel_load_run"), [llsid, ll.Constant(lli1, 0)], 
+                                name="subkernel.preload")
         else:
             assert False
 
+    def process_SubkernelAwaitArgs(self, insn):
+        llmin = self.map(insn.operands[0])
+        llmax = self.map(insn.operands[1])
+        lltagptr = self._build_subkernel_tags(insn.arg_types)
+        return self.llbuilder.call(self.llbuiltin("subkernel_await_message"), 
+                                    [ll.Constant(lli32, 0), ll.Constant(lli64, 10_000), lltagptr, llmin, llmax],
+                                    name="subkernel.await.args")
+
     def process_Closure(self, insn):
         llenv = self.map(insn.environment())
         llenv = self.llbuilder.bitcast(llenv, llptr)
@@ -1271,11 +1451,24 @@ class LLVMIRGenerator:
         else:
             llfun = self.map(insn.static_target_function)
         llenv     = self.llbuilder.extract_value(llclosure, 0, name="env.fun")
-        return llfun, [llenv] + list(llargs), {}
+        return llfun, [llenv] + list(llargs), {}, None
 
     def _prepare_ffi_call(self, insn):
         llargs = []
         llarg_attrs = {}
+
+        stack_save_needed = False
+        for i, arg in enumerate(insn.arguments()):
+            llarg = self.map(arg)            
+            if isinstance(llarg.type, (ll.LiteralStructType, ll.IdentifiedStructType)):
+                stack_save_needed = True
+                break
+
+        if stack_save_needed:
+            llcallstackptr = self.llbuilder.call(self.llbuiltin("llvm.stacksave"), [])
+        else:
+            llcallstackptr = None
+
         for i, arg in enumerate(insn.arguments()):
             llarg = self.map(arg)
             if isinstance(llarg.type, (ll.LiteralStructType, ll.IdentifiedStructType)):
@@ -1308,10 +1501,83 @@ class LLVMIRGenerator:
                 llfun.args[idx].add_attribute(attr)
             if 'nounwind' in insn.target_function().type.flags:
                 llfun.attributes.add('nounwind')
-            if 'nowrite' in insn.target_function().type.flags:
+            if 'nowrite' in insn.target_function().type.flags and not is_sret:
+                # Even if "nowrite" is correct from the user's perspective (doesn't
+                # access any other memory observable to ARTIQ Python), this isn't
+                # true on the LLVM IR level for sret return values.
                 llfun.attributes.add('inaccessiblememonly')
 
-        return llfun, list(llargs), llarg_attrs
+        return llfun, list(llargs), llarg_attrs, llcallstackptr
+
+    def _build_subkernel_tags(self, tag_list):
+        def ret_error_handler(typ):
+            printer = types.TypePrinter()
+            note = diagnostic.Diagnostic("note",
+                "value of type {type}",
+                {"type": printer.name(typ)},
+                fun_loc)
+            diag = diagnostic.Diagnostic("error",
+                "type {type} is not supported in subkernels",
+                {"type": printer.name(fun_type.ret)},
+                fun_loc, notes=[note])
+            self.engine.process(diag)
+        tag = b"".join([ir.rpc_tag(arg_type, ret_error_handler) for arg_type in tag_list])
+        lltag = self.llconst_of_const(ir.Constant(tag, builtins.TStr()))
+        lltagptr = self.llbuilder.alloca(lltag.type)
+        self.llbuilder.store(lltag, lltagptr)
+        return lltagptr
+
+    def _build_rpc_recv(self, ret, llstackptr, llnormalblock=None, llunwindblock=None):
+        # T result = {
+        #   void *ret_ptr = alloca(sizeof(T));
+        #   void *ptr = ret_ptr;
+        #   loop: int size = rpc_recv(ptr);
+        #   // Non-zero: Provide `size` bytes of extra storage for variable-length data.
+        #   if(size) { ptr = alloca(size); goto loop; }
+        #   else *(T*)ret_ptr
+        # }
+        llprehead   = self.llbuilder.basic_block
+        llhead      = self.llbuilder.append_basic_block(name="rpc.head")
+        if llunwindblock:
+            llheadu = self.llbuilder.append_basic_block(name="rpc.head.unwind")
+        llalloc     = self.llbuilder.append_basic_block(name="rpc.continue")
+        lltail      = self.llbuilder.append_basic_block(name="rpc.tail")
+
+        llretty = self.llty_of_type(ret)
+        llslot = self.llbuilder.alloca(llretty, name="rpc.ret.alloc")
+        llslotgen = self.llbuilder.bitcast(llslot, llptr, name="rpc.ret.ptr")
+        self.llbuilder.branch(llhead)
+
+        self.llbuilder.position_at_end(llhead)
+        llphi = self.llbuilder.phi(llslotgen.type, name="rpc.ptr")
+        llphi.add_incoming(llslotgen, llprehead)
+        if llunwindblock:
+            llsize = self.llbuilder.invoke(self.llbuiltin("rpc_recv"), [llphi],
+                                           llheadu, llunwindblock,
+                                           name="rpc.size.next")
+            self.llbuilder.position_at_end(llheadu)
+        else:
+            llsize = self.llbuilder.call(self.llbuiltin("rpc_recv"), [llphi],
+                                         name="rpc.size.next")
+        lldone = self.llbuilder.icmp_unsigned('==', llsize, ll.Constant(llsize.type, 0),
+                                              name="rpc.done")
+        self.llbuilder.cbranch(lldone, lltail, llalloc)
+
+        self.llbuilder.position_at_end(llalloc)
+        llalloca = self.llbuilder.alloca(lli8, llsize, name="rpc.alloc")
+        llalloca.align = self.max_target_alignment
+        llphi.add_incoming(llalloca, llalloc)
+        self.llbuilder.branch(llhead)
+
+        self.llbuilder.position_at_end(lltail)
+        llret = self.llbuilder.load(llslot, name="rpc.ret")
+        if not ret.fold(False, lambda r, t: r or builtins.is_allocated(t)):
+            # We didn't allocate anything except the slot for the value itself.
+            # Don't waste stack space.
+            self.llbuilder.call(self.llbuiltin("llvm.stackrestore"), [llstackptr])
+        if llnormalblock:
+            self.llbuilder.branch(llnormalblock)
+        return llret
 
     def _build_rpc(self, fun_loc, fun_type, args, llnormalblock, llunwindblock):
         llservice = ll.Constant(lli32, fun_type.service)
@@ -1388,57 +1654,103 @@ class LLVMIRGenerator:
 
             return ll.Undefined
 
-        # T result = {
+        llret = self._build_rpc_recv(fun_type.ret, llstackptr, llnormalblock, llunwindblock)
-        #   void *ret_ptr = alloca(sizeof(T));
-        #   void *ptr = ret_ptr;
-        #   loop: int size = rpc_recv(ptr);
-        #   // Non-zero: Provide `size` bytes of extra storage for variable-length data.
-        #   if(size) { ptr = alloca(size); goto loop; }
-        #   else *(T*)ret_ptr
-        # }
-        llprehead   = self.llbuilder.basic_block
-        llhead      = self.llbuilder.append_basic_block(name="rpc.head")
-        if llunwindblock:
-            llheadu = self.llbuilder.append_basic_block(name="rpc.head.unwind")
-        llalloc     = self.llbuilder.append_basic_block(name="rpc.continue")
-        lltail      = self.llbuilder.append_basic_block(name="rpc.tail")
 
-        llretty = self.llty_of_type(fun_type.ret)
-        llslot = self.llbuilder.alloca(llretty, name="rpc.ret.alloc")
-        llslotgen = self.llbuilder.bitcast(llslot, llptr, name="rpc.ret.ptr")
-        self.llbuilder.branch(llhead)
-
-        self.llbuilder.position_at_end(llhead)
-        llphi = self.llbuilder.phi(llslotgen.type, name="rpc.ptr")
-        llphi.add_incoming(llslotgen, llprehead)
-        if llunwindblock:
-            llsize = self.llbuilder.invoke(self.llbuiltin("rpc_recv"), [llphi],
-                                           llheadu, llunwindblock,
-                                           name="rpc.size.next")
-            self.llbuilder.position_at_end(llheadu)
-        else:
-            llsize = self.llbuilder.call(self.llbuiltin("rpc_recv"), [llphi],
-                                         name="rpc.size.next")
-        lldone = self.llbuilder.icmp_unsigned('==', llsize, ll.Constant(llsize.type, 0),
-                                              name="rpc.done")
-        self.llbuilder.cbranch(lldone, lltail, llalloc)
-
-        self.llbuilder.position_at_end(llalloc)
-        llalloca = self.llbuilder.alloca(lli8, llsize, name="rpc.alloc")
-        llalloca.align = 4 # maximum alignment required by OR1K ABI
-        llphi.add_incoming(llalloca, llalloc)
-        self.llbuilder.branch(llhead)
-
-        self.llbuilder.position_at_end(lltail)
-        llret = self.llbuilder.load(llslot, name="rpc.ret")
-        if not fun_type.ret.fold(False, lambda r, t: r or builtins.is_allocated(t)):
-            # We didn't allocate anything except the slot for the value itself.
-            # Don't waste stack space.
-            self.llbuilder.call(self.llbuiltin("llvm.stackrestore"), [llstackptr])
-        if llnormalblock:
-            self.llbuilder.branch(llnormalblock)
         return llret
 
+    def _build_subkernel_call(self, fun_loc, fun_type, args):
+        llsid = ll.Constant(lli32, fun_type.sid)
+        tag = b""
+
+        for arg in args:
+            def arg_error_handler(typ):
+                printer = types.TypePrinter()
+                note = diagnostic.Diagnostic("note",
+                    "value of type {type}",
+                    {"type": printer.name(typ)},
+                    arg.loc)
+                diag = diagnostic.Diagnostic("error",
+                    "type {type} is not supported in subkernel calls",
+                    {"type": printer.name(arg.type)},
+                    arg.loc, notes=[note])
+                self.engine.process(diag)
+            tag += ir.rpc_tag(arg.type, arg_error_handler)
+        tag += b":"
+
+        # run the kernel first
+        self.llbuilder.call(self.llbuiltin("subkernel_load_run"), [llsid, ll.Constant(lli1, 1)])
+
+        # arg sent in the same vein as RPC
+        llstackptr = self.llbuilder.call(self.llbuiltin("llvm.stacksave"), [],
+                                         name="subkernel.stack")
+
+        lltag = self.llconst_of_const(ir.Constant(tag, builtins.TStr()))
+        lltagptr = self.llbuilder.alloca(lltag.type)
+        self.llbuilder.store(lltag, lltagptr)
+
+        if args:
+            # only send args if there's anything to send, 'self' is excluded
+            llargs = self.llbuilder.alloca(llptr, ll.Constant(lli32, len(args)),
+                                        name="subkernel.args")
+            for index, arg in enumerate(args):
+                if builtins.is_none(arg.type):
+                    llargslot = self.llbuilder.alloca(llunit,
+                                                    name="subkernel.arg{}".format(index))
+                else:
+                    llarg = self.map(arg)
+                    llargslot = self.llbuilder.alloca(llarg.type,
+                                                    name="subkernel.arg{}".format(index))
+                    self.llbuilder.store(llarg, llargslot)
+                llargslot = self.llbuilder.bitcast(llargslot, llptr)
+
+                llargptr = self.llbuilder.gep(llargs, [ll.Constant(lli32, index)])
+                self.llbuilder.store(llargslot, llargptr)
+
+            llargcount = ll.Constant(lli8, len(args))
+
+            self.llbuilder.call(self.llbuiltin("subkernel_send_message"),
+                                [llsid, llargcount, lltagptr, llargs])
+            self.llbuilder.call(self.llbuiltin("llvm.stackrestore"), [llstackptr])
+
+        return llsid
+
+    def _build_subkernel_return(self, insn):
+        # builds a remote return.
+        # unlike args, return only sends one thing.
+        if builtins.is_none(insn.value().type):
+            # do not waste time and bandwidth on Nones
+            return
+
+        def ret_error_handler(typ):
+            printer = types.TypePrinter()
+            note = diagnostic.Diagnostic("note",
+                "value of type {type}",
+                {"type": printer.name(typ)},
+                fun_loc)
+            diag = diagnostic.Diagnostic("error",
+                "return type {type} is not supported in subkernel returns",
+                {"type": printer.name(fun_type.ret)},
+                fun_loc, notes=[note])
+            self.engine.process(diag)
+        tag = ir.rpc_tag(insn.value().type, ret_error_handler)
+        tag += b":"
+        lltag = self.llconst_of_const(ir.Constant(tag, builtins.TStr()))
+        lltagptr = self.llbuilder.alloca(lltag.type)
+        self.llbuilder.store(lltag, lltagptr)
+
+        llrets = self.llbuilder.alloca(llptr, ll.Constant(lli32, 1),
+                                    name="subkernel.return")    
+        llret = self.map(insn.value())
+        llretslot = self.llbuilder.alloca(llret.type, name="subkernel.retval")
+        self.llbuilder.store(llret, llretslot)
+        llretslot = self.llbuilder.bitcast(llretslot, llptr)
+        self.llbuilder.store(llretslot, llrets)
+
+        llsid = ll.Constant(lli32, 0)  # return goes back to master, sid is ignored
+        lltagcount = ll.Constant(lli8, 1)  # only one thing is returned
+        self.llbuilder.call(self.llbuiltin("subkernel_send_message"),
+                            [llsid, lltagcount, lltagptr, llrets])
+
     def process_Call(self, insn):
         functiontyp = insn.target_function().type
         if types.is_rpc(functiontyp):
@@ -1446,10 +1758,14 @@ class LLVMIRGenerator:
                                    functiontyp,
                                    insn.arguments(),
                                    llnormalblock=None, llunwindblock=None)
+        elif types.is_subkernel(functiontyp):
+            return self._build_subkernel_call(insn.target_function().loc,
+                                              functiontyp,
+                                              insn.arguments())
         elif types.is_external_function(functiontyp):
-            llfun, llargs, llarg_attrs = self._prepare_ffi_call(insn)
+            llfun, llargs, llarg_attrs, llcallstackptr = self._prepare_ffi_call(insn)
         else:
-            llfun, llargs, llarg_attrs = self._prepare_closure_call(insn)
+            llfun, llargs, llarg_attrs, llcallstackptr = self._prepare_closure_call(insn)
 
         if self.has_sret(functiontyp):
             llstackptr = self.llbuilder.call(self.llbuiltin("llvm.stacksave"), [])
@@ -1468,6 +1784,9 @@ class LLVMIRGenerator:
                 # {} elsewhere.
                 llresult = ll.Constant(llunit, [])
 
+        if llcallstackptr != None:
+            self.llbuilder.call(self.llbuiltin("llvm.stackrestore"), [llcallstackptr])
+
         return llresult
 
     def process_Invoke(self, insn):
@@ -1479,10 +1798,15 @@ class LLVMIRGenerator:
                                    functiontyp,
                                    insn.arguments(),
                                    llnormalblock, llunwindblock)
+        elif types.is_subkernel(functiontyp):
+            return self._build_subkernel_call(insn.target_function().loc,
+                                         functiontyp,
+                                         insn.arguments(),
+                                         llnormalblock, llunwindblock)
         elif types.is_external_function(functiontyp):
-            llfun, llargs, llarg_attrs = self._prepare_ffi_call(insn)
+            llfun, llargs, llarg_attrs, llcallstackptr = self._prepare_ffi_call(insn)
         else:
-            llfun, llargs, llarg_attrs = self._prepare_closure_call(insn)
+            llfun, llargs, llarg_attrs, llcallstackptr = self._prepare_closure_call(insn)
 
         if self.has_sret(functiontyp):
             llstackptr = self.llbuilder.call(self.llbuiltin("llvm.stacksave"), [])
@@ -1504,6 +1828,9 @@ class LLVMIRGenerator:
             # The !tbaa metadata is not legal to use with the invoke instruction,
             # so unlike process_Call, we do not set it here.
 
+        if llcallstackptr != None:
+            self.llbuilder.call(self.llbuiltin("llvm.stackrestore"), [llcallstackptr])
+
         return llresult
 
     def _quote_listish_to_llglobal(self, value, elt_type, path, kind_name):
@@ -1554,7 +1881,8 @@ class LLVMIRGenerator:
                 attrvalue = getattr(value, attr)
                 is_class_function = (types.is_constructor(typ) and
                                      types.is_function(typ.attributes[attr]) and
-                                     not types.is_external_function(typ.attributes[attr]))
+                                     not types.is_external_function(typ.attributes[attr]) and
+                                     not types.is_subkernel(typ.attributes[attr]))
                 if is_class_function:
                     attrvalue = self.embedding_map.specialize_function(typ.instance, attrvalue)
                 if not (types.is_instance(typ) and attr in typ.constant_attributes):
@@ -1625,6 +1953,13 @@ class LLVMIRGenerator:
             assert isinstance(value, (list, numpy.ndarray)), fail_msg
             elt_type  = builtins.get_iterable_elt(typ)
             lleltsptr = self._quote_listish_to_llglobal(value, elt_type, path, typ.find().name)
+            if builtins.is_list(typ):
+                llconst   = ll.Constant(llty.pointee, [lleltsptr, ll.Constant(lli32, len(value))])
+                name = self.llmodule.scope.deduplicate("quoted.{}".format(typ.find().name))
+                llglobal = ll.GlobalVariable(self.llmodule, llconst.type, name)
+                llglobal.initializer = llconst
+                llglobal.linkage = "private"
+                return llglobal
             llconst   = ll.Constant(llty, [lleltsptr, ll.Constant(lli32, len(value))])
             return llconst
         elif types.is_tuple(typ):
@@ -1632,7 +1967,8 @@ class LLVMIRGenerator:
             llelts = [self._quote(v, t, lambda: path() + [str(i)])
                 for i, (v, t) in enumerate(zip(value, typ.elts))]
             return ll.Constant(llty, llelts)
-        elif types.is_rpc(typ) or types.is_external_function(typ) or types.is_builtin_function(typ):
+        elif types.is_rpc(typ) or types.is_external_function(typ) or \
+                types.is_builtin_function(typ) or types.is_subkernel(typ):
             # RPC, C and builtin functions have no runtime representation.
             return ll.Constant(llty, ll.Undefined)
         elif types.is_function(typ):
@@ -1678,10 +2014,17 @@ class LLVMIRGenerator:
     def process_IndirectBranch(self, insn):
         llinsn = self.llbuilder.branch_indirect(self.map(insn.target()))
         for dest in insn.destinations():
-            llinsn.add_destination(self.map(dest))
+            dest = self.map(dest)
+            self.add_pred(self.llbuilder.basic_block, dest)
+            if dest not in self.llpred_map:
+                self.llpred_map[dest] = set()
+            self.llpred_map[dest].add(self.llbuilder.basic_block)
+            llinsn.add_destination(dest)
         return llinsn
 
     def process_Return(self, insn):
+        if insn.remote_return:
+            self._build_subkernel_return(insn)
         if builtins.is_none(insn.value().type):
             return self.llbuilder.ret_void()
         else:
@@ -1716,8 +2059,8 @@ class LLVMIRGenerator:
         llexn = self.map(insn.value())
         return self._gen_raise(insn, self.llbuiltin("__artiq_raise"), [llexn])
 
-    def process_Reraise(self, insn):
+    def process_Resume(self, insn):
-        return self._gen_raise(insn, self.llbuiltin("__artiq_reraise"), [])
+        return self._gen_raise(insn, self.llbuiltin("__artiq_resume"), [])
 
     def process_LandingPad(self, insn):
         # Layout on return from landing pad: {%_Unwind_Exception*, %Exception*}
@@ -1726,10 +2069,11 @@ class LLVMIRGenerator:
                                                  cleanup=insn.has_cleanup)
         llrawexn = self.llbuilder.extract_value(lllandingpad, 1)
         llexn = self.llbuilder.bitcast(llrawexn, self.llty_of_type(insn.type))
-        llexnnameptr = self.llbuilder.gep(llexn, [self.llindex(0), self.llindex(0)],
+        llexnidptr = self.llbuilder.gep(llexn, [self.llindex(0), self.llindex(0)],
                                           inbounds=True)
-        llexnname = self.llbuilder.load(llexnnameptr)
+        llexnid = self.llbuilder.load(llexnidptr)
 
+        landingpadbb = self.llbuilder.basic_block
         for target, typ in insn.clauses():
             if typ is None:
                 # we use a null pointer here, similar to how cpp does it
@@ -1742,42 +2086,40 @@ class LLVMIRGenerator:
                         ll.Constant(lli32, 0).inttoptr(llptr)
                     )
                 )
-            else:
-                exnname = "{}:{}".format(typ.id, typ.name)
 
-                llclauseexnname = self.llconst_of_const(
-                    ir.Constant(exnname, builtins.TStr()))
-                llclauseexnnameptr = self.llmodule.globals.get("exn.{}".format(exnname))
-                if llclauseexnnameptr is None:
-                    llclauseexnnameptr = ll.GlobalVariable(self.llmodule, llclauseexnname.type,
-                                                           name="exn.{}".format(exnname))
-                    llclauseexnnameptr.global_constant = True
-                    llclauseexnnameptr.initializer = llclauseexnname
-                    llclauseexnnameptr.linkage = "private"
-                    llclauseexnnameptr.unnamed_addr = True
-                lllandingpad.add_clause(ll.CatchClause(llclauseexnnameptr))
-
-            if typ is None:
                 # typ is None means that we match all exceptions, so no need to
                 # compare
-                self.llbuilder.branch(self.map(target))
+                target = self.map(target)
+                self.add_pred(landingpadbb, target)
+                self.add_pred(landingpadbb, self.llbuilder.basic_block)
+                self.llbuilder.branch(target)
             else:
-                llexnlen       = self.llbuilder.extract_value(llexnname, 1)
+                exnname = "{}:{}".format(typ.id, typ.name)
-                llclauseexnlen = self.llbuilder.extract_value(llclauseexnname, 1)
+                llclauseexnidptr = self.llmodule.globals.get("exn.{}".format(exnname))
-                llmatchinglen  = self.llbuilder.icmp_unsigned('==', llexnlen, llclauseexnlen)
+                exnid = ll.Constant(lli32, self.embedding_map.store_str(exnname))
-                with self.llbuilder.if_then(llmatchinglen):
+                if llclauseexnidptr is None:
-                    llexnptr       = self.llbuilder.extract_value(llexnname, 0)
+                    llclauseexnidptr = ll.GlobalVariable(self.llmodule, lli32,
-                    llclauseexnptr = self.llbuilder.extract_value(llclauseexnname, 0)
+                                                         name="exn.{}".format(exnname))
-                    llcomparedata  = self.llbuilder.call(self.llbuiltin("memcmp"),
+                    llclauseexnidptr.global_constant = True
-                                                         [llexnptr, llclauseexnptr, llexnlen])
+                    llclauseexnidptr.initializer = exnid
-                    llmatchingdata = self.llbuilder.icmp_unsigned('==', llcomparedata,
+                    llclauseexnidptr.linkage = "private"
-                                                                  ll.Constant(lli32, 0))
+                    llclauseexnidptr.unnamed_addr = True
+                lllandingpad.add_clause(ll.CatchClause(llclauseexnidptr))
+                llmatchingdata = self.llbuilder.icmp_unsigned("==", llexnid,
+                                                              exnid)
                 with self.llbuilder.if_then(llmatchingdata):
-                        self.llbuilder.branch(self.map(target))
+                    target = self.map(target)
+                    self.add_pred(landingpadbb, target)
+                    self.add_pred(landingpadbb, self.llbuilder.basic_block)
+                    self.llbuilder.branch(target)
+                self.add_pred(landingpadbb, self.llbuilder.basic_block)
 
         if self.llbuilder.basic_block.terminator is None:
             if insn.has_cleanup:
-                self.llbuilder.branch(self.map(insn.cleanup()))
+                target = self.map(insn.cleanup())
+                self.add_pred(landingpadbb, target)
+                self.add_pred(landingpadbb, self.llbuilder.basic_block)
+                self.llbuilder.branch(target)
             else:
                 self.llbuilder.resume(lllandingpad)
 

artiq/compiler/types.py

@@ -385,6 +385,50 @@ class TRPC(Type):
     def __hash__(self):
         return hash(self.service)
 
+class TSubkernel(TFunction):
+    """
+    A kernel to be run on a satellite.
+
+    :ivar args: (:class:`collections.OrderedDict` of string to :class:`Type`)
+        function arguments
+    :ivar ret: (:class:`Type`)
+        return type
+    :ivar sid: (int) subkernel ID number
+    :ivar destination: (int) satellite destination number
+    """
+
+    attributes = OrderedDict()
+
+    def __init__(self, args, optargs, ret, sid, destination):
+        assert isinstance(ret, Type)
+        super().__init__(args, optargs, ret)
+        self.sid, self.destination = sid, destination
+        self.delay = TFixedDelay(iodelay.Const(0))
+
+    def unify(self, other):
+        if other is self:
+            return
+        if isinstance(other, TSubkernel) and \
+                self.sid == other.sid and \
+                self.destination == other.destination:
+            self.ret.unify(other.ret)
+        elif isinstance(other, TVar):
+            other.unify(self)
+        else:
+            raise UnificationError(self, other)
+
+    def __repr__(self):
+        if getattr(builtins, "__in_sphinx__", False):
+            return str(self)
+        return "artiq.compiler.types.TSubkernel({})".format(repr(self.ret))
+
+    def __eq__(self, other):
+        return isinstance(other, TSubkernel) and \
+                self.sid == other.sid
+
+    def __hash__(self):
+        return hash(self.sid)
+
 class TBuiltin(Type):
     """
     An instance of builtin type. Every instance of a builtin
@@ -644,6 +688,9 @@ def is_function(typ):
 def is_rpc(typ):
     return isinstance(typ.find(), TRPC)
 
+def is_subkernel(typ):
+    return isinstance(typ.find(), TSubkernel)
+
 def is_external_function(typ, name=None):
     typ = typ.find()
     if name is None:
@@ -810,6 +857,10 @@ class TypePrinter(object):
             return "[rpc{} #{}](...)->{}".format(typ.service,
                                                  " async" if typ.is_async else "",
                                                  self.name(typ.ret, depth + 1))
+        elif isinstance(typ, TSubkernel):
+            return "<subkernel{} dest#{}>->{}".format(typ.sid,
+                                                      typ.destination,
+                                                      self.name(typ.ret, depth + 1))
         elif isinstance(typ, TBuiltinFunction):
             return "<function {}>".format(typ.name)
         elif isinstance(typ, (TConstructor, TExceptionConstructor)):

artiq/compiler/validators/escape.py

@@ -102,7 +102,19 @@ class RegionOf(algorithm.Visitor):
         if types.is_external_function(node.func.type, "cache_get"):
             # The cache is borrow checked dynamically
             return Global()
-        else:
+
+        if (types.is_builtin_function(node.func.type, "array")
+              or types.is_builtin_function(node.func.type, "make_array")
+              or types.is_builtin_function(node.func.type, "numpy.transpose")):
+            # While lifetime tracking across function calls in general is currently
+            # broken (see below), these special builtins that allocate an array on
+            # the stack of the caller _always_ allocate regardless of the parameters,
+            # and we can thus handle them without running into the precision issue
+            # mentioned in commit ae999db.
+            return self.visit_allocating(node)
+
+        # FIXME: Return statement missing here, but see m-labs/artiq#1497 and
+        # commit ae999db.
         self.visit_sometimes_allocating(node)
 
     # Value lives as long as the object/container, if it's mutable,

artiq/coredevice/ad53xx.py

@@ -233,7 +233,7 @@ class AD53xx:
     def write_gain_mu(self, channel, gain=0xffff):
         """Program the gain register for a DAC channel.
 
-        The DAC output is not updated until LDAC is pulsed (see :meth load:).
+        The DAC output is not updated until LDAC is pulsed (see :meth:`load`).
         This method advances the timeline by the duration of one SPI transfer.
 
         :param gain: 16-bit gain register value (default: 0xffff)
@@ -245,7 +245,7 @@ class AD53xx:
     def write_offset_mu(self, channel, offset=0x8000):
         """Program the offset register for a DAC channel.
 
-        The DAC output is not updated until LDAC is pulsed (see :meth load:).
+        The DAC output is not updated until LDAC is pulsed (see :meth:`load`).
         This method advances the timeline by the duration of one SPI transfer.
 
         :param offset: 16-bit offset register value (default: 0x8000)
@@ -258,7 +258,7 @@ class AD53xx:
         """Program the DAC offset voltage for a channel.
 
         An offset of +V can be used to trim out a DAC offset error of -V.
-        The DAC output is not updated until LDAC is pulsed (see :meth load:).
+        The DAC output is not updated until LDAC is pulsed (see :meth:`load`).
         This method advances the timeline by the duration of one SPI transfer.
 
         :param voltage: the offset voltage
@@ -270,7 +270,7 @@ class AD53xx:
     def write_dac_mu(self, channel, value):
         """Program the DAC input register for a channel.
 
-        The DAC output is not updated until LDAC is pulsed (see :meth load:).
+        The DAC output is not updated until LDAC is pulsed (see :meth:`load`).
         This method advances the timeline by the duration of one SPI transfer.
         """
         self.bus.write(
@@ -280,7 +280,7 @@ class AD53xx:
     def write_dac(self, channel, voltage):
         """Program the DAC output voltage for a channel.
 
-        The DAC output is not updated until LDAC is pulsed (see :meth load:).
+        The DAC output is not updated until LDAC is pulsed (see :meth:`load`).
         This method advances the timeline by the duration of one SPI transfer.
         """
         self.write_dac_mu(channel, voltage_to_mu(voltage, self.offset_dacs,
@@ -313,7 +313,7 @@ class AD53xx:
 
         If no LDAC device was defined, the LDAC pulse is skipped.
 
-        See :meth load:.
+        See :meth:`load`.
 
         :param values: list of DAC values to program
         :param channels: list of DAC channels to program. If not specified,
@@ -355,7 +355,7 @@ class AD53xx:
         """ Two-point calibration of a DAC channel.
 
         Programs the offset and gain register to trim out DAC errors. Does not
-        take effect until LDAC is pulsed (see :meth load:).
+        take effect until LDAC is pulsed (see :meth:`load`).
 
         Calibration consists of measuring the DAC output voltage for a channel
         with the DAC set to zero-scale (0x0000) and full-scale (0xffff).

artiq/coredevice/ad9154_spi.py

@@ -1,23 +0,0 @@
-from artiq.language.core import kernel
-
-
-class AD9154:
-    """Kernel interface to AD9154 registers, using non-realtime SPI."""
-
-    def __init__(self, dmgr, spi_device, chip_select):
-        self.core = dmgr.get("core")
-        self.bus = dmgr.get(spi_device)
-        self.chip_select = chip_select
-
-    @kernel
-    def setup_bus(self, div=16):
-        self.bus.set_config_mu(0, 24, div, self.chip_select)
-
-    @kernel
-    def write(self, addr, data):
-        self.bus.write((addr << 16) | (data<< 8))
-
-    @kernel
-    def read(self, addr):
-        self.write((1 << 15) | addr, 0)
-        return self.bus.read()

artiq/coredevice/ad9912.py

@@ -25,12 +25,14 @@ class AD9912:
         f_ref/clk_div*pll_n where f_ref is the reference frequency and clk_div
         is the reference clock divider (both set in the parent Urukul CPLD
         instance).
+    :param pll_en: PLL enable bit, set to 0 to bypass PLL (default: 1).
+        Note that when bypassing the PLL the red front panel LED may remain on.
     """
 
     def __init__(self, dmgr, chip_select, cpld_device, sw_device=None,
-                 pll_n=10):
+                 pll_n=10, pll_en=1):
         self.kernel_invariants = {"cpld", "core", "bus", "chip_select",
-                                  "pll_n", "ftw_per_hz"}
+                                  "pll_n", "pll_en", "ftw_per_hz"}
         self.cpld = dmgr.get(cpld_device)
         self.core = self.cpld.core
         self.bus = self.cpld.bus
@@ -39,8 +41,12 @@ class AD9912:
         if sw_device:
             self.sw = dmgr.get(sw_device)
             self.kernel_invariants.add("sw")
+        self.pll_en = pll_en
         self.pll_n = pll_n
+        if pll_en:
             sysclk = self.cpld.refclk / [1, 1, 2, 4][self.cpld.clk_div] * pll_n
+        else:
+            sysclk = self.cpld.refclk
         assert sysclk <= 1e9
         self.ftw_per_hz = 1 / sysclk * (int64(1) << 48)
 
@@ -102,8 +108,10 @@ class AD9912:
             raise ValueError("Urukul AD9912 product id mismatch")
         delay(50 * us)
         # HSTL power down, CMOS power down
-        self.write(AD9912_PWRCNTRL1, 0x80, length=1)
+        pwrcntrl1 = 0x80 | ((~self.pll_en & 1) << 4)
+        self.write(AD9912_PWRCNTRL1, pwrcntrl1, length=1)
         self.cpld.io_update.pulse(2 * us)
+        if self.pll_en:
             self.write(AD9912_N_DIV, self.pll_n // 2 - 2, length=1)
             self.cpld.io_update.pulse(2 * us)
             # I_cp = 375 µA, VCO high range

artiq/coredevice/ad9914.py

@@ -80,6 +80,13 @@ class AD9914:
         self.set_x_duration_mu     = 7 * self.write_duration_mu
         self.exit_x_duration_mu    = 3 * self.write_duration_mu
 
+    @staticmethod
+    def get_rtio_channels(bus_channel, channel, **kwargs):
+        # return only first entry, as there are several devices with the same RTIO channel
+        if channel == 0:
+            return [(bus_channel, None)]
+        return []
+
     @kernel
     def write(self, addr, data):
         rtio_output((self.bus_channel << 8) | addr, data)

artiq/coredevice/adf5356.py

@@ -73,6 +73,10 @@ class ADF5356:
 
         self._init_registers()
 
+    @staticmethod
+    def get_rtio_channels(**kwargs):
+        return []
+
     @kernel
     def init(self, blind=False):
         """
@@ -102,6 +106,18 @@ class ADF5356:
         else:
             self.sync()
 
+    @kernel
+    def set_att(self, att):
+        """Set digital step attenuator in SI units.
+
+        This method will write the attenuator settings of the channel.
+
+        .. seealso:: :meth:`artiq.coredevice.mirny.Mirny.set_att`
+
+        :param att: Attenuation in dB.
+        """
+        self.cpld.set_att(self.channel, att)
+
     @kernel
     def set_att_mu(self, att):
         """Set digital step attenuator in machine units.

artiq/coredevice/almazny.py

@@ -0,0 +1,185 @@
+from artiq.language.core import kernel, portable
+
+from numpy import int32
+
+
+# almazny-specific data
+ALMAZNY_LEGACY_REG_BASE = 0x0C
+ALMAZNY_LEGACY_OE_SHIFT = 12
+
+# higher SPI write divider to match almazny shift register timing 
+# min SER time before SRCLK rise = 125ns
+# -> div=32 gives 125ns for data before clock rise
+# works at faster dividers too but could be less reliable
+ALMAZNY_LEGACY_SPIT_WR = 32
+
+
+class AlmaznyLegacy:
+    """
+    Almazny (High frequency mezzanine board for Mirny)
+
+    This applies to Almazny hardware v1.1 and earlier.
+    Use :class:`artiq.coredevice.almazny.AlmaznyChannel` for Almazny v1.2 and later.
+
+    :param host_mirny: Mirny device Almazny is connected to
+    """
+
+    def __init__(self, dmgr, host_mirny):
+        self.mirny_cpld = dmgr.get(host_mirny)
+        self.att_mu = [0x3f] * 4
+        self.channel_sw = [0] * 4
+        self.output_enable = False
+
+    @kernel
+    def init(self):
+        self.output_toggle(self.output_enable)
+
+    @kernel
+    def att_to_mu(self, att):
+        """
+        Convert an attenuator setting in dB to machine units.
+
+        :param att: attenuator setting in dB [0-31.5]
+        :return: attenuator setting in machine units
+        """
+        mu = round(att * 2.0)
+        if mu > 63 or mu < 0:
+            raise ValueError("Invalid Almazny attenuator settings!")
+        return mu
+
+    @kernel
+    def mu_to_att(self, att_mu):
+        """
+        Convert a digital attenuator setting to dB.
+
+        :param att_mu: attenuator setting in machine units
+        :return: attenuator setting in dB
+        """
+        return att_mu / 2
+
+    @kernel
+    def set_att(self, channel, att, rf_switch=True):
+        """
+        Sets attenuators on chosen shift register (channel).
+
+        :param channel: index of the register [0-3]
+        :param att: attenuation setting in dBm [0-31.5]
+        :param rf_switch: rf switch (bool)
+        """
+        self.set_att_mu(channel, self.att_to_mu(att), rf_switch)
+
+    @kernel
+    def set_att_mu(self, channel, att_mu, rf_switch=True):
+        """
+        Sets attenuators on chosen shift register (channel).
+
+        :param channel: index of the register [0-3]
+        :param att_mu: attenuation setting in machine units [0-63]
+        :param rf_switch: rf switch (bool)
+        """
+        self.channel_sw[channel] = 1 if rf_switch else 0
+        self.att_mu[channel] = att_mu
+        self._update_register(channel)
+
+    @kernel
+    def output_toggle(self, oe):
+        """
+        Toggles output on all shift registers on or off.
+
+        :param oe: toggle output enable (bool)
+        """
+        self.output_enable = oe
+        cfg_reg = self.mirny_cpld.read_reg(1)
+        en = 1 if self.output_enable else 0
+        delay(100 * us)
+        new_reg = (en << ALMAZNY_LEGACY_OE_SHIFT) | (cfg_reg & 0x3FF)
+        self.mirny_cpld.write_reg(1, new_reg)
+        delay(100 * us)
+
+    @kernel
+    def _flip_mu_bits(self, mu):
+        # in this form MSB is actually 0.5dB attenuator
+        # unnatural for users, so we flip the six bits
+        return (((mu & 0x01) << 5)
+                | ((mu & 0x02) << 3) 
+                | ((mu & 0x04) << 1) 
+                | ((mu & 0x08) >> 1) 
+                | ((mu & 0x10) >> 3) 
+                | ((mu & 0x20) >> 5))
+
+    @kernel
+    def _update_register(self, ch):
+        self.mirny_cpld.write_ext(
+            ALMAZNY_LEGACY_REG_BASE + ch, 
+            8, 
+            self._flip_mu_bits(self.att_mu[ch]) | (self.channel_sw[ch] << 6), 
+            ALMAZNY_LEGACY_SPIT_WR
+        )
+        delay(100 * us)
+
+    @kernel
+    def _update_all_registers(self):
+        for i in range(4):
+            self._update_register(i)
+
+
+class AlmaznyChannel:
+    """
+    One Almazny channel
+    Almazny is a mezzanine for the Quad PLL RF source Mirny that exposes and
+    controls the frequency-doubled outputs.
+    This driver requires Almazny hardware revision v1.2 or later
+    and Mirny CPLD gateware v0.3 or later.
+    Use :class:`artiq.coredevice.almazny.AlmaznyLegacy` for Almazny hardware v1.1 and earlier.
+
+    :param host_mirny: Mirny CPLD device name
+    :param channel: channel index (0-3)
+    """
+
+    def __init__(self, dmgr, host_mirny, channel):
+        self.channel = channel
+        self.mirny_cpld = dmgr.get(host_mirny)
+
+    @portable
+    def to_mu(self, att, enable, led):
+        """
+        Convert an attenuation in dB, RF switch state and LED state to machine
+        units.
+
+        :param att: attenuator setting in dB (0-31.5)
+        :param enable: RF switch state (bool)
+        :param led: LED state (bool)
+        :return: channel setting in machine units
+        """
+        mu = int32(round(att * 2.))
+        if mu >= 64 or mu < 0:
+            raise ValueError("Attenuation out of range")
+        # unfortunate hardware design: bit reverse
+        mu = ((mu & 0x15) << 1) | ((mu >> 1) & 0x15)
+        mu = ((mu & 0x03) << 4) | (mu & 0x0c) | ((mu >> 4) & 0x03)
+        if enable:
+          mu |= 1 << 6
+        if led:
+          mu |= 1 << 7
+        return mu
+
+    @kernel
+    def set_mu(self, mu):
+        """
+        Set channel state (machine units).
+
+        :param mu: channel state in machine units.
+        """
+        self.mirny_cpld.write_ext(
+            addr=0xc + self.channel, length=8, data=mu, ext_div=32)
+
+    @kernel
+    def set(self, att, enable, led=False):
+        """
+        Set attenuation, RF switch, and LED state (SI units).
+
+        :param att: attenuator setting in dB (0-31.5)
+        :param enable: RF switch state (bool)
+        :param led: LED state (bool)
+        """
+        self.set_mu(self.to_mu(att, enable, led))

artiq/coredevice/basemod_att.py

@@ -1,79 +0,0 @@
-from artiq.language.core import kernel, portable, delay
-from artiq.language.units import us, ms
-from artiq.coredevice.shiftreg import ShiftReg
-
-
-@portable
-def to_mu(att):
-    return round(att*2.0) ^ 0x3f
-
-@portable
-def from_mu(att_mu):
-    return 0.5*(att_mu ^ 0x3f)
-
-
-class BaseModAtt:
-    def __init__(self, dmgr, rst_n, clk, le, mosi, miso):
-        self.rst_n = dmgr.get(rst_n)
-        self.shift_reg = ShiftReg(dmgr,
-            clk=clk, ser=mosi, latch=le, ser_in=miso, n=8*4)
-
-    @kernel
-    def reset(self):
-        # HMC's incompetence in digital design and interfaces means that
-        # the HMC542 needs a level low on RST_N and then a rising edge
-        # on Latch Enable. Their "latch" isn't a latch but a DFF.
-        # Of course, it also powers up with a random attenuation, and
-        # that cannot be fixed with simple pull-ups/pull-downs.
-        self.rst_n.off()
-        self.shift_reg.latch.off()
-        delay(1*us)
-        self.shift_reg.latch.on()
-        delay(1*us)
-        self.shift_reg.latch.off()
-        self.rst_n.on()
-        delay(1*us)
-
-    @kernel
-    def set_mu(self, att0, att1, att2, att3):
-        """
-        Sets the four attenuators on BaseMod.
-        The values are in half decibels, between 0 (no attenuation)
-        and 63 (31.5dB attenuation).
-        """
-        word = (
-            (att0 <<  2) |
-            (att1 << 10) | 
-            (att2 << 18) | 
-            (att3 << 26)
-        )
-        self.shift_reg.set(word)
-
-    @kernel
-    def get_mu(self):
-        """
-        Retrieves the current settings of the four attenuators on BaseMod.
-        """
-        word = self.shift_reg.get()
-        att0 = (word >>  2) & 0x3f
-        att1 = (word >> 10) & 0x3f
-        att2 = (word >> 18) & 0x3f
-        att3 = (word >> 26) & 0x3f
-        return att0, att1, att2, att3
-
-    @kernel
-    def set(self, att0, att1, att2, att3):
-        """
-        Sets the four attenuators on BaseMod.
-        The values are in decibels.
-        """
-        self.set_mu(to_mu(att0), to_mu(att1), to_mu(att2), to_mu(att3))
-
-    @kernel
-    def get(self):
-        """
-        Retrieves the current settings of the four attenuators on BaseMod.
-        The values are in decibels.
-        """
-        att0, att1, att2, att3 = self.get_mu()
-        return from_mu(att0), from_mu(att1), from_mu(att2), from_mu(att3)

artiq/coredevice/comm.py

@@ -1,28 +0,0 @@
-import sys
-import socket
-import logging
-
-logger = logging.getLogger(__name__)
-
-
-def set_keepalive(sock, after_idle, interval, max_fails):
-    if sys.platform.startswith("linux"):
-        sock.setsockopt(socket.SOL_SOCKET, socket.SO_KEEPALIVE, 1)
-        sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_KEEPIDLE, after_idle)
-        sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_KEEPINTVL, interval)
-        sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_KEEPCNT, max_fails)
-    elif sys.platform.startswith("win") or sys.platform.startswith("cygwin"):
-        # setting max_fails is not supported, typically ends up being 5 or 10
-        # depending on Windows version
-        sock.ioctl(socket.SIO_KEEPALIVE_VALS,
-                   (1, after_idle * 1000, interval * 1000))
-    else:
-        logger.warning("TCP keepalive not supported on platform '%s', ignored",
-                       sys.platform)
-
-
-def initialize_connection(host, port):
-    sock = socket.create_connection((host, port))
-    set_keepalive(sock, 10, 10, 3)
-    logger.debug("connected to %s:%d", host, port)
-    return sock

artiq/coredevice/comm_analyzer.py

@@ -102,15 +102,15 @@ def decode_dump(data):
     # messages are big endian
     parts = struct.unpack(endian + "IQbbb", data[:15])
     (sent_bytes, total_byte_count,
-     error_occured, log_channel, dds_onehot_sel) = parts
+     error_occurred, log_channel, dds_onehot_sel) = parts
 
     expected_len = sent_bytes + 15
     if expected_len != len(data):
         raise ValueError("analyzer dump has incorrect length "
                          "(got {}, expected {})".format(
                             len(data), expected_len))
-    if error_occured:
+    if error_occurred:
-        logger.warning("error occured within the analyzer, "
+        logger.warning("error occurred within the analyzer, "
                        "data may be corrupted")
     if total_byte_count > sent_bytes:
         logger.info("analyzer ring buffer has wrapped %d times",

artiq/coredevice/comm_kernel.py

@@ -8,9 +8,8 @@ from fractions import Fraction
 from collections import namedtuple
 
 from artiq.coredevice import exceptions
-from artiq.coredevice.comm import initialize_connection
 from artiq import __version__ as software_version
-
+from sipyco.keepalive import create_connection
 
 logger = logging.getLogger(__name__)
 
@@ -24,6 +23,8 @@ class Request(Enum):
     RPCReply = 7
     RPCException = 8
 
+    SubkernelUpload = 9
+
 
 class Reply(Enum):
     SystemInfo = 2
@@ -171,6 +172,16 @@ class CommKernelDummy:
         pass
 
 
+def incompatible_versions(v1, v2):
+    if v1.endswith(".beta") or v2.endswith(".beta"):
+        # Beta branches may introduce breaking changes. Check version strictly.
+        return v1 != v2
+    else:
+        # On stable branches, runtime/software protocol backward compatibility is kept.
+        # Runtime and software with the same major version number are compatible.
+        return v1.split(".", maxsplit=1)[0] != v2.split(".", maxsplit=1)[0]
+
+
 class CommKernel:
     warned_of_mismatch = False
 
@@ -185,7 +196,7 @@ class CommKernel:
     def open(self):
         if hasattr(self, "socket"):
             return
-        self.socket = initialize_connection(self.host, self.port)
+        self.socket = create_connection(self.host, self.port)
         self.socket.sendall(b"ARTIQ coredev\n")
         endian = self._read(1)
         if endian == b"e":
@@ -199,6 +210,7 @@ class CommKernel:
         self.unpack_float64 = struct.Struct(self.endian + "d").unpack
 
         self.pack_header = struct.Struct(self.endian + "lB").pack
+        self.pack_int8 = struct.Struct(self.endian + "B").pack
         self.pack_int32 = struct.Struct(self.endian + "l").pack
         self.pack_int64 = struct.Struct(self.endian + "q").pack
         self.pack_float64 = struct.Struct(self.endian + "d").pack
@@ -313,7 +325,7 @@ class CommKernel:
         self._write(chunk)
 
     def _write_int8(self, value):
-        self._write(value)
+        self._write(self.pack_int8(value))
 
     def _write_int32(self, value):
         self._write(self.pack_int32(value))
@@ -347,7 +359,7 @@ class CommKernel:
         runtime_id = self._read(4)
         if runtime_id == b"AROR":
             gateware_version = self._read_string().split(";")[0]
-            if gateware_version != software_version and not self.warned_of_mismatch:
+            if not self.warned_of_mismatch and incompatible_versions(gateware_version, software_version):
                 logger.warning("Mismatch between gateware (%s) "
                                "and software (%s) versions",
                                gateware_version, software_version)
@@ -373,6 +385,19 @@ class CommKernel:
         else:
             self._read_expect(Reply.LoadCompleted)
 
+    def upload_subkernel(self, kernel_library, id, destination):
+        self._write_header(Request.SubkernelUpload)
+        self._write_int32(id)
+        self._write_int8(destination)
+        self._write_bytes(kernel_library)
+        self._flush()
+
+        self._read_header()
+        if self._read_type == Reply.LoadFailed:
+            raise LoadError(self._read_string())
+        else:
+            self._read_expect(Reply.LoadCompleted)
+
     def run(self):
         self._write_empty(Request.RunKernel)
         self._flush()
@@ -409,6 +434,9 @@ class CommKernel:
             self._skip_rpc_value(tags)
         elif tag == "r":
             self._skip_rpc_value(tags)
+        elif tag == "a":
+            _ndims = tags.pop(0)
+            self._skip_rpc_value(tags)
         else:
             pass
 
@@ -571,29 +599,33 @@ class CommKernel:
 
             self._write_header(Request.RPCException)
 
+            # Note: instead of sending strings, we send object ID
+            # This is to avoid the need of allocatio on the device side
+            # This is a special case: this only applies to exceptions
             if hasattr(exn, "artiq_core_exception"):
                 exn = exn.artiq_core_exception
-                self._write_string(exn.name)
+                self._write_int32(embedding_map.store_str(exn.name))
-                self._write_string(self._truncate_message(exn.message))
+                self._write_int32(embedding_map.store_str(self._truncate_message(exn.message)))
                 for index in range(3):
                     self._write_int64(exn.param[index])
 
                 filename, line, column, function = exn.traceback[-1]
-                self._write_string(filename)
+                self._write_int32(embedding_map.store_str(filename))
                 self._write_int32(line)
                 self._write_int32(column)
-                self._write_string(function)
+                self._write_int32(embedding_map.store_str(function))
             else:
                 exn_type = type(exn)
                 if exn_type in (ZeroDivisionError, ValueError, IndexError, RuntimeError) or \
                         hasattr(exn, "artiq_builtin"):
-                    self._write_string("0:{}".format(exn_type.__name__))
+                    name = "0:{}".format(exn_type.__name__)
                 else:
                     exn_id = embedding_map.store_object(exn_type)
-                    self._write_string("{}:{}.{}".format(exn_id,
+                    name = "{}:{}.{}".format(exn_id,
                                              exn_type.__module__,
-                                                         exn_type.__qualname__))
+                                             exn_type.__qualname__)
-                self._write_string(self._truncate_message(str(exn)))
+                self._write_int32(embedding_map.store_str(name))
+                self._write_int32(embedding_map.store_str(self._truncate_message(str(exn))))
                 for index in range(3):
                     self._write_int64(0)
 
@@ -604,10 +636,10 @@ class CommKernel:
                     ((filename, line, function, _), ) = tb
                 else:
                     assert False
-                self._write_string(filename)
+                self._write_int32(embedding_map.store_str(filename))
                 self._write_int32(line)
                 self._write_int32(-1)  # column not known
-                self._write_string(function)
+                self._write_int32(embedding_map.store_str(function))
             self._flush()
         else:
             logger.debug("rpc service: %d %r %r = %r",
@@ -619,28 +651,65 @@ class CommKernel:
             self._flush()
 
     def _serve_exception(self, embedding_map, symbolizer, demangler):
-        name = self._read_string()
+        exception_count = self._read_int32()
-        message = self._read_string()
+        nested_exceptions = []
+
+        def read_exception_string():
+            # note: if length == -1, the following int32 is the object key
+            length = self._read_int32()
+            if length == -1:
+                return embedding_map.retrieve_str(self._read_int32())
+            else:
+                return self._read(length).decode("utf-8")
+
+        for _ in range(exception_count):
+            name = embedding_map.retrieve_str(self._read_int32())
+            message = read_exception_string()
             params = [self._read_int64() for _ in range(3)]
 
-        filename = self._read_string()
+            filename = read_exception_string()
             line = self._read_int32()
             column = self._read_int32()
-        function = self._read_string()
+            function = read_exception_string()
+            nested_exceptions.append([name, message, params,
+                                      filename, line, column, function])
+
+        demangled_names = demangler([ex[6] for ex in nested_exceptions])
+        for i in range(exception_count):
+            nested_exceptions[i][6] = demangled_names[i]
+
+        exception_info = []
+        for _ in range(exception_count):
+            sp = self._read_int32()
+            initial_backtrace = self._read_int32()
+            current_backtrace = self._read_int32()
+            exception_info.append((sp, initial_backtrace, current_backtrace))
+
+        backtrace = []
+        stack_pointers = []
+        for _ in range(self._read_int32()):
+            backtrace.append(self._read_int32())
+            stack_pointers.append(self._read_int32())
 
-        backtrace = [self._read_int32() for _ in range(self._read_int32())]
         self._process_async_error()
 
-        traceback = list(reversed(symbolizer(backtrace))) + \
+        traceback = list(symbolizer(backtrace))
-            [(filename, line, column, *demangler([function]), None)]
+        core_exn = exceptions.CoreException(nested_exceptions, exception_info,
-        core_exn = exceptions.CoreException(name, message, params, traceback)
+                                            traceback, stack_pointers)
 
         if core_exn.id == 0:
             python_exn_type = getattr(exceptions, core_exn.name.split('.')[-1])
         else:
             python_exn_type = embedding_map.retrieve_object(core_exn.id)
 
-        python_exn = python_exn_type(message.format(*params))
+        try:
+            python_exn = python_exn_type(
+                nested_exceptions[-1][1].format(*nested_exceptions[0][2]))
+        except Exception as ex:
+            python_exn = RuntimeError(
+                f"Exception type={python_exn_type}, which couldn't be "
+                f"reconstructed ({ex})"
+            )
         python_exn.artiq_core_exception = core_exn
         raise python_exn
 

artiq/coredevice/comm_mgmt.py

@@ -2,8 +2,7 @@ from enum import Enum
 import logging
 import struct
 
-from artiq.coredevice.comm import initialize_connection
+from sipyco.keepalive import create_connection
-
 
 logger = logging.getLogger(__name__)
 
@@ -54,7 +53,7 @@ class CommMgmt:
     def open(self):
         if hasattr(self, "socket"):
             return
-        self.socket = initialize_connection(self.host, self.port)
+        self.socket = create_connection(self.host, self.port)
         self.socket.sendall(b"ARTIQ management\n")
         endian = self._read(1)
         if endian == b"e":
@@ -111,9 +110,10 @@ class CommMgmt:
         return ty
 
     def _read_expect(self, ty):
-        if self._read_header() != ty:
+        header = self._read_header()
+        if header != ty:
             raise IOError("Incorrect reply from device: {} (expected {})".
-                          format(self._read_type, ty))
+                          format(header, ty))
 
     def _read_int32(self):
         (value, ) = struct.unpack(self.endian + "l", self._read(4))
@@ -160,7 +160,12 @@ class CommMgmt:
     def config_read(self, key):
         self._write_header(Request.ConfigRead)
         self._write_string(key)
-        self._read_expect(Reply.ConfigData)
+        ty = self._read_header()
+        if ty == Reply.Error:
+            raise IOError("Device failed to read config. The key may not exist.")
+        elif ty != Reply.ConfigData:
+            raise IOError("Incorrect reply from device: {} (expected {})".
+                          format(ty, Reply.ConfigData))
         return self._read_string()
 
     def config_write(self, key, value):
@@ -169,7 +174,7 @@ class CommMgmt:
         self._write_bytes(value)
         ty = self._read_header()
         if ty == Reply.Error:
-            raise IOError("Flash storage is full")
+            raise IOError("Device failed to write config. More information may be available in the log.")
         elif ty != Reply.Success:
             raise IOError("Incorrect reply from device: {} (expected {})".
                           format(ty, Reply.Success))

artiq/coredevice/comm_moninj.py

@@ -3,6 +3,7 @@ import logging
 import struct
 from enum import Enum
 
+from sipyco.keepalive import async_open_connection
 
 __all__ = ["TTLProbe", "TTLOverride", "CommMonInj"]
 
@@ -28,17 +29,16 @@ class CommMonInj:
         self.disconnect_cb = disconnect_cb
 
     async def connect(self, host, port=1383):
-        self._reader, self._writer = await asyncio.open_connection(host, port)
+        self._reader, self._writer = await async_open_connection(
+            host,
+            port,
+            after_idle=1,
+            interval=1,
+            max_fails=3,
+        )
+
         try:
             self._writer.write(b"ARTIQ moninj\n")
-            # get device endian
-            endian = await self._reader.read(1)
-            if endian == b"e":
-                self.endian = "<"
-            elif endian == b"E":
-                self.endian = ">"
-            else:
-                raise IOError("Incorrect reply from device: expected e/E.")
             self._receive_task = asyncio.ensure_future(self._receive_cr())
         except:
             self._writer.close()
@@ -46,6 +46,9 @@ class CommMonInj:
             del self._writer
             raise
 
+    def wait_terminate(self):
+        return self._receive_task
+
     async def close(self):
         self.disconnect_cb = None
         try:
@@ -60,19 +63,19 @@ class CommMonInj:
             del self._writer
 
     def monitor_probe(self, enable, channel, probe):
-        packet = struct.pack(self.endian + "bblb", 0, enable, channel, probe)
+        packet = struct.pack("<bblb", 0, enable, channel, probe)
         self._writer.write(packet)
 
     def monitor_injection(self, enable, channel, overrd):
-        packet = struct.pack(self.endian + "bblb", 3, enable, channel, overrd)
+        packet = struct.pack("<bblb", 3, enable, channel, overrd)
         self._writer.write(packet)
 
     def inject(self, channel, override, value):
-        packet = struct.pack(self.endian + "blbb", 1, channel, override, value)
+        packet = struct.pack("<blbb", 1, channel, override, value)
         self._writer.write(packet)
 
     def get_injection_status(self, channel, override):
-        packet = struct.pack(self.endian + "blb", 2, channel, override)
+        packet = struct.pack("<blb", 2, channel, override)
         self._writer.write(packet)
 
     async def _receive_cr(self):
@@ -82,17 +85,19 @@ class CommMonInj:
                 if not ty:
                     return
                 if ty == b"\x00":
-                    payload = await self._reader.readexactly(9)
+                    payload = await self._reader.readexactly(13)
-                    channel, probe, value = struct.unpack(
+                    channel, probe, value = struct.unpack("<lbq", payload)
-                        self.endian + "lbl", payload)
                     self.monitor_cb(channel, probe, value)
                 elif ty == b"\x01":
                     payload = await self._reader.readexactly(6)
-                    channel, override, value = struct.unpack(
+                    channel, override, value = struct.unpack("<lbb", payload)
-                        self.endian + "lbb", payload)
                     self.injection_status_cb(channel, override, value)
                 else:
                     raise ValueError("Unknown packet type", ty)
+        except asyncio.CancelledError:
+            raise
+        except:
+            logger.error("Moninj connection terminating with exception", exc_info=True)
         finally:
             if self.disconnect_cb is not None:
                 self.disconnect_cb()

artiq/coredevice/core.py

@@ -1,5 +1,7 @@
 import os, sys
 import numpy
+from inspect import getfullargspec
+from functools import wraps
 
 from pythonparser import diagnostic
 
@@ -52,6 +54,17 @@ def rtio_get_counter() -> TInt64:
     raise NotImplementedError("syscall not simulated")
 
 
+def get_target_cls(target):
+    if target == "rv32g":
+        return RV32GTarget
+    elif target == "rv32ima":
+        return RV32IMATarget
+    elif target == "cortexa9":
+        return CortexA9Target
+    else:
+        raise ValueError("Unsupported target")
+
+
 class Core:
     """Core device driver.
 
@@ -65,81 +78,164 @@ class Core:
     :param ref_multiplier: ratio between the RTIO fine timestamp frequency
         and the RTIO coarse timestamp frequency (e.g. SERDES multiplication
         factor).
+    :param analyzer_proxy: name of the core device analyzer proxy to trigger
+        (optional).
+    :param analyze_at_run_end: automatically trigger the core device analyzer
+        proxy after the Experiment's run stage finishes.
     """
 
     kernel_invariants = {
         "core", "ref_period", "coarse_ref_period", "ref_multiplier",
     }
 
-    def __init__(self, dmgr, host, ref_period, ref_multiplier=8, target="rv32g"):
+    def __init__(self, dmgr,
+                 host, ref_period,
+                 analyzer_proxy=None, analyze_at_run_end=False,
+                 ref_multiplier=8,
+                 target="rv32g", satellite_cpu_targets={}):
         self.ref_period = ref_period
         self.ref_multiplier = ref_multiplier
-        if target == "rv32g":
+        self.satellite_cpu_targets = satellite_cpu_targets
-            self.target_cls = RV32GTarget
+        self.target_cls = get_target_cls(target)
-        elif target == "rv32ima":
-            self.target_cls = RV32IMATarget
-        elif target == "cortexa9":
-            self.target_cls = CortexA9Target
-        else:
-            raise ValueError("Unsupported target")
         self.coarse_ref_period = ref_period*ref_multiplier
         if host is None:
             self.comm = CommKernelDummy()
         else:
             self.comm = CommKernel(host)
+        self.analyzer_proxy_name = analyzer_proxy
+        self.analyze_at_run_end = analyze_at_run_end
 
         self.first_run = True
         self.dmgr = dmgr
         self.core = self
         self.comm.core = self
+        self.analyzer_proxy = None
+
+    def notify_run_end(self):
+        if self.analyze_at_run_end:
+            self.trigger_analyzer_proxy()
 
     def close(self):
         self.comm.close()
 
     def compile(self, function, args, kwargs, set_result=None,
-                attribute_writeback=True, print_as_rpc=True):
+                attribute_writeback=True, print_as_rpc=True,
+                target=None, destination=0, subkernel_arg_types=[]):
         try:
             engine = _DiagnosticEngine(all_errors_are_fatal=True)
 
             stitcher = Stitcher(engine=engine, core=self, dmgr=self.dmgr,
-                                print_as_rpc=print_as_rpc)
+                                print_as_rpc=print_as_rpc,
+                                destination=destination, subkernel_arg_types=subkernel_arg_types)
             stitcher.stitch_call(function, args, kwargs, set_result)
             stitcher.finalize()
 
             module = Module(stitcher,
                 ref_period=self.ref_period,
                 attribute_writeback=attribute_writeback)
-            target = self.target_cls()
+            target = target if target is not None else self.target_cls()
 
             library = target.compile_and_link([module])
             stripped_library = target.strip(library)
 
             return stitcher.embedding_map, stripped_library, \
                    lambda addresses: target.symbolize(library, addresses), \
-                   lambda symbols: target.demangle(symbols)
+                   lambda symbols: target.demangle(symbols), \
+                   module.subkernel_arg_types
         except diagnostic.Error as error:
             raise CompileError(error.diagnostic) from error
 
+    def _run_compiled(self, kernel_library, embedding_map, symbolizer, demangler):
+        if self.first_run:
+            self.comm.check_system_info()
+            self.first_run = False
+        self.comm.load(kernel_library)
+        self.comm.run()
+        self.comm.serve(embedding_map, symbolizer, demangler)
+
     def run(self, function, args, kwargs):
         result = None
         @rpc(flags={"async"})
         def set_result(new_result):
             nonlocal result
             result = new_result
-
+        embedding_map, kernel_library, symbolizer, demangler, subkernel_arg_types = \
-        embedding_map, kernel_library, symbolizer, demangler = \
             self.compile(function, args, kwargs, set_result)
-
+        self.compile_and_upload_subkernels(embedding_map, args, subkernel_arg_types)
-        if self.first_run:
+        self._run_compiled(kernel_library, embedding_map, symbolizer, demangler)
-            self.comm.check_system_info()
-            self.first_run = False
-
-        self.comm.load(kernel_library)
-        self.comm.run()
-        self.comm.serve(embedding_map, symbolizer, demangler)
-
         return result
 
+    def compile_subkernel(self, sid, subkernel_fn, embedding_map, args, subkernel_arg_types):
+        # pass self to subkernels (if applicable)
+        # assuming the first argument is self
+        subkernel_args = getfullargspec(subkernel_fn.artiq_embedded.function)
+        self_arg = []
+        if len(subkernel_args[0]) > 0:
+            if subkernel_args[0][0] == 'self':
+                self_arg = args[:1]
+        destination = subkernel_fn.artiq_embedded.destination
+        destination_tgt = self.satellite_cpu_targets[destination]
+        target = get_target_cls(destination_tgt)(subkernel_id=sid)
+        object_map, kernel_library, _, _, _ = \
+            self.compile(subkernel_fn, self_arg, {}, attribute_writeback=False,
+                        print_as_rpc=False, target=target, destination=destination, 
+                        subkernel_arg_types=subkernel_arg_types.get(sid, []))
+        if object_map.has_rpc_or_subkernel():
+            raise ValueError("Subkernel must not use RPC or subkernels in other destinations")
+        return destination, kernel_library
+
+    def compile_and_upload_subkernels(self, embedding_map, args, subkernel_arg_types):
+        for sid, subkernel_fn in embedding_map.subkernels().items():
+            destination, kernel_library = \
+                self.compile_subkernel(sid, subkernel_fn, embedding_map,
+                                       args, subkernel_arg_types)
+            self.comm.upload_subkernel(kernel_library, sid, destination)
+
+    def precompile(self, function, *args, **kwargs):
+        """Precompile a kernel and return a callable that executes it on the core device
+        at a later time.
+
+        Arguments to the kernel are set at compilation time and passed to this function,
+        as additional positional and keyword arguments.
+        The returned callable accepts no arguments.
+
+        Precompiled kernels may use RPCs and subkernels.
+
+        Object attributes at the beginning of a precompiled kernel execution have the
+        values they had at precompilation time. If up-to-date values are required,
+        use RPC to read them.
+        Similarly, modified values are not written back, and explicit RPC should be used
+        to modify host objects.
+        Carefully review the source code of drivers calls used in precompiled kernels, as
+        they may rely on host object attributes being transfered between kernel calls.
+        Examples include code used to control DDS phase, and Urukul RF switch control
+        via the CPLD register.
+
+        The return value of the callable is the return value of the kernel, if any.
+
+        The callable may be called several times.
+        """
+        if not hasattr(function, "artiq_embedded"):
+            raise ValueError("Argument is not a kernel")
+
+        result = None
+        @rpc(flags={"async"})
+        def set_result(new_result):
+            nonlocal result
+            result = new_result
+
+        embedding_map, kernel_library, symbolizer, demangler, subkernel_arg_types = \
+            self.compile(function, args, kwargs, set_result, attribute_writeback=False)
+        self.compile_and_upload_subkernels(embedding_map, args, subkernel_arg_types)
+
+        @wraps(function)
+        def run_precompiled():
+            nonlocal result
+            self._run_compiled(kernel_library, embedding_map, symbolizer, demangler)
+            return result
+
+        return run_precompiled
+
     @portable
     def seconds_to_mu(self, seconds):
         """Convert seconds to the corresponding number of machine units
@@ -206,3 +302,23 @@ class Core:
         min_now = rtio_get_counter() + 125000
         if now_mu() < min_now:
             at_mu(min_now)
+
+    def trigger_analyzer_proxy(self):
+        """Causes the core analyzer proxy to retrieve a dump from the device,
+        and distribute it to all connected clients (typically dashboards).
+
+        Returns only after the dump has been retrieved from the device.
+
+        Raises IOError if no analyzer proxy has been configured, or if the
+        analyzer proxy fails. In the latter case, more details would be
+        available in the proxy log.
+        """
+        if self.analyzer_proxy is None:
+            if self.analyzer_proxy_name is not None:
+                self.analyzer_proxy = self.dmgr.get(self.analyzer_proxy_name)
+        if self.analyzer_proxy is None:
+            raise IOError("No analyzer proxy configured")
+        else:
+            success = self.analyzer_proxy.trigger()
+            if not success:
+                raise IOError("Analyzer proxy reported failure")

artiq/coredevice/coredevice_generic.schema.json

@@ -19,16 +19,24 @@
         },
         "min_artiq_version": {
             "type": "string",
-            "description": "Minimum required ARTIQ version"
+            "description": "Minimum required ARTIQ version",
+            "default": "0"
         },
         "hw_rev": {
             "type": "string",
             "description": "Hardware revision"
         },
         "base": {
+            "type": "string",
+            "enum": ["use_drtio_role", "standalone", "master", "satellite"],
+            "description": "Deprecated, use drtio_role instead",
+            "default": "use_drtio_role"
+        },
+        "drtio_role": {
             "type": "string",
             "enum": ["standalone", "master", "satellite"],
-            "description": "SoC base; value depends on intended system topology"
+            "description": "Role that this device takes in a DRTIO network; 'standalone' means no DRTIO",
+            "default": "standalone"
         },
         "ext_ref_frequency": {
             "type": "number",
@@ -122,7 +130,7 @@
                 },
                 "hw_rev": {
                     "type": "string",
-                    "enum": ["v1.0"]
+                    "enum": ["v1.0", "v1.1"]
                 }
             }
         }
@@ -134,7 +142,7 @@
             "properties": {
                 "type": {
                     "type": "string",
-                    "enum": ["dio", "urukul", "novogorny", "sampler", "suservo", "zotino", "grabber", "mirny", "fastino", "phaser", "hvamp"]
+                    "enum": ["dio", "dio_spi", "urukul", "novogorny", "sampler", "suservo", "zotino", "grabber", "mirny", "fastino", "phaser", "hvamp", "shuttler"]
                 },
                 "board": {
                     "type": "string"
@@ -170,15 +178,101 @@
                         },
                         "bank_direction_low": {
                             "type": "string",
-                            "enum": ["input", "output"]
+                            "enum": ["input", "output", "clkgen"]
                         },
                         "bank_direction_high": {
                             "type": "string",
-                            "enum": ["input", "output"]
+                            "enum": ["input", "output", "clkgen"]
                         }
                     },
                     "required": ["ports", "bank_direction_low", "bank_direction_high"]
                 }
+            }, {
+                "title": "DIO_SPI",
+                "if": {
+                    "properties": {
+                        "type": {
+                            "const": "dio_spi"
+                        }
+                    }
+                },
+                "then": {
+                    "properties": {
+                        "ports": {
+                            "type": "array",
+                            "items": {
+                                "type": "integer"
+                            },
+                            "minItems": 1,
+                            "maxItems": 1
+                        },
+                        "spi": {
+                            "type": "array",
+                            "items": {
+                                "type": "object",
+                                "properties": {
+                                    "name": {
+                                        "type": "string",
+                                        "default": "dio_spi"
+                                    },
+                                    "clk": {
+                                        "type": "integer",
+                                        "minimum": 0,
+                                        "maximum": 7
+                                    },
+                                    "mosi": {
+                                        "type": "integer",
+                                        "minimum": 0,
+                                        "maximum": 7
+                                    },
+                                    "miso": {
+                                        "type": "integer",
+                                        "minimum": 0,
+                                        "maximum": 7
+                                    },
+                                    "cs": {
+                                        "type": "array",
+                                        "items": {
+                                            "type": "integer",
+                                            "minimum": 0,
+                                            "maximum": 7
+                                        }
+                                    }
+                                },
+                                "required": ["clk"]
+                            },
+                            "minItems": 1
+                        },
+                        "ttl": {
+                            "type": "array",
+                            "items": {
+                                "type": "object",
+                                "properties": {
+                                    "name": {
+                                        "type": "string",
+                                        "default": "ttl"
+                                    },
+                                    "pin": {
+                                        "type": "integer",
+                                        "minimum": 0,
+                                        "maximum": 7
+                                    },
+                                    "direction": {
+                                        "type": "string",
+                                        "enum": ["input", "output"]
+                                    },
+                                    "edge_counter": {
+                                        "type": "boolean",
+                                        "default": false
+                                    }
+                                },
+                                "required": ["pin", "direction"]
+                            },
+                            "default": []
+                        }
+                    },
+                    "required": ["ports", "spi"]
+                }
             }, {
                 "title": "Urukul",
                 "if": {
@@ -214,11 +308,18 @@
                         "clk_div": {
                             "type": "integer",
                             "minimum": 0,
-                            "maximum": 3
+                            "maximum": 3,
+                            "default": 0
                         },
                         "pll_n": {
                             "type": "integer"
                         },
+                        "pll_en": {
+                            "type": "integer",
+                            "minimum": 0,
+                            "maximum": 1,
+                            "default": 1
+                        },
                         "pll_vco": {
                             "type": "integer"
                         },
@@ -293,6 +394,11 @@
                             "minItems": 2,
                             "maxItems": 2
                         },
+                        "sampler_hw_rev": {
+                            "type": "string",
+                            "pattern": "^v[0-9]+\\.[0-9]+",
+                            "default": "v2.2"
+                        },
                         "urukul0_ports": {
                             "type": "array",
                             "items": {
@@ -322,6 +428,12 @@
                             "type": "integer",
                             "default": 32
                         },
+                        "pll_en": {
+                            "type": "integer",
+                            "minimum": 0,
+                            "maximum": 1,
+                            "default": 1
+                        },
                         "pll_vco": {
                             "type": "integer"
                         }
@@ -413,6 +525,11 @@
                         "almazny": {
                             "type": "boolean",
                             "default": false
+                        },
+                        "almazny_hw_rev": {
+                            "type": "string",
+                            "pattern": "^v[0-9]+\\.[0-9]+",
+                            "default": "v1.2"
                         }
                     },
                     "required": ["ports"]
@@ -462,6 +579,11 @@
                             },
                             "minItems": 1,
                             "maxItems": 1
+                        },
+                        "mode": {
+                            "type": "string",
+                            "enum": ["base", "miqro"],
+                            "default": "base"
                         }
                     },
                     "required": ["ports"]
@@ -488,6 +610,31 @@
                     },
                     "required": ["ports"]
                 }
+            },{
+                "title": "Shuttler",
+                "if": {
+                    "properties": {
+                        "type": {
+                            "const": "shuttler"
+                        }
+                    }
+                },
+                "then": {
+                    "properties": {
+                        "ports": {
+                            "type": "array",
+                            "items": {
+                                "type": "integer"
+                            },
+                            "minItems": 1,
+                            "maxItems": 2
+                        },
+                        "drtio_destination": {
+                            "type": "integer"
+                        }
+                    },
+                    "required": ["ports"]
+                }
             }]
         }
     }

artiq/coredevice/dma.py

@@ -6,7 +6,7 @@ alone could achieve.
 """
 
 from artiq.language.core import syscall, kernel
-from artiq.language.types import TInt32, TInt64, TStr, TNone, TTuple
+from artiq.language.types import TInt32, TInt64, TStr, TNone, TTuple, TBool
 from artiq.coredevice.exceptions import DMAError
 
 from numpy import int64
@@ -17,7 +17,7 @@ def dma_record_start(name: TStr) -> TNone:
     raise NotImplementedError("syscall not simulated")
 
 @syscall
-def dma_record_stop(duration: TInt64) -> TNone:
+def dma_record_stop(duration: TInt64, enable_ddma: TBool) -> TNone:
     raise NotImplementedError("syscall not simulated")
 
 @syscall
@@ -25,11 +25,11 @@ def dma_erase(name: TStr) -> TNone:
     raise NotImplementedError("syscall not simulated")
 
 @syscall
-def dma_retrieve(name: TStr) -> TTuple([TInt64, TInt32]):
+def dma_retrieve(name: TStr) -> TTuple([TInt64, TInt32, TBool]):
     raise NotImplementedError("syscall not simulated")
 
 @syscall
-def dma_playback(timestamp: TInt64, ptr: TInt32) -> TNone:
+def dma_playback(timestamp: TInt64, ptr: TInt32, enable_ddma: TBool) -> TNone:
     raise NotImplementedError("syscall not simulated")
 
 
@@ -47,6 +47,7 @@ class DMARecordContextManager:
     def __init__(self):
         self.name = ""
         self.saved_now_mu = int64(0)
+        self.enable_ddma = False
 
     @kernel
     def __enter__(self):
@@ -56,7 +57,7 @@ class DMARecordContextManager:
 
     @kernel
     def __exit__(self, type, value, traceback):
-        dma_record_stop(now_mu()) # see above
+        dma_record_stop(now_mu(), self.enable_ddma) # see above
         at_mu(self.saved_now_mu)
 
 
@@ -74,12 +75,20 @@ class CoreDMA:
         self.epoch    = 0
 
     @kernel
-    def record(self, name):
+    def record(self, name, enable_ddma=False):
         """Returns a context manager that will record a DMA trace called ``name``.
         Any previously recorded trace with the same name is overwritten.
-        The trace will persist across kernel switches."""
+        The trace will persist across kernel switches.
+
+        In DRTIO context, distributed DMA can be toggled with ``enable_ddma``.
+        Enabling it allows running DMA on satellites, rather than sending all
+        events from the master.
+
+        Keeping it disabled it may improve performance in some scenarios, 
+        e.g. when there are many small satellite buffers."""
         self.epoch += 1
         self.recorder.name = name
+        self.recorder.enable_ddma = enable_ddma
         return self.recorder
 
     @kernel
@@ -92,24 +101,24 @@ class CoreDMA:
     def playback(self, name):
         """Replays a previously recorded DMA trace. This function blocks until
         the entire trace is submitted to the RTIO FIFOs."""
-        (advance_mu, ptr) = dma_retrieve(name)
+        (advance_mu, ptr, uses_ddma) = dma_retrieve(name)
-        dma_playback(now_mu(), ptr)
+        dma_playback(now_mu(), ptr, uses_ddma)
         delay_mu(advance_mu)
 
     @kernel
     def get_handle(self, name):
         """Returns a handle to a previously recorded DMA trace. The returned handle
         is only valid until the next call to :meth:`record` or :meth:`erase`."""
-        (advance_mu, ptr) = dma_retrieve(name)
+        (advance_mu, ptr, uses_ddma) = dma_retrieve(name)
-        return (self.epoch, advance_mu, ptr)
+        return (self.epoch, advance_mu, ptr, uses_ddma)
 
     @kernel
     def playback_handle(self, handle):
         """Replays a handle obtained with :meth:`get_handle`. Using this function
         is much faster than :meth:`playback` for replaying a set of traces repeatedly,
         but incurs the overhead of managing the handles onto the programmer."""
-        (epoch, advance_mu, ptr) = handle
+        (epoch, advance_mu, ptr, uses_ddma) = handle
         if self.epoch != epoch:
             raise DMAError("Invalid handle")
-        dma_playback(now_mu(), ptr)
+        dma_playback(now_mu(), ptr, uses_ddma)
         delay_mu(advance_mu)

artiq/coredevice/edge_counter.py

@@ -91,6 +91,10 @@ class EdgeCounter:
         self.channel = channel
         self.counter_max = (1 << (gateware_width - 1)) - 1
 
+    @staticmethod
+    def get_rtio_channels(channel, **kwargs):
+        return [(channel, None)]
+
     @kernel
     def gate_rising(self, duration):
         """Count rising edges for the given duration and request the total at

artiq/coredevice/exceptions.py

@@ -16,50 +16,94 @@ AssertionError = builtins.AssertionError
 
 class CoreException:
     """Information about an exception raised or passed through the core device."""
+    def __init__(self, exceptions, exception_info, traceback, stack_pointers):
+        self.exceptions = exceptions
+        self.exception_info = exception_info
+        self.traceback = list(traceback)
+        self.stack_pointers = stack_pointers
 
-    def __init__(self, name, message, params, traceback):
+        first_exception = exceptions[0]
+        name = first_exception[0]
         if ':' in name:
             exn_id, self.name = name.split(':', 2)
             self.id = int(exn_id)
         else:
             self.id, self.name = 0, name
-        self.message, self.params = message, params
+        self.message = first_exception[1]
-        self.traceback = list(traceback)
+        self.params = first_exception[2]
 
-    def __str__(self):
+    def append_backtrace(self, record, inlined=False):
-        lines = []
+        filename, line, column, function, address = record
-        lines.append("Core Device Traceback (most recent call last):")
-        last_address = 0
-        for (filename, line, column, function, address) in self.traceback:
         stub_globals = {"__name__": filename, "__loader__": source_loader}
         source_line = linecache.getline(filename, line, stub_globals)
         indentation = re.search(r"^\s*", source_line).end()
 
         if address is None:
             formatted_address = ""
-            elif address == last_address:
+        elif inlined:
             formatted_address = " (inlined)"
         else:
             formatted_address = " (RA=+0x{:x})".format(address)
-            last_address = address
 
         filename = filename.replace(artiq_dir, "<artiq>")
+        lines = []
         if column == -1:
+            lines.append("    {}".format(source_line.strip() if source_line else "<unknown>"))
             lines.append("  File \"{file}\", line {line}, in {function}{address}".
                          format(file=filename, line=line, function=function,
                                 address=formatted_address))
-                lines.append("    {}".format(source_line.strip() if source_line else "<unknown>"))
         else:
+            lines.append("    {}^".format(" " * (column - indentation)))
+            lines.append("    {}".format(source_line.strip() if source_line else "<unknown>"))
             lines.append("  File \"{file}\", line {line}, column {column},"
                          " in {function}{address}".
                          format(file=filename, line=line, column=column + 1,
                                 function=function, address=formatted_address))
-                lines.append("    {}".format(source_line.strip() if source_line else "<unknown>"))
+        return lines
-                lines.append("    {}^".format(" " * (column - indentation)))
 
-        lines.append("{}({}): {}".format(self.name, self.id,
+    def single_traceback(self, exception_index):
-                                         self.message.format(*self.params)))
+        # note that we insert in reversed order
-        return "\n".join(lines)
+        lines = []
+        last_sp = 0
+        start_backtrace_index = self.exception_info[exception_index][1]
+        zipped = list(zip(self.traceback[start_backtrace_index:],
+                          self.stack_pointers[start_backtrace_index:]))
+        exception = self.exceptions[exception_index]
+        name = exception[0]
+        message = exception[1]
+        params = exception[2]
+        if ':' in name:
+            exn_id, name = name.split(':', 2)
+            exn_id = int(exn_id)
+        else:
+            exn_id = 0
+        lines.append("{}({}): {}".format(name, exn_id, message.format(*params)))
+        zipped.append(((exception[3], exception[4], exception[5], exception[6],
+                       None, []), None))
+
+        for ((filename, line, column, function, address, inlined), sp) in zipped:
+            # backtrace of nested exceptions may be discontinuous
+            # but the stack pointer must increase monotonically
+            if sp is not None and sp <= last_sp:
+                continue
+            last_sp = sp
+
+            for record in reversed(inlined):
+                lines += self.append_backtrace(record, True)
+            lines += self.append_backtrace((filename, line, column, function,
+                                            address))
+
+        lines.append("Traceback (most recent call first):")
+
+        return "\n".join(reversed(lines))
+
+    def __str__(self):
+        tracebacks = [self.single_traceback(i) for i in range(len(self.exceptions))]
+        traceback_str = ('\n\nDuring handling of the above exception, ' +
+                        'another exception occurred:\n\n').join(tracebacks)
+        return 'Core Device Traceback:\n' +\
+                traceback_str +\
+                '\n\nEnd of Core Device Traceback\n'
 
 
 class InternalError(Exception):
@@ -104,6 +148,13 @@ class DMAError(Exception):
     artiq_builtin = True
 
 
+class SubkernelError(Exception):
+    """Raised when an operation regarding a subkernel is invalid 
+    or cannot be completed.
+    """
+    artiq_builtin = True
+
+
 class ClockFailure(Exception):
     """Raised when RTIO PLL has lost lock."""
 

artiq/coredevice/fastino.py

@@ -1,12 +1,12 @@
 """RTIO driver for the Fastino 32channel, 16 bit, 2.5 MS/s per channel,
 streaming DAC.
 """
-from numpy import int32
+from numpy import int32, int64
 
 from artiq.language.core import kernel, portable, delay, delay_mu
 from artiq.coredevice.rtio import (rtio_output, rtio_output_wide,
                                    rtio_input_data)
-from artiq.language.units import us
+from artiq.language.units import ns
 from artiq.language.types import TInt32, TList
 
 
@@ -21,7 +21,7 @@ class Fastino:
     DAC updates synchronized to a frame edge.
 
     The `log2_width=0` RTIO layout uses one DAC channel per RTIO address and a
-    dense RTIO address space. The RTIO words are narrow. (32 bit) and
+    dense RTIO address space. The RTIO words are narrow (32 bit) and
     few-channel updates are efficient. There is the least amount of DAC state
     tracking in kernels, at the cost of more DMA and RTIO data.
     The setting here and in the RTIO PHY (gateware) must match.
@@ -41,24 +41,52 @@ class Fastino:
     :param log2_width: Width of DAC channel group (logarithm base 2).
         Value must match the corresponding value in the RTIO PHY (gateware).
     """
-    kernel_invariants = {"core", "channel", "width"}
+    kernel_invariants = {"core", "channel", "width", "t_frame"}
 
     def __init__(self, dmgr, channel, core_device="core", log2_width=0):
         self.channel = channel << 8
         self.core = dmgr.get(core_device)
         self.width = 1 << log2_width
+        # frame duration in mu (14 words each 7 clock cycles each 4 ns)
+        # self.core.seconds_to_mu(14*7*4*ns)  # unfortunately this may round wrong
+        assert self.core.ref_period == 1*ns
+        self.t_frame = int64(14*7*4)
+
+    @staticmethod
+    def get_rtio_channels(channel, **kwargs):
+        return [(channel, None)]
 
     @kernel
     def init(self):
         """Initialize the device.
 
-        This clears reset, unsets DAC_CLR, enables AFE_PWR,
+            * disables RESET, DAC_CLR, enables AFE_PWR
-        clears error counters, then enables error counting
+            * clears error counters, enables error counting
+            * turns LEDs off
+            * clears `hold` and `continuous` on all channels
+            * clear and resets interpolators to unit rate change on all
+              channels
+
+        It does not change set channel voltages and does not reset the PLLs or clock
+        domains.
+
+        Note: On Fastino gateware before v0.2 this may lead to 0 voltage being emitted
+        transiently.
         """
         self.set_cfg(reset=0, afe_power_down=0, dac_clr=0, clr_err=1)
-        delay(1*us)
+        delay_mu(self.t_frame)
         self.set_cfg(reset=0, afe_power_down=0, dac_clr=0, clr_err=0)
-        delay(1*us)
+        delay_mu(self.t_frame)
+        self.set_continuous(0)
+        delay_mu(self.t_frame)
+        self.stage_cic(1)
+        delay_mu(self.t_frame)
+        self.apply_cic(0xffffffff)
+        delay_mu(self.t_frame)
+        self.set_leds(0)
+        delay_mu(self.t_frame)
+        self.set_hold(0)
+        delay_mu(self.t_frame)
 
     @kernel
     def write(self, addr, data):
@@ -78,8 +106,9 @@ class Fastino:
         :param addr: Address to read from.
         :return: The data read.
         """
-        rtio_output(self.channel | addr | 0x80)
+        raise NotImplementedError
-        return rtio_input_data(self.channel >> 8)
+        # rtio_output(self.channel | addr | 0x80)
+        # return rtio_input_data(self.channel >> 8)
 
     @kernel
     def set_dac_mu(self, dac, data):
@@ -252,9 +281,12 @@ class Fastino:
     def apply_cic(self, channel_mask):
         """Apply the staged interpolator configuration on the specified channels.
 
-        Each Fastino channel includes a fourth order (cubic) CIC interpolator with
+        Each Fastino channel starting with gateware v0.2 includes a fourth order
-        variable rate change and variable output gain compensation (see
+        (cubic) CIC interpolator with variable rate change and variable output
-        :meth:`stage_cic`).
+        gain compensation (see :meth:`stage_cic`).
+
+        Fastino gateware before v0.2 does not include the interpolators and the
+        methods affecting the CICs should not be used.
 
         Channels using non-unity interpolation rate should have
         continous DAC updates enabled (see :meth:`set_continuous`) unless

artiq/coredevice/grabber.py

@@ -25,6 +25,10 @@ class Grabber:
         # ROI engine outputs for one video frame.
         self.sentinel = int32(int64(2**count_width))
 
+    @staticmethod
+    def get_rtio_channels(channel_base, **kwargs):
+        return [(channel_base, "ROI coordinates"), (channel_base + 1, "ROI mask")]
+
     @kernel
     def setup_roi(self, n, x0, y0, x1, y1):
         """

artiq/coredevice/i2c.py

@@ -33,6 +33,11 @@ def i2c_read(busno: TInt32, ack: TBool) -> TInt32:
     raise NotImplementedError("syscall not simulated")
 
 
+@syscall(flags={"nounwind", "nowrite"})
+def i2c_switch_select(busno: TInt32, address: TInt32, mask: TInt32) -> TNone:
+    raise NotImplementedError("syscall not simulated")
+
+
 @kernel
 def i2c_poll(busno, busaddr):
     """Poll I2C device at address.
@@ -137,8 +142,10 @@ def i2c_read_many(busno, busaddr, addr, data):
         i2c_stop(busno)
 
 
-class PCA9548:
+class I2CSwitch:
-    """Driver for the PCA9548 I2C bus switch.
+    """Driver for the I2C bus switch.
+
+    PCA954X (or other) type detection is done by the CPU during I2C init.
 
     I2C transactions not real-time, and are performed by the CPU without
     involving RTIO.
@@ -151,25 +158,19 @@ class PCA9548:
         self.busno = busno
         self.address = address
 
-    @kernel
-    def select(self, mask):
-        """Enable/disable channels.
-
-        :param mask: Bit mask of enabled channels
-        """
-        i2c_write_byte(self.busno, self.address, mask)
-
     @kernel
     def set(self, channel):
         """Enable one channel.
 
         :param channel: channel number (0-7)
         """
-        self.select(1 << channel)
+        i2c_switch_select(self.busno, self.address >> 1, 1 << channel)
 
     @kernel
-    def readback(self):
+    def unset(self):
-        return i2c_read_byte(self.busno, self.address)
+        """Disable output of the I2C switch.
+        """
+        i2c_switch_select(self.busno, self.address >> 1, 0)
 
 
 class TCA6424A:
@@ -207,3 +208,46 @@ class TCA6424A:
 
         self._write24(0x8c, 0)  # set all directions to output
         self._write24(0x84, outputs_le)  # set levels
+
+class PCF8574A:
+    """Driver for the PCF8574 I2C remote 8-bit I/O expander.
+
+    I2C transactions not real-time, and are performed by the CPU without
+    involving RTIO.
+    """
+    def __init__(self, dmgr, busno=0, address=0x7c, core_device="core"):
+        self.core = dmgr.get(core_device)
+        self.busno = busno
+        self.address = address
+
+    @kernel
+    def set(self, data):
+        """Drive data on the quasi-bidirectional pins.
+
+        :param data: Pin data. High bits are weakly driven high
+            (and thus inputs), low bits are strongly driven low.
+        """
+        i2c_start(self.busno)
+        try:
+            if not i2c_write(self.busno, self.address):
+                raise I2CError("PCF8574A failed to ack address")
+            if not i2c_write(self.busno, data):
+                raise I2CError("PCF8574A failed to ack data")
+        finally:
+            i2c_stop(self.busno)
+
+    @kernel
+    def get(self):
+        """Retrieve quasi-bidirectional pin input data.
+
+        :return: Pin data
+        """
+        i2c_start(self.busno)
+        ret = 0
+        try:
+            if not i2c_write(self.busno, self.address | 1):
+                raise I2CError("PCF8574A failed to ack address")
+            ret = i2c_read(self.busno, False)
+        finally:
+            i2c_stop(self.busno)
+        return ret

artiq/coredevice/jsondesc.py

@@ -32,4 +32,7 @@ def load(description_path):
     global validator
     validator.validate(result)
 
+    if result["base"] != "use_drtio_role":
+        result["drtio_role"] = result["base"]
+
     return result

artiq/coredevice/kasli_i2c.py

@@ -37,13 +37,17 @@ class KasliEEPROM:
     @kernel
     def select(self):
         mask = 1 << self.port
-        self.sw0.select(mask)
+        if self.port < 8:
-        self.sw1.select(mask >> 8)
+            self.sw0.set(self.port)
+            self.sw1.unset()
+        else:
+            self.sw0.unset()
+            self.sw1.set(self.port - 8)
 
     @kernel
     def deselect(self):
-        self.sw0.select(0)
+        self.sw0.unset()
-        self.sw1.select(0)
+        self.sw1.unset()
 
     @kernel
     def write_i32(self, addr, value):

artiq/coredevice/mirny.py

@@ -1,7 +1,7 @@
 """RTIO driver for Mirny (4 channel GHz PLLs)
 """
 
-from artiq.language.core import kernel, delay
+from artiq.language.core import kernel, delay, portable
 from artiq.language.units import us
 
 from numpy import int32
@@ -31,16 +31,6 @@ WE = 1 << 24
 # supported CPLD code version
 PROTO_REV_MATCH = 0x0
 
-# almazny-specific data
-ALMAZNY_REG_BASE = 0x0C
-ALMAZNY_OE_SHIFT = 12
-
-# higher SPI write divider to match almazny shift register timing 
-# min SER time before SRCLK rise = 125ns
-# -> div=32 gives 125ns for data before clock rise
-# works at faster dividers too but could be less reliable
-ALMAZNY_SPIT_WR = 32
-
 
 class Mirny:
     """
@@ -132,6 +122,18 @@ class Mirny:
         self.write_reg(1, (self.clk_sel << 4))
         delay(1000 * us)
 
+    @portable(flags={"fast-math"})
+    def att_to_mu(self, att):
+        """Convert an attenuation setting in dB to machine units.
+
+        :param att: Attenuation setting in dB.
+        :return: Digital attenuation setting.
+        """
+        code = int32(255) - int32(round(att * 8))
+        if code < 0 or code > 255:
+            raise ValueError("Invalid Mirny attenuation!")
+        return code
+
     @kernel
     def set_att_mu(self, channel, att):
         """Set digital step attenuator in machine units.
@@ -141,6 +143,21 @@ class Mirny:
         self.bus.set_config_mu(SPI_CONFIG | spi.SPI_END, 16, SPIT_WR, SPI_CS)
         self.bus.write(((channel | 8) << 25) | (att << 16))
 
+    @kernel
+    def set_att(self, channel, att):
+        """Set digital step attenuator in SI units.
+
+        This method will write the attenuator settings of the selected channel.
+
+        .. seealso:: :meth:`set_att_mu`
+
+        :param channel: Attenuator channel (0-3).
+        :param att: Attenuation setting in dB. Higher value is more
+            attenuation. Minimum attenuation is 0*dB, maximum attenuation is
+            31.5*dB.
+        """
+        self.set_att_mu(channel, self.att_to_mu(att))
+
     @kernel
     def write_ext(self, addr, length, data, ext_div=SPIT_WR):
         """Perform SPI write to a prefixed address"""
@@ -150,106 +167,3 @@ class Mirny:
         if length < 32:
             data <<= 32 - length
         self.bus.write(data)
-
-
-class Almazny:
-    """
-    Almazny (High frequency mezzanine board for Mirny)
-
-    :param host_mirny - Mirny device Almazny is connected to
-    """
-
-    def __init__(self, dmgr, host_mirny):
-        self.mirny_cpld = dmgr.get(host_mirny)
-        self.att_mu = [0x3f] * 4
-        self.channel_sw = [0] * 4
-        self.output_enable = False
-
-    @kernel
-    def init(self):
-        self.output_toggle(self.output_enable)
-
-    @kernel
-    def att_to_mu(self, att):
-        """
-        Convert an attenuator setting in dB to machine units.
-
-        :param att: attenuator setting in dB [0-31.5]
-        :return: attenuator setting in machine units
-        """
-        mu = round(att * 2.0)
-        if mu > 63 or mu < 0:
-            raise ValueError("Invalid Almazny attenuator settings!")
-        return mu
-
-    @kernel
-    def mu_to_att(self, att_mu):
-        """
-        Convert a digital attenuator setting to dB.
-
-        :param att_mu: attenuator setting in machine units
-        :return: attenuator setting in dB
-        """
-        return att_mu / 2
-
-    @kernel
-    def set_att(self, channel, att, rf_switch=True):
-        """
-        Sets attenuators on chosen shift register (channel).
-        :param channel - index of the register [0-3]
-        :param att_mu - attenuation setting in dBm [0-31.5]
-        :param rf_switch - rf switch (bool)
-        """
-        self.set_att_mu(channel, self.att_to_mu(att), rf_switch)
-
-    @kernel
-    def set_att_mu(self, channel, att_mu, rf_switch=True):
-        """
-        Sets attenuators on chosen shift register (channel).
-        :param channel - index of the register [0-3]
-        :param att_mu - attenuation setting in machine units [0-63]
-        :param rf_switch - rf switch (bool)
-        """
-        self.channel_sw[channel] = 1 if rf_switch else 0
-        self.att_mu[channel] = att_mu
-        self._update_register(channel)
-
-    @kernel
-    def output_toggle(self, oe):
-        """
-        Toggles output on all shift registers on or off.
-        :param oe - toggle output enable (bool)
-        """
-        self.output_enable = oe
-        cfg_reg = self.mirny_cpld.read_reg(1)
-        en = 1 if self.output_enable else 0
-        delay(100 * us)
-        new_reg = (en << ALMAZNY_OE_SHIFT) | (cfg_reg & 0x3FF)
-        self.mirny_cpld.write_reg(1, new_reg)
-        delay(100 * us)
-
-    @kernel
-    def _flip_mu_bits(self, mu):
-        # in this form MSB is actually 0.5dB attenuator
-        # unnatural for users, so we flip the six bits
-        return (((mu & 0x01) << 5)
-                | ((mu & 0x02) << 3) 
-                | ((mu & 0x04) << 1) 
-                | ((mu & 0x08) >> 1) 
-                | ((mu & 0x10) >> 3) 
-                | ((mu & 0x20) >> 5))
-
-    @kernel
-    def _update_register(self, ch):
-        self.mirny_cpld.write_ext(
-            ALMAZNY_REG_BASE + ch, 
-            8, 
-            self._flip_mu_bits(self.att_mu[ch]) | (self.channel_sw[ch] << 6), 
-            ALMAZNY_SPIT_WR
-        )
-        delay(100 * us)
-
-    @kernel
-    def _update_all_registers(self):
-        for i in range(4):
-            self._update_register(i)

artiq/coredevice/pcf8574a.py

@@ -1,47 +0,0 @@
-from artiq.experiment import kernel
-from artiq.coredevice.i2c import (
-    i2c_start, i2c_write, i2c_read, i2c_stop, I2CError)
-
-
-class PCF8574A:
-    """Driver for the PCF8574 I2C remote 8-bit I/O expander.
-
-    I2C transactions not real-time, and are performed by the CPU without
-    involving RTIO.
-    """
-    def __init__(self, dmgr, busno=0, address=0x7c, core_device="core"):
-        self.core = dmgr.get(core_device)
-        self.busno = busno
-        self.address = address
-
-    @kernel
-    def set(self, data):
-        """Drive data on the quasi-bidirectional pins.
-
-        :param data: Pin data. High bits are weakly driven high
-            (and thus inputs), low bits are strongly driven low.
-        """
-        i2c_start(self.busno)
-        try:
-            if not i2c_write(self.busno, self.address):
-                raise I2CError("PCF8574A failed to ack address")
-            if not i2c_write(self.busno, data):
-                raise I2CError("PCF8574A failed to ack data")
-        finally:
-            i2c_stop(self.busno)
-
-    @kernel
-    def get(self):
-        """Retrieve quasi-bidirectional pin input data.
-
-        :return: Pin data
-        """
-        i2c_start(self.busno)
-        ret = 0
-        try:
-            if not i2c_write(self.busno, self.address | 1):
-                raise I2CError("PCF8574A failed to ack address")
-            ret = i2c_read(self.busno, False)
-        finally:
-            i2c_stop(self.busno)
-        return ret

artiq/coredevice/phaser.py

@@ -9,6 +9,10 @@ from artiq.coredevice.trf372017 import TRF372017
 
 
 PHASER_BOARD_ID = 19
+
+PHASER_GW_BASE = 1
+PHASER_GW_MIQRO = 2
+
 PHASER_ADDR_BOARD_ID = 0x00
 PHASER_ADDR_HW_REV = 0x01
 PHASER_ADDR_GW_REV = 0x02
@@ -40,6 +44,20 @@ PHASER_ADDR_DUC1_P = 0x26
 PHASER_ADDR_DAC1_DATA = 0x28
 PHASER_ADDR_DAC1_TEST = 0x2c
 
+# servo registers
+PHASER_ADDR_SERVO_CFG0 = 0x30
+PHASER_ADDR_SERVO_CFG1 = 0x31
+
+# 0x32 - 0x71 servo coefficients + offset data
+PHASER_ADDR_SERVO_DATA_BASE = 0x32
+
+# 0x72 - 0x78 Miqro channel profile/window memories
+PHASER_ADDR_MIQRO_MEM_ADDR = 0x72
+PHASER_ADDR_MIQRO_MEM_DATA = 0x74
+
+# Miqro profile memory select
+PHASER_MIQRO_SEL_PROFILE = 1 << 14
+
 PHASER_SEL_DAC = 1 << 0
 PHASER_SEL_TRF0 = 1 << 1
 PHASER_SEL_TRF1 = 1 << 2
@@ -58,6 +76,11 @@ PHASER_DAC_SEL_TEST = 1
 
 PHASER_HW_REV_VARIANT = 1 << 4
 
+SERVO_COEFF_WIDTH = 16
+SERVO_DATA_WIDTH = 16
+SERVO_COEFF_SHIFT = 14
+SERVO_T_CYCLE = (32+12+192+24+4)*ns  # Must match gateware ADC parameters
+
 
 class Phaser:
     """Phaser 4-channel, 16-bit, 1 GS/s DAC coredevice driver.
@@ -65,6 +88,26 @@ class Phaser:
     Phaser contains a 4 channel, 1 GS/s DAC chip with integrated upconversion,
     quadrature modulation compensation and interpolation features.
 
+    The coredevice RTIO PHY and the Phaser gateware come in different modes
+    that have different features. Phaser mode and coredevice PHY mode are both
+    selected at their respective gateware compile-time and need to match.
+
+    ===============  ==============  ===================================
+    Phaser gateware  Coredevice PHY  Features per :class:`PhaserChannel`
+    ===============  ==============  ===================================
+    Base <= v0.5     Base            Base (5 :class:`PhaserOscillator`)
+    Base >= v0.6     Base            Base + Servo
+    Miqro >= v0.6    Miqro           :class:`Miqro`
+    ===============  ==============  ===================================
+
+    The coredevice driver (this class and :class:`PhaserChannel`) exposes
+    the superset of all functionality regardless of the Coredevice RTIO PHY
+    or Phaser gateware modes. This is to evade type unification limitations.
+    Features absent in Coredevice PHY/Phaser gateware will not work and
+    should not be accessed.
+
+    **Base mode**
+
     The coredevice produces 2 IQ (in-phase and quadrature) data streams with 25
     MS/s and 14 bit per quadrature. Each data stream supports 5 independent
     numerically controlled IQ oscillators (NCOs, DDSs with 32 bit frequency, 16
@@ -95,6 +138,14 @@ class Phaser:
     absolute phase with respect to other RTIO input and output events
     (see `get_next_frame_mu()`).
 
+    **Miqro mode**
+
+    See :class:`Miqro`
+
+    Here the DAC operates in 4x interpolation.
+
+    **Analog flow**
+
     The four analog DAC outputs are passed through anti-aliasing filters.
 
     In the baseband variant, the even/in-phase DAC channels feed 31.5 dB range
@@ -112,6 +163,33 @@ class Phaser:
     configured through a shared SPI bus that is accessed and controlled via
     FPGA registers.
 
+    **Servo**
+
+    Each phaser output channel features a servo to control the RF output amplitude
+    using feedback from an ADC. The servo consists of a first order IIR (infinite
+    impulse response) filter fed by the ADC and a multiplier that scales the I
+    and Q datastreams from the DUC by the IIR output. The IIR state is updated at
+    the 3.788 MHz ADC sampling rate.
+
+    Each channel IIR features 4 profiles, each consisting of the [b0, b1, a1] filter
+    coefficients as well as an output offset. The coefficients and offset can be
+    set for each profile individually and the profiles each have their own ``y0``,
+    ``y1`` output registers (the ``x0``, ``x1`` inputs are shared). To avoid
+    transient effects, care should be taken to not update the coefficents in the
+    currently selected profile.
+
+    The servo can be en- or disabled for each channel. When disabled, the servo
+    output multiplier is simply bypassed and the datastream reaches the DAC unscaled.
+
+    The IIR output can be put on hold for each channel. In hold mode, the filter
+    still ingests samples and updates its input ``x0`` and ``x1`` registers, but
+    does not update the ``y0``, ``y1`` output registers.
+
+    After power-up the servo is disabled, in profile 0, with coefficients [0, 0, 0]
+    and hold is enabled. If older gateware without ther servo is loaded onto the
+    Phaser FPGA, the device simply behaves as if the servo is disabled and none of
+    the servo functions have any effect.
+
     .. note:: Various register settings of the DAC and the quadrature
         upconverters are available to be modified through the `dac`, `trf0`,
         `trf1` dictionaries. These can be set through the device database
@@ -151,7 +229,7 @@ class Phaser:
                          "dac_mmap"}
 
     def __init__(self, dmgr, channel_base, miso_delay=1, tune_fifo_offset=True,
-                 clk_sel=0, sync_dly=0, dac=None, trf0=None, trf1=None,
+                 clk_sel=0, sync_dly=0, dac=None, trf0=None, trf1=None, gw_rev=PHASER_GW_BASE,
                  core_device="core"):
         self.channel_base = channel_base
         self.core = dmgr.get(core_device)
@@ -165,12 +243,25 @@ class Phaser:
         self.clk_sel = clk_sel
         self.tune_fifo_offset = tune_fifo_offset
         self.sync_dly = sync_dly
+        self.gw_rev = gw_rev  # verified in init()
 
         self.dac_mmap = DAC34H84(dac).get_mmap()
 
         self.channel = [PhaserChannel(self, ch, trf)
                         for ch, trf in enumerate([trf0, trf1])]
 
+    @staticmethod
+    def get_rtio_channels(channel_base, gw_rev=PHASER_GW_BASE, **kwargs):
+        if gw_rev == PHASER_GW_MIQRO:
+            return [(channel_base, "base"), (channel_base + 1, "ch0"), (channel_base + 2, "ch1")]
+        elif gw_rev == PHASER_GW_BASE:
+            return [(channel_base, "base"),
+                    (channel_base + 1, "ch0 frequency"),
+                    (channel_base + 2, "ch0 phase amplitude"),
+                    (channel_base + 3, "ch1 frequency"),
+                    (channel_base + 4, "ch1 phase amplitude")]
+        raise ValueError("invalid gw_rev `{}`".format(gw_rev))
+
     @kernel
     def init(self, debug=False):
         """Initialize the board.
@@ -190,8 +281,9 @@ class Phaser:
 
         gw_rev = self.read8(PHASER_ADDR_GW_REV)
         if debug:
-            print("gw_rev:", gw_rev)
+            print("gw_rev:", self.gw_rev)
             self.core.break_realtime()
+        assert gw_rev == self.gw_rev
         delay(.1*ms)  # slack
 
         # allow a few errors during startup and alignment since boot
@@ -237,7 +329,7 @@ class Phaser:
 
         for data in self.dac_mmap:
             self.dac_write(data >> 16, data)
-            delay(40*us)
+            delay(120*us)
         self.dac_sync()
         delay(40*us)
 
@@ -308,8 +400,11 @@ class Phaser:
             if channel.get_att_mu() != 0x5a:
                 raise ValueError("attenuator test failed")
             delay(.1*ms)
-            channel.set_att_mu(0x00)  # minimum attenuation
+            channel.set_att_mu(0x00)  # maximum attenuation
 
+            channel.set_servo(profile=0, enable=0, hold=1)
+
+            if self.gw_rev == PHASER_GW_BASE:
                 # test oscillators and DUC
                 for i in range(len(channel.oscillator)):
                     oscillator = channel.oscillator[i]
@@ -337,6 +432,9 @@ class Phaser:
                         abs(data_i - data_q) > 2):
                     raise ValueError("DUC+oscillator phase/amplitude test failed")
 
+            if self.gw_rev == PHASER_GW_MIQRO:
+                channel.miqro.reset()
+
             if is_baseband:
                 continue
 
@@ -382,6 +480,12 @@ class Phaser:
         response = rtio_input_data(self.channel_base)
         return response >> self.miso_delay
 
+    @kernel
+    def write16(self, addr, data: TInt32):
+        """Write 16 bit to a sequence of FPGA registers."""
+        self.write8(addr, data >> 8)
+        self.write8(addr + 1, data)
+
     @kernel
     def write32(self, addr, data: TInt32):
         """Write 32 bit to a sequence of FPGA registers."""
@@ -460,8 +564,7 @@ class Phaser:
         * :const:`PHASER_STA_TRF1_LD`: Quadrature upconverter 1 lock detect
         * :const:`PHASER_STA_TERM0`: ADC channel 0 termination indicator
         * :const:`PHASER_STA_TERM1`: ADC channel 1 termination indicator
-        * :const:`PHASER_STA_SPI_IDLE`: SPI machine is idle and data registers
+        * :const:`PHASER_STA_SPI_IDLE`: SPI machine is idle and data registers can be read/written
-            can be read/written
 
         :return: Status register
         """
@@ -617,7 +720,7 @@ class Phaser:
         .. note:: Synchronising the NCO clears the phase-accumulator
         """
         config1f = self.dac_read(0x1f)
-        delay(.1*ms)
+        delay(.4*ms)
         self.dac_write(0x1f, config1f & ~int32(1 << 1))
         self.dac_write(0x1f, config1f | (1 << 1))
 
@@ -737,6 +840,8 @@ class Phaser:
             if good & (1 << o):
                 sum += o
                 count += 1
+        if count == 0:
+            raise ValueError("no good fifo offset")
         best = ((sum // count) + offset) % 8
         self.dac_write(0x09, (config9 & 0x1fff) | (best << 13))
         return best
@@ -747,18 +852,21 @@ class PhaserChannel:
 
     A Phaser channel contains:
 
-    * multiple oscillators (in the coredevice phy),
+    * multiple :class:`PhaserOscillator` (in the coredevice phy),
     * an interpolation chain and digital upconverter (DUC) on Phaser,
+    * a :class:`Miqro` instance on Phaser,
     * several channel-specific settings in the DAC:
+
         * quadrature modulation compensation QMC
         * numerically controlled oscillator NCO or coarse mixer CMIX,
-    * the analog quadrature upconverter (in the Phaser-Upconverter hardware
+
-        variant), and
+    * the analog quadrature upconverter (in the Phaser-Upconverter hardware variant), and
     * a digitally controlled step attenuator.
 
     Attributes:
 
     * :attr:`oscillator`: List of five :class:`PhaserOscillator`.
+    * :attr:`miqro`: A :class:`Miqro`.
 
     .. note:: The amplitude sum of the oscillators must be less than one to
         avoid clipping or overflow. If any of the DDS or DUC frequencies are
@@ -771,6 +879,8 @@ class PhaserChannel:
         changes in oscillator parameters, the overshoot can lead to clipping
         or overflow after the interpolation. Either band-limit any changes
         in the oscillator parameters or back off the amplitude sufficiently.
+        Miqro is not affected by this. But both the oscillators and Miqro can
+        be affected by intrinsic overshoot of the interpolator on the DAC.
     """
     kernel_invariants = {"index", "phaser", "trf_mmap"}
 
@@ -780,6 +890,7 @@ class PhaserChannel:
         self.trf_mmap = TRF372017(trf).get_mmap()
 
         self.oscillator = [PhaserOscillator(self, osc) for osc in range(5)]
+        self.miqro = Miqro(self)
 
     @kernel
     def get_dac_data(self) -> TInt32:
@@ -1039,6 +1150,133 @@ class PhaserChannel:
             data = data ^ ((1 << 12) | (1 << 13))
         self.trf_write(data)
 
+    @kernel
+    def set_servo(self, profile=0, enable=0, hold=0):
+        """Set the servo configuration.
+
+        :param enable: 1 to enable servo, 0 to disable servo (default). If disabled,
+            the servo is bypassed and hold is enforced since the control loop is broken.
+        :param hold: 1 to hold the servo IIR filter output constant, 0 for normal operation.
+        :param profile: Profile index to select for channel. (0 to 3)
+        """
+        if (profile < 0) or (profile > 3):
+            raise ValueError("invalid profile index")
+        addr = PHASER_ADDR_SERVO_CFG0 + self.index
+        # enforce hold if the servo is disabled
+        data = (profile << 2) | (((hold | ~enable) & 1) << 1) | (enable & 1)
+        self.phaser.write8(addr, data)
+
+    @kernel
+    def set_iir_mu(self, profile, b0, b1, a1, offset):
+        """Load a servo profile consiting of the three filter coefficients and an output offset.
+
+        Avoid setting the IIR parameters of the currently active profile.
+
+        The recurrence relation is (all data signed and MSB aligned):
+
+        .. math::
+            a_0 y_n = a_1 y_{n - 1} + b_0 x_n + b_1 x_{n - 1} + o
+
+        Where:
+
+            * :math:`y_n` and :math:`y_{n-1}` are the current and previous
+              filter outputs, clipped to :math:`[0, 1[`.
+            * :math:`x_n` and :math:`x_{n-1}` are the current and previous
+              filter inputs in :math:`[-1, 1[`.
+            * :math:`o` is the offset
+            * :math:`a_0` is the normalization factor :math:`2^{14}`
+            * :math:`a_1` is the feedback gain
+            * :math:`b_0` and :math:`b_1` are the feedforward gains for the two
+              delays
+
+        .. seealso:: :meth:`set_iir`
+
+        :param profile: Profile to set (0 to 3)
+        :param b0: b0 filter coefficient (16 bit signed)
+        :param b1: b1 filter coefficient (16 bit signed)
+        :param a1: a1 filter coefficient (16 bit signed)
+        :param offset: Output offset (16 bit signed)
+        """
+        if (profile < 0) or (profile > 3):
+            raise ValueError("invalid profile index")
+        # 32 byte-sized data registers per channel and 8 (2 bytes * (3 coefficients + 1 offset)) registers per profile
+        addr = PHASER_ADDR_SERVO_DATA_BASE + (8 * profile) + (self.index * 32)
+        for data in [b0, b1, a1, offset]:
+            self.phaser.write16(addr, data)
+            addr += 2
+
+    @kernel
+    def set_iir(self, profile, kp, ki=0., g=0., x_offset=0., y_offset=0.):
+        """Set servo profile IIR coefficients.
+
+        Avoid setting the IIR parameters of the currently active profile.
+
+        Gains are given in units of output full per scale per input full scale.
+
+        .. note:: Due to inherent constraints of the fixed point datatypes and IIR
+            filters, the ``x_offset`` (setpoint) resolution depends on the selected
+            gains. Low ``ki`` gains will lead to a low ``x_offset`` resolution.
+
+        The transfer function is (up to time discretization and
+        coefficient quantization errors):
+
+        .. math::
+            H(s) = k_p + \\frac{k_i}{s + \\frac{k_i}{g}}
+
+        Where:
+            * :math:`s = \\sigma + i\\omega` is the complex frequency
+            * :math:`k_p` is the proportional gain
+            * :math:`k_i` is the integrator gain
+            * :math:`g` is the integrator gain limit
+
+        :param profile: Profile number (0-3)
+        :param kp: Proportional gain. This is usually negative (closed
+            loop, positive ADC voltage, positive setpoint). When 0, this
+            implements a pure I controller.
+        :param ki: Integrator gain (rad/s). Equivalent to the gain at 1 Hz.
+            When 0 (the default) this implements a pure P controller.
+            Same sign as ``kp``.
+        :param g: Integrator gain limit (1). When 0 (the default) the
+            integrator gain limit is infinite. Same sign as ``ki``.
+        :param x_offset: IIR input offset. Used as the negative
+            setpoint when stabilizing to a desired input setpoint. Will
+            be converted to an equivalent output offset and added to y_offset.
+        :param y_offset: IIR output offset.
+        """
+        NORM = 1 << SERVO_COEFF_SHIFT
+        COEFF_MAX = 1 << SERVO_COEFF_WIDTH - 1
+        DATA_MAX = 1 << SERVO_DATA_WIDTH - 1
+
+        kp *= NORM
+        if ki == 0.:
+            # pure P
+            a1 = 0
+            b1 = 0
+            b0 = int(round(kp))
+        else:
+            # I or PI
+            ki *= NORM*SERVO_T_CYCLE/2.
+            if g == 0.:
+                c = 1.
+                a1 = NORM
+            else:
+                c = 1./(1. + ki/(g*NORM))
+                a1 = int(round((2.*c - 1.)*NORM))
+            b0 = int(round(kp + ki*c))
+            b1 = int(round(kp + (ki - 2.*kp)*c))
+            if b1 == -b0:
+                raise ValueError("low integrator gain and/or gain limit")
+
+        if (b0 >= COEFF_MAX or b0 < -COEFF_MAX or
+                b1 >= COEFF_MAX or b1 < -COEFF_MAX):
+            raise ValueError("high gains")
+
+        forward_gain = (b0 + b1) * (1 << SERVO_DATA_WIDTH - 1 - SERVO_COEFF_SHIFT)
+        effective_offset = int(round(DATA_MAX * y_offset + forward_gain * x_offset))
+
+        self.set_iir_mu(profile, b0, b1, a1, effective_offset)
+
+
 
 class PhaserOscillator:
     """Phaser IQ channel oscillator (NCO/DDS).
@@ -1096,3 +1334,305 @@ class PhaserOscillator:
             raise ValueError("amplitude out of bounds")
         pow = int32(round(phase*(1 << 16)))
         self.set_amplitude_phase_mu(asf, pow, clr)
+
+
+class Miqro:
+    """
+    Miqro pulse generator.
+
+    A Miqro instance represents one RF output. The DSP components are fully
+    contained in the Phaser gateware. The output is generated by with
+    the following data flow:
+
+    **Oscillators**
+
+    * There are n_osc = 16 oscillators with oscillator IDs 0..n_osc-1.
+    * Each oscillator outputs one tone at any given time
+
+        * I/Q (quadrature, a.k.a. complex) 2x16 bit signed data
+          at tau = 4 ns sample intervals, 250 MS/s, Nyquist 125 MHz, bandwidth 200 MHz
+          (from f = -100..+100 MHz, taking into account the interpolation anti-aliasing
+          filters in subsequent interpolators),
+        * 32 bit frequency (f) resolution (~ 1/16 Hz),
+        * 16 bit unsigned amplitude (a) resolution
+        * 16 bit phase offset (p) resolution
+
+    * The output phase p' of each oscillator at time t (boot/reset/initialization of the
+      device at t=0) is then p' = f*t + p (mod 1 turn) where f and p are the (currently
+      active) profile frequency and phase offset.
+    * Note: The terms  "phase coherent" and "phase tracking" are defined to refer to this
+      choice of oscillator output phase p'. Note that the phase offset p is not relative to
+      (on top of previous phase/profiles/oscillator history).
+      It is "absolute" in the sense that frequency f and phase offset p fully determine
+      oscillator output phase p' at time t. This is unlike typical DDS behavior.
+    * Frequency, phase, and amplitude of each oscillator are configurable by selecting one of
+      n_profile = 32 profiles 0..n_profile-1. This selection is fast and can be done for
+      each pulse. The phase coherence defined above is guaranteed for each
+      profile individually.
+    * Note: one profile per oscillator (usually profile index 0) should be reserved
+      for the NOP (no operation, identity) profile, usually with zero amplitude.
+    * Data for each profile for each oscillator can be configured
+      individually. Storing profile data should be considered "expensive".
+    * Note: The annotation that some operation is "expensive" does not mean it is
+      impossible, just that it may take a significant amount of time and
+      resources to execute such that it may be impractical when used often or
+      during fast pulse sequences. They are intended for use in calibration and
+      initialization.
+
+    **Summation**
+
+    * The oscillator outputs are added together (wrapping addition).
+    * The user must ensure that the sum of oscillators outputs does not exceed the
+      data range. In general that means that the sum of the amplitudes must not
+      exceed one.
+
+    **Shaper**
+
+    * The summed complex output stream is then multiplied with a the complex-valued
+      output of a triggerable shaper.
+    * Triggering the shaper corresponds to passing a pulse from all oscillators to
+      the RF output.
+    * Selected profiles become active simultaneously (on the same output sample) when
+      triggering the shaper with the first shaper output sample.
+    * The shaper reads (replays) window samples from a memory of size n_window = 1 << 10.
+    * The window memory can be segmented by choosing different start indices
+      to support different windows.
+    * Each window memory segment starts with a header determining segment
+      length and interpolation parameters.
+    * The window samples are interpolated by a factor (rate change) between 1 and
+      r = 1 << 12.
+    * The interpolation order is constant, linear, quadratic, or cubic. This
+      corresponds to interpolation modes from rectangular window (1st order CIC)
+      or zero order hold) to Parzen window (4th order CIC or cubic spline).
+    * This results in support for single shot pulse lengths (envelope support) between
+      tau and a bit more than r * n_window * tau = (1 << 12 + 10) tau ~ 17 ms.
+    * Windows can be configured to be head-less and/or tail-less, meaning, they
+      do not feed zero-amplitude samples into the shaper before and after
+      each window respectively. This is used to implement pulses with arbitrary
+      length or CW output.
+
+    **Overall properties**
+
+    * The DAC may upconvert the signal by applying a frequency offset f1 with
+      phase p1.
+    * In the Upconverter Phaser variant, the analog quadrature upconverter
+      applies another frequency of f2 and phase p2.
+    * The resulting phase of the signal from one oscillator at the SMA output is
+      (f + f1 + f2)*t + p + s(t - t0) + p1 + p2 (mod 1 turn)
+      where s(t - t0) is the phase of the interpolated
+      shaper output, and t0 is the trigger time (fiducial of the shaper).
+      Unsurprisingly the frequency is the derivative of the phase.
+    * Group delays between pulse parameter updates are matched across oscillators,
+      shapers, and channels.
+    * The minimum time to change profiles and phase offsets is ~128 ns (estimate, TBC).
+      This is the minimum pulse interval.
+      The sustained pulse rate of the RTIO PHY/Fastlink is one pulse per Fastlink frame
+      (may be increased, TBC).
+    """
+
+    def __init__(self, channel):
+        self.channel = channel
+        self.base_addr = (self.channel.phaser.channel_base + 1 +
+                self.channel.index) << 8
+
+    @kernel
+    def reset(self):
+        """Establish no-output profiles and no-output window and execute them.
+
+        This establishes the first profile (index 0) on all oscillators as zero
+        amplitude, creates a trivial window (one sample with zero amplitude,
+        minimal interpolation), and executes a corresponding pulse.
+        """
+        for osc in range(16):
+            self.set_profile_mu(osc, profile=0, ftw=0, asf=0)
+            delay(20*us)
+        self.set_window_mu(start=0, iq=[0], order=0)
+        self.pulse(window=0, profiles=[0])
+
+    @kernel
+    def set_profile_mu(self, oscillator, profile, ftw, asf, pow_=0):
+        """Store an oscillator profile (machine units).
+
+        :param oscillator: Oscillator index (0 to 15)
+        :param profile: Profile index (0 to 31)
+        :param ftw: Frequency tuning word (32 bit signed integer on a 250 MHz clock)
+        :param asf: Amplitude scale factor (16 bit unsigned integer)
+        :param pow_: Phase offset word (16 bit integer)
+        """
+        if oscillator >= 16:
+            raise ValueError("invalid oscillator index")
+        if profile >= 32:
+            raise ValueError("invalid profile index")
+        self.channel.phaser.write16(PHASER_ADDR_MIQRO_MEM_ADDR,
+                (self.channel.index << 15) | PHASER_MIQRO_SEL_PROFILE |
+                (oscillator << 6) | (profile << 1))
+        self.channel.phaser.write32(PHASER_ADDR_MIQRO_MEM_DATA, ftw)
+        self.channel.phaser.write32(PHASER_ADDR_MIQRO_MEM_DATA,
+            (asf & 0xffff) | (pow_ << 16))
+
+    @kernel
+    def set_profile(self, oscillator, profile, frequency, amplitude, phase=0.):
+        """Store an oscillator profile.
+
+        :param oscillator: Oscillator index (0 to 15)
+        :param profile: Profile index (0 to 31)
+        :param frequency: Frequency in Hz (passband -100 to 100 MHz).
+            Interpreted in the Nyquist sense, i.e. aliased.
+        :param amplitude: Amplitude in units of full scale (0. to 1.)
+        :param phase: Phase in turns. See :class:`Miqro` for a definition of
+            phase in this context.
+        :return: The quantized 32 bit frequency tuning word
+        """
+        ftw = int32(round(frequency*((1 << 30)/(62.5*MHz))))
+        asf = int32(round(amplitude*0xffff))
+        if asf < 0 or asf > 0xffff:
+            raise ValueError("amplitude out of bounds")
+        pow_ = int32(round(phase*(1 << 16)))
+        self.set_profile_mu(oscillator, profile, ftw, asf, pow_)
+        return ftw
+
+    @kernel
+    def set_window_mu(self, start, iq, rate=1, shift=0, order=3, head=1, tail=1):
+        """Store a window segment (machine units)
+
+        :param start: Window start address (0 to 0x3ff)
+        :param iq: List of IQ window samples. Each window sample is an integer
+            containing the signed I part in the 16 LSB and the signed Q part in
+            the 16 MSB. The maximum window length is 0x3fe. The user must
+            ensure that this window does not overlap with other windows in the
+            memory.
+        :param rate: Interpolation rate change (1 to 1 << 12)
+        :param shift: Interpolator amplitude gain compensation in powers of 2 (0 to 63)
+        :param order: Interpolation order from 0 (corresponding to
+            constant/rectangular window/zero-order-hold/1st order CIC interpolation)
+            to 3 (corresponding to cubic/Parzen window/4th order CIC interpolation)
+        :param head: Update the interpolator settings and clear its state at the start
+            of the window. This also implies starting the envelope from zero.
+        :param tail: Feed zeros into the interpolator after the window samples.
+            In the absence of further pulses this will return the output envelope
+            to zero with the chosen interpolation.
+        :return: Next available window memory address after this segment.
+        """
+        if start >= 1 << 10:
+            raise ValueError("start out of bounds")
+        if len(iq) >= 1 << 10:
+            raise ValueError("window length out of bounds")
+        if rate < 1 or rate > 1 << 12:
+            raise ValueError("rate out of bounds")
+        if shift > 0x3f:
+            raise ValueError("shift out of bounds")
+        if order > 3:
+            raise ValueError("order out of bounds")
+        self.channel.phaser.write16(PHASER_ADDR_MIQRO_MEM_ADDR,
+                (self.channel.index << 15) | start)
+        self.channel.phaser.write32(PHASER_ADDR_MIQRO_MEM_DATA,
+            (len(iq) & 0x3ff) |
+            ((rate - 1) << 10) |
+            (shift << 22) |
+            (order << 28) |
+            ((head & 1) << 30) |
+            ((tail & 1) << 31)
+        )
+        for iqi in iq:
+            self.channel.phaser.write32(PHASER_ADDR_MIQRO_MEM_DATA, iqi)
+            delay(20*us)  # slack for long windows
+        return (start + 1 + len(iq)) & 0x3ff
+
+    @kernel
+    def set_window(self, start, iq, period=4*ns, order=3, head=1, tail=1):
+        """Store a window segment
+
+        :param start: Window start address (0 to 0x3ff)
+        :param iq: List of IQ window samples. Each window sample is a pair of
+            two float numbers -1 to 1, one for each I and Q in units of full scale.
+            The maximum window length is 0x3fe. The user must ensure that this window
+            does not overlap with other windows in the memory.
+        :param period: Desired window sample period in SI units (4*ns to (4 << 12)*ns).
+        :param order: Interpolation order from 0 (corresponding to
+            constant/zero-order-hold/1st order CIC interpolation) to 3 (corresponding
+            to cubic/Parzen/4th order CIC interpolation)
+        :param head: Update the interpolator settings and clear its state at the start
+            of the window. This also implies starting the envelope from zero.
+        :param tail: Feed zeros into the interpolator after the window samples.
+            In the absence of further pulses this will return the output envelope
+            to zero with the chosen interpolation.
+        :return: Actual sample period in SI units
+        """
+        rate = int32(round(period/(4*ns)))
+        gain = 1.
+        for _ in range(order):
+            gain *= rate
+        shift = 0
+        while gain >= 2.:
+            shift += 1
+            gain *= .5
+        scale = ((1 << 15) - 1)/gain
+        iq_mu = [
+            (int32(round(iqi[0]*scale)) & 0xffff) |
+            (int32(round(iqi[1]*scale)) << 16)
+            for iqi in iq
+        ]
+        self.set_window_mu(start, iq_mu, rate, shift, order, head, tail)
+        return (len(iq) + order)*rate*4*ns
+
+    @kernel
+    def encode(self, window, profiles, data):
+        """Encode window and profile selection
+
+        :param window: Window start address (0 to 0x3ff)
+        :param profiles: List of profile indices for the oscillators. Maximum
+            length 16. Unused oscillators will be set to profile 0.
+        :param data: List of integers to store the encoded data words into.
+            Unused entries will remain untouched. Must contain at least three
+            lements if all oscillators are used and should be initialized to
+            zeros.
+        :return: Number of words from `data` used.
+        """
+        if len(profiles) > 16:
+            raise ValueError("too many oscillators")
+        if window > 0x3ff:
+            raise ValueError("window start out of bounds")
+        data[0] = window
+        word = 0
+        idx = 10
+        for profile in profiles:
+            if profile > 0x1f:
+                raise ValueError("profile out of bounds")
+            if idx > 32 - 5:
+                word += 1
+                idx = 0
+            data[word] |= profile << idx
+            idx += 5
+        return word + 1
+
+    @kernel
+    def pulse_mu(self, data):
+        """Emit a pulse (encoded)
+
+        The pulse fiducial timing resolution is 4 ns.
+
+        :param data: List of up to 3 words containing an encoded MIQRO pulse as
+            returned by :meth:`encode`.
+        """
+        word = len(data)
+        delay_mu(-8*word)  # back shift to align
+        while word > 0:
+            word -= 1
+            delay_mu(8)
+            # final write sets pulse stb
+            rtio_output(self.base_addr + word, data[word])
+
+    @kernel
+    def pulse(self, window, profiles):
+        """Emit a pulse
+
+        This encodes the window and profiles (see :meth:`encode`) and emits them
+        (see :meth:`pulse_mu`).
+
+        :param window: Window start address (0 to 0x3ff)
+        :param profiles: List of profile indices for the oscillators. Maximum
+            length 16. Unused oscillators will select profile 0.
+        """
+        data = [0, 0, 0]
+        words = self.encode(window, profiles, data)
+        self.pulse_mu(data[:words])

artiq/coredevice/sampler.py

@@ -15,24 +15,26 @@ SPI_CS_PGIA = 1  # separate SPI bus, CS used as RCLK
 
 
 @portable
-def adc_mu_to_volt(data, gain=0):
+def adc_mu_to_volt(data, gain=0, corrected_fs=True):
     """Convert ADC data in machine units to Volts.
 
     :param data: 16 bit signed ADC word
     :param gain: PGIA gain setting (0: 1, ..., 3: 1000)
+    :param corrected_fs: use corrected ADC FS reference.
+    Should be True for Samplers' revisions after v2.1. False for v2.1 and earlier.
     :return: Voltage in Volts
     """
     if gain == 0:
-        volt_per_lsb = 20./(1 << 16)
+        volt_per_lsb = 20.48 / (1 << 16) if corrected_fs else 20. / (1 << 16)
     elif gain == 1:
-        volt_per_lsb = 2./(1 << 16)
+        volt_per_lsb = 2.048 / (1 << 16) if corrected_fs else 2. / (1 << 16)
     elif gain == 2:
-        volt_per_lsb = .2/(1 << 16)
+        volt_per_lsb = .2048 / (1 << 16) if corrected_fs else .2 / (1 << 16)
     elif gain == 3:
-        volt_per_lsb = .02/(1 << 16)
+        volt_per_lsb = 0.02048 / (1 << 16) if corrected_fs else .02 / (1 << 16)
     else:
         raise ValueError("invalid gain")
-    return data*volt_per_lsb
+    return data * volt_per_lsb
 
 
 class Sampler:
@@ -48,12 +50,13 @@ class Sampler:
     :param gains: Initial value for PGIA gains shift register
         (default: 0x0000). Knowledge of this state is not transferred
         between experiments.
+    :param hw_rev: Sampler's hardware revision string (default 'v2.2')
     :param core_device: Core device name
     """
-    kernel_invariants = {"bus_adc", "bus_pgia", "core", "cnv", "div"}
+    kernel_invariants = {"bus_adc", "bus_pgia", "core", "cnv", "div", "corrected_fs"}
 
     def __init__(self, dmgr, spi_adc_device, spi_pgia_device, cnv_device,
-                 div=8, gains=0x0000, core_device="core"):
+                 div=8, gains=0x0000, hw_rev="v2.2", core_device="core"):
         self.bus_adc = dmgr.get(spi_adc_device)
         self.bus_adc.update_xfer_duration_mu(div, 32)
         self.bus_pgia = dmgr.get(spi_pgia_device)
@@ -62,6 +65,11 @@ class Sampler:
         self.cnv = dmgr.get(cnv_device)
         self.div = div
         self.gains = gains
+        self.corrected_fs = self.use_corrected_fs(hw_rev)
+
+    @staticmethod
+    def use_corrected_fs(hw_rev):
+        return hw_rev != "v2.1"
 
     @kernel
     def init(self):
@@ -144,4 +152,4 @@ class Sampler:
         for i in range(n):
             channel = i + 8 - len(data)
             gain = (self.gains >> (channel*2)) & 0b11
-            data[i] = adc_mu_to_volt(adc_data[i], gain)
+            data[i] = adc_mu_to_volt(adc_data[i], gain, self.corrected_fs)

artiq/coredevice/sawg.py

@@ -1,372 +0,0 @@
-"""
-Driver for the Smart Arbitrary Waveform Generator (SAWG) on RTIO.
-
-The SAWG is an "improved DDS" built in gateware and interfacing to
-high-speed DACs.
-
-Output event replacement is supported except on the configuration channel.
-"""
-
-
-from artiq.language.types import TInt32, TFloat
-from numpy import int32, int64
-from artiq.language.core import kernel
-from artiq.coredevice.spline import Spline
-from artiq.coredevice.rtio import rtio_output
-
-
-# sawg.Config addresses
-_SAWG_DIV = 0
-_SAWG_CLR = 1
-_SAWG_IQ_EN = 2
-# _SAWF_PAD = 3  # reserved
-_SAWG_OUT_MIN = 4
-_SAWG_OUT_MAX = 5
-_SAWG_DUC_MIN = 6
-_SAWG_DUC_MAX = 7
-
-
-class Config:
-    """SAWG configuration.
-
-    Exposes the configurable quantities of a single SAWG channel.
-
-    Access to the configuration registers for a SAWG channel can not
-    be concurrent. There must be at least :attr:`_rtio_interval` machine
-    units of delay between accesses. Replacement is not supported and will be
-    lead to an ``RTIOCollision`` as this is likely a programming error.
-    All methods therefore advance the timeline by the duration of one
-    configuration register transfer.
-
-    :param channel: RTIO channel number of the channel.
-    :param core: Core device.
-    """
-    kernel_invariants = {"channel", "core", "_out_scale", "_duc_scale",
-            "_rtio_interval"}
-
-    def __init__(self, channel, core, cordic_gain=1.):
-        self.channel = channel
-        self.core = core
-        # normalized DAC output
-        self._out_scale = (1 << 15) - 1.
-        # normalized DAC output including DUC cordic gain
-        self._duc_scale = self._out_scale/cordic_gain
-        # configuration channel access interval
-        self._rtio_interval = int64(3*self.core.ref_multiplier)
-
-    @kernel
-    def set_div(self, div: TInt32, n: TInt32=0):
-        """Set the spline evolution divider and current counter value.
-
-        The divider and the spline evolution are synchronized across all
-        spline channels within a SAWG channel. The DDS/DUC phase accumulators
-        always evolves at full speed.
-
-        .. note:: The spline evolution divider has not been tested extensively
-            and is currently considered a technological preview only.
-
-        :param div: Spline evolution divider, such that
-            ``t_sawg_spline/t_rtio_coarse = div + 1``. Default: ``0``.
-        :param n: Current value of the counter. Default: ``0``.
-        """
-        rtio_output((self.channel << 8) | _SAWG_DIV, div | (n << 16))
-        delay_mu(self._rtio_interval)
-
-    @kernel
-    def set_clr(self, clr0: TInt32, clr1: TInt32, clr2: TInt32):
-        """Set the accumulator clear mode for the three phase accumulators.
-
-        When the ``clr`` bit for a given DDS/DUC phase accumulator is
-        set, that phase accumulator will be cleared with every phase offset
-        RTIO command and the output phase of the DDS/DUC will be
-        exactly the phase RTIO value ("absolute phase update mode").
-
-        .. math::
-            q^\prime(t) = p^\prime + (t - t^\prime) f^\prime
-
-        In turn, when the bit is cleared, the phase RTIO channels
-        determine a phase offset to the current (carrier-) value of the
-        DDS/DUC phase accumulator. This "relative phase update mode" is
-        sometimes also called “continuous phase mode”.
-
-        .. math::
-            q^\prime(t) = q(t^\prime) + (p^\prime - p) +
-                (t - t^\prime) f^\prime
-
-        Where:
-
-            * :math:`q`, :math:`q^\prime`: old/new phase accumulator
-            * :math:`p`, :math:`p^\prime`: old/new phase offset
-            * :math:`f^\prime`: new frequency
-            * :math:`t^\prime`: timestamp of setting new :math:`p`, :math:`f`
-            * :math:`t`: running time
-
-        :param clr0: Auto-clear phase accumulator of the ``phase0``/
-          ``frequency0`` DUC. Default: ``True``
-        :param clr1: Auto-clear phase accumulator of the ``phase1``/
-          ``frequency1`` DDS. Default: ``True``
-        :param clr2: Auto-clear phase accumulator of the ``phase2``/
-          ``frequency2`` DDS. Default: ``True``
-        """
-        rtio_output((self.channel << 8) | _SAWG_CLR, clr0 |
-                (clr1 << 1) | (clr2 << 2))
-        delay_mu(self._rtio_interval)
-
-    @kernel
-    def set_iq_en(self, i_enable: TInt32, q_enable: TInt32):
-        """Enable I/Q data on this DAC channel.
-
-        Every pair of SAWG channels forms a buddy pair.
-        The ``iq_en`` configuration controls which DDS data is emitted to the
-        DACs.
-
-        Refer to the documentation of :class:`SAWG` for a mathematical
-        description of ``i_enable`` and ``q_enable``.
-
-        .. note:: Quadrature data from the buddy channel is currently
-            a technological preview only. The data is ignored in the SAWG
-            gateware and not added to the DAC output.
-            This is equivalent to the ``q_enable`` switch always being ``0``.
-
-        :param i_enable: Controls adding the in-phase
-              DUC-DDS data of *this* SAWG channel to *this* DAC channel.
-              Default: ``1``.
-        :param q_enable: controls adding the quadrature
-              DUC-DDS data of this SAWG's *buddy* channel to *this* DAC
-              channel. Default: ``0``.
-        """
-        rtio_output((self.channel << 8) | _SAWG_IQ_EN, i_enable |
-                (q_enable << 1))
-        delay_mu(self._rtio_interval)
-
-    @kernel
-    def set_duc_max_mu(self, limit: TInt32):
-        """Set the digital up-converter (DUC) I and Q data summing junctions
-        upper limit. In machine units.
-
-        The default limits are chosen to reach maximum and minimum DAC output
-        amplitude.
-
-        For a description of the limiter functions in normalized units see:
-
-        .. seealso:: :meth:`set_duc_max`
-        """
-        rtio_output((self.channel << 8) | _SAWG_DUC_MAX, limit)
-        delay_mu(self._rtio_interval)
-
-    @kernel
-    def set_duc_min_mu(self, limit: TInt32):
-        """.. seealso:: :meth:`set_duc_max_mu`"""
-        rtio_output((self.channel << 8) | _SAWG_DUC_MIN, limit)
-        delay_mu(self._rtio_interval)
-
-    @kernel
-    def set_out_max_mu(self, limit: TInt32):
-        """.. seealso:: :meth:`set_duc_max_mu`"""
-        rtio_output((self.channel << 8) | _SAWG_OUT_MAX, limit)
-        delay_mu(self._rtio_interval)
-
-    @kernel
-    def set_out_min_mu(self, limit: TInt32):
-        """.. seealso:: :meth:`set_duc_max_mu`"""
-        rtio_output((self.channel << 8) | _SAWG_OUT_MIN, limit)
-        delay_mu(self._rtio_interval)
-
-    @kernel
-    def set_duc_max(self, limit: TFloat):
-        """Set the digital up-converter (DUC) I and Q data summing junctions
-        upper limit.
-
-        Each of the three summing junctions has a saturating adder with
-        configurable upper and lower limits. The three summing junctions are:
-
-            * At the in-phase input to the ``phase0``/``frequency0`` fast DUC,
-              after the anti-aliasing FIR filter.
-            * At the quadrature input to the ``phase0``/``frequency0``
-              fast DUC, after the anti-aliasing FIR filter. The in-phase and
-              quadrature data paths both use the same limits.
-            * Before the DAC, where the following three data streams
-              are added together:
-
-                * the output of the ``offset`` spline,
-                * (optionally, depending on ``i_enable``) the in-phase output
-                  of the ``phase0``/``frequency0`` fast DUC, and
-                * (optionally, depending on ``q_enable``) the quadrature
-                  output of the ``phase0``/``frequency0`` fast DUC of the
-                  buddy channel.
-
-        Refer to the documentation of :class:`SAWG` for a mathematical
-        description of the summing junctions.
-
-        :param limit: Limit value ``[-1, 1]``. The output of the limiter will
-            never exceed this limit. The default limits are the full range
-            ``[-1, 1]``.
-
-        .. seealso::
-            * :meth:`set_duc_max`: Upper limit of the in-phase and quadrature
-              inputs to the DUC.
-            * :meth:`set_duc_min`: Lower limit of the in-phase and quadrature
-              inputs to the DUC.
-            * :meth:`set_out_max`: Upper limit of the DAC output.
-            * :meth:`set_out_min`: Lower limit of the DAC output.
-        """
-        self.set_duc_max_mu(int32(round(limit*self._duc_scale)))
-
-    @kernel
-    def set_duc_min(self, limit: TFloat):
-        """.. seealso:: :meth:`set_duc_max`"""
-        self.set_duc_min_mu(int32(round(limit*self._duc_scale)))
-
-    @kernel
-    def set_out_max(self, limit: TFloat):
-        """.. seealso:: :meth:`set_duc_max`"""
-        self.set_out_max_mu(int32(round(limit*self._out_scale)))
-
-    @kernel
-    def set_out_min(self, limit: TFloat):
-        """.. seealso:: :meth:`set_duc_max`"""
-        self.set_out_min_mu(int32(round(limit*self._out_scale)))
-
-
-class SAWG:
-    """Smart arbitrary waveform generator channel.
-    The channel is parametrized as: ::
-
-        oscillators = exp(2j*pi*(frequency0*t + phase0))*(
-            amplitude1*exp(2j*pi*(frequency1*t + phase1)) +
-            amplitude2*exp(2j*pi*(frequency2*t + phase2)))
-
-        output = (offset +
-            i_enable*Re(oscillators) +
-            q_enable*Im(buddy_oscillators))
-
-    This parametrization can be viewed as two complex (quadrature) oscillators
-    (``frequency1``/``phase1`` and ``frequency2``/``phase2``) that are
-    executing and sampling at the coarse RTIO frequency. They can represent
-    frequencies within the first Nyquist zone from ``-f_rtio_coarse/2`` to
-    ``f_rtio_coarse/2``.
-
-    .. note:: The coarse RTIO frequency ``f_rtio_coarse`` is the inverse of
-      ``ref_period*multiplier``. Both are arguments of the ``Core`` device,
-      specified in the device database ``device_db.py``.
-
-    The sum of their outputs is then interpolated by a factor of
-    :attr:`parallelism` (2, 4, 8 depending on the bitstream) using a
-    finite-impulse-response (FIR) anti-aliasing filter (more accurately
-    a half-band filter).
-
-    The filter is followed by a configurable saturating limiter.
-
-    After the limiter, the data is shifted in frequency using a complex
-    digital up-converter (DUC, ``frequency0``/``phase0``) running at
-    :attr:`parallelism` times the coarse RTIO frequency. The first Nyquist
-    zone of the DUC extends from ``-f_rtio_coarse*parallelism/2`` to
-    ``f_rtio_coarse*parallelism/2``. Other Nyquist zones are usable depending
-    on the interpolation/modulation options configured in the DAC.
-
-    The real/in-phase data after digital up-conversion can be offset using
-    another spline interpolator ``offset``.
-
-    The ``i_enable``/``q_enable`` switches enable emission of quadrature
-    signals for later analog quadrature mixing distinguishing upper and lower
-    sidebands and thus doubling the bandwidth. They can also be used to emit
-    four-tone signals.
-
-    .. note:: Quadrature data from the buddy channel is currently
-       ignored in the SAWG gateware and not added to the DAC output.
-       This is equivalent to the ``q_enable`` switch always being ``0``.
-
-    The configuration channel and the nine
-    :class:`artiq.coredevice.spline.Spline` interpolators are accessible as
-    attributes:
-
-    * :attr:`config`: :class:`Config`
-    * :attr:`offset`, :attr:`amplitude1`, :attr:`amplitude2`: in units
-      of full scale
-    * :attr:`phase0`, :attr:`phase1`, :attr:`phase2`: in units of turns
-    * :attr:`frequency0`, :attr:`frequency1`, :attr:`frequency2`: in units
-      of Hz
-
-    .. note:: The latencies (pipeline depths) of the nine data channels (i.e.
-        all except :attr:`config`) are matched. Equivalent channels (e.g.
-        :attr:`phase1` and :attr:`phase2`) are exactly matched. Channels of
-        different type or functionality (e.g. :attr:`offset` vs
-        :attr:`amplitude1`, DDS vs DUC, :attr:`phase0` vs :attr:`phase1`) are
-        only matched to within one coarse RTIO cycle.
-
-    :param channel_base: RTIO channel number of the first channel (amplitude).
-        The configuration channel and frequency/phase/amplitude channels are
-        then assumed to be successive channels.
-    :param parallelism: Number of output samples per coarse RTIO clock cycle.
-    :param core_device: Name of the core device that this SAWG is on.
-    """
-    kernel_invariants = {"channel_base", "core", "parallelism",
-                         "amplitude1", "frequency1", "phase1",
-                         "amplitude2", "frequency2", "phase2",
-                         "frequency0", "phase0", "offset"}
-
-    def __init__(self, dmgr, channel_base, parallelism, core_device="core"):
-        self.core = dmgr.get(core_device)
-        self.channel_base = channel_base
-        self.parallelism = parallelism
-        width = 16
-        time_width = 16
-        cordic_gain = 1.646760258057163  # Cordic(width=16, guard=None).gain
-        head_room = 1.001
-        self.config = Config(channel_base, self.core, cordic_gain)
-        self.offset = Spline(width, time_width, channel_base + 1,
-                             self.core, 2.*head_room)
-        self.amplitude1 = Spline(width, time_width, channel_base + 2,
-                                 self.core, 2*head_room*cordic_gain**2)
-        self.frequency1 = Spline(3*width, time_width, channel_base + 3,
-                                 self.core, 1/self.core.coarse_ref_period)
-        self.phase1 = Spline(width, time_width, channel_base + 4,
-                             self.core, 1.)
-        self.amplitude2 = Spline(width, time_width, channel_base + 5,
-                                 self.core, 2*head_room*cordic_gain**2)
-        self.frequency2 = Spline(3*width, time_width, channel_base + 6,
-                                 self.core, 1/self.core.coarse_ref_period)
-        self.phase2 = Spline(width, time_width, channel_base + 7,
-                             self.core, 1.)
-        self.frequency0 = Spline(2*width, time_width, channel_base + 8,
-                                 self.core,
-                                 parallelism/self.core.coarse_ref_period)
-        self.phase0 = Spline(width, time_width, channel_base + 9,
-                             self.core, 1.)
-
-    @kernel
-    def reset(self):
-        """Re-establish initial conditions.
-
-        This clears all spline interpolators, accumulators and configuration
-        settings.
-
-        This method advances the timeline by the time required to perform all
-        7 writes to the configuration channel, plus 9 coarse RTIO cycles.
-        """
-        self.config.set_div(0, 0)
-        self.config.set_clr(1, 1, 1)
-        self.config.set_iq_en(1, 0)
-        self.config.set_duc_min(-1.)
-        self.config.set_duc_max(1.)
-        self.config.set_out_min(-1.)
-        self.config.set_out_max(1.)
-        self.frequency0.set_mu(0)
-        coarse_cycle = int64(self.core.ref_multiplier)
-        delay_mu(coarse_cycle)
-        self.frequency1.set_mu(0)
-        delay_mu(coarse_cycle)
-        self.frequency2.set_mu(0)
-        delay_mu(coarse_cycle)
-        self.phase0.set_mu(0)
-        delay_mu(coarse_cycle)
-        self.phase1.set_mu(0)
-        delay_mu(coarse_cycle)
-        self.phase2.set_mu(0)
-        delay_mu(coarse_cycle)
-        self.amplitude1.set_mu(0)
-        delay_mu(coarse_cycle)
-        self.amplitude2.set_mu(0)
-        delay_mu(coarse_cycle)
-        self.offset.set_mu(0)
-        delay_mu(coarse_cycle)

artiq/coredevice/shiftreg.py

@@ -1,54 +0,0 @@
-from artiq.language.core import kernel, delay
-from artiq.language.units import us
-
-
-class ShiftReg:
-    """Driver for shift registers/latch combos connected to TTLs"""
-    kernel_invariants = {"dt", "n"}
-    
-    def __init__(self, dmgr, clk, ser, latch, n=32, dt=10*us, ser_in=None):
-        self.core = dmgr.get("core")
-        self.clk = dmgr.get(clk)
-        self.ser = dmgr.get(ser)
-        self.latch = dmgr.get(latch)
-        self.n = n
-        self.dt = dt
-        if ser_in is not None:
-            self.ser_in = dmgr.get(ser_in)
-
-    @kernel
-    def set(self, data):
-        """Sets the values of the latch outputs. This does not
-        advance the timeline and the waveform is generated before
-        `now`."""
-        delay(-2*(self.n + 1)*self.dt)
-        for i in range(self.n):
-            if (data >> (self.n-i-1)) & 1 == 0:
-                self.ser.off()
-            else:
-                self.ser.on()
-            self.clk.off()
-            delay(self.dt)
-            self.clk.on()
-            delay(self.dt)
-        self.clk.off()
-        self.latch.on()
-        delay(self.dt)
-        self.latch.off()
-        delay(self.dt)
-
-    @kernel
-    def get(self):
-        delay(-2*(self.n + 1)*self.dt)
-        data = 0
-        for i in range(self.n):
-            data <<= 1
-            self.ser_in.sample_input()
-            if self.ser_in.sample_get():
-                data |= 1
-            delay(self.dt)
-            self.clk.on()
-            delay(self.dt)
-            self.clk.off()
-        delay(self.dt)
-        return data

artiq/coredevice/shuttler.py

@@ -0,0 +1,623 @@
+from artiq.language.core import *
+from artiq.language.types import *
+from artiq.coredevice.rtio import rtio_output, rtio_input_data
+from artiq.coredevice import spi2 as spi
+from artiq.language.units import us
+
+
+@portable
+def shuttler_volt_to_mu(volt):
+    """Return the equivalent DAC code. Valid input range is from -10 to
+    10 - LSB.
+    """
+    return round((1 << 16) * (volt / 20.0)) & 0xffff
+
+
+class Config:
+    """Shuttler configuration registers interface.
+
+    The configuration registers control waveform phase auto-clear, and pre-DAC
+    gain & offset values for calibration with ADC on the Shuttler AFE card.
+
+    To find the calibrated DAC code, the Shuttler Core first multiplies the
+    output data with pre-DAC gain, then adds the offset.
+
+    .. note::
+        The DAC code is capped at 0x7fff and 0x8000.
+
+    :param channel: RTIO channel number of this interface.
+    :param core_device: Core device name.
+    """
+    kernel_invariants = {
+        "core", "channel", "target_base", "target_read",
+        "target_gain", "target_offset", "target_clr"
+    }
+
+    def __init__(self, dmgr, channel, core_device="core"):
+        self.core = dmgr.get(core_device)
+        self.channel = channel
+        self.target_base   = channel << 8
+        self.target_read   = 1 << 6
+        self.target_gain   = 0 * (1 << 4)
+        self.target_offset = 1 * (1 << 4)
+        self.target_clr    = 1 * (1 << 5)
+
+    @kernel
+    def set_clr(self, clr):
+        """Set/Unset waveform phase clear bits.
+
+        Each bit corresponds to a Shuttler waveform generator core. Setting a
+        clear bit forces the Shuttler Core to clear the phase accumulator on
+        waveform trigger (See :class:`Trigger` for the trigger method).
+        Otherwise, the phase accumulator increments from its original value.
+
+        :param clr: Waveform phase clear bits. The MSB corresponds to Channel
+            15, LSB corresponds to Channel 0.
+        """
+        rtio_output(self.target_base | self.target_clr, clr)
+    
+    @kernel
+    def set_gain(self, channel, gain):
+        """Set the 16-bits pre-DAC gain register of a Shuttler Core channel.
+
+        The `gain` parameter represents the decimal portion of the gain
+        factor. The MSB represents 0.5 and the sign bit. Hence, the valid
+        total gain value (1 +/- 0.gain) ranges from 0.5 to 1.5 - LSB.
+
+        :param channel: Shuttler Core channel to be configured.
+        :param gain: Shuttler Core channel gain.
+        """
+        rtio_output(self.target_base | self.target_gain | channel, gain)
+    
+    @kernel
+    def get_gain(self, channel):
+        """Return the pre-DAC gain value of a Shuttler Core channel.
+
+        :param channel: The Shuttler Core channel.
+        :return: Pre-DAC gain value. See :meth:`set_gain`.
+        """
+        rtio_output(self.target_base | self.target_gain |
+            self.target_read | channel, 0)
+        return rtio_input_data(self.channel)
+    
+    @kernel
+    def set_offset(self, channel, offset):
+        """Set the 16-bits pre-DAC offset register of a Shuttler Core channel.
+
+        .. seealso::
+            :meth:`shuttler_volt_to_mu`
+
+        :param channel: Shuttler Core channel to be configured.
+        :param offset: Shuttler Core channel offset.
+        """
+        rtio_output(self.target_base | self.target_offset | channel, offset)
+
+    @kernel
+    def get_offset(self, channel):
+        """Return the pre-DAC offset value of a Shuttler Core channel.
+
+        :param channel: The Shuttler Core channel.
+        :return: Pre-DAC offset value. See :meth:`set_offset`.
+        """
+        rtio_output(self.target_base | self.target_offset |
+            self.target_read | channel, 0)
+        return rtio_input_data(self.channel)
+
+
+class DCBias:
+    """Shuttler Core cubic DC-bias spline.
+
+    A Shuttler channel can generate a waveform `w(t)` that is the sum of a
+    cubic spline `a(t)` and a sinusoid modulated in amplitude by a cubic
+    spline `b(t)` and in phase/frequency by a quadratic spline `c(t)`, where
+
+    .. math::
+        w(t) = a(t) + b(t) * cos(c(t))
+    
+    And `t` corresponds to time in seconds.
+    This class controls the cubic spline `a(t)`, in which
+
+    .. math::
+        a(t) = p_0 + p_1t + \\frac{p_2t^2}{2} + \\frac{p_3t^3}{6}
+    
+    And `a(t)` is in Volt.
+
+    :param channel: RTIO channel number of this DC-bias spline interface.
+    :param core_device: Core device name.
+    """
+    kernel_invariants = {"core", "channel", "target_o"}
+
+    def __init__(self, dmgr, channel, core_device="core"):
+        self.core = dmgr.get(core_device)
+        self.channel = channel
+        self.target_o = channel << 8
+
+    @kernel
+    def set_waveform(self, a0: TInt32, a1: TInt32, a2: TInt64, a3: TInt64):
+        """Set the DC-bias spline waveform.
+
+        Given `a(t)` as defined in :class:`DCBias`, the coefficients should be
+        configured by the following formulae.
+
+        .. math::
+            T &= 8*10^{-9}
+
+            a_0 &= p_0
+
+            a_1 &= p_1T + \\frac{p_2T^2}{2} + \\frac{p_3T^3}{6}
+
+            a_2 &= p_2T^2 + p_3T^3
+
+            a_3 &= p_3T^3
+        
+        :math:`a_0`, :math:`a_1`, :math:`a_2` and :math:`a_3` are 16, 32, 48
+        and 48 bits in width respectively. See :meth:`shuttler_volt_to_mu` for
+        machine unit conversion.
+
+        Note: The waveform is not updated to the Shuttler Core until
+        triggered. See :class:`Trigger` for the update triggering mechanism.
+
+        :param a0: The :math:`a_0` coefficient in machine unit.
+        :param a1: The :math:`a_1` coefficient in machine unit.
+        :param a2: The :math:`a_2` coefficient in machine unit.
+        :param a3: The :math:`a_3` coefficient in machine unit.
+        """
+        coef_words = [
+            a0,
+            a1,
+            a1 >> 16,
+            a2 & 0xFFFF,
+            (a2 >> 16) & 0xFFFF,
+            (a2 >> 32) & 0xFFFF,
+            a3 & 0xFFFF,
+            (a3 >> 16) & 0xFFFF,
+            (a3 >> 32) & 0xFFFF,
+        ]
+
+        for i in range(len(coef_words)):
+            rtio_output(self.target_o | i, coef_words[i])
+            delay_mu(int64(self.core.ref_multiplier))
+
+
+class DDS:
+    """Shuttler Core DDS spline.
+
+    A Shuttler channel can generate a waveform `w(t)` that is the sum of a
+    cubic spline `a(t)` and a sinusoid modulated in amplitude by a cubic
+    spline `b(t)` and in phase/frequency by a quadratic spline `c(t)`, where
+
+    .. math::
+        w(t) = a(t) + b(t) * cos(c(t))
+    
+    And `t` corresponds to time in seconds.
+    This class controls the cubic spline `b(t)` and quadratic spline `c(t)`,
+    in which
+
+    .. math::
+        b(t) &= g * (q_0 + q_1t + \\frac{q_2t^2}{2} + \\frac{q_3t^3}{6})
+
+        c(t) &= r_0 + r_1t + \\frac{r_2t^2}{2}
+    
+    And `b(t)` is in Volt, `c(t)` is in number of turns. Note that `b(t)`
+    contributes to a constant gain of :math:`g=1.64676`.
+
+    :param channel: RTIO channel number of this DC-bias spline interface.
+    :param core_device: Core device name.
+    """
+    kernel_invariants = {"core", "channel", "target_o"}
+
+    def __init__(self, dmgr, channel, core_device="core"):
+        self.core = dmgr.get(core_device)
+        self.channel = channel
+        self.target_o = channel << 8
+
+    @kernel
+    def set_waveform(self, b0: TInt32, b1: TInt32, b2: TInt64, b3: TInt64,
+            c0: TInt32, c1: TInt32, c2: TInt32):
+        """Set the DDS spline waveform.
+
+        Given `b(t)` and `c(t)` as defined in :class:`DDS`, the coefficients
+        should be configured by the following formulae.
+
+        .. math::
+            T &= 8*10^{-9}
+
+            b_0 &= q_0
+
+            b_1 &= q_1T + \\frac{q_2T^2}{2} + \\frac{q_3T^3}{6}
+
+            b_2 &= q_2T^2 + q_3T^3
+
+            b_3 &= q_3T^3
+
+            c_0 &= r_0
+
+            c_1 &= r_1T + \\frac{r_2T^2}{2}
+
+            c_2 &= r_2T^2
+        
+        :math:`b_0`, :math:`b_1`, :math:`b_2` and :math:`b_3` are 16, 32, 48
+        and 48 bits in width respectively. See :meth:`shuttler_volt_to_mu` for
+        machine unit conversion. :math:`c_0`, :math:`c_1` and :math:`c_2` are
+        16, 32 and 32 bits in width respectively.
+
+        Note: The waveform is not updated to the Shuttler Core until
+        triggered. See :class:`Trigger` for the update triggering mechanism.
+
+        :param b0: The :math:`b_0` coefficient in machine unit.
+        :param b1: The :math:`b_1` coefficient in machine unit.
+        :param b2: The :math:`b_2` coefficient in machine unit.
+        :param b3: The :math:`b_3` coefficient in machine unit.
+        :param c0: The :math:`c_0` coefficient in machine unit.
+        :param c1: The :math:`c_1` coefficient in machine unit.
+        :param c2: The :math:`c_2` coefficient in machine unit.
+        """
+        coef_words = [
+            b0,
+            b1,
+            b1 >> 16,
+            b2 & 0xFFFF,
+            (b2 >> 16) & 0xFFFF,
+            (b2 >> 32) & 0xFFFF,
+            b3 & 0xFFFF,
+            (b3 >> 16) & 0xFFFF,
+            (b3 >> 32) & 0xFFFF,
+            c0,
+            c1,
+            c1 >> 16,
+            c2,
+            c2 >> 16,
+        ]
+
+        for i in range(len(coef_words)):
+            rtio_output(self.target_o | i, coef_words[i])
+            delay_mu(int64(self.core.ref_multiplier))
+
+
+class Trigger:
+    """Shuttler Core spline coefficients update trigger.
+
+    :param channel: RTIO channel number of the trigger interface.
+    :param core_device: Core device name.
+    """
+    kernel_invariants = {"core", "channel", "target_o"}
+
+    def __init__(self, dmgr, channel, core_device="core"):
+        self.core = dmgr.get(core_device)
+        self.channel = channel
+        self.target_o = channel << 8
+
+    @kernel
+    def trigger(self, trig_out):
+        """Triggers coefficient update of (a) Shuttler Core channel(s).
+
+        Each bit corresponds to a Shuttler waveform generator core. Setting
+        `trig_out` bits commits the pending coefficient update (from
+        `set_waveform` in :class:`DCBias` and :class:`DDS`) to the Shuttler Core
+        synchronously.
+
+        :param trig_out: Coefficient update trigger bits. The MSB corresponds
+            to Channel 15, LSB corresponds to Channel 0.
+        """
+        rtio_output(self.target_o, trig_out)
+
+
+RELAY_SPI_CONFIG = (0*spi.SPI_OFFLINE | 1*spi.SPI_END |
+                    0*spi.SPI_INPUT | 0*spi.SPI_CS_POLARITY |
+                    0*spi.SPI_CLK_POLARITY | 0*spi.SPI_CLK_PHASE |
+                    0*spi.SPI_LSB_FIRST | 0*spi.SPI_HALF_DUPLEX)
+
+ADC_SPI_CONFIG = (0*spi.SPI_OFFLINE | 0*spi.SPI_END |
+                  0*spi.SPI_INPUT | 0*spi.SPI_CS_POLARITY |
+                  1*spi.SPI_CLK_POLARITY | 1*spi.SPI_CLK_PHASE |
+                  0*spi.SPI_LSB_FIRST | 0*spi.SPI_HALF_DUPLEX)
+
+# SPI clock write and read dividers
+# CS should assert at least 9.5 ns after clk pulse
+SPIT_RELAY_WR = 4
+# 25 ns high/low pulse hold (limiting for write)
+SPIT_ADC_WR = 4
+SPIT_ADC_RD = 16
+
+# SPI CS line
+CS_RELAY = 1 << 0
+CS_LED = 1 << 1
+CS_ADC = 1 << 0
+
+# Referenced AD4115 registers
+_AD4115_REG_STATUS = 0x00
+_AD4115_REG_ADCMODE = 0x01
+_AD4115_REG_DATA = 0x04
+_AD4115_REG_ID = 0x07
+_AD4115_REG_CH0 = 0x10
+_AD4115_REG_SETUPCON0 = 0x20
+
+
+class Relay:
+    """Shuttler AFE relay switches.
+
+    It controls the AFE relay switches and the LEDs. Switch on the relay to
+    enable AFE output; And off to disable the output. The LEDs indicates the
+    relay status.
+
+    .. note::
+        The relay does not disable ADC measurements. Voltage of any channels
+        can still be read by the ADC even after switching off the relays.
+
+    :param spi_device: SPI bus device name.
+    :param core_device: Core device name.
+    """
+    kernel_invariant = {"core", "bus"}
+
+    def __init__(self, dmgr, spi_device, core_device="core"):
+        self.core = dmgr.get(core_device)
+        self.bus = dmgr.get(spi_device)
+    
+    @kernel
+    def init(self):
+        """Initialize SPI device.
+
+        Configures the SPI bus to 16-bits, write-only, simultaneous relay
+        switches and LED control.
+        """
+        self.bus.set_config_mu(
+            RELAY_SPI_CONFIG, 16, SPIT_RELAY_WR, CS_RELAY | CS_LED)
+
+    @kernel
+    def enable(self, en: TInt32):
+        """Enable/Disable relay switches of corresponding channels.
+
+        Each bit corresponds to the relay switch of a channel. Asserting a bit
+        turns on the corresponding relay switch; Deasserting the same bit
+        turns off the switch instead.
+
+        :param en: Switch enable bits. The MSB corresponds to Channel 15, LSB
+            corresponds to Channel 0.
+        """
+        self.bus.write(en << 16)
+
+
+class ADC:
+    """Shuttler AFE ADC (AD4115) driver.
+
+    :param spi_device: SPI bus device name.
+    :param core_device: Core device name.
+    """
+    kernel_invariant = {"core", "bus"}
+
+    def __init__(self, dmgr, spi_device, core_device="core"):
+        self.core = dmgr.get(core_device)
+        self.bus = dmgr.get(spi_device)
+
+    @kernel
+    def read_id(self) -> TInt32:
+        """Read the product ID of the ADC.
+
+        The expected return value is 0x38DX, the 4 LSbs are don't cares.
+
+        :return: The read-back product ID.
+        """
+        return self.read16(_AD4115_REG_ID)
+
+    @kernel
+    def reset(self):
+        """AD4115 reset procedure.
+
+        This performs a write operation of 96 serial clock cycles with DIN
+        held at high. It resets the entire device, including the register
+        contents.
+
+        .. note::
+            The datasheet only requires 64 cycles, but reasserting `CS_n` right
+            after the transfer appears to interrupt the start-up sequence.
+        """
+        self.bus.set_config_mu(ADC_SPI_CONFIG, 32, SPIT_ADC_WR, CS_ADC)
+        self.bus.write(0xffffffff)
+        self.bus.write(0xffffffff)
+        self.bus.set_config_mu(
+            ADC_SPI_CONFIG | spi.SPI_END, 32, SPIT_ADC_WR, CS_ADC)
+        self.bus.write(0xffffffff)
+
+    @kernel
+    def read8(self, addr: TInt32) -> TInt32:
+        """Read from 8 bit register.
+
+        :param addr: Register address.
+        :return: Read-back register content.
+        """
+        self.bus.set_config_mu(
+            ADC_SPI_CONFIG | spi.SPI_END | spi.SPI_INPUT,
+            16, SPIT_ADC_RD, CS_ADC)
+        self.bus.write((addr | 0x40) << 24)
+        return self.bus.read() & 0xff
+
+    @kernel
+    def read16(self, addr: TInt32) -> TInt32:
+        """Read from 16 bit register.
+
+        :param addr: Register address.
+        :return: Read-back register content.
+        """
+        self.bus.set_config_mu(
+            ADC_SPI_CONFIG | spi.SPI_END | spi.SPI_INPUT,
+            24, SPIT_ADC_RD, CS_ADC)
+        self.bus.write((addr | 0x40) << 24)
+        return self.bus.read() & 0xffff
+
+    @kernel
+    def read24(self, addr: TInt32) -> TInt32:
+        """Read from 24 bit register.
+
+        :param addr: Register address.
+        :return: Read-back register content.
+        """
+        self.bus.set_config_mu(
+            ADC_SPI_CONFIG | spi.SPI_END | spi.SPI_INPUT,
+            32, SPIT_ADC_RD, CS_ADC)
+        self.bus.write((addr | 0x40) << 24)
+        return self.bus.read() & 0xffffff
+
+    @kernel
+    def write8(self, addr: TInt32, data: TInt32):
+        """Write to 8 bit register.
+
+        :param addr: Register address.
+        :param data: Data to be written.
+        """
+        self.bus.set_config_mu(
+            ADC_SPI_CONFIG | spi.SPI_END, 16, SPIT_ADC_WR, CS_ADC)
+        self.bus.write(addr << 24 | (data & 0xff) << 16)
+
+    @kernel
+    def write16(self, addr: TInt32, data: TInt32):
+        """Write to 16 bit register.
+
+        :param addr: Register address.
+        :param data: Data to be written.
+        """
+        self.bus.set_config_mu(
+            ADC_SPI_CONFIG | spi.SPI_END, 24, SPIT_ADC_WR, CS_ADC)
+        self.bus.write(addr << 24 | (data & 0xffff) << 8)
+
+    @kernel
+    def write24(self, addr: TInt32, data: TInt32):
+        """Write to 24 bit register.
+
+        :param addr: Register address.
+        :param data: Data to be written.
+        """
+        self.bus.set_config_mu(
+            ADC_SPI_CONFIG | spi.SPI_END, 32, SPIT_ADC_WR, CS_ADC)
+        self.bus.write(addr << 24 | (data & 0xffffff))
+
+    @kernel
+    def read_ch(self, channel: TInt32) -> TFloat:
+        """Sample a Shuttler channel on the AFE.
+
+        It performs a single conversion using profile 0 and setup 0, on the
+        selected channel. The sample is then recovered and converted to volt.
+
+        :param channel: Shuttler channel to be sampled.
+        :return: Voltage sample in volt.
+        """
+        # Always configure Profile 0 for single conversion
+        self.write16(_AD4115_REG_CH0, 0x8000 | ((channel * 2 + 1) << 4))
+        self.write16(_AD4115_REG_SETUPCON0, 0x1300)
+        self.single_conversion()
+
+        delay(100*us)
+        adc_code = self.read24(_AD4115_REG_DATA)
+        return ((adc_code / (1 << 23)) - 1) * 2.5 / 0.1
+    
+    @kernel
+    def single_conversion(self):
+        """Place the ADC in single conversion mode.
+
+        The ADC returns to standby mode after the conversion is complete.
+        """
+        self.write16(_AD4115_REG_ADCMODE, 0x8010)
+
+    @kernel
+    def standby(self):
+        """Place the ADC in standby mode and disables power down the clock.
+
+        The ADC can be returned to single conversion mode by calling
+        :meth:`single_conversion`.
+        """
+        # Selecting internal XO (0b00) also disables clock during standby
+        self.write16(_AD4115_REG_ADCMODE, 0x8020)
+
+    @kernel
+    def power_down(self):
+        """Place the ADC in power-down mode.
+
+        The ADC must be reset before returning to other modes.
+        
+        .. note::
+            The AD4115 datasheet suggests placing the ADC in standby mode
+            before power-down. This is to prevent accidental entry into the
+            power-down mode.
+
+        .. seealso::
+            :meth:`standby`
+
+            :meth:`power_up`
+
+        """
+        self.write16(_AD4115_REG_ADCMODE, 0x8030)
+
+    @kernel
+    def power_up(self):
+        """Exit the ADC power-down mode.
+        
+        The ADC should be in power-down mode before calling this method.
+
+        .. seealso::
+            :meth:`power_down`
+        """
+        self.reset()
+        # Although the datasheet claims 500 us reset wait time, only waiting
+        # for ~500 us can result in DOUT pin stuck in high
+        delay(2500*us)
+
+    @kernel
+    def calibrate(self, volts, trigger, config, samples=[-5.0, 0.0, 5.0]):
+        """Calibrate the Shuttler waveform generator using the ADC on the AFE.
+
+        It finds the average slope rate and average offset by samples, and
+        compensate by writing the pre-DAC gain and offset registers in the
+        configuration registers.
+
+        .. note::
+            If the pre-calibration slope rate < 1, the calibration procedure
+            will introduce a pre-DAC gain compensation. However, this may
+            saturate the pre-DAC voltage code. (See :class:`Config` notes).
+            Shuttler cannot cover the entire +/- 10 V range in this case.
+
+        .. seealso::
+            :meth:`Config.set_gain`
+
+            :meth:`Config.set_offset`
+
+        :param volts: A list of all 16 cubic DC-bias spline.
+            (See :class:`DCBias`)
+        :param trigger: The Shuttler spline coefficient update trigger.
+        :param config: The Shuttler Core configuration registers.
+        :param samples: A list of sample voltages for calibration. There must
+            be at least 2 samples to perform slope rate calculation.
+        """
+        assert len(volts) == 16
+        assert len(samples) > 1
+
+        measurements = [0.0] * len(samples)
+
+        for ch in range(16):
+            # Find the average slope rate and offset
+            for i in range(len(samples)):
+                self.core.break_realtime()
+                volts[ch].set_waveform(
+                    shuttler_volt_to_mu(samples[i]), 0, 0, 0)
+                trigger.trigger(1 << ch)
+                measurements[i] = self.read_ch(ch)
+
+            # Find the average output slope
+            slope_sum = 0.0
+            for i in range(len(samples) - 1):
+                slope_sum += (measurements[i+1] - measurements[i])/(samples[i+1] - samples[i])
+            slope_avg = slope_sum / (len(samples) - 1)
+
+            gain_code = int32(1 / slope_avg * (2 ** 16)) & 0xffff
+
+            # Scale the measurements by 1/slope, find average offset
+            offset_sum = 0.0
+            for i in range(len(samples)):
+                offset_sum += (measurements[i] / slope_avg) - samples[i]
+            offset_avg = offset_sum / len(samples)
+
+            offset_code = shuttler_volt_to_mu(-offset_avg)
+
+            self.core.break_realtime()
+            config.set_gain(ch, gain_code)
+
+            delay_mu(int64(self.core.ref_multiplier))
+            config.set_offset(ch, offset_code)

artiq/coredevice/spi2.py

@@ -72,6 +72,10 @@ class SPIMaster:
         self.channel = channel
         self.update_xfer_duration_mu(div, length)
 
+    @staticmethod
+    def get_rtio_channels(channel, **kwargs):
+        return [(channel, None)]
+
     @portable
     def frequency_to_div(self, f):
         """Convert a SPI clock frequency to the closest SPI clock divider."""
@@ -273,9 +277,8 @@ class NRTSPIMaster:
     def set_config_mu(self, flags=0, length=8, div=6, cs=1):
         """Set the ``config`` register.
 
-        Note that the non-realtime SPI cores are usually clocked by the system
+        In many cases, the SPI configuration is already set by the firmware
-        clock and not the RTIO clock. In many cases, the SPI configuration is
+        and you do not need to call this method.
-        already set by the firmware and you do not need to call this method.
         """
         spi_set_config(self.busno, flags, length, div, cs)
 

artiq/coredevice/spline.py

@@ -1,228 +0,0 @@
-from numpy import int32, int64
-from artiq.language.core import kernel, portable, delay
-from artiq.coredevice.rtio import rtio_output, rtio_output_wide
-from artiq.language.types import TInt32, TInt64, TFloat
-
-
-class Spline:
-    r"""Spline interpolating RTIO channel.
-
-    One knot of a polynomial basis spline (B-spline) :math:`u(t)`
-    is defined by the coefficients :math:`u_n` up to order :math:`n = k`.
-    If the coefficients are evaluated starting at time :math:`t_0`,
-    the output :math:`u(t)` for :math:`t > t_0, t_0` is:
-
-    .. math::
-        u(t) &= \sum_{n=0}^k \frac{u_n}{n!} (t - t_0)^n \\
-             &= u_0 + u_1 (t - t_0) + \frac{u_2}{2} (t - t_0)^2 + \dots
-
-    This class contains multiple methods to convert spline knot data from SI
-    to machine units and multiple methods that set the current spline
-    coefficient data. None of these advance the timeline. The :meth:`smooth`
-    method is the only method that advances the timeline.
-
-    :param width: Width in bits of the quantity that this spline controls
-    :param time_width: Width in bits of the time counter of this spline
-    :param channel: RTIO channel number
-    :param core_device: Core device that this spline is attached to
-    :param scale: Scale for conversion between machine units and physical
-        units; to be given as the "full scale physical value".
-    """
-
-    kernel_invariants = {"channel", "core", "scale", "width",
-                         "time_width", "time_scale"}
-
-    def __init__(self, width, time_width, channel, core_device, scale=1.):
-        self.core = core_device
-        self.channel = channel
-        self.width = width
-        self.scale = float((int64(1) << width) / scale)
-        self.time_width = time_width
-        self.time_scale = float((1 << time_width) *
-                                core_device.coarse_ref_period)
-
-    @portable(flags={"fast-math"})
-    def to_mu(self, value: TFloat) -> TInt32:
-        """Convert floating point ``value`` from physical units to 32 bit
-        integer machine units."""
-        return int32(round(value*self.scale))
-
-    @portable(flags={"fast-math"})
-    def from_mu(self, value: TInt32) -> TFloat:
-        """Convert 32 bit integer ``value`` from machine units to floating
-        point physical units."""
-        return value/self.scale
-
-    @portable(flags={"fast-math"})
-    def to_mu64(self, value: TFloat) -> TInt64:
-        """Convert floating point ``value`` from physical units to 64 bit
-        integer machine units."""
-        return int64(round(value*self.scale))
-
-    @kernel
-    def set_mu(self, value: TInt32):
-        """Set spline value (machine units).
-
-        :param value: Spline value in integer machine units.
-        """
-        rtio_output(self.channel << 8, value)
-
-    @kernel(flags={"fast-math"})
-    def set(self, value: TFloat):
-        """Set spline value.
-
-        :param value: Spline value relative to full-scale.
-        """
-        if self.width > 32:
-            l = [int32(0)] * 2
-            self.pack_coeff_mu([self.to_mu64(value)], l)
-            rtio_output_wide(self.channel << 8, l)
-        else:
-            rtio_output(self.channel << 8, self.to_mu(value))
-
-    @kernel
-    def set_coeff_mu(self, value):  # TList(TInt32)
-        """Set spline raw values.
-
-        :param value: Spline packed raw values.
-        """
-        rtio_output_wide(self.channel << 8, value)
-
-    @portable(flags={"fast-math"})
-    def pack_coeff_mu(self, coeff, packed):  # TList(TInt64), TList(TInt32)
-        """Pack coefficients into RTIO data
-
-        :param coeff: TList(TInt64) list of machine units spline coefficients.
-            Lowest (zeroth) order first. The coefficient list is zero-extended
-            by the RTIO gateware.
-        :param packed: TList(TInt32) list for packed RTIO data. Must be
-            pre-allocated. Length in bits is
-            ``n*width + (n - 1)*n//2*time_width``
-        """
-        pos = 0
-        for i in range(len(coeff)):
-            wi = self.width + i*self.time_width
-            ci = coeff[i]
-            while wi != 0:
-                j = pos//32
-                used = pos - 32*j
-                avail = 32 - used
-                if avail > wi:
-                    avail = wi
-                cij = int32(ci)
-                if avail != 32:
-                    cij &= (1 << avail) - 1
-                packed[j] |= cij << used
-                ci >>= avail
-                wi -= avail
-                pos += avail
-
-    @portable(flags={"fast-math"})
-    def coeff_to_mu(self, coeff, coeff64):  # TList(TFloat), TList(TInt64)
-        """Convert a floating point list of coefficients into a 64 bit
-        integer (preallocated).
-
-        :param coeff: TList(TFloat) list of coefficients in physical units.
-        :param coeff64: TList(TInt64) preallocated list of coefficients in
-            machine units.
-        """
-        for i in range(len(coeff)):
-            vi = coeff[i] * self.scale
-            for j in range(i):
-                vi *= self.time_scale
-            ci = int64(round(vi))
-            coeff64[i] = ci
-            # artiq.wavesynth.coefficients.discrete_compensate:
-            if i == 2:
-                coeff64[1] += ci >> self.time_width + 1
-            elif i == 3:
-                coeff64[2] += ci >> self.time_width
-                coeff64[1] += ci // 6 >> 2*self.time_width
-
-    def coeff_as_packed_mu(self, coeff64):
-        """Pack 64 bit integer machine units coefficients into 32 bit integer
-        RTIO data list.
-
-        This is a host-only method that can be used to generate packed
-        spline coefficient data to be frozen into kernels at compile time.
-        """
-        n = len(coeff64)
-        width = n*self.width + (n - 1)*n//2*self.time_width
-        packed = [int32(0)] * ((width + 31)//32)
-        self.pack_coeff_mu(coeff64, packed)
-        return packed
-
-    def coeff_as_packed(self, coeff):
-        """Convert floating point spline coefficients into 32 bit integer
-        packed data.
-
-        This is a host-only method that can be used to generate packed
-        spline coefficient data to be frozen into kernels at compile time.
-        """
-        coeff64 = [int64(0)] * len(coeff)
-        self.coeff_to_mu(coeff, coeff64)
-        return self.coeff_as_packed_mu(coeff64)
-
-    @kernel(flags={"fast-math"})
-    def set_coeff(self, coeff):  # TList(TFloat)
-        """Set spline coefficients.
-
-        Missing coefficients (high order) are zero-extended byt the RTIO
-        gateware.
-
-        If more coefficients are supplied than the gateware supports the extra
-        coefficients are ignored.
-
-        :param value: List of floating point spline coefficients,
-            lowest order (constant) coefficient first. Units are the
-            unit of this spline's value times increasing powers of 1/s.
-        """
-        n = len(coeff)
-        coeff64 = [int64(0)] * n
-        self.coeff_to_mu(coeff, coeff64)
-        width = n*self.width + (n - 1)*n//2*self.time_width
-        packed = [int32(0)] * ((width + 31)//32)
-        self.pack_coeff_mu(coeff64, packed)
-        self.set_coeff_mu(packed)
-
-    @kernel(flags={"fast-math"})
-    def smooth(self, start: TFloat, stop: TFloat, duration: TFloat,
-               order: TInt32):
-        """Initiate an interpolated value change.
-
-        For zeroth order (step) interpolation, the step is at
-        ``start + duration/2``.
-
-        First order interpolation corresponds to a linear value ramp from
-        ``start`` to ``stop`` over ``duration``.
-
-        The third order interpolation is constrained to have zero first
-        order derivative at both `start` and `stop`.
-
-        For first order and third order interpolation (linear and cubic)
-        the interpolator needs to be stopped explicitly at the stop time
-        (e.g. by setting spline coefficient data or starting a new
-        :meth:`smooth` interpolation).
-
-        This method advances the timeline by ``duration``.
-
-        :param start: Initial value of the change. In physical units.
-        :param stop: Final value of the change. In physical units.
-        :param duration: Duration of the interpolation. In physical units.
-        :param order: Order of the interpolation. Only 0, 1,
-            and 3 are valid: step, linear, cubic.
-        """
-        if order == 0:
-            delay(duration/2.)
-            self.set_coeff([stop])
-            delay(duration/2.)
-        elif order == 1:
-            self.set_coeff([start, (stop - start)/duration])
-            delay(duration)
-        elif order == 3:
-            v2 = 6.*(stop - start)/(duration*duration)
-            self.set_coeff([start, 0., v2, -2.*v2/duration])
-            delay(duration)
-        else:
-            raise ValueError("Invalid interpolation order. "
-                             "Supported orders are: 0, 1, 3.")

artiq/coredevice/suservo.py

@@ -23,12 +23,12 @@ def y_mu_to_full_scale(y):
 
 
 @portable
-def adc_mu_to_volts(x, gain):
+def adc_mu_to_volts(x, gain, corrected_fs=True):
     """Convert servo ADC data from machine units to Volt."""
     val = (x >> 1) & 0xffff
     mask = 1 << 15
     val = -(val & mask) + (val & ~mask)
-    return sampler.adc_mu_to_volt(val, gain)
+    return sampler.adc_mu_to_volt(val, gain, corrected_fs)
 
 
 class SUServo:
@@ -62,14 +62,15 @@ class SUServo:
     :param gains: Initial value for PGIA gains shift register
         (default: 0x0000). Knowledge of this state is not transferred
         between experiments.
+    :param sampler_hw_rev: Sampler's revision string
     :param core_device: Core device name
     """
     kernel_invariants = {"channel", "core", "pgia", "cplds", "ddses",
-                         "ref_period_mu"}
+                         "ref_period_mu", "corrected_fs"}
 
     def __init__(self, dmgr, channel, pgia_device,
                  cpld_devices, dds_devices,
-                 gains=0x0000, core_device="core"):
+                 gains=0x0000, sampler_hw_rev="v2.2", core_device="core"):
 
         self.core = dmgr.get(core_device)
         self.pgia = dmgr.get(pgia_device)
@@ -81,8 +82,13 @@ class SUServo:
         self.gains = gains
         self.ref_period_mu = self.core.seconds_to_mu(
             self.core.coarse_ref_period)
+        self.corrected_fs = sampler.Sampler.use_corrected_fs(sampler_hw_rev)
         assert self.ref_period_mu == self.core.ref_multiplier
 
+    @staticmethod
+    def get_rtio_channels(channel, **kwargs):
+        return [(channel, None)]
+
     @kernel
     def init(self):
         """Initialize the servo, Sampler and both Urukuls.
@@ -234,7 +240,7 @@ class SUServo:
         """
         val = self.get_adc_mu(channel)
         gain = (self.gains >> (channel*2)) & 0b11
-        return adc_mu_to_volts(val, gain)
+        return adc_mu_to_volts(val, gain, self.corrected_fs)
 
 
 class Channel:
@@ -255,6 +261,10 @@ class Channel:
                               self.servo.channel)
         self.dds = self.servo.ddses[self.servo_channel // 4]
 
+    @staticmethod
+    def get_rtio_channels(channel, **kwargs):
+        return [(channel, None)]
+
     @kernel
     def set(self, en_out, en_iir=0, profile=0):
         """Operate channel.

artiq/coredevice/ttl.py

@@ -36,6 +36,10 @@ class TTLOut:
         self.channel = channel
         self.target_o = channel << 8
 
+    @staticmethod
+    def get_rtio_channels(channel, **kwargs):
+        return [(channel, None)]
+
     @kernel
     def output(self):
         pass
@@ -128,6 +132,10 @@ class TTLInOut:
         self.target_sens   = (channel << 8) + 2
         self.target_sample = (channel << 8) + 3
 
+    @staticmethod
+    def get_rtio_channels(channel, **kwargs):
+        return [(channel, None)]
+
     @kernel
     def set_oe(self, oe):
         rtio_output(self.target_oe, 1 if oe else 0)
@@ -465,6 +473,10 @@ class TTLClockGen:
 
         self.acc_width = numpy.int64(acc_width)
 
+    @staticmethod
+    def get_rtio_channels(channel, **kwargs):
+        return [(channel, None)]
+
     @portable
     def frequency_to_ftw(self, frequency):
         """Returns the frequency tuning word corresponding to the given

artiq/dashboard/datasets.py

@@ -5,7 +5,7 @@ import numpy as np
 from PyQt5 import QtCore, QtWidgets
 from sipyco import pyon
 
-from artiq.tools import short_format, exc_to_warning
+from artiq.tools import scale_from_metadata, short_format, exc_to_warning
 from artiq.gui.tools import LayoutWidget, QRecursiveFilterProxyModel
 from artiq.gui.models import DictSyncTreeSepModel
 from artiq.gui.scientific_spinbox import ScientificSpinBox
@@ -14,81 +14,18 @@ from artiq.gui.scientific_spinbox import ScientificSpinBox
 logger = logging.getLogger(__name__)
 
 
-class Editor(QtWidgets.QDialog):
+async def rename(key, new_key, value, metadata, persist, dataset_ctl):
-    def __init__(self, parent, dataset_ctl, key, value):
+    if key != new_key:
-        QtWidgets.QDialog.__init__(self, parent=parent)
+        await dataset_ctl.delete(key)
-        self.dataset_ctl = dataset_ctl
+    await dataset_ctl.set(new_key, value, metadata=metadata, persist=persist)
-        self.key = key
-        self.initial_type = type(value)
-
-        self.setWindowTitle("Edit dataset")
-        grid = QtWidgets.QGridLayout()
-        self.setLayout(grid)
-
-        grid.addWidget(QtWidgets.QLabel("Name:"), 0, 0)
-        grid.addWidget(QtWidgets.QLabel(key), 0, 1)
-
-        grid.addWidget(QtWidgets.QLabel("Value:"), 1, 0)
-        grid.addWidget(self.get_edit_widget(value), 1, 1)
-
-        buttons = QtWidgets.QDialogButtonBox(
-            QtWidgets.QDialogButtonBox.Ok | QtWidgets.QDialogButtonBox.Cancel)
-        grid.setRowStretch(2, 1)
-        grid.addWidget(buttons, 3, 0, 1, 2)
-        buttons.accepted.connect(self.accept)
-        buttons.rejected.connect(self.reject)
-
-    def accept(self):
-        value = self.initial_type(self.get_edit_widget_value())
-        asyncio.ensure_future(self.dataset_ctl.set(self.key, value))
-        QtWidgets.QDialog.accept(self)
-
-    def get_edit_widget(self, initial_value):
-        raise NotImplementedError
-
-    def get_edit_widget_value(self):
-        raise NotImplementedError
 
 
-class NumberEditor(Editor):
+class CreateEditDialog(QtWidgets.QDialog):
-    def get_edit_widget(self, initial_value):
+    def __init__(self, parent, dataset_ctl, key=None, value=None, metadata=None, persist=False):
-        self.edit_widget = ScientificSpinBox()
-        self.edit_widget.setDecimals(13)
-        self.edit_widget.setPrecision()
-        self.edit_widget.setRelativeStep()
-        self.edit_widget.setValue(float(initial_value))
-        return self.edit_widget
-
-    def get_edit_widget_value(self):
-        return self.edit_widget.value()
-
-
-class BoolEditor(Editor):
-    def get_edit_widget(self, initial_value):
-        self.edit_widget = QtWidgets.QCheckBox()
-        self.edit_widget.setChecked(bool(initial_value))
-        return self.edit_widget
-
-    def get_edit_widget_value(self):
-        return self.edit_widget.isChecked()
-
-
-class StringEditor(Editor):
-    def get_edit_widget(self, initial_value):
-        self.edit_widget = QtWidgets.QLineEdit()
-        self.edit_widget.setText(initial_value)
-        return self.edit_widget
-
-    def get_edit_widget_value(self):
-        return self.edit_widget.text()
-
-
-class Creator(QtWidgets.QDialog):
-    def __init__(self, parent, dataset_ctl):
         QtWidgets.QDialog.__init__(self, parent=parent)
         self.dataset_ctl = dataset_ctl
 
-        self.setWindowTitle("Create dataset")
+        self.setWindowTitle("Create dataset" if key is None else "Edit dataset")
         grid = QtWidgets.QGridLayout()
         grid.setRowMinimumHeight(1, 40)
         grid.setColumnMinimumWidth(2, 60)
@@ -106,9 +43,21 @@ class Creator(QtWidgets.QDialog):
         grid.addWidget(self.data_type, 1, 2)
         self.value_widget.textChanged.connect(self.dtype)
 
-        grid.addWidget(QtWidgets.QLabel("Persist:"), 2, 0)
+        grid.addWidget(QtWidgets.QLabel("Unit:"), 2, 0)
+        self.unit_widget = QtWidgets.QLineEdit()
+        grid.addWidget(self.unit_widget, 2, 1)
+
+        grid.addWidget(QtWidgets.QLabel("Scale:"), 3, 0)
+        self.scale_widget = QtWidgets.QLineEdit()
+        grid.addWidget(self.scale_widget, 3, 1)
+
+        grid.addWidget(QtWidgets.QLabel("Precision:"), 4, 0)
+        self.precision_widget = QtWidgets.QLineEdit()
+        grid.addWidget(self.precision_widget, 4, 1)
+
+        grid.addWidget(QtWidgets.QLabel("Persist:"), 5, 0)
         self.box_widget = QtWidgets.QCheckBox()
-        grid.addWidget(self.box_widget, 2, 1)
+        grid.addWidget(self.box_widget, 5, 1)
 
         self.ok = QtWidgets.QPushButton('&Ok')
         self.ok.setEnabled(False)
@@ -118,23 +67,62 @@ class Creator(QtWidgets.QDialog):
             self.ok, QtWidgets.QDialogButtonBox.AcceptRole)
         self.buttons.addButton(
             self.cancel, QtWidgets.QDialogButtonBox.RejectRole)
-        grid.setRowStretch(3, 1)
+        grid.setRowStretch(6, 1)
-        grid.addWidget(self.buttons, 4, 0, 1, 3)
+        grid.addWidget(self.buttons, 7, 0, 1, 3, alignment=QtCore.Qt.AlignHCenter)
         self.buttons.accepted.connect(self.accept)
         self.buttons.rejected.connect(self.reject)
 
+        self.key = key
+        self.name_widget.setText(key)
+
+        value_edit_string = self.value_to_edit_string(value)
+        if metadata is not None:
+            scale = scale_from_metadata(metadata)
+            t = value.dtype if value is np.ndarray else type(value)
+            if scale != 1 and np.issubdtype(t, np.number):
+                # degenerates to float type
+                value_edit_string = self.value_to_edit_string(
+                        np.float64(value / scale))
+            self.unit_widget.setText(metadata.get('unit', ''))
+            self.scale_widget.setText(str(metadata.get('scale', '')))
+            self.precision_widget.setText(str(metadata.get('precision', '')))
+
+        self.value_widget.setText(value_edit_string)
+        self.box_widget.setChecked(persist)
+
     def accept(self):
         key = self.name_widget.text()
         value = self.value_widget.text()
         persist = self.box_widget.isChecked()
-        asyncio.ensure_future(exc_to_warning(self.dataset_ctl.set(
+        unit = self.unit_widget.text()
-            key, pyon.decode(value), persist)))
+        scale = self.scale_widget.text()
+        precision = self.precision_widget.text()
+        metadata = {}
+        if unit != "":
+            metadata['unit'] = unit
+        if scale != "":
+            metadata['scale'] = float(scale)
+        if precision != "":
+            metadata['precision'] = int(precision)
+        scale = scale_from_metadata(metadata)
+        value = self.parse_edit_string(value)
+        t = value.dtype if value is np.ndarray else type(value)
+        if scale != 1 and np.issubdtype(t, np.number):
+            # degenerates to float type
+            value = np.float64(value * scale)
+        if self.key and self.key != key:
+            asyncio.ensure_future(exc_to_warning(rename(self.key, key, value, metadata, persist, self.dataset_ctl)))
+        else:
+            asyncio.ensure_future(exc_to_warning(self.dataset_ctl.set(key, value, metadata=metadata, persist=persist)))
+        self.key = key
         QtWidgets.QDialog.accept(self)
 
     def dtype(self):
         txt = self.value_widget.text()
         try:
-            result = pyon.decode(txt)
+            result = self.parse_edit_string(txt)
+            # ensure only pyon compatible types are permissable
+            pyon.encode(result)
         except:
             pixmap = self.style().standardPixmap(
                 QtWidgets.QStyle.SP_MessageBoxWarning)
@@ -144,24 +132,53 @@ class Creator(QtWidgets.QDialog):
             self.data_type.setText(type(result).__name__)
             self.ok.setEnabled(True)
 
+    @staticmethod
+    def parse_edit_string(s):
+        if s == "":
+            raise TypeError
+        _eval_dict = {
+            "__builtins__": {},
+            "array": np.array,
+            "null": np.nan,
+            "inf": np.inf
+        }
+        for t_ in pyon._numpy_scalar:
+            _eval_dict[t_] = eval("np.{}".format(t_), {"np": np})
+        return eval(s, _eval_dict, {})
+
+    @staticmethod
+    def value_to_edit_string(v):
+        t = type(v)
+        r = ""
+        if isinstance(v, np.generic):
+            r += t.__name__
+            r += "("
+            r += repr(v)
+            r += ")"
+        elif v is None:
+            return r
+        else:
+            r += repr(v)
+        return r
+
 
 class Model(DictSyncTreeSepModel):
     def __init__(self,  init):
-        DictSyncTreeSepModel.__init__(
+        DictSyncTreeSepModel.__init__(self, ".",
-            self, ".", ["Dataset", "Persistent", "Value"], init
+                                      ["Dataset", "Persistent", "Value"],
-        )
+                                      init)
 
     def convert(self, k, v, column):
         if column == 1:
-            return "Y" if v["persist"] else "N"
+            return "Y" if v[0] else "N"
         elif column == 2:
-            return short_format(v["value"])
+            return short_format(v[1], v[2])
         else:
             raise ValueError
 
 
 class DatasetsDock(QtWidgets.QDockWidget):
-    def __init__(self, datasets_sub, dataset_ctl):
+    def __init__(self, dataset_sub, dataset_ctl):
         QtWidgets.QDockWidget.__init__(self, "Datasets")
         self.setObjectName("Datasets")
         self.setFeatures(QtWidgets.QDockWidget.DockWidgetMovable |
@@ -201,7 +218,7 @@ class DatasetsDock(QtWidgets.QDockWidget):
         self.table.addAction(delete_action)
 
         self.table_model = Model(dict())
-        datasets_sub.add_setmodel_callback(self.set_model)
+        dataset_sub.add_setmodel_callback(self.set_model)
 
     def _search_datasets(self):
         if hasattr(self, "table_model_filter"):
@@ -215,7 +232,7 @@ class DatasetsDock(QtWidgets.QDockWidget):
         self.table.setModel(self.table_model_filter)
 
     def create_clicked(self):
-        Creator(self, self.dataset_ctl).open()
+        CreateEditDialog(self, self.dataset_ctl).open()
 
     def edit_clicked(self):
         idx = self.table.selectedIndexes()
@@ -223,19 +240,8 @@ class DatasetsDock(QtWidgets.QDockWidget):
             idx = self.table_model_filter.mapToSource(idx[0])
             key = self.table_model.index_to_key(idx)
             if key is not None:
-                dataset = self.table_model.backing_store[key]
+                persist, value, metadata = self.table_model.backing_store[key]
-                t = type(dataset["value"])
+                CreateEditDialog(self, self.dataset_ctl, key, value, metadata, persist).open()
-                if np.issubdtype(t, np.number):
-                    dialog_cls = NumberEditor
-                elif np.issubdtype(t, np.bool_):
-                    dialog_cls = BoolEditor
-                elif np.issubdtype(t, np.unicode_):
-                    dialog_cls = StringEditor
-                else:
-                    logger.error("Cannot edit dataset %s: "
-                                 "type %s is not supported", key, t)
-                    return
-                dialog_cls(self, self.dataset_ctl, key, dataset["value"]).open()
 
     def delete_clicked(self):
         idx = self.table.selectedIndexes()

artiq/dashboard/experiments.py

@@ -11,7 +11,9 @@ from sipyco import pyon
 
 from artiq.gui.entries import procdesc_to_entry, ScanEntry
 from artiq.gui.fuzzy_select import FuzzySelectWidget
-from artiq.gui.tools import LayoutWidget, log_level_to_name, get_open_file_name
+from artiq.gui.tools import (LayoutWidget, WheelFilter, 
+                             log_level_to_name, get_open_file_name)
+from artiq.tools import parse_devarg_override, unparse_devarg_override
 
 
 logger = logging.getLogger(__name__)
@@ -23,15 +25,6 @@ logger = logging.getLogger(__name__)
 # 2. file:<class name>@<file name>
 
 
-class _WheelFilter(QtCore.QObject):
-    def eventFilter(self, obj, event):
-        if (event.type() == QtCore.QEvent.Wheel and
-                event.modifiers() != QtCore.Qt.NoModifier):
-            event.ignore()
-            return True
-        return False
-
-
 class _ArgumentEditor(QtWidgets.QTreeWidget):
     def __init__(self, manager, dock, expurl):
         self.manager = manager
@@ -55,7 +48,7 @@ class _ArgumentEditor(QtWidgets.QTreeWidget):
         self.setStyleSheet("QTreeWidget {background: " +
                            self.palette().midlight().color().name() + " ;}")
 
-        self.viewport().installEventFilter(_WheelFilter(self.viewport()))
+        self.viewport().installEventFilter(WheelFilter(self.viewport(), True))
 
         self._groups = dict()
         self._arg_to_widgets = dict()
@@ -159,12 +152,29 @@ class _ArgumentEditor(QtWidgets.QTreeWidget):
         self._groups[name] = group
         return group
 
+    def update_argument(self, name, argument):
+        widgets = self._arg_to_widgets[name]
+
+        # Qt needs a setItemWidget() to handle layout correctly,
+        # simply replacing the entry inside the LayoutWidget
+        # results in a bug.
+
+        widgets["entry"].deleteLater()
+        widgets["entry"] = procdesc_to_entry(argument["desc"])(argument)
+        widgets["disable_other_scans"].setVisible(
+            isinstance(widgets["entry"], ScanEntry))
+        widgets["fix_layout"].deleteLater()
+        widgets["fix_layout"] = LayoutWidget()
+        widgets["fix_layout"].addWidget(widgets["entry"])
+        self.setItemWidget(widgets["widget_item"], 1, widgets["fix_layout"])
+        self.updateGeometries()
+
     def _recompute_argument_clicked(self, name):
         asyncio.ensure_future(self._recompute_argument(name))
 
     async def _recompute_argument(self, name):
         try:
-            expdesc = await self.manager.compute_expdesc(self.expurl)
+            expdesc, _ = await self.manager.compute_expdesc(self.expurl)
         except:
             logger.error("Could not recompute argument '%s' of '%s'",
                          name, self.expurl, exc_info=True)
@@ -175,22 +185,7 @@ class _ArgumentEditor(QtWidgets.QTreeWidget):
         state = procdesc_to_entry(procdesc).default_state(procdesc)
         argument["desc"] = procdesc
         argument["state"] = state
-
+        self.update_argument(name, argument)
-        # Qt needs a setItemWidget() to handle layout correctly,
-        # simply replacing the entry inside the LayoutWidget
-        # results in a bug.
-
-        widgets = self._arg_to_widgets[name]
-
-        widgets["entry"].deleteLater()
-        widgets["entry"] = procdesc_to_entry(procdesc)(argument)
-        widgets["disable_other_scans"].setVisible(
-            isinstance(widgets["entry"], ScanEntry))
-        widgets["fix_layout"].deleteLater()
-        widgets["fix_layout"] = LayoutWidget()
-        widgets["fix_layout"].addWidget(widgets["entry"])
-        self.setItemWidget(widgets["widget_item"], 1, widgets["fix_layout"])
-        self.updateGeometries()
 
     def _disable_other_scans(self, current_name):
         for name, widgets in self._arg_to_widgets.items():
@@ -216,6 +211,15 @@ class _ArgumentEditor(QtWidgets.QTreeWidget):
                 pass
         self.verticalScrollBar().setValue(state["scroll"])
 
+    # Hooks that allow user-supplied argument editors to react to imminent user
+    # actions. Here, we always keep the manager-stored submission arguments
+    # up-to-date, so no further action is required.
+    def about_to_submit(self):
+        pass
+
+    def about_to_close(self):
+        pass
+
 
 log_levels = ["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"]
 
@@ -241,7 +245,8 @@ class _ExperimentDock(QtWidgets.QMdiSubWindow):
         self.manager = manager
         self.expurl = expurl
 
-        self.argeditor = _ArgumentEditor(self.manager, self, self.expurl)
+        editor_class = self.manager.get_argument_editor_class(expurl)
+        self.argeditor = editor_class(self.manager, self, self.expurl)
         self.layout.addWidget(self.argeditor, 0, 0, 1, 5)
         self.layout.setRowStretch(0, 1)
 
@@ -258,7 +263,7 @@ class _ExperimentDock(QtWidgets.QMdiSubWindow):
             datetime.setDate(QtCore.QDate.currentDate())
         else:
             datetime.setDateTime(QtCore.QDateTime.fromMSecsSinceEpoch(
-                scheduling["due_date"]*1000))
+                int(scheduling["due_date"]*1000)))
         datetime_en.setChecked(scheduling["due_date"] is not None)
 
         def update_datetime(dt):
@@ -301,7 +306,7 @@ class _ExperimentDock(QtWidgets.QMdiSubWindow):
         flush = self.flush
         flush.setToolTip("Flush the pipeline (of current- and higher-priority "
                          "experiments) before starting the experiment")
-        self.layout.addWidget(flush, 2, 2, 1, 2)
+        self.layout.addWidget(flush, 2, 2)
 
         flush.setChecked(scheduling["flush"])
 
@@ -309,6 +314,20 @@ class _ExperimentDock(QtWidgets.QMdiSubWindow):
             scheduling["flush"] = bool(checked)
         flush.stateChanged.connect(update_flush)
 
+        devarg_override = QtWidgets.QComboBox()
+        devarg_override.setEditable(True)
+        devarg_override.lineEdit().setPlaceholderText("Override device arguments")
+        devarg_override.lineEdit().setClearButtonEnabled(True)
+        devarg_override.insertItem(0, "core:analyze_at_run_end=True")
+        self.layout.addWidget(devarg_override, 2, 3)
+
+        devarg_override.setCurrentText(options["devarg_override"])
+
+        def update_devarg_override(text):
+            options["devarg_override"] = text
+        devarg_override.editTextChanged.connect(update_devarg_override)
+        self.devarg_override = devarg_override
+
         log_level = QtWidgets.QComboBox()
         log_level.addItems(log_levels)
         log_level.setCurrentIndex(1)
@@ -329,6 +348,7 @@ class _ExperimentDock(QtWidgets.QMdiSubWindow):
         if "repo_rev" in options:
             repo_rev = QtWidgets.QLineEdit()
             repo_rev.setPlaceholderText("current")
+            repo_rev.setClearButtonEnabled(True)
             repo_rev_label = QtWidgets.QLabel("Revision:")
             repo_rev_label.setToolTip("Experiment repository revision "
                                       "(commit ID) to use")
@@ -369,6 +389,7 @@ class _ExperimentDock(QtWidgets.QMdiSubWindow):
         self.hdf5_load_directory = os.path.expanduser("~")
 
     def submit_clicked(self):
+        self.argeditor.about_to_submit()
         try:
             self.manager.submit(self.expurl)
         except:
@@ -391,7 +412,7 @@ class _ExperimentDock(QtWidgets.QMdiSubWindow):
 
     async def _recompute_arguments_task(self, overrides=dict()):
         try:
-            expdesc = await self.manager.compute_expdesc(self.expurl)
+            expdesc, ui_name = await self.manager.compute_expdesc(self.expurl)
         except:
             logger.error("Could not recompute experiment description of '%s'",
                          self.expurl, exc_info=True)
@@ -404,12 +425,13 @@ class _ExperimentDock(QtWidgets.QMdiSubWindow):
                 arginfo[k][0]["default"].insert(0, v)
             else:
                 arginfo[k][0]["default"] = v
-        self.manager.initialize_submission_arguments(self.expurl, arginfo)
+        self.manager.initialize_submission_arguments(self.expurl, arginfo, ui_name)
 
         argeditor_state = self.argeditor.save_state()
         self.argeditor.deleteLater()
 
-        self.argeditor = _ArgumentEditor(self.manager, self, self.expurl)
+        editor_class = self.manager.get_argument_editor_class(self.expurl)
+        self.argeditor = editor_class(self.manager, self, self.expurl)
         self.argeditor.restore_state(argeditor_state)
         self.layout.addWidget(self.argeditor, 0, 0, 1, 5)
 
@@ -422,7 +444,7 @@ class _ExperimentDock(QtWidgets.QMdiSubWindow):
 
     async def _recompute_sched_options_task(self):
         try:
-            expdesc = await self.manager.compute_expdesc(self.expurl)
+            expdesc, _ = await self.manager.compute_expdesc(self.expurl)
         except:
             logger.error("Could not recompute experiment description of '%s'",
                          self.expurl, exc_info=True)
@@ -459,6 +481,9 @@ class _ExperimentDock(QtWidgets.QMdiSubWindow):
             return
 
         try:
+            if "devarg_override" in expid:
+                self.devarg_override.setCurrentText(
+                    unparse_devarg_override(expid["devarg_override"]))
             self.log_level.setCurrentIndex(log_levels.index(
                 log_level_to_name(expid["log_level"])))
             if ("repo_rev" in expid and
@@ -473,6 +498,7 @@ class _ExperimentDock(QtWidgets.QMdiSubWindow):
         await self._recompute_arguments_task(arguments)
 
     def closeEvent(self, event):
+        self.argeditor.about_to_close()
         self.sigClosed.emit()
         QtWidgets.QMdiSubWindow.closeEvent(self, event)
 
@@ -544,7 +570,13 @@ class _QuickOpenDialog(QtWidgets.QDialog):
 
 
 class ExperimentManager:
-    def __init__(self, main_window,
+    #: Global registry for custom argument editor classes, indexed by the experiment
+    #: `argument_ui` string; can be populated by dashboard plugins such as ndscan.
+    #: If no handler for a requested UI name is found, the default built-in argument
+    #: editor will be used.
+    argument_ui_classes = dict()
+
+    def __init__(self, main_window, dataset_sub,
                  explist_sub, schedule_sub,
                  schedule_ctl, experiment_db_ctl):
         self.main_window = main_window
@@ -555,7 +587,10 @@ class ExperimentManager:
         self.submission_scheduling = dict()
         self.submission_options = dict()
         self.submission_arguments = dict()
+        self.argument_ui_names = dict()
 
+        self.datasets = dict()
+        dataset_sub.add_setmodel_callback(self.set_dataset_model)
         self.explist = dict()
         explist_sub.add_setmodel_callback(self.set_explist_model)
         self.schedule = dict()
@@ -570,6 +605,9 @@ class ExperimentManager:
         quick_open_shortcut.setContext(QtCore.Qt.ApplicationShortcut)
         quick_open_shortcut.activated.connect(self.show_quick_open)
 
+    def set_dataset_model(self, model):
+        self.datasets = model
+
     def set_explist_model(self, model):
         self.explist = model.backing_store
 
@@ -586,6 +624,17 @@ class ExperimentManager:
         else:
             raise ValueError("Malformed experiment URL")
 
+    def get_argument_editor_class(self, expurl):
+        ui_name = self.argument_ui_names.get(expurl, None)
+        if not ui_name and expurl[:5] == "repo:":
+            ui_name = self.explist.get(expurl[5:], {}).get("argument_ui", None)
+        if ui_name:
+            result = self.argument_ui_classes.get(ui_name, None)
+            if result:
+                return result
+            logger.warning("Ignoring unknown argument UI '%s'", ui_name)
+        return _ArgumentEditor
+
     def get_submission_scheduling(self, expurl):
         if expurl in self.submission_scheduling:
             return self.submission_scheduling[expurl]
@@ -608,14 +657,15 @@ class ExperimentManager:
         else:
             # mutated by _ExperimentDock
             options = {
-                "log_level": logging.WARNING
+                "log_level": logging.WARNING,
+                "devarg_override": ""
             }
             if expurl[:5] == "repo:":
                 options["repo_rev"] = None
             self.submission_options[expurl] = options
             return options
 
-    def initialize_submission_arguments(self, expurl, arginfo):
+    def initialize_submission_arguments(self, expurl, arginfo, ui_name):
         arguments = OrderedDict()
         for name, (procdesc, group, tooltip) in arginfo.items():
             state = procdesc_to_entry(procdesc).default_state(procdesc)
@@ -626,8 +676,23 @@ class ExperimentManager:
                 "state": state,  # mutated by entries
             }
         self.submission_arguments[expurl] = arguments
+        self.argument_ui_names[expurl] = ui_name
         return arguments
     
+    def set_argument_value(self, expurl, name, value):
+        try:
+            argument = self.submission_arguments[expurl][name]
+            if argument["desc"]["ty"] == "Scannable":
+                ty = value["ty"]
+                argument["state"]["selected"] = ty
+                argument["state"][ty] = value
+            else:
+                argument["state"] = value
+            if expurl in self.open_experiments.keys():
+                self.open_experiments[expurl].argeditor.update_argument(name, argument)
+        except:
+            logger.warn("Failed to set value for argument \"{}\" in experiment: {}.".format(name, expurl), exc_info=1)
+
     def get_submission_arguments(self, expurl):
         if expurl in self.submission_arguments:
             return self.submission_arguments[expurl]
@@ -635,9 +700,9 @@ class ExperimentManager:
             if expurl[:5] != "repo:":
                 raise ValueError("Submission arguments must be preinitialized "
                                  "when not using repository")
-            arginfo = self.explist[expurl[5:]]["arginfo"]
+            class_desc = self.explist[expurl[5:]]
-            arguments = self.initialize_submission_arguments(expurl, arginfo)
+            return self.initialize_submission_arguments(expurl,
-            return arguments
+                class_desc["arginfo"], class_desc.get("argument_ui", None))
 
     def open_experiment(self, expurl):
         if expurl in self.open_experiments:
@@ -688,7 +753,14 @@ class ExperimentManager:
             entry_cls = procdesc_to_entry(argument["desc"])
             argument_values[name] = entry_cls.state_to_value(argument["state"])
 
+        try:
+            devarg_override = parse_devarg_override(options["devarg_override"])
+        except:
+            logger.error("Failed to parse device argument overrides for %s", expurl)
+            return
+
         expid = {
+            "devarg_override": devarg_override,
             "log_level": options["log_level"],
             "file": file,
             "class_name": class_name,
@@ -726,7 +798,7 @@ class ExperimentManager:
             else:
                 repo_match = "repo_rev" not in expid
             if (repo_match and
-                    expid["file"] == file and
+                    ("file" in expid and expid["file"] == file) and
                     expid["class_name"] == class_name):
                 rids.append(rid)
         asyncio.ensure_future(self._request_term_multiple(rids))
@@ -739,13 +811,15 @@ class ExperimentManager:
             revision = None
         description = await self.experiment_db_ctl.examine(
             file, use_repository, revision)
-        return description[class_name]
+        class_desc = description[class_name]
+        return class_desc, class_desc.get("argument_ui", None)
 
     async def open_file(self, file):
         description = await self.experiment_db_ctl.examine(file, False)
         for class_name, class_desc in description.items():
             expurl = "file:{}@{}".format(class_name, file)
-            self.initialize_submission_arguments(expurl, class_desc["arginfo"])
+            self.initialize_submission_arguments(expurl, class_desc["arginfo"],
+                class_desc.get("argument_ui", None))
             if expurl in self.open_experiments:
                 self.open_experiments[expurl].close()
             self.open_experiment(expurl)
@@ -758,6 +832,7 @@ class ExperimentManager:
             "options": self.submission_options,
             "arguments": self.submission_arguments,
             "docks": self.dock_states,
+            "argument_uis": self.argument_ui_names,
             "open_docks": set(self.open_experiments.keys())
         }
 
@@ -768,6 +843,7 @@ class ExperimentManager:
         self.submission_scheduling = state["scheduling"]
         self.submission_options = state["options"]
         self.submission_arguments = state["arguments"]
+        self.argument_ui_names = state.get("argument_uis", {})
         for expurl in state["open_docks"]:
             self.open_experiment(expurl)
 

artiq/dashboard/explorer.py

@@ -159,7 +159,7 @@ class WaitingPanel(LayoutWidget):
 class ExplorerDock(QtWidgets.QDockWidget):
     def __init__(self, exp_manager, d_shortcuts,
                  explist_sub, explist_status_sub,
-                 schedule_ctl, experiment_db_ctl):
+                 schedule_ctl, experiment_db_ctl, device_db_ctl):
         QtWidgets.QDockWidget.__init__(self, "Explorer")
         self.setObjectName("Explorer")
         self.setFeatures(QtWidgets.QDockWidget.DockWidgetMovable |
@@ -251,6 +251,12 @@ class ExplorerDock(QtWidgets.QDockWidget):
         scan_repository_action.triggered.connect(scan_repository)
         self.el.addAction(scan_repository_action)
 
+        scan_ddb_action = QtWidgets.QAction("Scan device database", self.el)
+        def scan_ddb():
+            asyncio.ensure_future(device_db_ctl.scan())
+        scan_ddb_action.triggered.connect(scan_ddb)
+        self.el.addAction(scan_ddb_action)
+
         self.current_directory = ""
         open_file_action = QtWidgets.QAction("Open file outside repository",
                                              self.el)

artiq/dashboard/moninj.py

@@ -1,5 +1,6 @@
 import asyncio
 import logging
+import textwrap
 from collections import namedtuple
 
 from PyQt5 import QtCore, QtWidgets, QtGui
@@ -7,12 +8,27 @@ from PyQt5 import QtCore, QtWidgets, QtGui
 from sipyco.sync_struct import Subscriber
 
 from artiq.coredevice.comm_moninj import *
+from artiq.coredevice.ad9910 import (
+    _AD9910_REG_PROFILE0, _AD9910_REG_PROFILE7, 
+    _AD9910_REG_FTW, _AD9910_REG_CFR1
+)
+from artiq.coredevice.ad9912_reg import AD9912_POW1, AD9912_SER_CONF
 from artiq.gui.tools import LayoutWidget
 from artiq.gui.flowlayout import FlowLayout
 
 
 logger = logging.getLogger(__name__)
 
+class _CancellableLineEdit(QtWidgets.QLineEdit):
+    def escapePressedConnect(self, cb):
+        self.esc_cb = cb
+
+    def keyPressEvent(self, event):
+        key = event.key()
+        if key == QtCore.Qt.Key_Escape:
+            self.esc_cb(event)
+        QtWidgets.QLineEdit.keyPressEvent(self, event)
+
 
 class _TTLWidget(QtWidgets.QFrame):
     def __init__(self, dm, channel, force_out, title):
@@ -168,15 +184,172 @@ class _SimpleDisplayWidget(QtWidgets.QFrame):
         raise NotImplementedError
 
 
-class _DDSWidget(_SimpleDisplayWidget):
+class _DDSModel:
-    def __init__(self, dm, bus_channel, channel, title):
+    def __init__(self, dds_type, ref_clk, cpld=None, pll=1, clk_div=0):
+        self.cpld = cpld
+        self.cur_frequency = 0
+        self.cur_reg = 0
+        self.dds_type = dds_type
+        self.is_urukul = dds_type in ["AD9910", "AD9912"]
+    
+        if dds_type == "AD9914":
+            self.ftw_per_hz = 2**32 / ref_clk
+        else:
+            if dds_type == "AD9910":
+                max_freq = 1 << 32
+                clk_mult = [4, 1, 2, 4]
+            elif dds_type == "AD9912":  # AD9912
+                max_freq = 1 << 48
+                clk_mult = [1, 1, 2, 4]
+            else:
+                raise NotImplementedError
+            sysclk = ref_clk / clk_mult[clk_div] * pll
+            self.ftw_per_hz = 1 / sysclk * max_freq
+
+    def monitor_update(self, probe, value):
+        if self.dds_type == "AD9912":
+            value = value << 16
+        self.cur_frequency = self._ftw_to_freq(value)
+
+    def _ftw_to_freq(self, ftw):
+        return ftw / self.ftw_per_hz
+
+
+class _DDSWidget(QtWidgets.QFrame):
+    def __init__(self, dm, title, bus_channel=0, channel=0, dds_model=None):
+        self.dm = dm
         self.bus_channel = bus_channel
         self.channel = channel
+        self.dds_name = title
         self.cur_frequency = 0
-        _SimpleDisplayWidget.__init__(self, title)
+        self.dds_model = dds_model
+
+        QtWidgets.QFrame.__init__(self)
+
+        self.setFrameShape(QtWidgets.QFrame.Box)
+        self.setFrameShadow(QtWidgets.QFrame.Raised)
+
+        grid = QtWidgets.QGridLayout()
+        grid.setContentsMargins(0, 0, 0, 0)
+        grid.setHorizontalSpacing(0)
+        grid.setVerticalSpacing(0)
+        self.setLayout(grid)
+        label = QtWidgets.QLabel(title)
+        label.setAlignment(QtCore.Qt.AlignCenter)
+        grid.addWidget(label, 1, 1)
+
+        # FREQ DATA/EDIT FIELD
+        self.data_stack = QtWidgets.QStackedWidget()
+
+        # page 1: display data
+        grid_disp = LayoutWidget()
+        grid_disp.layout.setContentsMargins(0, 0, 0, 0)
+        grid_disp.layout.setHorizontalSpacing(0)
+        grid_disp.layout.setVerticalSpacing(0)
+
+        self.value_label = QtWidgets.QLabel()
+        self.value_label.setAlignment(QtCore.Qt.AlignCenter)
+        grid_disp.addWidget(self.value_label, 0, 1, 1, 2)
+
+        unit = QtWidgets.QLabel("MHz")
+        unit.setAlignment(QtCore.Qt.AlignCenter)
+        grid_disp.addWidget(unit, 0, 3, 1, 1)
+
+        self.data_stack.addWidget(grid_disp)
+
+        # page 2: edit data
+        grid_edit = LayoutWidget()
+        grid_edit.layout.setContentsMargins(0, 0, 0, 0)
+        grid_edit.layout.setHorizontalSpacing(0)
+        grid_edit.layout.setVerticalSpacing(0)
+
+        self.value_edit = _CancellableLineEdit(self)
+        self.value_edit.setAlignment(QtCore.Qt.AlignRight)
+        grid_edit.addWidget(self.value_edit, 0, 1, 1, 2)
+        unit = QtWidgets.QLabel("MHz")
+        unit.setAlignment(QtCore.Qt.AlignCenter)
+        grid_edit.addWidget(unit, 0, 3, 1, 1)
+        self.data_stack.addWidget(grid_edit)
+
+        grid.addWidget(self.data_stack, 2, 1)
+
+        # BUTTONS
+        self.button_stack = QtWidgets.QStackedWidget()
+
+        # page 1: SET button
+        set_grid = LayoutWidget()
+
+        set_btn = QtWidgets.QToolButton()
+        set_btn.setText("Set")
+        set_btn.setToolTip("Set frequency")
+        set_grid.addWidget(set_btn, 0, 1, 1, 1)
+        
+        # for urukuls also allow switching off RF
+        if self.dds_model.is_urukul:
+            off_btn = QtWidgets.QToolButton()
+            off_btn.setText("Off")
+            off_btn.setToolTip("Switch off the output")
+            set_grid.addWidget(off_btn, 0, 2, 1, 1)
+
+        self.button_stack.addWidget(set_grid)
+
+        # page 2: apply/cancel buttons
+        apply_grid = LayoutWidget()
+        apply = QtWidgets.QToolButton()
+        apply.setText("Apply")
+        apply.setToolTip("Apply changes")
+        apply_grid.addWidget(apply, 0, 1, 1, 1)
+        cancel = QtWidgets.QToolButton()
+        cancel.setText("Cancel")
+        cancel.setToolTip("Cancel changes")
+        apply_grid.addWidget(cancel, 0, 2, 1, 1)
+        self.button_stack.addWidget(apply_grid)
+        grid.addWidget(self.button_stack, 3, 1)
+
+        grid.setRowStretch(1, 1)
+        grid.setRowStretch(2, 1)
+        grid.setRowStretch(3, 1)
+
+        set_btn.clicked.connect(self.set_clicked)
+        apply.clicked.connect(self.apply_changes)
+        if self.dds_model.is_urukul:
+            off_btn.clicked.connect(self.off_clicked)
+            off_btn.setToolTip(textwrap.dedent(
+                """Note: If TTL RTIO sw for the channel is switched high,
+                this button will not disable the channel.
+                Use the TTL override instead."""))
+        self.value_edit.returnPressed.connect(lambda: self.apply_changes(None))
+        self.value_edit.escapePressedConnect(self.cancel_changes)
+        cancel.clicked.connect(self.cancel_changes)
+
+        self.refresh_display()
+
+    def set_clicked(self, set):
+        self.data_stack.setCurrentIndex(1)
+        self.button_stack.setCurrentIndex(1)
+        self.value_edit.setText("{:.7f}"
+                .format(self.cur_frequency/1e6))
+        self.value_edit.setFocus()
+        self.value_edit.selectAll()
+
+    def off_clicked(self, set):
+        self.dm.dds_channel_toggle(self.dds_name, self.dds_model, sw=False)
+    
+    def apply_changes(self, apply):
+        self.data_stack.setCurrentIndex(0)
+        self.button_stack.setCurrentIndex(0)
+        frequency = float(self.value_edit.text())*1e6
+        self.dm.dds_set_frequency(self.dds_name, self.dds_model, frequency)
+
+    def cancel_changes(self, cancel):
+        self.data_stack.setCurrentIndex(0)
+        self.button_stack.setCurrentIndex(0)
 
     def refresh_display(self):
-        self.value.setText("<font size=\"4\">{:.7f}</font><font size=\"2\"> MHz</font>"
+        self.cur_frequency = self.dds_model.cur_frequency
+        self.value_label.setText("<font size=\"4\">{:.7f}</font>"
+                           .format(self.cur_frequency/1e6))
+        self.value_edit.setText("{:.7f}"
                            .format(self.cur_frequency/1e6))
 
     def sort_key(self):
@@ -202,19 +375,19 @@ _WidgetDesc = namedtuple("_WidgetDesc", "uid comment cls arguments")
 
 
 def setup_from_ddb(ddb):
-    core_addr = None
+    mi_addr = None
+    mi_port = None
     dds_sysclk = None
     description = set()
 
     for k, v in ddb.items():
-        comment = None
-        if "comment" in v:
-            comment = v["comment"]
         try:
-            if isinstance(v, dict) and v["type"] == "local":
+            if isinstance(v, dict):
-                if k == "core":
+                comment = v.get("comment")
-                    core_addr = v["arguments"]["host"]
+                if v["type"] == "local":
-                elif v["module"] == "artiq.coredevice.ttl":
+                    if v["module"] == "artiq.coredevice.ttl":
+                        if "ttl_urukul" in k:
+                            continue
                         channel = v["arguments"]["channel"]
                         force_out = v["class"] == "TTLOut"
                         widget = _WidgetDesc(k, comment, _TTLWidget, (channel, force_out, k))
@@ -224,9 +397,26 @@ def setup_from_ddb(ddb):
                         bus_channel = v["arguments"]["bus_channel"]
                         channel = v["arguments"]["channel"]
                         dds_sysclk = v["arguments"]["sysclk"]
-                    widget = _WidgetDesc(k, comment, _DDSWidget, (bus_channel, channel, k))
+                        model = _DDSModel(v["class"], dds_sysclk)
+                        widget = _WidgetDesc(k, comment, _DDSWidget, (k, bus_channel, channel, model))
                         description.add(widget)
-                elif (   (v["module"] == "artiq.coredevice.ad53xx" and v["class"] == "AD53XX")
+                    elif (v["module"] == "artiq.coredevice.ad9910"
+                                and v["class"] == "AD9910") or \
+                            (v["module"] == "artiq.coredevice.ad9912"
+                                and v["class"] == "AD9912"):
+                        channel = v["arguments"]["chip_select"] - 4
+                        if channel < 0:
+                            continue
+                        dds_cpld = v["arguments"]["cpld_device"]
+                        spi_dev = ddb[dds_cpld]["arguments"]["spi_device"]
+                        bus_channel = ddb[spi_dev]["arguments"]["channel"]
+                        pll = v["arguments"]["pll_n"]
+                        refclk = ddb[dds_cpld]["arguments"]["refclk"]
+                        clk_div = v["arguments"].get("clk_div", 0)
+                        model = _DDSModel( v["class"], refclk, dds_cpld, pll, clk_div)
+                        widget = _WidgetDesc(k, comment, _DDSWidget, (k, bus_channel, channel, model))
+                        description.add(widget)       
+                    elif (   (v["module"] == "artiq.coredevice.ad53xx" and v["class"] == "AD53xx")
                           or (v["module"] == "artiq.coredevice.zotino" and v["class"] == "Zotino")):
                         spi_device = v["arguments"]["spi_device"]
                         spi_device = ddb[spi_device]
@@ -236,17 +426,23 @@ def setup_from_ddb(ddb):
                         for channel in range(32):
                             widget = _WidgetDesc((k, channel), comment, _DACWidget, (spi_channel, channel, k))
                             description.add(widget)
+                elif v["type"] == "controller" and k == "core_moninj":
+                    mi_addr = v["host"]
+                    mi_port = v.get("port_proxy", 1383)
         except KeyError:
             pass
-    return core_addr, dds_sysclk, description
+    return mi_addr, mi_port, description
 
 
 class _DeviceManager:
-    def __init__(self):
+    def __init__(self, schedule_ctl):
-        self.core_addr = None
+        self.mi_addr = None
-        self.reconnect_core = asyncio.Event()
+        self.mi_port = None
-        self.core_connection = None
+        self.reconnect_mi = asyncio.Event()
-        self.core_connector_task = asyncio.ensure_future(self.core_connector())
+        self.mi_connection = None
+        self.mi_connector_task = asyncio.ensure_future(self.mi_connector())
+
+        self.schedule_ctl = schedule_ctl
 
         self.ddb = dict()
         self.description = set()
@@ -265,13 +461,12 @@ class _DeviceManager:
         return ddb
 
     def notify(self, mod):
-        core_addr, dds_sysclk, description = setup_from_ddb(self.ddb)
+        mi_addr, mi_port, description = setup_from_ddb(self.ddb)
 
-        if core_addr != self.core_addr:
+        if (mi_addr, mi_port) != (self.mi_addr, self.mi_port):
-            self.core_addr = core_addr
+            self.mi_addr = mi_addr
-            self.reconnect_core.set()
+            self.mi_port = mi_port
-
+            self.reconnect_mi.set()
-        self.dds_sysclk = dds_sysclk
 
         for to_remove in self.description - description:
             widget = self.widgets_by_uid[to_remove.uid]
@@ -319,44 +514,172 @@ class _DeviceManager:
         self.description = description
 
     def ttl_set_mode(self, channel, mode):
-        if self.core_connection is not None:
+        if self.mi_connection is not None:
             widget = self.ttl_widgets[channel]
             if mode == "0":
                 widget.cur_override = True
                 widget.cur_level = False
-                self.core_connection.inject(channel, TTLOverride.level.value, 0)
+                self.mi_connection.inject(channel, TTLOverride.level.value, 0)
-                self.core_connection.inject(channel, TTLOverride.oe.value, 1)
+                self.mi_connection.inject(channel, TTLOverride.oe.value, 1)
-                self.core_connection.inject(channel, TTLOverride.en.value, 1)
+                self.mi_connection.inject(channel, TTLOverride.en.value, 1)
             elif mode == "1":
                 widget.cur_override = True
                 widget.cur_level = True
-                self.core_connection.inject(channel, TTLOverride.level.value, 1)
+                self.mi_connection.inject(channel, TTLOverride.level.value, 1)
-                self.core_connection.inject(channel, TTLOverride.oe.value, 1)
+                self.mi_connection.inject(channel, TTLOverride.oe.value, 1)
-                self.core_connection.inject(channel, TTLOverride.en.value, 1)
+                self.mi_connection.inject(channel, TTLOverride.en.value, 1)
             elif mode == "exp":
                 widget.cur_override = False
-                self.core_connection.inject(channel, TTLOverride.en.value, 0)
+                self.mi_connection.inject(channel, TTLOverride.en.value, 0)
             else:
                 raise ValueError
             # override state may have changed
             widget.refresh_display()
 
+    async def _submit_by_content(self, content, class_name, title):
+        expid = {
+            "log_level": logging.WARNING,
+            "content": content,
+            "class_name": class_name,
+            "arguments": {}
+        }
+        scheduling = {
+            "pipeline_name": "main",
+            "priority": 0,
+            "due_date": None,
+            "flush": False
+        }
+        rid = await self.schedule_ctl.submit(
+            scheduling["pipeline_name"],
+            expid,
+            scheduling["priority"], scheduling["due_date"],
+            scheduling["flush"])
+        logger.info("Submitted '%s', RID is %d", title, rid)
+
+    def _dds_faux_injection(self, dds_channel, dds_model, action, title, log_msg):
+        # create kernel and fill it in and send-by-content
+
+        # initialize CPLD (if applicable)
+        if dds_model.is_urukul:
+            # urukuls need CPLD init and switch to on
+            cpld_dev = """self.setattr_device("core_cache")
+                self.setattr_device("{}")""".format(dds_model.cpld)
+
+            # `sta`/`rf_sw`` variables are guaranteed for urukuls 
+            # so {action} can use it
+            # if there's no RF enabled, CPLD may have not been initialized
+            # but if there is, it has been initialised - no need to do again
+            cpld_init = """delay(15*ms)
+                was_init = self.core_cache.get("_{cpld}_init")
+                sta = self.{cpld}.sta_read()
+                rf_sw = urukul_sta_rf_sw(sta)
+                if rf_sw == 0 and len(was_init) == 0:
+                    delay(15*ms)
+                    self.{cpld}.init()
+                    self.core_cache.put("_{cpld}_init", [1])
+            """.format(cpld=dds_model.cpld)
+        else:
+            cpld_dev = ""
+            cpld_init = ""
+
+        # AD9912/9910: init channel (if uninitialized)
+        if dds_model.dds_type == "AD9912":
+            # 0xFF before init, 0x99 after
+            channel_init = """
+                if self.{dds_channel}.read({cfgreg}, length=1) == 0xFF:
+                    delay(10*ms)
+                    self.{dds_channel}.init()
+            """.format(dds_channel=dds_channel, cfgreg=AD9912_SER_CONF)
+        elif dds_model.dds_type == "AD9910":
+            # -1 before init, 2 after
+            channel_init = """
+                if self.{dds_channel}.read32({cfgreg}) == -1:
+                    delay(10*ms)
+                    self.{dds_channel}.init()
+            """.format(dds_channel=dds_channel, cfgreg=AD9912_SER_CONF)
+        else:
+            channel_init = "self.{dds_channel}.init()".format(dds_channel=dds_channel)
+
+        dds_exp = textwrap.dedent("""
+        from artiq.experiment import *
+        from artiq.coredevice.urukul import *
+
+        class {title}(EnvExperiment):
+            def build(self):
+                self.setattr_device("core")
+                self.setattr_device("{dds_channel}")
+                {cpld_dev}
+                
+            @kernel
+            def run(self):
+                self.core.break_realtime()
+                {cpld_init}
+                delay(10*ms)
+                {channel_init}
+                delay(15*ms)
+                {action}
+        """.format(title=title, action=action,
+                   dds_channel=dds_channel,
+                   cpld_dev=cpld_dev, cpld_init=cpld_init,
+                   channel_init=channel_init))
+        asyncio.ensure_future(
+            self._submit_by_content(
+                dds_exp, 
+                title, 
+                log_msg))
+
+    def dds_set_frequency(self, dds_channel, dds_model, freq):
+        action = "self.{ch}.set({freq})".format(
+            freq=freq, ch=dds_channel)
+        if dds_model.is_urukul:
+            action += """
+                ch_no = self.{ch}.chip_select - 4
+                self.{cpld}.cfg_switches(rf_sw | 1 << ch_no)
+            """.format(ch=dds_channel, cpld=dds_model.cpld)
+        self._dds_faux_injection(
+            dds_channel,
+            dds_model,
+            action,
+            "SetDDS", 
+            "Set DDS {} {}MHz".format(dds_channel, freq/1e6))
+
+    def dds_channel_toggle(self, dds_channel, dds_model, sw=True):
+        # urukul only
+        if sw:
+            switch = "| 1 << ch_no"
+        else:
+            switch = "& ~(1 << ch_no)"
+        action = """
+                ch_no = self.{dds_channel}.chip_select - 4
+                self.{cpld}.cfg_switches(rf_sw {switch})
+        """.format(
+            dds_channel=dds_channel,
+            cpld=dds_model.cpld,
+            switch=switch
+        )
+        self._dds_faux_injection(
+            dds_channel,
+            dds_model,
+            action,
+            "ToggleDDS", 
+            "Toggle DDS {} {}".format(dds_channel, "on" if sw else "off"))
+
     def setup_ttl_monitoring(self, enable, channel):
-        if self.core_connection is not None:
+        if self.mi_connection is not None:
-            self.core_connection.monitor_probe(enable, channel, TTLProbe.level.value)
+            self.mi_connection.monitor_probe(enable, channel, TTLProbe.level.value)
-            self.core_connection.monitor_probe(enable, channel, TTLProbe.oe.value)
+            self.mi_connection.monitor_probe(enable, channel, TTLProbe.oe.value)
-            self.core_connection.monitor_injection(enable, channel, TTLOverride.en.value)
+            self.mi_connection.monitor_injection(enable, channel, TTLOverride.en.value)
-            self.core_connection.monitor_injection(enable, channel, TTLOverride.level.value)
+            self.mi_connection.monitor_injection(enable, channel, TTLOverride.level.value)
             if enable:
-                self.core_connection.get_injection_status(channel, TTLOverride.en.value)
+                self.mi_connection.get_injection_status(channel, TTLOverride.en.value)
 
     def setup_dds_monitoring(self, enable, bus_channel, channel):
-        if self.core_connection is not None:
+        if self.mi_connection is not None:
-            self.core_connection.monitor_probe(enable, bus_channel, channel)
+            self.mi_connection.monitor_probe(enable, bus_channel, channel)
 
     def setup_dac_monitoring(self, enable, spi_channel, channel):
-        if self.core_connection is not None:
+        if self.mi_connection is not None:
-            self.core_connection.monitor_probe(enable, spi_channel, channel)
+            self.mi_connection.monitor_probe(enable, spi_channel, channel)
 
     def monitor_cb(self, channel, probe, value):
         if channel in self.ttl_widgets:
@@ -366,11 +689,11 @@ class _DeviceManager:
             elif probe == TTLProbe.oe.value:
                 widget.cur_oe = bool(value)
             widget.refresh_display()
-        if (channel, probe) in self.dds_widgets:
+        elif (channel, probe) in self.dds_widgets:
             widget = self.dds_widgets[(channel, probe)]
-            widget.cur_frequency = value*self.dds_sysclk/2**32
+            widget.dds_model.monitor_update(probe, value)
             widget.refresh_display()
-        if (channel, probe) in self.dac_widgets:
+        elif (channel, probe) in self.dac_widgets:
             widget = self.dac_widgets[(channel, probe)]
             widget.cur_value = value
             widget.refresh_display()
@@ -385,29 +708,31 @@ class _DeviceManager:
             widget.refresh_display()
 
     def disconnect_cb(self):
-        logger.error("lost connection to core device moninj")
+        logger.error("lost connection to moninj")
-        self.reconnect_core.set()
+        self.reconnect_mi.set()
 
-    async def core_connector(self):
+    async def mi_connector(self):
         while True:
-            await self.reconnect_core.wait()
+            await self.reconnect_mi.wait()
-            self.reconnect_core.clear()
+            self.reconnect_mi.clear()
-            if self.core_connection is not None:
+            if self.mi_connection is not None:
-                await self.core_connection.close()
+                await self.mi_connection.close()
-                self.core_connection = None
+                self.mi_connection = None
-            new_core_connection = CommMonInj(self.monitor_cb, self.injection_status_cb,
+            new_mi_connection = CommMonInj(self.monitor_cb, self.injection_status_cb,
                     self.disconnect_cb)
             try:
-                await new_core_connection.connect(self.core_addr, 1383)
+                await new_mi_connection.connect(self.mi_addr, self.mi_port)
             except asyncio.CancelledError:
-                logger.info("cancelled connection to core device moninj")
+                logger.info("cancelled connection to moninj")
                 break
             except:
-                logger.error("failed to connect to core device moninj", exc_info=True)
+                logger.error("failed to connect to moninj. Is aqctl_moninj_proxy running?", exc_info=True)
                 await asyncio.sleep(10.)
-                self.reconnect_core.set()
+                self.reconnect_mi.set()
             else:
-                self.core_connection = new_core_connection
+                logger.info("ARTIQ dashboard connected to moninj (%s)",
+                            self.mi_addr)
+                self.mi_connection = new_mi_connection
                 for ttl_channel in self.ttl_widgets.keys():
                     self.setup_ttl_monitoring(True, ttl_channel)
                 for bus_channel, channel in self.dds_widgets.keys():
@@ -416,13 +741,13 @@ class _DeviceManager:
                     self.setup_dac_monitoring(True, spi_channel, channel)
 
     async def close(self):
-        self.core_connector_task.cancel()
+        self.mi_connector_task.cancel()
         try:
-            await asyncio.wait_for(self.core_connector_task, None)
+            await asyncio.wait_for(self.mi_connector_task, None)
         except asyncio.CancelledError:
             pass
-        if self.core_connection is not None:
+        if self.mi_connection is not None:
-            await self.core_connection.close()
+            await self.mi_connection.close()
 
 
 class _MonInjDock(QtWidgets.QDockWidget):
@@ -448,12 +773,12 @@ class _MonInjDock(QtWidgets.QDockWidget):
 
 
 class MonInj:
-    def __init__(self):
+    def __init__(self, schedule_ctl):
         self.ttl_dock = _MonInjDock("TTL")
         self.dds_dock = _MonInjDock("DDS")
         self.dac_dock = _MonInjDock("DAC")
 
-        self.dm = _DeviceManager()
+        self.dm = _DeviceManager(schedule_ctl)
         self.dm.ttl_cb = lambda: self.ttl_dock.layout_widgets(
                             self.dm.ttl_widgets.values())
         self.dm.dds_cb = lambda: self.dds_dock.layout_widgets(

artiq/dashboard/schedule.py

@@ -48,7 +48,7 @@ class Model(DictSyncModel):
             else:
                 return "Outside repo."
         elif column == 6:
-            return v["expid"]["file"]
+            return v["expid"].get("file", "<none>")
         elif column == 7:
             if v["expid"]["class_name"] is None:
                 return ""

artiq/examples/kasli/device_db.py

@@ -7,7 +7,11 @@ device_db = {
         "type": "local",
         "module": "artiq.coredevice.core",
         "class": "Core",
-        "arguments": {"host": core_addr, "ref_period": 1e-9}
+        "arguments": {
+            "host": core_addr,
+            "ref_period": 1e-9,
+            "analyzer_proxy": "core_analyzer"
+        }
     },
     "core_log": {
         "type": "controller",
@@ -15,6 +19,20 @@ device_db = {
         "port": 1068,
         "command": "aqctl_corelog -p {port} --bind {bind} " + core_addr
     },
+    "core_moninj": {
+        "type": "controller",
+        "host": "::1",
+        "port_proxy": 1383,
+        "port": 1384,
+        "command": "aqctl_moninj_proxy --port-proxy {port_proxy} --port-control {port} --bind {bind} " + core_addr
+    },
+    "core_analyzer": {
+        "type": "controller",
+        "host": "::1",
+        "port_proxy": 1385,
+        "port": 1386,
+        "command": "aqctl_coreanalyzer_proxy --port-proxy {port_proxy} --port-control {port} --bind {bind} " + core_addr
+    },
     "core_cache": {
         "type": "local",
         "module": "artiq.coredevice.cache",
@@ -29,13 +47,13 @@ device_db = {
     "i2c_switch0": {
         "type": "local",
         "module": "artiq.coredevice.i2c",
-        "class": "PCA9548",
+        "class": "I2CSwitch",
         "arguments": {"address": 0xe0}
     },
     "i2c_switch1": {
         "type": "local",
         "module": "artiq.coredevice.i2c",
-        "class": "PCA9548",
+        "class": "I2CSwitch",
         "arguments": {"address": 0xe2}
     },
 }

artiq/examples/kasli_drtioswitching/device_db.py

@@ -5,7 +5,11 @@ device_db = {
         "type": "local",
         "module": "artiq.coredevice.core",
         "class": "Core",
-        "arguments": {"host": core_addr, "ref_period": 1/(8*150e6)}
+        "arguments": {
+            "host": core_addr,
+            "ref_period": 1e-9,
+            "analyzer_proxy": "core_analyzer"
+        }
     },
     "core_log": {
         "type": "controller",
@@ -13,6 +17,20 @@ device_db = {
         "port": 1068,
         "command": "aqctl_corelog -p {port} --bind {bind} " + core_addr
     },
+    "core_moninj": {
+        "type": "controller",
+        "host": "::1",
+        "port_proxy": 1383,
+        "port": 1384,
+        "command": "aqctl_moninj_proxy --port-proxy {port_proxy} --port-control {port} --bind {bind} " + core_addr
+    },
+    "core_analyzer": {
+        "type": "controller",
+        "host": "::1",
+        "port_proxy": 1385,
+        "port": 1386,
+        "command": "aqctl_coreanalyzer_proxy --port-proxy {port_proxy} --port-control {port} --bind {bind} " + core_addr
+    },
     "core_cache": {
         "type": "local",
         "module": "artiq.coredevice.cache",

artiq/examples/kasli_sawgmaster/device_db.py

@@ -1,177 +0,0 @@
-core_addr = "192.168.1.70"
-
-device_db = {
-    "core": {
-        "type": "local",
-        "module": "artiq.coredevice.core",
-        "class": "Core",
-        "arguments": {"host": core_addr, "ref_period": 1/(8*150e6)}
-    },
-    "core_log": {
-        "type": "controller",
-        "host": "::1",
-        "port": 1068,
-        "command": "aqctl_corelog -p {port} --bind {bind} " + core_addr
-    },
-    "core_cache": {
-        "type": "local",
-        "module": "artiq.coredevice.cache",
-        "class": "CoreCache"
-    },
-    "core_dma": {
-        "type": "local",
-        "module": "artiq.coredevice.dma",
-        "class": "CoreDMA"
-    },
-}
-
-device_db.update(
-    spi_urukul0={
-        "type": "local",
-        "module": "artiq.coredevice.spi2",
-        "class": "SPIMaster",
-        "arguments": {"channel": 0}
-    },
-    ttl_urukul0_io_update={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 1}
-    },
-    ttl_urukul0_sw0={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 2}
-    },
-    ttl_urukul0_sw1={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 3}
-    },
-    ttl_urukul0_sw2={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 4}
-    },
-    ttl_urukul0_sw3={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 5}
-    },
-    urukul0_cpld={
-        "type": "local",
-        "module": "artiq.coredevice.urukul",
-        "class": "CPLD",
-        "arguments": {
-            "spi_device": "spi_urukul0",
-            "io_update_device": "ttl_urukul0_io_update",
-            "refclk": 150e6,
-            "clk_sel": 2
-        }
-    }
-)
-
-for i in range(4):
-    device_db["urukul0_ch" + str(i)] = {
-        "type": "local",
-        "module": "artiq.coredevice.ad9910",
-        "class": "AD9910",
-        "arguments": {
-            "pll_n": 16,  # 600MHz sample rate
-            "pll_vco": 2,
-            "chip_select": 4 + i,
-            "cpld_device": "urukul0_cpld",
-            "sw_device": "ttl_urukul0_sw" + str(i)
-        }
-    }
-
-"""
-artiq_route routing.bin init
-artiq_route routing.bin set 0 0
-artiq_route routing.bin set 1 1 0
-artiq_route routing.bin set 2 1 1 0
-artiq_route routing.bin set 3 2 0
-artiq_route routing.bin set 4 2 1 0
-artiq_coremgmt -D kasli config write -f routing_table routing.bin
-"""
-
-for sayma in range(2):
-    amc_base = 0x010000 + sayma*0x020000
-    rtm_base = 0x020000 + sayma*0x020000
-    for i in range(4):
-        device_db["led" + str(4*sayma+i)] = {
-            "type": "local",
-            "module": "artiq.coredevice.ttl",
-            "class": "TTLOut",
-            "arguments": {"channel": amc_base + i}
-        }
-    for i in range(2):
-        device_db["ttl_mcx" + str(2*sayma+i)] = {
-            "type": "local",
-            "module": "artiq.coredevice.ttl",
-            "class": "TTLInOut",
-            "arguments": {"channel": amc_base + 4 + i}
-        }
-    for i in range(8):
-        device_db["sawg" + str(8*sayma+i)] = {
-            "type": "local",
-            "module": "artiq.coredevice.sawg",
-            "class": "SAWG",
-            "arguments": {"channel_base": amc_base + 6 + i*10, "parallelism": 4}
-        }
-    for basemod in range(2):
-        for i in range(4):
-            device_db["sawg_sw" + str(8*sayma+4*basemod+i)] = {
-                "type": "local",
-                "module": "artiq.coredevice.ttl",
-                "class": "TTLOut",
-                "arguments": {"channel": rtm_base + basemod*9 + i}
-            }
-        att_idx = 2*sayma + basemod
-        device_db["basemod_att_rst_n"+str(att_idx)] = {
-            "type": "local",
-            "module": "artiq.coredevice.ttl",
-            "class": "TTLOut",
-            "arguments": {"channel": rtm_base + basemod*9 + 4}
-        }
-        device_db["basemod_att_clk"+str(att_idx)] = {
-            "type": "local",
-            "module": "artiq.coredevice.ttl",
-            "class": "TTLOut",
-            "arguments": {"channel": rtm_base + basemod*9 + 5}
-        }
-        device_db["basemod_att_le"+str(att_idx)] = {
-            "type": "local",
-            "module": "artiq.coredevice.ttl",
-            "class": "TTLOut",
-            "arguments": {"channel": rtm_base + basemod*9 + 6}
-        }
-        device_db["basemod_att_mosi"+str(att_idx)] = {
-            "type": "local",
-            "module": "artiq.coredevice.ttl",
-            "class": "TTLOut",
-            "arguments": {"channel": rtm_base + basemod*9 + 7}
-        }
-        device_db["basemod_att_miso"+str(att_idx)] = {
-            "type": "local",
-            "module": "artiq.coredevice.ttl",
-            "class": "TTLInOut",
-            "arguments": {"channel": rtm_base + basemod*9 + 8}
-        }
-        device_db["basemod_att"+str(att_idx)] = {
-            "type": "local",
-            "module": "artiq.coredevice.basemod_att",
-            "class": "BaseModAtt",
-            "arguments": {
-                "rst_n": "basemod_att_rst_n"+str(att_idx),
-                "clk": "basemod_att_clk"+str(att_idx),
-                "le": "basemod_att_le"+str(att_idx),
-                "mosi": "basemod_att_mosi"+str(att_idx),
-                "miso": "basemod_att_miso"+str(att_idx),
-            }
-        }
-

artiq/examples/kasli_sawgmaster/repository/basemod.py

@@ -1,25 +0,0 @@
-from artiq.experiment import *
-
-
-class BaseMod(EnvExperiment):
-    def build(self):
-        self.setattr_device("core")
-        self.basemods = [self.get_device("basemod_att0"), self.get_device("basemod_att1")]
-        self.rfsws = [self.get_device("sawg_sw"+str(i)) for i in range(8)]
-
-    @kernel
-    def run(self):
-        self.core.reset()
-        for basemod in self.basemods:
-            self.core.break_realtime()
-            delay(10*ms)
-            basemod.reset()
-            delay(10*ms)
-            basemod.set(0.0, 0.0, 0.0, 0.0)
-            delay(10*ms)
-            print(basemod.get_mu())
-
-        self.core.break_realtime()
-        for rfsw in self.rfsws:
-            rfsw.on()
-            delay(1*ms)

artiq/examples/kasli_sawgmaster/repository/sines_2sayma.py

@@ -1,37 +0,0 @@
-from artiq.experiment import *
-
-
-class Sines2Sayma(EnvExperiment):
-    def build(self):
-        self.setattr_device("core")
-        self.sawgs = [self.get_device("sawg"+str(i)) for i in range(16)]
-
-    @kernel
-    def drtio_is_up(self):
-        for i in range(5):
-            if not self.core.get_rtio_destination_status(i):
-                return False
-        return True
-
-    @kernel
-    def run(self):
-        while True:
-            print("waiting for DRTIO ready...")
-            while not self.drtio_is_up():
-                pass
-            print("OK")
-
-            self.core.reset()
-
-            for sawg in self.sawgs:
-                delay(1*ms)
-                sawg.reset()
-
-            for sawg in self.sawgs:
-                delay(1*ms)
-                sawg.amplitude1.set(.4)
-                # Do not use a sub-multiple of oscilloscope sample rates.
-                sawg.frequency0.set(9*MHz)
-
-            while self.drtio_is_up():
-                pass

artiq/examples/kasli_sawgmaster/repository/sines_urukul_sayma.py

@@ -1,89 +0,0 @@
-from artiq.experiment import *
-
-
-class SinesUrukulSayma(EnvExperiment):
-    def build(self):
-        self.setattr_device("core")
-        self.setattr_device("urukul0_cpld")
-
-        # Urukul clock output syntonized to the RTIO clock.
-        # Can be used as HMC830 reference on Sayma RTM.
-        # When using this reference, Sayma must be recalibrated every time Urukul
-        # is rebooted, as Urukul is not synchronized to the Kasli.
-        self.urukul_hmc_ref = self.get_device("urukul0_ch3")
-
-        # Urukul measurement channels - compare with SAWG outputs.
-        # When testing sync, do not reboot Urukul, as it is not
-        # synchronized to the Kasli.
-        self.urukul_meas = [self.get_device("urukul0_ch" + str(i)) for i in range(3)]
-        # The same waveform is output on all first 4 SAWG channels (first DAC).
-        self.sawgs = [self.get_device("sawg"+str(i)) for i in range(4)]
-        self.basemod = self.get_device("basemod_att0")
-        self.rfsws = [self.get_device("sawg_sw"+str(i)) for i in range(4)]
-
-
-    # DRTIO destinations:
-    # 0: local
-    # 1: Sayma AMC
-    # 2: Sayma RTM
-    @kernel
-    def drtio_is_up(self):
-        for i in range(3):
-            if not self.core.get_rtio_destination_status(i):
-                return False
-        return True
-
-    @kernel
-    def run(self):
-        f = 9*MHz
-        dds_ftw = self.urukul_meas[0].frequency_to_ftw(f)
-        sawg_ftw = self.sawgs[0].frequency0.to_mu(f)
-        if dds_ftw != sawg_ftw:
-            print("DDS and SAWG FTWs do not match:", dds_ftw, sawg_ftw)
-            return
-
-        self.core.reset()
-        self.urukul0_cpld.init()
-
-        delay(1*ms)
-        self.urukul_hmc_ref.init()
-        self.urukul_hmc_ref.set_mu(0x40000000, asf=self.urukul_hmc_ref.amplitude_to_asf(0.6))
-        self.urukul_hmc_ref.set_att(6.)
-        self.urukul_hmc_ref.sw.on()
-
-        for urukul_ch in self.urukul_meas:
-            delay(1*ms)
-            urukul_ch.init()
-            urukul_ch.set_mu(dds_ftw, asf=urukul_ch.amplitude_to_asf(0.5))
-            urukul_ch.set_att(6.)
-            urukul_ch.sw.on()
-
-        while True:
-            print("waiting for DRTIO ready...")
-            while not self.drtio_is_up():
-                pass
-            print("OK")
-
-            self.core.reset()
-
-            delay(10*ms)
-            self.basemod.reset()
-            delay(10*ms)
-            self.basemod.set(3.0, 3.0, 3.0, 3.0)
-            delay(10*ms)
-            for rfsw in self.rfsws:
-                delay(1*ms)
-                rfsw.on()
-
-            for sawg in self.sawgs:
-                delay(1*ms)
-                sawg.reset()
-
-            for sawg in self.sawgs:
-                delay(1*ms)
-                sawg.amplitude1.set(.4)
-                sawg.frequency0.set_mu(sawg_ftw)
-                sawg.phase0.set_mu(sawg_ftw*now_mu() >> 17)
-
-            while self.drtio_is_up():
-                pass

artiq/examples/kasli_shuttler/kasli_shuttler.json

@@ -0,0 +1,18 @@
+{
+    "target": "kasli",
+    "variant": "shuttlerdemo",
+    "hw_rev": "v2.0",
+    "drtio_role": "master",
+    "peripherals": [
+        {
+            "type": "shuttler",
+            "ports": [0]
+        },
+        {
+            "type": "dio",
+            "ports": [1],
+            "bank_direction_low": "input",
+            "bank_direction_high": "output"
+        }
+    ]
+}   

artiq/examples/kasli_shuttler/repository/shuttler.py

@@ -0,0 +1,330 @@
+from artiq.experiment import *
+from artiq.coredevice.shuttler import shuttler_volt_to_mu
+
+DAC_Fs_MHZ = 125
+CORDIC_GAIN = 1.64676
+
+@portable
+def shuttler_phase_offset(offset_degree):
+    return round(offset_degree / 360 * (2 ** 16))
+
+@portable
+def shuttler_freq_mu(freq_mhz):
+    return round(float(2) ** 32 / DAC_Fs_MHZ * freq_mhz)
+
+@portable
+def shuttler_chirp_rate_mu(freq_mhz_per_us):
+    return round(float(2) ** 32 * freq_mhz_per_us / (DAC_Fs_MHZ ** 2))
+
+@portable
+def shuttler_freq_sweep(start_f_MHz, end_f_MHz, time_us):
+    return shuttler_chirp_rate_mu((end_f_MHz - start_f_MHz)/(time_us))
+
+@portable
+def shuttler_volt_amp_mu(volt):
+    return shuttler_volt_to_mu(volt)
+
+@portable
+def shuttler_volt_damp_mu(volt_per_us):
+    return round(float(2) ** 32 * (volt_per_us / 20) / DAC_Fs_MHZ)
+
+@portable
+def shuttler_volt_ddamp_mu(volt_per_us_square):
+    return round(float(2) ** 48 * (volt_per_us_square / 20) * 2 / (DAC_Fs_MHZ ** 2))
+
+@portable
+def shuttler_volt_dddamp_mu(volt_per_us_cube):
+    return round(float(2) ** 48 * (volt_per_us_cube / 20) * 6 / (DAC_Fs_MHZ ** 3))
+
+@portable
+def shuttler_dds_amp_mu(volt):
+    return shuttler_volt_amp_mu(volt / CORDIC_GAIN)
+
+@portable
+def shuttler_dds_damp_mu(volt_per_us):
+    return shuttler_volt_damp_mu(volt_per_us / CORDIC_GAIN)
+
+@portable
+def shuttler_dds_ddamp_mu(volt_per_us_square):
+    return shuttler_volt_ddamp_mu(volt_per_us_square / CORDIC_GAIN)
+
+@portable
+def shuttler_dds_dddamp_mu(volt_per_us_cube):
+    return shuttler_volt_dddamp_mu(volt_per_us_cube / CORDIC_GAIN)
+
+class Shuttler(EnvExperiment):
+    def build(self):
+        self.setattr_device("core")
+        self.setattr_device("core_dma")
+        self.setattr_device("scheduler")
+        self.shuttler0_leds = [ self.get_device("shuttler0_led{}".format(i)) for i in range(2) ]
+        self.setattr_device("shuttler0_config")
+        self.setattr_device("shuttler0_trigger")
+        self.shuttler0_dcbias = [ self.get_device("shuttler0_dcbias{}".format(i)) for i in range(16) ]
+        self.shuttler0_dds = [ self.get_device("shuttler0_dds{}".format(i)) for i in range(16) ]
+        self.setattr_device("shuttler0_relay")
+        self.setattr_device("shuttler0_adc")
+        
+
+    @kernel
+    def record(self):
+        with self.core_dma.record("example_waveform"):
+            self.example_waveform()
+
+    @kernel
+    def init(self):
+        self.led()
+        self.relay_init()
+        self.adc_init()
+        self.shuttler_reset()
+
+    @kernel
+    def run(self):
+        self.core.reset()
+        self.core.break_realtime()
+        self.init()
+
+        self.record()
+        example_waveform_handle = self.core_dma.get_handle("example_waveform")
+
+        print("Example Waveforms are on OUT0 and OUT1")
+        self.core.break_realtime()
+        while not(self.scheduler.check_termination()):
+            delay(1*s)
+            self.core_dma.playback_handle(example_waveform_handle)
+
+    @kernel
+    def shuttler_reset(self):
+        for i in range(16):
+            self.shuttler_channel_reset(i)
+            # To avoid RTIO Underflow
+            delay(50*us)
+
+    @kernel
+    def shuttler_channel_reset(self, ch):
+        self.shuttler0_dcbias[ch].set_waveform(
+            a0=0,
+            a1=0,
+            a2=0,
+            a3=0,
+        )
+        self.shuttler0_dds[ch].set_waveform(
+            b0=0,
+            b1=0,
+            b2=0,
+            b3=0,
+            c0=0,
+            c1=0,
+            c2=0,
+        )
+        self.shuttler0_trigger.trigger(1 << ch)
+
+    @kernel
+    def example_waveform(self):
+        # Equation of Output Waveform
+        #   w(t_us) = a(t_us) + b(t_us) * cos(c(t_us))
+        # Step 1:
+        #   Enable the Output Relay of OUT0 and OUT1
+        # Step 2: Cosine Wave Frequency Sweep from 10kHz to 50kHz in 500us
+        #   OUT0: b(t_us) = 1
+        #         c(t_us) = 2 * pi * (0.08 * t_us ^ 2 + 0.01 * t_us)
+        #   OUT1: b(t_us) = 1
+        #         c(t_us) = 2 * pi * (0.05 * t_us)
+        # Step 3(after 500us): Cosine Wave with 180 Degree Phase Offset
+        #   OUT0: b(t_us) = 1
+        #         c(t_us) = 2 * pi * (0.05 * t_us) + pi
+        #   OUT1: b(t_us) = 1
+        #         c(t_us) = 2 * pi * (0.05 * t_us)
+        # Step 4(after 500us): Cosine Wave with Amplitude Envelop
+        #   OUT0: b(t_us) = -0.0001367187 * t_us ^ 2 + 0.06835937 * t_us
+        #         c(t_us) = 2 * pi * (0.05 * t_us)
+        #   OUT1: b(t_us) = -0.0001367187 * t_us ^ 2 + 0.06835937 * t_us
+        #         c(t_us) = 0
+        # Step 5(after 500us): Sawtooth Wave Modulated with 50kHz Cosine Wave 
+        #   OUT0: a(t_us) = 0.01 * t_us - 5
+        #         b(t_us) = 1
+        #         c(t_us) = 2 * pi * (0.05 * t_us)
+        #   OUT1: a(t_us) = 0.01 * t_us - 5
+        # Step 6(after 1000us): A Combination of Previous Waveforms
+        #   OUT0: a(t_us) = 0.01 * t_us - 5
+        #         b(t_us) = -0.0001367187 * t_us ^ 2 + 0.06835937 * t_us
+        #         c(t_us) = 2 * pi * (0.08 * t_us ^ 2 + 0.01 * t_us)
+        # Step 7(after 500us): Mirrored Waveform in Step 6
+        #   OUT0: a(t_us) = 2.5 + -0.01 * (1000 ^ 2) * t_us
+        #         b(t_us) = 0.0001367187 * t_us ^ 2 - 0.06835937 * t_us
+        #         c(t_us) = 2 * pi * (-0.08 * t_us ^ 2 + 0.05 * t_us) + pi
+        # Step 8(after 500us):
+        #   Disable Output Relay of OUT0 and OUT1
+        #   Reset OUT0 and OUT1
+    
+        ## Step 1 ##
+        self.shuttler0_relay.enable(0b11)
+
+        ## Step 2 ##
+        start_f_MHz = 0.01
+        end_f_MHz = 0.05
+        duration_us = 500
+        # OUT0 and OUT1 have their frequency and phase aligned at 500us
+        self.shuttler0_dds[0].set_waveform(
+            b0=shuttler_dds_amp_mu(1.0),
+            b1=0,
+            b2=0,
+            b3=0,
+            c0=0,
+            c1=shuttler_freq_mu(start_f_MHz),
+            c2=shuttler_freq_sweep(start_f_MHz, end_f_MHz, duration_us),
+        )
+        self.shuttler0_dds[1].set_waveform(
+            b0=shuttler_dds_amp_mu(1.0),
+            b1=0,
+            b2=0,
+            b3=0,
+            c0=0,
+            c1=shuttler_freq_mu(end_f_MHz),
+            c2=0,
+        )
+        self.shuttler0_trigger.trigger(0b11)
+        delay(500*us)
+
+        ## Step 3 ##
+        # OUT0 and OUT1 has 180 degree phase difference
+        self.shuttler0_dds[0].set_waveform(
+            b0=shuttler_dds_amp_mu(1.0),
+            b1=0,
+            b2=0,
+            b3=0,
+            c0=shuttler_phase_offset(180.0),
+            c1=shuttler_freq_mu(end_f_MHz),
+            c2=0,
+        )
+        # Phase and Output Setting of OUT1 is retained 
+        #   if the channel is not triggered or config is not cleared
+        self.shuttler0_trigger.trigger(0b1)
+        delay(500*us)
+
+        ## Step 4 ##
+        #     b(0) = 0, b(250) = 8.545, b(500) = 0
+        self.shuttler0_dds[0].set_waveform(
+            b0=0,
+            b1=shuttler_dds_damp_mu(0.06835937),
+            b2=shuttler_dds_ddamp_mu(-0.0001367187),
+            b3=0,
+            c0=0,
+            c1=shuttler_freq_mu(end_f_MHz),
+            c2=0,
+        )
+        self.shuttler0_dds[1].set_waveform(
+            b0=0,
+            b1=shuttler_dds_damp_mu(0.06835937),
+            b2=shuttler_dds_ddamp_mu(-0.0001367187),
+            b3=0,
+            c0=0,
+            c1=0,
+            c2=0,
+        )
+        self.shuttler0_trigger.trigger(0b11)
+        delay(500*us)
+
+        ## Step 5 ##
+        self.shuttler0_dcbias[0].set_waveform(
+            a0=shuttler_volt_amp_mu(-5.0),
+            a1=int32(shuttler_volt_damp_mu(0.01)),
+            a2=0,
+            a3=0,
+        )
+        self.shuttler0_dds[0].set_waveform(
+            b0=shuttler_dds_amp_mu(1.0),
+            b1=0,
+            b2=0,
+            b3=0,
+            c0=0,
+            c1=shuttler_freq_mu(end_f_MHz),
+            c2=0,
+        )
+        self.shuttler0_dcbias[1].set_waveform(
+            a0=shuttler_volt_amp_mu(-5.0),
+            a1=int32(shuttler_volt_damp_mu(0.01)),
+            a2=0,
+            a3=0,
+        )
+        self.shuttler0_dds[1].set_waveform(
+            b0=0,
+            b1=0,
+            b2=0,
+            b3=0,
+            c0=0,
+            c1=0,
+            c2=0,
+        )
+        self.shuttler0_trigger.trigger(0b11)
+        delay(1000*us)
+        
+        ## Step 6 ##
+        self.shuttler0_dcbias[0].set_waveform(
+            a0=shuttler_volt_amp_mu(-2.5),
+            a1=int32(shuttler_volt_damp_mu(0.01)),
+            a2=0,
+            a3=0,
+        )
+        self.shuttler0_dds[0].set_waveform(
+            b0=0,
+            b1=shuttler_dds_damp_mu(0.06835937),
+            b2=shuttler_dds_ddamp_mu(-0.0001367187),
+            b3=0,
+            c0=0,
+            c1=shuttler_freq_mu(start_f_MHz),
+            c2=shuttler_freq_sweep(start_f_MHz, end_f_MHz, duration_us),
+        )
+        self.shuttler0_trigger.trigger(0b1)
+        self.shuttler_channel_reset(1)
+        delay(500*us)
+
+        ## Step 7 ##
+        self.shuttler0_dcbias[0].set_waveform(
+            a0=shuttler_volt_amp_mu(2.5),
+            a1=int32(shuttler_volt_damp_mu(-0.01)),
+            a2=0,
+            a3=0,
+        )
+        self.shuttler0_dds[0].set_waveform(
+            b0=0,
+            b1=shuttler_dds_damp_mu(-0.06835937),
+            b2=shuttler_dds_ddamp_mu(0.0001367187),
+            b3=0,
+            c0=shuttler_phase_offset(180.0),
+            c1=shuttler_freq_mu(end_f_MHz),
+            c2=shuttler_freq_sweep(end_f_MHz, start_f_MHz, duration_us),
+        )
+        self.shuttler0_trigger.trigger(0b1)
+        delay(500*us)
+
+        ## Step 8 ##
+        self.shuttler0_relay.enable(0)
+        self.shuttler_channel_reset(0)
+        self.shuttler_channel_reset(1)
+
+    @kernel
+    def led(self):
+        for i in range(2):
+            for j in range(3):
+                self.shuttler0_leds[i].pulse(.1*s)
+                delay(.1*s)
+
+    @kernel
+    def relay_init(self):
+        self.shuttler0_relay.init()
+        self.shuttler0_relay.enable(0x0000)
+
+    @kernel
+    def adc_init(self):
+        delay_mu(int64(self.core.ref_multiplier))
+        self.shuttler0_adc.power_up()
+
+        delay_mu(int64(self.core.ref_multiplier))
+        assert self.shuttler0_adc.read_id() >> 4 == 0x038d
+
+        delay_mu(int64(self.core.ref_multiplier))
+        # The actual output voltage is limited by the hardware, the calculated calibration gain and offset.
+        # For example, if the system has a calibration gain of 1.06, then the max output voltage = 10 / 1.06 = 9.43V.
+        # Setting a value larger than 9.43V will result in overflow.
+        self.shuttler0_adc.calibrate(self.shuttler0_dcbias, self.shuttler0_trigger, self.shuttler0_config)

artiq/examples/kasli_suservo/device_db.py

@@ -5,7 +5,11 @@ device_db = {
         "type": "local",
         "module": "artiq.coredevice.core",
         "class": "Core",
-        "arguments": {"host": core_addr, "ref_period": 1e-9}
+        "arguments": {
+            "host": core_addr,
+            "ref_period": 1e-9,
+            "analyzer_proxy": "core_analyzer"
+        }
     },
     "core_log": {
         "type": "controller",
@@ -13,6 +17,20 @@ device_db = {
         "port": 1068,
         "command": "aqctl_corelog -p {port} --bind {bind} " + core_addr
     },
+    "core_moninj": {
+        "type": "controller",
+        "host": "::1",
+        "port_proxy": 1383,
+        "port": 1384,
+        "command": "aqctl_moninj_proxy --port-proxy {port_proxy} --port-control {port} --bind {bind} " + core_addr
+    },
+    "core_analyzer": {
+        "type": "controller",
+        "host": "::1",
+        "port_proxy": 1385,
+        "port": 1386,
+        "command": "aqctl_coreanalyzer_proxy --port-proxy {port_proxy} --port-control {port} --bind {bind} " + core_addr
+    },
     "core_cache": {
         "type": "local",
         "module": "artiq.coredevice.cache",
@@ -27,13 +45,13 @@ device_db = {
     "i2c_switch0": {
         "type": "local",
         "module": "artiq.coredevice.i2c",
-        "class": "PCA9548",
+        "class": "I2CSwitch",
         "arguments": {"address": 0xe0}
     },
     "i2c_switch1": {
         "type": "local",
         "module": "artiq.coredevice.i2c",
-        "class": "PCA9548",
+        "class": "I2CSwitch",
         "arguments": {"address": 0xe2}
     },
 

artiq/examples/kc705_nist_clock/device_db.py

@@ -9,7 +9,11 @@ device_db = {
         "type": "local",
         "module": "artiq.coredevice.core",
         "class": "Core",
-        "arguments": {"host": core_addr, "ref_period": 1e-9}
+        "arguments": {
+            "host": core_addr,
+            "ref_period": 1e-9,
+            "analyzer_proxy": "core_analyzer"
+        }
     },
     "core_log": {
         "type": "controller",
@@ -17,6 +21,20 @@ device_db = {
         "port": 1068,
         "command": "aqctl_corelog -p {port} --bind {bind} " + core_addr
     },
+    "core_moninj": {
+        "type": "controller",
+        "host": "::1",
+        "port_proxy": 1383,
+        "port": 1384,
+        "command": "aqctl_moninj_proxy --port-proxy {port_proxy} --port-control {port} --bind {bind} " + core_addr
+    },
+    "core_analyzer": {
+        "type": "controller",
+        "host": "::1",
+        "port_proxy": 1385,
+        "port": 1386,
+        "command": "aqctl_coreanalyzer_proxy --port-proxy {port_proxy} --port-control {port} --bind {bind} " + core_addr
+    },
     "core_cache": {
         "type": "local",
         "module": "artiq.coredevice.cache",
@@ -31,7 +49,7 @@ device_db = {
     "i2c_switch": {
         "type": "local",
         "module": "artiq.coredevice.i2c",
-        "class": "PCA9548"
+        "class": "I2CSwitch"
     },
 
     # Generic TTL

artiq/examples/kc705_nist_clock/repository/dds_setter.py

@@ -20,7 +20,7 @@ class DDSSetter(EnvExperiment):
                     "driver": self.get_device(k),
                     "frequency": self.get_argument(
                         "{}_frequency".format(k),
-                        NumberValue(100e6, scale=1e6, unit="MHz", ndecimals=6))
+                        NumberValue(100e6, scale=1e6, unit="MHz", precision=6))
                 }
 
     @kernel

artiq/examples/kc705_nist_clock/repository/photon_histogram.py

@@ -12,8 +12,8 @@ class PhotonHistogram(EnvExperiment):
         self.setattr_device("bdd_sw")
         self.setattr_device("pmt")
 
-        self.setattr_argument("nbins", NumberValue(100, ndecimals=0, step=1))
+        self.setattr_argument("nbins", NumberValue(100, precision=0, step=1))
-        self.setattr_argument("repeats", NumberValue(100, ndecimals=0, step=1))
+        self.setattr_argument("repeats", NumberValue(100, precision=0, step=1))
 
         self.setattr_dataset("cool_f", 230*MHz)
         self.setattr_dataset("detect_f", 220*MHz)

artiq/examples/kc705_nist_clock/repository/precompile.py

@@ -0,0 +1,20 @@
+from artiq.experiment import *
+
+
+class Precompile(EnvExperiment):
+    def build(self):
+        self.setattr_device("core")
+        self.hello_str = "hello ARTIQ"
+
+    def prepare(self):
+    	self.precompiled = self.core.precompile(self.hello, "world")
+
+    @kernel
+    def hello(self, arg):
+    	print(self.hello_str, arg)
+    	self.hello_str = "nowriteback"
+
+    def run(self):
+        self.precompiled()
+        self.hello_str = "noupdate"
+        self.precompiled()

artiq/examples/kc705_nist_clock/repository/speed_benchmark.py

@@ -79,7 +79,7 @@ class SpeedBenchmark(EnvExperiment):
                                                            "CoreSend1MB",
                                                            "CorePrimes"]))
         self.setattr_argument("nruns", NumberValue(10, min=1, max=1000,
-                                                   ndecimals=0, step=1))
+                                                   precision=0, step=1))
         self.setattr_device("core")
         self.setattr_device("scheduler")
 

artiq/examples/metlino_sayma_ttl/device_db.py

@@ -1,95 +0,0 @@
-core_addr = "192.168.1.65"
-
-device_db = {
-    "core": {
-        "type": "local",
-        "module": "artiq.coredevice.core",
-        "class": "Core",
-        "arguments": {"host": core_addr, "ref_period": 1/(8*150e6)}
-    },
-    "core_log": {
-        "type": "controller",
-        "host": "::1",
-        "port": 1068,
-        "command": "aqctl_corelog -p {port} --bind {bind} " + core_addr
-    },
-    "core_cache": {
-        "type": "local",
-        "module": "artiq.coredevice.cache",
-        "class": "CoreCache"
-    },
-    "core_dma": {
-        "type": "local",
-        "module": "artiq.coredevice.dma",
-        "class": "CoreDMA"
-    }
-}
-
-# master peripherals
-for i in range(4):
-    device_db["led" + str(i)] = {
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": i},
-}
-
-# DEST#1 peripherals
-amc_base = 0x070000
-rtm_base = 0x020000
-
-for i in range(4):
-    device_db["led" + str(4+i)] = {
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": amc_base + i},
-    }
-
-#DIO (EEM0) starting at RTIO channel 0x000056
-for i in range(8):
-    device_db["ttl" + str(i)] = {
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": amc_base + 0x000056 + i},
-    }
-
-#DIO (EEM1) starting at RTIO channel 0x00005e
-for i in range(8):
-    device_db["ttl" + str(8+i)] = {
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": amc_base + 0x00005e + i},
-    }
-
-device_db["fmcdio_dirctl_clk"] = {
-    "type": "local",
-    "module": "artiq.coredevice.ttl",
-    "class": "TTLOut",
-    "arguments": {"channel": amc_base + 0x000066}
-}
-
-device_db["fmcdio_dirctl_ser"] = {
-    "type": "local",
-    "module": "artiq.coredevice.ttl",
-    "class": "TTLOut",
-    "arguments": {"channel": amc_base + 0x000067}
-}
-
-device_db["fmcdio_dirctl_latch"] = {
-    "type": "local",
-    "module": "artiq.coredevice.ttl",
-    "class": "TTLOut",
-    "arguments": {"channel": amc_base + 0x000068}
-}
-
-device_db["fmcdio_dirctl"] = {
-    "type": "local",
-    "module": "artiq.coredevice.shiftreg",
-    "class": "ShiftReg",
-    "arguments": {"clk": "fmcdio_dirctl_clk",
-                  "ser": "fmcdio_dirctl_ser",
-                  "latch": "fmcdio_dirctl_latch"}
-}

artiq/examples/metlino_sayma_ttl/repository/demo.py

@@ -1,129 +0,0 @@
-import sys
-import os
-import select
-
-from artiq.experiment import *
-from artiq.coredevice.fmcdio_vhdci_eem import *
-
-
-def chunker(seq, size):
-    res = []
-    for el in seq:
-        res.append(el)
-        if len(res) == size:
-            yield res
-            res = []
-    if res:
-        yield res
-
-
-def is_enter_pressed() -> TBool:
-    if os.name == "nt":
-        if msvcrt.kbhit() and msvcrt.getch() == b"\r":
-            return True
-        else:
-            return False
-    else:
-        if select.select([sys.stdin, ], [], [], 0.0)[0]:
-            sys.stdin.read(1)
-            return True
-        else:
-            return False
-
-
-class Demo(EnvExperiment):
-    def build(self):
-        self.setattr_device("core")
-        self.setattr_device("fmcdio_dirctl")
-
-        self.leds = dict()
-        self.ttl_outs = dict()
-
-        ddb = self.get_device_db()
-        for name, desc in ddb.items():
-            if isinstance(desc, dict) and desc["type"] == "local":
-                module, cls = desc["module"], desc["class"]
-                if (module, cls) == ("artiq.coredevice.ttl", "TTLOut"):
-                    dev = self.get_device(name)
-                    if "led" in name:   # guess
-                        self.leds[name] = dev
-                    elif "ttl" in name: # to exclude fmcdio_dirctl
-                        self.ttl_outs[name] = dev
-
-        self.leds = sorted(self.leds.items(), key=lambda x: x[1].channel)
-        self.ttl_outs = sorted(self.ttl_outs.items(), key=lambda x: x[1].channel)
-
-        self.dirctl_word = (
-            shiftreg_bits(0, dio_bank0_out_pins | dio_bank1_out_pins) |
-            shiftreg_bits(1, dio_bank0_out_pins | dio_bank1_out_pins)
-        )
-
-    @kernel
-    def init(self):
-        self.core.break_realtime()
-        print("*** Waiting for DRTIO ready...")
-        drtio_indices = [7]
-        for i in drtio_indices:
-            while not self.drtio_is_up(i):
-                pass
-
-        self.fmcdio_dirctl.set(self.dirctl_word)
-
-    @kernel
-    def drtio_is_up(self, drtio_index):
-        if not self.core.get_rtio_destination_status(drtio_index):
-            return False
-        print("DRTIO #", drtio_index, "is ready\n")
-        return True
-
-    @kernel
-    def test_led(self, led):
-        while not is_enter_pressed():
-            self.core.break_realtime()
-            # do not fill the FIFOs too much to avoid long response times
-            t = now_mu() - self.core.seconds_to_mu(0.2)
-            while self.core.get_rtio_counter_mu() < t:
-                pass
-            for i in range(3):
-                led.pulse(100*ms)
-                delay(100*ms)
-
-    def test_leds(self):
-        print("*** Testing LEDs.")
-        print("Check for blinking. Press ENTER when done.")
-
-        for led_name, led_dev in self.leds:
-            print("Testing LED: {}".format(led_name))
-            self.test_led(led_dev)
-
-    @kernel
-    def test_ttl_out_chunk(self, ttl_chunk):
-        while not is_enter_pressed():
-            self.core.break_realtime()
-            for _ in range(50000):
-                i = 0
-                for ttl in ttl_chunk:
-                    i += 1
-                    for _ in range(i):
-                        ttl.pulse(1*us)
-                        delay(1*us)
-                    delay(10*us)
-
-    def test_ttl_outs(self):
-        print("*** Testing TTL outputs.")
-        print("Outputs are tested in groups of 4. Touch each TTL connector")
-        print("with the oscilloscope probe tip, and check that the number of")
-        print("pulses corresponds to its number in the group.")
-        print("Press ENTER when done.")
-
-        for ttl_chunk in chunker(self.ttl_outs, 4):
-            print("Testing TTL outputs: {}.".format(", ".join(name for name, dev in ttl_chunk)))
-            self.test_ttl_out_chunk([dev for name, dev in ttl_chunk])
-
-    def run(self):
-        self.core.reset()
-
-        if self.leds:
-            self.test_leds()
-        if self.ttl_outs:
-            self.test_ttl_outs()

artiq/examples/no_hardware/repository/arguments_demo.py

@@ -45,13 +45,13 @@ class ArgumentsDemo(EnvExperiment):
             PYONValue(self.get_dataset("foo", default=42)))
         self.setattr_argument("number", NumberValue(42e-6,
                                                     unit="us",
-                                                    ndecimals=4))
+                                                    precision=4))
         self.setattr_argument("integer", NumberValue(42,
-                                                     step=1, ndecimals=0))
+                                                     step=1, precision=0))
         self.setattr_argument("string", StringValue("Hello World"))
         self.setattr_argument("scan", Scannable(global_max=400,
                                                 default=NoScan(325),
-                                                ndecimals=6))
+                                                precision=6))
         self.setattr_argument("boolean", BooleanValue(True), "Group")
         self.setattr_argument("enum", EnumerationValue(
             ["foo", "bar", "quux"], "foo"), "Group")

artiq/examples/no_hardware/repository/custom_applet.py

@@ -4,13 +4,13 @@ from artiq.applets.simple import SimpleApplet
 
 
 class DemoWidget(QtWidgets.QLabel):
-    def __init__(self, args):
+    def __init__(self, args, ctl):
         QtWidgets.QLabel.__init__(self)
         self.dataset_name = args.dataset
 
-    def data_changed(self, data, mods):
+    def data_changed(self, value, metadata, persist, mods):
         try:
-            n = str(data[self.dataset_name][1])
+            n = str(value[self.dataset_name])
         except (KeyError, ValueError, TypeError):
             n = "---"
         n = "<font size=15>" + n + "</font>"

artiq/examples/sayma_master/device_db.py

@@ -1,166 +0,0 @@
-core_addr = "192.168.1.60"
-
-device_db = {
-    "core": {
-        "type": "local",
-        "module": "artiq.coredevice.core",
-        "class": "Core",
-        "arguments": {"host": core_addr, "ref_period": 1/(8*150e6)}
-    },
-    "core_log": {
-        "type": "controller",
-        "host": "::1",
-        "port": 1068,
-        "command": "aqctl_corelog -p {port} --bind {bind} " + core_addr
-    },
-    "core_cache": {
-        "type": "local",
-        "module": "artiq.coredevice.cache",
-        "class": "CoreCache"
-    },
-    "core_dma": {
-        "type": "local",
-        "module": "artiq.coredevice.dma",
-        "class": "CoreDMA"
-    },
-}
-
-for i in range(4):
-    device_db["led" + str(i)] = {
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": i},
-    }
-
-
-for i in range(2):
-    device_db["ttl" + str(i)] = {
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLInOut",
-        "arguments": {"channel": 4 + i},
-    }
-
-
-device_db.update(
-    fmcdio_dirctl_clk={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 6}
-    },
-    fmcdio_dirctl_ser={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 7}
-    },
-    fmcdio_dirctl_latch={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 8}
-    },
-    fmcdio_dirctl={
-        "type": "local",
-        "module": "artiq.coredevice.shiftreg",
-        "class": "ShiftReg",
-        "arguments": {"clk": "fmcdio_dirctl_clk",
-                      "ser": "fmcdio_dirctl_ser",
-                      "latch": "fmcdio_dirctl_latch"}
-    }
-)
-
-device_db.update(
-    spi_urukul0={
-        "type": "local",
-        "module": "artiq.coredevice.spi2",
-        "class": "SPIMaster",
-        "arguments": {"channel": 17}
-    },
-    ttl_urukul0_io_update={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 18}
-    },
-    ttl_urukul0_sw0={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 19}
-    },
-    ttl_urukul0_sw1={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 20}
-    },
-    ttl_urukul0_sw2={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 21}
-    },
-    ttl_urukul0_sw3={
-        "type": "local",
-        "module": "artiq.coredevice.ttl",
-        "class": "TTLOut",
-        "arguments": {"channel": 22}
-    },
-    urukul0_cpld={
-        "type": "local",
-        "module": "artiq.coredevice.urukul",
-        "class": "CPLD",
-        "arguments": {
-            "spi_device": "spi_urukul0",
-            "io_update_device": "ttl_urukul0_io_update",
-            "refclk": 125e6,
-            "clk_sel": 0
-        }
-    }
-)
-
-for i in range(4):
-    device_db["urukul0_ch" + str(i)] = {
-        "type": "local",
-        "module": "artiq.coredevice.ad9910",
-        "class": "AD9910",
-        "arguments": {
-            "pll_n": 32,
-            "chip_select": 4 + i,
-            "cpld_device": "urukul0_cpld",
-            "sw_device": "ttl_urukul0_sw" + str(i)
-        }
-    }
-
-
-device_db["spi_zotino0"] = {
-    "type": "local",
-    "module": "artiq.coredevice.spi2",
-    "class": "SPIMaster",
-    "arguments": {"channel": 23}
-}
-device_db["ttl_zotino0_ldac"] = {
-    "type": "local",
-    "module": "artiq.coredevice.ttl",
-    "class": "TTLOut",
-    "arguments": {"channel": 24}
-}
-device_db["ttl_zotino0_clr"] = {
-    "type": "local",
-    "module": "artiq.coredevice.ttl",
-    "class": "TTLOut",
-    "arguments": {"channel": 25}
-}
-device_db["zotino0"] = {
-    "type": "local",
-    "module": "artiq.coredevice.zotino",
-    "class": "Zotino",
-    "arguments": {
-        "spi_device": "spi_zotino0",
-        "ldac_device": "ttl_zotino0_ldac",
-        "clr_device": "ttl_zotino0_clr"
-    }
-}

artiq/examples/sayma_master/repository/demo.py

@@ -1,41 +0,0 @@
-from artiq.experiment import *
-from artiq.coredevice.fmcdio_vhdci_eem import *
-
-
-class Demo(EnvExperiment):
-    def build(self):
-        self.setattr_device("core")
-        self.setattr_device("fmcdio_dirctl")
-
-        self.ttls = [self.get_device("ttl" + str(i)) for i in range(8)]
-        self.setattr_device("urukul0_cpld")
-        self.urukul_chs = [self.get_device("urukul0_ch" + str(i)) for i in range(4)]
-        self.setattr_device("zotino0")
-
-        self.dirctl_word = (
-            shiftreg_bits(1, urukul_out_pins) |
-            shiftreg_bits(0, urukul_aux_out_pins) |
-            shiftreg_bits(2, dio_bank0_out_pins | dio_bank1_out_pins) |
-            shiftreg_bits(3, zotino_out_pins))
-
-    @kernel
-    def run(self):
-        self.core.reset()
-        delay(10*ms)
-        self.fmcdio_dirctl.set(self.dirctl_word)
-        delay(10*ms)
-
-        self.urukul0_cpld.init()
-        delay(10*ms)
-
-        self.zotino0.init()
-        delay(1*ms)
-        for i in range(32):
-            self.zotino0.write_dac(i, i/4)
-            delay(1*ms)
-
-        while True:
-            for ttl in self.ttls:
-                ttl.pulse(100*ms)
-            for urukul_ch in self.urukul_chs:
-                urukul_ch.sw.pulse(100*ms)

artiq/firmware/Cargo.lock

@@ -13,6 +13,12 @@ dependencies = [
 name = "alloc_list"
 version = "0.0.0"
 
+[[package]]
+name = "arrayvec"
+version = "0.7.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "96d30a06541fbafbc7f82ed10c06164cfbd2c401138f6addd8404629c4b16711"
+
 [[package]]
 name = "bare-metal"
 version = "0.2.5"
@@ -240,6 +246,12 @@ version = "0.7.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c75de51135344a4f8ed3cfe2720dc27736f7711989703a0b43aadf3753c55577"
 
+[[package]]
+name = "managed"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0ca88d725a0a943b096803bd34e73a4437208b6077654cc4ecb2947a5f91618d"
+
 [[package]]
 name = "memchr"
 version = "2.4.1"
@@ -253,6 +265,7 @@ dependencies = [
  "byteorder",
  "cslice",
  "dyld",
+ "eh",
  "failure",
  "failure_derive",
  "io",
@@ -313,6 +326,7 @@ dependencies = [
  "build_misoc",
  "byteorder",
  "cslice",
+ "dyld",
  "eh",
  "failure",
  "failure_derive",
@@ -320,10 +334,11 @@ dependencies = [
  "io",
  "log",
  "logger_artiq",
- "managed",
+ "managed 0.7.2",
  "proto_artiq",
  "riscv",
  "smoltcp",
+ "tar-no-std",
  "unwind_backtrace",
 ]
 
@@ -340,10 +355,15 @@ dependencies = [
 name = "satman"
 version = "0.0.0"
 dependencies = [
+ "alloc_list",
  "board_artiq",
  "board_misoc",
  "build_misoc",
+ "cslice",
+ "eh",
+ "io",
  "log",
+ "proto_artiq",
  "riscv",
 ]
 
@@ -364,13 +384,13 @@ checksum = "388a1df253eca08550bef6c72392cfe7c30914bf41df5269b68cbd6ff8f570a3"
 
 [[package]]
 name = "smoltcp"
-version = "0.6.0"
+version = "0.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0fe46639fd2ec79eadf8fe719f237a7a0bd4dac5d957f1ca5bbdbc1c3c39e53a"
+checksum = "ee34c1e1bfc7e9206cc0fb8030a90129b4e319ab53856249bb27642cab914fb3"
 dependencies = [
  "bitflags",
  "byteorder",
- "managed",
+ "managed 0.8.0",
 ]
 
 [[package]]
@@ -403,6 +423,16 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "tar-no-std"
+version = "0.1.8"
+source = "git+https://git.m-labs.hk/M-Labs/tar-no-std?rev=2ab6dc5#2ab6dc58e5249c59c4eb03eaf3a119bcdd678d32"
+dependencies = [
+ "arrayvec",
+ "bitflags",
+ "log",
+]
+
 [[package]]
 name = "unicode-xid"
 version = "0.0.4"

artiq/firmware/bootloader/Cargo.toml

@@ -16,5 +16,5 @@ build_misoc = { path = "../libbuild_misoc" }
 byteorder = { version = "1.0", default-features = false }
 crc = { version = "1.7", default-features = false }
 board_misoc = { path = "../libboard_misoc", features = ["uart_console", "smoltcp"] }
-smoltcp = { version = "0.6.0", default-features = false, features = ["ethernet", "proto-ipv4", "proto-ipv6", "socket-tcp"] }
+smoltcp = { version = "0.8.2", default-features = false, features = ["medium-ethernet", "proto-ipv4", "proto-ipv6", "socket-tcp"] }
 riscv = { version = "0.6.0", features = ["inline-asm"] }

artiq/firmware/bootloader/main.rs

@@ -18,6 +18,10 @@ use board_misoc::slave_fpga;
 use board_misoc::{clock, ethmac, net_settings};
 use board_misoc::uart_console::Console;
 use riscv::register::{mcause, mepc, mtval};
+#[cfg(has_ethmac)]
+use smoltcp::iface::{Routes, SocketStorage};
+#[cfg(has_ethmac)]
+use smoltcp::wire::{HardwareAddress, IpAddress, Ipv4Address, Ipv6Address};
 
 fn check_integrity() -> bool {
     extern {
@@ -65,8 +69,8 @@ fn memory_test(total: &mut usize, wrong: &mut usize) -> bool {
         })
     }
 
-    fn prng32(seed: &mut u32) -> u32 { *seed = 1664525 * *seed + 1013904223; *seed }
+    fn prng32(seed: &mut u32) -> u32 { *seed = u32::wrapping_add(u32::wrapping_mul(1664525, *seed), 1013904223); *seed }
-    fn prng16(seed: &mut u16) -> u16 { *seed = 25173 * *seed + 13849; *seed }
+    fn prng16(seed: &mut u16) -> u16 { *seed = u16::wrapping_add(u16::wrapping_mul(25173, *seed), 13849); *seed }
 
     for _ in 0..4 {
         // Test data bus
@@ -396,6 +400,9 @@ fn network_boot() {
 
     println!("Initializing network...");
 
+    // Assuming only one socket is ever needed by the bootloader.
+    // The smoltcp reuses the listening socket when the connection is established.
+    let mut sockets = [SocketStorage::EMPTY];
     let mut net_device = unsafe { ethmac::EthernetDevice::new() };
     net_device.reset_phy_if_any();
 
@@ -405,38 +412,38 @@ fn network_boot() {
     let net_addresses = net_settings::get_adresses();
     println!("Network addresses: {}", net_addresses);
     let mut ip_addrs = [
-        IpCidr::new(net_addresses.ipv4_addr, 0),
+        IpCidr::new(IpAddress::Ipv4(Ipv4Address::UNSPECIFIED), 0),
-        IpCidr::new(net_addresses.ipv6_ll_addr, 0),
+        net_addresses.ipv6_ll_addr,
-        IpCidr::new(net_addresses.ipv6_ll_addr, 0)
+        IpCidr::new(IpAddress::Ipv6(Ipv6Address::UNSPECIFIED), 0)
     ];
-    let mut interface = match net_addresses.ipv6_addr {
+    if let net_settings::Ipv4AddrConfig::Static(ipv4) = net_addresses.ipv4_addr {
-        Some(addr) => {
+        ip_addrs[0] = IpCidr::Ipv4(ipv4);
-            ip_addrs[2] = IpCidr::new(addr, 0);
+    }
-            smoltcp::iface::EthernetInterfaceBuilder::new(net_device)
+    if let Some(ipv6) =  net_addresses.ipv6_addr {
-                       .ethernet_addr(net_addresses.hardware_addr)
+        ip_addrs[2] = IpCidr::Ipv6(ipv6);
+    };
+    let mut routes = [None; 2];
+    let mut interface = smoltcp::iface::InterfaceBuilder::new(net_device, &mut sockets[..])
+        .hardware_addr(HardwareAddress::Ethernet(net_addresses.hardware_addr))
         .ip_addrs(&mut ip_addrs[..])
         .neighbor_cache(neighbor_cache)
-                       .finalize()
+        .routes(Routes::new(&mut routes[..]))
+        .finalize();
+
+    if let Some(default_route) = net_addresses.ipv4_default_route {
+        interface.routes_mut().add_default_ipv4_route(default_route).unwrap();
+    }
+    if let Some(default_route) = net_addresses.ipv6_default_route {
+        interface.routes_mut().add_default_ipv6_route(default_route).unwrap();
     }
-        None =>
-            smoltcp::iface::EthernetInterfaceBuilder::new(net_device)
-                       .ethernet_addr(net_addresses.hardware_addr)
-                       .ip_addrs(&mut ip_addrs[..2])
-                       .neighbor_cache(neighbor_cache)
-                       .finalize()
-    };
 
     let mut rx_storage = [0; 4096];
     let mut tx_storage = [0; 128];
 
-    let mut socket_set_entries: [_; 1] = Default::default();
-    let mut sockets =
-        smoltcp::socket::SocketSet::new(&mut socket_set_entries[..]);
-
     let tcp_rx_buffer = smoltcp::socket::TcpSocketBuffer::new(&mut rx_storage[..]);
     let tcp_tx_buffer = smoltcp::socket::TcpSocketBuffer::new(&mut tx_storage[..]);
     let tcp_socket = smoltcp::socket::TcpSocket::new(tcp_rx_buffer, tcp_tx_buffer);
-    let tcp_handle = sockets.add(tcp_socket);
+    let tcp_handle = interface.add_socket(tcp_socket);
 
     let mut net_conn = NetConn::new();
     let mut boot_time = None;
@@ -446,7 +453,7 @@ fn network_boot() {
     loop {
         let timestamp = clock::get_ms() as i64;
         {
-            let socket = &mut *sockets.get::<smoltcp::socket::TcpSocket>(tcp_handle);
+            let socket = &mut *interface.get_socket::<smoltcp::socket::TcpSocket>(tcp_handle);
 
             match boot_time {
                 None => {
@@ -475,7 +482,7 @@ fn network_boot() {
             }
         }
 
-        match interface.poll(&mut sockets, smoltcp::time::Instant::from_millis(timestamp)) {
+        match interface.poll(smoltcp::time::Instant::from_millis(timestamp)) {
             Ok(_) => (),
             Err(smoltcp::Error::Unrecognized) => (),
             Err(err) => println!("Network error: {}", err)
@@ -493,7 +500,7 @@ pub extern fn main() -> i32 {
     println!(r"|_|  |_|_|____/ \___/ \____|");
     println!("");
     println!("MiSoC Bootloader");
-    println!("Copyright (c) 2017-2021 M-Labs Limited");
+    println!("Copyright (c) 2017-2023 M-Labs Limited");
     println!("");
 
     #[cfg(has_ethmac)]

artiq/firmware/firmware.ld

@@ -6,7 +6,7 @@ ENTRY(_reset_handler)
  * ld does not allow this expression here.
  */
 MEMORY {
-    runtime (RWX) : ORIGIN = 0x40000000, LENGTH = 0x4000000 /* 64M */
+    firmware (RWX) : ORIGIN = 0x40000000, LENGTH = 0x4000000 /* 64M */
 }
 
 SECTIONS
@@ -14,24 +14,24 @@ SECTIONS
     .vectors :
     {
         *(.vectors)
-    } > runtime
+    } > firmware
 
     .text :
     {
         *(.text .text.*)
-    } > runtime
+    } > firmware
 
     .eh_frame :
     {
         __eh_frame_start = .;
         KEEP(*(.eh_frame))
         __eh_frame_end = .;
-    } > runtime
+    } > firmware
 
     .eh_frame_hdr :
     {
         KEEP(*(.eh_frame_hdr))
-    } > runtime
+    } > firmware
 
     __eh_frame_hdr_start = SIZEOF(.eh_frame_hdr) > 0 ? ADDR(.eh_frame_hdr) : 0;
     __eh_frame_hdr_end = SIZEOF(.eh_frame_hdr) > 0 ? . : 0;
@@ -39,35 +39,35 @@ SECTIONS
     .gcc_except_table :
     {
         *(.gcc_except_table)
-    } > runtime
+    } > firmware
 
     /* https://sourceware.org/bugzilla/show_bug.cgi?id=20475 */
     .got :
     {
         *(.got)
-    } > runtime
+    } > firmware
 
     .got.plt :
     {
         *(.got.plt)
-    } > runtime
+    } > firmware
 
     .rodata :
     {
         *(.rodata .rodata.*)
-    } > runtime
+    } > firmware
 
     .data :
     {
         *(.data .data.*)
-    } > runtime
+    } > firmware
 
     .bss (NOLOAD) : ALIGN(4)
     {
         _fbss = .;
         *(.sbss .sbss.* .bss .bss.*);
         _ebss = .;
-    } > runtime
+    } > firmware
 
     .stack (NOLOAD) : ALIGN(0x1000)
     {
@@ -76,12 +76,12 @@ SECTIONS
         _estack = .;
         . += 0x10000;
         _fstack = . - 16;
-    } > runtime
+    } > firmware
 
     .heap (NOLOAD) : ALIGN(16)
     {
         _fheap = .;
-        . = ORIGIN(runtime) + LENGTH(runtime);
+        . = ORIGIN(firmware) + LENGTH(firmware);
         _eheap = .;
-    } > runtime
+    } > firmware
 }

artiq/firmware/ksupport/Makefile

@@ -26,7 +26,7 @@ $(RUSTOUT)/libksupport.a:
 
 ksupport.elf: $(RUSTOUT)/libksupport.a glue.o
 	$(link) -T $(KSUPPORT_DIRECTORY)/ksupport.ld \
-		-lunwind-$(CPU)-elf -lprintf-float -lm
+		-lunwind-$(CPU)-libc -lprintf-float -lm
 
 %.o: $(KSUPPORT_DIRECTORY)/%.c
 	$(compile)