Merge branch 'master' into 117_rtio_channels

default.nix

@@ -22,7 +22,7 @@ let
       name = "firmware";
 
       src = ./src;
-      cargoSha256 = "0p9d2j7qp00wpxm48phl5rq26simzry6w0m673lyhrlbzqdz4frb";
+      cargoSha256 = "sha256-uiwESZNwPdVnDkA1n0v1DQHp3rTazDkgIYscVTpgNq0=";
 
       nativeBuildInputs = [
         pkgs.gnumake
@@ -35,7 +35,7 @@ let
         export XARGO_RUST_SRC="${rustPlatform.rust.rustc}/lib/rustlib/src/rust/library"
         export CLANG_EXTRA_INCLUDE_DIR="${pkgs.llvmPackages_9.clang-unwrapped.lib}/lib/clang/9.0.1/include"
         export CARGO_HOME=$(mktemp -d cargo-home.XXX)
-        make TARGET=${target} GWARGS="${if json == null then "-V ${variant}" else json}" ${fwtype}
+        make TARGET=${target} GWARGS="${if json == null then "-V ${variant}" else json}" ../build/${fwtype}.bin
       '';
 
       installPhase = ''

src/Makefile

@@ -1,18 +1,15 @@
 TARGET := zc706
 GWARGS := -V simple
 
-all: runtime
-
-runtime: ../build/runtime.bin
+all: ../build/runtime.bin
 
 .PHONY: all
 
-
-../build/pl.rs ../build/rustc-cfg: gateware/*
+../build/pl.rs ../build/rustc-cfg ../build/mem.rs: gateware/* 
 	mkdir -p ../build
 	python gateware/$(TARGET).py -r ../build/pl.rs -c ../build/rustc-cfg -m ../build/mem.rs $(GWARGS)
 
-../build/firmware/armv7-none-eabihf/release/runtime: ../build/pl.rs ../build/rustc-cfg
+../build/firmware/armv7-none-eabihf/release/runtime: ../build/pl.rs ../build/rustc-cfg ../build/mem.rs $(shell find . -print)
 	cd runtime && \
 	XBUILD_SYSROOT_PATH=`pwd`/../../build/sysroot \
 	cargo xbuild --release \
@@ -22,12 +19,12 @@ runtime: ../build/runtime.bin
 ../build/runtime.bin: ../build/firmware/armv7-none-eabihf/release/runtime
 	llvm-objcopy -O binary ../build/firmware/armv7-none-eabihf/release/runtime ../build/runtime.bin
 
-satmanout: ../build/pl.rs ../build/rustc-cfg
+../build/firmware/armv7-none-eabihf/release/satman: ../build/pl.rs ../build/rustc-cfg ../build/mem.rs $(shell find . -print)
 	cd satman && \
 	XBUILD_SYSROOT_PATH=`pwd`/../../build/sysroot \
 	cargo xbuild --release \
 		--target-dir ../../build/firmware \
 		--no-default-features --features=target_$(TARGET)
 
-satman: satmanout
+../build/satman.bin: ../build/firmware/armv7-none-eabihf/release/satman
 	llvm-objcopy -O binary ../build/firmware/armv7-none-eabihf/release/satman ../build/satman.bin

src/gateware/drtio_aux_controller.py

@@ -0,0 +1,85 @@
+"""Auxiliary controller, common to satellite and master"""
+
+from artiq.gateware.drtio.aux_controller import Transmitter, Receiver
+from migen.fhdl.simplify import FullMemoryWE
+from misoc.interconnect.csr import *
+from migen_axi.interconnect.sram import SRAM
+from migen_axi.interconnect import axi
+
+max_packet = 1024
+
+class _DRTIOAuxControllerBase(Module):
+    def __init__(self, link_layer):
+        self.bus = axi.Interface()
+        self.submodules.transmitter = Transmitter(link_layer, len(self.bus.w.data))
+        self.submodules.receiver = Receiver(link_layer, len(self.bus.w.data))
+
+    def get_csrs(self):
+        return self.transmitter.get_csrs() + self.receiver.get_csrs()
+
+
+# TODO: FullMemoryWE should be applied by migen.build
+@FullMemoryWE()
+class DRTIOAuxControllerAxi(_DRTIOAuxControllerBase):
+    def __init__(self, link_layer):
+        _DRTIOAuxControllerBase.__init__(self, link_layer)
+
+        tx_sdram_if = SRAM(self.transmitter.mem, read_only=False)
+        rx_sdram_if = SRAM(self.receiver.mem, read_only=True)
+        aw_decoder = axi.AddressDecoder(self.bus.aw,
+            [(lambda a: a[log2_int(max_packet)] == 0, tx_sdram_if.bus.aw),
+             (lambda a: a[log2_int(max_packet)] == 1, rx_sdram_if.bus.aw)],
+            register=True)
+        ar_decoder = axi.AddressDecoder(self.bus.ar,
+            [(lambda a: a[log2_int(max_packet)] == 0, tx_sdram_if.bus.ar),
+             (lambda a: a[log2_int(max_packet)] == 1, rx_sdram_if.bus.ar)],
+            register=True)
+        # unlike wb, axi address decoder only connects ar/aw lanes,
+        # the rest must also be connected!
+        # not quite unlike an address decoder itself.
+
+        # connect bus.b with tx.b
+        self.comb += [tx_sdram_if.bus.b.ready.eq(self.bus.b.ready),
+                      self.bus.b.id.eq(tx_sdram_if.bus.b.id),
+                      self.bus.b.resp.eq(tx_sdram_if.bus.b.resp),
+                      self.bus.b.valid.eq(tx_sdram_if.bus.b.valid)]
+        # connect bus.w with tx.w
+        # no worries about w.valid and slave sel here, only tx will be written to
+        self.comb += [tx_sdram_if.bus.w.id.eq(self.bus.w.id),
+                      tx_sdram_if.bus.w.data.eq(self.bus.w.data),
+                      tx_sdram_if.bus.w.strb.eq(self.bus.w.strb),
+                      tx_sdram_if.bus.w.last.eq(self.bus.w.last),
+                      tx_sdram_if.bus.w.valid.eq(self.bus.w.valid),
+                      self.bus.w.ready.eq(tx_sdram_if.bus.w.ready)]
+        # connect bus.r with rx.r and tx.r w/o data
+        self.comb += [self.bus.r.id.eq(rx_sdram_if.bus.r.id | tx_sdram_if.bus.r.id),
+                #self.bus.r.data.eq(rx_sdram_if.bus.r.data | tx_sdram_if.bus.r.data),
+                self.bus.r.resp.eq(rx_sdram_if.bus.r.resp | tx_sdram_if.bus.r.resp),
+                self.bus.r.last.eq(rx_sdram_if.bus.r.last | tx_sdram_if.bus.r.last),
+                self.bus.r.valid.eq(rx_sdram_if.bus.r.valid | tx_sdram_if.bus.r.valid),
+                rx_sdram_if.bus.r.ready.eq(self.bus.r.ready),
+                tx_sdram_if.bus.r.ready.eq(self.bus.r.ready)]
+        # connect read data after being masked
+        masked = [Replicate(rx_sdram_if.bus.r.valid,
+                            len(self.bus.r.data)
+                            ) & rx_sdram_if.bus.r.data,
+                 Replicate(tx_sdram_if.bus.r.valid,
+                            len(self.bus.r.data)
+                            ) & tx_sdram_if.bus.r.data]
+        self.comb += self.bus.r.data.eq(reduce(or_, masked))
+
+        self.submodules += tx_sdram_if, rx_sdram_if, aw_decoder, ar_decoder
+
+
+@FullMemoryWE()
+class DRTIOAuxControllerBare(_DRTIOAuxControllerBase):
+    # Barebones version of the AuxController. No SRAM, no decoders.
+    # add memories manually from tx and rx in target code.
+    def get_tx_port(self):
+        return self.transmitter.mem.get_port(write_capable=True)
+
+    def get_rx_port(self):
+        return self.receiver.mem.get_port(write_capable=False)
+
+    def get_mem_size(self):
+        return max_packet

src/gateware/kasli_soc.py

@@ -15,11 +15,16 @@ from misoc.integration import cpu_interface
 from artiq.coredevice import jsondesc
 from artiq.gateware import rtio, eem_7series
 from artiq.gateware.rtio.phy import ttl_simple
+from artiq.gateware.rtio.xilinx_clocking import RTIOClockMultiplier
+from artiq.gateware.drtio.transceiver import gtx_7series
+from artiq.gateware.drtio.siphaser import SiPhaser7Series
+from artiq.gateware.drtio.rx_synchronizer import XilinxRXSynchronizer
+from artiq.gateware.drtio import *
 
 import dma
 import analyzer
 import acpki
-
+import drtio_aux_controller
 
 class RTIOCRG(Module, AutoCSR):
     def __init__(self, platform):
@@ -70,7 +75,7 @@ class RTIOCRG(Module, AutoCSR):
             MultiReg(pll_locked, self.pll_locked.status)
         ]
 
-
+        
 eem_iostandard_dict = {
      0: "LVDS_25",
      1: "LVDS_25",
@@ -173,13 +178,287 @@ class GenericStandalone(SoCCore):
 
 
 class GenericMaster(SoCCore):
-    def __init__(self, description, **kwargs):
-        raise NotImplementedError
+    def __init__(self, description, acpki=False):
+        sys_clk_freq = 125e6
+        rtio_clk_freq = 125e6
+
+        self.acpki = acpki
+        self.rustc_cfg = dict()
+
+        platform = kasli_soc.Platform()
+        platform.toolchain.bitstream_commands.extend([
+            "set_property BITSTREAM.GENERAL.COMPRESS True [current_design]",
+        ])
+        ident = self.__class__.__name__
+        if self.acpki:
+            ident = "acpki_" + ident
+        SoCCore.__init__(self, platform=platform, csr_data_width=32, ident=ident)
+
+        platform.add_platform_command("create_clock -name clk_fpga_0 -period 8 [get_pins \"PS7/FCLKCLK[0]\"]")
+        platform.add_platform_command("set_input_jitter clk_fpga_0 0.24")
+
+        data_pads = [platform.request("sfp", i) for i in range(4)]
+
+        self.submodules.drtio_transceiver = gtx_7series.GTX(
+            clock_pads=platform.request("clk125_gtp"),
+            pads=data_pads,
+            sys_clk_freq=sys_clk_freq)
+        self.csr_devices.append("drtio_transceiver")
+
+        self.crg = self.ps7 # HACK for eem_7series to find the clock
+        self.submodules.rtio_crg = RTIOClockMultiplier(rtio_clk_freq)
+        self.csr_devices.append("rtio_crg")
+
+        self.rtio_channels = []
+        has_grabber = any(peripheral["type"] == "grabber" for peripheral in description["peripherals"])
+        if has_grabber:
+            self.grabber_csr_group = []
+        eem_7series.add_peripherals(self, description["peripherals"], iostandard=eem_iostandard)
+        for i in (0, 1):
+            print("USER LED at RTIO channel 0x{:06x}".format(len(self.rtio_channels)))
+            user_led = self.platform.request("user_led", i)
+            phy = ttl_simple.Output(user_led)
+            self.submodules += phy
+            self.rtio_channels.append(rtio.Channel.from_phy(phy))
+        self.config["RTIO_LOG_CHANNEL"] = len(self.rtio_channels)
+        self.rtio_channels.append(rtio.LogChannel())
+
+        self.submodules.rtio_tsc = rtio.TSC("async", glbl_fine_ts_width=3)
+
+        drtio_csr_group = []
+        drtioaux_csr_group = []
+        drtioaux_memory_group = []
+        self.drtio_cri = []
+        for i in range(len(self.drtio_transceiver.channels)):
+            core_name = "drtio" + str(i)
+            coreaux_name = "drtioaux" + str(i)
+            memory_name = "drtioaux" + str(i) + "_mem"
+            drtio_csr_group.append(core_name)
+            drtioaux_csr_group.append(coreaux_name)
+            drtioaux_memory_group.append(memory_name)
+
+            cdr = ClockDomainsRenamer({"rtio_rx": "rtio_rx" + str(i)})
+
+            core = cdr(DRTIOMaster(self.rtio_tsc, self.drtio_transceiver.channels[i]))
+            setattr(self.submodules, core_name, core)
+            self.drtio_cri.append(core.cri)
+            self.csr_devices.append(core_name)
+
+            coreaux = cdr(drtio_aux_controller.DRTIOAuxControllerBare(core.link_layer))
+            setattr(self.submodules, coreaux_name, coreaux)
+            self.csr_devices.append(coreaux_name)
+
+            size = coreaux.get_mem_size()
+            memory_address = self.axi2csr.register_port(coreaux.get_tx_port(), size)
+            self.axi2csr.register_port(coreaux.get_rx_port(), size)
+            self.add_memory_region(memory_name, self.mem_map["csr"] + memory_address, size * 2)
+        self.rustc_cfg["has_drtio"] = None
+        self.rustc_cfg["has_drtio_routing"] = None
+        self.add_csr_group("drtio", drtio_csr_group)
+        self.add_csr_group("drtioaux", drtioaux_csr_group)
+        self.add_memory_group("drtioaux_mem", drtioaux_memory_group)
+
+        self.submodules.rtio_core = rtio.Core(self.rtio_tsc, self.rtio_channels)
+        self.csr_devices.append("rtio_core")
+
+        if self.acpki:
+            self.rustc_cfg["ki_impl"] = "acp"
+            self.submodules.rtio = acpki.KernelInitiator(self.rtio_tsc,
+                                                         bus=self.ps7.s_axi_acp,
+                                                         user=self.ps7.s_axi_acp_user,
+                                                         evento=self.ps7.event.o)
+            self.csr_devices.append("rtio")
+        else:
+            self.rustc_cfg["ki_impl"] = "csr"
+            self.submodules.rtio = rtio.KernelInitiator(self.rtio_tsc, now64=True)
+            self.csr_devices.append("rtio")
+
+        self.submodules.rtio_dma = dma.DMA(self.ps7.s_axi_hp0)
+        self.csr_devices.append("rtio_dma")
+
+        self.submodules.cri_con = rtio.CRIInterconnectShared(
+            [self.rtio.cri, self.rtio_dma.cri],
+            [self.rtio_core.cri] + self.drtio_cri,
+            enable_routing=True)
+        self.csr_devices.append("cri_con")
+
+        self.submodules.rtio_moninj = rtio.MonInj(self.rtio_channels)
+        self.csr_devices.append("rtio_moninj")
+
+        self.submodules.routing_table = rtio.RoutingTableAccess(self.cri_con)
+        self.csr_devices.append("routing_table")
+
+        self.submodules.rtio_analyzer = analyzer.Analyzer(self.rtio_tsc, self.rtio_core.cri,
+                                                          self.ps7.s_axi_hp1)
+        self.csr_devices.append("rtio_analyzer")
+
+        if has_grabber:
+            self.rustc_cfg["has_grabber"] = None
+            self.add_csr_group("grabber", self.grabber_csr_group)
 
 
 class GenericSatellite(SoCCore):
-    def __init__(self, description, **kwargs):
-        raise NotImplementedError
+    def __init__(self, description, acpki=False):
+        sys_clk_freq = 125e6  
+        rtio_clk_freq = 125e6
+
+        self.acpki = acpki
+        self.rustc_cfg = dict()
+
+        platform = kasli_soc.Platform()
+        platform.toolchain.bitstream_commands.extend([
+            "set_property BITSTREAM.GENERAL.COMPRESS True [current_design]",
+        ])
+        ident = self.__class__.__name__
+        if self.acpki:
+            ident = "acpki_" + ident
+        SoCCore.__init__(self, platform=platform, csr_data_width=32, ident=ident)
+
+        platform.add_platform_command("create_clock -name clk_fpga_0 -period 8 [get_pins \"PS7/FCLKCLK[0]\"]")
+        platform.add_platform_command("set_input_jitter clk_fpga_0 0.24")
+
+        self.crg = self.ps7 # HACK for eem_7series to find the clock
+        self.submodules.rtio_crg = RTIOClockMultiplier(rtio_clk_freq)
+        self.csr_devices.append("rtio_crg")
+        
+        data_pads = [platform.request("sfp", i) for i in range(4)]
+        
+        self.submodules.drtio_transceiver = gtx_7series.GTX(
+            clock_pads=platform.request("clk125_gtp"),  
+            pads=data_pads,
+            sys_clk_freq=sys_clk_freq)
+        self.csr_devices.append("drtio_transceiver")
+
+        self.rtio_channels = []
+        has_grabber = any(peripheral["type"] == "grabber" for peripheral in description["peripherals"])
+        if has_grabber:
+            self.grabber_csr_group = []
+        eem_7series.add_peripherals(self, description["peripherals"], iostandard=eem_iostandard)
+        for i in (0, 1):
+            print("USER LED at RTIO channel 0x{:06x}".format(len(self.rtio_channels)))
+            user_led = self.platform.request("user_led", i)
+            phy = ttl_simple.Output(user_led)
+            self.submodules += phy
+            self.rtio_channels.append(rtio.Channel.from_phy(phy))
+        self.config["RTIO_LOG_CHANNEL"] = len(self.rtio_channels)
+        self.rtio_channels.append(rtio.LogChannel())
+
+        self.submodules.rtio_tsc = rtio.TSC("sync", glbl_fine_ts_width=3)
+
+        drtioaux_csr_group = []
+        drtioaux_memory_group = []
+        drtiorep_csr_group = []
+        self.drtio_cri = []
+        for i in range(len(self.drtio_transceiver.channels)):
+            coreaux_name = "drtioaux" + str(i)
+            memory_name = "drtioaux" + str(i) + "_mem"
+            drtioaux_csr_group.append(coreaux_name)
+            drtioaux_memory_group.append(memory_name)
+
+            cdr = ClockDomainsRenamer({"rtio_rx": "rtio_rx" + str(i)})
+
+            if i == 0:
+                self.submodules.rx_synchronizer = cdr(XilinxRXSynchronizer())
+                core = cdr(DRTIOSatellite(
+                    self.rtio_tsc, self.drtio_transceiver.channels[i],
+                    self.rx_synchronizer))
+                self.submodules.drtiosat = core
+                self.csr_devices.append("drtiosat")
+            else:
+                corerep_name = "drtiorep" + str(i-1)
+                drtiorep_csr_group.append(corerep_name)
+
+                core = cdr(DRTIORepeater(
+                    self.rtio_tsc, self.drtio_transceiver.channels[i]))
+                setattr(self.submodules, corerep_name, core)
+                self.drtio_cri.append(core.cri)
+                self.csr_devices.append(corerep_name)
+
+            coreaux = cdr(drtio_aux_controller.DRTIOAuxControllerBare(core.link_layer))
+            setattr(self.submodules, coreaux_name, coreaux)
+            self.csr_devices.append(coreaux_name)
+
+            mem_size = coreaux.get_mem_size()
+            tx_port = coreaux.get_tx_port()
+            rx_port = coreaux.get_rx_port()
+            memory_address = self.axi2csr.register_port(tx_port, mem_size)
+            # rcv in upper half of the memory, thus added second
+            self.axi2csr.register_port(rx_port, mem_size)
+            # and registered in PS interface
+            # manually, because software refers to rx/tx by halves of entire memory block, not names
+            self.add_memory_region(memory_name, self.mem_map["csr"] + memory_address, mem_size * 2)
+        self.rustc_cfg["has_drtio"] = None
+        self.rustc_cfg["has_drtio_routing"] = None
+        self.add_csr_group("drtioaux", drtioaux_csr_group)
+        self.add_memory_group("drtioaux_mem", drtioaux_memory_group)
+        self.add_csr_group("drtiorep", drtiorep_csr_group)
+
+        if self.acpki:
+            self.rustc_cfg["ki_impl"] = "acp"
+            self.submodules.rtio = acpki.KernelInitiator(self.rtio_tsc,
+                                                         bus=self.ps7.s_axi_acp,
+                                                         user=self.ps7.s_axi_acp_user,
+                                                         evento=self.ps7.event.o)
+            self.csr_devices.append("rtio")
+        else:
+            self.rustc_cfg["ki_impl"] = "csr"
+            self.submodules.rtio = rtio.KernelInitiator(self.rtio_tsc, now64=True)
+            self.csr_devices.append("rtio")
+
+        self.submodules.rtio_dma = dma.DMA(self.ps7.s_axi_hp0)
+        self.csr_devices.append("rtio_dma")
+
+        self.submodules.local_io = SyncRTIO(self.rtio_tsc, self.rtio_channels)
+        self.comb += self.drtiosat.async_errors.eq(self.local_io.async_errors)
+
+        self.submodules.cri_con = rtio.CRIInterconnectShared(
+            [self.drtiosat.cri],
+            [self.local_io.cri] + self.drtio_cri,
+            mode="sync", enable_routing=True)
+        self.csr_devices.append("cri_con")
+
+        self.submodules.routing_table = rtio.RoutingTableAccess(self.cri_con)
+        self.csr_devices.append("routing_table")     
+
+        self.submodules.rtio_moninj = rtio.MonInj(self.rtio_channels)
+        self.csr_devices.append("rtio_moninj")
+
+        rtio_clk_period = 1e9/rtio_clk_freq
+        self.rustc_cfg["rtio_frequency"] = str(rtio_clk_freq/1e6)
+
+        self.submodules.siphaser = SiPhaser7Series(
+            si5324_clkin=platform.request("cdr_clk"),
+            rx_synchronizer=self.rx_synchronizer,
+            ultrascale=False,
+            rtio_clk_freq=self.drtio_transceiver.rtio_clk_freq)
+        platform.add_false_path_constraints(
+            self.crg.cd_sys.clk, self.siphaser.mmcm_freerun_output)
+        self.csr_devices.append("siphaser")
+        self.rustc_cfg["has_si5324"] = None
+        self.rustc_cfg["has_siphaser"] = None
+        self.rustc_cfg["si5324_soft_reset"] = None
+
+        gtx0 = self.drtio_transceiver.gtxs[0]
+        platform.add_period_constraint(gtx0.txoutclk, rtio_clk_period)
+        platform.add_period_constraint(gtx0.rxoutclk, rtio_clk_period)
+        platform.add_false_path_constraints(
+            self.crg.cd_sys.clk,
+            gtx0.txoutclk, gtx0.rxoutclk)
+        for gtx in self.drtio_transceiver.gtxs[1:]:
+            platform.add_period_constraint(gtx.rxoutclk, rtio_clk_period)
+            platform.add_false_path_constraints(
+                self.crg.cd_sys.clk, gtx.rxoutclk)
+
+        if has_grabber:
+            self.rustc_cfg["has_grabber"] = None
+            self.add_csr_group("grabber", self.grabber_csr_group)
+            # no RTIO CRG here
+     
+
+def write_mem_file(soc, filename):
+    with open(filename, "w") as f:
+        f.write(cpu_interface.get_mem_rust(
+            soc.get_memory_regions(), soc.get_memory_groups(), None))
 
 
 def write_csr_file(soc, filename):
@@ -204,6 +483,8 @@ def main():
         help="build Rust interface into the specified file")
     parser.add_argument("-c", default=None,
         help="build Rust compiler configuration into the specified file")
+    parser.add_argument("-m", default=None,
+        help="build Rust memory interface into the specified file")
     parser.add_argument("-g", default=None,
         help="build gateware into the specified directory")
     parser.add_argument("--acpki", default=False, action="store_true",
@@ -230,6 +511,8 @@ def main():
 
     if args.r is not None:
         write_csr_file(soc, args.r)
+    if args.m is not None:
+        write_mem_file(soc, args.m)
     if args.c is not None:
         write_rustc_cfg_file(soc, args.c)
     if args.g is not None:

src/gateware/zc706.py

@@ -11,13 +11,20 @@ from migen_axi.integration.soc_core import SoCCore
 from migen_axi.platforms import zc706
 from misoc.interconnect.csr import *
 from misoc.integration import cpu_interface
+from misoc.cores import gpio
 
 from artiq.gateware import rtio, nist_clock, nist_qc2
 from artiq.gateware.rtio.phy import ttl_simple, ttl_serdes_7series, dds, spi2
+from artiq.gateware.rtio.xilinx_clocking import RTIOClockMultiplier, fix_serdes_timing_path
+from artiq.gateware.drtio.transceiver import gtx_7series
+from artiq.gateware.drtio.siphaser import SiPhaser7Series
+from artiq.gateware.drtio.rx_synchronizer import XilinxRXSynchronizer
+from artiq.gateware.drtio import *
 
 import dma
 import analyzer
 import acpki
+import drtio_aux_controller
 
 
 class RTIOCRG(Module, AutoCSR):
@@ -64,23 +71,45 @@ class RTIOCRG(Module, AutoCSR):
         ]
 
 
+# The NIST backplanes require setting VADJ to 3.3V by reprogramming the power supply.
+# This also changes the I/O standard for some on-board LEDs.
+leds_fmc33 = [
+    ("user_led_33", 0, Pins("Y21"), IOStandard("LVCMOS33")),
+    ("user_led_33", 1, Pins("G2"), IOStandard("LVCMOS15")),
+    ("user_led_33", 2, Pins("W21"), IOStandard("LVCMOS33")),
+    ("user_led_33", 3, Pins("A17"), IOStandard("LVCMOS15")),
+]
+
+# same deal as with LEDs - changed I/O standard.
+si5324_fmc33 = [
+    ("si5324_33", 0,
+        Subsignal("rst_n", Pins("W23"), IOStandard("LVCMOS33")),
+        Subsignal("int", Pins("AJ25"), IOStandard("LVCMOS33"))
+    ),
+]
+
+
+def prepare_zc706_platform(platform):
+    platform.toolchain.bitstream_commands.extend([
+        "set_property BITSTREAM.GENERAL.COMPRESS True [current_design]",
+    ])
+    platform.add_platform_command("create_clock -name clk_fpga_0 -period 8 [get_pins \"PS7/FCLKCLK[0]\"]")
+    platform.add_platform_command("set_input_jitter clk_fpga_0 0.24")
+
+
 class ZC706(SoCCore):
     def __init__(self, acpki=False):
         self.acpki = acpki
         self.rustc_cfg = dict()
 
         platform = zc706.Platform()
-        platform.toolchain.bitstream_commands.extend([
-            "set_property BITSTREAM.GENERAL.COMPRESS True [current_design]",
-        ])
+        prepare_zc706_platform(platform)
+
         ident = self.__class__.__name__
         if self.acpki:
             ident = "acpki_" + ident
         SoCCore.__init__(self, platform=platform, csr_data_width=32, ident=ident)
 
-        platform.add_platform_command("create_clock -name clk_fpga_0 -period 8 [get_pins \"PS7/FCLKCLK[0]\"]")
-        platform.add_platform_command("set_input_jitter clk_fpga_0 0.24")
-
         self.submodules.rtio_crg = RTIOCRG(self.platform, self.ps7.cd_sys.clk)
         self.csr_devices.append("rtio_crg")
         self.rustc_cfg["has_rtio_crg_clock_sel"] = None
@@ -122,10 +151,284 @@ class ZC706(SoCCore):
         self.csr_devices.append("rtio_analyzer")
 
 
-class Simple(ZC706):
-    def __init__(self, **kwargs):
-        ZC706.__init__(self, **kwargs)
+class _MasterBase(SoCCore):
+    def __init__(self, acpki=False):
+        self.acpki = acpki
+        self.rustc_cfg = dict()
+
+        platform = zc706.Platform()
+        prepare_zc706_platform(platform)
+        ident = self.__class__.__name__
+        if self.acpki:
+            ident = "acpki_" + ident
+        SoCCore.__init__(self, platform=platform, csr_data_width=32, ident=ident)
+
+        platform.add_extension(si5324_fmc33)
+
+        self.sys_clk_freq = 125e6
+
+        platform = self.platform
+
+        self.comb += platform.request("sfp_tx_disable_n").eq(1)
+        data_pads = [
+            platform.request("sfp"),
+            platform.request("user_sma_mgt")
+        ]
+
+        # 1000BASE_BX10 Ethernet compatible, 125MHz RTIO clock
+        self.submodules.drtio_transceiver = gtx_7series.GTX(
+            clock_pads=platform.request("si5324_clkout"),
+            pads=data_pads,
+            sys_clk_freq=self.sys_clk_freq)
+        self.csr_devices.append("drtio_transceiver")
+
+        self.submodules.rtio_tsc = rtio.TSC("async", glbl_fine_ts_width=3)
+
+        drtio_csr_group = []
+        drtioaux_csr_group = []
+        drtioaux_memory_group = []
+        self.drtio_cri = []
+        for i in range(len(self.drtio_transceiver.channels)):
+            core_name = "drtio" + str(i)
+            coreaux_name = "drtioaux" + str(i)
+            memory_name = "drtioaux" + str(i) + "_mem"
+            drtio_csr_group.append(core_name)
+            drtioaux_csr_group.append(coreaux_name)
+            drtioaux_memory_group.append(memory_name)
+
+            cdr = ClockDomainsRenamer({"rtio_rx": "rtio_rx" + str(i)})
+
+            core = cdr(DRTIOMaster(
+                self.rtio_tsc, self.drtio_transceiver.channels[i]))
+            setattr(self.submodules, core_name, core)
+            self.drtio_cri.append(core.cri)
+            self.csr_devices.append(core_name)
+
+            coreaux = cdr(drtio_aux_controller.DRTIOAuxControllerBare(core.link_layer))
+            setattr(self.submodules, coreaux_name, coreaux)
+            self.csr_devices.append(coreaux_name)
+
+            mem_size = coreaux.get_mem_size()
+            memory_address = self.axi2csr.register_port(coreaux.get_tx_port(), mem_size)
+            self.axi2csr.register_port(coreaux.get_rx_port(), mem_size)
+            self.add_memory_region(memory_name, self.mem_map["csr"] + memory_address, mem_size * 2)
+        self.rustc_cfg["has_drtio"] = None
+        self.rustc_cfg["has_drtio_routing"] = None
+        self.add_csr_group("drtio", drtio_csr_group)
+        self.add_csr_group("drtioaux", drtioaux_csr_group)
+        self.add_memory_group("drtioaux_mem", drtioaux_memory_group)
+
+        self.rustc_cfg["RTIO_FREQUENCY"] = str(self.drtio_transceiver.rtio_clk_freq/1e6)
+
+        self.submodules.si5324_rst_n = gpio.GPIOOut(platform.request("si5324_33").rst_n)
+        self.csr_devices.append("si5324_rst_n")
+        self.rustc_cfg["has_si5324"] = None
+        self.rustc_cfg["si5324_as_synthesizer"] = None
+
+        rtio_clk_period = 1e9/self.drtio_transceiver.rtio_clk_freq
+        # Constrain TX & RX timing for the first transceiver channel
+        # (First channel acts as master for phase alignment for all channels' TX)
+        gtx0 = self.drtio_transceiver.gtxs[0]
+        platform.add_period_constraint(gtx0.txoutclk, rtio_clk_period)
+        platform.add_period_constraint(gtx0.rxoutclk, rtio_clk_period)
+        platform.add_false_path_constraints(
+            self.ps7.cd_sys.clk,
+            gtx0.txoutclk, gtx0.rxoutclk)
+        # Constrain RX timing for the each transceiver channel
+        # (Each channel performs single-lane phase alignment for RX)
+        for gtx in self.drtio_transceiver.gtxs[1:]:
+            platform.add_period_constraint(gtx.rxoutclk, rtio_clk_period)
+            platform.add_false_path_constraints(
+                self.ps7.cd_sys.clk, gtx0.txoutclk, gtx.rxoutclk)
+
+        self.submodules.rtio_crg = RTIOClockMultiplier(self.sys_clk_freq)
+        self.csr_devices.append("rtio_crg")
+        fix_serdes_timing_path(self.platform)
+
+    def add_rtio(self, rtio_channels):
+        self.submodules.rtio_tsc = rtio.TSC("async", glbl_fine_ts_width=3)
+        self.submodules.rtio_core = rtio.Core(self.rtio_tsc, rtio_channels)
+        self.csr_devices.append("rtio_core")
+
+        if self.acpki:
+            self.rustc_cfg["ki_impl"] = "acp"
+            self.submodules.rtio = acpki.KernelInitiator(self.rtio_tsc,
+                                                         bus=self.ps7.s_axi_acp,
+                                                         user=self.ps7.s_axi_acp_user,
+                                                         evento=self.ps7.event.o)
+            self.csr_devices.append("rtio")
+        else:
+            self.rustc_cfg["ki_impl"] = "csr"
+            self.submodules.rtio = rtio.KernelInitiator(self.rtio_tsc, now64=True)
+            self.csr_devices.append("rtio")
+
+        self.submodules.rtio_dma = dma.DMA(self.ps7.s_axi_hp0)
+        self.csr_devices.append("rtio_dma")
+
+        self.submodules.local_io = SyncRTIO(self.rtio_tsc, rtio_channels)
+        self.submodules.cri_con = rtio.CRIInterconnectShared(
+            [self.rtio.cri, self.rtio_dma.cri],
+            [self.local_io.cri] + self.drtio_cri,
+            mode="sync", enable_routing=True)
+        self.csr_devices.append("cri_con")
+
+        self.submodules.rtio_moninj = rtio.MonInj(rtio_channels)
+        self.csr_devices.append("rtio_moninj")
+
+        self.submodules.rtio_analyzer = analyzer.Analyzer(self.rtio_tsc, self.rtio_core.cri,
+                                                          self.ps7.s_axi_hp1)
+        self.csr_devices.append("rtio_analyzer")
+
+        self.submodules.routing_table = rtio.RoutingTableAccess(self.cri_con)
+        self.csr_devices.append("routing_table")
+
+
+class _SatelliteBase(SoCCore):
+    def __init__(self, acpki=False):
+        self.acpki = acpki
+        self.rustc_cfg = dict()
+
+        platform = zc706.Platform()
+        prepare_zc706_platform(platform)
+        ident = self.__class__.__name__
+        if self.acpki:
+            ident = "acpki_" + ident
+        SoCCore.__init__(self, platform=platform, csr_data_width=32, ident=ident)
+
+        platform.add_extension(si5324_fmc33)
 
+        self.sys_clk_freq = 125e6
+        platform = self.platform
+
+        # SFP
+        self.comb += platform.request("sfp_tx_disable_n").eq(0)
+        data_pads = [
+            platform.request("sfp"),
+            platform.request("user_sma_mgt")
+        ]
+
+        self.submodules.rtio_tsc = rtio.TSC("sync", glbl_fine_ts_width=3)
+
+        # 1000BASE_BX10 Ethernet compatible, 125MHz RTIO clock
+        self.submodules.drtio_transceiver = gtx_7series.GTX(
+            clock_pads=platform.request("si5324_clkout"),
+            pads=data_pads,
+            sys_clk_freq=self.sys_clk_freq)
+        self.csr_devices.append("drtio_transceiver")
+
+        drtioaux_csr_group = []
+        drtioaux_memory_group = []
+        drtiorep_csr_group = []
+        self.drtio_cri = []
+        for i in range(len(self.drtio_transceiver.channels)):
+            coreaux_name = "drtioaux" + str(i)
+            memory_name = "drtioaux" + str(i) + "_mem"
+            drtioaux_csr_group.append(coreaux_name)
+            drtioaux_memory_group.append(memory_name)
+
+            cdr = ClockDomainsRenamer({"rtio_rx": "rtio_rx" + str(i)})
+
+            # Satellite
+            if i == 0:
+                self.submodules.rx_synchronizer = cdr(XilinxRXSynchronizer())
+                core = cdr(DRTIOSatellite(
+                    self.rtio_tsc, self.drtio_transceiver.channels[0], self.rx_synchronizer))
+                self.submodules.drtiosat = core
+                self.csr_devices.append("drtiosat")
+            # Repeaters
+            else:
+                corerep_name = "drtiorep" + str(i-1)
+                drtiorep_csr_group.append(corerep_name)
+                core = cdr(DRTIORepeater(
+                    self.rtio_tsc, self.drtio_transceiver.channels[i]))
+                setattr(self.submodules, corerep_name, core)
+                self.drtio_cri.append(core.cri)
+                self.csr_devices.append(corerep_name)
+
+            coreaux = cdr(drtio_aux_controller.DRTIOAuxControllerBare(core.link_layer))
+            setattr(self.submodules, coreaux_name, coreaux)
+            self.csr_devices.append(coreaux_name)
+
+            mem_size = coreaux.get_mem_size()
+            tx_port = coreaux.get_tx_port()
+            rx_port = coreaux.get_rx_port()
+            memory_address = self.axi2csr.register_port(tx_port, mem_size)
+            # rcv in upper half of the memory, thus added second
+            self.axi2csr.register_port(rx_port, mem_size)
+            # and registered in PS interface
+            # manually, because software refers to rx/tx by halves of entire memory block, not names
+            self.add_memory_region(memory_name, self.mem_map["csr"] + memory_address, mem_size * 2)
+        self.rustc_cfg["has_drtio"] = None
+        self.rustc_cfg["has_drtio_routing"] = None
+        self.add_csr_group("drtioaux", drtioaux_csr_group)
+        self.add_csr_group("drtiorep", drtiorep_csr_group)
+        self.add_memory_group("drtioaux_mem", drtioaux_memory_group)
+
+        self.rustc_cfg["rtio_frequency"] = str(self.drtio_transceiver.rtio_clk_freq/1e6)
+
+        # Si5324 Phaser
+        self.submodules.siphaser = SiPhaser7Series(
+            si5324_clkin=platform.request("si5324_clkin"),
+            rx_synchronizer=self.rx_synchronizer,
+            ultrascale=False,
+            rtio_clk_freq=self.drtio_transceiver.rtio_clk_freq)
+        platform.add_false_path_constraints(
+            self.ps7.cd_sys.clk, self.siphaser.mmcm_freerun_output)
+        self.csr_devices.append("siphaser")
+        self.submodules.si5324_rst_n = gpio.GPIOOut(platform.request("si5324_33").rst_n)
+        self.csr_devices.append("si5324_rst_n")
+        self.rustc_cfg["has_si5324"] = None
+        self.rustc_cfg["has_siphaser"] = None
+
+        rtio_clk_period = 1e9/self.drtio_transceiver.rtio_clk_freq
+        # Constrain TX & RX timing for the first transceiver channel
+        # (First channel acts as master for phase alignment for all channels' TX)
+        gtx0 = self.drtio_transceiver.gtxs[0]
+        platform.add_period_constraint(gtx0.txoutclk, rtio_clk_period)
+        platform.add_period_constraint(gtx0.rxoutclk, rtio_clk_period)
+        platform.add_false_path_constraints(
+            self.ps7.cd_sys.clk,
+            gtx0.txoutclk, gtx0.rxoutclk)
+        # Constrain RX timing for the each transceiver channel
+        # (Each channel performs single-lane phase alignment for RX)
+        for gtx in self.drtio_transceiver.gtxs[1:]:
+            platform.add_period_constraint(gtx.rxoutclk, rtio_clk_period)
+            platform.add_false_path_constraints(
+                self.ps7.cd_sys.clk, gtx.rxoutclk)
+
+        self.submodules.rtio_crg = RTIOClockMultiplier(self.sys_clk_freq)
+        self.csr_devices.append("rtio_crg")
+        fix_serdes_timing_path(self.platform)
+
+    def add_rtio(self, rtio_channels):
+        self.submodules.rtio_moninj = rtio.MonInj(rtio_channels)
+        self.csr_devices.append("rtio_moninj")
+
+        if self.acpki:
+            self.rustc_cfg["ki_impl"] = "acp"
+            self.submodules.rtio = acpki.KernelInitiator(self.rtio_tsc,
+                                                         bus=self.ps7.s_axi_acp,
+                                                         user=self.ps7.s_axi_acp_user,
+                                                         evento=self.ps7.event.o)
+            self.csr_devices.append("rtio")
+        else:
+            self.rustc_cfg["ki_impl"] = "csr"
+            self.submodules.rtio = rtio.KernelInitiator(self.rtio_tsc, now64=True)
+            self.csr_devices.append("rtio")
+
+        self.submodules.local_io = SyncRTIO(self.rtio_tsc, rtio_channels)
+        self.submodules.cri_con = rtio.CRIInterconnectShared(
+            [self.drtiosat.cri],
+            [self.local_io.cri] + self.drtio_cri,
+            mode="sync", enable_routing=True)
+        self.csr_devices.append("cri_con")
+
+        self.submodules.routing_table = rtio.RoutingTableAccess(self.cri_con)
+        self.csr_devices.append("routing_table")
+
+
+class _Simple_RTIO:
+    def __init__(self):
         platform = self.platform
 
         rtio_channels = []
@@ -170,13 +473,11 @@ _sdcard_spi_33 = [
     )
 ]
 
-class NIST_CLOCK(ZC706):
+class _NIST_CLOCK_RTIO:
     """
     NIST clock hardware, with old backplane and 11 DDS channels
     """
-    def __init__(self, **kwargs):
-        ZC706.__init__(self, **kwargs)
-
+    def __init__(self):
         platform = self.platform
         platform.add_extension(nist_clock.fmc_adapter_io)
         platform.add_extension(leds_fmc33)
@@ -245,14 +546,12 @@ class NIST_CLOCK(ZC706):
         self.add_rtio(rtio_channels)
 
 
-class NIST_QC2(ZC706):
+class _NIST_QC2_RTIO:
     """
     NIST QC2 hardware, as used in Quantum I and Quantum II, with new backplane
     and 24 DDS channels.  Two backplanes are used.
     """
-    def __init__(self, **kwargs):
-        ZC706.__init__(self, **kwargs)
-
+    def __init__(self):
         platform = self.platform
         platform.add_extension(nist_qc2.fmc_adapter_io)
         platform.add_extension(leds_fmc33)
@@ -309,7 +608,56 @@ class NIST_QC2(ZC706):
         self.add_rtio(rtio_channels)
 
 
-VARIANTS = {cls.__name__.lower(): cls for cls in [Simple, NIST_CLOCK, NIST_QC2]}
+class Simple(ZC706, _Simple_RTIO):
+    def __init__(self, acpki):
+        ZC706.__init__(self, acpki)
+        _Simple_RTIO.__init__(self)
+
+class Master(_MasterBase, _Simple_RTIO):
+    def __init__(self, acpki):
+        _MasterBase.__init__(self, acpki)
+        _Simple_RTIO.__init__(self)
+
+class Satellite(_SatelliteBase, _Simple_RTIO):
+    def __init__(self, acpki):
+        _SatelliteBase.__init__(self, acpki)
+        _Simple_RTIO.__init__(self)
+
+class NIST_CLOCK(ZC706, _NIST_CLOCK_RTIO):
+    def __init__(self, acpki):
+        ZC706.__init__(self, acpki)
+        _NIST_CLOCK_RTIO.__init__(self)
+
+class NIST_CLOCK_Master(_MasterBase, _NIST_CLOCK_RTIO):
+    def __init__(self, acpki):
+        _MasterBase.__init__(self, acpki)
+
+        _NIST_CLOCK_RTIO.__init__(self)
+
+class NIST_CLOCK_Satellite(_SatelliteBase, _NIST_CLOCK_RTIO):
+    def __init__(self, acpki):
+        _SatelliteBase.__init__(self, acpki)
+        _NIST_CLOCK_RTIO.__init__(self)
+
+class NIST_QC2(ZC706, _NIST_QC2_RTIO):
+    def __init__(self, acpki):
+        ZC706.__init__(self, acpki)
+        _NIST_QC2_RTIO.__init__(self)
+
+class NIST_QC2_Master(_MasterBase, _NIST_QC2_RTIO):
+    def __init__(self, acpki):
+        _MasterBase.__init__(self, acpki)
+        _NIST_QC2_RTIO.__init__(self)
+
+class NIST_QC2_Satellite(_SatelliteBase, _NIST_QC2_RTIO):
+    def __init__(self, acpki):
+        _SatelliteBase.__init__(self, acpki)
+        _NIST_QC2_RTIO.__init__(self)
+
+
+VARIANTS = {cls.__name__.lower(): cls for cls in [Simple, Master, Satellite, 
+                                                  NIST_CLOCK, NIST_CLOCK_Master, NIST_CLOCK_Satellite,
+                                                  NIST_QC2, NIST_QC2_Master, NIST_QC2_Satellite]}
 
 
 def write_csr_file(soc, filename):
@@ -317,6 +665,11 @@ def write_csr_file(soc, filename):
         f.write(cpu_interface.get_csr_rust(
             soc.get_csr_regions(), soc.get_csr_groups(), soc.get_constants()))
 
+def write_mem_file(soc, filename):
+    with open(filename, "w") as f:
+        f.write(cpu_interface.get_mem_rust(
+            soc.get_memory_regions(), soc.get_memory_groups(), None))
+
 
 def write_rustc_cfg_file(soc, filename):
     with open(filename, "w") as f:
@@ -332,6 +685,8 @@ def main():
         description="ARTIQ port to the ZC706 Zynq development kit")
     parser.add_argument("-r", default=None,
         help="build Rust interface into the specified file")
+    parser.add_argument("-m", default=None,
+        help="build Rust memory interface into the specified file")
     parser.add_argument("-c", default=None,
         help="build Rust compiler configuration into the specified file")
     parser.add_argument("-g", default=None,
@@ -356,11 +711,12 @@ def main():
 
     if args.r is not None:
         write_csr_file(soc, args.r)
+    if args.m is not None:
+        write_mem_file(soc, args.m)
     if args.c is not None:
         write_rustc_cfg_file(soc, args.c)
     if args.g is not None:
         soc.build(build_dir=args.g)
 
-
 if __name__ == "__main__":
     main()

src/libboard_artiq/Cargo.toml

@@ -0,0 +1,31 @@
+[package]
+name = "libboard_artiq"
+version = "0.0.0"
+authors = ["M-Labs"]
+edition = "2018"
+
+[lib]
+name = "libboard_artiq"
+
+[features]
+target_zc706 = []
+target_kasli_soc = []
+
+[build-dependencies]
+build_zynq = { path = "../libbuild_zynq" }
+
+[dependencies]
+log = "0.4"
+log_buffer = { version = "1.2" }
+crc = { version = "1.7", default-features = false }
+core_io = { version = "0.1", features = ["collections"] }
+embedded-hal = "0.2"
+nb = "1.0"
+void = { version = "1", default-features = false }
+
+io = { path = "../libio", features = ["byteorder"] }
+libboard_zynq = { git = "https://git.m-labs.hk/M-Labs/zynq-rs.git"}
+libregister = { git = "https://git.m-labs.hk/M-Labs/zynq-rs.git" }
+libconfig = { git = "https://git.m-labs.hk/M-Labs/zynq-rs.git"}
+libcortex_a9 = { git = "https://git.m-labs.hk/M-Labs/zynq-rs.git" }
+libasync = { git = "https://git.m-labs.hk/M-Labs/zynq-rs.git" }

src/libboard_artiq/build.rs

@@ -0,0 +1,5 @@
+extern crate build_zynq;
+
+fn main() {
+    build_zynq::cfg();
+}

src/libboard_artiq/src/drtio_routing.rs

@@ -0,0 +1,109 @@
+use libconfig::Config;
+#[cfg(has_drtio_routing)]
+use crate::pl::csr;
+use core::fmt;
+
+use log::{warn, info};
+
+#[cfg(has_drtio_routing)]
+pub const DEST_COUNT: usize = 256;
+#[cfg(not(has_drtio_routing))]
+pub const DEST_COUNT: usize = 0;
+pub const MAX_HOPS: usize = 32;
+pub const INVALID_HOP: u8 = 0xff;
+
+pub struct RoutingTable(pub [[u8; MAX_HOPS]; DEST_COUNT]);
+
+impl RoutingTable {
+    // default routing table is for star topology with no repeaters
+    pub fn default_master(default_n_links: usize) -> RoutingTable {
+        let mut ret = RoutingTable([[INVALID_HOP; MAX_HOPS]; DEST_COUNT]);
+        let n_entries = default_n_links + 1;  // include local RTIO
+        for i in 0..n_entries {
+            ret.0[i][0] = i as u8;
+        }
+        for i in 1..n_entries {
+            ret.0[i][1] = 0x00;
+        }
+        ret
+    }
+
+    // use this by default on satellite, as they receive
+    // the routing table from the master
+    pub fn default_empty() -> RoutingTable {
+        RoutingTable([[INVALID_HOP; MAX_HOPS]; DEST_COUNT])
+    }
+}
+
+impl fmt::Display for RoutingTable {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        write!(f, "RoutingTable {{")?;
+        for i in 0..DEST_COUNT {
+            if self.0[i][0] != INVALID_HOP {
+                write!(f, " {}:", i)?;
+                for j in 0..MAX_HOPS {
+                    if self.0[i][j] == INVALID_HOP {
+                        break;
+                    }
+                    write!(f, " {}", self.0[i][j])?;
+                }
+                write!(f, ";")?;
+            }
+        }
+        write!(f, " }}")?;
+        Ok(())
+    }
+}
+
+pub fn config_routing_table(default_n_links: usize, cfg: &Config) -> RoutingTable {
+    let mut ret = RoutingTable::default_master(default_n_links);
+    if let Ok(data) = cfg.read("routing_table") {
+        if data.len() == DEST_COUNT*MAX_HOPS
+        {
+            for i in 0..DEST_COUNT {
+                for j in 0..MAX_HOPS {
+                    ret.0[i][j] = data[i*MAX_HOPS+j];
+                }
+            }
+        }
+        else {
+            warn!("length of the routing table is incorrect, using default");
+        }
+    }
+    else {
+        warn!("could not read routing table from configuration, using default");
+    }
+    info!("routing table: {}", ret);
+    ret
+}
+
+#[cfg(has_drtio_routing)]
+pub fn interconnect_enable(routing_table: &RoutingTable, rank: u8, destination: u8) {
+    let hop = routing_table.0[destination as usize][rank as usize];
+    unsafe {
+        csr::routing_table::destination_write(destination);
+        csr::routing_table::hop_write(hop);
+    }
+}
+
+#[cfg(has_drtio_routing)]
+pub fn interconnect_disable(destination: u8) {
+    unsafe {
+        csr::routing_table::destination_write(destination);
+        csr::routing_table::hop_write(INVALID_HOP);
+    }
+}
+
+#[cfg(has_drtio_routing)]
+pub fn interconnect_enable_all(routing_table: &RoutingTable, rank: u8) {
+    for i in 0..DEST_COUNT {
+        interconnect_enable(routing_table, rank, i as u8);
+    }
+}
+
+#[cfg(has_drtio_routing)]
+pub fn interconnect_disable_all() {
+    for i in 0..DEST_COUNT {
+        interconnect_disable(i as u8);
+    }
+}

src/libboard_artiq/src/drtioaux.rs

@@ -0,0 +1,174 @@
+use crc;
+
+use core_io::{ErrorKind as IoErrorKind, Error as IoError};
+
+use io::{proto::ProtoRead, proto::ProtoWrite, Cursor};
+use libboard_zynq::{timer::GlobalTimer, time::Milliseconds};
+use crate::mem::mem::DRTIOAUX_MEM;
+use crate::pl::csr::DRTIOAUX;
+use crate::drtioaux_proto::Error as ProtocolError;
+
+pub use crate::drtioaux_proto::Packet;
+
+#[derive(Debug)]
+pub enum Error {
+    GatewareError,
+    CorruptedPacket,
+
+    LinkDown,
+    TimedOut,
+    UnexpectedReply,
+
+    RoutingError,
+
+    Protocol(ProtocolError)
+}
+
+impl From<ProtocolError> for Error {
+    fn from(value: ProtocolError) -> Error {
+        Error::Protocol(value)
+    }
+}
+
+impl From<IoError> for Error {
+    fn from(value: IoError) -> Error {
+        Error::Protocol(ProtocolError::Io(value))
+    }
+}
+
+pub fn reset(linkno: u8) {
+    let linkno = linkno as usize;
+    unsafe {
+        // clear buffer first to limit race window with buffer overflow
+        // error. We assume the CPU is fast enough so that no two packets
+        // will be received between the buffer and the error flag are cleared.
+        (DRTIOAUX[linkno].aux_rx_present_write)(1);
+        (DRTIOAUX[linkno].aux_rx_error_write)(1);
+    }
+}
+
+pub fn has_rx_error(linkno: u8) -> bool {
+    let linkno = linkno as usize;
+    unsafe {
+        let error = (DRTIOAUX[linkno].aux_rx_error_read)() != 0;
+        if error {
+            (DRTIOAUX[linkno].aux_rx_error_write)(1)
+        }
+        error
+    }
+}
+
+pub fn copy_with_swap(src: *mut u8, dst: *mut u8, len: isize) {
+    // for some reason, everything except checksum arrives
+    // with byte order swapped. and it must be sent as such too.
+    unsafe {
+        for i in (0..(len-4)).step_by(4) {
+            *dst.offset(i) = *src.offset(i+3);
+            *dst.offset(i+1) = *src.offset(i+2);
+            *dst.offset(i+2) = *src.offset(i+1);
+            *dst.offset(i+3) = *src.offset(i);
+        }
+        // checksum untouched
+        // unrolled for performance
+        *dst.offset(len-4) = *src.offset(len-4);
+        *dst.offset(len-3) = *src.offset(len-3);
+        *dst.offset(len-2) = *src.offset(len-2);
+        *dst.offset(len-1) = *src.offset(len-1);
+    }
+}
+
+fn receive<F, T>(linkno: u8, f: F) -> Result<Option<T>, Error>
+    where F: FnOnce(&[u8]) -> Result<T, Error>
+{
+    let linkidx = linkno as usize;
+    unsafe {
+        if (DRTIOAUX[linkidx].aux_rx_present_read)() == 1 {
+            let ptr = (DRTIOAUX_MEM[linkidx].base + DRTIOAUX_MEM[linkidx].size / 2) as *mut u8;
+            let len = (DRTIOAUX[linkidx].aux_rx_length_read)() as usize;
+            // work buffer, as byte order will need to be swapped, cannot be in place
+            let mut buf: [u8; 1024] = [0; 1024];
+            copy_with_swap(ptr, buf.as_mut_ptr(), len as isize);
+            let result = f(&buf[0..len]);
+            (DRTIOAUX[linkidx].aux_rx_present_write)(1);
+            Ok(Some(result?))
+        } else {
+            Ok(None)
+        }
+    }
+}
+
+pub fn recv(linkno: u8) -> Result<Option<Packet>, Error> {
+    if has_rx_error(linkno) {
+        return Err(Error::GatewareError)
+    }
+
+    receive(linkno, |buffer| {
+        if buffer.len() < 8 {
+            return Err(IoError::new(IoErrorKind::UnexpectedEof, "Unexpected end").into())
+        }
+
+        let mut reader = Cursor::new(buffer);
+
+        let checksum_at = buffer.len() - 4;
+        let checksum = crc::crc32::checksum_ieee(&reader.get_ref()[0..checksum_at]);
+        reader.set_position(checksum_at);
+        if reader.read_u32()? != checksum {
+            return Err(Error::CorruptedPacket)
+        }
+        reader.set_position(0);
+
+        Ok(Packet::read_from(&mut reader)?)
+    })
+}
+
+pub fn recv_timeout(linkno: u8, timeout_ms: Option<u64>,
+    timer: GlobalTimer) -> Result<Packet, Error> 
+{
+    let timeout_ms = Milliseconds(timeout_ms.unwrap_or(10));
+    let limit = timer.get_time() + timeout_ms;
+    while timer.get_time() < limit {
+        match recv(linkno)? {
+            None => (),
+            Some(packet) => return Ok(packet),
+        }
+    }
+    Err(Error::TimedOut)
+}
+
+fn transmit<F>(linkno: u8, f: F) -> Result<(), Error>
+    where F: FnOnce(&mut [u8]) -> Result<usize, Error>
+{
+    let linkno = linkno as usize;
+    unsafe {
+        while (DRTIOAUX[linkno].aux_tx_read)() != 0 {}
+        let ptr = DRTIOAUX_MEM[linkno].base as *mut u8;
+        let len = DRTIOAUX_MEM[linkno].size / 2;
+        // work buffer, works with unaligned mem access
+        let mut buf: [u8; 1024] = [0; 1024]; 
+        let len = f(&mut buf[0..len])?;
+        copy_with_swap(buf.as_mut_ptr(), ptr, len as isize);
+        (DRTIOAUX[linkno].aux_tx_length_write)(len as u16);
+        (DRTIOAUX[linkno].aux_tx_write)(1);
+        Ok(())
+    }
+}
+
+pub fn send(linkno: u8, packet: &Packet) -> Result<(), Error> {
+    transmit(linkno, |buffer| {
+        let mut writer = Cursor::new(buffer);
+
+        packet.write_to(&mut writer)?;
+        
+        let padding = 4 - (writer.position() % 4);
+        if padding != 4 {
+            for _ in 0..padding {
+                writer.write_u8(0)?;
+            }
+        }
+
+        let checksum = crc::crc32::checksum_ieee(&writer.get_ref()[0..writer.position()]);
+        writer.write_u32(checksum)?;
+
+        Ok(writer.position())
+    })
+}

src/libboard_artiq/src/drtioaux_async.rs

@@ -0,0 +1,139 @@
+use crc;
+
+use core_io::{ErrorKind as IoErrorKind, Error as IoError};
+use void::Void;
+use nb;
+
+use libboard_zynq::{timer::GlobalTimer, time::Milliseconds};
+use libasync::{task, block_async};
+
+use io::{proto::ProtoRead, proto::ProtoWrite, Cursor};
+use crate::mem::mem::DRTIOAUX_MEM;
+use crate::pl::csr::DRTIOAUX;
+use crate::drtioaux::{Error, has_rx_error, copy_with_swap};
+
+pub use crate::drtioaux_proto::Packet;
+
+pub async fn reset(linkno: u8) {
+    let linkno = linkno as usize;
+    unsafe {
+        // clear buffer first to limit race window with buffer overflow
+        // error. We assume the CPU is fast enough so that no two packets
+        // will be received between the buffer and the error flag are cleared.
+        (DRTIOAUX[linkno].aux_rx_present_write)(1);
+        (DRTIOAUX[linkno].aux_rx_error_write)(1);
+    }
+}
+
+fn tx_ready(linkno: usize) -> nb::Result<(), Void> {
+    unsafe {
+        if (DRTIOAUX[linkno].aux_tx_read)() != 0 {
+            Err(nb::Error::WouldBlock)
+        }
+        else {
+            Ok(())
+        }
+    }
+}
+
+async fn receive<F, T>(linkno: u8, f: F) -> Result<Option<T>, Error>
+    where F: FnOnce(&[u8]) -> Result<T, Error>
+{
+    let linkidx = linkno as usize;
+    unsafe {
+        if (DRTIOAUX[linkidx].aux_rx_present_read)() == 1 {
+            let ptr = (DRTIOAUX_MEM[linkidx].base + DRTIOAUX_MEM[linkidx].size / 2) as *mut u8;
+            let len = (DRTIOAUX[linkidx].aux_rx_length_read)() as usize;
+            // work buffer, as byte order will need to be swapped, cannot be in place
+            let mut buf: [u8; 1024] = [0; 1024];