runtime: cargo fmt (NFC)

Co-authored-by: abdul124 <ar@m-labs.hk>
Co-committed-by: abdul124 <ar@m-labs.hk>

flake.lock

@@ -3,19 +3,19 @@
     "artiq": {
       "inputs": {
         "artiq-comtools": "artiq-comtools",
-        "mozilla-overlay": "mozilla-overlay",
         "nixpkgs": "nixpkgs",
+        "rust-overlay": "rust-overlay",
         "sipyco": "sipyco",
         "src-migen": "src-migen",
         "src-misoc": "src-misoc",
         "src-pythonparser": "src-pythonparser"
       },
       "locked": {
-        "lastModified": 1717638354,
+        "lastModified": 1724411572,
-        "narHash": "sha256-eyI8OsOrn/j8ChbCpyFpS5VXBW8xSNGGIboFGQj/d4I=",
+        "narHash": "sha256-33vj/pJ9iaVvaFP8uuBKMSQPN20mRlCbeBkTCNc9WB4=",
         "ref": "refs/heads/master",
-        "rev": "ebc1e3fb767d6c0eac6eac20c3afeaba2ab70d1a",
+        "rev": "352cf907ee67f7db5478fe23217cd5fcb7334617",
-        "revCount": 8833,
+        "revCount": 8996,
         "type": "git",
         "url": "https://github.com/m-labs/artiq.git"
       },
@@ -37,11 +37,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1717637438,
+        "lastModified": 1720768567,
-        "narHash": "sha256-BXFidNm3Em8iChPGu1L0s2bY+f2yQ0VVid4MuOoTehw=",
+        "narHash": "sha256-3VoK7o5MtHtbHLrc6Pv+eQWFtaz5Gd/YWyV5TD3c5Ss=",
         "owner": "m-labs",
         "repo": "artiq-comtools",
-        "rev": "78d27026efe76a13f7b4698a554f55811369ec4d",
+        "rev": "f93570d8f2ed5a3cfb3e1c16ab00f2540551e994",
         "type": "github"
       },
       "original": {
@@ -100,34 +100,18 @@
         "type": "github"
       }
     },
-    "mozilla-overlay_3": {
-      "flake": false,
-      "locked": {
-        "lastModified": 1704373101,
-        "narHash": "sha256-+gi59LRWRQmwROrmE1E2b3mtocwueCQqZ60CwLG+gbg=",
-        "owner": "mozilla",
-        "repo": "nixpkgs-mozilla",
-        "rev": "9b11a87c0cc54e308fa83aac5b4ee1816d5418a2",
-        "type": "github"
-      },
-      "original": {
-        "owner": "mozilla",
-        "repo": "nixpkgs-mozilla",
-        "type": "github"
-      }
-    },
     "nixpkgs": {
       "locked": {
-        "lastModified": 1717281328,
+        "lastModified": 1723362943,
-        "narHash": "sha256-evZPzpf59oNcDUXxh2GHcxHkTEG4fjae2ytWP85jXRo=",
+        "narHash": "sha256-dFZRVSgmJkyM0bkPpaYRtG/kRMRTorUIDj8BxoOt1T4=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "b3b2b28c1daa04fe2ae47c21bb76fd226eac4ca1",
+        "rev": "a58bc8ad779655e790115244571758e8de055e3d",
         "type": "github"
       },
       "original": {
         "owner": "NixOS",
-        "ref": "nixos-24.05",
+        "ref": "nixos-unstable",
         "repo": "nixpkgs",
         "type": "github"
       }
@@ -135,10 +119,32 @@
     "root": {
       "inputs": {
         "artiq": "artiq",
-        "mozilla-overlay": "mozilla-overlay_2",
+        "mozilla-overlay": "mozilla-overlay",
         "zynq-rs": "zynq-rs"
       }
     },
+    "rust-overlay": {
+      "inputs": {
+        "nixpkgs": [
+          "artiq",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1719454714,
+        "narHash": "sha256-MojqG0lyUINkEk0b3kM2drsU5vyaF8DFZe/FAlZVOGs=",
+        "owner": "oxalica",
+        "repo": "rust-overlay",
+        "rev": "d1c527659cf076ecc4b96a91c702d080b213801e",
+        "type": "github"
+      },
+      "original": {
+        "owner": "oxalica",
+        "ref": "snapshot/2024-08-01",
+        "repo": "rust-overlay",
+        "type": "github"
+      }
+    },
     "sipyco": {
       "inputs": {
         "nixpkgs": [
@@ -163,11 +169,11 @@
     "src-migen": {
       "flake": false,
       "locked": {
-        "lastModified": 1715484909,
+        "lastModified": 1721561053,
-        "narHash": "sha256-4DCHBUBfc/VA+7NW2Hr0+JP4NnKPru2uVJyZjCCk0Ws=",
+        "narHash": "sha256-z3LRhNmKZrjr6rFD0yxtccSa/SWvFIYmb+G/D5d2Jd8=",
         "owner": "m-labs",
         "repo": "migen",
-        "rev": "4790bb577681a8c3a8d226bc196a4e5deb39e4df",
+        "rev": "9279e8623f8433bc4f23ac51e5e2331bfe544417",
         "type": "github"
       },
       "original": {
@@ -227,18 +233,18 @@
     },
     "zynq-rs": {
       "inputs": {
-        "mozilla-overlay": "mozilla-overlay_3",
+        "mozilla-overlay": "mozilla-overlay_2",
         "nixpkgs": [
           "artiq",
           "nixpkgs"
         ]
       },
       "locked": {
-        "lastModified": 1716889070,
+        "lastModified": 1720537402,
-        "narHash": "sha256-w+M5NfukmcMTt73+u6Cmltjn4qpQH8bcoTGskB2IzBE=",
+        "narHash": "sha256-ybvaQ48SVBqYVqgYmGUdefGZkni7PJ90qYQPHnFOwDs=",
         "ref": "refs/heads/master",
-        "rev": "51b8111e799ebe90ca231ae4d02f84ede32632d5",
+        "rev": "b2b3e5c933cbc4b7cb14adde480d7561a3ae71ee",
-        "revCount": 646,
+        "revCount": 648,
         "type": "git",
         "url": "https://git.m-labs.hk/m-labs/zynq-rs"
       },

flake.nix

@@ -18,11 +18,11 @@
 
     fastnumbers = pkgs.python3Packages.buildPythonPackage rec {
       pname = "fastnumbers";
-      version = "2.2.1";
+      version = "5.1.0";
 
       src = pkgs.python3Packages.fetchPypi {
         inherit pname version;
-        sha256 = "0j15i54p7nri6hkzn1wal9pxri4pgql01wgjccig6ar0v5jjbvsy";
+        sha256 = "sha256-4JLTP4uVwxcaL7NOV57+DFSwKQ3X+W/6onYkN2AdkKc=";
       };
     };
 
@@ -126,6 +126,7 @@
           lockFile = src/Cargo.lock;
           outputHashes = {
               "tar-no-std-0.1.8" = "sha256-xm17108v4smXOqxdLvHl9CxTCJslmeogjm4Y87IXFuM=";
+              "nalgebra-0.32.6" = "sha256-L/YudkVOtfGYoNQKBD7LMk/sMYgRDzPDdpGL5rO7G2I=";
             };
         };
 

src/Cargo.lock

@@ -2,6 +2,15 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "approx"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cab112f0a86d568ea0e627cc1d6be74a1e9cd55214684db5561995f6dad897c6"
+dependencies = [
+ "num-traits",
+]
+
 [[package]]
 name = "arrayvec"
 version = "0.7.4"
@@ -246,6 +255,7 @@ dependencies = [
  "libsupport_zynq",
  "log",
  "log_buffer",
+ "nalgebra",
  "nb 0.1.3",
  "unwind",
  "vcell",
@@ -382,6 +392,19 @@ version = "0.7.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c75de51135344a4f8ed3cfe2720dc27736f7711989703a0b43aadf3753c55577"
 
+[[package]]
+name = "nalgebra"
+version = "0.32.6"
+source = "git+https://git.m-labs.hk/M-Labs/nalgebra.git?rev=dd00f9b#dd00f9b46046e0b931d1b470166db02fd29591be"
+dependencies = [
+ "approx",
+ "num-complex",
+ "num-rational",
+ "num-traits",
+ "simba",
+ "typenum",
+]
+
 [[package]]
 name = "nb"
 version = "0.1.3"
@@ -397,6 +420,15 @@ version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "546c37ac5d9e56f55e73b677106873d9d9f5190605e41a856503623648488cae"
 
+[[package]]
+name = "num-complex"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "26873667bbbb7c5182d4a37c1add32cdf09f841af72da53318fdb81543c15085"
+dependencies = [
+ "num-traits",
+]
+
 [[package]]
 name = "num-derive"
 version = "0.3.3"
@@ -408,6 +440,26 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "num-integer"
+version = "0.1.46"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7969661fd2958a5cb096e56c8e1ad0444ac2bbcd0061bd28660485a44879858f"
+dependencies = [
+ "num-traits",
+]
+
+[[package]]
+name = "num-rational"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d41702bd167c2df5520b384281bc111a4b5efcf7fbc4c9c222c815b07e0a6a6a"
+dependencies = [
+ "autocfg",
+ "num-integer",
+ "num-traits",
+]
+
 [[package]]
 name = "num-traits"
 version = "0.2.15"
@@ -415,8 +467,15 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "578ede34cf02f8924ab9447f50c28075b4d3e5b269972345e7e0372b38c6cdcd"
 dependencies = [
  "autocfg",
+ "libm",
 ]
 
+[[package]]
+name = "paste"
+version = "1.0.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "57c0d7b74b563b49d38dae00a0c37d4d6de9b432382b2892f0574ddcae73fd0a"
+
 [[package]]
 name = "pin-project-lite"
 version = "0.2.9"
@@ -523,6 +582,18 @@ version = "0.1.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d4f410fedcf71af0345d7607d246e7ad15faaadd49d240ee3b24e5dc21a820ac"
 
+[[package]]
+name = "simba"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "50582927ed6f77e4ac020c057f37a268fc6aebc29225050365aacbb9deeeddc4"
+dependencies = [
+ "approx",
+ "num-complex",
+ "num-traits",
+ "paste",
+]
+
 [[package]]
 name = "smoltcp"
 version = "0.7.5"
@@ -555,6 +626,12 @@ dependencies = [
  "log",
 ]
 
+[[package]]
+name = "typenum"
+version = "1.17.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42ff0bf0c66b8238c6f3b578df37d0b7848e55df8577b3f74f92a69acceeb825"
+
 [[package]]
 name = "unicode-ident"
 version = "1.0.5"

src/gateware/kasli_soc.py

@@ -560,7 +560,10 @@ class GenericSatellite(SoCCore):
         self.submodules.local_io = SyncRTIO(
             self.rtio_tsc, self.rtio_channels, lane_count=description["sed_lanes"]
         )
-        self.comb += self.drtiosat.async_errors.eq(self.local_io.async_errors)
+        self.comb += [
+            self.drtiosat.async_errors.eq(self.local_io.async_errors),
+            self.local_io.sed_spread_enable.eq(self.drtiosat.sed_spread_enable.storage)
+        ]
 
         self.submodules.cri_con = rtio.CRIInterconnectShared(
             [self.drtiosat.cri, self.rtio_dma.cri, self.rtio.cri],

src/gateware/zc706.py

@@ -487,6 +487,10 @@ class _SatelliteBase(SoCCore):
         self.csr_devices.append("rtio_dma")
 
         self.submodules.local_io = SyncRTIO(self.rtio_tsc, rtio_channels)
+        self.comb += [
+            self.drtiosat.async_errors.eq(self.local_io.async_errors),
+            self.local_io.sed_spread_enable.eq(self.drtiosat.sed_spread_enable.storage)
+        ]
         self.submodules.cri_con = rtio.CRIInterconnectShared(
             [self.drtiosat.cri, self.rtio_dma.cri, self.rtio.cri],
             [self.local_io.cri] + self.drtio_cri,

src/libboard_artiq/src/drtioaux_proto.rs

@@ -267,12 +267,14 @@ pub enum Packet {
         exception_src: u8,
     },
     SubkernelExceptionRequest {
+        source: u8,
         destination: u8,
     },
     SubkernelException {
+        destination: u8,
         last: bool,
         length: u16,
-        data: [u8; SAT_PAYLOAD_MAX_SIZE],
+        data: [u8; MASTER_PAYLOAD_MAX_SIZE],
     },
     SubkernelMessage {
         source: u8,
@@ -524,14 +526,17 @@ impl Packet {
                 exception_src: reader.read_u8()?,
             },
             0xc9 => Packet::SubkernelExceptionRequest {
+                source: reader.read_u8()?,
                 destination: reader.read_u8()?,
             },
             0xca => {
+                let destination = reader.read_u8()?;
                 let last = reader.read_bool()?;
                 let length = reader.read_u16()?;
-                let mut data: [u8; SAT_PAYLOAD_MAX_SIZE] = [0; SAT_PAYLOAD_MAX_SIZE];
+                let mut data: [u8; MASTER_PAYLOAD_MAX_SIZE] = [0; MASTER_PAYLOAD_MAX_SIZE];
                 reader.read_exact(&mut data[0..length as usize])?;
                 Packet::SubkernelException {
+                    destination: destination,
                     last: last,
                     length: length,
                     data: data,
@@ -896,12 +901,19 @@ impl Packet {
                 writer.write_bool(with_exception)?;
                 writer.write_u8(exception_src)?;
             }
-            Packet::SubkernelExceptionRequest { destination } => {
+            Packet::SubkernelExceptionRequest { source, destination } => {
                 writer.write_u8(0xc9)?;
+                writer.write_u8(source)?;
                 writer.write_u8(destination)?;
             }
-            Packet::SubkernelException { last, length, data } => {
+            Packet::SubkernelException {
+                destination,
+                last,
+                length,
+                data,
+            } => {
                 writer.write_u8(0xca)?;
+                writer.write_u8(destination)?;
                 writer.write_bool(last)?;
                 writer.write_u16(length)?;
                 writer.write_all(&data[0..length as usize])?;
@@ -943,6 +955,8 @@ impl Packet {
             Packet::SubkernelLoadRunReply { destination, .. } => Some(*destination),
             Packet::SubkernelMessage { destination, .. } => Some(*destination),
             Packet::SubkernelMessageAck { destination } => Some(*destination),
+            Packet::SubkernelExceptionRequest { destination, .. } => Some(*destination),
+            Packet::SubkernelException { destination, .. } => Some(*destination),
             Packet::DmaPlaybackStatus { destination, .. } => Some(*destination),
             Packet::SubkernelFinished { destination, .. } => Some(*destination),
             _ => None,

src/libksupport/Cargo.toml.tpl

@@ -32,3 +32,9 @@ unwind = { path = "../libunwind" }
 libc = { path = "../libc" }
 io = { path = "../libio" }
 libboard_artiq = { path = "../libboard_artiq" }
+
+[dependencies.nalgebra]
+git = "https://git.m-labs.hk/M-Labs/nalgebra.git"
+rev = "dd00f9b"
+default-features = false
+features = ["libm", "alloc"]

src/libksupport/src/eh_artiq.rs

@@ -14,8 +14,10 @@
 
 use core::mem;
 
-use cslice::CSlice;
+use core_io::Error as ReadError;
+use cslice::{AsCSlice, CSlice};
 use dwarf::eh::{self, EHAction, EHContext};
+use io::{Cursor, ProtoRead};
 use libc::{c_int, c_void, uintptr_t};
 use log::{error, trace};
 use unwind as uw;
@@ -220,8 +222,6 @@ pub unsafe fn artiq_personality(
 }
 
 pub unsafe extern "C" fn raise(exception: *const Exception) -> ! {
-    use cslice::AsCSlice;
-
     let count = EXCEPTION_BUFFER.exception_count;
     let stack = &mut EXCEPTION_BUFFER.exception_stack;
     let diff = exception as isize - EXCEPTION_BUFFER.exceptions.as_ptr() as isize;
@@ -295,6 +295,60 @@ pub unsafe extern "C" fn raise(exception: *const Exception) -> ! {
     unreachable!();
 }
 
+fn read_exception_string<'a>(reader: &mut Cursor<&[u8]>) -> Result<CSlice<'a, u8>, ReadError> {
+    let len = reader.read_u32()? as usize;
+    if len == usize::MAX {
+        let data = reader.read_u32()?;
+        Ok(unsafe { CSlice::new(data as *const u8, len) })
+    } else {
+        let pos = reader.position();
+        let slice = unsafe {
+            let ptr = reader.get_ref().as_ptr().offset(pos as isize);
+            CSlice::new(ptr, len)
+        };
+        reader.set_position(pos + len);
+        Ok(slice)
+    }
+}
+
+fn read_exception(raw_exception: &[u8]) -> Result<Exception, ReadError> {
+    let mut reader = Cursor::new(raw_exception);
+
+    let mut byte = reader.read_u8()?;
+    // to sync
+    while byte != 0x5a {
+        byte = reader.read_u8()?;
+    }
+    // skip sync bytes, 0x09 indicates exception
+    while byte != 0x09 {
+        byte = reader.read_u8()?;
+    }
+    let _len = reader.read_u32()?;
+    // ignore the remaining exceptions, stack traces etc. - unwinding from another device would be unwise anyway
+    Ok(Exception {
+        id: reader.read_u32()?,
+        message: read_exception_string(&mut reader)?,
+        param: [
+            reader.read_u64()? as i64,
+            reader.read_u64()? as i64,
+            reader.read_u64()? as i64,
+        ],
+        file: read_exception_string(&mut reader)?,
+        line: reader.read_u32()?,
+        column: reader.read_u32()?,
+        function: read_exception_string(&mut reader)?,
+    })
+}
+
+pub fn raise_raw(raw_exception: &[u8]) -> ! {
+    use crate::artiq_raise;
+    if let Ok(exception) = read_exception(raw_exception) {
+        unsafe { raise(&exception) };
+    } else {
+        artiq_raise!("SubkernelError", "Error passing exception");
+    }
+}
+
 pub unsafe extern "C" fn resume() -> ! {
     trace!("resume");
     assert!(EXCEPTION_BUFFER.exception_count != 0);
@@ -421,20 +475,30 @@ extern "C" fn stop_fn(
     }
 }
 
-// Must be kept in sync with preallocate_runtime_exception_names() in artiq/language/embedding_map.py
+// Must be kept in sync with preallocate_runtime_exception_names() in `artiq.compiler.embedding`
-static EXCEPTION_ID_LOOKUP: [(&str, u32); 12] = [
+static EXCEPTION_ID_LOOKUP: [(&str, u32); 22] = [
-    ("RuntimeError", 0),
+    ("RTIOUnderflow", 0),
-    ("RTIOUnderflow", 1),
+    ("RTIOOverflow", 1),
-    ("RTIOOverflow", 2),
+    ("RTIODestinationUnreachable", 2),
-    ("RTIODestinationUnreachable", 3),
+    ("DMAError", 3),
-    ("DMAError", 4),
+    ("I2CError", 4),
-    ("I2CError", 5),
+    ("CacheError", 5),
-    ("CacheError", 6),
+    ("SPIError", 6),
-    ("SPIError", 7),
+    ("SubkernelError", 7),
-    ("ZeroDivisionError", 8),
+    ("AssertionError", 8),
-    ("IndexError", 9),
+    ("AttributeError", 9),
-    ("UnwrapNoneError", 10),
+    ("IndexError", 10),
-    ("SubkernelError", 11),
+    ("IOError", 11),
+    ("KeyError", 12),
+    ("NotImplementedError", 13),
+    ("OverflowError", 14),
+    ("RuntimeError", 15),
+    ("TimeoutError", 16),
+    ("TypeError", 17),
+    ("ValueError", 18),
+    ("ZeroDivisionError", 19),
+    ("LinAlgError", 20),
+    ("UnwrapNoneError", 21),
 ];
 
 pub fn get_exception_id(name: &str) -> u32 {
@@ -469,3 +533,29 @@ macro_rules! artiq_raise {
     }};
     ($name:expr, $message:expr) => {{ artiq_raise!($name, $message, 0, 0, 0) }};
 }
+
+/// Takes as input exception id from host
+/// Generates a new exception with:
+///   * `id` set to `exn_id`
+///   * `message` set to corresponding exception name from `EXCEPTION_ID_LOOKUP`
+///
+/// The message is matched on host to ensure correct exception is being referred
+/// This test checks the synchronization of exception ids for runtime errors
+#[no_mangle]
+pub extern "C" fn test_exception_id_sync(exn_id: u32) {
+    let message = EXCEPTION_ID_LOOKUP
+        .iter()
+        .find_map(|&(name, id)| if id == exn_id { Some(name) } else { None })
+        .unwrap_or("unallocated internal exception id");
+
+    let exn = Exception {
+        id: exn_id,
+        file: file!().as_c_slice(),
+        line: 0,
+        column: 0,
+        function: "test_exception_id_sync".as_c_slice(),
+        message: message.as_c_slice(),
+        param: [0, 0, 0],
+    };
+    unsafe { raise(&exn) };
+}

src/libksupport/src/kernel/api.rs

@@ -9,7 +9,7 @@ use log::{info, warn};
 use super::subkernel;
 use super::{cache,
             core1::rtio_get_destination_status,
-            dma,
+            dma, linalg,
             rpc::{rpc_recv, rpc_send, rpc_send_async}};
 use crate::{eh_artiq, i2c, rtio};
 
@@ -319,6 +319,26 @@ pub fn resolve(required: &[u8]) -> Option<u32> {
             }
             api!(yn = yn)
         },
+
+        // linalg
+        api!(np_linalg_cholesky = linalg::np_linalg_cholesky),
+        api!(np_linalg_qr = linalg::np_linalg_qr),
+        api!(np_linalg_svd = linalg::np_linalg_svd),
+        api!(np_linalg_inv = linalg::np_linalg_inv),
+        api!(np_linalg_pinv = linalg::np_linalg_pinv),
+        api!(np_linalg_matrix_power = linalg::np_linalg_matrix_power),
+        api!(np_linalg_det = linalg::np_linalg_det),
+        api!(sp_linalg_lu = linalg::sp_linalg_lu),
+        api!(sp_linalg_schur = linalg::sp_linalg_schur),
+        api!(sp_linalg_hessenberg = linalg::sp_linalg_hessenberg),
+
+        /*
+         * syscall for unit tests
+         * Used in `artiq.tests.coredevice.test_exceptions.ExceptionTest.test_raise_exceptions_kernel`
+         * This syscall checks that the exception IDs used in the Python `EmbeddingMap` (in `artiq.language.embedding`)
+         * match the `EXCEPTION_ID_LOOKUP` defined in the firmware (`libksupport::src::eh_artiq`)
+         */
+        api!(test_exception_id_sync = eh_artiq::test_exception_id_sync)
     ];
     api.iter()
         .find(|&&(exported, _)| exported.as_bytes() == required)

src/libksupport/src/kernel/linalg.rs

@@ -0,0 +1,440 @@
+// Uses `nalgebra` crate to invoke `np_linalg` and `sp_linalg` functions
+// When converting between `nalgebra::Matrix` and `NDArray` following considerations are necessary
+//
+// * Both `nalgebra::Matrix` and `NDArray` require their content to be stored in row-major order
+// * `NDArray` data pointer can be directly read and converted to `nalgebra::Matrix` (row and column number must be known)
+// * `nalgebra::Matrix::as_slice` returns the content of matrix in column-major order and initial data needs to be transposed before storing it in `NDArray` data pointer
+
+use alloc::vec::Vec;
+use core::slice;
+
+use nalgebra::DMatrix;
+
+use crate::artiq_raise;
+
+pub struct InputMatrix {
+    pub ndims: usize,
+    pub dims: *const usize,
+    pub data: *mut f64,
+}
+
+impl InputMatrix {
+    fn get_dims(&mut self) -> Vec<usize> {
+        let dims = unsafe { slice::from_raw_parts(self.dims, self.ndims) };
+        dims.to_vec()
+    }
+}
+
+/// # Safety
+///
+/// `mat1` should point to a valid 2DArray of `f64` floats in row-major order
+#[no_mangle]
+pub unsafe extern "C" fn np_linalg_cholesky(mat1: *mut InputMatrix, out: *mut InputMatrix) {
+    let mat1 = mat1.as_mut().unwrap();
+    let out = out.as_mut().unwrap();
+
+    if mat1.ndims != 2 {
+        artiq_raise!(
+            "ValueError",
+            "expected 2D Vector Input, but received {1}D input)",
+            0,
+            mat1.ndims as i64,
+            0
+        );
+    }
+
+    let dim1 = (*mat1).get_dims();
+    if dim1[0] != dim1[1] {
+        artiq_raise!(
+            "ValueError",
+            "last 2 dimensions of the array must be square: {1} != {2}",
+            0,
+            dim1[0] as i64,
+            dim1[1] as i64
+        );
+    }
+
+    let outdim = out.get_dims();
+    let out_slice = slice::from_raw_parts_mut(out.data, outdim[0] * outdim[1]);
+    let data_slice1 = slice::from_raw_parts_mut(mat1.data, dim1[0] * dim1[1]);
+
+    let matrix1 = DMatrix::from_row_slice(dim1[0], dim1[1], data_slice1);
+    let result = matrix1.cholesky();
+    match result {
+        Some(res) => {
+            out_slice.copy_from_slice(res.unpack().transpose().as_slice());
+        }
+        None => {
+            artiq_raise!("LinAlgError", "Matrix is not positive definite");
+        }
+    };
+}
+
+/// # Safety
+///
+/// `mat1` should point to a valid 2DArray of `f64` floats in row-major order
+#[no_mangle]
+pub unsafe extern "C" fn np_linalg_qr(mat1: *mut InputMatrix, out_q: *mut InputMatrix, out_r: *mut InputMatrix) {
+    let mat1 = mat1.as_mut().unwrap();
+    let out_q = out_q.as_mut().unwrap();
+    let out_r = out_r.as_mut().unwrap();
+
+    if mat1.ndims != 2 {
+        artiq_raise!(
+            "ValueError",
+            "expected 2D Vector Input, but received {1}D input)",
+            0,
+            mat1.ndims as i64,
+            0
+        );
+    }
+
+    let dim1 = (*mat1).get_dims();
+    let outq_dim = (*out_q).get_dims();
+    let outr_dim = (*out_r).get_dims();
+
+    let data_slice1 = slice::from_raw_parts_mut(mat1.data, dim1[0] * dim1[1]);
+    let out_q_slice = slice::from_raw_parts_mut(out_q.data, outq_dim[0] * outq_dim[1]);
+    let out_r_slice = slice::from_raw_parts_mut(out_r.data, outr_dim[0] * outr_dim[1]);
+
+    // Refer to https://github.com/dimforge/nalgebra/issues/735
+    let matrix1 = DMatrix::from_row_slice(dim1[0], dim1[1], data_slice1);
+
+    let res = matrix1.qr();
+    let (q, r) = res.unpack();
+
+    // Uses different algo need to match numpy
+    out_q_slice.copy_from_slice(q.transpose().as_slice());
+    out_r_slice.copy_from_slice(r.transpose().as_slice());
+}
+
+/// # Safety
+///
+/// `mat1` should point to a valid 2DArray of `f64` floats in row-major order
+#[no_mangle]
+pub unsafe extern "C" fn np_linalg_svd(
+    mat1: *mut InputMatrix,
+    outu: *mut InputMatrix,
+    outs: *mut InputMatrix,
+    outvh: *mut InputMatrix,
+) {
+    let mat1 = mat1.as_mut().unwrap();
+    let outu = outu.as_mut().unwrap();
+    let outs = outs.as_mut().unwrap();
+    let outvh = outvh.as_mut().unwrap();
+
+    if mat1.ndims != 2 {
+        artiq_raise!(
+            "ValueError",
+            "expected 2D Vector Input, but received {1}D input)",
+            0,
+            mat1.ndims as i64,
+            0
+        );
+    }
+
+    let dim1 = (*mat1).get_dims();
+    let outu_dim = (*outu).get_dims();
+    let outs_dim = (*outs).get_dims();
+    let outvh_dim = (*outvh).get_dims();
+
+    let data_slice1 = slice::from_raw_parts_mut(mat1.data, dim1[0] * dim1[1]);
+    let out_u_slice = slice::from_raw_parts_mut(outu.data, outu_dim[0] * outu_dim[1]);
+    let out_s_slice = slice::from_raw_parts_mut(outs.data, outs_dim[0]);
+    let out_vh_slice = slice::from_raw_parts_mut(outvh.data, outvh_dim[0] * outvh_dim[1]);
+
+    let matrix = DMatrix::from_row_slice(dim1[0], dim1[1], data_slice1);
+    let result = matrix.svd(true, true);
+    out_u_slice.copy_from_slice(result.u.unwrap().transpose().as_slice());
+    out_s_slice.copy_from_slice(result.singular_values.as_slice());
+    out_vh_slice.copy_from_slice(result.v_t.unwrap().transpose().as_slice());
+}
+
+/// # Safety
+///
+/// `mat1` should point to a valid 2DArray of `f64` floats in row-major order
+#[no_mangle]
+pub unsafe extern "C" fn np_linalg_inv(mat1: *mut InputMatrix, out: *mut InputMatrix) {
+    let mat1 = mat1.as_mut().unwrap();
+    let out = out.as_mut().unwrap();
+
+    if mat1.ndims != 2 {
+        artiq_raise!(
+            "ValueError",
+            "expected 2D Vector Input, but received {1}D input)",
+            0,
+            mat1.ndims as i64,
+            0
+        );
+    }
+    let dim1 = (*mat1).get_dims();
+
+    if dim1[0] != dim1[1] {
+        artiq_raise!(
+            "ValueError",
+            "last 2 dimensions of the array must be square: {1} != {2}",
+            0,
+            dim1[0] as i64,
+            dim1[1] as i64
+        );
+    }
+
+    let outdim = out.get_dims();
+    let out_slice = slice::from_raw_parts_mut(out.data, outdim[0] * outdim[1]);
+    let data_slice1 = slice::from_raw_parts_mut(mat1.data, dim1[0] * dim1[1]);
+
+    let matrix = DMatrix::from_row_slice(dim1[0], dim1[1], data_slice1);
+    if !matrix.is_invertible() {
+        artiq_raise!("LinAlgError", "no inverse for Singular Matrix");
+    }
+    let inv = matrix.try_inverse().unwrap();
+    out_slice.copy_from_slice(inv.transpose().as_slice());
+}
+
+/// # Safety
+///
+/// `mat1` should point to a valid 2DArray of `f64` floats in row-major order
+#[no_mangle]
+pub unsafe extern "C" fn np_linalg_pinv(mat1: *mut InputMatrix, out: *mut InputMatrix) {
+    let mat1 = mat1.as_mut().unwrap();
+    let out = out.as_mut().unwrap();
+
+    if mat1.ndims != 2 {
+        artiq_raise!(
+            "ValueError",
+            "expected 2D Vector Input, but received {1}D input)",
+            0,
+            mat1.ndims as i64,
+            0
+        );
+    }
+    let dim1 = (*mat1).get_dims();
+    let outdim = out.get_dims();
+    let out_slice = slice::from_raw_parts_mut(out.data, outdim[0] * outdim[1]);
+    let data_slice1 = slice::from_raw_parts_mut(mat1.data, dim1[0] * dim1[1]);
+
+    let matrix = DMatrix::from_row_slice(dim1[0], dim1[1], data_slice1);
+    let svd = matrix.svd(true, true);
+    let inv = svd.pseudo_inverse(1e-15);
+
+    match inv {
+        Ok(m) => {
+            out_slice.copy_from_slice(m.transpose().as_slice());
+        }
+        Err(_) => {
+            artiq_raise!("LinAlgError", "SVD computation does not converge");
+        }
+    }
+}
+
+/// # Safety
+///
+/// `mat1` should point to a valid 2DArray of `f64` floats in row-major order
+#[no_mangle]
+pub unsafe extern "C" fn np_linalg_matrix_power(mat1: *mut InputMatrix, mat2: *mut InputMatrix, out: *mut InputMatrix) {
+    let mat1 = mat1.as_mut().unwrap();
+    let mat2 = mat2.as_mut().unwrap();
+    let out = out.as_mut().unwrap();
+
+    if mat1.ndims != 2 {
+        artiq_raise!(
+            "ValueError",
+            "expected 2D Vector Input, but received {1}D input)",
+            0,
+            mat1.ndims as i64,
+            0
+        );
+    }
+
+    let dim1 = (*mat1).get_dims();
+    let power = slice::from_raw_parts_mut(mat2.data, 1);
+    let power = power[0];
+    let outdim = out.get_dims();
+    let out_slice = slice::from_raw_parts_mut(out.data, outdim[0] * outdim[1]);
+    let data_slice1 = slice::from_raw_parts_mut(mat1.data, dim1[0] * dim1[1]);
+    let mut abs_power = power;
+    if abs_power < 0.0 {
+        abs_power = abs_power * -1.0;
+    }
+    let matrix1 = DMatrix::from_row_slice(dim1[0], dim1[1], data_slice1);
+    if !matrix1.is_square() {
+        artiq_raise!(
+            "ValueError",
+            "last 2 dimensions of the array must be square: {1} != {2}",
+            0,
+            dim1[0] as i64,
+            dim1[1] as i64
+        );
+    }
+    let mut result = matrix1.pow(abs_power as u32);
+
+    if power < 0.0 {
+        if !matrix1.is_invertible() {
+            artiq_raise!("LinAlgError", "no inverse for Singular Matrix");
+        }
+        result = result.try_inverse().unwrap();
+    }
+    out_slice.copy_from_slice(result.transpose().as_slice());
+}
+
+/// # Safety
+///
+/// `mat1` should point to a valid 2DArray of `f64` floats in row-major order
+#[no_mangle]
+pub unsafe extern "C" fn np_linalg_det(mat1: *mut InputMatrix, out: *mut InputMatrix) {
+    let mat1 = mat1.as_mut().unwrap();
+    let out = out.as_mut().unwrap();
+
+    if mat1.ndims != 2 {
+        artiq_raise!(
+            "ValueError",
+            "expected 2D Vector Input, but received {1}D input)",
+            0,
+            mat1.ndims as i64,
+            0
+        );
+    }
+    let dim1 = (*mat1).get_dims();
+    let out_slice = slice::from_raw_parts_mut(out.data, 1);
+    let data_slice1 = slice::from_raw_parts_mut(mat1.data, dim1[0] * dim1[1]);
+
+    let matrix = DMatrix::from_row_slice(dim1[0], dim1[1], data_slice1);
+    if !matrix.is_square() {
+        artiq_raise!(
+            "ValueError",
+            "last 2 dimensions of the array must be square: {1} != {2}",
+            0,
+            dim1[0] as i64,
+            dim1[1] as i64
+        );
+    }
+    out_slice[0] = matrix.determinant();
+}
+
+/// # Safety
+///
+/// `mat1` should point to a valid 2DArray of `f64` floats in row-major order
+#[no_mangle]
+pub unsafe extern "C" fn sp_linalg_lu(mat1: *mut InputMatrix, out_l: *mut InputMatrix, out_u: *mut InputMatrix) {
+    let mat1 = mat1.as_mut().unwrap();
+    let out_l = out_l.as_mut().unwrap();
+    let out_u = out_u.as_mut().unwrap();
+
+    if mat1.ndims != 2 {
+        artiq_raise!(
+            "ValueError",
+            "expected 2D Vector Input, but received {1}D input)",
+            0,
+            mat1.ndims as i64,
+            0
+        );
+    }
+
+    let dim1 = (*mat1).get_dims();
+    let outl_dim = (*out_l).get_dims();
+    let outu_dim = (*out_u).get_dims();
+
+    let data_slice1 = slice::from_raw_parts_mut(mat1.data, dim1[0] * dim1[1]);
+    let out_l_slice = slice::from_raw_parts_mut(out_l.data, outl_dim[0] * outl_dim[1]);
+    let out_u_slice = slice::from_raw_parts_mut(out_u.data, outu_dim[0] * outu_dim[1]);
+
+    let matrix = DMatrix::from_row_slice(dim1[0], dim1[1], data_slice1);
+    let (_, l, u) = matrix.lu().unpack();
+
+    out_l_slice.copy_from_slice(l.transpose().as_slice());
+    out_u_slice.copy_from_slice(u.transpose().as_slice());
+}
+
+/// # Safety
+///
+/// `mat1` should point to a valid 2DArray of `f64` floats in row-major order
+#[no_mangle]
+pub unsafe extern "C" fn sp_linalg_schur(mat1: *mut InputMatrix, out_t: *mut InputMatrix, out_z: *mut InputMatrix) {
+    let mat1 = mat1.as_mut().unwrap();
+    let out_t = out_t.as_mut().unwrap();
+    let out_z = out_z.as_mut().unwrap();
+
+    if mat1.ndims != 2 {
+        artiq_raise!(
+            "ValueError",
+            "expected 2D Vector Input, but received {1}D input)",
+            0,
+            mat1.ndims as i64,
+            0
+        );
+    }
+
+    let dim1 = (*mat1).get_dims();
+
+    if dim1[0] != dim1[1] {
+        artiq_raise!(
+            "ValueError",
+            "last 2 dimensions of the array must be square: {1} != {2}",
+            0,
+            dim1[0] as i64,
+            dim1[1] as i64
+        );
+    }
+
+    let out_t_dim = (*out_t).get_dims();
+    let out_z_dim = (*out_z).get_dims();
+
+    let data_slice1 = slice::from_raw_parts_mut(mat1.data, dim1[0] * dim1[1]);
+    let out_t_slice = slice::from_raw_parts_mut(out_t.data, out_t_dim[0] * out_t_dim[1]);
+    let out_z_slice = slice::from_raw_parts_mut(out_z.data, out_z_dim[0] * out_z_dim[1]);
+
+    let matrix = DMatrix::from_row_slice(dim1[0], dim1[1], data_slice1);
+    let (z, t) = matrix.schur().unpack();
+
+    out_t_slice.copy_from_slice(t.transpose().as_slice());
+    out_z_slice.copy_from_slice(z.transpose().as_slice());
+}
+
+/// # Safety
+///
+/// `mat1` should point to a valid 2DArray of `f64` floats in row-major order
+#[no_mangle]
+pub unsafe extern "C" fn sp_linalg_hessenberg(
+    mat1: *mut InputMatrix,
+    out_h: *mut InputMatrix,
+    out_q: *mut InputMatrix,
+) {
+    let mat1 = mat1.as_mut().unwrap();
+    let out_h = out_h.as_mut().unwrap();
+    let out_q = out_q.as_mut().unwrap();
+
+    if mat1.ndims != 2 {
+        artiq_raise!(
+            "ValueError",
+            "expected 2D Vector Input, but received {1}D input)",
+            0,
+            mat1.ndims as i64,
+            0
+        );
+    }
+
+    let dim1 = (*mat1).get_dims();
+
+    if dim1[0] != dim1[1] {
+        artiq_raise!(
+            "ValueError",
+            "last 2 dimensions of the array must be square: {1} != {2}",
+            0,
+            dim1[0] as i64,
+            dim1[1] as i64
+        );
+    }
+
+    let out_h_dim = (*out_h).get_dims();
+    let out_q_dim = (*out_q).get_dims();
+
+    let data_slice1 = slice::from_raw_parts_mut(mat1.data, dim1[0] * dim1[1]);
+    let out_h_slice = slice::from_raw_parts_mut(out_h.data, out_h_dim[0] * out_h_dim[1]);
+    let out_q_slice = slice::from_raw_parts_mut(out_q.data, out_q_dim[0] * out_q_dim[1]);
+
+    let matrix = DMatrix::from_row_slice(dim1[0], dim1[1], data_slice1);
+    let (q, h) = matrix.hessenberg().unpack();
+
+    out_h_slice.copy_from_slice(h.transpose().as_slice());
+    out_q_slice.copy_from_slice(q.transpose().as_slice());
+}

src/libksupport/src/kernel/mod.rs

@@ -13,6 +13,7 @@ mod dma;
 mod rpc;
 pub use dma::DmaRecorder;
 mod cache;
+mod linalg;
 #[cfg(has_drtio)]
 mod subkernel;
 
@@ -23,6 +24,7 @@ pub enum SubkernelStatus {
     Timeout,
     IncorrectState,
     CommLost,
+    Exception(Vec<u8>),
     OtherError,
 }
 
@@ -90,9 +92,7 @@ pub enum Message {
         timeout: i64,
     },
     #[cfg(has_drtio)]
-    SubkernelAwaitFinishReply {
+    SubkernelAwaitFinishReply,
-        status: SubkernelStatus,
-    },
     #[cfg(has_drtio)]
     SubkernelMsgSend {
         id: u32,
@@ -109,9 +109,10 @@ pub enum Message {
     },
     #[cfg(has_drtio)]
     SubkernelMsgRecvReply {
-        status: SubkernelStatus,
         count: u8,
     },
+    #[cfg(has_drtio)]
+    SubkernelError(SubkernelStatus),
 }
 
 static CHANNEL_0TO1: Mutex<Option<sync_channel::Sender<'static, Message>>> = Mutex::new(None);

src/libksupport/src/kernel/subkernel.rs

@@ -3,7 +3,7 @@ use alloc::vec::Vec;
 use cslice::CSlice;
 
 use super::{Message, SubkernelStatus, KERNEL_CHANNEL_0TO1, KERNEL_CHANNEL_1TO0};
-use crate::{artiq_raise, rpc::send_args};
+use crate::{artiq_raise, eh_artiq, rpc::send_args};
 
 pub extern "C" fn load_run(id: u32, destination: u8, run: bool) {
     unsafe {
@@ -36,21 +36,18 @@ pub extern "C" fn await_finish(id: u32, timeout: i64) {
             });
     }
     match unsafe { KERNEL_CHANNEL_0TO1.as_mut().unwrap() }.recv() {
-        Message::SubkernelAwaitFinishReply {
+        Message::SubkernelAwaitFinishReply => (),
-            status: SubkernelStatus::NoError,
+        Message::SubkernelError(SubkernelStatus::IncorrectState) => {
-        } => (),
+            artiq_raise!("SubkernelError", "Subkernel not running")
-        Message::SubkernelAwaitFinishReply {
+        }
-            status: SubkernelStatus::IncorrectState,
+        Message::SubkernelError(SubkernelStatus::Timeout) => artiq_raise!("SubkernelError", "Subkernel timed out"),
-        } => artiq_raise!("SubkernelError", "Subkernel not running"),
+        Message::SubkernelError(SubkernelStatus::CommLost) => {
-        Message::SubkernelAwaitFinishReply {
+            artiq_raise!("SubkernelError", "Lost communication with satellite")
-            status: SubkernelStatus::Timeout,
+        }
-        } => artiq_raise!("SubkernelError", "Subkernel timed out"),
+        Message::SubkernelError(SubkernelStatus::OtherError) => {
-        Message::SubkernelAwaitFinishReply {
+            artiq_raise!("SubkernelError", "An error occurred during subkernel operation")
-            status: SubkernelStatus::CommLost,
+        }
-        } => artiq_raise!("SubkernelError", "Lost communication with satellite"),
+        Message::SubkernelError(SubkernelStatus::Exception(raw_exception)) => eh_artiq::raise_raw(&raw_exception),
-        Message::SubkernelAwaitFinishReply {
-            status: SubkernelStatus::OtherError,
-        } => artiq_raise!("SubkernelError", "An error occurred during subkernel operation"),
         _ => panic!("expected SubkernelAwaitFinishReply after SubkernelAwaitFinishRequest"),
     }
 }
@@ -92,30 +89,22 @@ pub extern "C" fn await_message(id: i32, timeout: i64, tags: &CSlice<u8>, min: u
             });
     }
     match unsafe { KERNEL_CHANNEL_0TO1.as_mut().unwrap() }.recv() {
-        Message::SubkernelMsgRecvReply {
+        Message::SubkernelMsgRecvReply { count } => {
-            status: SubkernelStatus::NoError,
-            count,
-        } => {
             if min > count || count > max {
                 artiq_raise!("SubkernelError", "Received more or less arguments than required")
             }
         }
-        Message::SubkernelMsgRecvReply {
+        Message::SubkernelError(SubkernelStatus::IncorrectState) => {
-            status: SubkernelStatus::IncorrectState,
+            artiq_raise!("SubkernelError", "Subkernel not running")
-            ..
+        }
-        } => artiq_raise!("SubkernelError", "Subkernel not running"),
+        Message::SubkernelError(SubkernelStatus::Timeout) => artiq_raise!("SubkernelError", "Subkernel timed out"),
-        Message::SubkernelMsgRecvReply {
+        Message::SubkernelError(SubkernelStatus::CommLost) => {
-            status: SubkernelStatus::Timeout,
+            artiq_raise!("SubkernelError", "Lost communication with satellite")
-            ..
+        }
-        } => artiq_raise!("SubkernelError", "Subkernel timed out"),
+        Message::SubkernelError(SubkernelStatus::OtherError) => {
-        Message::SubkernelMsgRecvReply {
+            artiq_raise!("SubkernelError", "An error occurred during subkernel operation")
-            status: SubkernelStatus::CommLost,
+        }
-            ..
+        Message::SubkernelError(SubkernelStatus::Exception(raw_exception)) => eh_artiq::raise_raw(&raw_exception),
-        } => artiq_raise!("SubkernelError", "Lost communication with satellite"),
-        Message::SubkernelMsgRecvReply {
-            status: SubkernelStatus::OtherError,
-            ..
-        } => artiq_raise!("SubkernelError", "An error occurred during subkernel operation"),
         _ => panic!("expected SubkernelMsgRecvReply after SubkernelMsgRecvRequest"),
     }
     // RpcRecvRequest should be called after this to receive message data

src/runtime/src/comms.rs

@@ -422,33 +422,23 @@ async fn handle_run_kernel(
             #[cfg(has_drtio)]
             kernel::Message::SubkernelAwaitFinishRequest { id, timeout } => {
                 let res = subkernel::await_finish(aux_mutex, routing_table, timer, id, timeout).await;
-                let status = match res {
+                let response = match res {
-                    Ok(ref res) => {
+                    Ok(res) => {
                         if res.status == subkernel::FinishStatus::CommLost {
-                            kernel::SubkernelStatus::CommLost
+                            kernel::Message::SubkernelError(kernel::SubkernelStatus::CommLost)
-                        } else if let Some(exception) = &res.exception {
+                        } else if let Some(exception) = res.exception {
-                            error!("Exception in subkernel");
+                            kernel::Message::SubkernelError(kernel::SubkernelStatus::Exception(exception))
-                            match stream {
-                                None => (),
-                                Some(stream) => {
-                                    write_chunk(stream, exception).await?;
-                                }
-                            }
-                            // will not be called after exception is served
-                            kernel::SubkernelStatus::OtherError
                         } else {
-                            kernel::SubkernelStatus::NoError
+                            kernel::Message::SubkernelAwaitFinishReply
                         }
                     }
-                    Err(SubkernelError::Timeout) => kernel::SubkernelStatus::Timeout,
+                    Err(SubkernelError::Timeout) => kernel::Message::SubkernelError(kernel::SubkernelStatus::Timeout),
-                    Err(SubkernelError::IncorrectState) => kernel::SubkernelStatus::IncorrectState,
+                    Err(SubkernelError::IncorrectState) => {
-                    Err(_) => kernel::SubkernelStatus::OtherError,
+                        kernel::Message::SubkernelError(kernel::SubkernelStatus::IncorrectState)
+                    }
+                    Err(_) => kernel::Message::SubkernelError(kernel::SubkernelStatus::OtherError),
                 };
-                control
+                control.borrow_mut().tx.async_send(response).await;
-                    .borrow_mut()
-                    .tx
-                    .async_send(kernel::Message::SubkernelAwaitFinishReply { status: status })
-                    .await;
             }
             #[cfg(has_drtio)]
             kernel::Message::SubkernelMsgSend { id, destination, data } => {
@@ -469,35 +459,23 @@ async fn handle_run_kernel(
             #[cfg(has_drtio)]
             kernel::Message::SubkernelMsgRecvRequest { id, timeout, tags } => {
                 let message_received = subkernel::message_await(id as u32, timeout, timer).await;
-                let (status, count) = match message_received {
+                let response = match message_received {
-                    Ok(ref message) => (kernel::SubkernelStatus::NoError, message.count),
+                    Ok(ref message) => kernel::Message::SubkernelMsgRecvReply { count: message.count },
-                    Err(SubkernelError::Timeout) => (kernel::SubkernelStatus::Timeout, 0),
+                    Err(SubkernelError::Timeout) => kernel::Message::SubkernelError(kernel::SubkernelStatus::Timeout),
-                    Err(SubkernelError::IncorrectState) => (kernel::SubkernelStatus::IncorrectState, 0),
+                    Err(SubkernelError::IncorrectState) => {
-                    Err(SubkernelError::CommLost) => (kernel::SubkernelStatus::CommLost, 0),
+                        kernel::Message::SubkernelError(kernel::SubkernelStatus::IncorrectState)
+                    }
+                    Err(SubkernelError::CommLost) => kernel::Message::SubkernelError(kernel::SubkernelStatus::CommLost),
                     Err(SubkernelError::SubkernelException) => {
-                        error!("Exception in subkernel");
                         // just retrieve the exception
                         let status = subkernel::await_finish(aux_mutex, routing_table, timer, id as u32, timeout)
                             .await
                             .unwrap();
-                        match stream {
+                        kernel::Message::SubkernelError(kernel::SubkernelStatus::Exception(status.exception.unwrap()))
-                            None => (),
-                            Some(stream) => {
-                                write_chunk(stream, &status.exception.unwrap()).await?;
-                            }
-                        }
-                        (kernel::SubkernelStatus::OtherError, 0)
                     }
-                    Err(_) => (kernel::SubkernelStatus::OtherError, 0),
+                    Err(_) => kernel::Message::SubkernelError(kernel::SubkernelStatus::OtherError),
                 };
-                control
+                control.borrow_mut().tx.async_send(response).await;
-                    .borrow_mut()
-                    .tx
-                    .async_send(kernel::Message::SubkernelMsgRecvReply {
-                        status: status,
-                        count: count,
-                    })
-                    .await;
                 if let Ok(message) = message_received {
                     // receive code almost identical to RPC recv, except we are not reading from a stream
                     let mut reader = Cursor::new(message.data);
@@ -529,7 +507,7 @@ async fn handle_run_kernel(
                             .async_send(kernel::Message::RpcRecvReply(Ok(0)))
                             .await;
                         i += 1;
-                        if i < count {
+                        if i < message.count {
                             current_tags = remaining_tags;
                         } else {
                             break;
@@ -771,14 +749,13 @@ pub fn main(timer: GlobalTimer, cfg: Config) {
     #[cfg(has_drtio_routing)]
     drtio_routing::interconnect_disable_all();
 
-    rtio_mgt::startup(&aux_mutex, &drtio_routing_table, &up_destinations, timer);
+    rtio_mgt::startup(&aux_mutex, &drtio_routing_table, &up_destinations, &cfg, timer);
     ksupport::setup_device_map(&cfg);
 
     analyzer::start(&aux_mutex, &drtio_routing_table, &up_destinations, timer);
     moninj::start(timer, &aux_mutex, &drtio_routing_table);
 
     let control: Rc<RefCell<kernel::Control>> = Rc::new(RefCell::new(kernel::Control::start()));
-    let idle_kernel = Rc::new(cfg.read("idle_kernel").ok());
     if let Ok(buffer) = cfg.read("startup_kernel") {
         info!("Loading startup kernel...");
         let routing_table = drtio_routing_table.borrow();
@@ -805,13 +782,26 @@ pub fn main(timer: GlobalTimer, cfg: Config) {
         }
     }
 
-    mgmt::start(cfg);
+    let cfg = Rc::new(cfg);
+    let restart_idle = Rc::new(Semaphore::new(1, 1));
+    mgmt::start(cfg.clone(), restart_idle.clone());
 
     task::spawn(async move {
         let connection = Rc::new(Semaphore::new(1, 1));
         let terminate = Rc::new(Semaphore::new(0, 1));
+        let can_restart_idle = Rc::new(Semaphore::new(1, 1));
+        let restart_idle = restart_idle.clone();
         loop {
-            let mut stream = TcpStream::accept(1381, 0x10_000, 0x10_000).await.unwrap();
+            let control = control.clone();
+            let mut maybe_stream = select_biased! {
+                s = (async {
+                        TcpStream::accept(1381, 0x10_000, 0x10_000).await.unwrap()
+                    }).fuse() => Some(s),
+                _ = (async {
+                        restart_idle.async_wait().await;
+                        can_restart_idle.async_wait().await;
+                    }).fuse() => None
+            };
 
             if connection.try_wait().is_none() {
                 // there is an existing connection
@@ -819,47 +809,58 @@ pub fn main(timer: GlobalTimer, cfg: Config) {
                 connection.async_wait().await;
             }
 
+            let maybe_idle_kernel = cfg.read("idle_kernel").ok();
+            if maybe_idle_kernel.is_none() && maybe_stream.is_none() {
+                control.borrow_mut().restart(); // terminate idle kernel if running
+            }
+
             let control = control.clone();
-            let idle_kernel = idle_kernel.clone();
             let connection = connection.clone();
             let terminate = terminate.clone();
+            let can_restart_idle = can_restart_idle.clone();
             let up_destinations = up_destinations.clone();
             let aux_mutex = aux_mutex.clone();
             let routing_table = drtio_routing_table.clone();
 
             // we make sure the value of terminate is 0 before we start
             let _ = terminate.try_wait();
+            let _ = can_restart_idle.try_wait();
             task::spawn(async move {
                 let routing_table = routing_table.borrow();
                 select_biased! {
                     _ = (async {
-                        let _ = handle_connection(&mut stream, control.clone(), &up_destinations, &aux_mutex, &routing_table, timer)
+                        if let Some(stream) = &mut maybe_stream {
-                            .await
+                            let _ = handle_connection(stream, control.clone(), &up_destinations, &aux_mutex, &routing_table, timer)
-                            .map_err(|e| warn!("connection terminated: {}", e));
+                                .await
-                        if let Some(buffer) = &*idle_kernel {
+                                .map_err(|e| warn!("connection terminated: {}", e));
-                            info!("Loading idle kernel");
+                        }
-                            let res = handle_flash_kernel(&buffer, &control, &up_destinations,  &aux_mutex, &routing_table, timer)
+                        can_restart_idle.signal();
-                                .await;
+                        match maybe_idle_kernel {
-                            match res {
+                            Some(buffer) => {
-                                #[cfg(has_drtio)]
+                                loop {
-                                Err(Error::DestinationDown) => {
+                                    info!("loading idle kernel");
-                                    let mut countdown = timer.countdown();
+                                    match handle_flash_kernel(&buffer, &control, &up_destinations, &aux_mutex, &routing_table, timer).await {
-                                    delay(&mut countdown, Milliseconds(500)).await;
+                                        Ok(_) => {
+                                            info!("running idle kernel");
+                                            match handle_run_kernel(None, &control, &up_destinations, &aux_mutex, &routing_table, timer).await {
+                                                Ok(_) => info!("idle kernel finished"),
+                                                Err(_) => warn!("idle kernel running error")
+                                            }
+                                        },
+                                        Err(_) => warn!("idle kernel loading error")
+                                    }
                                 }
-                                Err(_) => warn!("error loading idle kernel"),
+                            },
-                                _ => (),
+                            None => info!("no idle kernel found")
-                            }
-                            info!("Running idle kernel");
-                            let _ = handle_run_kernel(None, &control, &up_destinations, &aux_mutex, &routing_table, timer)
-                                .await.map_err(|_| warn!("error running idle kernel"));
-                            info!("Idle kernel terminated");
                         }
                     }).fuse() => (),
                     _ = terminate.async_wait().fuse() => ()
                 }
                 connection.signal();
-                let _ = stream.flush().await;
+                if let Some(stream) = maybe_stream {
-                let _ = stream.abort().await;
+                    let _ = stream.flush().await;
+                    let _ = stream.abort().await;
+                }
             });
         }
     });
@@ -908,7 +909,8 @@ pub fn soft_panic_main(timer: GlobalTimer, cfg: Config) -> ! {
 
     Sockets::init(32);
 
-    mgmt::start(cfg);
+    let dummy = Rc::new(Semaphore::new(0, 1));
+    mgmt::start(Rc::new(cfg), dummy);
 
     // getting eth settings disables the LED as it resets GPIO
     // need to re-enable it here

src/runtime/src/mgmt.rs

@@ -6,6 +6,7 @@ use libasync::{smoltcp::TcpStream, task};
 use libboard_artiq::logger::{BufferLogger, LogBufferRef};
 use libboard_zynq::{slcr, smoltcp};
 use libconfig::Config;
+use libcortex_a9::semaphore::Semaphore;
 use log::{self, debug, error, info, warn, LevelFilter};
 use num_derive::FromPrimitive;
 use num_traits::FromPrimitive;
@@ -111,7 +112,12 @@ async fn read_key(stream: &mut TcpStream) -> Result<String> {
     Ok(String::from_utf8(buffer).unwrap())
 }
 
-async fn handle_connection(stream: &mut TcpStream, pull_id: Rc<RefCell<u32>>, cfg: Rc<Config>) -> Result<()> {
+async fn handle_connection(
+    stream: &mut TcpStream,
+    pull_id: Rc<RefCell<u32>>,
+    cfg: Rc<Config>,
+    restart_idle: Rc<Semaphore>,
+) -> Result<()> {
     if !expect(&stream, b"ARTIQ management\n").await? {
         return Err(Error::UnexpectedPattern);
     }
@@ -200,6 +206,9 @@ async fn handle_connection(stream: &mut TcpStream, pull_id: Rc<RefCell<u32>>, cf
                 let value = cfg.write(&key, buffer);
                 if value.is_ok() {
                     debug!("write success");
+                    if key == "idle_kernel" {
+                        restart_idle.signal();
+                    }
                     write_i8(stream, Reply::Success as i8).await?;
                 } else {
                     // this is an error because we do not expect write to fail
@@ -213,6 +222,9 @@ async fn handle_connection(stream: &mut TcpStream, pull_id: Rc<RefCell<u32>>, cf
                 let value = cfg.remove(&key);
                 if value.is_ok() {
                     debug!("erase success");
+                    if key == "idle_kernel" {
+                        restart_idle.signal();
+                    }
                     write_i8(stream, Reply::Success as i8).await?;
                 } else {
                     warn!("erase failed");
@@ -229,17 +241,17 @@ async fn handle_connection(stream: &mut TcpStream, pull_id: Rc<RefCell<u32>>, cf
     }
 }
 
-pub fn start(cfg: Config) {
+pub fn start(cfg: Rc<Config>, restart_idle: Rc<Semaphore>) {
     task::spawn(async move {
         let pull_id = Rc::new(RefCell::new(0u32));
-        let cfg = Rc::new(cfg);
         loop {
             let mut stream = TcpStream::accept(1380, 2048, 2048).await.unwrap();
             let pull_id = pull_id.clone();
             let cfg = cfg.clone();
+            let restart_idle = restart_idle.clone();
             task::spawn(async move {
                 info!("received connection");
-                let _ = handle_connection(&mut stream, pull_id, cfg)
+                let _ = handle_connection(&mut stream, pull_id, cfg, restart_idle)
                     .await
                     .map_err(|e| warn!("connection terminated: {:?}", e));
                 let _ = stream.flush().await;

src/runtime/src/moninj.rs

@@ -102,7 +102,7 @@ mod remote_moninj {
         overrd: i8,
         value: i8,
     ) {
-        let _lock = aux_mutex.lock();
+        let _lock = aux_mutex.async_lock().await;
         drtioaux_async::send(
             linkno,
             &drtioaux_async::Packet::InjectionRequest {

src/runtime/src/rtio_mgt.rs

@@ -3,7 +3,9 @@ use core::cell::RefCell;
 
 use libboard_artiq::{drtio_routing, drtio_routing::RoutingTable, pl::csr};
 use libboard_zynq::timer::GlobalTimer;
+use libconfig::Config;
 use libcortex_a9::mutex::Mutex;
+use log::{info, warn};
 
 #[cfg(has_drtio)]
 pub mod drtio {
@@ -127,6 +129,8 @@ pub mod drtio {
             | Packet::SubkernelLoadRunReply { destination, .. }
             | Packet::SubkernelMessage { destination, .. }
             | Packet::SubkernelMessageAck { destination, .. }
+            | Packet::SubkernelException { destination, .. }
+            | Packet::SubkernelExceptionRequest { destination, .. }
             | Packet::DmaPlaybackStatus { destination, .. }
             | Packet::SubkernelFinished { destination, .. } => {
                 if destination == 0 {
@@ -181,10 +185,7 @@ pub mod drtio {
 
     async fn drain_buffer(linkno: u8, draining_time: Milliseconds, timer: GlobalTimer) {
         let max_time = timer.get_time() + draining_time;
-        loop {
+        while timer.get_time() < max_time {
-            if timer.get_time() > max_time {
-                return;
-            }
             let _ = drtioaux_async::recv(linkno).await;
         }
     }
@@ -833,13 +834,19 @@ pub mod drtio {
                 linkno,
                 routing_table,
                 &Packet::SubkernelExceptionRequest {
+                    source: 0,
                     destination: destination,
                 },
                 timer,
             )
             .await?;
             match reply {
-                Packet::SubkernelException { last, length, data } => {
+                Packet::SubkernelException {
+                    destination: 0,
+                    last,
+                    length,
+                    data,
+                } => {
                     remote_data.extend(&data[0..length as usize]);
                     if last {
                         return Ok(remote_data);
@@ -898,12 +905,36 @@ pub mod drtio {
     pub fn reset(_aux_mutex: Rc<Mutex<bool>>, _routing_table: &RoutingTable, mut _timer: GlobalTimer) {}
 }
 
+fn toggle_sed_spread(val: u8) {
+    unsafe {
+        csr::rtio_core::sed_spread_enable_write(val);
+    }
+}
+
+fn setup_sed_spread(cfg: &Config) {
+    if let Ok(spread_enable) = cfg.read_str("sed_spread_enable") {
+        match spread_enable.as_ref() {
+            "1" => toggle_sed_spread(1),
+            "0" => toggle_sed_spread(0),
+            _ => {
+                warn!("sed_spread_enable value not supported (only 1, 0 allowed), disabling by default");
+                toggle_sed_spread(0)
+            }
+        };
+    } else {
+        info!("SED spreading disabled by default");
+        toggle_sed_spread(0);
+    }
+}
+
 pub fn startup(
     aux_mutex: &Rc<Mutex<bool>>,
     routing_table: &Rc<RefCell<RoutingTable>>,
     up_destinations: &Rc<RefCell<[bool; drtio_routing::DEST_COUNT]>>,
+    cfg: &Config,
     timer: GlobalTimer,
 ) {
+    setup_sed_spread(cfg);
     drtio::startup(aux_mutex, routing_table, up_destinations, timer);
     unsafe {
         csr::rtio_core::reset_phy_write(1);

src/satman/src/main.rs

@@ -12,6 +12,7 @@ extern crate io;
 extern crate ksupport;
 extern crate libboard_artiq;
 extern crate libboard_zynq;
+extern crate libconfig;
 extern crate libcortex_a9;
 extern crate libregister;
 extern crate libsupport_zynq;
@@ -38,6 +39,7 @@ use libboard_artiq::{drtio_routing, drtioaux,
 #[cfg(feature = "target_kasli_soc")]
 use libboard_zynq::error_led::ErrorLED;
 use libboard_zynq::{i2c::I2c, print, println, time::Milliseconds, timer::GlobalTimer};
+use libconfig::Config;
 use libcortex_a9::{l2c::enable_l2_cache, regs::MPIDR};
 use libregister::RegisterR;
 use libsupport_zynq::{exception_vectors, ram};
@@ -81,15 +83,37 @@ fn drtiosat_tsc_loaded() -> bool {
     }
 }
 
+fn toggle_sed_spread(val: u8) {
+    unsafe {
+        csr::drtiosat::sed_spread_enable_write(val);
+    }
+}
+
 #[cfg(has_drtio_routing)]
 macro_rules! forward {
-    ($routing_table:expr, $destination:expr, $rank:expr, $repeaters:expr, $packet:expr, $timer:expr) => {{
+    (
+        $router:expr,
+        $routing_table:expr,
+        $destination:expr,
+        $rank:expr,
+        $self_destination:expr,
+        $repeaters:expr,
+        $packet:expr,
+        $timer:expr
+    ) => {{
         let hop = $routing_table.0[$destination as usize][$rank as usize];
         if hop != 0 {
             let repno = (hop - 1) as usize;
             if repno < $repeaters.len() {
                 if $packet.expects_response() {
-                    return $repeaters[repno].aux_forward($packet, $timer);
+                    return $repeaters[repno].aux_forward(
+                        $packet,
+                        $router,
+                        $routing_table,
+                        $rank,
+                        $self_destination,
+                        $timer,
+                    );
                 } else {
                     return $repeaters[repno].aux_send($packet);
                 }
@@ -102,7 +126,16 @@ macro_rules! forward {
 
 #[cfg(not(has_drtio_routing))]
 macro_rules! forward {
-    ($routing_table:expr, $destination:expr, $rank:expr, $repeaters:expr, $packet:expr, $timer:expr) => {};
+    (
+        $router:expr,
+        $routing_table:expr,
+        $destination:expr,
+        $rank:expr,
+        $self_destination:expr,
+        $repeaters:expr,
+        $packet:expr,
+        $timer:expr
+    ) => {};
 }
 
 fn process_aux_packet(
@@ -183,6 +216,10 @@ fn process_aux_packet(
                             &drtioaux::Packet::DestinationStatusRequest {
                                 destination: destination,
                             },
+                            router,
+                            _routing_table,
+                            *rank,
+                            *self_destination,
                             timer,
                         ) {
                             Ok(()) => (),
@@ -244,7 +281,16 @@ fn process_aux_packet(
             channel,
             probe,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             let value;
             #[cfg(has_rtio_moninj)]
             unsafe {
@@ -266,7 +312,16 @@ fn process_aux_packet(
             overrd,
             value,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             #[cfg(has_rtio_moninj)]
             unsafe {
                 csr::rtio_moninj::inj_chan_sel_write(channel as _);
@@ -280,7 +335,16 @@ fn process_aux_packet(
             channel,
             overrd,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             let value;
             #[cfg(has_rtio_moninj)]
             unsafe {
@@ -299,7 +363,16 @@ fn process_aux_packet(
             destination: _destination,
             busno: _busno,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             let succeeded = i2c.start().is_ok();
             drtioaux::send(0, &drtioaux::Packet::I2cBasicReply { succeeded: succeeded })
         }
@@ -307,7 +380,16 @@ fn process_aux_packet(
             destination: _destination,
             busno: _busno,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             let succeeded = i2c.restart().is_ok();
             drtioaux::send(0, &drtioaux::Packet::I2cBasicReply { succeeded: succeeded })
         }
@@ -315,7 +397,16 @@ fn process_aux_packet(
             destination: _destination,
             busno: _busno,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             let succeeded = i2c.stop().is_ok();
             drtioaux::send(0, &drtioaux::Packet::I2cBasicReply { succeeded: succeeded })
         }
@@ -324,7 +415,16 @@ fn process_aux_packet(
             busno: _busno,
             data,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             match i2c.write(data) {
                 Ok(ack) => drtioaux::send(
                     0,
@@ -347,7 +447,16 @@ fn process_aux_packet(
             busno: _busno,
             ack,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             match i2c.read(ack) {
                 Ok(data) => drtioaux::send(
                     0,
@@ -371,7 +480,16 @@ fn process_aux_packet(
             address,
             mask,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             let ch = match mask {
                 //decode from mainline, PCA9548-centric API
                 0x00 => None,
@@ -397,7 +515,16 @@ fn process_aux_packet(
             div: _div,
             cs: _cs,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             // todo: reimplement when/if SPI is available
             //let succeeded = spi::set_config(busno, flags, length, div, cs).is_ok();
             drtioaux::send(0, &drtioaux::Packet::SpiBasicReply { succeeded: false })
@@ -407,7 +534,16 @@ fn process_aux_packet(
             busno: _busno,
             data: _data,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             // todo: reimplement when/if SPI is available
             //let succeeded = spi::write(busno, data).is_ok();
             drtioaux::send(0, &drtioaux::Packet::SpiBasicReply { succeeded: false })
@@ -416,7 +552,16 @@ fn process_aux_packet(
             destination: _destination,
             busno: _busno,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             // todo: reimplement when/if SPI is available
             // match spi::read(busno) {
             //     Ok(data) => drtioaux::send(0,
@@ -436,7 +581,16 @@ fn process_aux_packet(
         drtioaux::Packet::AnalyzerHeaderRequest {
             destination: _destination,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             let header = analyzer.get_header();
             drtioaux::send(
                 0,
@@ -450,7 +604,16 @@ fn process_aux_packet(
         drtioaux::Packet::AnalyzerDataRequest {
             destination: _destination,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             let mut data_slice: [u8; SAT_PAYLOAD_MAX_SIZE] = [0; SAT_PAYLOAD_MAX_SIZE];
             let meta = analyzer.get_data(&mut data_slice);
             drtioaux::send(
@@ -471,7 +634,16 @@ fn process_aux_packet(
             length,
             trace,
         } => {
-            forward!(_routing_table, destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             *self_destination = destination;
             let succeeded = dma_manager.add(source, id, status, &trace, length as usize).is_ok();
             router.send(
@@ -492,7 +664,16 @@ fn process_aux_packet(
             id,
             succeeded,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             dma_manager.ack_upload(
                 kernel_manager,
                 source,
@@ -510,7 +691,16 @@ fn process_aux_packet(
             destination: _destination,
             id,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             let succeeded = dma_manager.erase(source, id).is_ok();
             router.send(
                 drtioaux::Packet::DmaRemoveTraceReply {
@@ -526,7 +716,16 @@ fn process_aux_packet(
             destination: _destination,
             succeeded: _,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             Ok(())
         }
         drtioaux::Packet::DmaPlaybackRequest {
@@ -535,7 +734,16 @@ fn process_aux_packet(
             id,
             timestamp,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             let succeeded = if !kernel_manager.running() {
                 dma_manager.playback(source, id, timestamp).is_ok()
             } else {
@@ -555,7 +763,16 @@ fn process_aux_packet(
             destination: _destination,
             succeeded,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             if !succeeded {
                 kernel_manager.ddma_nack();
             }
@@ -569,7 +786,16 @@ fn process_aux_packet(
             channel,
             timestamp,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             dma_manager.remote_finished(kernel_manager, id, error, channel, timestamp);
             Ok(())
         }
@@ -581,7 +807,16 @@ fn process_aux_packet(
             length,
             data,
         } => {
-            forward!(_routing_table, destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             *self_destination = destination;
             let succeeded = kernel_manager.add(id, status, &data, length as usize).is_ok();
             drtioaux::send(0, &drtioaux::Packet::SubkernelAddDataReply { succeeded: succeeded })
@@ -592,7 +827,16 @@ fn process_aux_packet(
             id,
             run,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             let mut succeeded = kernel_manager.load(id).is_ok();
             // allow preloading a kernel with delayed run
             if run {
@@ -617,7 +861,16 @@ fn process_aux_packet(
             destination: _destination,
             succeeded,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             // received if local subkernel started another, remote subkernel
             kernel_manager.subkernel_load_run_reply(succeeded);
             Ok(())
@@ -628,25 +881,73 @@ fn process_aux_packet(
             with_exception,
             exception_src,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             kernel_manager.remote_subkernel_finished(id, with_exception, exception_src);
             Ok(())
         }
         drtioaux::Packet::SubkernelExceptionRequest {
+            source,
             destination: _destination,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
-            let mut data_slice: [u8; SAT_PAYLOAD_MAX_SIZE] = [0; SAT_PAYLOAD_MAX_SIZE];
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
+            let mut data_slice: [u8; MASTER_PAYLOAD_MAX_SIZE] = [0; MASTER_PAYLOAD_MAX_SIZE];
             let meta = kernel_manager.exception_get_slice(&mut data_slice);
-            drtioaux::send(
+            router.send(
-                0,
+                drtioaux::Packet::SubkernelException {
-                &drtioaux::Packet::SubkernelException {
+                    destination: source,
                     last: meta.status.is_last(),
                     length: meta.len,
                     data: data_slice,
                 },
+                _routing_table,
+                *rank,
+                *self_destination,
             )
         }
+        drtioaux::Packet::SubkernelException {
+            destination: _destination,
+            last,
+            length,
+            data,
+        } => {
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
+            kernel_manager.received_exception(
+                &data[..length as usize],
+                last,
+                router,
+                _routing_table,
+                *rank,
+                *self_destination,
+            );
+            Ok(())
+        }
         drtioaux::Packet::SubkernelMessage {
             source,
             destination: _destination,
@@ -655,7 +956,16 @@ fn process_aux_packet(
             length,
             data,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             kernel_manager.message_handle_incoming(status, id, length as usize, &data);
             router.send(
                 drtioaux::Packet::SubkernelMessageAck { destination: source },
@@ -667,7 +977,16 @@ fn process_aux_packet(
         drtioaux::Packet::SubkernelMessageAck {
             destination: _destination,
         } => {
-            forward!(_routing_table, _destination, *rank, _repeaters, &packet, timer);
+            forward!(
+                router,
+                _routing_table,
+                _destination,
+                *rank,
+                *self_destination,
+                _repeaters,
+                &packet,
+                timer
+            );
             if kernel_manager.message_ack_slice() {
                 let mut data_slice: [u8; MASTER_PAYLOAD_MAX_SIZE] = [0; MASTER_PAYLOAD_MAX_SIZE];
                 if let Some(meta) = kernel_manager.message_get_slice(&mut data_slice) {
@@ -920,6 +1239,28 @@ pub extern "C" fn main_core0() -> i32 {
     #[cfg(has_si549)]
     si549::helper_setup(&mut timer, &SI549_SETTINGS).expect("cannot initialize helper Si549");
 
+    let cfg = match Config::new() {
+        Ok(cfg) => cfg,
+        Err(err) => {
+            warn!("config initialization failed: {}", err);
+            Config::new_dummy()
+        }
+    };
+
+    if let Ok(spread_enable) = cfg.read_str("sed_spread_enable") {
+        match spread_enable.as_ref() {
+            "1" => toggle_sed_spread(1),
+            "0" => toggle_sed_spread(0),
+            _ => {
+                warn!("sed_spread_enable value not supported (only 1, 0 allowed), disabling by default");
+                toggle_sed_spread(0)
+            }
+        };
+    } else {
+        info!("SED spreading disabled by default");
+        toggle_sed_spread(0);
+    }
+
     #[cfg(has_drtio_routing)]
     let mut repeaters = [repeater::Repeater::default(); csr::DRTIOREP.len()];
     #[cfg(not(has_drtio_routing))]

src/satman/src/repeater.rs

@@ -208,10 +208,37 @@ impl Repeater {
         }
     }
 
-    pub fn aux_forward(&self, request: &drtioaux::Packet, timer: &mut GlobalTimer) -> Result<(), drtioaux::Error> {
+    pub fn aux_forward(
+        &self,
+        request: &drtioaux::Packet,
+        router: &mut Router,
+        routing_table: &drtio_routing::RoutingTable,
+        rank: u8,
+        self_destination: u8,
+        timer: &mut GlobalTimer,
+    ) -> Result<(), drtioaux::Error> {
         self.aux_send(request)?;
-        let reply = self.recv_aux_timeout(200, timer)?;
+        loop {
-        drtioaux::send(0, &reply).unwrap();
+            let reply = self.recv_aux_timeout(200, timer)?;
+            match reply {
+                // async/locally requested packets to be consumed or routed
+                // these may come while a packet would be forwarded
+                drtioaux::Packet::DmaPlaybackStatus { .. }
+                | drtioaux::Packet::SubkernelFinished { .. }
+                | drtioaux::Packet::SubkernelMessage { .. }
+                | drtioaux::Packet::SubkernelMessageAck { .. }
+                | drtioaux::Packet::SubkernelLoadRunReply { .. }
+                | drtioaux::Packet::SubkernelException { .. }
+                | drtioaux::Packet::DmaAddTraceReply { .. }
+                | drtioaux::Packet::DmaPlaybackReply { .. } => {
+                    router.route(reply, routing_table, rank, self_destination);
+                }
+                _ => {
+                    drtioaux::send(0, &reply).unwrap();
+                    break;
+                }
+            }
+        }
         Ok(())
     }
 

src/satman/src/routing.rs

@@ -4,7 +4,7 @@ use core::cmp::min;
 #[cfg(has_drtio_routing)]
 use libboard_artiq::pl::csr;
 use libboard_artiq::{drtio_routing, drtioaux,
-                     drtioaux_proto::{PayloadStatus, MASTER_PAYLOAD_MAX_SIZE, SAT_PAYLOAD_MAX_SIZE}};
+                     drtioaux_proto::{PayloadStatus, MASTER_PAYLOAD_MAX_SIZE}};
 
 pub struct SliceMeta {
     pub destination: u8,
@@ -57,7 +57,6 @@ impl Sliceable {
         self.data.extend(data);
     }
 
-    get_slice_fn!(get_slice_sat, SAT_PAYLOAD_MAX_SIZE);
     get_slice_fn!(get_slice_master, MASTER_PAYLOAD_MAX_SIZE);
 }
 

src/satman/src/subkernel.rs

@@ -11,7 +11,7 @@ use io::{Cursor, ProtoWrite};
 use ksupport::{eh_artiq, kernel, rpc};
 use libboard_artiq::{drtio_routing::RoutingTable,
                      drtioaux,
-                     drtioaux_proto::{PayloadStatus, MASTER_PAYLOAD_MAX_SIZE, SAT_PAYLOAD_MAX_SIZE},
+                     drtioaux_proto::{PayloadStatus, MASTER_PAYLOAD_MAX_SIZE},
                      pl::csr};
 use libboard_zynq::{time::Milliseconds, timer::GlobalTimer};
 use libcortex_a9::sync_channel::Receiver;
@@ -47,6 +47,9 @@ enum KernelState {
     DmaAwait {
         max_time: Milliseconds,
     },
+    SubkernelRetrievingException {
+        destination: u8,
+    },
 }
 
 #[derive(Debug)]
@@ -123,10 +126,11 @@ struct MessageManager {
 struct Session {
     id: u32,
     kernel_state: KernelState,
-    last_exception: Option<Sliceable>,
+    last_exception: Option<Sliceable>,   // exceptions raised locally
+    external_exception: Option<Vec<u8>>, // exceptions from sub-subkernels
     messages: MessageManager,
     source: u8, // which destination requested running the kernel
-    subkernels_finished: Vec<u32>,
+    subkernels_finished: Vec<(u32, Option<u8>)>,
 }
 
 impl Session {
@@ -135,6 +139,7 @@ impl Session {
             id: id,
             kernel_state: KernelState::Absent,
             last_exception: None,
+            external_exception: None,
             messages: MessageManager::new(),
             source: 0,
             subkernels_finished: Vec::new(),
@@ -410,9 +415,9 @@ impl<'a> Manager<'_> {
         }
     }
 
-    pub fn exception_get_slice(&mut self, data_slice: &mut [u8; SAT_PAYLOAD_MAX_SIZE]) -> SliceMeta {
+    pub fn exception_get_slice(&mut self, data_slice: &mut [u8; MASTER_PAYLOAD_MAX_SIZE]) -> SliceMeta {
         match self.session.last_exception.as_mut() {
-            Some(exception) => exception.get_slice_sat(data_slice),
+            Some(exception) => exception.get_slice_master(data_slice),
             None => SliceMeta {
                 destination: 0,
                 len: 0,
@@ -540,7 +545,7 @@ impl<'a> Manager<'_> {
             return;
         }
 
-        match self.process_external_messages(timer) {
+        match self.process_external_messages(router, routing_table, rank, destination, timer) {
             Ok(()) => (),
             Err(Error::AwaitingMessage) => return, // kernel still waiting, do not process kernel messages
             Err(Error::KernelException(exception)) => {
@@ -596,6 +601,41 @@ impl<'a> Manager<'_> {
         }
     }
 
+    fn check_finished_kernels(
+        &mut self,
+        id: u32,
+        router: &mut Router,
+        routing_table: &RoutingTable,
+        rank: u8,
+        self_destination: u8,
+    ) {
+        for (i, (status, exception_source)) in self.session.subkernels_finished.iter().enumerate() {
+            if *status == id {
+                if exception_source.is_none() {
+                    self.control.tx.send(kernel::Message::SubkernelAwaitFinishReply);
+                    self.session.kernel_state = KernelState::Running;
+                    self.session.subkernels_finished.swap_remove(i);
+                } else {
+                    let destination = exception_source.unwrap();
+                    self.session.external_exception = Some(Vec::new());
+                    self.session.kernel_state = KernelState::SubkernelRetrievingException {
+                        destination: destination,
+                    };
+                    router.route(
+                        drtioaux::Packet::SubkernelExceptionRequest {
+                            source: self_destination,
+                            destination: destination,
+                        },
+                        &routing_table,
+                        rank,
+                        self_destination,
+                    );
+                }
+                break;
+            }
+        }
+    }
+
     pub fn subkernel_load_run_reply(&mut self, succeeded: bool) {
         if self.session.kernel_state == KernelState::SubkernelAwaitLoad {
             self.control
@@ -608,16 +648,46 @@ impl<'a> Manager<'_> {
     }
 
     pub fn remote_subkernel_finished(&mut self, id: u32, with_exception: bool, exception_source: u8) {
-        if with_exception {
+        let exception_src = if with_exception { Some(exception_source) } else { None };
-            self.kernel_stop();
+        self.session.subkernels_finished.push((id, exception_src));
-            self.last_finished = Some(SubkernelFinished {
+    }
-                source: self.session.source,
+
-                id: self.session.id,
+    pub fn received_exception(
-                with_exception: true,
+        &mut self,
-                exception_source: exception_source,
+        exception_data: &[u8],
-            })
+        last: bool,
+        router: &mut Router,
+        routing_table: &RoutingTable,
+        rank: u8,
+        self_destination: u8,
+    ) {
+        if let KernelState::SubkernelRetrievingException { destination } = self.session.kernel_state {
+            self.session
+                .external_exception
+                .as_mut()
+                .unwrap()
+                .extend_from_slice(exception_data);
+            if last {
+                self.control
+                    .tx
+                    .send(kernel::Message::SubkernelError(kernel::SubkernelStatus::Exception(
+                        self.session.external_exception.take().unwrap(),
+                    )));
+                self.session.kernel_state = KernelState::Running;
+            } else {
+                /* fetch another slice */
+                router.route(
+                    drtioaux::Packet::SubkernelExceptionRequest {
+                        source: self_destination,
+                        destination: destination,
+                    },
+                    routing_table,
+                    rank,
+                    self_destination,
+                );
+            }
         } else {
-            self.session.subkernels_finished.push(id);
+            warn!("Received unsolicited exception data");
         }
     }
 
@@ -780,28 +850,35 @@ impl<'a> Manager<'_> {
         Ok(false)
     }
 
-    fn process_external_messages(&mut self, timer: &GlobalTimer) -> Result<(), Error> {
+    fn process_external_messages(
+        &mut self,
+        router: &mut Router,
+        routing_table: &RoutingTable,
+        rank: u8,
+        self_destination: u8,
+        timer: &GlobalTimer,
+    ) -> Result<(), Error> {
         match &self.session.kernel_state {
             KernelState::MsgAwait { max_time, id, tags } => {
                 if let Some(max_time) = *max_time {
                     if timer.get_time() > max_time {
-                        self.control.tx.send(kernel::Message::SubkernelMsgRecvReply {
+                        self.control
-                            status: kernel::SubkernelStatus::Timeout,
+                            .tx
-                            count: 0,
+                            .send(kernel::Message::SubkernelError(kernel::SubkernelStatus::Timeout));
-                        });
                         self.session.kernel_state = KernelState::Running;
                         return Ok(());
                     }
                 }
                 if let Some(message) = self.session.messages.get_incoming(*id) {
-                    self.control.tx.send(kernel::Message::SubkernelMsgRecvReply {
+                    self.control
-                        status: kernel::SubkernelStatus::NoError,
+                        .tx
-                        count: message.count,
+                        .send(kernel::Message::SubkernelMsgRecvReply { count: message.count });
-                    });
                     let tags = tags.clone();
                     self.session.kernel_state = KernelState::Running;
                     self.pass_message_to_kernel(&message, tags, timer)
                 } else {
+                    let id = *id;
+                    self.check_finished_kernels(id, router, routing_table, rank, self_destination);
                     Err(Error::AwaitingMessage)
                 }
             }
@@ -817,27 +894,18 @@ impl<'a> Manager<'_> {
             KernelState::SubkernelAwaitFinish { max_time, id } => {
                 if let Some(max_time) = *max_time {
                     if timer.get_time() > max_time {
-                        self.control.tx.send(kernel::Message::SubkernelAwaitFinishReply {
+                        self.control
-                            status: kernel::SubkernelStatus::Timeout,
+                            .tx
-                        });
+                            .send(kernel::Message::SubkernelError(kernel::SubkernelStatus::Timeout));
                         self.session.kernel_state = KernelState::Running;
                         return Ok(());
                     }
                 }
-                let mut i = 0;
+                let id = *id;
-                for status in &self.session.subkernels_finished {
+                self.check_finished_kernels(id, router, routing_table, rank, self_destination);
-                    if *status == *id {
-                        self.control.tx.send(kernel::Message::SubkernelAwaitFinishReply {
-                            status: kernel::SubkernelStatus::NoError,
-                        });
-                        self.session.kernel_state = KernelState::Running;
-                        self.session.subkernels_finished.swap_remove(i);
-                        break;
-                    }
-                    i += 1;
-                }
                 Ok(())
             }
+            KernelState::SubkernelRetrievingException { .. } => Err(Error::AwaitingMessage),
             KernelState::DmaAwait { max_time } | KernelState::DmaPendingAwait { max_time, .. } => {
                 if timer.get_time() > *max_time {
                     self.control.tx.send(kernel::Message::DmaAwaitRemoteReply {