Direct Driver HAL

.github/workflows/ci-linux.yml

@@ -49,13 +49,10 @@ jobs:
           git remote add origin $REPO_ADDRESS
           git -c protocol.version=2 fetch --depth 1 origin $BRANCH_NAME
           git reset --hard FETCH_HEAD
-          git -c submodule."third_party/torch-mlir".update=none -c submodule."third_party/stablehlo".update=none -c submodule."src/runtime_src/core/common/aiebu".update=none submodule update --init --recursive --depth 1 --single-branch -j 10
-
-      - name: Install deps
-        run: |
-          dnf install -y almalinux-release-devel epel-release
-          yum remove -y openssl-devel zlib-devel || true
-          yum install -y protobuf-devel protobuf-compiler tmate
+          git -c submodule."third_party/torch-mlir".update=none \
+              -c submodule."third_party/stablehlo".update=none \
+              -c submodule."third_party/XRT".update=none \
+              submodule update --init --recursive --depth 1 --single-branch -j 10
 
       - name: Python deps
         run: |
@@ -69,6 +66,11 @@ jobs:
           key:  ${{ env.CACHE_KEY }}
           restore-keys: linux-build-test-cpp-
 
+      - name: Peano dep
+        run: |
+          bash build_tools/download_peano.sh
+          echo "PEANO_INSTALL_DIR=$PWD/llvm-aie" >> $GITHUB_ENV
+
       - name: Build packages
         run: |
           export cache_dir="${{ env.CACHE_DIR }}"
@@ -147,60 +149,54 @@ jobs:
           source .venv/bin/activate
           pip install -r tests/requirements.txt
 
+      - name: Query device info
+        run: |
+          source .venv/bin/activate
+          echo "aie-metadata"
+          python build_tools/ci/amdxdna_driver_utils/amdxdna_ioctl.py --aie-metadata
+          echo "aie-version"
+          python build_tools/ci/amdxdna_driver_utils/amdxdna_ioctl.py --aie-version
+          echo "XRT_LITE_N_CORE_ROWS=$(python build_tools/ci/amdxdna_driver_utils/amdxdna_ioctl.py --num-rows)" >> $GITHUB_ENV
+          echo "XRT_LITE_N_CORE_COLS=$(python build_tools/ci/amdxdna_driver_utils/amdxdna_ioctl.py --num-cols)" >> $GITHUB_ENV
+
       - name : E2E comparison of AIE to llvm-cpu
         run: |
           source .venv/bin/activate
-          source /opt/xilinx/xrt/setup.sh
           python build_tools/ci/cpu_comparison/run.py \
             test_aie_vs_cpu \
             $PWD/iree-install \
             $PWD/llvm-aie \
-            --xrt-dir /opt/xilinx/xrt \
             --vitis-dir /opt/Xilinx/Vitis/2024.2 \
-            --reset-npu-between-runs -v
+            --reset-npu-between-runs -v \
+            --xrt_lite_n_core_rows=$XRT_LITE_N_CORE_ROWS \
+            --xrt_lite_n_core_cols=$XRT_LITE_N_CORE_COLS
 
       - name: E2E correctness matmul test
         run: |
-          # Without this additional line an error like
-          #
-          # [XRT] ERROR: Failed to allocate host memory buffer (mmap(len=10616832, prot=3, flags=8193, offset=4294967296)
-          # failed (err=11): Resource temporarily unavailable), make sure host bank is enabled (see xbutil configure --host-mem)
-          # iree-amd-aie/runtime/src/iree-amd-aie/driver/xrt/direct_allocator.cc:179: RESOURCE_EXHAUSTED; could not allocate
-          # memory for buffer; while invoking C++ function matmul_test.generate_random_matrix; while calling import;
-          #
-          # might be observed when too much memory is allocated. This
-          # error was seen when running a bf16->f32 matmul with m=n=k=2304.
-          #
-          # This line was suggested at https://github.com/Xilinx/mlir-air/issues/566
-          #
-          # Note that this is only half of the fix. It is also necessary that
-          # the machine that CI is running on has permission to run this line.
-          #
-          # This permission can be adding by adding the line
-          # ```
-          # %github ALL=(ALL) NOPASSWD: /usr/bin/prlimit *
-          # ```
-          #
-          # to the file /etc/sudoers.d/github, which can be done by running
-          # ```
-          # sudo visudo -f /etc/sudoers.d/github
-          # ```
-          # on the github CI machine.
+          # https://stackoverflow.com/a/17567422
+          # shim_xdna::bo::map_drm_bo does an mmap with MAP_LOCKED
+          # which can fail if limit is to low
           sudo prlimit -lunlimited --pid $$
           source .venv/bin/activate
-          source /opt/xilinx/xrt/setup.sh
           bash build_tools/ci/run_matmul_test.sh \
             test_matmuls \
             iree-install \
             $PWD/llvm-aie \
-            /opt/xilinx/xrt \
             /opt/Xilinx/Vitis/2024.2
 
       - name: Python tests
         run: |
           source .venv/bin/activate
-          source /opt/xilinx/xrt/setup.sh
           pytest -v tests \
             --capture=tee-sys \
             --iree-install-dir=$PWD/iree-install \
-            --peano-install-dir=$PWD/llvm-aie
+            --peano-install-dir=$PWD/llvm-aie \
+            --xrt_lite_n_core_rows=$XRT_LITE_N_CORE_ROWS \
+            --xrt_lite_n_core_cols=$XRT_LITE_N_CORE_COLS
+
+      - name: XRT-LITE tests
+        run: |
+          DEVICE_TEST_DIR="$PWD/iree-install/device_tests"
+          for t in $(ls $DEVICE_TEST_DIR); do
+            $DEVICE_TEST_DIR/$t --xrt_lite_n_core_rows=$XRT_LITE_N_CORE_ROWS --xrt_lite_n_core_cols=$XRT_LITE_N_CORE_COLS
+          done

.github/workflows/ci-macos.yml

@@ -62,7 +62,10 @@ jobs:
           git remote add origin $REPO_ADDRESS
           git -c protocol.version=2 fetch --depth 1 origin $BRANCH_NAME
           git reset --hard FETCH_HEAD
-          git -c submodule."third_party/torch-mlir".update=none -c submodule."third_party/stablehlo".update=none -c submodule."src/runtime_src/core/common/aiebu".update=none submodule update --init --recursive --depth 1 --single-branch -j 10
+          git -c submodule."third_party/torch-mlir".update=none \
+              -c submodule."third_party/stablehlo".update=none \
+              -c submodule."third_party/XRT".update=none \
+              submodule update --init --recursive --depth 1 --single-branch -j 10
 
       - uses: actions/setup-python@v4
         with:

.github/workflows/ci-windows.yml

@@ -60,7 +60,10 @@ jobs:
           git remote add origin $REPO_ADDRESS
           git -c protocol.version=2 fetch --depth 1 origin $BRANCH_NAME
           git reset --hard FETCH_HEAD
-          git -c submodule."third_party/torch-mlir".update=none -c submodule."third_party/stablehlo".update=none -c submodule."src/runtime_src/core/common/aiebu".update=none submodule update --init --recursive --depth 1 --single-branch -j 10
+          git -c submodule."third_party/torch-mlir".update=none \
+              -c submodule."third_party/stablehlo".update=none \
+              -c submodule."src/runtime_src/core/common/aiebu".update=none \
+              submodule update --init --recursive --depth 1 --single-branch -j 10
 
       - name: Setup Cpp
         uses: aminya/setup-cpp@v1
@@ -87,14 +90,18 @@ jobs:
           key: ${{ env.CACHE_KEY }}
           restore-keys: windows-build-test-cpp-
 
+      - name: Peano dep
+        run: |
+          .\build_tools\download_peano.ps1
+          Add-Content -Path $env:GITHUB_ENV -Value "PEANO_INSTALL_DIR=$PWD\llvm-aie"
+
       - name: Build packages
         run: |
           $env:cache_dir = "${{ env.CACHE_DIR }}"
           $env:CCACHE_COMPILERCHECK = "string:$(clang-cl.exe --version)"
           .\build_tools\build_llvm.ps1
           # Remove-Item -Path "$pwd\llvm-build" -Force
           $env:llvm_install_dir = "$pwd\llvm-install"
-          echo $env:llvm_install_dir
           .\build_tools.\build_test_cpp.ps1
 
       - name: Create artifacts
@@ -170,6 +177,7 @@ jobs:
         shell: bash
         run: |
           source .venv/Scripts/activate
+          export DEVICE_HAL=xrt
           bash build_tools/ci/run_matmul_test.sh \
             /c/test_matmuls \
             $PWD/iree-install \
@@ -182,7 +190,8 @@ jobs:
           python build_tools/ci/cpu_comparison/run.py \
             /c/test_aie_vs_cpu \
             $PWD/iree-install \
-            $PWD/llvm-aie -v
+            $PWD/llvm-aie -v \
+            --device-hal=xrt
 
       - name: Python tests
         run: |
@@ -191,5 +200,6 @@ jobs:
           mkdir temp
           pytest tests -sv `
             --basetemp=$PWD\temp `
-            --iree-install-dir="$PWD/iree-install" `
-            --peano-install-dir="$PWD/llvm-aie"
+            --iree-install-dir="$PWD\iree-install" `
+            --peano-install-dir="$PWD\llvm-aie" `
+            --device-hal=xrt

README.md

@@ -4,12 +4,7 @@
 
 # AMD AIE Plugin for IREE
 
-This repository contains an early-phase IREE compiler and runtime plugin for interfacing the AMD AIE accelerator to IREE.
-
-## Architectural Overview
-
-![image](https://github.com/nod-ai/iree-amd-aie/assets/74956/3fa73139-5fdf-4658-86c3-0705352c4ea0)
-
+This repository contains an early-phase IREE compiler and runtime plugin for targeting AMD NPUs with IREE.
 
 ## Developer Setup
 
@@ -26,32 +21,30 @@ git clone --recursive git@github.com:nod-ai/iree-amd-aie.git
 git clone --recursive https://github.com/nod-ai/iree-amd-aie.git
 ```
 
-or if you want a faster checkout
-
+or, if you want a faster checkout,
 
 ```
 git \
   -c submodule."third_party/torch-mlir".update=none \
   -c submodule."third_party/stablehlo".update=none \
-  -c submodule."src/runtime_src/core/common/aiebu".update=none \
+  -c submodule."third_party/XRT".update=none \
   clone \
   --recursive \
   --shallow-submodules \
-  https://github.com/nod-ai/iree-amd-aie.git
+  git@github.com:nod-ai/iree-amd-aie.git # https://github.com/nod-ai/iree-amd-aie.git
 ```
 
-The above avoids cloning entire repo histories, and skips unused nested submodules.
+The above avoids cloning entire repo histories for submodules, and skips a few, currently, unused, 
+submodules that are nested in IREE.
 
 ## Building (along with IREE)
 
 ### Just show me the CMake
 
-To configure and build with XRT runtime enabled
-
 ```
 cd iree-amd-aie
 cmake \
-  -B $WHERE_YOU_WOULD_LIKE_TO_BUILD \
+  -B <WHERE_YOU_WOULD_LIKE_TO_BUILD> \
   -S third_party/iree \
   -DIREE_CMAKE_PLUGIN_PATHS=$PWD \
   -DIREE_BUILD_PYTHON_BINDINGS=ON \
@@ -62,20 +55,20 @@ cmake \
   -DIREE_TARGET_BACKEND_DEFAULTS=OFF \
   -DIREE_TARGET_BACKEND_LLVM_CPU=ON \
   -DIREE_BUILD_TESTS=ON \
-  -DIREE_EXTERNAL_HAL_DRIVERS=xrt \
-  -DCMAKE_INSTALL_PREFIX=$WHERE_YOU_WOULD_LIKE_TO_INSTALL
-cmake --build $WHERE_YOU_WOULD_LIKE_TO_BUILD
+  -DIREE_EXTERNAL_HAL_DRIVERS=xrt-lite \
+  -DCMAKE_INSTALL_PREFIX=<WHERE_YOU_WOULD_LIKE_TO_INSTALL>
+cmake --build <WHERE_YOU_WOULD_LIKE_TO_BUILD>
 ```
 
 ### Instructions
 
-The bare minimum configure command for IREE with the amd-aie plugin
+The bare minimum configure command for IREE with the amd-aie plugin 
 
 ```
 cmake \
-  -B $WHERE_YOU_WOULD_LIKE_TO_BUILD \
-  -S $IREE_REPO_SRC_DIR \
-  -DIREE_CMAKE_PLUGIN_PATHS=$IREE_AMD_AIE_REPO_SRC_DIR \
+  -B <WHERE_YOU_WOULD_LIKE_TO_BUILD> \
+  -S <IREE_REPO_SRC_DIR> \
+  -DIREE_CMAKE_PLUGIN_PATHS=<IREE_AMD_AIE_REPO_SRC_DIR> \
   -DIREE_BUILD_PYTHON_BINDINGS=ON
 ```
 
@@ -88,7 +81,8 @@ Very likely, you will want to use `ccache` and `lld` (or some other modern linke
   -DCMAKE_SHARED_LINKER_FLAGS="-fuse-ld=lld"
 ```
 
-If you don't plan on using any of IREE's frontends or backends/targets (e.g., you're doing work on this code base itself), you can opt-out of everything (except the `llvm-cpu` backend) with
+If you don't plan on using any of IREE's frontends or backends/targets (e.g., you're doing work on this code base itself),
+you can opt-out of everything (except the `llvm-cpu` backend) with
 
 ```
   -DIREE_INPUT_STABLEHLO=OFF \
@@ -111,75 +105,64 @@ If you're "bringing your own LLVM", i.e., you have a prebuilt/compiled distribut
   -DIREE_BUILD_BUNDLED_LLVM=OFF
 ```
 
-In this case you will need to supply `-DLLVM_EXTERNAL_LIT=$SOMEWHERE` (e.g., `pip install lit; SOMEWHERE=$(which lit)`).
+In this case you will need `lit` somewhere in your environment and you will need to add to CMake `-DLLVM_EXTERNAL_LIT=<SOMEWHERE>` 
+(e.g., `pip install lit; SOMEWHERE=$(which lit)`).
 
-Note, getting the right/matching build of LLVM, that works with IREE is tough (besides the commit hash, there are various flags to set).
-To enable adventurous users to avail themselves of `-DIREE_BUILD_BUNDLED_LLVM=OFF` we cache/store/save the LLVM distribution for every successful CI run.
-These can then be downloaded by checking the artifacts section of any recent CI run's [Summary page](https://github.com/nod-ai/iree-amd-aie/actions/runs/10713474448):
+See [Bringing your own LLVM](#bringing-your-own-llvm) below for more information on using prebuilt/compiled distributions of LLVM.
 
-<p align="center">
-<img src="https://github.com/user-attachments/assets/97fdeff2-41af-4a6d-a072-6ef0a1ec5695" width="500">
-</p>
+## Testing
 
-Lit tests specific to AIE can be run with something like 
+Lit tests (i.e., compiler tests) specific to AIE can be run with something like 
 
 ```
-cd $WHERE_YOU_WOULD_LIKE_TO_BUILD
-ctest -R amd-aie
+cd <WHERE_YOU_WOULD_LIKE_TO_BUILD>
+ctest -R amd-aie --output-on-failure -j 10
 ```
 
-Other tests which run on hardware and requiring XRT are in the `build_tools` subdirectory. 
-
-## Runtime driver setup
+(the `-j 10` runs `10` tests in parallel)
 
-To enable the runtime driver, you need to also enable the XRT HAL
+Other tests, which run on device, are in the `build_tools` subdirectory. 
+See [build_tools/ci/run_all_runtime_tests.sh](build_tools/ci/run_all_runtime_tests.sh) for an example script that shows how to run all the runtime tests.
 
-```
-  -DIREE_EXTERNAL_HAL_DRIVERS=xrt
-```
+## Pro-tips
 
-Additional IREE-specific flags are explained at [IREE's build instructions](https://iree.dev/building-from-source/getting-started/#quickstart-clone-and-build). To use Ninja instead of Make, and clang++ instead of g++, you can add
+### Bringing your own LLVM
 
+When using a pre-built distribution of LLVM, getting the right/matching build, that works with IREE, is tough (besides the commit hash, there are various flags to set).
+To enable adventurous users to avail themselves of `-DIREE_BUILD_BUNDLED_LLVM=OFF` we cache/store/save the LLVM distribution for every successful CI run.
+These can then be downloaded by checking the artifacts section of any recent CI run's [Summary page](https://github.com/nod-ai/iree-amd-aie/actions/runs/10713474448):
 
-```
-  -G Ninja \
-  -DCMAKE_CXX_COMPILER=clang++ \
-  -DCMAKE_C_COMPILER=clang
-```
+<p align="center">
+<img src="https://github.com/user-attachments/assets/97fdeff2-41af-4a6d-a072-6ef0a1ec5695" width="500">
+</p>
 
 
-### Ubuntu Dependencies
+### Debugging HAL
 
-XRT requires a number of packages. Here are the requirements for various operating systems
+You can turn on HAL API tracing by adding to CMake:
 
 ```
-apt install \
-  libcurl4-openssl-dev \
-  libdrm-dev \
-  libelf-dev \
-  libprotobuf-dev \
-  libudev-dev \
-  pkg-config \
-  protobuf-compiler \
-  python3-pybind11 \
-  systemtap-sdt-dev \
-  uuid-dev
+-DIREE_ENABLE_RUNTIME_TRACING=ON
+-DIREE_TRACING_PROVIDER=console
+// optional but recommended
+-DIREE_TRACING_CONSOLE_FLUSH=1
 ```
 
-### RH Based Deps
+This will you show you all the HAL APIs that have `IREE_TRACE_ZONE_BEGIN ... IREE_TRACE_ZONE_END` that are hit during a run/execution (of, e.g., `iree-run-module`).
 
-This is an incomplete list derived by adding what is needed to our development base manylinux (AlmaLinux 8) image.
+You can turn on VM tracing by adding to CMake:
 
 ```
-yum install \
-  libcurl-devel \
-  libdrm-devel \
-  libudev-devel \
-  libuuid-devel \
-  ncurses-devel \
-  pkgconfig \
-  protobuf-compiler \
-  protobuf-devel \
-  systemtap-sdt-devel \
-  uuid-devel
+-DIREE_VM_EXECUTION_TRACING_ENABLE=1
+-DIREE_VM_EXECUTION_TRACING_FORCE_ENABLE=1
+// optional
+-DIREE_VM_EXECUTION_TRACING_SRC_LOC_ENABLE=1
 ```
+
+This will show you all of the [VM dispatches](https://github.com/iree-org/iree/blob/0e8a5737dfe49a48a4e9c15ba7a7d24dd2fd7623/runtime/src/iree/vm/bytecode/dispatch.c#L661) that actually occur during a run/execution.
+Note, this is roughly equivalent to [passing](https://github.com/nod-ai/iree-amd-aie/blob/737092791dc2428ad71bc172f69804c583b0f60e/build_tools/ci/run_matmul_test.sh#L420) `--compile-to=vm` to `iree-compile`.
+
+## Architectural overview (out of date)
+
+![image](https://github.com/nod-ai/iree-amd-aie/assets/74956/3fa73139-5fdf-4658-86c3-0705352c4ea0)
+