Update on "Use c10 version of half/bfloat16 in executorch"

Accomplished by importing relevant files from c10 into
executorch/runtime/core/portable_type/c10, and then using `using` in
the top-level ExecuTorch headers. This approach should keep the
ExecuTorch build hermetic for embedded use cases. In the future, we
should add a CI job to ensure the c10 files stay identical to the
PyTorch ones.

Differential Revision: [D66106969](https://our.internmc.facebook.com/intern/diff/D66106969/)

[ghstack-poisoned]

Author: swolchok

.ci/docker/conda-env-ci.txt

@@ -1,2 +1,4 @@
 cmake=3.22.1
 ninja=1.10.2
+libuv
+pkg-config

.ci/scripts/setup-arm-baremetal-tools.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+# Copyright 2024 Arm Limited and/or its affiliates.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+# NB: This function could be used to install Arm dependencies
+# Setup arm example environment (including TOSA tools)
+git config --global user.email "[email protected]"
+git config --global user.name "Github Executorch"
+bash examples/arm/setup.sh --i-agree-to-the-contained-eula

.ci/scripts/setup-macos.sh

@@ -131,5 +131,9 @@ if [[ -z "${GITHUB_RUNNER:-}" ]]; then
 fi
 
 print_cmake_info
-install_executorch
+install_pytorch_and_domains
+# We build PyTorch from source here instead of using nightly. This allows CI to test against
+# the pinned commit from PyTorch
+install_executorch "use-pt-pinned-commit"
 build_executorch_runner "${BUILD_TOOL}"
+do_not_use_nightly_on_ci

.ci/scripts/utils.sh

@@ -40,6 +40,42 @@ install_pip_dependencies() {
   popd || return
 }
 
+install_domains() {
+  echo "Install torchvision and torchaudio"
+  pip install --no-use-pep517 --user "git+https://github.com/pytorch/audio.git@${TORCHAUDIO_VERSION}"
+  pip install --no-use-pep517 --user "git+https://github.com/pytorch/vision.git@${TORCHVISION_VERSION}"
+}
+
+install_pytorch_and_domains() {
+  pushd .ci/docker || return
+  TORCH_VERSION=$(cat ci_commit_pins/pytorch.txt)
+  popd || return
+
+  git clone https://github.com/pytorch/pytorch.git
+
+  # Fetch the target commit
+  pushd pytorch || return
+  git checkout "${TORCH_VERSION}"
+  git submodule update --init --recursive
+
+  export USE_DISTRIBUTED=1
+  # Then build and install PyTorch
+  python setup.py bdist_wheel
+  pip install "$(echo dist/*.whl)"
+
+  # Grab the pinned audio and vision commits from PyTorch
+  TORCHAUDIO_VERSION=$(cat .github/ci_commit_pins/audio.txt)
+  export TORCHAUDIO_VERSION
+  TORCHVISION_VERSION=$(cat .github/ci_commit_pins/vision.txt)
+  export TORCHVISION_VERSION
+
+  install_domains
+
+  popd || return
+  # Print sccache stats for debugging
+  sccache --show-stats || true
+}
+
 install_flatc_from_source() {
   # NB: This function could be used to install flatbuffer from source
   pushd third-party/flatbuffers || return
@@ -59,17 +95,6 @@ install_flatc_from_source() {
   popd || return
 }
 
-install_arm() {
-  # NB: This function could be used to install Arm dependencies
-  # Setup arm example environment (including TOSA tools)
-  git config --global user.email "[email protected]"
-  git config --global user.name "Github Executorch"
-  bash examples/arm/setup.sh --i-agree-to-the-contained-eula
-
-  # Test tosa_reference flow
-  source examples/arm/ethos-u-scratch/setup_path.sh
-}
-
 build_executorch_runner_buck2() {
   # Build executorch runtime with retry as this step is flaky on macos CI
   retry buck2 build //examples/portable/executor_runner:executor_runner

.github/workflows/pull.yml

@@ -354,13 +354,11 @@ jobs:
         EXECUTORCH_BUILD_ARM_BAREMETAL=ON \
         .ci/scripts/setup-linux.sh "${BUILD_TOOL}"
 
-        source .ci/scripts/utils.sh
         # Install Arm dependencies
-        install_arm
-
-        # Run pytest with coverage
-        pytest -c /dev/null -v -n auto --cov=./ --cov-report=xml backends/arm/test
+        .ci/scripts/setup-arm-baremetal-tools.sh
 
+        # Run pytest without simulator
+        backends/arm/test/test_arm_baremetal.sh test_pytest
 
   test-llama-runner-qnn-linux:
     name: test-llama-runner-qnn-linux

.github/workflows/trunk.yml

@@ -146,14 +146,15 @@ jobs:
         source .ci/scripts/utils.sh
         install_executorch
 
-        install_arm
+        .ci/scripts/setup-arm-baremetal-tools.sh
 
         # Increase number of files user can monitor to bypass buck failures.
         # Hopefully this is high enough for this setup.
         sudo sysctl fs.inotify.max_user_watches=1048576 # 1024 * 1024
 
         # Test ethos-u delegate examples with run.sh
-        PYTHON_EXECUTABLE=python bash examples/arm/run.sh examples/arm/ethos-u-scratch/
+        backends/arm/test/test_arm_baremetal.sh test_run_ethosu_fvp
+
 
   test-arm-reference-delegation:
     name: test-arm-reference-delegation
@@ -172,10 +173,10 @@ jobs:
         source .ci/scripts/utils.sh
         install_executorch
 
-        install_arm
+        .ci/scripts/setup-arm-baremetal-tools.sh
 
-        # Run arm unit tests
-        pytest -c /dev/null -v -n auto --cov=./ --cov-report=xml backends/arm/test
+        # Run arm unit tests using the simulator
+        backends/arm/test/test_arm_baremetal.sh test_pytest_ethosu_fvp
 
   test-coreml-delegate:
     name: test-coreml-delegate

CONTRIBUTING.md

@@ -197,7 +197,7 @@ If it's not clear how to add a test for your PR, take a look at the blame for
 the code you're modifying and find an author who has more context. Ask them
 for their help in the PR comments.
 
-TODO: Explain how to run tests locally without needing to push and wait for CI.
+The `test/run_oss_cpp_tests.sh` script will build and run C++ tests locally.
 
 ### Continuous Integration
 See https://hud.pytorch.org/hud/pytorch/executorch/main for the current state of

backends/arm/README.md

@@ -39,6 +39,28 @@ Other:
 - `third-party/` - Dependencies on other code - in particular the TOSA serialization_lib for compiling to TOSA and the ethos-u-core-driver for the bare-metal backend supporting Ethos-U
 - `test/` - Unit test and test support functions
 
+## Testing
+
+After a setup you can run unit tests with the test_arm_baremetal.sh script.
+
+To run the pytests suite run
+
+```
+backends/arm/test/test_arm_baremetal.sh test_pytest
+```
+
+To run the unit test suite with Corstone3x0 FVP simulator support use
+
+```
+backends/arm/test/test_arm_baremetal.sh test_pytest_ethosu_fvp
+```
+
+You can test to run some models with the run.sh flow
+
+```
+backends/arm/test/test_arm_baremetal.sh test_run_ethosu_fvp
+```
+
 ## Unit tests
 This is the structure of the test directory
 
@@ -51,6 +73,8 @@ test                            #  Root test folder
 ├── tester                      #  Arm Tester class
 ├── tosautil                    #  Utility functions for TOSA artifacts
 ├ common.py                     #  Common functions and definitions used by many tests
+├ setup_testing.sh              #  Script to prepare testing for using the Corstone 3x0 FVP
+├ test_arm_baremetal.sh         #  Help script to trigger testing
 ```
 
 Some example commands to run these tests follow. Run a single test:
@@ -59,6 +83,12 @@ Some example commands to run these tests follow. Run a single test:
 python -m unittest backends.arm.test.ops.test_add.TestSimpleAdd -k test_add2_tosa_BI
 ```
 
+or with pytest
+
+```
+pytest -c /dev/null -v -n auto backends/arm/test/ops/test_add.py -k test_add2_tosa_BI
+```
+
 Or all tests in "TestSimpleAdd":
 
 ```
@@ -71,6 +101,28 @@ Or discover and run many tests:
 python -m unittest discover -s backends/arm/test/ops/
 ```
 
+or with pytest
+
+```
+pytest -c /dev/null -v -n auto backends/arm/test/ops/
+```
+
+
+You can run tests using Corstone3x0 simulators to see how it would work on something more target like
+first you need to build and prepare some used target libs
+
+```
+examples/arm/run.sh --model_name=add --build_only
+backends/arm/test/setup_testing.sh
+```
+
+The you can run the tests with
+
+```
+pytest -c /dev/null -v -n auto backends/arm/test --arm_quantize_io --arm_run_corstoneFVP
+```
+
+
 ### A note on unit tests
 
 There are currently 3 ways we unit test our code.

backends/arm/_passes/annotate_decomposed_matmul.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Arm Limited and/or its affiliates.
+# Copyright 2024-2025 Arm Limited and/or its affiliates.
 # All rights reserved.
 #
 # This source code is licensed under the BSD-style license found in the
@@ -36,7 +36,6 @@ def call(self, graph_module: GraphModule) -> PassResult:
             itertools.chain.from_iterable(matmul_partitions.values())
         )
         matmul_targets = {
-            exir_ops.edge.aten.mm.default,
             exir_ops.edge.aten.bmm.default,
         }
         for partition in matmul_partitions:

backends/arm/_passes/arm_pass_manager.py

@@ -1,5 +1,5 @@
 # Copyright (c) Meta Platforms, Inc. and affiliates.
-# Copyright 2024 Arm Limited and/or its affiliates.
+# Copyright 2024-2025 Arm Limited and/or its affiliates.
 # All rights reserved.
 #
 # This source code is licensed under the BSD-style license found in the
@@ -45,6 +45,7 @@
 from executorch.backends.arm._passes.meandim_to_averagepool_pass import (
     ConvertMeanDimToAveragePool,
 )
+from executorch.backends.arm._passes.mm_to_bmm_pass import ConvertMmToBmmPass
 from executorch.backends.arm._passes.remove_clone_pass import RemoveClonePass
 from executorch.backends.arm._passes.scalars_to_attribute_pass import (
     ScalarsToAttributePass,
@@ -79,6 +80,7 @@ def transform_to_backend_pipeline(
         self.add_pass(ConvertMeanDimToAveragePool())
         self.add_pass(DecomposeMeanDimPass())
         self.add_pass(ConvertSplitToSlicePass())
+        self.add_pass(ConvertMmToBmmPass())
         # TODO MLETORCH-558
         self.add_pass(AnnotateDecomposedMatmulPass())
         self.add_pass(QuantizeFullArgument())
@@ -99,7 +101,6 @@ def transform_to_backend_pipeline(
                     exir_ops.edge.aten.hardtanh.default,
                     exir_ops.edge.aten.log.default,
                     exir_ops.edge.aten.max_pool2d.default,
-                    exir_ops.edge.aten.mm.default,
                     exir_ops.edge.aten.mul.Tensor,
                     exir_ops.edge.aten.permute_copy.default,
                     exir_ops.edge.aten.reciprocal.default,