// Build, test, or develop the Cortex-M (CMSIS-NN) backend. Use when working on backends/cortex_m/, running Cortex-M tests, or exporting models for Cortex-M targets.
| name | cortex-m |
| description | Build, test, or develop the Cortex-M (CMSIS-NN) backend. Use when working on backends/cortex_m/, running Cortex-M tests, or exporting models for Cortex-M targets. |
Not a delegate backend — no partitioner. Custom ops and graph passes replace ATen quantized ops with CMSIS-NN equivalents at the graph level.
Uses standard PT2E quantization (prepare_pt2e / convert_pt2e), then CortexMPassManager rewrites quantized ops to cortex_m:: equivalents.
from executorch.backends.cortex_m.quantizer.quantizer import CortexMQuantizer
from executorch.backends.cortex_m.passes.cortex_m_pass_manager import CortexMPassManager
from torch.export import export
from torchao.quantization.pt2e.quantize_pt2e import convert_pt2e, prepare_pt2e
from executorch.exir import to_edge_transform_and_lower, EdgeCompileConfig
quantizer = CortexMQuantizer()
captured = export(model, example_inputs).module()
prepared = prepare_pt2e(captured, quantizer)
prepared(*example_inputs) # calibration
quantized = convert_pt2e(prepared)
exported = export(quantized, example_inputs)
edge = to_edge_transform_and_lower(
exported,
compile_config=EdgeCompileConfig(_check_ir_validity=False),
)
edge._edge_programs["forward"] = CortexMPassManager(
edge.exported_program(), CortexMPassManager.pass_list
).transform()
et_program = edge.to_executorch()
In tests, CortexMTester wraps this pipeline:
from executorch.backends.cortex_m.test.tester import CortexMTester
tester = CortexMTester(model, example_inputs)
tester.quantize().export().to_edge().run_passes().to_executorch()
| File | Purpose |
|---|---|
backends/cortex_m/quantizer/quantizer.py | CortexMQuantizer — quantizes model for CMSIS-NN |
backends/cortex_m/passes/cortex_m_pass_manager.py | CortexMPassManager — rewrites ATen ops → cortex_m:: ops |
backends/cortex_m/test/tester.py | CortexMTester — test harness with test_dialect() and test_implementation() |
backends/cortex_m/ops/operators.py | Python op definitions and reference implementations (cortex_m:: namespace) |
backends/cortex_m/ops/operators.yaml | C++ kernel registration schemas (used by build system) |
C++ kernels calling CMSIS-NN APIs live under backends/cortex_m/ops/.
Toolchain setup (required for test_implementation tests):
./examples/arm/setup.sh --i-agree-to-the-contained-eula
source ./examples/arm/arm-scratch/setup_path.sh
Run all tests:
source ./examples/arm/arm-scratch/setup_path.sh
pytest backends/cortex_m/test/
test_dialect_* tests verify graph correctness (pure Python, no toolchain needed).
test_implementation_* tests verify numerical accuracy on the Corstone-300 FVP (requires toolchain on PATH).
Baremetal build:
backends/cortex_m/test/build_test_runner.sh
operators.pybackends/cortex_m/ops/ calling CMSIS-NN APIs.out kernel in operators.yamlcortex_m:: opCortexMTester.test_dialect() (graph correctness) and test_implementation() (numerical accuracy on FVP)Build, test, or develop the QNN (Qualcomm AI Engine Direct) backend. Use when working on backends/qualcomm/, building QNN (use backends/qualcomm/scripts/build.sh), adding new ops or passes, running QNN delegate tests, or exporting models for Qualcomm HTP/GPU targets. Also exposes a Buck-vs-CMake parity workflow — invoke as `/qualcomm buck-fix`, `/qualcomm buck-cmake fix`, `/qualcomm buck-parity`, or any user request to fix `test-qnn-buck-build-linux` CI failures or check buck/cmake drift in backends/qualcomm/.
Build and configure ExecuTorch as a Zephyr RTOS module for embedded boards. Use when setting up a Zephyr workspace with ET, adding board support (overlays, confs, memory layout), building with west, or debugging linker memory overflow.
Search the ExecuTorch tribal knowledge base covering QNN, XNNPACK, Vulkan, CoreML, Arm, and Cadence backends, quantization recipes, export pitfalls, runtime errors, and SoC compatibility. Use when debugging ExecuTorch errors, choosing quantization configs, checking backend op support, or answering questions about Qualcomm HTP / Snapdragon / Apple Neural Engine behavior.
Build ExecuTorch from source — Python package, C++ runtime, runners, cross-compilation, and backend-specific builds. Use when compiling anything in the ExecuTorch repo, diagnosing build failures, or setting up platform-specific builds.
Analyze and reduce ExecuTorch binary size. Use when investigating binary size, running size tests, or optimizing the runtime for size-constrained deployments.
Export a PyTorch model to .pte format for ExecuTorch. Use when converting models, lowering to edge, or generating .pte files.