WebGPU JSEP: Make shader code not depend on input broadcasting patterns #22536
Conversation
This PR adds inputs broadcasting information into the cache key of MatMul shaders, which currently impacts the shader code. This PR fixes the results for MatMul nodes with identical input ranks but different broadcasting patterns.
|
PR description edited, previous:
|
|
/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline |
|
/azp run Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,onnxruntime-binary-size-checks-ci-pipeline,Big Models,Linux Android Emulator QNN CI Pipeline |
|
/azp run Android CI Pipeline,iOS CI Pipeline,ONNX Runtime React Native CI Pipeline,CoreML CI Pipeline,Linux DNNL CI Pipeline,Linux MIGraphX CI Pipeline,Linux ROCm CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
2 similar comments
|
Azure Pipelines successfully started running 1 pipeline(s). |
|
Azure Pipelines successfully started running 1 pipeline(s). |
js/web/lib/wasm/jsep/webgpu/ops/3rd-party/matmul_packed_webgpu.ts
Outdated
Show resolved
Hide resolved
Done. |
|
/azp run ONNX Runtime Web CI Pipeline,Windows GPU CI Pipeline,Linux Android Emulator QNN CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
|
/azp run Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,Windows ARM64 QNN CI Pipeline,Windows CPU CI Pipeline |
|
Azure Pipelines could not run because the pipeline triggers exclude this branch/path. |
|
/azp run Windows GPU TensorRT CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,Windows x64 QNN CI Pipeline,Big Models |
|
/azp run Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
|
Azure Pipelines could not run because the pipeline triggers exclude this branch/path. |
|
lint not happy: |
|
The issue comes from merging, fixed in the latest commit. Please take a look, thanks! |
|
/azp run ONNX Runtime Web CI Pipeline,Windows GPU CI Pipeline,Linux Android Emulator QNN CI Pipeline |
|
/azp run Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,Windows ARM64 QNN CI Pipeline,Windows CPU CI Pipeline |
|
/azp run Windows GPU TensorRT CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,Windows x64 QNN CI Pipeline,Big Models |
|
Azure Pipelines successfully started running 1 pipeline(s). |
|
Azure Pipelines could not run because the pipeline triggers exclude this branch/path. |
|
/azp run Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
|
Azure Pipelines could not run because the pipeline triggers exclude this branch/path. |
…ns (microsoft#22536) This PR make MatMul shaders not depend on inputs broadcasting pattern, but only depend on input ranks and their shape provided in uniform. This change fix the issue that currently shaders code are different for different broadcasting, but have identical cache key and results in wrong cache hit.
…ns (#22536) This PR make MatMul shaders not depend on inputs broadcasting pattern, but only depend on input ranks and their shape provided in uniform. This change fix the issue that currently shaders code are different for different broadcasting, but have identical cache key and results in wrong cache hit.
…ns (microsoft#22536) This PR make MatMul shaders not depend on inputs broadcasting pattern, but only depend on input ranks and their shape provided in uniform. This change fix the issue that currently shaders code are different for different broadcasting, but have identical cache key and results in wrong cache hit.
…ns (microsoft#22536) This PR make MatMul shaders not depend on inputs broadcasting pattern, but only depend on input ranks and their shape provided in uniform. This change fix the issue that currently shaders code are different for different broadcasting, but have identical cache key and results in wrong cache hit.
…ns (microsoft#22536) This PR make MatMul shaders not depend on inputs broadcasting pattern, but only depend on input ranks and their shape provided in uniform. This change fix the issue that currently shaders code are different for different broadcasting, but have identical cache key and results in wrong cache hit.
This PR make MatMul shaders not depend on inputs broadcasting pattern, but only depend on input ranks and their shape provided in uniform. This change fix the issue that currently shaders code are different for different broadcasting, but have identical cache key and results in wrong cache hit.