microsoft
Use the scalar MlasSgemm CopyPackB and TransposePackB implementation for RISCV
Add new define MLAS_TARGET_RISCV under _M_RISCV or __riscv. Add MLAS_TARGET_RISCV in check across MlasSgemmCopyPackB and MlasSgemmTransposePackB implementation to use 4 wide packing functions.
For RISCV, the MlasSgemmKernel is used which has packing wide of 4. The default MlasSgemmCopyPackB (which was under just !defined(MLAS_TARGET_WASM_SCALAR) chack) has packing width of 16, causing the tests to mismatch.
@microsoft-github-policy-service agree [company="{Imagination Technologies}"]
@microsoft-github-policy-service agree company="Imagination Technologies"
/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline
/azp run Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,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
/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline
/azp run Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,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
