Closed joviliast closed 3 months ago
Support WMMA in ConvertTritonGPUToLLVMPass is in progress for now. Here are auxiliary PRs: https://github.com/ROCmSoftwarePlatform/triton/pull/435 https://github.com/ROCmSoftwarePlatform/triton/pull/436
working branch: https://github.com/joviliast/triton/tree/wmma-convertions
WMMA is partially enabled in draft PR: https://github.com/ROCmSoftwarePlatform/triton/pull/481
Performance results on working branch using WMMA instructions:
Unfortunately, couldn't wait for results without WMMA to compare. fused-attention-tflops.txt
fused-attention mismatches for now
All the works are moved to the upstream for now. Please check PRs:
https://github.com/openai/triton/pull/3112 Introduce WMMA layout attr https://github.com/openai/triton/pull/3170 Emit Indices for WMMA https://github.com/openai/triton/pull/3171 Support SharedToDotOperandWMMA https://github.com/openai/triton/pull/3199 Convert WMMA dot op to LLVM
fused-attention mismatches for now
Fused attention is fixed here https://github.com/joviliast/triton/tree/wmma-convertions
All required PRs were merged to the upstream: https://github.com/openai/triton Swizzling is not working for now. Fix in progress,
Here is highlevel tasks for WMMA enabling for GEMM:
This issue includes https://github.com/ROCmSoftwarePlatform/triton/issues/250.