Add test and benchmark for explicit dot GEMM

ROCm · Sep 24, 2024 · f6209e7 · f6209e7
1 parent 96b3d37
commit f6209e7
Show file tree

Hide file tree

Showing 2 changed files with 442 additions and 21 deletions.
diff --git a/.github/workflows/amd_perf_kernel_Integration_tests.yml b/.github/workflows/amd_perf_kernel_Integration_tests.yml
@@ -128,8 +128,10 @@ jobs:
           pytest -vvv ./python/perf-kernels/flash-attention.py
           pytest -vvvv ./python/perf-kernels/softmax.py
           pytest -vvv ./python/perf-kernels/rmsnorm.py
+          pytest -vvv ./python/perf-kernels/multreduce_matmul_kernel.py
       - name: Run Perf Kernels Benchmark
         run: |
           python ./python/perf-kernels/flash-attention.py
           python ./python/perf-kernels/softmax.py
           python ./python/perf-kernels/rmsnorm.py
+          python ./python/perf-kernels/multreduce_matmul_kernel.py bench