[GEMM] Reduce env

Signed-off-by: Whitney Tsang <[email protected]>

Author: whitneywhtsang

.github/workflows/triton-benchmarks.yml

@@ -132,26 +132,6 @@ jobs:
           cd benchmarks
           python setup.py install
 
-      - name: Run Triton Softmax kernel benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'fused_softmax.py') }}
-        run: |
-          cd benchmarks/triton_kernels_benchmark
-          python fused_softmax.py --reports $REPORTS
-          source ../../scripts/capture-hw-details.sh
-          python ../../scripts/build_report.py $REPORTS/softmax-performance.csv $REPORTS/softmax-triton-report.csv --benchmark softmax --compiler triton --param_cols "N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
-          python ../../scripts/build_report.py $REPORTS/softmax-performance.csv $REPORTS/softmax-xetla-report.csv --benchmark softmax --compiler xetla --param_cols "N" --tflops_col XeTLA-TFlops --hbm_col "XeTLA-GB/s" --tag $TAG
-
-      - name: Run Triton GEMM kernel benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_benchmark.py') }}
-        run: |
-          cd benchmarks/triton_kernels_benchmark
-          python gemm_benchmark.py --reports $REPORTS
-          mv $REPORTS/matmul-performance.csv $REPORTS/matmul-performance-base.csv
-
-          source ../../scripts/capture-hw-details.sh
-          python ../../scripts/build_report.py $REPORTS/matmul-performance-base.csv $REPORTS/gemm-triton-report.csv --benchmark gemm --compiler triton --param_cols "B,M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
-          python ../../scripts/build_report.py $REPORTS/matmul-performance-base.csv $REPORTS/gemm-xetla-report.csv --benchmark gemm --compiler xetla --param_cols "B,M,K,N" --tflops_col XeTLA-TFlops --hbm_col "XeTLA-GB/s" --tag $TAG
-
       - name: Run Triton GEMM kernel benchmark - default path
         if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_benchmark.py_default') }}
         run: |
@@ -182,117 +162,61 @@ jobs:
           TAG="${TAG}-adv"
           python ../../scripts/build_report.py $REPORTS/matmul-performance-adv-path.csv $REPORTS/gemm-triton-advanced-report.csv --benchmark gemm --compiler triton --param_cols "B,M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
 
-      - name: Run Triton GEMM (A@B^t) kernel benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_benchmark.py_abt') }}
-        run: |
-          cd benchmarks/triton_kernels_benchmark
-          TRANSPOSE_B=1 python gemm_benchmark.py --reports $REPORTS
-          mv $REPORTS/matmul-performance.csv $REPORTS/matmul-performance-bt.csv
-          source ../../scripts/capture-hw-details.sh
-
-          python ../../scripts/build_report.py $REPORTS/matmul-performance-bt.csv $REPORTS/gemm-bt-triton-report.csv --benchmark gemm-bt --compiler triton --param_cols "B,M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
-          python ../../scripts/build_report.py $REPORTS/matmul-performance-bt.csv $REPORTS/gemm-bt-onednn-report.csv --benchmark gemm-bt --compiler onednn --param_cols "B,M,K,N" --tflops_col onednn-TFlops --hbm_col "onednn-GB/s" --tag $TAG
-
-      - name: Run Triton GEMM (A^t@B) kernel benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_benchmark.py_atb') }}
-        run: |
-          cd benchmarks/triton_kernels_benchmark
-          TRANSPOSE_A=1 python gemm_benchmark.py --reports $REPORTS
-          mv $REPORTS/matmul-performance.csv $REPORTS/matmul-performance-at.csv
-          source ../../scripts/capture-hw-details.sh
-
-          python ../../scripts/build_report.py $REPORTS/matmul-performance-at.csv $REPORTS/gemm-at-triton-report.csv --benchmark gemm-at --compiler triton --param_cols "B,M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
-          python ../../scripts/build_report.py $REPORTS/matmul-performance-at.csv $REPORTS/gemm-at-onednn-report.csv --benchmark gemm-at --compiler onednn --param_cols "B,M,K,N" --tflops_col onednn-TFlops --hbm_col "onednn-GB/s" --tag $TAG
-
-      - name: Run Triton GEMM (stream-k) kernel benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_streamk_benchmark.py') }}
-        run: |
-          cd benchmarks/triton_kernels_benchmark
-          python gemm_streamk_benchmark.py --reports $REPORTS
-          source ../../scripts/capture-hw-details.sh
-          python ../../scripts/build_report.py $REPORTS/matmul-streamk-performance.csv $REPORTS/gemm-streamk-triton-report.csv --benchmark gemm-streamk --compiler triton --param_cols "M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
-
-      - name: Run Triton GEMM (split-k) kernel benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_splitk_benchmark.py') }}
-        run: |
-          cd benchmarks/triton_kernels_benchmark
-          python gemm_splitk_benchmark.py --reports $REPORTS
-          source ../../scripts/capture-hw-details.sh
-          python ../../scripts/build_report.py $REPORTS/matmul-splitk-performance.csv $REPORTS/gemm-splitk-triton-report.csv --benchmark gemm-splitk --compiler triton --param_cols "M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
-
-      - name: Run Triton GEMM + PreOp (exp) kernel benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_preop_exp_benchmark.py') }}
-        run: |
-          cd benchmarks/triton_kernels_benchmark
-          python gemm_preop_exp_benchmark.py --reports $REPORTS
-          source ../../scripts/capture-hw-details.sh
-          python ../../scripts/build_report.py $REPORTS/matmul-performance-preop-exp.csv $REPORTS/gemm-preop-exp-triton-report.csv --benchmark gemm-preop-exp --compiler triton --param_cols "B,M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
-
-      - name: Run Triton GEMM + PostOp (Gelu) kernel benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_postop_gelu_benchmark.py') }}
+      - name: Run Triton GEMM kernel benchmark - default path (remove DisableLoopUnroll)
+        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_benchmark.py_default') }}
         run: |
           cd benchmarks/triton_kernels_benchmark
-          python gemm_postop_gelu_benchmark.py --reports $REPORTS
-          source ../../scripts/capture-hw-details.sh
-          python ../../scripts/build_report.py $REPORTS/matmul-performance-postop-gelu.csv $REPORTS/gemm-postop-gelu-triton-report.csv --benchmark gemm-postop-gelu --compiler triton --param_cols "B,M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
+          # Default path:
+          TRITON_INTEL_ADVANCED_PATH=0 \
+          IGC_VISAOptions=" -enableBCR -nolocalra" \
+          python gemm_benchmark.py --reports $REPORTS
+          mv $REPORTS/matmul-performance.csv $REPORTS/matmul-performance-default-path.csv
 
-      - name: Run Triton GEMM + PostOp (add matrix) kernel benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_postop_addmatrix_benchmark.py') }}
-        run: |
-          cd benchmarks/triton_kernels_benchmark
-          python gemm_postop_addmatrix_benchmark.py --reports $REPORTS
           source ../../scripts/capture-hw-details.sh
-          python ../../scripts/build_report.py $REPORTS/matmul-performance-postop-addmatrix.csv $REPORTS/gemm-postop-addmatrix-triton-report.csv --benchmark gemm-postop-addmatrix --compiler triton --param_cols "B,M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
+          TAG="${TAG}-dflt"
+          python ../../scripts/build_report.py $REPORTS/matmul-performance-default-path.csv $REPORTS/gemm-triton-default-report.csv --benchmark gemm --compiler triton --param_cols "B,M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
 
-      - name: Run Triton FA kernel benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'flash_attention_fwd_benchmark.py') }}
+      - name: Run Triton GEMM kernel benchmark - advanced path (remove DisableLoopUnroll)
+        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_benchmark.py_advanced') }}
         run: |
           cd benchmarks/triton_kernels_benchmark
-          python flash_attention_fwd_benchmark.py --reports $REPORTS
+          # Advanced path:
+          TRITON_INTEL_ADVANCED_PATH=1 \
+          IGC_VISAOptions=" -enableBCR -nolocalra" \
+          python gemm_benchmark.py --reports $REPORTS
+          mv $REPORTS/matmul-performance.csv $REPORTS/matmul-performance-adv-path.csv
 
           source ../../scripts/capture-hw-details.sh
-          python ../../scripts/build_report.py $REPORTS/attn-performance.csv $REPORTS/attn-triton-report.csv --benchmark attn --compiler triton --param_cols "Z,H,N_CTX,D_HEAD,CAUSAL" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
-          python ../../scripts/build_report.py $REPORTS/attn-performance.csv $REPORTS/attn-xetla-report.csv --benchmark attn --compiler xetla --param_cols "Z,H,N_CTX,D_HEAD,CAUSAL" --tflops_col XeTLA-TFlops --hbm_col "XeTLA-GB/s" --tag $TAG
+          TAG="${TAG}-adv"
+          python ../../scripts/build_report.py $REPORTS/matmul-performance-adv-path.csv $REPORTS/gemm-triton-advanced-report.csv --benchmark gemm --compiler triton --param_cols "B,M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
 
-      - name: Run Triton FA kernel benchmark - default path
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmark || '[]'), 'flash_attention_fwd_benchmark.py_default') }}
+      - name: Run Triton GEMM kernel benchmark - default path (remove VISAOptions)
+        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_benchmark.py_default') }}
         run: |
           cd benchmarks/triton_kernels_benchmark
+          # Default path:
           TRITON_INTEL_ADVANCED_PATH=0 \
-          TRITON_INTEL_ENABLE_ADDRESS_PAYLOAD_OPT=1 \
-          IGC_VISAOptions=" -enableBCR" \
-          python flash_attention_fwd_benchmark.py --reports $REPORTS
+          IGC_DisableLoopUnroll=1 \
+          python gemm_benchmark.py --reports $REPORTS
+          mv $REPORTS/matmul-performance.csv $REPORTS/matmul-performance-default-path.csv
 
-          TAG="${TAG}-dflt"
           source ../../scripts/capture-hw-details.sh
-          python ../../scripts/build_report.py $REPORTS/attn-performance.csv $REPORTS/attn-triton-default-report.csv --benchmark attn --compiler triton --param_cols "Z,H,N_CTX,D_HEAD,CAUSAL" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
+          TAG="${TAG}-dflt"
+          python ../../scripts/build_report.py $REPORTS/matmul-performance-default-path.csv $REPORTS/gemm-triton-default-report.csv --benchmark gemm --compiler triton --param_cols "B,M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
 
-      - name: Run Triton FA kernel benchmark - advanced path
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'flash_attention_fwd_benchmark.py_advanced') }}
+      - name: Run Triton GEMM kernel benchmark - advanced path (remove VISAOptions)
+        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'gemm_benchmark.py_advanced') }}
         run: |
           cd benchmarks/triton_kernels_benchmark
+          # Advanced path:
           TRITON_INTEL_ADVANCED_PATH=1 \
-          TRITON_INTEL_ENABLE_ADDRESS_PAYLOAD_OPT=1 \
-          IGC_VISAOptions=" -enableBCR" \
-          python flash_attention_fwd_benchmark.py --reports $REPORTS
-
-          TAG="${TAG}-adv"
-          source ../../scripts/capture-hw-details.sh
-          python ../../scripts/build_report.py $REPORTS/attn-performance.csv $REPORTS/attn-triton-advanced-report.csv --benchmark attn --compiler triton --param_cols "Z,H,N_CTX,D_HEAD,CAUSAL" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
+          IGC_DisableLoopUnroll=1 \
+          python gemm_benchmark.py --reports $REPORTS
+          mv $REPORTS/matmul-performance.csv $REPORTS/matmul-performance-adv-path.csv
 
-      - name: Run Prefix Sums kernel benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'prefix_sums.py') }}
-        run: |
-          cd benchmarks/triton_kernels_benchmark
-          python prefix_sums.py --reports $REPORTS
           source ../../scripts/capture-hw-details.sh
-          python ../../scripts/build_report.py $REPORTS/prefix-sums.csv $REPORTS/prefix_sums-triton-report.csv --benchmark prefix_sums --compiler triton --param_cols "N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
-
-      - name: Run micro benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() && !contains(fromJson(inputs.skip_benchmarks || '[]'), 'micro_benchmarks') }}
-        run: |
-          cd benchmarks/micro_benchmarks
-          python run_benchmarks.py --reports $REPORTS
+          TAG="${TAG}-adv"
+          python ../../scripts/build_report.py $REPORTS/matmul-performance-adv-path.csv $REPORTS/gemm-triton-advanced-report.csv --benchmark gemm --compiler triton --param_cols "B,M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
 
       - name: Save pip cache
         if: ${{ steps.pip-cache.outputs.status == 'miss' }}