diff --git a/README.md b/README.md index 202f180..b775722 100644 --- a/README.md +++ b/README.md @@ -22,8 +22,9 @@ GFLOPs at matrix size 4092x4092: | 8: Avoid Bank Conflicts (Offset) | 11646.9 | 78.7% | | 7: Avoid Bank Conflicts (Linearize) | 11923.9 | 80.6% | | 6: Vectorized Mem Access | 12088.9 | 81.7% | -| 9: Autotuning | 12717.4 | 86.0% | -| 0: cuBLAS | 14792.5 | 100.0% | +| 9: Autotuning | 12715.3 | 85.9% | +| 10: Warptiling | 12828.0 | 86.7% | +| 0: cuBLAS | 14797.8 | 100.0% | ## Setup diff --git a/gen_benchmark_results.sh b/gen_benchmark_results.sh index e30cbb0..3839d2e 100755 --- a/gen_benchmark_results.sh +++ b/gen_benchmark_results.sh @@ -8,7 +8,7 @@ set -euo pipefail mkdir -p benchmark_results -for kernel in {0..9}; do +for kernel in {0..10}; do echo "" ./build/sgemm $kernel | tee "benchmark_results/${kernel}_output.txt" sleep 2