diff --git a/README.md b/README.md index 67e6d300..e6c0f923 100644 --- a/README.md +++ b/README.md @@ -87,7 +87,7 @@ Starting from CUTLASS 3.0, CUTLASS removed support for the following: # Performance -

+

CUTLASS primitives are very efficient. When used to construct device-wide GEMM kernels, they exhibit peak performance comparable to cuBLAS for scalar GEMM diff --git a/media/images/cutlass-3.1-gemm-peak-performance.png b/media/images/cutlass-3.1-gemm-peak-performance.png new file mode 100644 index 00000000..b2f550a2 Binary files /dev/null and b/media/images/cutlass-3.1-gemm-peak-performance.png differ