diff --git a/examples/47_ampere_gemm_universal_streamk/ampere_gemm_universal_streamk.cu b/examples/47_ampere_gemm_universal_streamk/ampere_gemm_universal_streamk.cu index 717ae346..fe25f509 100644 --- a/examples/47_ampere_gemm_universal_streamk/ampere_gemm_universal_streamk.cu +++ b/examples/47_ampere_gemm_universal_streamk/ampere_gemm_universal_streamk.cu @@ -34,7 +34,7 @@ "classic data-parallel" and "Split-K" decompositions. For more details regarding the Stream-K method, see "Stream-K: Work-centric Parallel Decomposition - for Dense Matrix-Matrix Multiplication on the GPU" + for Dense Matrix-Matrix Multiplication on the GPU" (https://arxiv.org/abs/2301.03598) Requires NVIDIA Ampere or newer device (SM80+).