From 9354bfd7c1e18499fedfbde5eef8c35f88ee8796 Mon Sep 17 00:00:00 2001 From: zkyue <51477259+zkyue@users.noreply.github.com> Date: Tue, 20 May 2025 10:53:15 +0800 Subject: [PATCH] Keep the documentation consistent with the sgemm_1.cu code. (#2285) * Keep the documentation consistent with the sgemm_1.cu code. * fix typo --------- Co-authored-by: zky --- media/docs/cpp/cute/0x_gemm_tutorial.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/media/docs/cpp/cute/0x_gemm_tutorial.md b/media/docs/cpp/cute/0x_gemm_tutorial.md index 38e57e4e..462cf848 100644 --- a/media/docs/cpp/cute/0x_gemm_tutorial.md +++ b/media/docs/cpp/cute/0x_gemm_tutorial.md @@ -206,8 +206,8 @@ With the static smem layouts, the `gemm_device` kernel can allocate the required ```cpp // Shared memory buffers - __shared__ TA smemA[cosize_v]; - __shared__ TB smemB[cosize_v]; + __shared__ TA smemA[cosize_v]; + __shared__ TB smemB[cosize_v]; Tensor sA = make_tensor(make_smem_ptr(smemA), sA_layout); // (BLK_M,BLK_K) Tensor sB = make_tensor(make_smem_ptr(smemB), sB_layout); // (BLK_N,BLK_K) ```