lukasplevac/cuda-samples
1
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2025-04-11 02:32:12 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge fb9f77575a08918a682d7eb0781c6e5f1d4f0bf3 into f3b7c41ad6202902290d2bbd16428455b3ee375a

Browse Source
This commit is contained in:
Tailing Yuan 2025-02-24 13:38:18 +08:00 committed by GitHub
commit 72265778c8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Samples/3_CUDA_Features/bf16TensorCoreGemm/bf16TensorCoreGemm.cu
View File

@ -592,8 +592,8 @@ __global__ void simple_wmma_bf16gemm(__nv_bfloat16 *a, __nv_bfloat16 *b, float *
int aCol = i;
int aRow = warpM * M;
int bCol = i;
int bRow = warpN * N;
int bCol = warpN * N;
int bRow = i;
// Bounds checking
if (aRow < m_ld && aCol < k_ld && bRow < k_ld && bCol < n_ld) {