mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2025-04-10 18:22:11 +01:00
Merge fb9f77575a08918a682d7eb0781c6e5f1d4f0bf3 into 3e8f91d1a116060d3fedfe856f3721db970de030
This commit is contained in:
commit
9a15c3d631
@ -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) {
|
||||
|
Loading…
x
Reference in New Issue
Block a user