NASP/cuda-samples
35
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2024-11-24 16:49:18 +08:00
Code Issues Packages Projects Releases Wiki Activity

update sample bf16TensorCoreGemm to add explicit casting

Browse Source
This commit is contained in:
Rutwik Choughule 2021-11-01 13:22:44 +05:30
parent 1f76a2d110
commit 01789304f0
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/bf16TensorCoreGemm/bf16TensorCoreGemm.cu
View File

@ -184,13 +184,13 @@ __host__ void init_host_matrices(__nv_bfloat16 *a, __nv_bfloat16 *b, float *c)
{ {
for (int i = 0; i < M_GLOBAL; i++) { for (int i = 0; i < M_GLOBAL; i++) {
for (int j = 0; j < K_GLOBAL; j++) { for (int j = 0; j < K_GLOBAL; j++) {
a[i*K_GLOBAL+j] = (__nv_bfloat16)(rand() % 3); a[i*K_GLOBAL+j] = (__nv_bfloat16)(float)(rand() % 3);
} }
} }
for (int i = 0; i < N_GLOBAL; i++) { for (int i = 0; i < N_GLOBAL; i++) {
for (int j = 0; j < K_GLOBAL; j++) { for (int j = 0; j < K_GLOBAL; j++) {
b[i*K_GLOBAL+j] = (__nv_bfloat16)(rand() % 3); b[i*K_GLOBAL+j] = (__nv_bfloat16)(float)(rand() % 3);
} }
} }