NASP/cuda-samples
85
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2026-10-25 22:28:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

Transpose: Change TILE_DIM to 32 to fix bank conflicts

Browse Source 
Fixes #175
This commit is contained in:
Jonathan Bentz
2025-02-20 17:46:44 -06:00
committed by GitHub
parent 8d564d5e3a
commit efb46383e0
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Samples/6_Performance/transpose/transpose.cu
View File

@@ -53,7 +53,7 @@ const char *sSDKsample = "Transpose";
// TILE_DIM/BLOCK_ROWS elements. TILE_DIM must be an integral multiple of
// BLOCK_ROWS
#define TILE_DIM 16
#define TILE_DIM 32
#define BLOCK_ROWS 16
// This sample assumes that MATRIX_SIZE_X = MATRIX_SIZE_Y