NASP/cuda-samples
47
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2025-07-01 12:00:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update transpose for code format check

Browse Source
This commit is contained in:
shawnz 2025-05-19 17:38:42 +08:00
parent 107f3f537f
commit 5987a9e9fa
1 changed files with 5 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
Samples/6_Performance/transpose/transpose.cu
View File

@ -597,17 +597,16 @@ int main(int argc, char **argv)
1, 1,
TILE_DIM * BLOCK_ROWS); TILE_DIM * BLOCK_ROWS);
// Reset d_odata to zero before starting the next loop iteration to avoid // Reset d_odata to zero before starting the next loop iteration to avoid
// carrying over results from previous kernels. Without this reset, residual // carrying over results from previous kernels. Without this reset, residual
// data from a prior kernel (e.g., 'copy') could make a subsequent // data from a prior kernel (e.g., 'copy') could make a subsequent
// kernel (e.g., 'copySharedMem') appear correct even if it performs no work, // kernel (e.g., 'copySharedMem') appear correct even if it performs no work,
// leading to false positives in compareData. // leading to false positives in compareData.
for (int i = 0; i < (size_x * size_y); ++i) { for (int i = 0; i < (size_x * size_y); ++i) {
h_odata[i] = 0; h_odata[i] = 0;
} }
// copy host data to device // copy host data to device
checkCudaErrors( checkCudaErrors(cudaMemcpy(d_odata, h_odata, mem_size, cudaMemcpyHostToDevice));
cudaMemcpy(d_odata, h_odata, mem_size, cudaMemcpyHostToDevice));
} }
// cleanup // cleanup