Fix: add back cudaDeviceSynchronize
This commit is contained in:
@@ -190,6 +190,7 @@ int main() {
|
||||
|
||||
cudaError_t launch_err = cudaGetLastError();
|
||||
if (launch_err != cudaSuccess) { printf("LAUNCH ERROR: %s\n", cudaGetErrorString(launch_err)); return 1; }
|
||||
cudaError_t err = cudaDeviceSynchronize();
|
||||
if (err != cudaSuccess) { printf("CUDA ERROR: %s\n", cudaGetErrorString(err)); return 1; }
|
||||
|
||||
cudaMemcpy(h_o, d_o, HD*sizeof(bf16_t), cudaMemcpyDeviceToHost);
|
||||
|
||||
Reference in New Issue
Block a user