Fix: add back cudaDeviceSynchronize

This commit is contained in:
2026-05-28 14:28:24 +00:00
parent fb8af865f4
commit f94693fdc2

View File

@@ -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);