Update to cudaDeviceSynchronize()

This commit is contained in:
Edward H 2019-04-02 15:01:45 -05:00 committed by GitHub
parent 61c9d02ec4
commit 9b7afaca07
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -229,7 +229,7 @@ void time_gpu(int TA, int TB, int m, int k, int n)
clock_t start = clock(), end;
for(i = 0; i<iter; ++i){
gemm_gpu(TA,TB,m,n,k,1,a_cl,lda,b_cl,ldb,1,c_cl,n);
cudaThreadSynchronize();
cudaDeviceSynchronize();
}
double flop = ((double)m)*n*(2.*k + 2.)*iter;
double gflop = flop/pow(10., 9);