diff --git a/src/gemm.c b/src/gemm.c
index 648027f2..9e8b1d5d 100644
--- a/src/gemm.c
+++ b/src/gemm.c
@@ -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);