wip

Python/numbapig.py

@@ -112,4 +112,17 @@ mflops = NPTS*5.0/(1.0e6*(end_time-start_time))
 print("both with CUDA kernel reduction:")
 print("   NPTS = %d, pi = %f"%(NPTS,pi[0]))
 print("   time = %f, estimated MFlops = %f"%(end_time-start_time,mflops))
+#
+# both with CUDA kernel reduction and transfer
+#
+start_time = time.time()
+init[grid_size,block_size](arr)
+CUDA_reduce(arr,NPTS)
+CUDA_result(arr,result)
+pi = result.copy_to_host()
+end_time = time.time()
+mflops = NPTS*5.0/(1.0e6*(end_time-start_time))
+print("both with CUDA kernel reduction and transfer:")
+print("   NPTS = %d, pi = %f"%(NPTS,pi[0]))
+print("   time = %f, estimated MFlops = %f"%(end_time-start_time,mflops))