-
kevinchenkai
#include <stdio.h> #include "cuda_runtime.h" __global__ void helloFromGPU() { printf("hello from GPU\n"); } int main(void) { float *dx; cudaMalloc(&dx, 1<<4*sizeof(float)); printf("hello from cpu.\n"); helloFromGPU<<<1, 10>>>(); cudaDeviceSynchronize(); }
同步下就可以了