我正在研究基于Visual Studio 2008的CUDA.你能告诉我如何使语法高亮显示在.cu文件中吗?
我对__shfl_down和__shfl_down_sync感到困惑,他们给出了不同的结果.
__global__ void shufledown1(double* a, double *b,double *c, int N)
{
double temp = 2.0;
__syncthreads();
for (int offset = 32/2; offset > 0; offset /= 2){
temp+=__shfl_down(temp, offset,32);
}
printf("%d %f %d \n",threadIdx.x ,temp,blockDim.x * gridDim.x);
}
__global__ void shufledown2(double* a, double *b,double *c, int N)
{
double temp = 2.0;
__syncthreads();
for (int offset = 32/2; offset > 0; offset /= 2){
temp+=__shfl_down_sync(temp, offset,32)
}
printf("%d %f %d \n",threadIdx.x ,temp,blockDim.x * gridDim.x);
}
Run Code Online (Sandbox Code Playgroud)
第一个给出:
0 64.000000 64
''''' …Run Code Online (Sandbox Code Playgroud)