根据NVIDIA,这是最快的减少内核:
template <unsigned int blockSize>
__device__ void warpReduce(volatile int *sdata, unsigned int tid) {
if (blockSize >= 64) sdata[tid] += sdata[tid + 32];
if (blockSize >= 32) sdata[tid] += sdata[tid + 16];
if (blockSize >= 16) sdata[tid] += sdata[tid + 8];
if (blockSize >= 8) sdata[tid] += sdata[tid + 4];
if (blockSize >= 4) sdata[tid] += sdata[tid + 2];
if (blockSize >= 2) sdata[tid] += sdata[tid + 1];
}
template <unsigned int blockSize>
__global__ void reduce6(int *g_idata, int …