我想在CUDA程序中添加CUB库,请问要怎么做?
环境:Win10+VS2013+CUDA8.0
CUB库文档:http://nvlabs.github.io/cub/
文档中仅说明了使用nvcc编译时的方法,
例如nvcc -arch=sm_XX example_block_radix_sort.cu -I../.. -lcudart -O3
但是我想知道怎么在VS项目中加入CUB库
使用CUB库的例子程序:
#include <cub/cub.cuh>
#include <stdio.h>
#define nTPB 32
#define ELEMS_PER_THREAD 1
// Block-sorting CUDA kernel (nTPB threads each owning ELEMS_PER THREAD integers)
__global__ void BlockSortKernel()
{
__shared__ int my_val[nTPB*ELEMS_PER_THREAD];
using namespace cub;
// Specialize BlockRadixSort collective types
typedef BlockRadixSort<int, nTPB, ELEMS_PER_THREAD> my_block_sort;
// Allocate shared memory for collectives
__shared__ typename my_block_sort::TempStorage sort_temp_stg;
// need to extend synthetic data for ELEMS_PER_THREAD > 1
my_val[threadIdx.x*ELEMS_PER_THREAD] = (threadIdx.x + 5)%nTPB; // synth data
__syncthreads();
printf("thread %d data = %d\n", threadIdx.x, my_val[threadIdx.x*ELEMS_PER_THREAD]);
// Collectively sort the keys
my_block_sort(sort_temp_stg).Sort(*static_cast<int(*)[ELEMS_PER_THREAD]>(static_cast<void*>(my_val+(threadIdx.x*ELEMS_PER_THREAD))));
__syncthreads();
printf("thread %d sorted data = %d\n", threadIdx.x, my_val[threadIdx.x*ELEMS_PER_THREAD]);
}
int main(){
BlockSortKernel<<<1,nTPB>>>();
cudaDeviceSynchronize();
}