1、使用lambda进行测试,求解x*x+y*y+z*z。新建test.cu文件
#include <thrust/copy.h>
#include <thrust/device_vector.h>
#include <thrust/functional.h>
#include <thrust/generate.h>
#include <thrust/host_vector.h>
#include <thrust/sort.h>
#include <thrust/transform.h>
#include <time.h>
#include <algorithm>
#include <vector>
int main(void) {
float x[4] = {1, 2, 3, 4};
float y[4] = {1, 1, 1, 1};
float z[4] = {2, 2, 3, 4};
thrust::device_vector<float> X(x, x + 4);
thrust::device_vector<float> Y(y, y + 4);
thrust::device_vector<float> Z(z, z + 4);
thrust::device_vector<float> sum(4,0);
thrust :: device_vector <int > H(4);
thrust::transform(X.begin(),X.end(),Y.begin(),sum.begin(),[=]__host__ __device__ (float x, float y) { return x*x+y*y;});
thrust::transform(Z.begin(),Z.end(),sum.begin(),sum.begin(),[=]__host__ __device__ (float x, float y) { return x*x+y;});
//求解x*x+y*y+z*z的大小,thrust的lambda
for (size_t i = 0; i < 4; i++)
std::cout << x[i] << " * " << x[i] << " + " << y[i] << " * " << y[i]<< " + " << z[i] << " * " << z[i]<<" = " << sum[i] << std::endl;
return 0;
}
2、新建编译文本
CMAKE_MINIMUM_REQUIRED(VERSION 3.5)
PROJECT(thrust_examples)
set(CMAKE_BUILD_TYPE Release)
find_package(CUDA)
include_directories(${CUDA_INCLUDE_DIRS})
message(STATUS "${CUDA_INCLUDE_DIRS}")
message(STATUS "${CUDA_LIBRARIES}")
set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS};--expt-extended-lambda")
cuda_add_executable(thrust_examples test.cu)
注意:一定要加上CUDA_NVCC_FLAGS中--expt-extended-lambda,否则编译出错