我目前正在试图从我的代码中删除繁琐的cudaMallocHost/cudaFreeHost部分。为此,我愿意只使用std::vector,但我绝对需要底层内存必须是固定的cuda内存类型。
但是,我使用thrust库中的thrust::system::cuda::experimental::pinned_allocator<>时遇到了奇怪的行为:
在我的设置中,这将给出:
但是,我使用thrust库中的thrust::system::cuda::experimental::pinned_allocator<>时遇到了奇怪的行为:
//STL
#include <iostream>
#include <string>
#include <vector>
#include <algorithm>
//CUDA
#include <cuda_runtime.h>
#include <thrust/device_vector.h>
#include <thrust/transform.h>
#include <thrust/system/cuda/experimental/pinned_allocator.h>
#define SIZE 4
#define INITVAL 2
#define ENDVAL 4
//Compile using nvcc ./main.cu -o test -std=c++11
int main( int argc, char* argv[] )
{
// init host
std::vector<float,thrust::system::cuda::experimental::pinned_allocator<float> > hostVec(SIZE);
std::fill(hostVec.begin(),hostVec.end(),INITVAL);
//Init device
thrust::device_vector<float> thrustVec(hostVec.size());
//Copy
thrust::copy(hostVec.begin(), hostVec.end(), thrustVec.begin());
//std::cout << "Dereferencing values of the device, values should be "<< INITVAL << std::endl;
std::for_each(thrustVec.begin(),thrustVec.end(),[](float in){ std::cout <<"val is "<<in<<std::endl;} );
std::cout << "------------------------" << std::endl;
//Do Stuff
thrust::transform( thrustVec.begin(), thrustVec.end(), thrust::make_constant_iterator(2), thrustVec.begin(), thrust::multiplies<float>() );
//std::cout << "Dereferencing values of the device, values should now be "<< ENDVAL << std::endl;
std::for_each(thrustVec.begin(),thrustVec.end(),[](float in){ std::cout <<"val is "<<in<<std::endl;} );
std::cout << "------------------------" << std::endl;
//Copy back
thrust::copy(thrustVec.begin(), thrustVec.end(), hostVec.begin());
//Synchronize
//cudaDeviceSynchronize(); //makes the weird behaviour to go away
//Check result
//std::cout << "Dereferencing values on the host, values should now be "<< ENDVAL << std::endl;//Also makes the weird behaviour to go away
std::for_each(hostVec.begin(),hostVec.end(),[](float in){ std::cout <<"val is "<<in<<std::endl;} );
return EXIT_SUCCESS;
}
在我的设置中,这将给出:
val is 2
val is 2
val is 2
val is 2
------------------------
val is 4
val is 4
val is 4
val is 4
------------------------
val is 2
val is 4
val is 4
val is 4
为什么从设备到主机的复制似乎失败了?但是Nvvp显示出正确值的完美时序图。
顺便说一下,我使用的是7.5包中的NVCC/cuda/thrust和GCC (GCC) 4.8.5以及TitanX显卡。
非常感谢您的帮助。