命令提示符下的 nvcc cuda 不使用 gpu

Question

尝试使用 nvcc 从命令提示符运行 CUDA 程序，但 GPU 代码似乎没有按预期运行。完全相同的代码在 Visual Studio 上成功运行并输出预期的输出。

nvcc -arch=sm_60 -std=c++11 -o test.cu test.exe
test.exe

环境： 视窗 10, 英伟达 Quadro k4200, CUDA 10.2

源代码

#include <stdio.h>
#include <stdlib.h>
#include <vector>
#include <iostream>

/* this is the vector addition kernel. 
  :inputs: n -> Size of vector, integer
           a -> constant multiple, float
           x -> input 'vector', constant pointer to float
           y -> input and output 'vector', pointer to float  */
__global__ void saxpy(int n, float a, const float x[], float y[])
{
  int id = threadIdx.x + blockDim.x*blockIdx.x; /* Performing that for loop */ 
  // check to see if id is greater than size of array
  if(id < n){
     y[id] +=  a*x[id];
  } 
}

int main()
{
  int N = 256; 

  //create pointers and device
  float *d_x, *d_y; 

  const float a = 2.0f;

  //allocate and initializing memory on host
  std::vector<float> x(N, 1.f);
  std::vector<float> y(N, 1.f);

  //allocate our memory on GPU 
  cudaMalloc(&d_x, N*sizeof(float));
  cudaMalloc(&d_y, N*sizeof(float));

  //Memory Transfer! 
  cudaMemcpy(d_x, x.data(), N*sizeof(float), cudaMemcpyHostToDevice);
  cudaMemcpy(d_y, y.data(), N*sizeof(float), cudaMemcpyHostToDevice); 

  //Launch the Kernel! In this configuration there is 1 block with 256 threads
  //Use gridDim = int((N-1)/256) in general  
  saxpy<<<1, 256>>>(N, a, d_x, d_y);

  //Transfering Memory back! 
  cudaMemcpy(y.data(), d_y, N*sizeof(float), cudaMemcpyDeviceToHost);

  std::cout << y[0] << std::endl;

  cudaFree(d_x);
  cudaFree(d_y);

  return 0;
}

输出

1

预期输出

3

我尝试过的事情

当我第一次尝试使用 nvcc 进行编译时，出现了与此处讨论的相同的错误。

Cuda compilation error: class template has already been defined

所以我尝试了建议的解决方案 “现在：D:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.22.27905\bin\Hostx64\x64” 现在它编译并运行，但输出不符合预期。

Answer 1

“此外，-arch=sm_60 是 Quadro K4200 的不正确的拱形规范。它应该是 Robert Crovella 的 -arch=sm_30”