c++ cuda拷贝内存

https://developer.nvidia.com/zh-cn/blog/how-overlap-data-transfers-cuda-cc/

分批拷贝：

https://github.com/NVIDIA-developer-blog/code-samples/blob/master/series/cuda-cpp/overlap-data-transfers/async.cu

  

   

    

     

    
    

     
 float *a, *d_a;
     
    
   

    

     

    
    

     
  checkCuda( cudaMallocHost((void**)&a, bytes) );      // host pinned
     
    
   

    

     

    
    

     
  checkCuda( cudaMalloc((void**)&d_a, bytes) ); // device
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      for (int i = 0; i < nStreams; ++i) {
     
    
   

    

     

    
    

     
  int offset = i * streamSize;
     
    
   

    

     

    
    

     
  cudaMemcpyAsync(&d_a[offset], &a[offset],
     
    
   

    

     

    
    

     

                        streamBytes, cudaMemcpyHostToDevice, cudaMemcpyHostToDevice, stream[i]);
     
    
   

    

     

    
    

     

      }
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      for (int i = 0; i < nStreams; ++i) {
     
    
   

    

     

    
    

     
  int offset = i * streamSize;
     
    
   

    

     

    
    

     

        kernel<<<streamSize/blockSize, blockSize, 0, stream[i]>>>(d_a, offset);
     
    
   

    

     

    
    

     

      }
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      for (int i = 0; i < nStreams; ++i) {
     
    
   

    

     

    
    

     
  int offset = i * streamSize;
     
    
   

    

     

    
    

     
  cudaMemcpyAsync(&a[offset], &d_a[offset],
     
    
   

    

     

    
    

     

                        streamBytes, cudaMemcpyDeviceToHost, cudaMemcpyDeviceToHost, stream[i]);
     
    
   

    

     

    
    

     

      }
     
    
  
 

文章来源: blog.csdn.net，作者：AI视觉网奇，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/jacke121/article/details/121879290