cudaMemcpy分段错误

我已经被这个错误困扰了很长一段时间所以我决定在这里发布它 .

调用cudaMemcpy时发生此分段错误：

CurrentGrid->cdata[i] = new float[size];
cudaMemcpy(CurrentGrid->cdata[i], Grid_dev->cdata[i], size*sizeof(float),\
                cudaMemcpyDeviceToHost);

CurrentGrid 和 Grid_dev 分别指向主机和设备上的 grid 类对象，在此上下文中i = 0 . 类成员 cdata 是一个浮点类型指针数组 . 对于调试，在此cudaMemcpy调用之前，我打印出 Grid_Dev->cdata[i] 的每个元素的值， CurrentGrid->cdata[i] 和 Grid_dev->cdata[i] 的地址以及 size 的值，这些都看起来不错 . 但它仍然以"Segmentation fault (core dumped)"结束，这是唯一的错误消息 . cuda-memcheck只给了"process didn't terminate successfully" . 我目前无法使用cuda-gdb . 关于去哪儿的任何建议？

UPDATE ：现在看来我已经通过cudaMalloc解决了这个问题，设备上的另一个浮点指针A和cudaMemcpy的Grid_dev-> cdata [i]的值为A，然后是cudaMemcpy A来主机 . 所以上面写的代码段变成：

float * A;
cudaMalloc((void**)&A, sizeof(float));
...
...
cudaMemcpy(&A, &(Grid_dev->cdata[i]), sizeof(float *), cudaMemcpyDeviceToHost);    
CurrentGrid->cdata[i] = new float[size];
cudaMemcpy(CurrentGrid->cdata[i], A, size*sizeof(float), cudaMemcpyDeviceToHost);

我之所以这样做是因为valgrind出现了"invalid read of size 8"，我认为这是指 Grid_dev->cdata[i] . 我用gdb再次检查它，打印出 Grid_dev->cdata[i] 的值为NULL . 所以我想即使在这个cudaMemcpy调用中也无法直接取消引用设备指针 . 但为什么 ？根据thread底部的评论，我们应该能够在cudaMemcpy函数中取消引用设备指针 .

另外，我不知道cudaMalloc和cudaMemcpy如何工作的基本机制，但我认为cudaMalloc是一个指针，比如A，我们实际上指定这个指针指向设备上的某个地址 . 并且通过cudaMemcpy Grid_dev->cdata[i] 到A，如上面的修改代码，我们重新分配指针A指向数组 . 那么，当它是cudaMalloced时，我们不会失去A指向的先前地址的轨道吗？这会导致内存泄漏吗？如果是的话，我应该如何妥善解决这种情况？谢谢！

作为参考，我将完整函数的代码放在下面发生此错误的代码中 .

非常感谢！

__global__ void Print(grid *, int);
__global__ void Printcell(grid *, int);
void CopyDataToHost(param_t p, grid * CurrentGrid, grid * Grid_dev){

    cudaMemcpy(CurrentGrid, Grid_dev, sizeof(grid), cudaMemcpyDeviceToHost);
#if DEBUG_DEV
    cudaCheckErrors("cudaMemcpy1 error");
#endif
    printf("\nBefore copy cell data\n");
    Print<<<1,1>>>(Grid_dev, 0);            //Print out some Grid_dev information for 
    cudaDeviceSynchronize();                //debug 
    int NumberOfBaryonFields = CurrentGrid->ReturnNumberOfBaryonFields();
    int size = CurrentGrid->ReturnSize();
    int vsize = CurrentGrid->ReturnVSize();
    CurrentGrid->FieldType = NULL;
    CurrentGrid->FieldType = new int[NumberOfBaryonFields];
    printf("CurrentGrid size is %d\n", size);
    for( int i = 0; i < p.NumberOfFields; i++){
        CurrentGrid->cdata[i] = NULL;
        CurrentGrid->vdata[i] = NULL;
        CurrentGrid->cdata[i] = new float[size];
        CurrentGrid->vdata[i] = new float[vsize];

        Printcell<<<1,1>>>(Grid_dev, i);//Print out element value of Grid_dev->cdata[i]
        cudaDeviceSynchronize();        

        cudaMemcpy(CurrentGrid->cdata[i], Grid_dev->cdata[i], size*sizeof(float),\
                cudaMemcpyDeviceToHost);               //where error occurs
#if DEBUG_DEV
        cudaCheckErrors("cudaMemcpy2 error");
#endif
        printf("\nAfter copy cell data\n");
        Print<<<1,1>>>(Grid_dev, i);
        cudaDeviceSynchronize();
        cudaMemcpy(CurrentGrid->vdata[i], Grid_dev->vdata[i], vsize*sizeof(float),\
                cudaMemcpyDeviceToHost);
#if DEBUG_DEV
        cudaCheckErrors("cudaMemcpy3 error");
#endif
    }
    cudaMemcpy(CurrentGrid->FieldType, Grid_dev->FieldType,\
            NumberOfBaryonFields*sizeof(int), cudaMemcpyDeviceToHost);
#if DEBUG_DEV
    cudaCheckErrors("cudaMemcpy4 error");
#endif
}

编辑：这是来自valgrind的信息，我正试图追踪内存泄漏发生的位置 .

==19340== Warning: set address range perms: large range [0x800000000, 0xd00000000) (noaccess)
==19340== Warning: set address range perms: large range [0x200000000, 0x400000000) (noaccess)
==19340== Invalid read of size 8
==19340==    at 0x402C79: CopyDataToHost(param_t, grid*, grid*) (CheckDevice.cu:48)
==19340==    by 0x403646: CheckDevice(param_t, grid*, grid*) (CheckDevice.cu:186)
==19340==    by 0x40A6CD: main (Transport.cu:81)
==19340==  Address 0x2003000c0 is not stack'd, malloc'd or (recently) free'd
==19340== 
==19340== 
==19340== Process terminating with default action of signal 11 (SIGSEGV)
==19340==  Bad permissions for mapped region at address 0x2003000C0
==19340==    at 0x402C79: CopyDataToHost(param_t, grid*, grid*) (CheckDevice.cu:48)
==19340==    by 0x403646: CheckDevice(param_t, grid*, grid*) (CheckDevice.cu:186)
==19340==    by 0x40A6CD: main (Transport.cu:81)
==19340== 
==19340== HEAP SUMMARY:
==19340==     in use at exit: 2,611,365 bytes in 5,017 blocks
==19340==   total heap usage: 5,879 allocs, 862 frees, 4,332,278 bytes allocated
==19340== 
==19340== LEAK SUMMARY:
==19340==    definitely lost: 0 bytes in 0 blocks
==19340==    indirectly lost: 0 bytes in 0 blocks
==19340==      possibly lost: 37,416 bytes in 274 blocks
==19340==    still reachable: 2,573,949 bytes in 4,743 blocks
==19340==         suppressed: 0 bytes in 0 blocks
==19340== Rerun with --leak-check=full to see details of leaked memory
==19340== 
==19340== For counts of detected and suppressed errors, rerun with: -v
==19340== ERROR SUMMARY: 1 errors from 1 contexts (suppressed: 2 from 2)