CUDA中使用多维数组

今天想起一个问题，看到的绝大多数CUDA代码都是使用的一维数组，是否可以在CUDA中使用一维数组，这是一个问题，想了各种问题，各种被77的错误状态码和段错误折磨，最后发现有一个cudaMallocManaged函数，这个函数可以很好的组织多维数组的多重指针的形式

，后来发现，这个问题之前在Stack Overflow中就有很好的解决。先贴一下我自己的代码实现：

#include "cuda_runtime.h"  
#include "device_launch_parameters.h"  
  
#include <stdio.h>  
const int arraySize = 5; 
cudaError_t addWithCuda(int *c, const int *a, const int *b, size_t size);  
  
__global__ void addKernel(int **c, const int *a, const int *b)  
{  
    int i = threadIdx.x;  
    if(i<arraySize)
        c[0][i] = a[i] + b[i];  
    else
        c[1][i-arraySize]= a[i-arraySize]+b[i-arraySize];
}  

int main()  
{  
 
    const int a[arraySize] = { 1, 2, 3, 4, 5 };  
    const int b[arraySize] = { 10, 20, 30, 40, 50 };  
    int c[arraySize] = { 0 };  
  
    // Add vectors in parallel.  
    cudaError_t cudaStatus = addWithCuda(c, a, b, arraySize);  
    if (cudaStatus != cudaSuccess) {  
        fprintf(stderr, "addWithCuda failed!");  
        return 1;  
    }  
  
    printf("{1,2,3,4,5} + {10,20,30,40,50} = {%d,%d,%d,%d,%d}
",  
        c[0], c[1], c[2], c[3], c[4]);  
  
    // cudaThreadExit must be called before exiting in order for profiling and  
    // tracing tools such as Nsight and Visual Profiler to show complete traces.  
    cudaStatus = cudaThreadExit();  
    if (cudaStatus != cudaSuccess) {  
        fprintf(stderr, "cudaThreadExit failed!");  
        return 1;  
    }  
  
    return 0;  
}  
  
// Helper function for using CUDA to add vectors in parallel.  
cudaError_t addWithCuda(int *c, const int *a, const int *b, size_t size)  
{  
    int *dev_a = 0;  
    int *dev_b = 0;  
    int *dev_c0;
    int **dev_c ;
    cudaError_t cudaStatus;  
  
    // Choose which GPU to run on, change this on a multi-GPU system.  
    cudaStatus = cudaSetDevice(0);  
    if (cudaStatus != cudaSuccess) {  
        fprintf(stderr, "cudaSetDevice failed!  Do you have a CUDA-capable GPU installed?");  
        goto Error;  
    }  
  
    // Allocate GPU buffers for three vectors (two input, one output)    
    cudaStatus  =  cudaMallocManaged(&dev_c, 2*sizeof(int*));
    if (cudaStatus != cudaSuccess) {  
        fprintf(stderr, "cudaMalloc failed!");  
        goto Error;  
    } 
    cudaStatus = cudaMalloc((void**)&(dev_c0), size * sizeof(int)*2);  
    if (cudaStatus != cudaSuccess) {  
        fprintf(stderr, "cudaMalloc failed!");  
        goto Error;  
    }  

    dev_c[0]=dev_c0;
    dev_c[1]=dev_c0+arraySize;
    cudaStatus = cudaMalloc((void**)&dev_a, size * sizeof(int));  
    if (cudaStatus != cudaSuccess) {  
        fprintf(stderr, "cudaMalloc failed!");  
        goto Error;  
    }  
  
    cudaStatus = cudaMalloc((void**)&dev_b, size * sizeof(int));  
    if (cudaStatus != cudaSuccess) {  
        fprintf(stderr, "cudaMalloc failed!");  
        goto Error;  
    }  
  
    // Copy input vectors from host memory to GPU buffers.  
    cudaStatus = cudaMemcpy(dev_a, a, size * sizeof(int), cudaMemcpyHostToDevice);  
    if (cudaStatus != cudaSuccess) {  
        fprintf(stderr, "cudaMemcpy failed!");  
        goto Error;  
    }  
  
    cudaStatus = cudaMemcpy(dev_b, b, size * sizeof(int), cudaMemcpyHostToDevice);  
    if (cudaStatus != cudaSuccess) {  
        fprintf(stderr, "cudaMemcpy failed!");  
        goto Error;  
    }  
  
    // Launch a kernel on the GPU with one thread for each element.  
    addKernel<<<1, size*2>>>(dev_c, dev_a, dev_b);  
  
    // cudaThreadSynchronize waits for the kernel to finish, and returns  
    // any errors encountered during the launch.  
    cudaStatus = cudaThreadSynchronize();  
    if (cudaStatus != cudaSuccess) {  
        fprintf(stderr, "cudaThreadSynchronize returned error code %d after launching addKernel!
", cudaStatus);  
        goto Error;  
    }  
  
    // Copy output vector from GPU buffer to host memory.  
    cudaStatus = cudaMemcpy(c, dev_c[1], size * sizeof(int), cudaMemcpyDeviceToHost);  
    if (cudaStatus != cudaSuccess) {  
        fprintf(stderr, "cudaMemcpy failed!");  
        goto Error;  
    }  
  
Error:  

    cudaFree(dev_a);  
    cudaFree(dev_b);  
      
    return cudaStatus;  
}  

在别人很好的代码下就不漏丑了，贴一下stack overflow的代码，非常直观易懂

//https://stackoverflow.com/questions/40388242/multidimensional-array-allocation-with-cuda-unified-memory-on-power-8
 
#include <iostream>
#include <assert.h>
 
template<typename T>
T**** create_4d_flat(int a, int b, int c, int d) {
    T *base;
    cudaError_t err = cudaMallocManaged(&base, a*b*c*d * sizeof(T));
    assert(err == cudaSuccess);
    T ****ary;
    err = cudaMallocManaged(&ary, (a + a * b + a * b*c) * sizeof(T*));
    assert(err == cudaSuccess);
    for (int i = 0; i < a; i++) {
        ary[i] = (T ***)((ary + a) + i * b);
        for (int j = 0; j < b; j++) {
            ary[i][j] = (T **)((ary + a + a * b) + i * b*c + j * c);
            for (int k = 0; k < c; k++)
                ary[i][j][k] = base + ((i*b + j)*c + k)*d;
        }
    }
    return ary;
}
 
template<typename T>
void free_4d_flat(T**** ary) {
    if (ary[0][0][0]) cudaFree(ary[0][0][0]);
    if (ary) cudaFree(ary);
}
 
 
template<typename T>
__global__ void fill(T**** data, int a, int b, int c, int d) {
    unsigned long long int val = 0;
    for (int i = 0; i < a; i++)
        for (int j = 0; j < b; j++)
            for (int k = 0; k < c; k++)
                for (int l = 0; l < d; l++)
                    data[i][j][k][l] = val++;
}
 
void report_gpu_mem()
{
    size_t free, total;
    cudaMemGetInfo(&free, &total);
    std::cout << "Free = " << free << " Total = " << total << std::endl;
}
 
int main() {
    report_gpu_mem();
 
    unsigned long long int ****data2;
    std::cout << "allocating..." << std::endl;
    data2 = create_4d_flat<unsigned long long int>(64, 63, 62, 5);
 
    report_gpu_mem();
 
    fill << <1, 1 >> > (data2, 64, 63, 62, 5);
    cudaError_t err = cudaDeviceSynchronize();
    assert(err == cudaSuccess);
 
    std::cout << "validating..." << std::endl;
    for (int i = 0; i < 64 * 63 * 62 * 5; i++)
        if (*(data2[0][0][0] + i) != i) { std::cout << "mismatch at " << i << " was " << *(data2[0][0][0] + i) << std::endl; return -1; }
    free_4d_flat(data2);
    return 0;
}