Geek asks and answers

Submitting 2D Array to Cuda Core

I'm having trouble understanding how to send a 2D array to Cuda. I have a program that parses a large file with 30 data points on each line. I read about 10 rows at a time, and then create a matrix for each row and elements (so in my example of 10 rows with 30 data points it will be int list[10][30];My goal is to send this array to my core and each block processes the row (I got this to work perfectly in normal C, but Cuda was a bit more complicated).

Here is what I have been doing so far, but no luck (note: sizeofbucket = rows and sizeOfBucketsHoldings = elements in a row ... I know that I have to win the reward for the names of the odd variables):

    int list[sizeOfBuckets][sizeOfBucketsHoldings]; //this is created at the start of the file and I can confirmed its filled with the correct data
#define sizeOfBuckets 10 //size of buckets before sending to process list
#define sizeOfBucketsHoldings  30
    //Cuda part
                //define device variables
                int *dev_current_list[sizeOfBuckets][sizeOfBucketsHoldings];
                //time to malloc the 2D array on device
                size_t pitch;
                cudaMallocPitch((int**)&dev_current_list,  (size_t *)&pitch, sizeOfBucketsHoldings * sizeof(int), sizeOfBuckets);

                //copy data from host to device
                cudaMemcpy2D( dev_current_list, pitch, list, sizeOfBuckets * sizeof(int), sizeOfBuckets * sizeof(int), sizeOfBucketsHoldings * sizeof(int),cudaMemcpyHostToDevice );

                process_list<<<count,1>>> (sizeOfBuckets, sizeOfBucketsHoldings, dev_current_list, pitch);
                //free memory of device
                cudaFree( dev_current_list );


    __global__ void process_list(int sizeOfBuckets, int sizeOfBucketsHoldings, int *current_list, int pitch) {
        int tid = blockIdx.x;
        for (int r = 0; r < sizeOfBuckets; ++r) {
            int* row = (int*)((char*)current_list + r * pitch);
            for (int c = 0; c < sizeOfBucketsHoldings; ++c) {
                 int element = row[c];
            }
        }

The error I get is:

main.cu(266): error: argument of type "int *(*)[30]" is incompatible with parameter of type "int *"
1 error detected in the compilation of "/tmp/tmpxft_00003f32_00000000-4_main.cpp1.ii".

266 - process_list<<<count,1>>> (count, countListItem, dev_current_list, pitch); , , int *, ? C- int current_list[num_of_rows][num_items_in_row], , Cuda.

. , (sizeOfBuckets), (sizeOfBucketHoldings). , , cudamalloc cudaMemcpy, , MallocPitch 2dcopy ( cuda by example), , ( CUDA_C, . 22, ). ? , ?

: , ( ). :

__global__ void process_list(int sizeOfBuckets, int sizeOfBucketsHoldings, int *current_list, size_t pitch, int *total) {
    //TODO: we need to flip the list as well
    int tid = blockIdx.x;
    for (int c = 0; c < sizeOfBucketsHoldings; ++c) {
        total[tid] = total + current_list[tid][c];
    }
}

, :

int *dev_total;
cudaMalloc( (void**)&dev_total, sizeOfBuckets * sizeof(int) );
+5
1

.

  • , . . .
  • 2D- . , . , . . .

:

__global__ void process_list(int sizeOfBucketsHoldings, int* total, int* current_list, int pitch)
{
    int tid = blockIdx.x;
    total[tid] = 0;
    for (int c = 0; c < sizeOfBucketsHoldings; ++c)
    {
        total[tid] += *((int*)((char*)current_list + tid * pitch) + c);
    }
}

int main()
{
    size_t sizeOfBuckets         = 10;
    size_t sizeOfBucketsHoldings = 30;

    size_t width = sizeOfBucketsHoldings * sizeof(int);//ned to be in bytes
    size_t height = sizeOfBuckets;

    int* list = new int [sizeOfBuckets * sizeOfBucketsHoldings];// one dimensional
    for (int i = 0; i < sizeOfBuckets; i++)
        for (int j = 0; j < sizeOfBucketsHoldings; j++)
            list[i *sizeOfBucketsHoldings + j] = i;

    size_t pitch_h = sizeOfBucketsHoldings * sizeof(int);// always in bytes

    int* dev_current_list;
    size_t pitch_d;
    cudaMallocPitch((int**)&dev_current_list, &pitch_d, width, height);

    int *test;
    cudaMalloc((void**)&test, sizeOfBuckets * sizeof(int));
    int* h_test = new int[sizeOfBuckets];

    cudaMemcpy2D(dev_current_list, pitch_d, list, pitch_h, width, height, cudaMemcpyHostToDevice);

    process_list<<<10, 1>>>(sizeOfBucketsHoldings, test, dev_current_list, pitch_d);
    cudaDeviceSynchronize();

    cudaMemcpy(h_test, test, sizeOfBuckets * sizeof(int), cudaMemcpyDeviceToHost);

    for (int i = 0; i < sizeOfBuckets; i++)
        printf("%d %d\n", i , h_test[i]);
    return 0;
}

2D- , base_addr + y * pitch_d + x. : pitvh . byte*.

+3

More articles:


All Articles