Geek asks and answers

Finding High and Low with CUBLAS

I am having problems understanding why my function, which finds the maximum and minimum in the doubling range using CUBLAS, does not work properly.

The code is as follows:

void findMaxAndMinGPU(double* values, int* max_idx, int* min_idx, int n)
{
    double* d_values;
    cublasHandle_t handle;
    cublasStatus_t stat;
    safecall( cudaMalloc((void**) &d_values, sizeof(double) * n), "cudaMalloc     (d_values) in findMaxAndMinGPU");
    safecall( cudaMemcpy(d_values, values, sizeof(double) * n, cudaMemcpyHostToDevice), "cudaMemcpy (h_values > d_values) in findMaxAndMinGPU");
    cublasCreate(&handle);

    stat = cublasIdamax(handle, n, d_values, sizeof(double), max_idx);
    if (stat != CUBLAS_STATUS_SUCCESS)
        printf("Max failed\n");

    stat = cublasIdamin(handle, n, d_values, sizeof(double), min_idx);
    if (stat != CUBLAS_STATUS_SUCCESS)
        printf("min failed\n");

    cudaFree(d_values);
    cublasDestroy(handle);
}

Where the values ​​are the values ​​to search inside. Max_idx and min_idx are the index of the numbers found in the values. The results of CUBLAS calls seem rather random and display incorrect indexes.

Anyone with a good answer to my problem? At the moment, I'm a little sad :(

+3
source share
2 answers

cublasIdamax cublasIdamin . incx BLAS 1 , . , - :

stat = cublasIdamax(handle, n, d_values, 1, max_idx);
if (stat != CUBLAS_STATUS_SUCCESS)
    printf("Max failed\n");

stat = cublasIdamin(handle, n, d_values, 1, min_idx);
if (stat != CUBLAS_STATUS_SUCCESS)
    printf("min failed\n");

sizeof(double), , 8, . , 1 d_values.

: , . . , :

#include <cuda_runtime.h>
#include <cublas_v2.h>
#include <cstdio>
#include <cstdlib>
#include <sys/time.h>


typedef float Real;

void findMaxAndMinGPU(Real* values, int* max_idx, int* min_idx, int n)
{
    Real* d_values;
    cublasHandle_t handle;
    cublasStatus_t stat;
    cudaMalloc((void**) &d_values, sizeof(Real) * n);
    cudaMemcpy(d_values, values, sizeof(Real) * n, cudaMemcpyHostToDevice);
    cublasCreate(&handle);

    stat = cublasIsamax(handle, n, d_values, 1, max_idx);
    if (stat != CUBLAS_STATUS_SUCCESS)
        printf("Max failed\n");

    stat = cublasIsamin(handle, n, d_values, 1, min_idx);
    if (stat != CUBLAS_STATUS_SUCCESS)
        printf("min failed\n");

    cudaFree(d_values);
    cublasDestroy(handle);
}

int main(void)
{
    const int vmax=1000, nvals=10000;

    float vals[nvals];
    srand ( time(NULL) );
    for(int j=0; j<nvals; j++) {
       vals[j] = float(rand() % vmax);
    }

    int minIdx, maxIdx;
    findMaxAndMinGPU(vals, &maxIdx, &minIdx, nvals);

    int cmin = 0, cmax=0;
    for(int i=1; i<nvals; i++) {
        cmin = (vals[i] < vals[cmin]) ? i : cmin;
        cmax = (vals[i] > vals[cmax]) ? i : cmax;
    }

    fprintf(stdout, "%d %d %d %d\n", minIdx, cmin, maxIdx, cmax);

    return 0;
}

:

$ g++ -I/usr/local/cuda/include -L/usr/local/cuda/lib cublastest.cc -lcudart -lcublas
$ ./a.out
273 272 85 84

, CUBLAS FORTRAN 1 , , CUBLAS CPU 1.

+4

: : http://docs.nvidia.com/cuda/cublas/index.html#topic_6_1

if you have { 1, 2, 3, -33, 22, 11 }

4! 5

abs(-33) > 22
+2

More articles:


All Articles