CUDA：对传递给 GPU 的数组的每个第 n 个点进行分组

Question

我正在尝试在外部 Unix 上使用 Tesla 卡在 CUDA 上实现 k-means 算法。我读取输入文件并将所有数据点的坐标存储在 dataX 和 dataY 数组中。下一步是选择每个 centreInterval-th 点并将其存储在分配在 GPU 内存中的另一个数组中。但是，我不知道如果我能得到的只是“分段错误”并且由于明显的原因无法从内核打印任何类型的输出，我什至如何检查问题是什么。

编辑 2：我将此示例简化为最短的解决方案。我在过程中找到了我的解决方案，但决定提供此问题中尚未解决的版本，以更清楚导致问题的原因。

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <strings.h>
#include <math.h>
#include <time.h>
#include <unistd.h>
#define BLOCK_SIZE 16

// My kernel - Selects some centres at the beginning of algorithm and stores it at appropriate place
__global__ void kMeansSelectInitialCentres(float* d_dataX, float* d_dataY, float* d_centresX, float* d_centresY, int centreInterval) {

    int i = blockIdx.x * blockDim.x + threadIdx.x;
    int idx = i * centreInterval;
    d_centresX[i] = d_dataX[idx];
    d_centresY[i] = d_dataY[idx];
}

// Simplified example
int main(int argn, char ** argc) {

    // My data - let's say it is 32 floats in each
    int dataSize = 32;
    float* dataX = new float[dataSize];
    float* dataY = new float[dataSize]; 

    // Fill arrays with numbers
    for (int i = 0; i < dataSize; i++) {
        dataX[i] = i;
        dataY[i] = i;
    }

    // Interval - we select first number, then 1 + N * centreInterval 
    int centreInterval = 2;

    // There I will store my results in program
    int centreSize = dataSize / centreInterval;
    float* centresX = new float[centreSize];
    float* centresY = new float[centreSize];

    // Pointers to the arrays stored in GPU memory
    float* d_dataX;
    float* d_dataY;
    float* d_centresX;
    float* d_centresY;

// Allocate memory for those arrays
    // Calculate how much space in memory do we need for this
    size_t d_centreSize = sizeof(float) * centreSize;
    size_t d_dataSize = sizeof(float) * dataSize;

    // Memory for raw data
    cudaMalloc((void**)&d_dataX, d_dataSize);   
    cudaMalloc((void**)&d_dataY, d_dataSize);

    // Copy raw data to the device memory so we can operate on it freely
    cudaMemcpy(d_dataY, dataY, d_dataSize, cudaMemcpyHostToDevice);
    cudaMemcpy(d_dataX, dataX, d_dataSize, cudaMemcpyHostToDevice);

    // Memory for centre results
    cudaMalloc((void**)&d_centresX, d_dataSize);
    cudaMalloc((void**)&d_centresY, d_dataSize);

    // Call kernel
    dim3 dimBlock(BLOCK_SIZE);
    dim3 dimGridK((centreSize + dimBlock.x) / dimBlock.x);
    kMeansSelectInitialCentres <<<dimGridK, dimBlock>>> (d_dataX, d_dataY, d_centresX, d_centresY, centreInterval);

    // Check results - we get every n-th point
    float* check_x = new float[centreSize];
    float* check_y = new float[centreSize];

    cudaMemcpy(check_x, d_centresX, d_dataSize, cudaMemcpyDeviceToHost);
    cudaMemcpy(check_y, d_centresY, d_dataSize, cudaMemcpyDeviceToHost);

    printf("X: ");  
    for (int i = 0; i < centreSize; i++)
        printf("%.2f ", check_x[i]);
    printf("\nY: ");
    for (int i = 0; i < centreSize; i++)
        printf("%.2f ", check_y[i]);
    printf("\n");

}

主要问题：这个内核/签出数据有什么问题？

附带问题：在这种情况下是否有任何公平的方法来调试程序内核？

Answer 1

所以，这是我在简化案例后提出的解决方案。内存使用存在问题 - 我尝试存储/读取的数据量与分配时声称使用的数据量不同。我希望它对将来的任何人都有帮助：

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <strings.h>
#include <math.h>
#include <time.h>
#include <unistd.h>
#define BLOCK_SIZE 16

// My kernel - Selects some centres at the beginning of algorithm and stores it at appropriate place
__global__ void kMeansSelectInitialCentres(float* d_dataX, float* d_dataY, float* d_centresX, float* d_centresY, int centreInterval) {

    int i = blockIdx.x * blockDim.x + threadIdx.x;
    int idx = i * centreInterval;
    d_centresX[i] = d_dataX[idx];
    d_centresY[i] = d_dataY[idx];
}

// Simplified example
int main(int argn, char ** argc) {

    // My data - let's say it is 32 floats in each
    int dataSize = 32;
    float* dataX = new float[dataSize];
    float* dataY = new float[dataSize]; 

    // Fill arrays with numbers
    for (int i = 0; i < dataSize; i++) {
        dataX[i] = i;
        dataY[i] = i;
    }

    // Interval - we select first number, then 1 + N * centreInterval 
    int centreInterval = 2;

    // There I will store my results in program
    int centreSize = dataSize / centreInterval;
    float* centresX = new float[centreSize];
    float* centresY = new float[centreSize];

    // Pointers to the arrays stored in GPU memory
    float* d_dataX;
    float* d_dataY;
    float* d_centresX;
    float* d_centresY;

// Allocate memory for those arrays
    // Calculate how much space in memory do we need for this
    size_t d_centreSize = sizeof(float) * centreSize;
    size_t d_dataSize = sizeof(float) * dataSize;

    // Memory for raw data
    cudaMalloc((void**)&d_dataX, d_dataSize);   
    cudaMalloc((void**)&d_dataY, d_dataSize);

    // Copy raw data to the device memory so we can operate on it freely
    cudaMemcpy(d_dataY, dataY, d_dataSize, cudaMemcpyHostToDevice);
    cudaMemcpy(d_dataX, dataX, d_dataSize, cudaMemcpyHostToDevice);

    // Memory for centre results
    cudaMalloc((void**)&d_centresX, d_centreSize);
    cudaMalloc((void**)&d_centresY, d_centreSize);

    // Call kernel
    dim3 dimBlock(BLOCK_SIZE);
    dim3 dimGridK((centreSize + dimBlock.x) / dimBlock.x);
    kMeansSelectInitialCentres <<<dimGridK, dimBlock>>> (d_dataX, d_dataY, d_centresX, d_centresY, centreInterval);

    // Check results - we get every n-th point
    float* check_x = new float[centreSize];
    float* check_y = new float[centreSize];

    cudaMemcpy(check_x, d_centresX, d_centreSize, cudaMemcpyDeviceToHost);
    cudaMemcpy(check_y, d_centresY, d_centreSize, cudaMemcpyDeviceToHost);

    printf("X: ");  
    for (int i = 0; i < centreSize; i++)
        printf("%.2f ", check_x[i]);
    printf("\nY: ");
    for (int i = 0; i < centreSize; i++)
        printf("%.2f ", check_y[i]);
    printf("\n");

}