Question

我正在尝试使用CUDA和C编写基本的矩阵乘法程序。代码本身现在并没有真正做任何事情，但至少应该编译。经过对该问题的一些研究后，我确定问题是未能包含CUDA头文件，这表明我的Makefile存在问题。我对CUDA（以及C）非常缺乏经验，所以任何帮助都会非常感激。

命令输出：make matrixMult1

c99    -I. -I/usr/local/cuda/include -c matrixMult1.c -o matrixMult1.o
matrixMult1.c: In function 'main':
matrixMult1.c:77: warning: implicit declaration of function 'cudaMalloc'
matrixMult1.c:82: warning: implicit declaration of function 'cudaMemcpy'
matrixMult1.c:83: error: 'cudaMemcpyHostToDevice' undeclared (first use in this
function)
matrixMult1.c:83: error: (Each undeclared identifier is reported only once
matrixMult1.c:83: error: for each function it appears in.)
matrixMult1.c:106: warning: implicit declaration of function 'cudaFree'
make: *** [matrixMult1.o] Error 1

生成文件：

GCC = c99
CUDA_INSTALL_PATH := /usr/local/cuda
INCLUDES := -I. -I$(CUDA_INSTALL_PATH)/include
CUDA_LIBS := -L$(CUDA_INSTALL_PATH)/lib -lcudart

matrixMult1.o:          matrixMult1.c
                $(GCC)  $(INCLUDES) -c matrixMult1.c -o $@

matrixMult1:            matrixMult1.o
                $(GCC)  -o $@ matrixMult1.o $(CUDA_LIBS)

C计划：

//********************************************************************
// matrixMult1.c
//
// A basic matrix multiplication program.
//********************************************************************

#include <stdlib.h>
#include <stdio.h>
#include <math.h>
#include "cuda.h"

#define WA 3
#define HA 3
#define WB 3
#define HB WA
#define WC WB
#define HC HA

void initMatrix(float * matrix, int numIndices);

//*************
// Main Program
//*************
int main(int argc, char** argv) {

    /* Set random seed */
    srand(2013);

    /* Compute memory sizes for matrices A, B, and C */
    unsigned int sizeA = WA * HA;
    unsigned int sizeB = WB * HB;
    unsigned int sizeC = WC * HC;
    unsigned int memoryA = sizeof(float) * sizeA;
    unsigned int memoryB = sizeof(float) * sizeB;
    unsigned int memoryC = sizeof(float) * sizeC;

    /* Allocate memory for matrices A, B, and C */
    float * matrixA = (float *) malloc(memoryA);
    float * matrixB = (float *) malloc(memoryB);
    float * matrixC = (float *) malloc(memoryC);

    /* Initialize matrices A and B */
    initMatrix(matrixA, sizeA);
    initMatrix(matrixB, sizeB);

    /* Print matrix A */
    printf("\nMatrix A:\n");
    for (int i = 0; i < sizeA; i++) {
        printf("%f ", matrixA[i]);

    if (((i + 1) % WA) == 0) {
        printf("\n");
    } else {
        printf(" | ");
    }
    }

    /* Print matrix B */
    printf("\nMatrix B:\n");
    for (int i = 0; i < sizeB; i++) {
    printf("%f ", matrixB[i]);

    if (((i + 1) % WA) == 0) {
        printf("\n");
    } else {
        printf(" | ");
    }
    }

    /* Allocate device memory */
    float* deviceMemA;
    float* deviceMemB;
    float* deviceMemC;
    cudaMalloc((void**) &deviceMemA, memoryA);
    cudaMalloc((void**) &deviceMemB, memoryB);
    cudaMalloc((void**) &deviceMemC, memoryC);

    /* Copy host memory to device */
    cudaMemcpy(deviceMemA, matrixA, memoryA,
           cudaMemcpyHostToDevice);
    cudaMemcpy(deviceMemB, matrixB, memoryB,
               cudaMemcpyHostToDevice);
    cudaMemcpy(deviceMemC, matrixC, memoryC,
           cudaMemcpyHostToDevice);

    /* Print matrix C */
    printf("\nMatrix C:\n");
    for (int i = 0; i < sizeC; i++) {
    printf("%f ", matrixC[i]);

    if (((i + 1) % WC) == 0) {
        printf("\n");
    } else {
        printf(" | ");
    }
    }
    printf("\n");

    /* Free up memory */
    free(matrixA);
    free(matrixB);
    free(matrixC);
    cudaFree(deviceMemA);
    cudaFree(deviceMemB);
    cudaFree(deviceMemC);
}

//--------------------------------------------------------------------
// initMatrix - Assigns a random float value to each indice of the
//              matrix.
//
// PRE:  matrix is a pointer to a block of bytes in memory; numIndices
//       is the number of indicies in the matrix being instantiated.
// POST: Each index of the matrix has been instantiated with a random
//       float value.
//--------------------------------------------------------------------
void initMatrix(float * matrix, int numIndices) {

    /*
    Loop through the block of bytes, assigning a random float
    for each index of the matrix
    */
    for (int i = 0; i < numIndices; ++i) {

    /* Assign a random float between 0 and 1 at this byte */
    matrix[i] = rand() / (float)RAND_MAX;
    }
}

Answer 1

这里有两个问题：

您未将相应的标题包含在您的代码中（已修复）
事实上，你的Makefile已被破坏。它应该看起来像：

GCC = c99
CUDA_INSTALL_PATH := /usr/local/cuda
INCLUDES := -I. -I$(CUDA_INSTALL_PATH)/include
CUDA_LIBS := -L$(CUDA_INSTALL_PATH)/lib -lcudart

matrixMult1.o:          matrixMult1.c
                $(GCC) $(INCLUDES) -c matrixMult1.c -o $@

matrixMult1:            matrixMult1.o
                $(GCC) -o $@ matrixMult1.o  $(CUDA_LIBS)

[免责声明：未经测试，自担风险使用]

当前的问题是包含路径仅在构建的链接阶段指定。

请注意，这些更改还会抢占在链接期间从未链接到CUDA运行时库时出现的缺失符号错误。请注意，根据您使用的是32位还是64位主机操作系统，可能需要将库路径更改为$(CUDA_INSTALL_PATH)/lib64，以使链接正常工作。

Answer 2

CUDA程序需要由nvcc编译。虽然你的程序还没有包含任何CUDA内核，但我相信这就是你想要实现的目标。

将文件从matrixMult1.c重命名为matrixMult1.cu，删除#include "cuda.h"行（使用nvcc编译的程序不需要任何特定于CUDA的包含）并使用{编译{1}}而不是nvcc（例如，在Makefile的开头设置gcc）。

CUDA Makefile包含错误

2 个答案: