Question

我正在尝试通过使用Google Colab上的cuRAND库来运行CUDA程序以生成随机数，但出现链接器问题。

我知道，我们可以在与gcc一起编译时通过使用-lcurand来解决此问题，但据我所知，我们无法在colab中访问终端。

我正在使用它生成2 * N个随机数。

#include <curand_kernel.h>

int status;
curandGenerator_t gen;
status = curandCreateGenerator(&gen, CURAND_RNG_PSEUDO_MRG32K3A);
status |= curandSetPseudoRandomGeneratorSeed(gen, 4294967296ULL^time(NULL));
status |= curandGenerateUniform(gen, randomnums, (2*N));
status |= curandDestroyGenerator(gen);

错误：

/tmp/tmpxft_000006b3_00000000-10_11f5cb12-9471-4d0d-9dcb-659af6ee1dae.o: In function `main':
tmpxft_000006b3_00000000-5_11f5cb12-9471-4d0d-9dcb-659af6ee1dae.cudafe1.cpp:(.text+0xb0): undefined reference to `curandCreateGenerator'
tmpxft_000006b3_00000000-5_11f5cb12-9471-4d0d-9dcb-659af6ee1dae.cudafe1.cpp:(.text+0xdc): undefined reference to `curandSetPseudoRandomGeneratorSeed'
tmpxft_000006b3_00000000-5_11f5cb12-9471-4d0d-9dcb-659af6ee1dae.cudafe1.cpp:(.text+0xfa): undefined reference to `curandGenerateUniform'
tmpxft_000006b3_00000000-5_11f5cb12-9471-4d0d-9dcb-659af6ee1dae.cudafe1.cpp:(.text+0x109): undefined reference to `curandDestroyGenerator'
collect2: error: ld returned 1 exit status

Answer 1

这是一种可能的方法：

确保您的colab会话具有GPU：

只需在“笔记本设置”的“加速器”下拉列表中选择“ GPU”（通过“编辑”菜单或cmd / ctrl-shift-P上的命令面板）。

安装the nvcc4jupyter plugin：

!pip install git+git://github.com/andreinechaev/nvcc4jupyter.git

加载插件：
```
%load_ext nvcc_plugin
```

将所需的代码放入单元格中，并传递文件名：

%%cuda --name my_curand.cu 
/*
 * This program uses the host CURAND API to generate 100 
 * pseudorandom floats.
 */
#include <stdio.h>
#include <stdlib.h>
#include <cuda.h>
#include <curand.h>

#define CUDA_CALL(x) do { if((x)!=cudaSuccess) { \
    printf("Error at %s:%d\n",__FILE__,__LINE__);\
    return EXIT_FAILURE;}} while(0)
#define CURAND_CALL(x) do { if((x)!=CURAND_STATUS_SUCCESS) { \
    printf("Error at %s:%d\n",__FILE__,__LINE__);\
    return EXIT_FAILURE;}} while(0)

int main(int argc, char *argv[])
{
    size_t n = 100;
    size_t i;
    curandGenerator_t gen;
    float *devData, *hostData;

    /* Allocate n floats on host */
    hostData = (float *)calloc(n, sizeof(float));

    /* Allocate n floats on device */
    CUDA_CALL(cudaMalloc((void **)&devData, n*sizeof(float)));

    /* Create pseudo-random number generator */
    CURAND_CALL(curandCreateGenerator(&gen, 
                CURAND_RNG_PSEUDO_DEFAULT));

    /* Set seed */
    CURAND_CALL(curandSetPseudoRandomGeneratorSeed(gen, 
                1234ULL));

    /* Generate n floats on device */
    CURAND_CALL(curandGenerateUniform(gen, devData, n));

    /* Copy device memory to host */
    CUDA_CALL(cudaMemcpy(hostData, devData, n * sizeof(float),
        cudaMemcpyDeviceToHost));

    /* Show result */
    for(i = 0; i < n; i++) {
        printf("%1.4f ", hostData[i]);
    }
    printf("\n");

    /* Cleanup */
    CURAND_CALL(curandDestroyGenerator(gen));
    CUDA_CALL(cudaFree(devData));
    free(hostData);    
    return EXIT_SUCCESS;
}

（您的代码已损坏/不完整，所以我使用的是curand docs中的示例代码）。

注意单元格输出：

'File written in /content/src/my_curand.cu'

编译代码：

!nvcc -o /content/src/my_curand /content/src/my_curand.cu -lcurand

运行代码

!/content/src/my_curand

注意单元格输出：

0.1455 0.8202 0.5504 0.2948 0.9147 0.8690 0.3219 0.7829 0.0113 0.2855 0.7816 0.2338 0.6791 0.2824 0.6299 0.1212 0.4333 0.3831 0.5136 0.2987 0.4166 0.0345 0.0494 0.0467 0.6166 0.6480 0.8685 0.4012 0.0631 0.4972 0.6809 0.9350 0.0704 0.0458 0.1324 0.3785 0.6457 0.9930 0.9952 0.7677 0.3217 0.8210 0.2765 0.2691 0.4579 0.1969 0.9555 0.8739 0.7996 0.3810 0.6662 0.3153 0.9428 0.5006 0.3369 0.1490 0.8637 0.6191 0.6820 0.4573 0.9261 0.5650 0.7117 0.8252 0.8755 0.2216 0.2958 0.4046 0.3896 0.7335 0.7301 0.8154 0.0913 0.0866 0.6974 0.1811 0.5834 0.9255 0.9029 0.0413 0.9522 0.5507 0.7237 0.3976 0.7519 0.4398 0.4638 0.6094 0.7358 0.3272 0.6961 0.4893 0.9698 0.0456 0.2025 0.9491 0.1516 0.0424 0.6149 0.5638

在Google Colab上执行CUDA程序时如何链接库？

1 个答案: