docker镜像配置挂载GPU的实现步骤

#include <iostream>
#include <cuda_runtime.h>
#include <device_launch_parameters.h>
// CUDA 核函数（Kernel）：运行在GPU上
__global__ void vectorAdd(const float *a, const float *b, float *c, int n) {
    // 计算当前线程的全局索引
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    // 确保索引在数组范围内，然后执行加法
    if (idx < n) {
        c[idx] = a[idx] + b[idx];
    }
}
int main() {
    // 定义向量长度
    const int n = 10000;
    const size_t size = n * sizeof(float);
    // 在主机（CPU）上分配并初始化内存
    float *h_a = new float[n];
    float *h_b = new float[n];
    float *h_c = new float[n];
    for (int i = 0; i < n; i++) {
        h_a[i] = static_cast<float>(i);       // 例如: 0.0, 1.0, 2.0...
        h_b[i] = static_cast<float>(i * 2);   // 例如: 0.0, 2.0, 4.0...
    }
    // 在设备（GPU）上分配内存
    float *d_a = nullptr;
    float *d_b = nullptr;
    float *d_c = nullptr;
    cudaMalloc(&d_a, size);
    cudaMalloc(&d_b, size);
    cudaMalloc(&d_c, size);
    // 将数据从主机内存复制到设备内存
    cudaMemcpy(d_a, h_a, size, cudaMemcpyHostToDevice);
    cudaMemcpy(d_b, h_b, size, cudaMemcpyHostToDevice);
    // 设置GPU线程的组织结构
    int threadsPerBlock = 256; // 每个线程块包含256个线程
    // 计算需要多少个线程块才能覆盖整个向量
    int blocksPerGrid = (n + threadsPerBlock - 1) / threadsPerBlock;
    // 在GPU上启动核函数（Kernel）
    vectorAdd<<<blocksPerGrid, threadsPerBlock>>>(d_a, d_b, d_c, n);
    // 等待GPU上所有线程计算完成
    cudaDeviceSynchronize();
    // 将计算结果从设备内存复制回主机内存
    cudaMemcpy(h_c, d_c, size, cudaMemcpyDeviceToHost);
    // （可选）验证前10个结果是否正确
    std::cout << "Checking the first 10 results..." << std::endl;
    std::cout << "t" << "CPU" << "tt" << "GPU" << std::endl;
    for (int i = 0; i < 10; i++) {
        float expected = h_a[i] + h_b[i];
        if (std::abs(h_c[i] - expected) > 1e-5) {
            std::cout << "Error at index " << i << ": " << h_c[i] << " != " << expected << std::endl;
        } else {
            std::cout << "t" << expected << "tt" << h_c[i] << " [PASS]" << std::endl;
        }
    }
    // 释放所有申请的内存
    delete[] h_a;
    delete[] h_b;
    delete[] h_c;
    cudaFree(d_a);
    cudaFree(d_b);
    cudaFree(d_c);
    std::cout << "Vector addition completed successfully!" << std::endl;
    return 0;
}

./GPUTest_exe 
Checking the first 10 results...
tCPUttGPU
t0tt0 [PASS]
t3tt3 [PASS]
t6tt6 [PASS]
t9tt9 [PASS]
t12tt12 [PASS]
t15tt15 [PASS]
t18tt18 [PASS]
t21tt21 [PASS]
t24tt24 [PASS]
t27tt27 [PASS]
Vector addition completed successfully!

docker run --memory=10g --memory-swap=10g --rm \
-v /Bin_Release:/JX \
-v /usr/local/corex:/usr/local/corex \
-v /usr/local/cuda-10.2:/usr/local/cuda-10.2 \
-v /usr/lib64:/usr/lib64 \
-e LD_LIBRARY_PATH=/usr/local/corex/lib64:/usr/local/cuda-10.2/lib64 \
--device=/dev/iluvatar0 \
--privileged \
-w /docker_test:v1.0 \
./GPU_Bin/GPUTest_exe

-v /usr/local/corex:/usr/local/corex 
-v /usr/local/cuda-10.2:/usr/local/cuda-10.2 

-e LD_LIBRARY_PATH=/usr/local/corex/lib64:/usr/local/cuda-10.2/lib64 \

--device=/dev/iluvatar0
#有些设备是corex ,则需要配置
--device=/dev/corex

error while loading shared libraries: libcudart.so.10.2: cannot open shared object file

-e LD_LIBRARY_PATH=/usr/local/corex/lib64:/usr/local/cuda-10.2/lib64

./GPU_Bin/GPUTest_exe
Checking the first 10 results...
tCPUttGPU
t0tt0 [PASS]
Error at index 1: 0 != 3
Error at index 2: 0 != 6
Error at index 3: 0 != 9
Error at index 4: 0 != 12
Error at index 5: 0 != 15
Error at index 6: 0 != 18
Error at index 7: 0 != 21
Error at index 8: 0 != 24
Error at index 9: 0 != 27
Vector addition completed successfully!

--device=/dev/corex

./GPU_Bin/GPUTest_exedocker: Error response from daemon: error gathering device information while adding custom device "/dev/corex": no such file or directory.