Cuda 学习教程：Cuda 程序初始化

Cuda程序初始化

目前，cuda里面没有对设备的初始化函数InitDevice()，只能每次调用的api函数的时候，加载设备的上下文，自动进行初始化，这将带来问题：

---

• First函数调用的时候，需要自动初始化设备，因此耗时过长
• 无法分析第一个api函数的耗时

---

处理办法

• 在程序前加设置初始化函数： cudaFree(0)，后面程序就不会再次初始化，cudamalloc()也将很快;
• 一次初始化后，程序cudamalloc()分配的内存不释放，继续使用，所有程序运行结束后，再一起释放。

TestCode

简单的测试demo，例如：

@ Bytry Zhang#include "cuda_runtime.h"#include "device_launch_parameters.h"#include <time.h>#include<iostream>#include <stdio.h>using namespace std;cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size);__global__ void addKernel(int *c, const int *a, const int *b){    int i = threadIdx.x;    c[i] = a[i] + b[i];}int main(){    const int arraySize = 5;    const int a[arraySize] = { 1, 2, 3, 4, 5 };    const int b[arraySize] = { 10, 20, 30, 40, 50 };    int c[arraySize] = { 0 };    // Add vectors in parallel.    cudaError_t cudaStatus = addWithCuda(c, a, b, arraySize);    if (cudaStatus != cudaSuccess) {        fprintf(stderr, "addWithCuda failed!");        return 1;    }    printf("{1,2,3,4,5} + {10,20,30,40,50} = {%d,%d,%d,%d,%d}\n",        c[0], c[1], c[2], c[3], c[4]);    // cudaDeviceReset must be called before exiting in order for profiling and    // tracing tools such as Nsight and Visual Profiler to show complete traces.    cudaStatus = cudaDeviceReset();    if (cudaStatus != cudaSuccess) {        fprintf(stderr, "cudaDeviceReset failed!");        return 1;    }    return 0;}// Helper function for using CUDA to add vectors in parallel.cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size){    int *dev_a = 0;    int *dev_b = 0;    int *dev_c = 0;    cudaError_t cudaStatus;    cudaStatus = cudaFree(0);    //cudaStatus = cudaSetDevice(0);    if (cudaStatus != cudaSuccess) {        fprintf(stderr, "cudaSetDevice failed!  Do you have a CUDA-capable GPU installed?");        goto Error;    }    clock_t t = clock();    // Choose which GPU to run on, change this on a multi-GPU system.    // Allocate GPU buffers for three vectors (two input, one output)    .    cudaStatus = cudaMalloc((void**)&dev_c, size * sizeof(int));    if (cudaStatus != cudaSuccess) {        fprintf(stderr, "cudaMalloc failed!");        goto Error;    }    cudaStatus = cudaMalloc((void**)&dev_a, size * sizeof(int));    if (cudaStatus != cudaSuccess) {        fprintf(stderr, "cudaMalloc failed!");        goto Error;    }    cudaStatus = cudaMalloc((void**)&dev_b, size * sizeof(int));    if (cudaStatus != cudaSuccess) {        fprintf(stderr, "cudaMalloc failed!");        goto Error;    }    cout << "cudaMemcpy time =  " << clock() - t << endl;    // Copy input vectors from host memory to GPU buffers.    cudaStatus = cudaMemcpy(dev_a, a, size * sizeof(int), cudaMemcpyHostToDevice);    if (cudaStatus != cudaSuccess) {        fprintf(stderr, "cudaMemcpy failed!");        goto Error;    }    cudaStatus = cudaMemcpy(dev_b, b, size * sizeof(int), cudaMemcpyHostToDevice);    if (cudaStatus != cudaSuccess) {        fprintf(stderr, "cudaMemcpy failed!");        goto Error;    }    // Launch a kernel on the GPU with one thread for each element.    addKernel<<<1, size>>>(dev_c, dev_a, dev_b);    // Check for any errors launching the kernel    cudaStatus = cudaGetLastError();    if (cudaStatus != cudaSuccess) {        fprintf(stderr, "addKernel launch failed: %s\n", cudaGetErrorString(cudaStatus));        goto Error;    }    // cudaDeviceSynchronize waits for the kernel to finish, and returns    // any errors encountered during the launch.    cudaStatus = cudaDeviceSynchronize();    if (cudaStatus != cudaSuccess) {        fprintf(stderr, "cudaDeviceSynchronize returned error code %d after launching addKernel!\n", cudaStatus);        goto Error;    }    // Copy output vector from GPU buffer to host memory.    cudaStatus = cudaMemcpy(c, dev_c, size * sizeof(int), cudaMemcpyDeviceToHost);    if (cudaStatus != cudaSuccess) {        fprintf(stderr, "cudaMemcpy failed!");        goto Error;    }Error:    cudaFree(dev_c);    cudaFree(dev_a);    cudaFree(dev_b);    return cudaStatus;}