【 声明：版权所有，欢迎转载，请勿用于商业用途。 联系信箱：feixiaoxing @163.com】
cuda是nvidia公司用于gpu开发的一门语言。它来自于c，但是又对c进行了扩展。目前cuda广泛用于高性能计算、深度学习训练、嵌入式设备等各种应用场景。然而cuda入门容易，深入困难，如果只是基本概念学习，不足以对其有深刻的认识，因此最好结合具体的代码来一起开发，才能真正将gpu的作用发挥出来。
因此，我查看了个人笔记本，虽然显示的是nvidia mx150，一个比较低阶的移动GPU版本，但是也可以用cuda进行开发。所以利用下午这一段时间，安装了一下cuda环境，收获很多。
1、安装visual studio 2015
目前cuda支持vs2012、vs2013、vs2015、vs2017、vs2019。
2、下载cuda安装包
可以选择适合自己的cuda包，我这里下载的是cuda_10.2.89_441.22_win10.exe。
3、安装cuda软件
基本上不停的按下一步、下一步就可以了。中间cuda会先自解压，然后再进行安装。
4、确认cuda是否安装成功
在cmd下面输入nvcc --help，如果有打印信息，代表一切ok。
5、查找示例代码
如果安装没有问题，在C:\ProgramData\NVIDIA Corporation\CUDA Samples会看到一个目录，目录下有很多的示例代码。
6、编译示例代码
示例代码很多，分别是0_Simple、1_Utilities、2_Graphics、3_Imaging、4_Finance、5_Simulations、6_Advanced、7_CUDALibraries。刚开始的时候可以只选择编译一部分内容，比如0_Simple，如果编译、运行本身没多大问题，说明我们的安装是非常成功的。
7、简单的示例代码vectorAdd.cu
代码内容就是一个向量的计算，比较简洁，但是对我们了解cuda加速的原理足够了。
/**
* Copyright 1993-2015 NVIDIA Corporation. All rights reserved.
*
* Please refer to the NVIDIA end user license agreement (EULA) associated
* with this source code for terms and conditions that govern your use of
* this software. Any use, reproduction, disclosure, or distribution of
* this software and related documentation outside the terms of the EULA
* is strictly prohibited.
*
*/
/**
* Vector addition: C = A + B.
*
* This sample is a very basic sample that implements element by element
* vector addition. It is the same as the sample illustrating Chapter 2
* of the programming guide with some additions like error checking.
*/
#include <stdio.h>
// For the CUDA runtime routines (prefixed with "cuda_")
#include <cuda_runtime.h>
#include <helper_cuda.h>
/**
* CUDA Kernel Device code
*
* Computes the vector addition of A and B into C. The 3 vectors have the same
* number of elements numElements.
*/
__global__ void
vectorAdd(const float *A, const float *B, float *C, int numElements)
{
int i = blockDim.x * blockIdx.x + threadIdx.x;
if (i < numElements)
{
C[i] = A[i] + B[i];
}
}
/**
* Host main routine
*/
int
main(void)
{
// Error code to check return values for CUDA calls
cudaError_t err = cudaSuccess;
// Print the vector length to be used, and compute its size
int numElements = 50000;
size_t size = numElements * sizeof(float);
printf("[Vector addition of %d elements]\n", numElements);
// Allocate the host input vector A
float *h_A = (float *)malloc(size);
// Allocate the host input vector B
float *h_B = (float *)malloc(size);
// Allocate the host output vector C
float *h_C = (float *)malloc(size);
// Verify that allocations succeeded
if (h_A == NULL || h_B == NULL || h_C == NULL)
{
fprintf(stderr, "Failed to allocate host vectors!\n");
exit(EXIT_FAILURE);
}
// Initialize the host input vectors
for (int i = 0; i < numElements; ++i)
{
h_A[i] = rand()/(float)RAND_MAX;
h_B[i] = rand()/(float)RAND_MAX;
}
// Allocate the device input vector A
float *d_A = NULL;
err = cudaMalloc((void **)&d_A, size);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to allocate device vector A (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Allocate the device input vector B
float *d_B = NULL;
err = cudaMalloc((void **)&d_B, size);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to allocate device vector B (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Allocate the device output vector C
float *d_C = NULL;
err = cudaMalloc((void **)&d_C, size);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to allocate device vector C (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Copy the host input vectors A and B in host memory to the device input vectors in
// device memory
printf("Copy input data from the host memory to the CUDA device\n");
err = cudaMemcpy(d_A, h_A, size, cudaMemcpyHostToDevice);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to copy vector A from host to device (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
err = cudaMemcpy(d_B, h_B, size, cudaMemcpyHostToDevice);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to copy vector B from host to device (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Launch the Vector Add CUDA Kernel
int threadsPerBlock = 256;
int blocksPerGrid =(numElements + threadsPerBlock - 1) / threadsPerBlock;
printf("CUDA kernel launch with %d blocks of %d threads\n", blocksPerGrid, threadsPerBlock);
vectorAdd<<<blocksPerGrid, threadsPerBlock>>>(d_A, d_B, d_C, numElements);
err = cudaGetLastError();
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to launch vectorAdd kernel (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Copy the device result vector in device memory to the host result vector
// in host memory.
printf("Copy output data from the CUDA device to the host memory\n");
err = cudaMemcpy(h_C, d_C, size, cudaMemcpyDeviceToHost);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to copy vector C from device to host (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Verify that the result vector is correct
for (int i = 0; i < numElements; ++i)
{
if (fabs(h_A[i] + h_B[i] - h_C[i]) > 1e-5)
{
fprintf(stderr, "Result verification failed at element %d!\n", i);
exit(EXIT_FAILURE);
}
}
printf("Test PASSED\n");
// Free device global memory
err = cudaFree(d_A);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to free device vector A (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
err = cudaFree(d_B);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to free device vector B (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
err = cudaFree(d_C);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to free device vector C (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Free host memory
free(h_A);
free(h_B);
free(h_C);
printf("Done\n");
return 0;
}
8、验证是否可以从visual studio创建nvida工程
9、从windows到ubuntu开发环境
windows上面的vs环境调试比较方便，整体使用比较容易。对于开发嵌入式设备的朋友来说，在移植到nvidia jetson ubuntu环境之前，最好还是在windows环境上优化好，这样可以节省不少的时间。