原文: http://blog.csdn.NET/u012234115/article/details/34860273
在做項目集成的時候需要用到cpp和cuda文件聯調,自己摸索了兩種方式實現cpp和cu文件混合編譯。
本文環境:
- windows7 64位
- VS2010
- CUDA5.5
- 英偉達顯卡Tesla C1060
前言
CUDA_BIN_PATH %CUDA_PATH%\bin
CUDA_LIB_PATH %CUDA_PATH%\lib\Win32
CUDA_SDK_BIN %CUDA_SDK_PATH%\bin\Win32
CUDA_SDK_LIB %CUDA_SDK_PATH%\common\lib\Win32
CUDA_SDK_PATH C:\cuda\cudasdk\common
方法一:先建立cuda工程,再添加cpp文件
1.打開vs2010,新建一個cuda項目,名稱CudaCpp。
2.cuda默認建立的工程是如下,實現了兩個一維向量的並行相加。kernel函數和執行函數還有main函數全都寫在了一個cu文件裏。
3.接下來在工程裏添加一個空的cpp文件。將原來cu文件裏main函數裏的內容剪切到cpp文件main函數裏。
爲了讓cpp能夠調用cu文件裏面的函數,在addWithCuda函數前加上extern “C” 關鍵字 (注意C大寫,爲什麼addKernel不用加呢?因爲cpp裏面直接調用的是addWithCuda)
4.在cpp裏也要加上addWithCuda函數的完整前向聲明。下圖就是工程的完整結構
5.可以在cpp裏的main函數return之間加入getchar()防止運行後一閃就退出,加上system(“pause”)或者直接ctrl+F5也行。
運行結果:
下面貼出CudaCpp項目代碼。
kernel.cu
- #include “cuda_runtime.h”
- #include “device_launch_parameters.h”
- #include <stdio.h>
- __global__ void addKernel(int *c, const int *a, const int *b)
- {
- int i = threadIdx.x;
- c[i] = a[i] + b[i];
- }
- // Helper function for using CUDA to add vectors in parallel.
- extern “C”
- 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;
- // Choose which GPU to run on, change this on a multi-GPU system.
- cudaStatus = cudaSetDevice(0);
- if (cudaStatus != cudaSuccess) {
- fprintf(stderr, “cudaSetDevice failed! Do you have a CUDA-capable GPU installed?”);
- goto Error;
- }
- // 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;
- }
- // 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;
- }
- #include <stdio.h>
- #include “cuda_runtime.h”
- #include “device_launch_parameters.h”
- extern “C”
- cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size);
- 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]);
- printf(”cuda工程中調用cpp成功!\n”);
- // 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;
- }
- getchar(); //here we want the console to hold for a while
- return 0;
- }
方法二:先建立cpp工程,再添加cu文件
方法一由於是cuda工程是自動建立的,所以比較簡單,不需要多少額外的配置。而在cpp工程裏面添加cu就要複雜一些。爲了簡單起見,這裏採用console程序講解,至於MFC或者Direct3D程序同理。
1.建立一個空的win32控制檯工程,名稱CppCuda。
2.然後右鍵工程–>添加一個cu文件
3.將方法一中cu和cpp文件的代碼分別拷貝到這個工程裏來(做了少許修改,extern “C”關鍵字和某些頭文件不要忘了加),工程結構如圖:
這個時候編譯是通不過的,需要作一些配置。
4.關鍵的一步,右鍵工程–>生成自定義 ,將對話框中CUDA5.5前面的勾打上。
這時點擊 工程–>屬性,會發現多了CUDA鏈接器這一項。
5.關鍵的一步,右鍵kernel.cu文件–>屬性,在 常規–>項類型 裏面選擇CUDA C/C++(由於cu文件是由nvcc編譯的,這裏要修改編譯鏈接屬性)
6.工程–>屬性–>鏈接器–>附加依賴項,加入cudart.lib
7.工具–>選項–>文本編輯器–>文件擴展名 添加cu \cuh兩個文件擴展名
8.至此配置成功。運行一下:
9.爲了更加確信cuda中的函數確實被調用,在main.cpp裏面調用cuda函數的地方加入了一個斷點。
單步執行一下。
可以看到程序跳到了cu文件裏去執行了,說明cpp調用cuda函數成功。
貼上代碼(其實跟方式一基本一樣,沒怎麼改),工程CppCuda
kernel.cu
- #include “cuda_runtime.h”
- #include “device_launch_parameters.h”
- #include <stdio.h>
- //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];
- }
- // Helper function for using CUDA to add vectors in parallel.
- extern “C”
- 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;
- // Choose which GPU to run on, change this on a multi-GPU system.
- cudaStatus = cudaSetDevice(0);
- if (cudaStatus != cudaSuccess) {
- fprintf(stderr, “cudaSetDevice failed! Do you have a CUDA-capable GPU installed?”);
- goto Error;
- }
- // 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;
- }
- // 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;
- }
- #include <iostream>
- #include “cuda_runtime.h”
- #include “device_launch_parameters.h”
- using namespace std;
- extern “C”
- cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size);
- int main(int argc,char **argv)
- {
- 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;
- }
- cout<<”{1,2,3,4,5} + {10,20,30,40,50} = {“<<c[0]<<‘,’<<c[1]<<‘,’<<c[2]<<‘,’<<c[3]<<‘}’<<endl;
- printf(”cpp工程中調用cu成功!\n”);
- // 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;
- }
- system(”pause”); //here we want the console to hold for a while
- return 0;
- }