1. 创建AddVectors.h文件
1. 创建AddVectors.h文件
#ifndef __ADDVECTORS_H__
#define __ADDVECTORS_H_
extern void addVectors(float*A, float*B, float*C, int size);
#endif// ____ADDVECTORS_H_
2.AddVectors.cu函数
#include "AddVectors.h"
#include "D:\MATLAB\R2014b\extern\include\mex.h"
__global__ void addVectorsMask(float*A, float*B, float*C, int size)
{
int i = blockIdx.x;
if(i>= size)
return;
C[i] = A[i] + B[i];
}
void addVectors(float*A, float*B, float*C, int size)
{
float *devPtrA = 0,*devPtrB = 0,*devPtrC = 0;
cudaMalloc(&devPtrA,sizeof(float)* size);
cudaMalloc(&devPtrB,sizeof(float)* size);
cudaMalloc(&devPtrC,sizeof(float)* size);
cudaMemcpy(devPtrA,A, sizeof(float)* size, cudaMemcpyHostToDevice);
cudaMemcpy(devPtrB,B, sizeof(float)* size, cudaMemcpyHostToDevice);
addVectorsMask<< <size,1>> >(devPtrA,devPtrB, devPtrC, size);
cudaMemcpy(C,devPtrC, sizeof(float)* size, cudaMemcpyDeviceToHost);
cudaFree(devPtrA);
cudaFree(devPtrB);
cudaFree(devPtrC);
}
3. AddVectors.cpp
文件
#include "mex.h"
#include "addVectors.h"
void mexFunction(int nlhs, mxArray *plhs[], int nrhs, mxArray *prhs[])
{
if (nrhs != 2)
mexErrMsgTxt("Invaid number of input arguments");
if (nlhs != 1)
mexErrMsgTxt("Invalid number of outputs");
if (!mxIsSingle(prhs[0]) && !mxIsSingle(prhs[1]))
mexErrMsgTxt("input vector data type must be single");
int numRowsA = (int)mxGetM(prhs[0]);
int numColsA = (int)mxGetN(prhs[0]);
int numRowsB = (int)mxGetM(prhs[1]);
int numColsB = (int)mxGetN(prhs[1]);
if (numRowsA != numRowsB || numColsA != numColsB)
mexErrMsgTxt("Invalid size. The sizes of two vectors must be same");
int minSize = (numRowsA < numColsA) ? numRowsA : numColsA;
int maxSize = (numRowsA > numColsA) ? numRowsA : numColsA;
if (minSize != 1)
mexErrMsgTxt("Invalid size. The vector must be one dimentional");
float* A = (float*)mxGetData(prhs[0]);
float* B = (float*)mxGetData(prhs[1]);
//create the output vector
plhs[0] = mxCreateNumericMatrix(numRowsA, numColsB, mxSINGLE_CLASS, mxREAL);
float* C = (float*)mxGetData(plhs[0]);
addVectors(A, B, C, maxSize);
}
4. runaddVectors.cpp
文件
clc
clear all
close all
disp('1.nvccAddVectors.cu compiling...');
system('nvcc -c AddVectors.cu -ccbin "D:\Microsoft Visual Studio 9.0\VC\bin"')
disp('nvcccompiling done!');
disp('2.C/C++ compiling for AddVectorsCuda.cpp withAddVectors.obj...');
mex AddVectors.cpp AddVectors.obj -lcudart -L"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v5.0\lib\x64"
disp('C/C++compiling done!');
disp('3.TestAddVectors()...');
disp('Twoinput arrays:');
A = single([1 2 3 4 5 6 7 8 9 10]);
B = single([10 9 8 7 6 5 4 3 2 1]);
C = AddVectors(A,B);
5.结果
A = single([1 2 3 4 5 6 7 8 9 10]);
B = single([10 9 8 7 6 5 4 3 2 1]);
C = AddVectorsCuda(A,B);
C = 11 11 11 11 11 11 11 11 11 11
6.可能出现的问题
出现错误提醒:
CUDA linking error - Visual Express 2008 - nvcc fatal due to (null) configuration file
解决办法:
Make sure that Windows SDK is targeting the correct version (7.0) by launching the Windows SDK Configuration Tool from start menu, choose the right version (v7.0), and click "Make Current".
Make sure to include the following directories for x64 compiling (under "Tools->Options->Projects And Solutions->VC++ Directories): C:\CUDA\bin64 C:\CUDA\lib64 C:\CUDA\include C:\Program Files (x86)\Microsoft Visual Studio 9.0\VC\bin\amd64
Now there's one other thing to change for a 64-bit system. Apparently the cuda compiler has a "hard-coded" directory for 64-bit compilers on Visual Express 2008. To make the fix, copy the needed file "vcvars64.bat" and rename it to "vcvarsamd64.bat" as follows:
C:\Program Files (x86)\Microsoft Visual Studio 9.0\VC\bin\vcvars64.bat
to
C:\Program Files (x86)\Microsoft Visual Studio 9.0\VC\bin\amd64\vcvarsamd64.bat