转自:https://blog.csdn.net/caoenze/article/details/46699327
mkl 使用手册下载:http://download.csdn.net/detail/caoenze/8855821
- 从intel官网下载c_studio_xe_2013_sp1_update3_setup.exe文件(完全离线安装包)
- 双击.exe文件,自动提取文件并进入安装引导
- 安装完成后,配置VS2010(前提是本机已正确安装过VS2010)
- 新建一C++项目,比如win32控制台项目:MKL_TEST
- 点击菜单栏 项目——》MKL_TEST属性——》配置属性——》VC++目录:
可执行文件目录添加:C:\Program Files (x86)\Intel\Composer XE\mkl\bin\ia32
包含目录添加:C:\Program Files (x86)\Intel\Composer XE\mkl\include
库目录添加:C:\Program Files (x86)\Intel\Composer XE\mkl\lib\ia32
注意:包含目录不区分ia32和intel64
Bin和lib目录区分ia32和intel64根据自己的CPU架构选择。
IA32可以认为是X86或者X86-32
Intel64:intel与HP联合开发的64-bits全新架构,与X86不兼容,没有太大市场。
6 、连接器——》输入
附加依赖项:添加
mkl_intel_c.lib
mkl_intel_thread.lib
mkl_core.lib
libiomp5mt.lib//我只添加了前三个,添加第4个,编译时提示找不到此库
7、配置属性——Intel Performance Library
右侧Use Intel MKL :
选择Parallel
其它两项可以选择性配置,不配置也可以。
8、至此,VS2010调用MKL已配置完毕,可在MKL_TEST项目里添加源文件main.c 测试代码如下:
#define min(x,y) (((x) < (y)) ? (x) : (y))
#include <stdio.h>
#include <stdlib.h>
#include "mkl.h"
int main()
{
double *A, *B, *C;
int m, n, k, i, j;
double alpha, beta;
printf ("\n This example computes real matrix C=alpha*A*B+beta*C using \n"
" Intel® MKL function dgemm, where A, B, and C are matrices and \n"
" alpha and beta are double precision scalars\n\n");
m = 2000, k = 200, n = 1000;
printf (" Initializing data for matrix multiplication C=A*B for matrix \n"
" A(%ix%i) and matrix B(%ix%i)\n\n", m, k, k, n);
alpha = 1.0; beta = 0.0;
printf (" Allocating memory for matrices aligned on 64-byte boundary for better \n"
" performance \n\n");
A = (double *)mkl_malloc( m*k*sizeof( double ), 64 );
B = (double *)mkl_malloc( k*n*sizeof( double ), 64 );
C = (double *)mkl_malloc( m*n*sizeof( double ), 64 );
if (A == NULL || B == NULL || C == NULL) {
printf( "\n ERROR: Can't allocate memory for matrices. Aborting... \n\n");
mkl_free(A);
mkl_free(B);
mkl_free(C);
return 1;
}
printf (" Intializing matrix data \n\n");
for (i = 0; i < (m*k); i++) {
A[i] = (double)(i+1);
}
for (i = 0; i < (k*n); i++) {
B[i] = (double)(-i-1);
}
for (i = 0; i < (m*n); i++) {
C[i] = 0.0;
}
printf (" Computing matrix product using Intel® MKL dgemm function via CBLAS interface \n\n");
cblas_dgemm(CblasRowMajor, CblasNoTrans, CblasNoTrans,
m, n, k, alpha, A, k, B, n, beta, C, n);
printf ("\n Computations completed.\n\n");
printf (" Top left corner of matrix A: \n");
for (i=0; i<min(m,6); i++) {
for (j=0; j<min(k,6); j++) {
printf ("%12.0f", A[j+i*k]);
}
printf ("\n");
}
printf ("\n Top left corner of matrix B: \n");
for (i=0; i<min(k,6); i++) {
for (j=0; j<min(n,6); j++) {
printf ("%12.0f", B[j+i*n]);
}
printf ("\n");
}
printf ("\n Top left corner of matrix C: \n");
for (i=0; i<min(m,6); i++) {
for (j=0; j<min(n,6); j++) {
printf ("%12.5G", C[j+i*n]);
}
printf ("\n");
}
getchar();
printf ("\n Deallocating memory \n\n");
mkl_free(A);
mkl_free(B);
mkl_free(C);
printf (" Example completed. \n\n");
return 0;
}