Question

在某些优化问题中，我必须使用intel mkl，因此在cygwin的Win7 64bit下测试以下标准代码，以确保我已正确设置它：

In [135]: res = np.empty((3,5), object)                                                                      
In [136]: res                                                                                                
Out[136]: 
array([[None, None, None, None, None],
       [None, None, None, None, None],
       [None, None, None, None, None]], dtype=object)
In [137]: res.flat[:11] = np.arange(1,12)                                                                    
In [138]: res                                                                                                
Out[138]: 
array([[1, 2, 3, 4, 5],
       [6, 7, 8, 9, 10],
       [11, None, None, None, None]], dtype=object)

为了进行编译，我首先必须链接MKL库，如文档的第3步所示： https://software.intel.com/en-us/articles/intel-math-kernel-library-intel-mkl-2018-getting-started

例如，在Windows下，我们已设置：

    #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(R) 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(R) 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");
        }
        printf ("\n Deallocating memory \n\n");
        mkl_free(A);
        mkl_free(B);
        mkl_free(C);
        printf (" Example completed. \n\n");
        return 0;
    }

或在Linux下：

> ..\compilers_and_libraries_2018\windows\mkl\bin\mklvars.bat" ia32
>  cl.exe mkl_lab_solution.c  mkl_intel_c.lib mkl_core.lib mkl_intel_thread.lib libiomp5md.lib

但是我陷入了第一个命令行，即当我

1) if with gcc $source /opt/intel/compilers_and_libraries_2018/linux/mkl/bin/mklvars.sh ia32 $gcc -m32 mkl_lab_solution.c -lmkl_intel -lmkl_intel_thread -lmkl_core -liomp5 -lpthread -lm

它显示gcc -o temp temp.c -mkl

我知道这意味着我没有在第一个命令行中设置环境，但是在谷歌搜索后现在不知道并尝试在Intel Parallel Studio XE 2018下进行编译。

在Cygwin下链接英特尔MKL

0 个答案: