Java 本地调用连接 Intel 数学核心库

/* DO NOT EDIT THIS FILE - it is machine generated */
#include <jni.h>
/* Header for class com_haswalk_jblas_JBlas */

#ifndef _Included_com_haswalk_jblas_JBlas
#define _Included_com_haswalk_jblas_JBlas
#ifdef __cplusplus
extern "C" {
#endif

/*
 * Class:     com_haswalk_jblas_JBlas
 * Method:    dgemm
 * Signature: (IIIIIID[DI[DID[DI)V
 */
JNIEXPORT void JNICALL Java_com_haswalk_jblas_JBlas_dgemm
  (JNIEnv *, jclass, jint, jint, jint, jint, jint, jint, jdouble, jdoubleArray, jint, jdoubleArray, jint, jdouble, jdoubleArray, jint);

#ifdef __cplusplus
}
#endif
#endif

#include <jni.h>
#include <assert.h>
#include "mkl_cblas.h"

#ifndef _Included_com_haswalk_jblas_JBlas
#define _Included_com_haswalk_jblas_JBlas
#ifdef __cplusplus
extern "C" {
#endif

/*
 * Class:     com_haswalk_jblas_JBlas
 * Method:    dgemm
 * Signature: (IIIIIID[DI[DID[DI)V
 */
JNIEXPORT void JNICALL Java_com_haswalk_jblas_JBlas_dgemm
  (JNIEnv * env, jclass clazz, jint order, jint transA, jint transB, jint m, jint n, jint k, 
  jdouble alpha, jdoubleArray A, jint LDA, jdoubleArray B, jint LDB, jdouble beta, jdoubleArray C, jint LDC){
	  
	jdouble *aElems, *bElems, *cElems;
	//将 Java 数组拷贝到 C 数组中
	aElems = (*env) -> GetDoubleArrayElements(env, A, NULL);
	bElems = (*env) -> GetDoubleArrayElements(env, B, NULL);
	cElems = (*env) -> GetDoubleArrayElements(env, C, NULL);
	assert(aElems && bElems && cElems);
	//计算
	cblas_dgemm((CBLAS_ORDER) order, (CBLAS_TRANSPOSE) transA, 
	(CBLAS_TRANSPOSE) transB, (int)m, (int)n, (int)k, alpha, aElems, (int)LDA, bElems, (int)LDB, beta, cElems, (int)LDC);
	//释放资源
	(*env) -> ReleaseDoubleArrayElements(env, C, cElems, 0);
	(*env) -> ReleaseDoubleArrayElements(env, B, bElems, JNI_ABORT);
	(*env) -> ReleaseDoubleArrayElements(env, A, aElems, JNI_ABORT);
  }

#ifdef __cplusplus
}
#endif
#endif

#include <stdio.h>
#include <stdlib.h>
#include "mkl.h"

int main()
{
    double *A, *B, *C;
    int m, n, p, i, j;
    double alpha, beta;

    m = 2000, p = 200, n = 1000;
    alpha = 1.0; beta = 0.0;

    A = (double *)mkl_malloc( m*p*sizeof( double ), 64 );
    B = (double *)mkl_malloc( p*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*p); i++) {
        A[i] = (double)(i+1);
    }

    for (i = 0; i < (p*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");
	
	printf(" Warmup...\n\n");
	for(i = 0; i < 10; i++) {
		cblas_dgemm(CblasRowMajor, CblasNoTrans, CblasNoTrans, 
                m, n, p, alpha, A, p, B, n, beta, C, n);
	}
	
	double s_initial, s_elapsed, total;
	printf(" Loop...\n\n");
	
	for(int i = 0; i < 10; i++) {
		s_initial = dsecnd();
		cblas_dgemm(CblasRowMajor, CblasNoTrans, CblasNoTrans, 
                m, n, p, alpha, A, p, B, n, beta, C, n);
		s_elapsed = dsecnd() - s_initial;
		total += s_elapsed;
		printf(" Iteration %d: %5f\n", i, s_elapsed * 1000);

	}
	printf("\n Average time: %5f\n", total /10.0 * 1000);
	printf ("\n Computations completed.\n\n");

    mkl_free(A);
    mkl_free(B);
    mkl_free(C);

    return 0;
}
/*
 Iteration 0: 36870.120442
 Iteration 1: 34055.884578
 Iteration 2: 41175.512597
 Iteration 3: 39219.469414
 Iteration 4: 37622.348522
 Iteration 5: 31426.735572
 Iteration 6: 31998.701277
 Iteration 7: 33684.410388
 Iteration 8: 38041.815511
 Iteration 9: 35845.068516

 Average time: 35994.006682
*/