Documentation
Rate This Document
Findability
Accuracy
Completeness
Readability
SubmitClose

?omatmul

Perform scaling and multiplication of two matrices including their out-of-place transposition/copying.

That is, .

Interface Definition

C interface:

void cblas_somatmul(const enum CBLAS_ORDER ordering, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_TRANSPOSE TransB, const BLASINT m, const BLASINT n, const float alpha, float *A, const BLASINT lda, float *B, const BLASINT ldb, float *C, const BLASINT ldc);

void cblas_domatmul(const enum CBLAS_ORDER ordering, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_TRANSPOSE TransB, const BLASINT m, const BLASINT n, const double alpha, double *A, const BLASINT lda, double *B, const BLASINT ldb, double *C, const BLASINT ldc);

void cblas_comatmul(const enum CBLAS_ORDER ordering, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_TRANSPOSE TransB, const BLASINT m, const BLASINT n, const float *alpha, float *A, const BLASINT lda, float *B, const BLASINT ldb, float *C, const BLASINT ldc);

void cblas_zomatmul(const enum CBLAS_ORDER ordering, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_TRANSPOSE TransB, const BLASINT m, const BLASINT n, const double *alpha, double *A, const BLASINT lda, double *B, const BLASINT ldb, double *C, const BLASINT ldc);

Fortran interface:

CALL SOMATMUL(ORDER, TRANSA, TRANSB, M, N, ALPHA, A, LDA, B, LDB, C, LDC)

CALL DOMATMUL(ORDER, TRANSA, TRANSB, M, N, ALPHA, A, LDA, B, LDB, C, LDC)

CALL COMATMUL(ORDER, TRANSA, TRANSB, M, N, ALPHA, A, LDA, B, LDB, C, LDC)

CALL ZOMATMUL(ORDER, TRANSA, TRANSB, M, N, ALPHA, A, LDA, B, LDB, C, LDC)

Parameters

Parameter

Type

Description

Input/Output

order

Enumeration type CBLAS_ORDER

Indicates whether the matrix is in row- or column-major order.

Input

TransA

Enumeration type CBLAS_TRANSPOSE

Indicates whether matrix A is a conventional matrix, a transpose matrix, or a conjugate matrix.

  • If TransA = CblasNoTrans, op(A) = A.
  • If TransA = CblasTrans, op(A) = A'.
  • If TransA = CblasConjNoTrans, op(A) = conj(A).
  • If TransA = CblasConjTrans, op(A) = conj(A').

Input

TransB

Enumeration type CBLAS_TRANSPOSE

Indicates whether matrix B is a conventional matrix, a transpose matrix, or a conjugate matrix.

  • If TransB = CblasNoTrans, op(B) = B.
  • If TransB = CblasTrans, op(B) = B'.
  • If TransB = CblasConjNoTrans, op(B) = conj(B).
  • If TransB = CblasConjTrans, op(B) = conj(B').

Input

M

Integer

Number of rows of matrices op (A), op (B), and C.

Input

N

Integer

Number of columns of matrices op (A), op (B), and C.

Input

alpha
  • Single-precision floating-point type for somatmul
  • Double-precision floating-point type for domatmul
  • Single-precision complex type for comatmul
  • Double-precision complex type for zomatmul

Multiplication coefficient.

Input

A
  • Single-precision floating-point type for somatmul
  • Double-precision floating-point type for domatmul
  • Single-precision complex type for comatmul
  • Double-precision complex type for zomatmul

Matrix A.

Input

lda

Integer
  • If matrix A is column store and TransA = CblasNoTrans, lda is at least max(1, m); otherwise, lda is at least max(1, n).
  • If matrix A is row store and TransA = CblasNoTrans, lda is at least max(1, n); otherwise, lda is at least max(1, m).

Input

B
  • Single-precision floating-point type for somatmul
  • Double-precision floating-point type for domatmul
  • Single-precision complex type for comatmul
  • Double-precision complex type for zomatmul

Matrix B.

Input

ldb

Integer
  • If the matrix is column store and TransB = CblasNoTrans, ldb is at least max(1, m); otherwise, ldb is at least max(1, n).
  • If the matrix is row store and TransB = CblasNoTrans, ldb is at least max(1, n); otherwise, ldb is at least max(1, m).

Input

C
  • Single-precision floating-point type for somatmul
  • Double-precision floating-point type for domatmul
  • Single-precision complex type for comatmul
  • Double-precision complex type for zomatmul

Matrix C.

Output

ldc

Integer

If the matrix is column store, ldc must be at least max(1, m). Otherwise, ldc must be at least max(1, n).

Input

Dependency

#include "kblas.h"

Examples

C interface:

    int m = 4;
    int n = 3;
    int lda = 4;
    int ldb = 4;
    int ldc = 4;
    float alpha = 2.0;

    /** 
     *    A: 
     *         -0.399988, -0.211286, 0.226351,           
     *         0.057980, 0.185737, 0.015954,     
     *         -0.181192, 0.092167, -0.125647,     
     *         0.206140, -0.441963, -0.307887       
     *    B: 
     *         0.274879, -0.184964, -0.331672,              
     *         -0.476422, 0.318246, 0.295214,     
     *         -0.067229, 0.314890, -0.072014,     
     *         -0.088924, -0.222191, -0.121713,     
     *    C: 
     *         0, 0, 0,
     *         0, 0, 0,
     *         0, 0, 0,
     *         0, 0, 0
     */

    float a[12] = {-0.399988, -0.211286, 0.226351,
                   0.057980, 0.185737, 0.015954,
                   -0.181192, 0.092167, -0.125647,
                   0.206140, -0.441963, -0.307887
    };

    float b[12] = {0.274879, -0.184964, -0.331672,
                   -0.476422, 0.318246, 0.295214,
                   -0.067229, 0.314890, -0.072014,
                   -0.088924, -0.222191, -0.121713,
    };

    float c[12] = {0};

    cblas_somatmul(CblasColMajor, CblasNoTrans, CblasNoTrans, m, n, alpha, a, lda, b, ldb, c, ldc);

    /** 
     * Output C: 
     *        -0.219897, 0.078161, -0.150148,      
     *        -0.055246, 0.118220, 0.009419,
     *        0.024363, 0.058045, 0.018097, 
     *        -0.036661, 0.196401, 0.074947
     */

Fortran interface:

      PROGRAM OMATMUL
      INTEGER :: M=4, N=3
      INTEGER :: LDA=4, LDB=4, LDC=4
      REAL(4) :: ALPHA=2.0
      REAL(4) :: A(4, 3), B(4, 3), C(4, 3)
      DATA A/-0.399988, -0.211286, 0.226351,
             0.057980, 0.185737, 0.015954,
             -0.181192, 0.092167, -0.125647,
             0.206140, -0.441963, -0.307887/
      DATA B/0.274879, -0.184964, -0.331672,
             -0.476422, 0.318246, 0.295214,
             -0.067229, 0.314890, -0.072014,
             -0.088924, -0.222191, -0.121713/
      DATA C/0.0, 0.0, 0.0,
             0.0, 0.0, 0.0,
             0.0, 0.0, 0.0/
      EXTERNAL SOMATMUL
      CALL SOMATMUL('C', 'N', 'N', M, N, ALPHA, A, LDA, B, LDB, C, LDC)
      END

     * Output C: 
     *        -0.219897, 0.078161, -0.150148,      
     *        -0.055246, 0.118220, 0.009419,
     *        0.024363, 0.058045, 0.018097,
     *        -0.036661, 0.196401, 0.074947
Parent topic: KML_BLAS-like Extensions