?gemm_compute

Perform general matrix multiplication on the packed A/B matrix.

That is, $\text{[math]}$ .

The value of op(X) may be $\text{[math]}$ . alpha and beta are multiplication coefficients; op(A) is an m*k matrix, op(B) is a k*n matrix, and C is an m*n matrix.

Interface Definition

C interface:

void cblas_sgemm_compute(const enum CBLAS_ORDER order, const enum CBLAS_TRANSPOSE transA, const enum CBLAS_TRANSPOSE transB, const BLASINT m, const BLASINT n, const BLASINT k, const float alpha, const float *a, const BLASINT lda, const float *b, const BLASINT ldb, const float beta, float *c, const BLASINT ldc);

void cblas_dgemm_compute(const enum CBLAS_ORDER order, const enum CBLAS_TRANSPOSE transA, const enum CBLAS_TRANSPOSE transB, const BLASINT m, const BLASINT n, const BLASINT k, const double alpha, const double *a, const BLASINT lda, const double *b, const BLASINT ldb, const double beta, double *c, const BLASINT ldc);

void cblas_cgemm_compute(const enum CBLAS_ORDER order, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_TRANSPOSE TransB, const BLASINT m, const BLASINT n, const BLASINT k, const void *alpha, const void *a, const BLASINT lda, const void *b, const BLASINT ldb, const void *beta, void *c, const BLASINT ldc);

void cblas_zgemm_compute(const enum CBLAS_ORDER order, const enum CBLAS_TRANSPOSE TransA, const enum CBLAS_TRANSPOSE TransB, const BLASINT m, const BLASINT n, const BLASINT k, const void *alpha, const void *a, const BLASINT lda, const void *b, const BLASINT ldb, const void *beta, void *c, const BLASINT ldc);

void cblas_bgemm_compute(const enum CBLAS_ORDER order, const enum CBLAS_TRANSPOSE transA, const enum CBLAS_TRANSPOSE transB, const BLASINT m, const BLASINT n, const BLASINT k, const __bf16 alpha, const __bf16 *a, const BLASINT lda, const __bf16 *b, const BLASINT ldb, const __bf16 beta, __bf16 *c, const BLASINT ldc);

void cblas_sbgemm_compute(const enum CBLAS_ORDER order, const enum CBLAS_TRANSPOSE transA, const enum CBLAS_TRANSPOSE transB, const BLASINT m, const BLASINT n, const BLASINT k, const __bf16 alpha, const __bf16 *a, const BLASINT lda, const __bf16 *b, const BLASINT ldb, const __bf16 beta, float *c, const BLASINT ldc);

Parameters

Parameter	Type	Description	Input/Output
order	Enumeration type CBLAS_ORDER	Whether the matrix is in row-major order or column-major order.	Input
TransA	Enumeration type CBLAS_TRANSPOSE	Whether matrix A is a conventional matrix, a transposed matrix, or a conjugate matrix. If trans = CblasNoTrans, $\text{[math]}$ . If trans = CblasTrans, $\text{[math]}$ .	Input
TransB	Enumeration type CBLAS_TRANSPOSE	Whether matrix B is a conventional matrix, a transposed matrix, or a conjugate matrix. If trans = CblasNoTrans, $\text{[math]}$ . If trans = CblasTrans, $\text{[math]}$ .	Input
M	Integer	Number of rows of matrix op(A) and matrix C.	Input
N	Integer	Number of columns of matrix op(B) and matrix C.	Input
K	Integer	Number of columns of matrix op(A) and number of rows of matrix op(B).	Input
alpha	Single-precision floating-point type for sgemm. Double-precision floating-point type for dgemm. Single-precision complex type for cgemm. Double-precision complex type for zgemm. Half-precision floating-point type for bgemm. Half-precision floating-point type for sbgemm.	Multiplication coefficient.	Input
A	Single-precision floating-point type for sgemm. Double-precision floating-point type for dgemm. Single-precision complex type for cgemm. Double-precision complex type for zgemm. Half-precision floating-point type for bgemm. Half-precision floating-point type for sbgemm.	Matrix A.	Input
lda	Integer	For column-major matrices, if TransA = CblasNoTrans, lda must be at least max(1, m); otherwise, it must be at least max(1, k). For row-major matrices, if TransA = CblasNoTrans, lda must be at least max(1, k); otherwise, it must be at least max(1, m).	Input
B	Single-precision floating-point type for sgemm. Double-precision floating-point type for dgemm. Single-precision complex type for cgemm. Double-precision complex type for zgemm. Half-precision floating-point type for bgemm. Half-precision floating-point type for sbgemm.	Matrix B.	Input
ldb	Integer	For column-major matrices, if TransB = CblasNoTrans, ldb must be at least max(1, k); otherwise, it must be at least max(1, n). For row-major matrices, if TransB = CblasNoTrans, ldb must be at least max(1, n); otherwise, it must be at least max(1, k).	Input
beta	Single-precision floating-point type for sgemm. Double-precision floating-point type for dgemm. Single-precision complex type for cgemm. Double-precision complex type for zgemm. Half-precision floating-point type for bgemm. Single-precision floating-point type for sbgemm.	Multiplication coefficient.	Input
C	Single-precision floating-point type for sgemm. Double-precision floating-point type for dgemm. Single-precision complex type for cgemm. Double-precision complex type for zgemm. Half-precision floating-point type for bgemm. Single-precision floating-point type for sbgemm.	Matrix C.	Input/Output
ldc	Integer	For column-major matrices, ldc must be at least max(1, m); otherwise, it must be at least max(1, n).	Input

Dependency

#include "kblas.h"

Examples

C interface:

    int m = 4, k = 3, n = 4, lda = 4, ldb = 3, ldc = 4; 
    float alpha = 1.0, beta = 2.0; 
     /* 
     * A: 
     *     0.340188,       0.411647,       -0.222225, 
     *     -0.105617,      -0.302449,      0.053970, 
     *     0.283099,       -0.164777,      -0.022603, 
     *     0.298440,       0.268230,       0.128871, 
     * B: 
     *     -0.135216,      0.416195,       -0.358397,      -0.257113, 
     *     0.013401,       0.135712,       0.106969,       -0.362768, 
     *     0.452230,       0.217297,       -0.483699,      0.304177, 
     * C: 
     *     -0.343321,      0.498924,       0.112640,       -0.006417, 
     *     -0.099056,      -0.281743,      -0.203968,      0.472775, 
     *     -0.370210,      0.012932,       0.137552,       -0.207483, 
     *     -0.391191,      0.339112,       0.024287,       0.271358, 
     */ 
    float a[12] = {0.340188, -0.105617, 0.283099, 
                    0.298440, 0.411647, -0.302449, 
                    -0.164777, 0.268230, -0.222225, 
                    0.053970, -0.022603, 0.128871}; 
    float b[12] = {-0.135216, 0.013401, 0.452230, 0.416195, 
                    0.135712, 0.217297, -0.358397, 0.106969, 
                    -0.483699, -0.257113, -0.362768, 0.304177}; 
    float c[16] = {-0.343321, -0.099056, -0.370210, -0.391191, 
                    0.498924, -0.281743, 0.012932, 0.339112, 
                    0.112640, -0.203968, 0.137552, 0.024287, 
                    -0.006417, 0.472775, -0.207483, 0.271358}; 
    size_t size_a = cblas_sgemm_pack_get_size(CblasA, m, n, k);
    size_t size_b = cblas_sgemm_pack_get_size(CblasB, m, n, k);
    float *sa = (float *)malloc(size_a);
    float *sb = (float *)malloc(size_b);
    cblas_sgemm_pack(CblasColMajor, CblasA, CblasNoTrans, m, n, k, a, ld, sa);
    cblas_sgemm_pack(CblasColMajor, CblasB, CblasNoTrans, m, n, k, b, ld, sb);
    cblas_sgemm_compute(CblasColMajor,CblasNoTrans,CblasNoTrans, m, n, k, alpha, sa, lda, sb, ldb, beta, c, ldc); 
    free(sa);
    free(sb);
    /* 
     * Output C: 
     *     -0.827621       1.147010        0.254881        -0.317229 
     *     -0.163476       -0.636762       -0.428542       1.098841 
     *     -0.791128       0.116416        0.166949        -0.434854 
     *     -0.760862       0.866839        -0.092028       0.407877 
     * 
     */

Parent topic: KML_BLAS-like extensions