DSPF_sp_mat_mul_gemm
[Matrix]

Collaboration diagram for DSPF_sp_mat_mul_gemm:

---

Detailed Description

void	DSPF_sp_mat_mul_gemm (float *x1, float const a, const int r1, const int c1, float *x2, const int c2, float *restrict y)

---

Function Documentation

void DSPF_sp_mat_mul_gemm	(	float *	x1,
		float const	a,
		const int	r1,
		const int	c1,
		float *	x2,
		const int	c2,
		float *restrict	y
	)

This function computes the expression y = a*x1*x2+y. The column dimension of x1 must match the row dimension of x2. The values stored in the matrices are assumed to be single-precision floating-point values. This code is suitable for dense matrices. No optimizations are made for sparse matrices.

Parameters:

	x1	= Pointer to r1 by c1 input matrix.
	a	= Scalar value.
	r1	= Number of rows in x1.
	c1	= Number of columns in x1. Also number of rows in x2.
	x2	= Pointer to c1 by c2 input matrix.
	c2	= Number of columns in x2.
	y	= Pointer to r1 by c2 output matrix.

Algorithm:

DSPF_sp_mat_mul_gemm.c is the natural C equivalent of the optimized intrinsic C code withoutrestrictions. Note that the intrinsic C code is optimized and restrictions may apply.

Assumptions:

The arrays x1, x2 and y are stored in distinct arrays. In-place processing is not allowed.
r1, c2 are assumed to be an interger multiple of 4. c1 is assumed to be even.

Implementation Notes:

Interruptibility : The code is interruptible.
Endian support : supports both Little and Big endian modes.

---

Copyright 2014, Texas Instruments Incorporated