Header containing mangled F77 BLAS routine names. More...

#include <oski/config.h>

Defines
#define	INC_OSKI_BLAS_NAMES_H
	blas_names.h included.
#define	F77_FUNC(x, y) x
	Default definition for F77_FUNC if none exists.
Macros for creating BLAS routine names.
#define	MAKE_BLAS_NAME0(tag, name, TAG, NAME) F77_FUNC(tag ## name, TAG ## NAME)
	Creates an Fortran-77 name by concatenating a type tag and a base name.
#define	MAKE_BLAS_NAME0_I(itag, tag, name, ITAG, TAG, NAME) F77_FUNC(itag ## tag ## name, ITAG ## TAG ## NAME)
	Generate a non-standard BLAS name which includes an additional prefix to indicate the integer precision.
#define	MAKE_BLAS_NAME1(tag, name, TAG, NAME) MAKE_BLAS_NAME0(tag, name, TAG, NAME)
	Creates a Fortran 77 name by concatenating a type tag and a base name.
#define	MAKE_BLAS_NAME1_I(itag, tag, name, ITAG, TAG, NAME) MAKE_BLAS_NAME0_I(itag, tag, name, ITAG, TAG, NAME)
	Generates a non-standard BLAS name which includes an additional prefix to indicate the integer precision.
#define	MAKE_BLAS_NAME(name, NAME) MAKE_BLAS_NAME1(VAL_TAG, name, VAL_TAG_CAPS, NAME)
	Make the standard name of a BLAS routine.
#define	MAKE_BLAS_NAME_I(name, NAME)
	Make the non-standard name of a BLAS routine which uses a non-standard integer precision.
BLAS routine names, hidden behind macros.
#define	BLAS_xSCAL MAKE_BLAS_NAME_I(scal, SCAL)
#define	BLAS_xAXPY MAKE_BLAS_NAME_I(axpy, AXPY)
#define	BLAS_xGEMV MAKE_BLAS_NAME_I(gemv, GEMV)
#define	BLAS_xTRSV MAKE_BLAS_NAME_I(trsv, TRSV)
Functions
void	BLAS_xSCAL (const oski_index_t len, oski_value_t alpha, oski_value_t x, const oski_index_t stride)
	BLAS vector scale routine, ?scal, which computes $x \leftarrow \alpha\cdot x$ .
void	BLAS_xAXPY (const oski_index_t len, const oski_value_t alpha, const oski_value_t x, const oski_index_t incx, oski_value_t y, const oski_index_t incy)
	BLAS vector AXPY operation, ?axpy, which computes $y \leftarrow y + \alpha\cdot x$ .
void	BLAS_xGEMV (const char op, const oski_index_t m, const oski_index_t n, const oski_value_t alpha, const oski_value_t A, const oski_index_t lda, const oski_value_t x, const oski_index_t incx, const oski_value_t beta, oski_value_t y, const oski_index_t *incy)
	BLAS matrix-vector multiply routine, ?gemv, which computes the dense matrix-vector multiply operation, $y \leftarrow \beta\cdot y + \alpha\cdot\mathrm{op}(A)\cdot x$ .
void	BLAS_xTRSV (const char shape, const char op, const char diag, const oski_index_t n, const oski_value_t A, const oski_index_t lda, oski_value_t x, const oski_index_t incx)
	BLAS triangular solve routine, ?trsv, which computes dense triangular solve operation, $x \leftarrow \mathrm{op}(A^{-1})\cdot x$ .

Detailed Description

Header containing mangled F77 BLAS routine names.

This file depends on config.h, and so is intended for use only at library build time.

Define Documentation

#define INC_OSKI_BLAS_NAMES_H

blas_names.h included.

#define MAKE_BLAS_NAME	(	name,
		NAME
	)	MAKE_BLAS_NAME1(VAL_TAG, name, VAL_TAG_CAPS, NAME)

Make the standard name of a BLAS routine.

Given the base BLAS routine name, in both lowercase and uppercase versions (e.g., gemm and GEMM, trsv and TRSV), create a Fortran 77 compatible name, given the C-to-Fortran calling conventions determined at configure time.

#define MAKE_BLAS_NAME0	(	tag,
		name,
		TAG,
		NAME
	)	F77_FUNC(tag ## name, TAG ## NAME)

Creates an Fortran-77 name by concatenating a type tag and a base name.

This macro directly concatenates. To allow for macro expansion, see MAKE_BLAS_NAME1().

Parameters:

[in]	tag	Lowercase, single-letter type tag.
[in]	name	Lowercase base name.
[in]	TAG	Uppercase, single-letter type tag.
[in]	NAME	Uppercase base name.

Returns:: A Fortran 77 name following the naming conventions determined at configure-time (e.g., adding a trailing underscore).

See also:: MAKE_BLAS_NAME1(); F77_FUNC()

#define MAKE_BLAS_NAME1	(	tag,
		name,
		TAG,
		NAME
	)	MAKE_BLAS_NAME0(tag, name, TAG, NAME)

Creates a Fortran 77 name by concatenating a type tag and a base name.

This macro immediately calls MAKE_BLAS_NAME0(), thereby allowing the tags and base names to be macros that are expanded just before concatenation.

See also:: MAKE_BLAS_NAME0()

#define MAKE_BLAS_NAME_I	(	name,
		NAME
	)

Value:

MAKE_BLAS_NAME1_I(IND_TAG, VAL_TAG, name, \
                          IND_TAG_CAPS, VAL_TAG_CAPS, NAME)

Make the non-standard name of a BLAS routine which uses a non-standard integer precision.

Function Documentation

void BLAS_xAXPY	(	const oski_index_t *	len,
		const oski_value_t *	alpha,
		const oski_value_t *	x,
		const oski_index_t *	incx,
		oski_value_t *	y,
		const oski_index_t *	incy
	)

BLAS vector AXPY operation, ?axpy, which computes $y \leftarrow y + \alpha\cdot x$ .

Parameters:

[in]	len	Length of x and y.
[in]	alpha	Scalar multiplier, $\alpha$ .
[in]	x	Vector .
[in]	incx	Distance between consecutive elements of .
[in,out]	y	Vector .
[in]	incy	Distance between consecutive elements of .

void BLAS_xGEMV	(	const char *	op,
		const oski_index_t *	m,
		const oski_index_t *	n,
		const oski_value_t *	alpha,
		const oski_value_t *	A,
		const oski_index_t *	lda,
		const oski_value_t *	x,
		const oski_index_t *	incx,
		const oski_value_t *	beta,
		oski_value_t *	y,
		const oski_index_t *	incy
	)

BLAS matrix-vector multiply routine, ?gemv, which computes the dense matrix-vector multiply operation, $y \leftarrow \beta\cdot y + \alpha\cdot\mathrm{op}(A)\cdot x$ .

Parameters:

[in]	op	Transpose operation ('n', 't'),
[in]	m	Number of rows in .
[in]	n	Number of columns in .
[in]	A	Array storing , in column major format.
[in]	lda	Leading dimension of A.
[in]	alpha	Scalar $\alpha$ .
[in]	x	Vector .
[in]	incx	Distance between $x_i, x_{i+1}$ in x.
[in]	beta	Scalar $\beta$ .
[in,out]	y	Vector .
[in]	incy	Distance between $y_i, y_{i+1}$ in y.

References IS_VAL_ONE, IS_VAL_ZERO, and OSKI_ERR_BAD_MATOP.

void BLAS_xSCAL	(	const oski_index_t *	len,
		oski_value_t *	alpha,
		oski_value_t *	x,
		const oski_index_t *	stride
	)

BLAS vector scale routine, ?scal, which computes $x \leftarrow \alpha\cdot x$ .

Parameters:

[in]	len	Length of the vector.
[in]	alpha	Scalar multiplier, $\alpha$ .
[in,out]	x	Vector, .
[in]	stride	Distance between consecutive elements.

void BLAS_xTRSV	(	const char *	shape,
		const char *	op,
		const char *	diag,
		const oski_index_t *	n,
		const oski_value_t *	A,
		const oski_index_t *	lda,
		oski_value_t *	x,
		const oski_index_t *	incx
	)

BLAS triangular solve routine, ?trsv, which computes dense triangular solve operation, $x \leftarrow \mathrm{op}(A^{-1})\cdot x$ .

Parameters:

[in]	shape	Lower or upper triangular ('l' or 'u').
[in]	op	Transpose operation ('n', 't', 'c').
[in]	diag	Has unit diag or not ('u', 'n').
[in]	n	Dimension of .
[in]	A	Values of the dense matrix , in column major layout.
[in]	lda	Leading dimension of A.
[in,out]	x	Initial right-hand side, which is overwritten by the solution on output.
[in]	incx	Distance between elements of x.

References xTRSV().

Defines

Functions

Detailed Description

Define Documentation

Function Documentation