cabs.s

Optimized GotoBLAS libraries

/*********************************************************************/
/*                                                                   */
/*             Optimized BLAS libraries                              */
/*                     By Kazushige Goto <[e-mail]>     */
/*                                                                   */
/* Copyright (c) The University of Texas, 2005. All rights reserved. */
/* UNIVERSITY EXPRESSLY DISCLAIMS ANY AND ALL WARRANTIES CONCERNING  */
/* THIS SOFTWARE AND DOCUMENTATION, INCLUDING ANY WARRANTIES OF      */
/* MERCHANTABILITY, FITNESS FOR ANY PARTICULAR PURPOSE,              */
/* NON-INFRINGEMENT AND WARRANTIES OF PERFORMANCE, AND ANY WARRANTY  */
/* THAT MIGHT OTHERWISE ARISE FROM COURSE OF DEALING OR USAGE OF     */
/* TRADE. NO WARRANTY IS EITHER EXPRESS OR IMPLIED WITH RESPECT TO   */
/* THE USE OF THE SOFTWARE OR DOCUMENTATION.                         */
/* Under no circumstances shall University be liable for incidental, */
/* special, indirect, direct or consequential damages or loss of     */
/* profits, interruption of business, or related expenses which may  */
/* arise from use of Software or Documentation, including but not    */
/* limited to those resulting from defects in Software and/or        */
/* Documentation, or loss or inaccuracy of data of any kind.         */
/*********************************************************************/

#define ASSEMBLER
#include "common.h"

	PROLOGUE
	PROFCODE

#ifdef DOUBLE
	movsd	0 * SIZE(ARG1), %xmm0
	movsd	1 * SIZE(ARG1), %xmm1
	pcmpeqb	%xmm4, %xmm4
		
	psrlq	$1, %xmm4
	andpd	%xmm4, %xmm0
	andpd	%xmm4, %xmm1
	addpd	%xmm1, %xmm0
#else
	movss	0 * SIZE(ARG1), %xmm0
	movss	1 * SIZE(ARG1), %xmm1
	pcmpeqb	%xmm4, %xmm4
		
	psrld	$1, %xmm4
	andps	%xmm4, %xmm0
	andps	%xmm4, %xmm1
	addps	%xmm1, %xmm0
#endif
	
#if !defined(DOUBLE) && defined(NEED_F2CCONV)
	cvtss2sd	%xmm0, %xmm0
#endif
	ret

	EPILOGUE