⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 axpy.s

📁 Optimized GotoBLAS libraries
💻 S
字号:
/*********************************************************************//*                                                                   *//*             Optimized BLAS libraries                              *//*                     By Kazushige Goto <kgoto@tacc.utexas.edu>     *//*                                                                   *//* 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"#define STACK	12#define ARGS	 0	#define STACK_M		 4 + STACK + ARGS(%esp)#define STACK_ALPHA	16 + STACK + ARGS(%esp)#ifdef DOUBLE#define STACK_X		24 + STACK + ARGS(%esp)#define STACK_INCX	28 + STACK + ARGS(%esp)#define STACK_Y		32 + STACK + ARGS(%esp)#define STACK_INCY	36 + STACK + ARGS(%esp)#else#define STACK_X		20 + STACK + ARGS(%esp)#define STACK_INCX	24 + STACK + ARGS(%esp)#define STACK_Y		28 + STACK + ARGS(%esp)#define STACK_INCY	32 + STACK + ARGS(%esp)#endif#define M	%ebx#define X	%esi#define INCX	%ecx#define Y	%edi#define INCY	%edx	PROLOGUE	pushl	%edi	pushl	%esi	pushl	%ebx	PROFCODE#ifdef F_INTERFACE_GFORT	EMMS#endif	FLD	STACK_ALPHA	movl	STACK_M,    M	movl	STACK_X,    X	movl	STACK_INCX, INCX	movl	STACK_Y,    Y	movl	STACK_INCY, INCY	leal	(, INCX, SIZE), INCX	leal	(, INCY, SIZE), INCY	cmpl	$SIZE, INCX	jne	.L14	cmpl	$SIZE, INCY	jne	.L14	movl	M, %eax	sarl	$3,   %eax	jle	.L15	ALIGN_3#define PRESIZE 33.L16:#ifdef HAS_PREFETCH	prefetcht0	PRESIZE * SIZE(X)#endif	FLD	0 * SIZE(X)	fmul	%st(1),%st	FADD	0 * SIZE(Y)	FST	0 * SIZE(Y)	FLD	1 * SIZE(X)	fmul	%st(1),%st	FADD	1 * SIZE(Y)	FST	1 * SIZE(Y)	FLD	2 * SIZE(X)	fmul	%st(1),%st	FADD	2 * SIZE(Y)	FST	2 * SIZE(Y)	FLD	3 * SIZE(X)	fmul	%st(1),%st	FADD	3 * SIZE(Y)	FST	3 * SIZE(Y)#ifdef HAS_PREFETCH	prefetcht0	(4 + PRESIZE) * SIZE(X)#endif	FLD	4 * SIZE(X)	fmul	%st(1),%st	FADD	4 * SIZE(Y)	FST	4 * SIZE(Y)	FLD	5 * SIZE(X)	fmul	%st(1),%st	FADD	5 * SIZE(Y)	FST	5 * SIZE(Y)	FLD	6 * SIZE(X)	fmul	%st(1),%st	FADD	6 * SIZE(Y)	FST	6 * SIZE(Y)	FLD	7 * SIZE(X)	fmul	%st(1),%st	FADD	7 * SIZE(Y)	FST	7 * SIZE(Y)#ifdef HAVE_3DNOW	prefetchw	24 * SIZE(Y)#endif		addl	$8 * SIZE, X	addl	$8 * SIZE, Y	decl	%eax	jg	.L16	ALIGN_3.L15:	movl	M, %eax	andl	$7,   %eax	jle	.L40	ALIGN_3.L22:	FLD	0 * SIZE(X)	fmul	%st(1),%st	FADD	0 * SIZE(Y)	FST	0 * SIZE(Y)	addl	$SIZE, X	addl	$SIZE, Y	decl	%eax	jg	.L22	jmp	.L40	ALIGN_3.L14:	movl	M, %eax	sarl	$2,   %eax	jle	.L28	ALIGN_3.L29:	FLD	(X)	fmul	%st(1),%st	FADD	(Y)	FST	(Y)	addl	INCX, X	addl	INCY, Y	FLD	(X)	fmul	%st(1),%st	FADD	(Y)	FST	(Y)	addl	INCX, X	addl	INCY, Y	FLD	(X)	fmul	%st(1),%st	FADD	(Y)	FST	(Y)	addl	INCX, X	addl	INCY, Y	FLD	(X)	fmul	%st(1),%st	FADD	(Y)	FST	(Y)	addl	INCX, X	addl	INCY, Y	decl	%eax	jg	.L29	ALIGN_3.L28:	movl	M, %eax	andl	$3,   %eax	jle	.L40	ALIGN_3.L35:	FLD	(X)	fmul	%st(1),%st	FADD	(Y)	FST	(Y)	addl	INCX, X	addl	INCY, Y	decl	%eax	jg	.L35	ALIGN_3.L40:	ffreep	%st(0)	xorl	%eax,%eax	popl	%ebx	popl	%esi	popl	%edi	ret	EPILOGUE

⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -