asum.s

来自「Optimized GotoBLAS libraries」· S 代码 · 共 138 行

S
138
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"#include "version.h"	PROLOGUE	PROFCODE	.frame	$sp, 0, $26, 0#ifdef F_INTERFACE	ldl	$16,   0($16)	fclr	$f0	ldl	$18,   0($18)	fclr	$f29#else	fclr	$f0	unop	fclr	$f29	unop#endif#ifndef PROFILE	.prologue 0#else	.prologue 1#endif	fclr	$f30	sra	$16, 2, $20	fclr	$f28	ble	$16,  $End	and	$16, 3, $21	ble	$18,  $End	.align 4	ble	$20, $Sub	.align 4	lda	$20,  -1($20)	LD	$f16,  0($17)	SXADDQ	$18, $17, $17	LD	$f17,  0($17)	SXADDQ	$18, $17, $17	LD	$f18,  0($17)	SXADDQ	$18, $17, $17	LD	$f19,  0($17)	SXADDQ	$18, $17, $17	ble	$20, $MainLoopEnd	.align 4$MainLoop:	fabs	$f16, $f20	LD	$f16,  0($17)	unop	SXADDQ	$18, $17, $17	fabs	$f17, $f21	LD	$f17,  0($17)	unop	SXADDQ	$18, $17, $17	fabs	$f18, $f22	LD	$f18,  0($17)	unop	SXADDQ	$18, $17, $17	fabs	$f19, $f23	LD	$f19,  0($17)	unop	lda	$20,  -1($20)	ADD	$f0,  $f20, $f0	ADD	$f28, $f21, $f28	ADD	$f29, $f22, $f29	ADD	$f30, $f23, $f30	SXADDQ	$18, $17, $17	unop	unop	bne	$20, $MainLoop	.align 4$MainLoopEnd:	fabs	$f16, $f20	fabs	$f17, $f21	fabs	$f18, $f22	fabs	$f19, $f23	ADD	$f0,  $f20, $f0	ADD	$f28, $f21, $f28	ADD	$f29, $f22, $f29	ADD	$f30, $f23, $f30	.align 4$Sub:	ADD	$f0,  $f28, $f0	unop	ADD	$f29, $f30, $f29	ble	$21, $End	.align 4$SubLoop:	LD	$f16,  0($17)	SXADDQ	$18, $17, $17	fabs	$f16, $f20	ADD	$f0,  $f20, $f0	lda	$21,  -1($21)	bne	$21, $SubLoop	.align 4$End:	ADD	$f0,  $f29, $f0	ret	EPILOGUE

⌨️ 快捷键说明

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