📄 zasum.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 8#define ARGS 0 #define M 4 + STACK + ARGS(%esp)#define X 8 + STACK + ARGS(%esp)#define INCX 12 + STACK + ARGS(%esp) PROLOGUE pushl %esi pushl %ebx PROFCODE#ifdef F_INTERFACE_GFORT EMMS#endif movl M, %edx movl INCX, %esi movl X, %ecx#ifdef F_INTERFACE movl (%edx), %ebx movl (%esi), %esi#endif fldz testl %ebx, %ebx jle .L999 testl %esi, %esi jle .L999 sall $ZBASE_SHIFT, %esi fldz fldz fldz cmpl $SIZE * 2, %esi jne .L40 movl %ebx, %edx sarl $2, %edx jle .L20 ALIGN_4 .L10: FLD 0 * SIZE(%ecx) fabs FLD 1 * SIZE(%ecx) fabs FLD 2 * SIZE(%ecx) fabs FLD 3 * SIZE(%ecx) fabs faddp %st, %st(7) faddp %st, %st(5) faddp %st, %st(3) faddp %st, %st(1) FLD 4 * SIZE(%ecx) fabs FLD 5 * SIZE(%ecx) fabs FLD 6 * SIZE(%ecx) fabs FLD 7 * SIZE(%ecx) fabs addl $8 * SIZE, %ecx faddp %st, %st(7) faddp %st, %st(5) faddp %st, %st(3) faddp %st, %st(1) decl %edx jg .L10 ALIGN_4.L20: andl $3, %ebx jle .L998 ALIGN_4.L21: FLD 0 * SIZE(%ecx) fabs FLD 1 * SIZE(%ecx) fabs faddp %st,%st(3) faddp %st,%st(1) addl $2 * SIZE, %ecx decl %ebx jg .L21 jmp .L998 ALIGN_4.L40: movl %ebx, %edx sarl $2, %edx jle .L60 ALIGN_4 .L50: FLD 0 * SIZE(%ecx) fabs FLD 1 * SIZE(%ecx) addl %esi, %ecx fabs FLD 0 * SIZE(%ecx) fabs FLD 1 * SIZE(%ecx) addl %esi, %ecx fabs faddp %st, %st(7) faddp %st, %st(5) faddp %st, %st(3) faddp %st, %st(1) FLD 0 * SIZE(%ecx) fabs FLD 1 * SIZE(%ecx) addl %esi, %ecx fabs FLD 0 * SIZE(%ecx) fabs FLD 1 * SIZE(%ecx) addl %esi, %ecx fabs faddp %st, %st(7) faddp %st, %st(5) faddp %st, %st(3) faddp %st, %st(1) decl %edx jg .L50 ALIGN_4.L60: andl $3, %ebx jle .L998 ALIGN_4.L61: FLD 0 * SIZE(%ecx) fabs FLD 1 * SIZE(%ecx) addl %esi, %ecx fabs faddp %st,%st(3) faddp %st,%st(1) decl %ebx jg .L61 ALIGN_4.L998: faddp %st,%st(2) faddp %st,%st(1) faddp %st,%st(1) ALIGN_4.L999: popl %ebx popl %esi 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 + -