📄 qaxpy.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)#define STACK_X 32 + STACK + ARGS(%esp)#define STACK_INCX 36 + STACK + ARGS(%esp)#define STACK_Y 40 + STACK + ARGS(%esp)#define STACK_INCY 44 + STACK + ARGS(%esp)#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 sall $BASE_SHIFT, INCX sall $BASE_SHIFT, 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 FLD 0 * SIZE(Y) faddp %st, %st(1) FST 0 * SIZE(Y) FLD 1 * SIZE(X) fmul %st(1),%st FLD 1 * SIZE(Y) faddp %st, %st(1) FST 1 * SIZE(Y) FLD 2 * SIZE(X) fmul %st(1),%st FLD 2 * SIZE(Y) faddp %st, %st(1) FST 2 * SIZE(Y) FLD 3 * SIZE(X) fmul %st(1),%st FLD 3 * SIZE(Y) faddp %st, %st(1) FST 3 * SIZE(Y)#ifdef HAS_PREFETCH prefetcht0 (4 + PRESIZE) * SIZE(X)#endif FLD 4 * SIZE(X) fmul %st(1),%st FLD 4 * SIZE(Y) faddp %st, %st(1) FST 4 * SIZE(Y) FLD 5 * SIZE(X) fmul %st(1),%st FLD 5 * SIZE(Y) faddp %st, %st(1) FST 5 * SIZE(Y) FLD 6 * SIZE(X) fmul %st(1),%st FLD 6 * SIZE(Y) faddp %st, %st(1) FST 6 * SIZE(Y) FLD 7 * SIZE(X) fmul %st(1),%st FLD 7 * SIZE(Y) faddp %st, %st(1) 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 FLD 0 * SIZE(Y) faddp %st, %st(1) 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 FLD (Y) faddp %st, %st(1) FST (Y) addl INCX, X addl INCY, Y FLD (X) fmul %st(1),%st FLD (Y) faddp %st, %st(1) FST (Y) addl INCX, X addl INCY, Y FLD (X) fmul %st(1),%st FLD (Y) faddp %st, %st(1) FST (Y) addl INCX, X addl INCY, Y FLD (X) fmul %st(1),%st FLD (Y) faddp %st, %st(1) 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 FLD (Y) faddp %st, %st(1) 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 + -