dnl X86-64 mpn_rsh1add_n, mpn_rsh1sub_n optimised for Intel Sandy Bridge.
dnl Copyright 2003, 2005, 2009-2012 Free Software Foundation, Inc.
dnl This file is part of the GNU MP Library.
dnl
dnl The GNU MP Library is free software; you can redistribute it and/or modify
dnl it under the terms of either:
dnl
dnl * the GNU Lesser General Public License as published by the Free
dnl Software Foundation; either version 3 of the License, or (at your
dnl option) any later version.
dnl
dnl or
dnl
dnl * the GNU General Public License as published by the Free Software
dnl Foundation; either version 2 of the License, or (at your option) any
dnl later version.
dnl
dnl or both in parallel, as here.
dnl
dnl The GNU MP Library is distributed in the hope that it will be useful, but
dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
dnl for more details.
dnl
dnl You should have received copies of the GNU General Public License and the
dnl GNU Lesser General Public License along with the GNU MP Library. If not,
dnl see https://www.gnu.org/licenses/.
include(`../config.m4')
C cycles/limb
C AMD K8,K9 ?
C AMD K10 4.25
C Intel P4 21.5
C Intel core2 3.2
C Intel NHM 3.87
C Intel SBR 2.05
C Intel atom ?
C VIA nano 44.9
mov (up), %rbp
ADDSUB (vp), %rbp
L(ent):
sbb R32(%rbx), R32(%rbx) C save cy mov R32(%rbp), R32(%rax) and $1, R32(%rax) C return value
mov R32(n), R32(%r11) and $3, R32(%r11)
cmp $1, R32(%r11) je L(do) C jump if n = 1 5 9 ...
L(n1): cmp $2, R32(%r11) jne L(n2) C jump unless n = 2 6 10 ... add R32(%rbx), R32(%rbx) C restore cy mov 8(up), %r10
ADCSBB 8(vp), %r10 lea 8(up), up lea 8(vp), vp lea 8(rp), rp
sbb R32(%rbx), R32(%rbx) C save cy
shrd $1, %r10, %rbp mov %rbp, -8(rp) jmp L(cj1)
L(n2): cmp $3, R32(%r11) jne L(n3) C jump unless n = 3 7 11 ... add R32(%rbx), R32(%rbx) C restore cy mov 8(up), %r9 mov 16(up), %r10
ADCSBB 8(vp), %r9
ADCSBB 16(vp), %r10 lea 16(up), up lea 16(vp), vp lea 16(rp), rp
sbb R32(%rbx), R32(%rbx) C save cy
shrd $1, %r9, %rbp mov %rbp, -16(rp) jmp L(cj2)
L(n3): dec n C come here for n = 4 8 12 ... add R32(%rbx), R32(%rbx) C restore cy mov 8(up), %r8 mov 16(up), %r9
ADCSBB 8(vp), %r8
ADCSBB 16(vp), %r9 mov 24(up), %r10
ADCSBB 24(vp), %r10 lea 24(up), up lea 24(vp), vp lea 24(rp), rp
sbb R32(%rbx), R32(%rbx) C save cy
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.