dnl x86 mpn_divrem_2 -- Divide an mpn number by a normalized 2-limb number.
dnl Copyright 2007, 2008 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 norm frac
C 486
C P5
C P6-1329.2
C P6-15 *26
C K6
C K7 22
C K8 *19
C P4-f1
C P4-f2 *65
C P4-f3
C P4-f4 *72
C A star means numbers not updated for the latest version of the code.
C TODO
C * Perhaps keep ecxoresi in stack slot, freeing up a reg for q0.
C * The loop has not been carefully tuned. We should at the very least do
C some local insn swapping.
C * The code outside the main loop is what gcc generated. Clean up!
C * Clean up stack slot usage.
C INPUT PARAMETERS
C qp
C fn
C up_param
C un_param
C dp
C eax ebx ecxedxesiediebp
C cnt qp
ASM_START()
TEXT ALIGN(16)
PROLOGUE(mpn_divrem_2) push %ebp push %edi push %esi push %ebx sub $36, %esp mov68(%esp), %ecx C un mov72(%esp), %esi C dp
movl $0, 32(%esp) lea0(,%ecx,4), %edi add64(%esp), %edi C up mov (%esi), %ebx mov4(%esi), %eax mov %ebx, 20(%esp) sub $12, %edi mov %eax, 24(%esp) mov %edi, 12(%esp) mov8(%edi), %ebx mov4(%edi), %ebp cmp %eax, %ebx
jb L(8)
seta %dl cmp20(%esp), %ebp
setae %al
orb %dl, %al C "orb" form to placate Sun tools jne L(35)
L(8): mov60(%esp), %esi C fn lea -3(%esi,%ecx), %edi
test %edi, %edi
js L(9) mov24(%esp), %edx mov $-1, %esi mov %esi, %eax mov %esi, %ecx
not %edx
divl 24(%esp) mov %eax, %esi
imul 24(%esp), %eax mov %eax, (%esp) mov %esi, %eax
mull 20(%esp) mov (%esp), %eax add20(%esp), %eax adc $0, %ecx add %eax, %edx adc $0, %ecx mov %ecx, %eax
js L(32)
L(36): dec %esi sub24(%esp), %edx
sbb $0, %eax
jns L(36)
L(32): mov %esi, 16(%esp) C di mov %edi, %ecx C un mov12(%esp), %esi C up mov24(%esp), %eax neg %eax mov %eax, 4(%esp) C -d1 ALIGN(16) nop
C eax ebx ecxedxesiediebp0481216202428325660
C n2 un up n1 q0 -d1 di d0 d1 msl qp fn
L(loop): mov16(%esp), %eax C di mul %ebx add %ebp, %eax mov %eax, (%esp) C q0 adc %ebx, %edx mov %edx, %edi C q
imul 4(%esp), %edx mov20(%esp), %eax lea (%edx, %ebp), %ebx C n1 -= ... mul %edi xor %ebp, %ebp cmp60(%esp), %ecx jl L(19) mov (%esi), %ebp sub $4, %esi
L(19): sub20(%esp), %ebp
sbb 24(%esp), %ebx sub %eax, %ebp
sbb %edx, %ebx mov20(%esp), %eax C d1 inc %edi xor %edx, %edx cmp (%esp), %ebx adc $-1, %edx C mask add %edx, %edi C q-- and %edx, %eax C d0 or0 and24(%esp), %edx C d1 or0 add %eax, %ebp adc %edx, %ebx cmp24(%esp), %ebx
jae L(fix)
L(bck): mov56(%esp), %edx mov %edi, (%edx, %ecx, 4) dec %ecx
jns L(loop)
L(9): mov64(%esp), %esi C up mov %ebp, (%esi) mov %ebx, 4(%esi) mov32(%esp), %eax add $36, %esp pop %ebx pop %esi pop %edi pop %ebp ret
L(fix): seta %dl cmp20(%esp), %ebp
setae %al
orb %dl, %al C "orb" form to placate Sun tools je L(bck) inc %edi sub20(%esp), %ebp
sbb 24(%esp), %ebx jmp L(bck)
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.