diff options
author | Kevin Ryde <user42@zip.com.au> | 2001-10-31 00:19:08 +0100 |
---|---|---|
committer | Kevin Ryde <user42@zip.com.au> | 2001-10-31 00:19:08 +0100 |
commit | fe8a1bd85adf3318b3d80f5761d18c93a6ec5eed (patch) | |
tree | 80800e7fcce7330ed7067a1d3c3453fee4dd22d7 /mpn | |
parent | f0ce87f5bc40f4a14f987a4f0401aa2058778ed7 (diff) | |
download | gmp-fe8a1bd85adf3318b3d80f5761d18c93a6ec5eed.tar.gz |
* mpn/x86/mod_34lsub1.asm: New file.
Diffstat (limited to 'mpn')
-rw-r--r-- | mpn/x86/mod_34lsub1.asm | 173 |
1 files changed, 173 insertions, 0 deletions
diff --git a/mpn/x86/mod_34lsub1.asm b/mpn/x86/mod_34lsub1.asm new file mode 100644 index 000000000..f30f8e756 --- /dev/null +++ b/mpn/x86/mod_34lsub1.asm @@ -0,0 +1,173 @@ +dnl Generic x86 mpn_mod_32lsub1 -- mpn remainder modulo 2^24-1. +dnl +dnl cycles/limb +dnl P5: 3.0 +dnl P6: 3.7 +dnl K6: 3.0 +dnl K7: 1.3 +dnl P4: 9 + +dnl Copyright 2000, 2001 Free Software Foundation, Inc. +dnl +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 +dnl modify it under the terms of the GNU Lesser General Public License as +dnl published by the Free Software Foundation; either version 2.1 of the +dnl License, or (at your option) any later version. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, +dnl but WITHOUT ANY WARRANTY; without even the implied warranty of +dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +dnl Lesser General Public License for more details. +dnl +dnl You should have received a copy of the GNU Lesser General Public +dnl License along with the GNU MP Library; see the file COPYING.LIB. If +dnl not, write to the Free Software Foundation, Inc., 59 Temple Place - +dnl Suite 330, Boston, MA 02111-1307, USA. + +include(`../config.m4') + + +C mp_limb_t mpn_mod_34lsub1 (mp_srcptr src, mp_size_t size) +C + +defframe(PARAM_SIZE, 8) +defframe(PARAM_SRC, 4) + +dnl re-use parameter space +define(SAVE_EBX, `PARAM_SRC') + + TEXT + ALIGN(16) +PROLOGUE(mpn_mod_34lsub1) +deflit(`FRAME',0) + + movl PARAM_SIZE, %ecx + movl PARAM_SRC, %edx + + subl $2, %ecx + ja L(three_or_more) + + movl (%edx), %eax + jb L(one) + + movl 4(%edx), %ecx + movl %eax, %edx + shrl $24, %eax C src[0] low + + andl $0xFFFFFF, %edx C src[0] high + addl %edx, %eax + movl %ecx, %edx + + andl $0xFFFF, %ecx + shrl $16, %edx C src[1] high + addl %edx, %eax + + shll $8, %ecx C src[1] low + addl %ecx, %eax + +L(one): + ret + + +L(three_or_more): + C eax + C ebx + C ecx size-2 + C edx src + C esi + C edi + C ebp + + movl %ebx, SAVE_EBX C and arrange 16-byte loop alignment + xorl %ebx, %ebx + + pushl %esi FRAME_pushl() + xorl %esi, %esi + + pushl %edi FRAME_pushl() + xorl %eax, %eax C and clear carry flag + + + C offset 0x40 here +L(top): + C eax acc 0mod3 + C ebx acc 1mod3 + C ecx counter, limbs + C edx src + C esi acc 2mod3 + C edi + C ebp + + leal 12(%edx), %edx + leal -2(%ecx), %ecx + + adcl -12(%edx), %eax + adcl -8(%edx), %ebx + adcl -4(%edx), %esi + + decl %ecx + jg L(top) + + + C ecx is -2, -1 or 0 representing 0, 1 or 2 more limbs, respectively + + movl $0xFFFFFFFF, %edi + incl %ecx + js L(combine) + + adcl (%edx), %eax + movl $0xFFFFFF00, %edi + decl %ecx + js L(combine) + + adcl 4(%edx), %ebx + movl $0xFFFF0000, %edi + + +L(combine): + C eax acc 0mod3 + C ebx acc 1mod3 + C ecx + C edx + C esi acc 2mod3 + C edi mask + C ebp + + sbbl %ecx, %ecx C carry + movl %eax, %edx C 0mod3 + + shrl $24, %eax C 0mod3 high + andl %edi, %ecx C carry masked + + subl %ecx, %eax C apply carry + movl %ebx, %edi C 1mod3 + + shrl $16, %ebx C 1mod3 high + andl $0x00FFFFFF, %edx C 0mod3 low + + addl %edx, %eax C apply 0mod3 low + andl $0xFFFF, %edi + + shll $8, %edi C 1mod3 low + addl %ebx, %eax C apply 1mod3 high + + addl %edi, %eax C apply 1mod3 low + movl %esi, %edx C 2mod3 + + shrl $8, %esi C 2mod3 high + andl $0xFF, %edx C 2mod3 low + + shll $16, %edx C 2mod3 low + addl %esi, %eax C apply 2mod3 high + + addl %edx, %eax C apply 2mod3 low + popl %edi FRAME_popl() + + movl SAVE_EBX, %ebx + popl %esi FRAME_popl() + + ret + +EPILOGUE() |