diff options
author | Kevin Ryde <user42@zip.com.au> | 2000-04-23 00:36:10 +0200 |
---|---|---|
committer | Kevin Ryde <user42@zip.com.au> | 2000-04-23 00:36:10 +0200 |
commit | 6c54d1e311e6a79aae09e97b1088d49cdd3508da (patch) | |
tree | 071183fcf7a6624e98317877b4631d0b9b04005a /mpn/x86/aorsmul_1.asm | |
parent | 31942ad2569a580f29238ddf28f15c22f53b5787 (diff) | |
download | gmp-6c54d1e311e6a79aae09e97b1088d49cdd3508da.tar.gz |
Convert addmul_1.S and submul_1.S to a multi-function aorsmul_1.asm.
No object code changes.
Diffstat (limited to 'mpn/x86/aorsmul_1.asm')
-rw-r--r-- | mpn/x86/aorsmul_1.asm | 134 |
1 files changed, 134 insertions, 0 deletions
diff --git a/mpn/x86/aorsmul_1.asm b/mpn/x86/aorsmul_1.asm new file mode 100644 index 000000000..0968ea0b4 --- /dev/null +++ b/mpn/x86/aorsmul_1.asm @@ -0,0 +1,134 @@ +dnl x86 __gmpn_addmul_1 (for 386 and 486) -- Multiply a limb vector with a +dnl limb and add the result to a second limb vector. + + +dnl Copyright (C) 1992, 1994, 1997, 1999, 2000 Free Software Foundation, +dnl 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 Library General Public License as +dnl published by the Free Software Foundation; either version 2 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 Library General Public License for more details. +dnl +dnl You should have received a copy of the GNU Library 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') + + +ifdef(`OPERATION_addmul_1',` + define(M4_inst, addl) + define(M4_function_1, mpn_addmul_1) + +',`ifdef(`OPERATION_submul_1',` + define(M4_inst, subl) + define(M4_function_1, mpn_submul_1) + +',`m4_error(`Need OPERATION_addmul_1 or OPERATION_submul_1 +')')') + +MULFUNC_PROLOGUE(mpn_addmul_1 mpn_submul_1) + + +C mp_limb_t M4_function_1 (mp_ptr dst, mp_srcptr src, mp_size_t size, +C mp_limb_t mult); + +define(PARAM_MULTIPLIER, `FRAME+16(%esp)') +define(PARAM_SIZE, `FRAME+12(%esp)') +define(PARAM_SRC, `FRAME+8(%esp)') +define(PARAM_DST, `FRAME+4(%esp)') + + TEXT + ALIGN(8) + +PROLOGUE(M4_function_1) +deflit(`FRAME',0) + + pushl %edi + pushl %esi + pushl %ebx + pushl %ebp +deflit(`FRAME',16) + + movl PARAM_DST,%edi + movl PARAM_SRC,%esi + movl PARAM_SIZE,%ecx + + xorl %ebx,%ebx + andl $3,%ecx + jz L(end0) + +L(oop0): + movl (%esi),%eax + mull PARAM_MULTIPLIER + leal 4(%esi),%esi + addl %ebx,%eax + movl $0,%ebx + adcl %ebx,%edx + M4_inst %eax,(%edi) + adcl %edx,%ebx C propagate carry into cylimb + + leal 4(%edi),%edi + decl %ecx + jnz L(oop0) + +L(end0): + movl PARAM_SIZE,%ecx + shrl $2,%ecx + jz L(end) + + ALIGN(8) +L(oop): movl (%esi),%eax + mull PARAM_MULTIPLIER + addl %eax,%ebx + movl $0,%ebp + adcl %edx,%ebp + + movl 4(%esi),%eax + mull PARAM_MULTIPLIER + M4_inst %ebx,(%edi) + adcl %eax,%ebp C new lo + cylimb + movl $0,%ebx + adcl %edx,%ebx + + movl 8(%esi),%eax + mull PARAM_MULTIPLIER + M4_inst %ebp,4(%edi) + adcl %eax,%ebx C new lo + cylimb + movl $0,%ebp + adcl %edx,%ebp + + movl 12(%esi),%eax + mull PARAM_MULTIPLIER + M4_inst %ebx,8(%edi) + adcl %eax,%ebp C new lo + cylimb + movl $0,%ebx + adcl %edx,%ebx + + M4_inst %ebp,12(%edi) + adcl $0,%ebx C propagate carry into cylimb + + leal 16(%esi),%esi + leal 16(%edi),%edi + decl %ecx + jnz L(oop) + +L(end): movl %ebx,%eax + + popl %ebp + popl %ebx + popl %esi + popl %edi + ret + +EPILOGUE() |