/* Pentium __mpn_add_n -- Add two limb vectors of the same length > 0 and store sum in a third limb vector. Copyright (C) 1992-2013 Free Software Foundation, Inc. This file is part of the GNU MP Library. The GNU MP Library is free software; you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License as published by the Free Software Foundation; either version 2.1 of the License, or (at your option) any later version. The GNU MP Library is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more details. You should have received a copy of the GNU Lesser General Public License along with the GNU MP Library; see the file COPYING.LIB. If not, see . */ #include "sysdep.h" #include "asm-syntax.h" #include "bp-sym.h" #include "bp-asm.h" #define PARMS LINKAGE+16 /* space for 4 saved regs */ #define RES PARMS #define S1 RES+PTR_SIZE #define S2 S1+PTR_SIZE #define SIZE S2+PTR_SIZE .text ENTRY (BP_SYM (__mpn_add_n)) pushl %edi cfi_adjust_cfa_offset (4) pushl %esi cfi_adjust_cfa_offset (4) pushl %ebp cfi_adjust_cfa_offset (4) pushl %ebx cfi_adjust_cfa_offset (4) movl RES(%esp),%edi cfi_rel_offset (edi, 12) movl S1(%esp),%esi cfi_rel_offset (esi, 8) movl S2(%esp),%ebx cfi_rel_offset (ebx, 0) movl SIZE(%esp),%ecx movl (%ebx),%ebp cfi_rel_offset (ebp, 4) decl %ecx movl %ecx,%edx shrl $3,%ecx andl $7,%edx testl %ecx,%ecx /* zero carry flag */ jz L(end) pushl %edx cfi_adjust_cfa_offset (4) ALIGN (3) L(oop): movl 28(%edi),%eax /* fetch destination cache line */ leal 32(%edi),%edi L(1): movl (%esi),%eax movl 4(%esi),%edx adcl %ebp,%eax movl 4(%ebx),%ebp adcl %ebp,%edx movl 8(%ebx),%ebp movl %eax,-32(%edi) movl %edx,-28(%edi) L(2): movl 8(%esi),%eax movl 12(%esi),%edx adcl %ebp,%eax movl 12(%ebx),%ebp adcl %ebp,%edx movl 16(%ebx),%ebp movl %eax,-24(%edi) movl %edx,-20(%edi) L(3): movl 16(%esi),%eax movl 20(%esi),%edx adcl %ebp,%eax movl 20(%ebx),%ebp adcl %ebp,%edx movl 24(%ebx),%ebp movl %eax,-16(%edi) movl %edx,-12(%edi) L(4): movl 24(%esi),%eax movl 28(%esi),%edx adcl %ebp,%eax movl 28(%ebx),%ebp adcl %ebp,%edx movl 32(%ebx),%ebp movl %eax,-8(%edi) movl %edx,-4(%edi) leal 32(%esi),%esi leal 32(%ebx),%ebx decl %ecx jnz L(oop) popl %edx cfi_adjust_cfa_offset (-4) L(end): decl %edx /* test %edx w/o clobbering carry */ js L(end2) incl %edx L(oop2): leal 4(%edi),%edi movl (%esi),%eax adcl %ebp,%eax movl 4(%ebx),%ebp movl %eax,-4(%edi) leal 4(%esi),%esi leal 4(%ebx),%ebx decl %edx jnz L(oop2) L(end2): movl (%esi),%eax adcl %ebp,%eax movl %eax,(%edi) sbbl %eax,%eax negl %eax popl %ebx cfi_adjust_cfa_offset (-4) cfi_restore (ebx) popl %ebp cfi_adjust_cfa_offset (-4) cfi_restore (ebp) popl %esi cfi_adjust_cfa_offset (-4) cfi_restore (esi) popl %edi cfi_adjust_cfa_offset (-4) cfi_restore (edi) ret END (BP_SYM (__mpn_add_n))