glibc/sysdeps/x86_64/addmul_1.S
Ulrich Drepper 893a5fd440 Optimizations from GMP.
* sysdeps/x86_64/add_n.S: New file.
	* sysdeps/x86_64/addmul_1.S: New file.
	* sysdeps/x86_64/lshift.S: New file.
	* sysdeps/x86_64/mul_1.S: New file.
	* sysdeps/x86_64/rshift.S: New file.
	* sysdeps/x86_64/sub_n.S: New file.
	* sysdeps/x86_64/submul_1.S: New file.
2009-04-14 22:26:05 +00:00

47 lines
1.4 KiB
ArmAsm

/* AMD64 __mpn_addmul_1 -- Multiply a limb vector with a limb and add
the result to a second limb vector.
Copyright (C) 2004 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, write to
the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
MA 02111-1307, USA. */
#include "sysdep.h"
#include "asm-syntax.h"
.text
ENTRY (__mpn_addmul_1)
movq %rdx, %r11
leaq (%rsi,%rdx,8), %rsi
leaq (%rdi,%rdx,8), %rdi
negq %r11
xorl %r8d, %r8d
xorl %r10d, %r10d
.p2align 2
L(loop):
movq (%rsi,%r11,8), %rax
mulq %rcx
addq (%rdi,%r11,8), %rax
adcq %r10, %rdx
addq %r8, %rax
movq %r10, %r8
movq %rax, (%rdi,%r11,8)
adcq %rdx, %r8
incq %r11
jne L(loop)
movq %r8, %rax
ret
END (__mpn_addmul_1)