glibc/sysdeps/x86_64/mul_1.S

129 lines
2.6 KiB
ArmAsm
Raw Normal View History

/* AMD64 __mpn_mul_1 -- Multiply a limb vector with a limb and store
the result in a second limb vector.
Copyright (C) 2003-2020 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,
Prefer https to http for gnu.org and fsf.org URLs Also, change sources.redhat.com to sourceware.org. This patch was automatically generated by running the following shell script, which uses GNU sed, and which avoids modifying files imported from upstream: sed -ri ' s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g ' \ $(find $(git ls-files) -prune -type f \ ! -name '*.po' \ ! -name 'ChangeLog*' \ ! -path COPYING ! -path COPYING.LIB \ ! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \ ! -path manual/texinfo.tex ! -path scripts/config.guess \ ! -path scripts/config.sub ! -path scripts/install-sh \ ! -path scripts/mkinstalldirs ! -path scripts/move-if-change \ ! -path INSTALL ! -path locale/programs/charmap-kw.h \ ! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \ ! '(' -name configure \ -execdir test -f configure.ac -o -f configure.in ';' ')' \ ! '(' -name preconfigure \ -execdir test -f preconfigure.ac ';' ')' \ -print) and then by running 'make dist-prepare' to regenerate files built from the altered files, and then executing the following to cleanup: chmod a+x sysdeps/unix/sysv/linux/riscv/configure # Omit irrelevant whitespace and comment-only changes, # perhaps from a slightly-different Autoconf version. git checkout -f \ sysdeps/csky/configure \ sysdeps/hppa/configure \ sysdeps/riscv/configure \ sysdeps/unix/sysv/linux/csky/configure # Omit changes that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines git checkout -f \ sysdeps/powerpc/powerpc64/ppc-mcount.S \ sysdeps/unix/sysv/linux/s390/s390-64/syscall.S # Omit change that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 05:40:42 +00:00
see <https://www.gnu.org/licenses/>. */
#include <sysdep.h>
#include "asm-syntax.h"
#define rp %rdi
#define up %rsi
#define n_param %rdx
#define vl %rcx
#define n %r11
.text
ENTRY (__mpn_mul_1)
push %rbx
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%rbx, 0)
xor %r10, %r10
mov (up), %rax /* read first u limb early */
mov n_param, %rbx /* move away n from rdx, mul uses it */
mul vl
mov %rbx, %r11
add %r10, %rax
adc $0, %rdx
and $3, %ebx
jz L(b0)
cmp $2, %ebx
jz L(b2)
jg L(b3)
L(b1): dec n
jne L(gt1)
mov %rax, (rp)
jmp L(ret)
L(gt1): lea 8(up,n,8), up
lea -8(rp,n,8), rp
neg n
xor %r10, %r10
xor %ebx, %ebx
mov %rax, %r9
mov (up,n,8), %rax
mov %rdx, %r8
jmp L(L1)
L(b0): lea (up,n,8), up
lea -16(rp,n,8), rp
neg n
xor %r10, %r10
mov %rax, %r8
mov %rdx, %rbx
jmp L(L0)
L(b3): lea -8(up,n,8), up
lea -24(rp,n,8), rp
neg n
mov %rax, %rbx
mov %rdx, %r10
jmp L(L3)
L(b2): lea -16(up,n,8), up
lea -32(rp,n,8), rp
neg n
xor %r8, %r8
xor %ebx, %ebx
mov %rax, %r10
mov 24(up,n,8), %rax
mov %rdx, %r9
jmp L(L2)
.p2align 4
L(top): mov %r10, (rp,n,8)
add %rax, %r9
mov (up,n,8), %rax
adc %rdx, %r8
mov $0, %r10d
L(L1): mul vl
mov %r9, 8(rp,n,8)
add %rax, %r8
adc %rdx, %rbx
L(L0): mov 8(up,n,8), %rax
mul vl
mov %r8, 16(rp,n,8)
add %rax, %rbx
adc %rdx, %r10
L(L3): mov 16(up,n,8), %rax
mul vl
mov %rbx, 24(rp,n,8)
mov $0, %r8d # zero
mov %r8, %rbx # zero
add %rax, %r10
mov 24(up,n,8), %rax
mov %r8, %r9 # zero
adc %rdx, %r9
L(L2): mul vl
add $4, n
js L(top)
mov %r10, (rp,n,8)
add %rax, %r9
adc %r8, %rdx
mov %r9, 8(rp,n,8)
add %r8, %rdx
L(ret): mov %rdx, %rax
pop %rbx
cfi_adjust_cfa_offset (-8)
cfi_restore (%rbx)
ret
END (__mpn_mul_1)