83 lines
2.3 KiB
ArmAsm
83 lines
2.3 KiB
ArmAsm
/* AMD64 (x86_64) rshift -- Right shift a limb vector and store
|
|
* result in a second limb vector.
|
|
*
|
|
* Copyright (C) 1992, 1994, 1995, 1998,
|
|
* 2001, 2002, 2006 Free Software Foundation, Inc.
|
|
*
|
|
* This file is part of Libgcrypt.
|
|
*
|
|
* Libgcrypt 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.
|
|
*
|
|
* Libgcrypt 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 this program; if not, see <https://www.gnu.org/licenses/>.
|
|
* SPDX-License-Identifier: LGPL-2.1-or-later
|
|
*
|
|
* Note: This code is heavily based on the GNU MP Library.
|
|
* Actually it's the same code with only minor changes in the
|
|
* way the data is stored; this is to support the abstraction
|
|
* of an optional secure memory allocation which may be used
|
|
* to avoid revealing of sensitive data due to paging etc.
|
|
*/
|
|
|
|
|
|
#include "sysdep.h"
|
|
#include "asm-syntax.h"
|
|
|
|
/*******************
|
|
* mpi_limb_t
|
|
* _gcry_mpih_rshift( mpi_ptr_t wp, rdi
|
|
* mpi_ptr_t up, rsi
|
|
* mpi_size_t usize, rdx
|
|
* unsigned cnt) rcx
|
|
*/
|
|
|
|
TEXT
|
|
ALIGN(4)
|
|
.globl C_SYMBOL_NAME(_gcry_mpih_rshift)
|
|
C_SYMBOL_NAME(_gcry_mpih_rshift:)
|
|
FUNC_ENTRY()
|
|
/* Note: %xmm6 and %xmm7 not used for WIN64 ABI compatibility. */
|
|
movq (%rsi), %xmm4
|
|
movd %ecx, %xmm1
|
|
movl $64, %eax
|
|
subl %ecx, %eax
|
|
movd %eax, %xmm0
|
|
movdqa %xmm4, %xmm3
|
|
psllq %xmm0, %xmm4
|
|
movq %xmm4, %rax
|
|
leaq (%rsi,%rdx,8), %rsi
|
|
leaq (%rdi,%rdx,8), %rdi
|
|
negq %rdx
|
|
addq $2, %rdx
|
|
jg .Lendo
|
|
|
|
ALIGN(4) /* minimal alignment for claimed speed */
|
|
.Loop: movq -8(%rsi,%rdx,8), %xmm5
|
|
movdqa %xmm5, %xmm2
|
|
psllq %xmm0, %xmm5
|
|
psrlq %xmm1, %xmm3
|
|
por %xmm5, %xmm3
|
|
movq %xmm3, -16(%rdi,%rdx,8)
|
|
je .Lende
|
|
movq (%rsi,%rdx,8), %xmm4
|
|
movdqa %xmm4, %xmm3
|
|
psllq %xmm0, %xmm4
|
|
psrlq %xmm1, %xmm2
|
|
por %xmm4, %xmm2
|
|
movq %xmm2, -8(%rdi,%rdx,8)
|
|
addq $2, %rdx
|
|
jle .Loop
|
|
|
|
.Lendo: movdqa %xmm3, %xmm2
|
|
.Lende: psrlq %xmm1, %xmm2
|
|
movq %xmm2, -8(%rdi)
|
|
FUNC_EXIT()
|