Revision control
Copy as Markdown
Other Tools
/* ARM mul_3 -- Multiply a limb vector with a limb and subtract the result
* from a second limb vector.
*
* Copyright (C) 2013 Jussi Kivilinna <jussi.kivilinna@iki.fi>
*
* 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
*
* Note: This code is heavily based on the GNU MP Library (version 4.2.1).
*/
#include "sysdep.h"
#include "asm-syntax.h"
.syntax unified
.arm
/*******************
* mpi_limb_t
* _gcry_mpih_submul_1( mpi_ptr_t res_ptr, %r0
* mpi_ptr_t s1_ptr, %r1
* mpi_size_t s1_size, %r2
* mpi_limb_t s2_limb) %r3
*/
.text
.globl _gcry_mpih_submul_1
.type _gcry_mpih_submul_1,%function
_gcry_mpih_submul_1:
push {%r4, %r5, %r6, %r8, %r9, %r10, %lr};
mov %lr, #0;
cmp %r0, #0; /* prepare carry flag for sbc */
tst %r2, #3;
beq .Large_loop;
.Loop:
ldr %r5, [%r1], #4;
mov %r4, %lr;
mov %lr, #0;
ldr %r6, [%r0];
umlal %r4, %lr, %r5, %r3;
sub %r2, #1;
sbcs %r4, %r6, %r4;
tst %r2, #3;
str %r4, [%r0], #4;
bne .Loop;
teq %r2, #0;
beq .Lend;
.Large_loop:
ldr %r5, [%r1], #4;
mov %r9, #0;
ldr %r4, [%r0, #0];
umlal %lr, %r9, %r5, %r3;
ldr %r6, [%r0, #4];
ldr %r5, [%r1], #4;
sbcs %r4, %r4, %lr;
mov %lr, #0;
umlal %r9, %lr, %r5, %r3;
ldr %r8, [%r0, #8];
ldr %r5, [%r1], #4;
sbcs %r6, %r6, %r9;
mov %r9, #0;
umlal %lr, %r9, %r5, %r3;
ldr %r10, [%r0, #12];
ldr %r5, [%r1], #4;
sbcs %r8, %r8, %lr;
mov %lr, #0;
umlal %r9, %lr, %r5, %r3;
sub %r2, #4;
sbcs %r10, %r10, %r9;
teq %r2, #0;
stm %r0!, {%r4, %r6, %r8, %r10};
bne .Large_loop;
.Lend:
it cc
movcc %r2, #1;
add %r0, %lr, %r2;
pop {%r4, %r5, %r6, %r8, %r9, %r10, %pc};
.size _gcry_mpih_submul_1,.-_gcry_mpih_submul_1;