glibc/sysdeps/mips/submul_1.S
Steve Ellcey 8b2800c0fb 2014-12-19 Steve Ellcey <sellcey@imgtec.com>
* sysdeps/mips/addmul_1.S (__mpn_addmul_1): Use mulu/muhu instead
	of multu on MIPSr6.
	* sysdeps/mips/mul_1.S (__mpn_mul_1): Ditto.
	* sysdeps/mips/submul_1.S (__mpn_submul_1): Ditto.
	* sysdeps/mips/mips64/addmul_1.S (__mpn_addmul_1): Ditto.
	* sysdeps/mips/mips64/mul_1.S (__mpn_mul_1): Ditto.
	* sysdeps/mips/mips64/submul_1.S (__mpn_submul_1): Ditto.
2014-12-19 14:39:18 -08:00

130 lines
2.7 KiB
ArmAsm

/* MIPS __mpn_submul_1 -- Multiply a limb vector with a single limb and
subtract the product from a second limb vector.
Copyright (C) 1995-2014 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. If not, see
<http://www.gnu.org/licenses/>. */
#include <sysdep.h>
/* INPUT PARAMETERS
res_ptr $4
s1_ptr $5
size $6
s2_limb $7
*/
#ifdef __PIC__
.option pic2
#endif
ENTRY (__mpn_submul_1)
.set noreorder
#ifdef __PIC__
.cpload t9
#endif
.set nomacro
/* warm up phase 0 */
lw $8,0($5)
/* warm up phase 1 */
addiu $5,$5,4
#if __mips_isa_rev < 6
multu $8,$7
#else
mulu $11,$8,$7
muhu $12,$8,$7
#endif
addiu $6,$6,-1
beq $6,$0,L(LC0)
move $2,$0 /* zero cy2 */
addiu $6,$6,-1
beq $6,$0,L(LC1)
lw $8,0($5) /* load new s1 limb as early as possible */
L(Loop): lw $10,0($4)
#if __mips_isa_rev < 6
mflo $3
mfhi $9
#else
move $3,$11
move $9,$12
#endif
addiu $5,$5,4
addu $3,$3,$2 /* add old carry limb to low product limb */
#if __mips_isa_rev < 6
multu $8,$7
#else
mulu $11,$8,$7
muhu $12,$8,$7
#endif
lw $8,0($5) /* load new s1 limb as early as possible */
addiu $6,$6,-1 /* decrement loop counter */
sltu $2,$3,$2 /* carry from previous addition -> $2 */
subu $3,$10,$3
sgtu $10,$3,$10
addu $2,$2,$10
sw $3,0($4)
addiu $4,$4,4
bne $6,$0,L(Loop) /* should be "bnel" */
addu $2,$9,$2 /* add high product limb and carry from addition */
/* cool down phase 1 */
L(LC1): lw $10,0($4)
#if __mips_isa_rev < 6
mflo $3
mfhi $9
#else
move $3,$11
move $9,$12
#endif
addu $3,$3,$2
sltu $2,$3,$2
#if __mips_isa_rev < 6
multu $8,$7
#else
mulu $11,$8,$7
muhu $12,$8,$7
#endif
subu $3,$10,$3
sgtu $10,$3,$10
addu $2,$2,$10
sw $3,0($4)
addiu $4,$4,4
addu $2,$9,$2 /* add high product limb and carry from addition */
/* cool down phase 0 */
L(LC0): lw $10,0($4)
#if __mips_isa_rev < 6
mflo $3
mfhi $9
#else
move $3,$11
move $9,$12
#endif
addu $3,$3,$2
sltu $2,$3,$2
subu $3,$10,$3
sgtu $10,$3,$10
addu $2,$2,$10
sw $3,0($4)
j $31
addu $2,$9,$2 /* add high product limb and carry from addition */
END (__mpn_submul_1)