File: [local] / OpenXM_contrib / gmp / mpn / alpha / Attic / addmul_1.asm (download)
Revision 1.1.1.1 (vendor branch), Sat Sep 9 14:12:22 2000 UTC (24 years ago) by maekawa
Branch: GMP
CVS Tags: maekawa-ipv6, VERSION_3_1_1, VERSION_3_1, RELEASE_1_2_2, RELEASE_1_2_1, RELEASE_1_1_3 Changes since 1.1: +0 -0
lines
Import gmp 3.1
|
dnl Alpha __gmpn_addmul_1 -- Multiply a limb vector with a limb and add
dnl the result to a second limb vector.
dnl Copyright (C) 1992, 1994, 1995, 2000 Free Software Foundation, Inc.
dnl This file is part of the GNU MP Library.
dnl The GNU MP Library is free software; you can redistribute it and/or modify
dnl it under the terms of the GNU Lesser General Public License as published
dnl by the Free Software Foundation; either version 2.1 of the License, or (at
dnl your option) any later version.
dnl The GNU MP Library is distributed in the hope that it will be useful, but
dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
dnl License for more details.
dnl You should have received a copy of the GNU Lesser General Public License
dnl along with the GNU MP Library; see the file COPYING.LIB. If not, write to
dnl the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
dnl MA 02111-1307, USA.
include(`../config.m4')
dnl INPUT PARAMETERS
dnl res_ptr r16
dnl s1_ptr r17
dnl size r18
dnl s2_limb r19
dnl This code runs at 42 cycles/limb on EV4, 18 cycles/limb on EV5, and 7
dnl cycles/limb on EV6.
ASM_START()
PROLOGUE(mpn_addmul_1)
ldq r2,0(r17) C r2 = s1_limb
addq r17,8,r17 C s1_ptr++
subq r18,1,r18 C size--
mulq r2,r19,r3 C r3 = prod_low
ldq r5,0(r16) C r5 = *res_ptr
umulh r2,r19,r0 C r0 = prod_high
beq r18,$Lend1 C jump if size was == 1
ldq r2,0(r17) C r2 = s1_limb
addq r17,8,r17 C s1_ptr++
subq r18,1,r18 C size--
addq r5,r3,r3
cmpult r3,r5,r4
stq r3,0(r16)
addq r16,8,r16 C res_ptr++
beq r18,$Lend2 C jump if size was == 2
ALIGN(8)
$Loop: mulq r2,r19,r3 C r3 = prod_low
ldq r5,0(r16) C r5 = *res_ptr
addq r4,r0,r0 C cy_limb = cy_limb + 'cy'
subq r18,1,r18 C size--
umulh r2,r19,r4 C r4 = cy_limb
ldq r2,0(r17) C r2 = s1_limb
addq r17,8,r17 C s1_ptr++
addq r3,r0,r3 C r3 = cy_limb + prod_low
cmpult r3,r0,r0 C r0 = carry from (cy_limb + prod_low)
addq r5,r3,r3
cmpult r3,r5,r5
stq r3,0(r16)
addq r16,8,r16 C res_ptr++
addq r5,r0,r0 C combine carries
bne r18,$Loop
$Lend2: mulq r2,r19,r3 C r3 = prod_low
ldq r5,0(r16) C r5 = *res_ptr
addq r4,r0,r0 C cy_limb = cy_limb + 'cy'
umulh r2,r19,r4 C r4 = cy_limb
addq r3,r0,r3 C r3 = cy_limb + prod_low
cmpult r3,r0,r0 C r0 = carry from (cy_limb + prod_low)
addq r5,r3,r3
cmpult r3,r5,r5
stq r3,0(r16)
addq r5,r0,r0 C combine carries
addq r4,r0,r0 C cy_limb = prod_high + cy
ret r31,(r26),1
$Lend1: addq r5,r3,r3
cmpult r3,r5,r5
stq r3,0(r16)
addq r0,r5,r0
ret r31,(r26),1
EPILOGUE(mpn_addmul_1)
ASM_END()