dnl Alpha mpn_lshift -- Shift a number left.
dnl Copyright 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.
dnl INPUT PARAMETERS
dnl res_ptr r16
dnl s1_ptr r17
dnl size r18
dnl cnt r19
dnl This code runs at 4.8 cycles/limb on the 21064. With infinite unrolling,
dnl it would take 4 cycles/limb. It should be possible to get down to 3
dnl cycles/limb since both ldq and stq can be paired with the other used
dnl instructions. But there are many restrictions in the 21064 pipeline that
dnl makes it hard, if not impossible, to get down to 3 cycles/limb:
dnl 1. ldq has a 3 cycle delay, srl and sll have a 2 cycle delay.
dnl 2. Only aligned instruction pairs can be paired.
dnl 3. The store buffer or silo might not be able to deal with the bandwidth.
s8addq r18,r17,r17 C make r17 point at end of s1
ldq r4,-8(r17) C load first limb
s8addq r18,r16,r16 C make r16 point at end of RES
and r18,4-1,r20 C number of limbs in first loop
srl r4,r7,r0 C compute function result
$L0: beq r18,$Lend
$Loop: ldq r3,-8(r17)
$Lend: sll r4,r19,r8