mirror of
https://review.haiku-os.org/buildtools
synced 2025-02-07 14:34:51 +01:00
4c74403188
Change-Id: Iae65e95cfa0d92091b8b0a424ae36d88efa76aa9 Reviewed-on: https://review.haiku-os.org/c/buildtools/+/3020 Reviewed-by: Adrien Destugues <pulkomandy@gmail.com>
85 lines
2.1 KiB
NASM
85 lines
2.1 KiB
NASM
dnl ARM mpn_copyd.
|
|
|
|
dnl Contributed to the GNU project by Robert Harley and Torbjörn Granlund.
|
|
|
|
dnl Copyright 2003, 2012, 2013 Free Software Foundation, Inc.
|
|
|
|
dnl This file is part of the GNU MP Library.
|
|
dnl
|
|
dnl The GNU MP Library is free software; you can redistribute it and/or modify
|
|
dnl it under the terms of either:
|
|
dnl
|
|
dnl * the GNU Lesser General Public License as published by the Free
|
|
dnl Software Foundation; either version 3 of the License, or (at your
|
|
dnl option) any later version.
|
|
dnl
|
|
dnl or
|
|
dnl
|
|
dnl * the GNU General Public License as published by the Free Software
|
|
dnl Foundation; either version 2 of the License, or (at your option) any
|
|
dnl later version.
|
|
dnl
|
|
dnl or both in parallel, as here.
|
|
dnl
|
|
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 General Public License
|
|
dnl for more details.
|
|
dnl
|
|
dnl You should have received copies of the GNU General Public License and the
|
|
dnl GNU Lesser General Public License along with the GNU MP Library. If not,
|
|
dnl see https://www.gnu.org/licenses/.
|
|
|
|
include(`../config.m4')
|
|
|
|
C cycles/limb
|
|
C StrongARM ?
|
|
C XScale ?
|
|
C Cortex-A7 ?
|
|
C Cortex-A8 ?
|
|
C Cortex-A9 1.25-1.5
|
|
C Cortex-A15 1.25
|
|
|
|
C TODO
|
|
C * Consider wider unrolling. Analogous 8-way code runs 10% faster on both A9
|
|
C and A15. But it probably slows things down for 8 <= n < a few dozen.
|
|
|
|
define(`rp', `r0')
|
|
define(`up', `r1')
|
|
define(`n', `r2')
|
|
|
|
ASM_START()
|
|
PROLOGUE(mpn_copyd)
|
|
mov r12, n, lsl #2
|
|
sub r12, r12, #4
|
|
add rp, rp, r12
|
|
add up, up, r12
|
|
|
|
tst n, #1
|
|
beq L(skip1)
|
|
ldr r3, [up], #-4
|
|
str r3, [rp], #-4
|
|
L(skip1):
|
|
tst n, #2
|
|
beq L(skip2)
|
|
ldmda up!, { r3,r12 }
|
|
stmda rp!, { r3,r12 }
|
|
L(skip2):
|
|
bics n, n, #3
|
|
beq L(rtn)
|
|
|
|
push { r4-r5 }
|
|
subs n, n, #4
|
|
ldmda up!, { r3,r4,r5,r12 }
|
|
beq L(end)
|
|
|
|
L(top): subs n, n, #4
|
|
stmda rp!, { r3,r4,r5,r12 }
|
|
ldmda up!, { r3,r4,r5,r12 }
|
|
bne L(top)
|
|
|
|
L(end): stmda rp, { r3,r4,r5,r12 }
|
|
pop { r4-r5 }
|
|
L(rtn): return lr
|
|
EPILOGUE()
|