| 1 |
734 |
jeremybenn |
/* Unsigned 32 bit division optimized for Epiphany.
|
| 2 |
|
|
Copyright (C) 2009, 2011 Free Software Foundation, Inc.
|
| 3 |
|
|
Contributed by Embecosm on behalf of Adapteva, Inc.
|
| 4 |
|
|
|
| 5 |
|
|
This file is part of GCC.
|
| 6 |
|
|
|
| 7 |
|
|
This file is free software; you can redistribute it and/or modify it
|
| 8 |
|
|
under the terms of the GNU General Public License as published by the
|
| 9 |
|
|
Free Software Foundation; either version 3, or (at your option) any
|
| 10 |
|
|
later version.
|
| 11 |
|
|
|
| 12 |
|
|
This file is distributed in the hope that it will be useful, but
|
| 13 |
|
|
WITHOUT ANY WARRANTY; without even the implied warranty of
|
| 14 |
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
| 15 |
|
|
General Public License for more details.
|
| 16 |
|
|
|
| 17 |
|
|
Under Section 7 of GPL version 3, you are granted additional
|
| 18 |
|
|
permissions described in the GCC Runtime Library Exception, version
|
| 19 |
|
|
3.1, as published by the Free Software Foundation.
|
| 20 |
|
|
|
| 21 |
|
|
You should have received a copy of the GNU General Public License and
|
| 22 |
|
|
a copy of the GCC Runtime Library Exception along with this program;
|
| 23 |
|
|
see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
|
| 24 |
|
|
. */
|
| 25 |
|
|
|
| 26 |
|
|
#include "epiphany-asm.h"
|
| 27 |
|
|
|
| 28 |
|
|
/* Because we handle a divident with bit 31 set with truncating integer
|
| 29 |
|
|
arithmetic, there is no rounding-related overflow. */
|
| 30 |
|
|
FSTAB (__umodsi3,T_UINT)
|
| 31 |
|
|
.global SYM(__umodsi3)
|
| 32 |
|
|
.balign 4
|
| 33 |
|
|
HIDDEN_FUNC(__umodsi3)
|
| 34 |
|
|
SYM(__umodsi3):
|
| 35 |
|
|
float r2,r0
|
| 36 |
|
|
mov TMP1,%low(0xb0800000) ; ??? this would be faster with small data
|
| 37 |
|
|
float TMP2,r1
|
| 38 |
|
|
movt TMP1,%high(0xb0800000)
|
| 39 |
|
|
asr TMP0,r0,8
|
| 40 |
|
|
sub TMP0,TMP0,TMP1
|
| 41 |
|
|
mov TMP1,%low(.L0step)
|
| 42 |
|
|
movgteu r2,TMP0
|
| 43 |
|
|
sub r2,r2,TMP2
|
| 44 |
|
|
blteu .L0step
|
| 45 |
|
|
asr r2,r2,23
|
| 46 |
|
|
movt TMP1,%high(.L0step)
|
| 47 |
|
|
lsl TMP2,r2,3
|
| 48 |
|
|
lsl r2,r1,r2` sub r2,r0,r2` movgteu r0,r2 ; STEP(r2)
|
| 49 |
|
|
sub r2,TMP1,TMP2
|
| 50 |
|
|
jr r2
|
| 51 |
|
|
#define STEP(n) lsl.l r2,r1,n` sub r2,r0,r2` movgteu r0,r2
|
| 52 |
|
|
.balign 8,,2
|
| 53 |
|
|
STEP(31)` STEP(30)` STEP(29)` STEP(28)`
|
| 54 |
|
|
STEP(27)` STEP(26)` STEP(25)` STEP(24)`
|
| 55 |
|
|
STEP(23)` STEP(22)` STEP(21)` STEP(20)`
|
| 56 |
|
|
STEP(19)` STEP(18)` STEP(17)` STEP(16)`
|
| 57 |
|
|
STEP(15)` STEP(14)` STEP(13)` STEP(12)`
|
| 58 |
|
|
STEP(11)` STEP(10)` STEP(9)` STEP(8)`
|
| 59 |
|
|
STEP(7)` STEP(6)` STEP(5)` STEP(4)` STEP(3)` STEP(2)` STEP(1)
|
| 60 |
|
|
.L0step:STEP(0)
|
| 61 |
|
|
.Lret_r0:
|
| 62 |
|
|
rts
|
| 63 |
|
|
ENDFUNC(__umodsi3)
|