newlib-cygwin/newlib/libc/machine/arc/strlen.S

166 lines
4.0 KiB
ArmAsm

/*
Copyright (c) 2015, Synopsys, Inc. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
1) Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
2) Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
3) Neither the name of the Synopsys, Inc., nor the names of its contributors
may be used to endorse or promote products derived from this software
without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
*/
/* This implementation is optimized for performance. For code size a generic
implementation of this function from newlib/libc/string/strlen.c will be
used. */
#if !defined (__OPTIMIZE_SIZE__) && !defined (PREFER_SIZE_OVER_SPEED)
#include "asm.h"
#if defined(__ARC601__) || !defined (__ARC_BARREL_SHIFTER__)
/* This code is optimized for the ARC601 pipeline without barrel shifter. */
ENTRY (strlen)
or r3,r0,7
ld r2,[r3,-7]
ld.a r6,[r3,-3]
mov r4,0x01010101
; uses long immediate
#ifdef __LITTLE_ENDIAN__
bmsk.f 0,r0,1
mov_s r1,31
add3_s r1,r1,r0
bmsk r7,r4,r1
xor.ne r7,r7,r4
btst_s r0,2
ror r5,r4
sub r1,r2,r7
bic_s r1,r1,r2
mov.eq r7,r4
sub r12,r6,r7
bic r12,r12,r6
or.eq r12,r12,r1
and r12,r12,r5
brne r12,0,.Learly_end
#else /* BIG ENDIAN */
add.f r1,r4,30 ; r1 mod 31 := -1; clear carry
ror r5,r4
sub3 r7,r1,r0
btst_s r0,2
sub r1,r2,r4
bic_s r1,r1,r2
bmsk r1,r1,r7
sub r12,r6,r4
bic r12,r12,r6
bmsk.ne r12,r12,r7
or.eq r12,r12,r1
and r12,r12,r5
brne r12,0,.Learly_end
#endif /* ENDIAN */
.Loop:
ld_s r2,[r3,4]
ld.a r6,[r3,8]
; stall for load result
sub r1,r2,r4
bic_s r1,r1,r2
sub r12,r6,r4
bic r12,r12,r6
or_s r12,r12,r1
and r12,r12,r5
breq_s r12,0,.Loop
.Lend:
and.f r1,r1,r5
sub.ne r3,r3,4
#ifdef __LITTLE_ENDIAN__
mov.eq r1,r12
btst_s r1,7
sub r0,r3,r0
add.eq r0,r0,1
bmsk.f 0,r1,15
add.eq r0,r0,1
bmsk.f 0,r1,23
j_s.d [blink]
add.eq r0,r0,1
#else /* BIG ENDIAN */
#ifdef __OPTIMIZE_SIZE__
1: ldb_s r1,[r3]
breq_s r1,0,0f
ldb.a r1,[r3,1]
breq_s r1,0,0f
ldb.a r1,[r3,1]
breq_s r1,0,0f
add_s r3,r3,1
0: j_s.d [blink]
sub r0,r3,r0
#define SPECIAL_EARLY_END
.Learly_end:
mov_s r3,r0
b_s 1b
#elif 0 /* Need more information about pipeline to assess if this is faster. */
mov.eq r2,r6
and r2,r2,r5
sub1 r2,r4,r2
mov.eq r1,r12
bic.f r1,r1,r2
sub r0,r3,r0
add.pl r0,r0,1
btst.pl r1,23
add.eq r0,r0,1
btst.eq r1,15
j_s.d [blink]
add.eq r0,r0,1
#else /* !__OPTIMIZE_SIZE__ */
/* Need carry clear here. */
mov.eq r2,r6
1: bmsk r1,r2,23
breq r1,r2,0f
bmsk r2,r1,15
breq.d r1,r2,0f
add_s r3,r3,1
cmp r2,0x100
add_s r3,r3,2
0: j_s.d [blink]
sbc r0,r3,r0
#define SPECIAL_EARLY_END
.Learly_end:
sub_s.ne r1,r1,r1
mov_s r12,0
bset r12,r12,r7
sub1 r2,r2,r12
b.d .Lend
sub1.ne r6,r6,r12
#endif /* !__OPTIMIZE_SIZE__ */
#endif /* ENDIAN */
#ifndef SPECIAL_EARLY_END
.balign 4
.Learly_end:
b.d .Lend
sub_s.ne r1,r1,r1
#endif /* !SPECIAL_EARLY_END */
ENDFUNC (strlen)
#endif /* __ARC601__ || !__ARC_BARREL_SHIFTER__*/
#endif /* !__OPTIMIZE_SIZE__ && !PREFER_SIZE_OVER_SPEED */