mirror of
https://github.com/autc04/Retro68.git
synced 2024-12-11 19:49:32 +00:00
172 lines
4.5 KiB
ArmAsm
172 lines
4.5 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/strncpy.c will be
|
|
used. */
|
|
#if !defined (__OPTIMIZE_SIZE__) && !defined (PREFER_SIZE_OVER_SPEED)
|
|
|
|
#include "asm.h"
|
|
|
|
/* If dst and src are 4 byte aligned, copy 8 bytes at a time.
|
|
If the src is 4, but not 8 byte aligned, we first read 4 bytes to get
|
|
it 8 byte aligned. Thus, we can do a little read-ahead, without
|
|
dereferencing a cache line that we should not touch.
|
|
Note that short and long instructions have been scheduled to avoid
|
|
branch stalls.
|
|
The beq_s to r3z could be made unaligned & long to avoid a stall
|
|
there, but the it is not likely to be taken often, and it
|
|
would also be likey to cost an unaligned mispredict at the next call. */
|
|
|
|
#if !defined (__ARC601__) && defined (__ARC_BARREL_SHIFTER__)
|
|
|
|
#if defined (__ARC700___) || defined (__ARCEM__) || defined (__ARCHS__)
|
|
#define BRand(a,b,l) tst a,b ` bne_l l
|
|
#else
|
|
#define BRand(a,b,l) and a,a,b ` brne_s a,0,l
|
|
#endif
|
|
|
|
ENTRY (strncpy)
|
|
cmp_s r2,8
|
|
or r12,r0,r1
|
|
bmsk.cc.f r12,r12,1
|
|
brne.d r12,0,.Lbytewise
|
|
mov_s r10,r0
|
|
ld_s r3,[r1,0]
|
|
mov r8,0x01010101
|
|
sub lp_count,r2,1
|
|
bbit0.d r1,2,.Loop_start
|
|
ror r11,r8
|
|
sub r12,r3,r8
|
|
bic_l r12,r12,r3
|
|
BRand (r12,r11,.Lr3z)
|
|
mov_s r4,r3
|
|
ld.a r3,[r1,4]
|
|
sub lp_count,lp_count,4
|
|
st.ab r4,[r10,4]
|
|
.balign 4
|
|
.Loop_start:
|
|
lsr.f lp_count,lp_count,3
|
|
lpne .Loop_end
|
|
ld.a r4,[r1,4]
|
|
sub r12,r3,r8
|
|
bic_s r12,r12,r3
|
|
BRand (r12,r11,.Lr3z)
|
|
st.ab r3,[r10,4]
|
|
sub r12,r4,r8
|
|
bic r12,r12,r4
|
|
BRand (r12,r11,.Lr4z)
|
|
ld.a r3,[r1,4]
|
|
st.ab r4,[r10,4]
|
|
.Loop_end:
|
|
bcc_s .Lastword
|
|
ld.a r4,[r1,4]
|
|
sub r12,r3,r8
|
|
bic_s r12,r12,r3
|
|
BRand (r12,r11,.Lr3z)
|
|
st.ab r3,[r10,4]
|
|
mov_s r3,r4
|
|
.Lastword:
|
|
and.f lp_count,r2,3
|
|
mov.eq lp_count,4
|
|
lp .Last_byte_end
|
|
#ifdef __LITTLE_ENDIAN__
|
|
bmsk.f r1,r3,7
|
|
lsr.ne r3,r3,8
|
|
#else
|
|
lsr.f r1,r3,24
|
|
asl.ne r3,r3,8
|
|
#endif
|
|
stb.ab r1,[r10,1]
|
|
.Last_byte_end:
|
|
j_s [blink]
|
|
|
|
.balign 4
|
|
.Lr4z:
|
|
mov_l r3,r4
|
|
.Lr3z:
|
|
#if defined (__ARC700__) || defined (__ARCEM__) || defined (__ARCHS__)
|
|
#ifdef __LITTLE_ENDIAN__
|
|
bmsk.f r1,r3,7
|
|
lsr_s r3,r3,8
|
|
#else
|
|
lsr.f r1,r3,24
|
|
asl_s r3,r3,8
|
|
#endif
|
|
bne.d .Lr3z
|
|
stb.ab r1,[r10,1]
|
|
#else /* ! __ARC700__ */
|
|
#ifdef __LITTLE_ENDIAN__
|
|
bmsk.f r1,r3,7
|
|
.Lr3z_loop:
|
|
lsr_s r3,r3,8
|
|
stb.ab r1,[r10,1]
|
|
bne.d .Lr3z_loop
|
|
bmsk.f r1,r3,7
|
|
#else
|
|
lsr.f r1,r3,24
|
|
.Lr3z_loop:
|
|
asl_s r3,r3,8
|
|
stb.ab r1,[r10,1]
|
|
bne.d .Lr3z_loop
|
|
lsr.f r1,r3,24
|
|
#endif /* ENDIAN */
|
|
#endif /* ! __ARC700__ */
|
|
.Lzero_rest:
|
|
; __strncpy_bzero requires:
|
|
; return value in r0
|
|
; zeroing length in r2
|
|
; zeroing start address in r3
|
|
mov_s r3,r10
|
|
add_s r2,r2,r0
|
|
b.d __strncpy_bzero
|
|
sub_s r2,r2,r3
|
|
|
|
.balign 4
|
|
.Lbytewise:
|
|
sub.f r2,r2,1
|
|
mov_l r3,r0
|
|
jcs [blink]
|
|
.Lcharloop:
|
|
ldb.ab r12,[r1,1]
|
|
beq.d .Last_byte
|
|
sub.f r2,r2,1
|
|
brne.d r12,0,.Lcharloop
|
|
stb.ab r12,[r3,1]
|
|
b.d __strncpy_bzero
|
|
stb.ab r12,[r3,1]
|
|
.Last_byte:
|
|
j_s.d [blink]
|
|
stb_l r12,[r3]
|
|
ENDFUNC (strncpy)
|
|
#endif /* !__ARC601__ && __ARC_BARREL_SHIFTER__ */
|
|
|
|
#endif /* !__OPTIMIZE_SIZE__ && !PREFER_SIZE_OVER_SPEED */
|