2003-11-03 17:41:17 +00:00
|
|
|
/* Optimized strcmp implementation for PowerPC64.
|
2019-01-01 00:11:28 +00:00
|
|
|
Copyright (C) 2003-2019 Free Software Foundation, Inc.
|
2003-11-03 17:41:17 +00:00
|
|
|
This file is part of the GNU C Library.
|
|
|
|
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
|
|
|
modify it under the terms of the GNU Lesser General Public
|
|
|
|
License as published by the Free Software Foundation; either
|
|
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
|
|
|
|
The GNU C Library is distributed in the hope that it will be useful,
|
|
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
Lesser General Public License for more details.
|
|
|
|
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
2012-02-09 23:18:22 +00:00
|
|
|
License along with the GNU C Library; if not, see
|
|
|
|
<http://www.gnu.org/licenses/>. */
|
2003-11-03 17:41:17 +00:00
|
|
|
|
|
|
|
#include <sysdep.h>
|
|
|
|
|
|
|
|
/* See strlen.s for comments on how the end-of-string testing works. */
|
|
|
|
|
|
|
|
/* int [r3] strncmp (const char *s1 [r3], const char *s2 [r4], size_t size [r5]) */
|
|
|
|
|
2017-04-11 17:18:34 +00:00
|
|
|
#ifndef STRNCMP
|
|
|
|
# define STRNCMP strncmp
|
|
|
|
#endif
|
|
|
|
|
PowerPC64 ENTRY_TOCLESS
A number of functions in the sysdeps/powerpc/powerpc64/ tree don't use
or change r2, yet declare a global entry that sets up r2. This patch
fixes that problem, and consolidates the ENTRY and EALIGN macros.
* sysdeps/powerpc/powerpc64/sysdep.h: Formatting.
(NOPS, ENTRY_3): New macros.
(ENTRY): Rewrite.
(ENTRY_TOCLESS): Define.
(EALIGN, EALIGN_W_0, EALIGN_W_1, EALIGN_W_2, EALIGN_W_4, EALIGN_W_5,
EALIGN_W_6, EALIGN_W_7, EALIGN_W_8): Delete.
* sysdeps/powerpc/powerpc64/a2/memcpy.S: Replace EALIGN with ENTRY.
* sysdeps/powerpc/powerpc64/dl-trampoline.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_ceil.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_ceilf.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_floor.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_floorf.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_nearbyint.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_nearbyintf.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_rint.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_rintf.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_round.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_roundf.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_trunc.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_truncf.S: Likewise.
* sysdeps/powerpc/powerpc64/memset.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/fpu/s_finite.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/fpu/s_isinf.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/fpu/s_isnan.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/strstr.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/fpu/e_expf.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/fpu/s_cosf.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/fpu/s_sinf.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/strcasestr.S: Likewise.
* sysdeps/powerpc/powerpc64/addmul_1.S: Use ENTRY_TOCLESS.
* sysdeps/powerpc/powerpc64/cell/memcpy.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_copysign.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_copysignl.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_fabsl.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_isnan.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_llrint.S: Likewise.
* sysdeps/powerpc/powerpc64/fpu/s_llrintf.S: Likewise.
* sysdeps/powerpc/powerpc64/lshift.S: Likewise.
* sysdeps/powerpc/powerpc64/memcpy.S: Likewise.
* sysdeps/powerpc/powerpc64/mul_1.S: Likewise.
* sysdeps/powerpc/powerpc64/power4/memcmp.S: Likewise.
* sysdeps/powerpc/powerpc64/power4/memcpy.S: Likewise.
* sysdeps/powerpc/powerpc64/power4/memset.S: Likewise.
* sysdeps/powerpc/powerpc64/power4/strncmp.S: Likewise.
* sysdeps/powerpc/powerpc64/power5+/fpu/s_ceil.S: Likewise.
* sysdeps/powerpc/powerpc64/power5+/fpu/s_ceilf.S: Likewise.
* sysdeps/powerpc/powerpc64/power5+/fpu/s_floor.S: Likewise.
* sysdeps/powerpc/powerpc64/power5+/fpu/s_floorf.S: Likewise.
* sysdeps/powerpc/powerpc64/power5+/fpu/s_llround.S: Likewise.
* sysdeps/powerpc/powerpc64/power5+/fpu/s_round.S: Likewise.
* sysdeps/powerpc/powerpc64/power5+/fpu/s_roundf.S: Likewise.
* sysdeps/powerpc/powerpc64/power5+/fpu/s_trunc.S: Likewise.
* sysdeps/powerpc/powerpc64/power5+/fpu/s_truncf.S: Likewise.
* sysdeps/powerpc/powerpc64/power5/fpu/s_isnan.S: Likewise.
* sysdeps/powerpc/powerpc64/power6/fpu/s_copysign.S: Likewise.
* sysdeps/powerpc/powerpc64/power6/fpu/s_isnan.S: Likewise.
* sysdeps/powerpc/powerpc64/power6/memcpy.S: Likewise.
* sysdeps/powerpc/powerpc64/power6/memset.S: Likewise.
* sysdeps/powerpc/powerpc64/power6x/fpu/s_isnan.S: Likewise.
* sysdeps/powerpc/powerpc64/power6x/fpu/s_llrint.S: Likewise.
* sysdeps/powerpc/powerpc64/power6x/fpu/s_llround.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/add_n.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/memchr.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/memcmp.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/memcpy.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/memmove.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/mempcpy.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/memrchr.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/memset.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/rawmemchr.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/strcasecmp.S (strcasecmp_l):
Likewise.
* sysdeps/powerpc/powerpc64/power7/strchr.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/strchrnul.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/strcmp.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/strlen.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/strncmp.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/strncpy.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/strnlen.S: Likewise.
* sysdeps/powerpc/powerpc64/power7/strrchr.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/fpu/s_finite.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/fpu/s_isinf.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/fpu/s_isnan.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/fpu/s_llrint.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/fpu/s_llround.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/memcmp.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/memset.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/strchr.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/strcmp.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/strcpy.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/strlen.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/strncmp.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/strncpy.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/strnlen.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/strrchr.S: Likewise.
* sysdeps/powerpc/powerpc64/power8/strspn.S: Likewise.
* sysdeps/powerpc/powerpc64/power9/strcmp.S: Likewise.
* sysdeps/powerpc/powerpc64/power9/strncmp.S: Likewise.
* sysdeps/powerpc/powerpc64/strchr.S: Likewise.
* sysdeps/powerpc/powerpc64/strcmp.S: Likewise.
* sysdeps/powerpc/powerpc64/strlen.S: Likewise.
* sysdeps/powerpc/powerpc64/strncmp.S: Likewise.
* sysdeps/powerpc/powerpc64/ppc-mcount.S: Store LR earlier. Don't
add nop when SHARED.
* sysdeps/powerpc/powerpc64/start.S: Fix comment.
* sysdeps/powerpc/powerpc64/multiarch/strrchr-power8.S (ENTRY): Don't
define.
(ENTRY_TOCLESS): Define.
* sysdeps/powerpc/powerpc32/sysdep.h (ENTRY_TOCLESS): Define.
* sysdeps/powerpc/fpu/s_fma.S: Use ENTRY_TOCLESS.
* sysdeps/powerpc/fpu/s_fmaf.S: Likewise.
2017-06-14 01:15:50 +00:00
|
|
|
ENTRY_TOCLESS (STRNCMP, 4)
|
2004-10-06 22:09:35 +00:00
|
|
|
CALL_MCOUNT 3
|
2003-11-03 17:41:17 +00:00
|
|
|
|
2013-08-17 09:11:17 +00:00
|
|
|
#define rTMP2 r0
|
2003-11-03 17:41:17 +00:00
|
|
|
#define rRTN r3
|
|
|
|
#define rSTR1 r3 /* first string arg */
|
|
|
|
#define rSTR2 r4 /* second string arg */
|
|
|
|
#define rN r5 /* max string length */
|
|
|
|
#define rWORD1 r6 /* current word in s1 */
|
|
|
|
#define rWORD2 r7 /* current word in s2 */
|
|
|
|
#define rFEFE r8 /* constant 0xfefefefefefefeff (-0x0101010101010101) */
|
|
|
|
#define r7F7F r9 /* constant 0x7f7f7f7f7f7f7f7f */
|
|
|
|
#define rNEG r10 /* ~(word in s1 | 0x7f7f7f7f7f7f7f7f) */
|
|
|
|
#define rBITDIF r11 /* bits that differ in s1 & s2 words */
|
2013-08-17 09:11:17 +00:00
|
|
|
#define rTMP r12
|
2003-11-03 17:41:17 +00:00
|
|
|
|
|
|
|
dcbt 0,rSTR1
|
|
|
|
or rTMP, rSTR2, rSTR1
|
|
|
|
lis r7F7F, 0x7f7f
|
|
|
|
dcbt 0,rSTR2
|
|
|
|
clrldi. rTMP, rTMP, 61
|
2005-11-17 21:19:33 +00:00
|
|
|
cmpldi cr1, rN, 0
|
2003-11-03 17:41:17 +00:00
|
|
|
lis rFEFE, -0x101
|
|
|
|
bne L(unaligned)
|
2013-01-07 17:20:53 +00:00
|
|
|
/* We are doubleword aligned so set up for two loops. first a double word
|
2003-11-03 17:41:17 +00:00
|
|
|
loop, then fall into the byte loop if any residual. */
|
|
|
|
srdi. rTMP, rN, 3
|
|
|
|
clrldi rN, rN, 61
|
|
|
|
addi rFEFE, rFEFE, -0x101
|
2005-11-17 21:19:33 +00:00
|
|
|
addi r7F7F, r7F7F, 0x7f7f
|
2013-06-05 20:44:03 +00:00
|
|
|
cmpldi cr1, rN, 0
|
2003-11-03 17:41:17 +00:00
|
|
|
beq L(unaligned)
|
|
|
|
|
|
|
|
mtctr rTMP /* Power4 wants mtctr 1st in dispatch group. */
|
|
|
|
ld rWORD1, 0(rSTR1)
|
|
|
|
ld rWORD2, 0(rSTR2)
|
|
|
|
sldi rTMP, rFEFE, 32
|
|
|
|
insrdi r7F7F, r7F7F, 32, 0
|
|
|
|
add rFEFE, rFEFE, rTMP
|
|
|
|
b L(g1)
|
|
|
|
|
2013-06-05 20:44:03 +00:00
|
|
|
L(g0):
|
2003-11-03 17:41:17 +00:00
|
|
|
ldu rWORD1, 8(rSTR1)
|
|
|
|
bne- cr1, L(different)
|
|
|
|
ldu rWORD2, 8(rSTR2)
|
|
|
|
L(g1): add rTMP, rFEFE, rWORD1
|
|
|
|
nor rNEG, r7F7F, rWORD1
|
|
|
|
bdz L(tail)
|
|
|
|
and. rTMP, rTMP, rNEG
|
|
|
|
cmpd cr1, rWORD1, rWORD2
|
|
|
|
beq+ L(g0)
|
2013-06-05 20:44:03 +00:00
|
|
|
|
2003-11-03 17:41:17 +00:00
|
|
|
/* OK. We've hit the end of the string. We need to be careful that
|
|
|
|
we don't compare two strings as different because of gunk beyond
|
|
|
|
the end of the strings... */
|
2013-06-05 20:44:03 +00:00
|
|
|
|
2013-08-17 09:11:17 +00:00
|
|
|
#ifdef __LITTLE_ENDIAN__
|
|
|
|
L(endstring):
|
|
|
|
addi rTMP2, rTMP, -1
|
|
|
|
beq cr1, L(equal)
|
|
|
|
andc rTMP2, rTMP2, rTMP
|
|
|
|
rldimi rTMP2, rTMP2, 1, 0
|
|
|
|
and rWORD2, rWORD2, rTMP2 /* Mask off gunk. */
|
|
|
|
and rWORD1, rWORD1, rTMP2
|
|
|
|
cmpd cr1, rWORD1, rWORD2
|
|
|
|
beq cr1, L(equal)
|
|
|
|
xor rBITDIF, rWORD1, rWORD2 /* rBITDIF has bits that differ. */
|
|
|
|
neg rNEG, rBITDIF
|
|
|
|
and rNEG, rNEG, rBITDIF /* rNEG has LS bit that differs. */
|
|
|
|
cntlzd rNEG, rNEG /* bitcount of the bit. */
|
|
|
|
andi. rNEG, rNEG, 56 /* bitcount to LS byte that differs. */
|
|
|
|
sld rWORD1, rWORD1, rNEG /* shift left to clear MS bytes. */
|
|
|
|
sld rWORD2, rWORD2, rNEG
|
|
|
|
xor. rBITDIF, rWORD1, rWORD2
|
|
|
|
sub rRTN, rWORD1, rWORD2
|
|
|
|
blt- L(highbit)
|
|
|
|
sradi rRTN, rRTN, 63 /* must return an int. */
|
|
|
|
ori rRTN, rRTN, 1
|
|
|
|
blr
|
|
|
|
L(equal):
|
|
|
|
li rRTN, 0
|
|
|
|
blr
|
|
|
|
|
|
|
|
L(different):
|
|
|
|
ld rWORD1, -8(rSTR1)
|
|
|
|
xor rBITDIF, rWORD1, rWORD2 /* rBITDIF has bits that differ. */
|
|
|
|
neg rNEG, rBITDIF
|
|
|
|
and rNEG, rNEG, rBITDIF /* rNEG has LS bit that differs. */
|
|
|
|
cntlzd rNEG, rNEG /* bitcount of the bit. */
|
|
|
|
andi. rNEG, rNEG, 56 /* bitcount to LS byte that differs. */
|
|
|
|
sld rWORD1, rWORD1, rNEG /* shift left to clear MS bytes. */
|
|
|
|
sld rWORD2, rWORD2, rNEG
|
|
|
|
xor. rBITDIF, rWORD1, rWORD2
|
|
|
|
sub rRTN, rWORD1, rWORD2
|
|
|
|
blt- L(highbit)
|
|
|
|
sradi rRTN, rRTN, 63
|
|
|
|
ori rRTN, rRTN, 1
|
|
|
|
blr
|
|
|
|
L(highbit):
|
|
|
|
sradi rRTN, rWORD2, 63
|
|
|
|
ori rRTN, rRTN, 1
|
|
|
|
blr
|
|
|
|
|
|
|
|
#else
|
2003-11-03 17:41:17 +00:00
|
|
|
L(endstring):
|
|
|
|
and rTMP, r7F7F, rWORD1
|
|
|
|
beq cr1, L(equal)
|
|
|
|
add rTMP, rTMP, r7F7F
|
|
|
|
xor. rBITDIF, rWORD1, rWORD2
|
|
|
|
andc rNEG, rNEG, rTMP
|
|
|
|
blt- L(highbit)
|
|
|
|
cntlzd rBITDIF, rBITDIF
|
|
|
|
cntlzd rNEG, rNEG
|
|
|
|
addi rNEG, rNEG, 7
|
|
|
|
cmpd cr1, rNEG, rBITDIF
|
|
|
|
sub rRTN, rWORD1, rWORD2
|
|
|
|
blt- cr1, L(equal)
|
2013-08-17 09:11:17 +00:00
|
|
|
sradi rRTN, rRTN, 63 /* must return an int. */
|
2003-11-03 17:41:17 +00:00
|
|
|
ori rRTN, rRTN, 1
|
|
|
|
blr
|
|
|
|
L(equal):
|
|
|
|
li rRTN, 0
|
|
|
|
blr
|
|
|
|
|
|
|
|
L(different):
|
2013-08-17 09:11:17 +00:00
|
|
|
ld rWORD1, -8(rSTR1)
|
2003-11-03 17:41:17 +00:00
|
|
|
xor. rBITDIF, rWORD1, rWORD2
|
|
|
|
sub rRTN, rWORD1, rWORD2
|
|
|
|
blt- L(highbit)
|
|
|
|
sradi rRTN, rRTN, 63
|
|
|
|
ori rRTN, rRTN, 1
|
|
|
|
blr
|
|
|
|
L(highbit):
|
2013-08-17 09:11:17 +00:00
|
|
|
sradi rRTN, rWORD2, 63
|
|
|
|
ori rRTN, rRTN, 1
|
2003-11-03 17:41:17 +00:00
|
|
|
blr
|
2013-08-17 09:11:17 +00:00
|
|
|
#endif
|
2003-11-03 17:41:17 +00:00
|
|
|
|
|
|
|
/* Oh well. In this case, we just do a byte-by-byte comparison. */
|
|
|
|
.align 4
|
|
|
|
L(tail):
|
|
|
|
and. rTMP, rTMP, rNEG
|
|
|
|
cmpd cr1, rWORD1, rWORD2
|
|
|
|
bne- L(endstring)
|
|
|
|
addi rSTR1, rSTR1, 8
|
|
|
|
bne- cr1, L(different)
|
|
|
|
addi rSTR2, rSTR2, 8
|
2005-11-17 21:19:33 +00:00
|
|
|
cmpldi cr1, rN, 0
|
2003-11-03 17:41:17 +00:00
|
|
|
L(unaligned):
|
|
|
|
mtctr rN /* Power4 wants mtctr 1st in dispatch group */
|
2005-11-17 21:19:33 +00:00
|
|
|
bgt cr1, L(uz)
|
2003-11-03 17:41:17 +00:00
|
|
|
L(ux):
|
|
|
|
li rRTN, 0
|
|
|
|
blr
|
2005-11-17 21:19:33 +00:00
|
|
|
.align 4
|
|
|
|
L(uz):
|
|
|
|
lbz rWORD1, 0(rSTR1)
|
|
|
|
lbz rWORD2, 0(rSTR2)
|
|
|
|
nop
|
|
|
|
b L(u1)
|
2003-11-03 17:41:17 +00:00
|
|
|
L(u0):
|
|
|
|
lbzu rWORD2, 1(rSTR2)
|
|
|
|
L(u1):
|
|
|
|
bdz L(u3)
|
|
|
|
cmpdi cr1, rWORD1, 0
|
|
|
|
cmpd rWORD1, rWORD2
|
|
|
|
beq- cr1, L(u3)
|
|
|
|
lbzu rWORD1, 1(rSTR1)
|
|
|
|
bne- L(u2)
|
|
|
|
lbzu rWORD2, 1(rSTR2)
|
|
|
|
bdz L(u3)
|
|
|
|
cmpdi cr1, rWORD1, 0
|
|
|
|
cmpd rWORD1, rWORD2
|
|
|
|
bne- L(u3)
|
|
|
|
lbzu rWORD1, 1(rSTR1)
|
|
|
|
bne+ cr1, L(u0)
|
|
|
|
|
2013-06-05 20:44:03 +00:00
|
|
|
L(u2): lbzu rWORD1, -1(rSTR1)
|
2003-11-03 17:41:17 +00:00
|
|
|
L(u3): sub rRTN, rWORD1, rWORD2
|
|
|
|
blr
|
2017-04-11 17:18:34 +00:00
|
|
|
END (STRNCMP)
|
2003-11-03 17:41:17 +00:00
|
|
|
libc_hidden_builtin_def (strncmp)
|