ddb2897514
Add SSE math and C++ namespace to i386 bits/mathinline.h
2012-06-12 21:10:00 -07:00
c08010c7cd
Use x86_64 fpu/bits/fenv.h for i386 and x86_64
2012-06-06 10:13:19 -07:00
0e4a3cd708
Use i486 bits/string.h for i386 and x86_64
2012-06-04 13:45:43 -07:00
6704c645b0
Provide 32-bit inline string functions for >= i486
2012-06-04 13:44:46 -07:00
62f62904cf
Use i386 bits/huge_vall.h for i386/x86-64
2012-05-30 15:51:32 -07:00
404fe9d90e
Use x86_64 bits/select.h for i386/x86_64
2012-05-30 15:49:31 -07:00
d48d04460a
Use x86_64 bits/setjmp.h for i386/x86_64
2012-05-30 15:43:34 -07:00
7dc00e0d3c
Use x86_64 bits/mathdef.h for i386/x86_64
2012-05-30 15:42:28 -07:00
6bd976963f
Use x86_64 bits/{link.h,linkmap.h} for i386/x86_64
2012-05-30 15:21:55 -07:00
f726f0bb75
Use the same bits/endian.h for i386/x86_64
2012-05-30 14:50:32 -07:00
13764867fe
Use x86-64 bits/byteswap.h for both i386 and x86_64
2012-05-30 14:13:18 -07:00
8422c9a560
Add systemtap static probe points in setjmp/longjmp on x86.
2012-05-25 13:41:03 -07:00
795405f956
Don't include exceptions in libm-test-ulps test names.
2012-05-24 12:14:03 +00:00
80bad0ccae
Test underflow exceptions in libm-test.inc.
2012-05-24 11:26:36 +00:00
d8d1017e5e
Fix warnings in wcschr-c.c
...
Fixes:
In file included from ../sysdeps/i386/i686/multiarch/wcschr-c.c:8:0:
../wcsmbs/wcschr.c:26:1: warning: function declaration isn’t a prototype [-Wstrict-prototypes]
../wcsmbs/wcschr.c:37:1: warning: data definition has no type or storage class [enabled by default]
../wcsmbs/wcschr.c:37:1: warning: type defaults to ‘int’ in declaration of ‘__hidden_ver1’ [enabled by default]
../wcsmbs/wcschr.c:37:1: warning: parameter names (without types) in function declaration [enabled by default]
2012-05-21 22:27:11 +02:00
e0b16cc25c
Fix ccos, csin, ccosh, csinh overflows (bug 14123).
2012-05-19 15:35:29 +00:00
de7f5ce7c5
Fix warnings on Linux/i686
...
Fixes:
../sysdeps/i386/dl-machine.h:336:30: warning: unused variable ‘refsym’ [-Wunused-variable]
rtld.c:1435:3: warning: implicit declaration of function ‘_dl_discover_osversion’ [-Wimplicit-function-declaration]
2012-05-17 20:17:53 +02:00
1a0994f535
BZ#14059: Fix AVX and FMA4 detection.
...
Fix AVX and FMA4 detection by following the guidelines
set out by Intel and AMD for detecting these features.
2012-05-17 06:59:28 -07:00
a9538892ad
Split up stackguard-macros.h into sysdeps directories.
2012-05-15 23:34:30 +00:00
caae5a8101
Remove unused functions from i386/mathinline.h
2012-05-14 16:13:24 +02:00
d7bb4c428a
Add optimized expf for x86
...
2012-05-14 Liubov Dmitrieva <liubov.dmitrieva@gmail.com>
* sysdeps/i386/i686/fpu/multiarch/Makefile: New file.
* sysdeps/i386/i686fpu/multiarch/e_expf.c: New file.
* sysdeps/i386/i686fpu/multiarch/e_expf-ia32.S: New file.
* sysdeps/i386/i686/fpu/multiarch/e_expf-sse2.S: New file.
2012-05-14 11:23:56 +02:00
495fd99f3a
Fix x86/x86_64 expm1l inaccuracy and exceptions (bugs 13885, 13923).
2012-05-07 19:13:08 +00:00
d8b82cad1b
Fix exp10 inaccuracy and exceptions (bugs 13884, 13914).
2012-05-06 18:23:44 +00:00
41498f4db1
Fix missing exceptions from exp (bugs 13787, 13922, 14036).
2012-05-05 19:37:39 +00:00
6698b8bf43
Use .S sources for x86/x86_64 expl.
2012-05-05 19:34:31 +00:00
0c51e5500a
Update sysdeps/i386/fpu/libm-test-ulps
2012-05-03 16:22:52 +02:00
7cb029ee6e
Fix nexttoward bugs (bugs 2550, 2570).
2012-05-01 15:37:43 +00:00
adfbc8ac9e
Fix x86 acos near 1 (bug 13942).
2012-04-30 18:56:39 +00:00
5ba3cc691c
Fix acos (-1) in round-downwards mode on x86 (bug 14034).
2012-04-30 09:38:06 +00:00
fb5e92c979
Remove useless __ilogb*_finite aliases
2012-04-18 00:40:13 +02:00
76da726532
Fix ilogb exception and errno (bug 6794)
...
[BZ #6794 ]
Following Joseph comments about bug 6794, here is a proposed fix. It turned out
to be a large fix mainly because I had to move some file along to follow libm
files/names conventions.
Basically I have added wrappers (w_ilogb.c, w_ilogbf.c, w_ilogbl.c) that now calls
the symbol '__ieee754_ilogb'. The wrappers checks for '__ieee754_ilogb' output and
set the errno and raise exceptions as expected.
The '__ieee754_ilogb' is implemented in sysdeps. I have moved the 's_ilogb[f|l]' files
to e_ilogb[f|l] and renamed the '__ilogb[f|l]' to '__ieee754_ilogb[f|l]'.
I also found out a bug in i386 and x86-64 assembly coded ilogb implementation where
it raises a FE_DIVBYZERO when argument is '0.0'. I corrected this issue as well.
Finally I added the errno and FE_INVALID tests for 0.0, NaN and +-InF argument. Tested
on i386, x86-64, ppc32 and ppc64.
2012-04-17 22:12:53 +02:00
751728a1f1
Reverse arguments of fdivp in i386 code.
2012-04-16 11:03:41 +02:00
8f9a2faee0
Fix spurious overflow exceptions from x86/x86_64 powl (bug 13872).
2012-04-09 22:32:45 +00:00
bcc8d6617b
Fix ctan, ctanh overflow (bug 11521).
2012-04-09 22:31:35 +00:00
8de131cbff
Fix missing clobber in i386 __sincos_code asm.
2012-04-09 12:20:48 -07:00
c483f6b4a4
Fix x86 pow inaccuracy for large integer exponents (bug 706).
2012-04-09 09:42:05 +00:00
3884932b78
memset: also update copyright years
...
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
2012-04-08 14:20:37 -04:00
1e4920e080
memset: fix define usage for shared libs
...
The proper define to check "am I in a shared lib" is "SHARED", not "PIC".
The two new memset_chk functions incorrectly depend on "PIC".
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
2012-04-07 16:33:50 -04:00
f8887d0a5f
Add byteswap-16.h for __bswap_16
2012-04-06 15:14:52 -07:00
b1aa60f32d
Add __bswap_64 definition for non GCC compilers.
...
[BZ#13926]
Currently __bswap_64 is not defined at all for non-GCC compilers.
Define it but guard it with __GLIBC_HAVE_LONG_LONG.
endian.h uses __bswap_64, make the functions only available
if __GLIBC_HAVE_LONG_LONG is defined.
2012-04-03 09:13:59 +02:00
228c019e63
Call __ctype_init in early glibc startup.
...
This adds the bits missing from fd5bdc0924
2012-04-02 22:26:43 +02:00
4b43400f6a
optimize the following memcpy: sysdeps/i386/i686/multiarch/memcpy-ssse3.S
...
I've improved the following implementation of memcpy:
"sysdeps/i386/i686/multiarch/memcpy-ssse3.S".
The patch includes some minor style fixes, but the important part is
just using prefetch loops for the case:
DATA_CACHE_SIZE_HALF <= len < SHARED_CACHE_SIZE_HALF and
src and dst pointers have unequal 16 byte alignments.
This gives from 6% - 50% performance boost on the atom machine, about
24,73% in geometric mean.
2012-03-30 16:45:27 -04:00
d6270972f7
Fix pow of negative numbers to integer exponents (bugs 369, 2678, 3866).
2012-03-28 14:57:58 +00:00
6143dc8d00
Regenerate
2012-03-27 21:37:02 +02:00
1e3cdfda74
Merge branch 'elf-move'
...
Conflicts:
debug/backtracesymsfd.c
sysdeps/generic/elf/backtracesymsfd.c
sysdeps/i386/configure.in
2012-03-27 21:35:36 +02:00
7c69cd143b
Fix cexp overflow (bug 13892).
2012-03-22 19:38:09 +00:00
40b601fbb7
Use autoconf macro for testing compiler options with empty input.
2012-03-21 16:33:57 +00:00
1a4ac776eb
Remove inaccurate x86 cexp implementations (bug 13883).
2012-03-21 15:28:05 +00:00
2460d3aa21
Fix pow of zero and infinity to large powers.
2012-03-21 12:16:00 +00:00
eb96ffb07d
Move stdio-common/_itoa.h to sysdeps/generic
2012-03-20 16:00:23 -07:00
d6373f9ce3
Merge branch 'master' into elf-move
2012-03-20 20:40:16 +01:00
1897ad4432
Fix clog overflow/underflow (bug 13629).
2012-03-19 20:14:26 +00:00
735095ae95
Merge sysdeps/i386/elf/Versions into sysdeps/i386/Versions.
...
Move sysdeps/i386/elf/start.S to sysdeps/i386/
Merge sysdeps/i386/elf/configure.in into sysdeps/i386/configure.in
Delete merged files sysdeps/i386/elf/configure.in, sysdeps/i386/elf/Versions
and sysdeps/i386/elf/configure.
2012-03-19 21:02:40 +01:00
bd37f2ee31
Optimize private 387 fenv access; share code between i386 and x86_64.
2012-03-19 06:51:39 -07:00
d0adc92230
i386/x86_64: Optimize feholdexcept.
2012-03-19 06:51:06 -07:00
7d2e8012cf
i386: Convert libc_{feholdexcept_setround,updateenv}_53bit to functions.
...
Also fix a bug in libc_feupdateenv_53bit: don't force the rounding
precision back to _FPU_EXTENDED, instead restore the precision that
the user had in effect beforehand.
2012-03-19 06:49:04 -07:00
c36e1d2369
Disable Bessel function TLOSS errors in POSIX mode.
2012-03-16 20:08:02 +00:00
11b90b9f50
Fix tan, tanl for large inputs.
2012-03-16 20:05:37 +00:00
8848d99dce
Implement ldbl-96 sinl / cosl / sincosl (bug 13851).
2012-03-16 12:30:05 +00:00
d5ce0ef38d
Update
2012-03-15 18:03:38 +01:00
ee010c9e95
* sysdeps/i386/fpu/s_tanf.S: Delete so that i386 uses the
...
ieee754/flt-32 implementation for tan.
* math/libm-test.inc (tan_test): Add tests for large input.
* sysdeps/i386/fpu/libm-test-ulps: Update.
2012-03-15 17:34:24 +01:00
8c0247db32
[BZ #13852 ]
...
* sysdeps/i386/fpu/e_rem_pio2f.c: Delete so that i386 uses the
ieee754/flt-32 implementation.
* sysdeps/i386/fpu/k_rem_pio2f.c: Likewise.
* sysdeps/i386/fpu/s_cosf.S: Likewise.
* sysdeps/i386/fpu/s_sincosf.S: Likewise.
* sysdeps/i386/fpu/s_sinf.S: Likewise.
* math/libm-test.inc (cos_test): Enable some large input tests for
float as well
(sin_test): Likewise.
(sincos_test): Likewise.
* sysdeps/i386/fpu/libm-test-ulps: Update.
2012-03-15 17:23:43 +01:00
ad6e0564b8
Cleanup formatting.
2012-03-15 14:14:39 +01:00
22417c803d
Update ULPs.
2012-03-14 17:23:31 +01:00
c4814b6b3a
Implement and use libc_feholdexcept_setround_53bit and libc_feupdateenv_53bit
...
so that double arithmetic in s_sin is done in 53 bit (without extend i386 double precision)
2012-03-14 17:20:10 +01:00
1e2405c8fa
Remove files so that i386 uses the iee754/dbl-64 sin and cos implementation.
2012-03-14 17:09:07 +01:00
e456826d7a
Fix csqrt overflow/underflow (bug 13841).
2012-03-14 11:53:32 +00:00
c524201ab0
Replace FSF snail mail address with URL in miscellaneous files.
2012-03-10 00:45:35 +00:00
b8c036204f
Use include_next to chain math_private.h headers.
2012-03-09 16:11:26 -08:00
1ed0291c31
Use <> for math.h and math_private.h everywhere.
...
Entire tree edited via find | grep | sed.
2012-03-09 16:09:10 -08:00
af6a1e3755
Fix sysdeps/i386/configure.in cpuid.h test for bootstrapping.
2012-03-07 20:51:54 +00:00
d1d3431a3a
Fix signs of zeros from casinh, cacosh etc. (bug 10716).
2012-03-07 15:15:19 +00:00
30ee4ced20
* sysdeps/i386/fpu/libm-test-ulps: Update.
2012-03-05 13:37:29 +01:00
b7cd39e8f8
Fix pow in non-default rounding modes (bug 3976).
2012-03-05 12:22:46 +00:00
ca811b2256
Test cosh, sinh in non-default rounding modes (bug 3976).
2012-03-05 12:20:24 +00:00
bc957d531c
Remove oldish __GNUC_PREREQ.
2012-03-03 22:57:00 +01:00
804360ed83
Fix sin, cos, tan in non-default rounding modes (bug 3976).
2012-03-02 20:51:39 +00:00
28afd92dbd
Fix exp in non-default rounding modes (bug 3976).
2012-03-02 15:12:53 +00:00
7b1902cb3e
Improve erfc accuracy.
2012-03-01 21:15:38 +00:00
0bab47b6b2
Fix x86 strcasecmp_l (bug 13786).
2012-02-29 22:37:38 +00:00
0fcad3e243
Add test for bug 5794 (incorrect expm1 overflow).
2012-02-29 20:49:20 +00:00
5b8a4d4a09
Reduce large expected errors from libm tests on x86 and x86_64.
2012-02-29 20:40:50 +00:00
5ad91f6e6f
Resort ULPs files with gen-libm-test.pl -n in C locale.
2012-02-20 18:06:05 +00:00
7c35ffedf1
Fix x86 PLT slot usage for feraiseexcept.
...
Then we're elf/check-localplt.out-clean again.
2012-02-10 21:05:54 +01:00
59ba27a63a
Replace FSF snail mail address with URLs.
2012-02-09 23:18:22 +00:00
6c6dbc6300
Reduce ldouble ULPs for jn tests on x86
2012-02-08 22:25:15 +01:00
3add8e1353
Support crti.S and crtn.S provided directly by architectures.
2012-02-08 01:45:26 +00:00
622c86f480
Remove __ELF__ conditionals
2012-02-07 00:41:11 +01:00
d4a54ac649
Undefine and redefine __i686 for assembly code.
2012-02-06 23:01:25 +00:00
314054eaef
Match x86 PIC thunk names to compiler version.
2012-02-06 18:05:54 +00:00
d8e0ca509a
Use macro for PIC setup in inline asm.
2012-02-05 14:34:14 +00:00
b1da7dd99d
Use macros for x86 PIC thunk names.
2012-02-03 23:24:19 +00:00
9a1d92541f
Consistently use macros for x86 PIC thunks.
2012-02-03 23:22:53 +00:00
56f6f6a240
Use -msse2avx option for x86-64 libm functions
2012-01-28 14:48:46 -05:00
8db2188281
Remove __STDC__ conditionals from libm.
2012-01-27 17:29:45 +00:00
965a54a4ee
Remove __STDC__ conditionals from non-installed headers.
2012-01-26 23:31:37 +00:00
a0da5fe1e4
More fallout from supporting only ELF
2012-01-08 00:45:01 -05:00
a784e50247
Remove pre-ISO C support
...
No more __const.
2012-01-07 23:57:22 -05:00
0269750ca6
Remove non-ELF support
2012-01-07 20:30:26 -05:00
67371b5666
Prevent warnings due to long long constants
2011-12-23 13:52:59 -05:00
70c6c246a2
Optimize x86-32 feraiseexcept also for !__SSE_MATH__
2011-12-23 09:18:02 -05:00
c044cf14b0
Fix wrong copying processing for last bytes in x86-32 wcscpy
...
Wrong copy algorithm for last bytes, not thread safety.
In some particular cases it uses the destination
memory beyond the string end for
16-byte load, puts changes into that part that is relevant
to destination string and writes whole 16-byte chunk into memory.
I have a test case where the memory beyond the string end contains
malloc/free data, that appear corrupted in case free() updates
it in between the 16-byte read and 16-byte write.
2011-12-23 08:50:39 -05:00
aed9d17150
Add feraiseexcept optimization for x86-32
2011-12-22 17:52:30 -05:00
db910efdbd
Also retrieve SSE exceptions in x86-32 fegetexceptflag
2011-12-22 16:28:08 -05:00
2bd779ae3f
Fix overrun in strcpy destination buffer in x86-32/SSSE3 version
2011-12-22 14:22:00 -05:00
1d3e4b618a
Optimized wcschr and wcscpy for x86-64 and x86-32
2011-12-17 14:39:23 -05:00
5583a0862c
Fix SSSE3/SSE4.2 strcasecmp[_l]/strncasecmp[_l] for non-PIC and -mno-tls-direct-seg-refs
2011-11-16 11:48:10 +01:00
6abf346582
Add SSE4.2 support for strcasecmp and strncasecmp on x86-32
2011-11-14 18:24:35 -05:00
76e3966e9e
SSSE3 optimized strcasecmp and strncasecmp for x86-32
2011-11-13 09:50:13 -05:00
e7f4b08ee9
Fix warnings in fallback C code of x86-32 wide memory functions
2011-11-12 00:50:26 -05:00
fe72eebd67
Remove unnecessary code from x86-32 SSSE3 strncmp
2011-11-08 07:50:20 -05:00
0c92d8a87a
Fix some warning nits
2011-10-28 12:02:08 +02:00
b43433460b
Move wide char related routines to wcsmbs subdir
2011-10-28 12:01:29 +02:00
f6ce9294b0
Make math_force_eval accept non-addressable arguments
2011-10-26 11:44:08 +02:00
2fa2ae85ca
Fix strnlen change
2011-10-23 16:30:40 -04:00
fc2ee42abe
Add optimized wcslen and strnlen for x86-32
2011-10-23 15:17:23 -04:00
979c70a3b1
Improve x86-32 SSSE3 memcpy
2011-10-23 14:28:26 -04:00
f17424ed53
Fix WS
2011-10-23 13:35:24 -04:00
95584d3b33
Fix signedness in wcscmp comparison
2011-10-23 13:34:15 -04:00
ed72b6545f
Check for FMA4 support and generate appropriate fma functions
2011-10-20 22:43:15 -04:00
79b195b55a
No need for boundary case handling in x86-32 __ieee_log
2011-10-15 22:21:53 -04:00
bcf01e6d80
Optimize exp
...
Add __exp*_finite optimizations and rewrite some wrappers.
2011-10-15 20:22:59 -04:00
ba1a0d5938
No need for boundary case handling in x86-32 __ieee_logf
2011-10-15 18:09:12 -04:00
be13f7bff6
Optimized memcmp and wmemcmp for x86-64 and x86-32
2011-10-15 11:10:08 -04:00
38ad40ceca
Optimize x86-32 log
2011-10-14 23:41:47 -04:00
f9e123204e
Fix whitespaces
2011-10-12 11:42:57 -04:00
951fbcec70
Optimized memchr, memrchr, rawmemchr for x86-32
2011-10-12 11:42:04 -04:00
0ac5ae2335
Optimize libm
...
libm is now somewhat integrated with gcc's -ffinite-math-only option
and lots of the wrapper functions have been optimized.
2011-10-12 11:27:51 -04:00
3a62d00d40
Don't call ifunc functions in trace mode
2011-10-05 14:35:40 +02:00
e529793b50
Avoid macro clash between <sys/select.h> and <linux/posix_types.h>
2011-09-13 15:16:38 +02:00
83cd142045
Remove --wth-tls option, TLS support is required
2011-09-11 15:02:01 -04:00
d063d16433
Remove support for !USE___THREAD
2011-09-10 16:50:28 -04:00
1248c1c415
Fix jn precision
2011-09-09 22:16:10 -04:00
48882a1abe
Fix up x86-32 section names for Atom code
2011-09-07 22:28:44 -04:00
ceaa0c5dc3
Move Atom-optimized code out of the way and together
2011-09-06 21:53:03 -04:00
b0fc1ff04e
Fix whitespaces
2011-09-05 17:12:27 -04:00
693fb94884
Optimized strchr and strrchr with SSE2 on x86-32
2011-09-05 17:11:11 -04:00
5fc11f0d64
Fix whitespaces
2011-09-05 13:54:51 -04:00
1b48c53782
Add x86-32 optimized wcscmp
2011-09-05 13:53:27 -04:00
fbeb5f4db1
rtld, i386: Fix cfi directive in audit trampoline code
...
_dl_runtime_profile function has wrong cfi directive when
rewinding stack back for the pltexit path.
Only 8 bytes - 2 'pop edx' instructions from the pltentry-only
code should be rewinded back.
With attached patch, I'm able to rewind stack correctly
throught the rtld code from audit library callback.
2011-08-29 09:14:51 -04:00
2cae499541
Fix spurious nop at start of __strspn_ia32
2011-08-23 15:53:51 +02:00
85ae058936
More warning patrol, in dead code (sigh).
2011-08-14 19:26:36 -07:00
b969a69b2e
Fix whitespaces
2011-08-04 15:38:35 -04:00
5fa16e9b01
Improve x86-32 strcat functions with SSE2/SSSE3
2011-08-04 15:33:38 -04:00
8c1a459f9a
Fix inline strncat/strncmp on x86
2011-08-04 14:59:25 -04:00
db290cf592
Never use -mpreferred-stack-boundary=2 on i386, now disallowed by GCC.
2011-07-16 03:10:06 -07:00
661607b3dd
Quash a warning in strstr-c.c built for static.
2011-07-14 20:47:54 -07:00
acb0d739c5
Fix unwind info in 32bit SSE2/SSSE3 strncpy
2011-06-25 01:32:27 -04:00
0b1cbaaef5
Optimized st{r,p}{,n}cpy for SSE2/SSSE3 on x86-32
2011-06-24 14:15:32 -04:00
42675c6ff0
Add an elf_ifunc_invoke interface so that architectures can implement
...
the ifunc resolver calls however they wish.
2011-06-20 19:56:40 -07:00
H.J. Lu
Roland McGrath
Joseph Myers
Andreas Jaeger
Andreas Jaeger
Carlos O'Donell
Liubov Dmitrieva
Andreas Schwab
Adhemerval Zanella
Marek Polacek
Mike Frysinger
Thomas Schwinge
Richard Henderson
Paul Eggert
Thomas Schwinge
Ulrich Drepper
Andreas Schwab
Michael Zolotukhin
Petr Baudis
Liubov Dmitrieva
Jiri Olsa
H.J. Lu
David S. Miller