This change is equivalent to the commit
c65db17340
and only affects code that is from the Arm optimized-routines project.
It does not affect the observable behaviour, but the code generation
can be different on 64bit targets. The intention is to make the
portable semantics of the code obvious by using a fixed size type.
* (mkcategories): Fix a bug that outputs incorrect Unicode category
table for code point ranges.
* (categories.t): Rebuild it using the bug-fixed mkcategories.
This fixes the problem reported in the following post.
https://cygwin.com/ml/cygwin/2018-06/msg00248.html
Here is the correct patch with both filenames and int cast fixed:
This patch is a complete rewrite of sinf, cosf and sincosf. The new version
is significantly faster, as well as simple and accurate.
The worst-case ULP is 0.56072, maximum relative error is 0.5303p-23 over all
4 billion inputs. In non-nearest rounding modes the error is 1ULP.
The algorithm uses 3 main cases: small inputs which don't need argument
reduction, small inputs which need a simple range reduction and large inputs
requiring complex range reduction. The code uses approximate integer
comparisons to quickly decide between these cases - on some targets this may
be slow, so this can be configured to use floating point comparisons.
The small range reducer uses a single reduction step to handle values up to
120.0. It is fastest on targets which support inlined round instructions.
The large range reducer uses integer arithmetic for simplicity. It does a
32x96 bit multiply to compute a 64-bit modulo result. This is more than
accurate enough to handle the worst-case cancellation for values close to
an integer multiple of PI/4. It could be further optimized, however it is
already much faster than necessary.
Simple benchmark showing speedup factor on AArch64 for various ranges:
range 0.7853982 sinf 1.7 cosf 2.2 sincosf 2.8
range 1.570796 sinf 1.9 cosf 1.9 sincosf 2.7
range 3.141593 sinf 2.0 cosf 2.0 sincosf 3.5
range 6.283185 sinf 2.3 cosf 2.3 sincosf 4.2
range 125.6637 sinf 2.9 cosf 3.0 sincosf 5.1
range 1.1259e15 sinf 26.8 cosf 26.8 sincosf 45.2
ChangeLog:
2018-05-18 Wilco Dijkstra <wdijkstr@arm.com>
* newlib/libm/common/Makefile.in: Regenerated.
* newlib/libm/common/Makefile.am: Add sinf.c, cosf.c, sincosf.c
sincosf.h, sincosf_data.c. Add -fbuiltin -fno-math-errno to CFLAGS.
* newlib/libm/common/math_config.h: Add HAVE_FAST_ROUND, HAVE_FAST_LROUND,
roundtoint, converttoint, force_eval_float, force_eval_double, eval_as_float,
eval_as_double, likely, unlikely.
* newlib/libm/common/cosf.c: New file.
* newlib/libm/common/sinf.c: Likewise.
* newlib/libm/common/sincosf.h: Likewise.
* newlib/libm/common/sincosf.c: Likewise.
* newlib/libm/common/sincosf_data.c: Likewise.
* newlib/libm/math/sf_cos.c: Add #if to build conditionally.
* newlib/libm/math/sf_sin.c: Likewise.
* newlib/libm/math/wf_sincos.c: Likewise.
--
This patch is a complete rewrite of sinf, cosf and sincosf. The new version
is significantly faster, as well as simple and accurate.
The worst-case ULP is 0.56072, maximum relative error is 0.5303p-23 over all
4 billion inputs. In non-nearest rounding modes the error is 1ULP.
The algorithm uses 3 main cases: small inputs which don't need argument
reduction, small inputs which need a simple range reduction and large inputs
requiring complex range reduction. The code uses approximate integer
comparisons to quickly decide between these cases - on some targets this may
be slow, so this can be configured to use floating point comparisons.
The small range reducer uses a single reduction step to handle values up to
120.0. It is fastest on targets which support inlined round instructions.
The large range reducer uses integer arithmetic for simplicity. It does a
32x96 bit multiply to compute a 64-bit modulo result. This is more than
accurate enough to handle the worst-case cancellation for values close to
an integer multiple of PI/4. It could be further optimized, however it is
already much faster than necessary.
Simple benchmark showing speedup factor on AArch64 for various ranges:
range 0.7853982 sinf 1.7 cosf 2.2 sincosf 2.8
range 1.570796 sinf 1.9 cosf 1.9 sincosf 2.7
range 3.141593 sinf 2.0 cosf 2.0 sincosf 3.5
range 6.283185 sinf 2.3 cosf 2.3 sincosf 4.2
range 125.6637 sinf 2.9 cosf 3.0 sincosf 5.1
range 1.1259e15 sinf 26.8 cosf 26.8 sincosf 45.2
ChangeLog:
2018-06-18 Wilco Dijkstra <wdijkstr@arm.com>
* newlib/libm/common/Makefile.in: Regenerated.
* newlib/libm/common/Makefile.am: Add sinf.c, cosf.c, sincosf.c
sincosf.h, sincosf_data.c. Add -fbuiltin -fno-math-errno to CFLAGS.
* newlib/libm/common/math_config.h: Add HAVE_FAST_ROUND, HAVE_FAST_LROUND,
roundtoint, converttoint, force_eval_float, force_eval_double, eval_as_float,
eval_as_double, likely, unlikely.
* newlib/libm/common/cosf.c: New file.
* newlib/libm/common/sinf.c: Likewise.
* newlib/libm/common/sincosf.h: Likewise.
* newlib/libm/common/sincosf.c: Likewise.
* newlib/libm/common/sincosf_data.c: Likewise.
* newlib/libm/math/sf_cos.c: Add #if to build conditionally.
* newlib/libm/math/sf_sin.c: Likewise.
* newlib/libm/math/wf_sincos.c: Likewise.
--
Previously, "test 1 2 3 -a -b -c" was permuted to "test -a -b -c 1 2 3",
but "test 1 2 3 -abc" was left as "test 1 2 3 -abc".
Signed-off-by: Thomas Kindler <mail+newlib@t-kindler.de>
- when calculating a correction to align next brk to page boundary,
ensure that the correction is less than a page size
- if allocating the correction fails, ensure that the top size is
set to brk + sbrk_size (minus any front alignment made)
Signed-off-by: Jeff Johnston <jjohnstn@redhat.com>
When converting number of days since epoch (32-bits) to seconds,
calculations using 32-bit `long` overflow for years above 2038. Solve
this by casting number of days to `time_t` just before final
multiplication.
Signed-off-by: Freddie Chopin <freddie.chopin@gmail.com>
- From: Cesar Philippidis <cesar@codesourcery.com>
Date: Tue, 10 Apr 2018 14:43:42 -0700
Subject: [PATCH] nvptx port
This port adds support for Nvidia GPU's, which are primarily used as
offload accelerators in OpenACC and OpenMP.
The gdtoa implementation uses the type long, defined as Long, in lots
of code. For historical reason newlib defines Long as int32_t instead.
This works fine, as long as floating point exceptions are not enabled.
The conversion to 32 bit int can lead to a FE_INVALID situation.
Example:
const char *str = "121645100408832000.0";
char *ptr;
feenableexcept (FE_INVALID);
strtod (str, &ptr);
This leads to the following situation in strtod
double aadj;
Long L;
[...]
L = (Long)aadj;
For instance, on x86_64 the code here is
cvttsd2si %xmm0,%eax
At this point, aadj is 2529648000.0 in our example. The conversion to
32 bit %eax results in a negative int value, thus the conversion is
invalid. With feenableexcept (FE_INVALID), a SIGFPE is raised.
Fix this by always using 64 bit ints here if double is not a 32 bit type
to avoid this type of FP exceptions.
Signed-off-by: Corinna Vinschen <corinna@vinschen.de>
Classical function call recursion wastes a lot of stack space.
Each recursion level requires a full stack frame comprising all
local variables and additional space as dictated by the
processor calling convention.
This implementation instead stores the variables that are unique
for each recursion level in a parameter stack array, and uses
iteration to emulate recursion. Function call recursion is not
used until the array is full.
To ensure the stack consumption isn't worsened by this design, the
size of the parameter stack array is chosen to be similar to the
stack frame excluding the array. Each function call recursion level
can handle 8 iterative recursion levels.
Stack consumption will worsen when sorting tiny arrays that do not
need recursion (of 6 elements or less). It will be about equal for
up to 15 elements, and be an improvement for larger arrays. The best
case improvement is a stack size reduction down to about one quarter
of the stack consumption before the change.
A design where the parameter stack array is large enough for the
worst case recursion level was rejected because it would worsen
the stack consumption when sorting arrays smaller than about 1500
elements. The worst case is 31 levels on a 32-bit system.
A design with a dynamic parameter array size was rejected because
of limitations in some compilers.
The qsort algorithm splits the input array in three parts. The
left and right parts may need further sorting. One of them is
sorted by recursion, the other by iteration. This update ensures
that it is the smaller part that is chosen for recursion.
By choosing the smaller part, each recursion level will handle
less than half the array of the previous recursion level. Hence
the recursion depth is bounded to be less than log2(n) i.e. 1
level per significant bit in the array size n.
The update also includes code comments explaining the algorithm.
Newlib has a build configuration where syscalls can be directly
embedded in the newlib library rather than relying on libgloss.
This configuration was broken recently by an update to the libgloss
support for Arm that was not propagated to the syscalls interface in
newlib itself. This patch restores the build. It's essentially a
copy of https://sourceware.org/ml/newlib/2018/msg00128.html but there
are some other minor cleanups and changes that I've made at the same
time. None of those cleanups affect functionality.
The prototypes of the following functions have been updated: _link,
_sbrk, _getpid, _write, _swiwrite, _lseek, _swilseek, _read and
_swiread.
Signed-off-by: Richard Earnshaw <Richard.Earnshaw@arm.com>
E.g. arm ABI requires -fshort-enums for bare-metal toolchains.
Given there are only 29 category enums, the compiler chooses an
8 bit enum type, so a size of 11 bits for the bitfield leads to
a compile time error:
error: width of 'cat' exceeds its type
enum category cat: 11;
^~~
Fix this by aligning the size of the category members to byte
borders.
Signed-off-by: Corinna Vinschen <corinna@vinschen.de>
Scripts do not try to acquire Unicode data by best-effort magic anymore.
Options supported:
-h for help
-i to copy Unicode data from /usr/share/unicode/ucd first
-u to download Unicode data from unicode.org first
If (despite of -i or -u if given) the necessary Unicode files are not
available locally, table generation is skipped, but no error code is
returned, so not to obstruct the build process if called from a Makefile.
E.g. arm ABI requires -fshort-enums for bare-metal toolchains.
Given there are only 29 category enums, the compiler chooses an
8 bit enum type, so a size of 11 bits for the bitfield leads to
a compile time error:
error: width of 'cat' exceeds its type
enum category cat: 11;
^~~
Fix this by aligning the size of the category members to byte
borders.
Signed-off-by: Corinna Vinschen <corinna@vinschen.de>
touupper and toulower didn't return a value in all cases. Worse,
this only broke Cygwin when building without optimization for debug
purposes.
Why GCC neglects to notice this is a mystery.
While at it, fix formatting.
Signed-off-by: Corinna Vinschen <corinna@vinschen.de>
The tow* functions use an included case conversion table which can be
generated from Unicode data.
The isw* functions use a character categories table (provided by
categories.c) which can be generated from Unicode data.
Delegation between current-locale and specific-locale-dependent functions
was reverted towards the generic locale-dependent functions (*_l.c);
this is however only relevant on systems with non-Unicode wide character
locales, thus not on Cygwin.
Table categories.t and tag enumeration categories.cat provide
character class data for most of the isw* functions.
These data are generated from Unicode data.
Linux and FreeBSD use int as well. In addition, this fixes an Ada
incompatiblity problem on 64-bit targets. See also GCC:
gcc/ada/libgnarl/s-osinte__rtems.ads
Signed-off-by: Sebastian Huber <sebastian.huber@embedded-brains.de>
Locale modifier @cjkwide makes Unicode "ambiguous width" characters
wide. So ambiguous width characters can be enforced to have width 2
even in non-CJK locales. This gives e.g. users of "Powerline symbols"
the opportunity to adjust their width to the desired behaviour (and the
behaviour apparently expected by some tools) without having to set a CJK
locale and without losing consistence of terminal character width with
wcwidth/wcswidth locale width.
At least with Binutils 2.30 and GCC 7.3 we need symbol definitions
without the leading underscore.
Signed-off-by: Sebastian Huber <sebastian.huber@embedded-brains.de>
This is a NetBSD-specific detail which does not apply to Newlib, causing
linking issues in certain scenarios:
https://cygwin.com/ml/cygwin/2018-01/msg00189.html
Signed-off-by: Yaakov Selkowitz <yselkowi@redhat.com>
New optimized powf, logf, log2f, expf and exp2f yield worse performance
on Arm targets with only single precision instructions because the
double precision arithmetic is then implemented via softfloat routines.
This patch uses the old implementation when double precision
instructions are not available on Arm targets.
Testing: Built newlib with GCC's rmprofile Arm multilibs and compared
before/after -> only the above functions are changed and calls to them
(name change from logf to __ieee754_logf and similar). Testing the
changed function on a panel of values yields the same result before the
original patches to improve them and after this one. Double checking the
performance by looping the same panel of values being tested on Arm
Cortex-M4 does show the performance regression is fixed.
This patch fixes a syntax error in exit.c that was introduced during the
ANSI-fication of newlib. The patch fixes a compile-time issue that arises when
newlib is configured with the --enable-lite-exit feature.
Code path for _MB_CAPABLE scans for the '%' character and advances
'fmt' pointer past '%'. Code path for !_MB_CAPABLE leaved fmt pointing
to '%', which caused the state machine to go from START to DONE state
immediately.
Neither upstream FreeBSD nor glibc ever call fflush from ftell
and friends. In border cases it has the tendency to return
wrong or unexpected values, for instance on block devices.
Signed-off-by: Corinna Vinschen <corinna@vinschen.de>
Make prototype of _kill() always visible when _COMPILING_NEWLIB is
defined. This makes <sys/signal.h> consistent with the use of
_COMPILING_NEWLIB in <sys/unistd.h>, <sys/times.h>, etc.
Updated patch to use 0.0f in addition to calling rintf.
Tested same way as before, with a testcase that triggers the code and
make check.
OK?
newlib/
* libm/math/wf_pow.c (powf): Call rintf instead of rint. Use 0.0f
for compare.
To update my email address to my current employer. Specifix died quite a while
ago, and I've had two jobs in the interim.
newlib/
* MAINTAINERS: Update my email address.
To follow up the thread starting at [1], since all uses of TRAD_SYNOPSIS
have been removed, and all uses of ANSI_SYNOPSIS have been renamed to
SYNOPSIS, we can now warn about the use of these.
[1] https://sourceware.org/ml/newlib/2017/msg01182.html
Signed-off-by: Jon Turney <jon.turney@dronecode.org.uk>
Discard QUICKREF sections, rather than writing them to stderr
Discard MATHREF sections, rather than discarding as an error
Pass NOTES sections through to texinfo, rather than discarding as an error
Don't redirect makedoc stderr to .ref file
Remove makedoc output on error
Remove .ref files from CLEANFILES
Regenerate Makefile.ins
Signed-off-by: Jon Turney <jon.turney@dronecode.org.uk>
Old BSD bug: While ^ is recognized and the set of matching characters
is negated, the code neglects to increment the pointer pointing to the
matching characters. Thus, on a negation expression like %[^xyz], the
matching doesn't only stop at x, y, or z, but incorrectly also on ^.
Fix this by setting the start pointer after recognizing the ^.
Signed-off-by: Corinna Vinschen <corinna@vinschen.de>
The following functions are also guarded in glibc:
fwprintf, swprintf, wprintf, vfwprintf, vswprintf, vwprintf.
Signed-off-by: Yaakov Selkowitz <yselkowi@redhat.com>
* vfscanf: per POSIX, if the target type is wchar_t, the width is
counted in (multibyte) characters, not in bytes.
* vfscanf: Handle UTF-8 multibyte sequences converted to surrogate
pairs on UTF-16 systems.
* vfwscanf: Don't count high surrogates in input against field width
counting. Per POSIX, input is
Signed-off-by: Corinna Vinschen <corinna@vinschen.de>
The width value keeps the maximum field width. This is the maximum
field width of the *input*. It's *never* to be used in conjunction
with the number of bytes or characters written to the output argument.
However, especially in vfwscanf, the code is partially taken from
NetBSD which erroneously subtracts the number of multibyte chars
written to the argument from the width variable, thus potentially
subtracting up to MB_CUR_MAX from width for a single character in
the input stream.
To make matters worse, the previous patch adding %m added basically
the same mistake for 'c' type input.
Fix it.
Signed-off-by: Corinna Vinschen <corinna@vinschen.de>
* The new code is guarded with _WANT_IO_POSIX_EXTENSIONS, but
this is automatically enabled with _WANT_IO_C99_FORMATS for now.
* vfscanf neglects to implement %l[, so %ml[ is not implemented yet
either.
* Sidenote: vfwscanf doesn't allow ranges in %[ yet. Strictly this
is allowed per POSIX, but it differes from vfscanf as well as from
glibc.
Signed-off-by: Corinna Vinschen <corinna@vinschen.de>
The implementation is from NetBSD, with the addition of feature test macros
for readlink. glibc also wraps the following functions:
confstr, getdomainname, getgroups, gethostname, getlogin_r, getwd, pread,
readlinkat, ttyname_r.
Signed-off-by: Yaakov Selkowitz <yselkowi@redhat.com>
The implementation is mostly from NetBSD, except for switching fgets to
pure inline, and the addition of fgets_unlocked, fread, and fread_unlocked
for parity with glibc. The following functions are also guarded in glibc:
asprintf, dprintf, fprintf, printf, vasprintf, vdprintf, vfprintf, vprintf.
Signed-off-by: Yaakov Selkowitz <yselkowi@redhat.com>
The implementation is from NetBSD, with the addition of mempcpy (a GNU
extension) for parity with glibc and libssp.
Signed-off-by: Yaakov Selkowitz <yselkowi@redhat.com>
The Object Size Checking (-D_FORTIFY_SOURCE=*) functionality provides
wrappers around functions suspectible to buffer overflows. While
independent from Stack Smashing Protection (-fstack-protector*), they
are often used and implemented together.
While GCC also provides an implementation in libssp, it is completely
broken (CVE-2016-4973, RHBZ#1324759) and seemingly unfixable, as there
is no reliable way for a preprocessor macro to trigger a link flag.
Therefore, adding this here is necessary to make it work.
Note that this does require building gcc with --disable-libssp and
gcc_cv_libc_provides_ssp=yes.
Signed-off-by: Yaakov Selkowitz <yselkowi@redhat.com>
Compiling with any of the -fstack-protector* flags requires the
__stack_chk_guard data import (which needs to be initialized) and the
__stack_chk_fail{,_local} functions. While GCC's own libssp can provide
these, it is better that we provide these ourselves. The implementation
is custom due to being OS-specific.
Signed-off-by: Yaakov Selkowitz <yselkowi@redhat.com>
The special handling of %\0 in [w]scanf is flawed. It's just a
matching failure and should be handled as such. scanf also
fakes an int input value on %X with X being an invalid conversion
char. This is also just a matching failure and should be handled
the same way as %\0.
There's no indication of the reason for this "disgusting
backwards compatibility hacks" in the logs, given this
code made it into newlib before setting up the CVS repo.
Just handle these cases identically as matching failures.
Signed-off-by: Corinna Vinschen <corinna@vinschen.de>
Since commit 8128f5482f, we have all the
non-tracing functions listed in posixoptions(7). The tracing functions
are gated by their own option, and are obsolecent anyway.
Signed-off-by: Yaakov Selkowitz <yselkowi@redhat.com>
Difference to Linux: We can't create files which don't show up
in the filesystem due to OS restrictions. As a kludge, make a
(half-hearted) attempt to hide the file in the filesystem.
Signed-off-by: Corinna Vinschen <corinna@vinschen.de>
The variable doesn't follow the convention of having the same name as
the function it's bundled with. Furthermore, it clashes with the
variable of the same name in newlib/libc/stdlib/calloc.c.
Signed-off-by: Florian Schmidt <florian.schmidt@neclab.eu>
RTEMS provides the option to have a global or per-thread reentrancy
as part of application configuration. As part of this, RTEMS provides
the implementation of __getreent() as appropriate. Allow the target
to determine if this method is present in libc.a.
Szabolcs Nagy
Takashi Yano
Corinna Vinschen
Jon Beniston
Wilco Dijkstra
Thomas Kindler
Jeff Johnston
Matthias Kannwischer
Freddie Chopin
Thomas Wolff
Hakan Lindqvist
Joel Sherrill
Richard Earnshaw
Yaakov Selkowitz
Thomas Wolff
Jon Turney
Sebastian Huber
Our Air Quality
Jaap de Wolff
Thomas Preudhomme
Orlando Arias
Kito Cheng
Ivan Grokhotkov
Alexander Fedotov
Jim Wilson
Martin Aberg
Florian Schmidt