The CORE-MATH implementation is correctly rounded (for any rounding mode)
and shows better performance to the generic tanf.
The code was adapted to glibc style, to use the definition of
math_config.h, to remove errno handling, and to use a generic
128 bit routine for ABIs that do not support it natively.
Benchtest on x64_64 (Ryzen 9 5900X, gcc 14.2.1), aarch64 (neoverse1,
gcc 13.2.1), and powerpc (POWER10, gcc 13.2.1):
latency master patched improvement
x86_64 82.3961 54.8052 33.49%
x86_64v2 82.3415 54.8052 33.44%
x86_64v3 69.3661 50.4864 27.22%
i686 219.271 45.5396 79.23%
aarch64 29.2127 19.1951 34.29%
power10 19.5060 16.2760 16.56%
reciprocal-throughput master patched improvement
x86_64 28.3976 19.7334 30.51%
x86_64v2 28.4568 19.7334 30.65%
x86_64v3 21.1815 16.1811 23.61%
i686 105.016 15.1426 85.58%
aarch64 18.1573 10.7681 40.70%
power10 8.7207 8.7097 0.13%
Signed-off-by: Alexei Sibidanov <sibid@uvic.ca>
Signed-off-by: Paul Zimmermann <Paul.Zimmermann@inria.fr>
Signed-off-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Reviewed-by: DJ Delorie <dj@redhat.com>
The CORE-MATH implementation is correctly rounded (for any rounding mode)
and shows better performance compared to the generic exp2m1f.
The code was adapted to glibc style and to use the definition of
math_config.h (to handle errno, overflow, and underflow). The
only change is to handle FLT_MAX_EXP for FE_DOWNWARD or FE_TOWARDZERO.
The benchmark inputs are based on exp2f ones.
Benchtest on x64_64 (Ryzen 9 5900X, gcc 14.2.1), aarch64 (Neoverse-N1,
gcc 13.3.1), and powerpc (POWER10, gcc 13.2.1):
Latency master patched improvement
x86_64 40.6042 48.7104 -19.96%
x86_64v2 40.7506 35.9032 11.90%
x86_64v3 35.2301 31.7956 9.75%
i686 102.094 94.6657 7.28%
aarch64 18.2704 15.1387 17.14%
power10 11.9444 8.2402 31.01%
reciprocal-throughput master patched improvement
x86_64 20.8683 16.1428 22.64%
x86_64v2 19.5076 10.4474 46.44%
x86_64v3 19.2106 10.4014 45.86%
i686 56.4054 59.3004 -5.13%
aarch64 12.0781 7.3953 38.77%
power10 6.5306 5.9388 9.06%
The generic implementation calls __ieee754_exp2f and x86_64 provides
an optimized ifunc version (built with -mfma -mavx2, not correctly
rounded). This explains the performance difference for x86_64.
Same for i686, where the ABI provides an optimized __ieee754_exp2f
version built with '-msse2 -mfpmath=sse'. When built wth same
flags, the new algorithm shows a better performance:
master patched improvement
latency 102.094 91.2823 10.59%
reciprocal-throughput 56.4054 52.7984 6.39%
Signed-off-by: Alexei Sibidanov <sibid@uvic.ca>
Signed-off-by: Paul Zimmermann <Paul.Zimmermann@inria.fr>
Signed-off-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Reviewed-by: DJ Delorie <dj@redhat.com>
The CORE-MATH implementation is correctly rounded (for any rounding mode)
and shows better performance compared to the generic exp10m1f.
The code was adapted to glibc style and to use the definition of
math_config.h (to handle errno, overflow, and underflow). I mostly
fixed some small issues in corner cases (sNaN handling, -INFINITY,
a specific overflow check).
Benchtest on x64_64 (Ryzen 9 5900X, gcc 14.2.1), aarch64 (Neoverse-N1,
gcc 13.3.1), and powerpc (POWER10, gcc 13.2.1):
Latency master patched improvement
x86_64 45.4690 49.5845 -9.05%
x86_64v2 46.1604 36.2665 21.43%
x86_64v3 37.8442 31.0359 17.99%
i686 121.367 93.0079 23.37%
aarch64 21.1126 15.0165 28.87%
power10 12.7426 8.4929 33.35%
reciprocal-throughput master patched improvement
x86_64 19.6005 17.4005 11.22%
x86_64v2 19.6008 11.1977 42.87%
x86_64v3 17.5427 10.2898 41.34%
i686 59.4215 60.9675 -2.60%
aarch64 13.9814 7.9173 43.37%
power10 6.7814 6.4258 5.24%
The generic implementation calls __ieee754_exp10f which has an
optimized version, although it is not correctly rounded, which is
the main culprit of the the latency difference for x86_64 and
throughp for i686.
Signed-off-by: Alexei Sibidanov <sibid@uvic.ca>
Signed-off-by: Paul Zimmermann <Paul.Zimmermann@inria.fr>
Signed-off-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Reviewed-by: DJ Delorie <dj@redhat.com>
The CORE-MATH implementation is correctly rounded (for any rounding mode).
This can be checked by exhaustive tests in a few minutes since there are
less than 2^32 values to check against for example GNU MPFR.
This patch also adds some bench values for tgammaf.
Tested on x86_64 and x86 (cfarm26).
With the initial GNU libc code it gave on an Intel(R) Core(TM) i7-8700:
"tgammaf": {
"": {
"duration": 3.50188e+09,
"iterations": 2e+07,
"max": 602.891,
"min": 65.1415,
"mean": 175.094
}
}
With the new code:
"tgammaf": {
"": {
"duration": 3.30825e+09,
"iterations": 5e+07,
"max": 211.592,
"min": 32.0325,
"mean": 66.1649
}
}
With the initial GNU libc code it gave on cfarm26 (i686):
"tgammaf": {
"": {
"duration": 3.70505e+09,
"iterations": 6e+06,
"max": 2420.23,
"min": 243.154,
"mean": 617.509
}
}
With the new code:
"tgammaf": {
"": {
"duration": 3.24497e+09,
"iterations": 1.8e+07,
"max": 1238.15,
"min": 101.155,
"mean": 180.276
}
}
Signed-off-by: Alexei Sibidanov <sibid@uvic.ca>
Signed-off-by: Paul Zimmermann <Paul.Zimmermann@inria.fr>
Changes in v2:
- include <math.h> (fix the linknamespace failures)
- restored original benchtests/strcoll-inputs/filelist#en_US.UTF-8 file
- restored original wrapper code (math/w_tgammaf_compat.c),
except for the dealing with the sign
- removed the tgammaf/float entries in all libm-test-ulps files
- address other comments from Joseph Myers
(https://sourceware.org/pipermail/libc-alpha/2024-July/158736.html)
Changes in v3:
- pass NULL argument for signgam from w_tgammaf_compat.c
- use of math_narrow_eval
- added more comments
Changes in v4:
- initialize local_signgam to 0 in math/w_tgamma_template.c
- replace sysdeps/ieee754/dbl-64/gamma_productf.c by dummy file
Changes in v5:
- do not mention local_signgam any more in math/w_tgammaf_compat.c
- initialize local_signgam to 1 instead of 0 in w_tgamma_template.c
and added comment
Changes in v6:
- pass NULL as 2nd argument of __ieee754_gammaf_r in
w_tgammaf_compat.c, and check for NULL in e_gammaf_r.c
Changes in v7:
- added Signed-off-by line for Alexei Sibidanov (author of the code)
Changes in v8:
- added Signed-off-by line for Paul Zimmermann (submitted of the patch)
Changes in v9:
- address comments from review by Adhemerval Zanella
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Several copies of the licenses in files contained whitespace related
problems. Two cases are addressed here, the first is two spaces
after a period which appears between "PURPOSE." and "See". The other
is a space after the last forward slash in the URL. Both issues are
corrected and the licenses now match the official textual description
of the license (and the other license in the sources).
Since these whitespaces changes do not alter the paragraph structure of
the license, nor create new sentences, they do not change the license.
Based on a -march=x86-64-v4 -mfpmath=sse build, with and without
--disable-multi-arch, running on a Zen 4 CPU. Also used different
-march=x8i6-64-v… settings.
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the exp2m1 and exp10m1 functions (exp2(x)-1 and
exp10(x)-1, like expm1).
As with other such functions, these use type-generic templates that
could be replaced with faster and more accurate type-specific
implementations in future. Test inputs are copied from those for
expm1, plus some additions close to the overflow threshold (copied
from exp2 and exp10) and also some near the underflow threshold.
exp2m1 has the unusual property of having an input (M_MAX_EXP) where
whether the function overflows (under IEEE semantics) depends on the
rounding mode. Although these could reasonably be XFAILed in the
testsuite (as we do in some cases for arguments very close to a
function's overflow threshold when an error of a few ulps in the
implementation can result in the implementation not agreeing with an
ideal one on whether overflow takes place - the testsuite isn't smart
enough to handle this automatically), since these functions aren't
required to be correctly rounding, I made the implementation check for
and handle this case specially.
The Makefile ordering expected by lint-makefiles for the new functions
is a bit peculiar, but I implemented it in this patch so that the test
passes; I don't know why log2 also needed moving in one Makefile
variable setting when it didn't in my previous patches, but the
failure showed a different place was expected for that function as
well.
The powerpc64le IFUNC setup seems not to be as self-contained as one
might hope; it shouldn't be necessary to add IFUNCs for new functions
such as these simply to get them building, but without setting up
IFUNCs for the new functions, there were undefined references to
__GI___expm1f128 (that IFUNC machinery results in no such function
being defined, but doesn't stop include/math.h from doing the
redirection resulting in the exp2m1f128 and exp10m1f128
implementations expecting to call it).
Tested for x86_64 and x86, and with build-many-glibcs.py.
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the log10p1 functions (log10(1+x): like log1p, but for
base-10 logarithms).
This is directly analogous to the log2p1 implementation (except that
whereas log2p1 has a smaller underflow range than log1p, log10p1 has a
larger underflow range). The test inputs are copied from those for
log1p and log2p1, plus a few more inputs in that wider underflow
range.
Tested for x86_64 and x86, and with build-many-glibcs.py.
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the logp1 functions (aliases for log1p functions - the
name is intended to be more consistent with the new log2p1 and
log10p1, where clearly it would have been very confusing to name those
functions log21p and log101p). As aliases rather than new functions,
the content of this patch is somewhat different from those actually
adding new functions.
Tests are shared with log1p, so this patch *does* mechanically update
all affected libm-test-ulps files to expect the same errors for both
functions.
The vector versions of log1p on aarch64 and x86_64 are *not* updated
to have logp1 aliases (and thus there are no corresponding header,
tests, abilist or ulps changes for vector functions either). It would
be reasonable for such vector aliases and corresponding changes to
other files to be made separately. For now, the log1p tests instead
avoid testing logp1 in the vector case (a Makefile change is needed to
avoid problems with grep, used in generating the .c files for vector
function tests, matching more than one ALL_RM_TEST line in a file
testing multiple functions with the same inputs, when it assumes that
the .inc file only has a single such line).
Tested for x86_64 and x86, and with build-many-glibcs.py.
Linux pinacolada 6.6.32-gentoo #1 SMP PREEMPT Sun Jun 9 14:18:17 CEST 2024 x86_64 Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz GenuineIntel GNU/Linux
32bit build for multilib environment
Signed-off-by: Andreas K. Hüttel <dilfridge@gentoo.org>
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the log2p1 functions (log2(1+x): like log1p, but for
base-2 logarithms).
This illustrates the intended structure of implementations of all
these function families: define them initially with a type-generic
template implementation. If someone wishes to add type-specific
implementations, it is likely such implementations can be both faster
and more accurate than the type-generic one and can then override it
for types for which they are implemented (adding benchmarks would be
desirable in such cases to demonstrate that a new implementation is
indeed faster).
The test inputs are copied from those for log1p. Note that these
changes make gen-auto-libm-tests depend on MPFR 4.2 (or later).
The bulk of the changes are fairly generic for any such new function.
(sysdeps/powerpc/nofpu/Makefile only needs changing for those
type-generic templates that use fabs.)
Tested for x86_64 and x86, and with build-many-glibcs.py.
Commit c73c96a4a1 updated memcpy.S and
mempcpy.S, but omitted memmove.S and memset.S. As a result, the static
library built as PIC, whether with or without multiarch support,
contains two definitions for each of the __memmove_chk and __memset_chk
symbols.
/usr/lib/gcc/i686-pc-linux-gnu/14/../../../../i686-pc-linux-gnu/bin/ld: /usr/lib/gcc/i686-pc-linux-gnu/14/../../../../lib/libc.a(memset-ia32.o): in function `__memset_chk':
/var/tmp/portage/sys-libs/glibc-2.39-r3/work/glibc-2.39/string/../sysdeps/i386/i686/memset.S:32: multiple definition of `__memset_chk'; /usr/lib/gcc/i686-pc-linux-gnu/14/../../../../lib/libc.a(memset_chk.o):/var/tmp/portage/sys-libs/glibc-2.39-r3/work/glibc-2.39/debug/../sysdeps/i386/i686/multiarch/memset_chk.c:24: first defined here
After this change, regardless of PIC options, the static library, built
for i686 with multiarch contains implementations of these functions
respectively from debug/memmove_chk.c and debug/memset_chk.c, and
without multiarch contains implementations of these functions
respectively from sysdeps/i386/memmove_chk.S and
sysdeps/i386/memset_chk.S. This ensures that memmove and memset won't
pull in __chk_fail and the routines it calls.
Reported-by: Sam James <sam@gentoo.org>
Tested-by: Sam James <sam@gentoo.org>
Fixes: c73c96a4a1 ("i686: Fix build with --disable-multiarch")
Signed-off-by: Gabi Falk <gabifalk@gmx.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Reviewed-by: Dmitry V. Levin <ldv@altlinux.org>
Before this change, we incorrectly used the SSE2 variant in the
implementation, without checking that the system actually supports
SSE2.
Tested-by: Sam James <sam@gentoo.org>
CET is only support for x86_64, this patch reverts:
- faaee1f07e x86: Support shadow stack pointer in setjmp/longjmp.
- be9ccd27c0 i386: Add _CET_ENDBR to indirect jump targets in
add_n.S/sub_n.S
- c02695d776 x86/CET: Update vfork to prevent child return
- 5d844e1b72 i386: Enable CET support in ucontext functions
- 124bcde683 x86: Add _CET_ENDBR to functions in crti.S
- 562837c002 x86: Add _CET_ENDBR to functions in dl-tlsdesc.S
- f753fa7dea x86: Support IBT and SHSTK in Intel CET [BZ #21598]
- 825b58f3fb i386-mcount.S: Add _CET_ENDBR to _mcount and __fentry__
- 7e119cd582 i386: Use _CET_NOTRACK in i686/memcmp.S
- 177824e232 i386: Use _CET_NOTRACK in memcmp-sse4.S
- 0a899af097 i386: Use _CET_NOTRACK in memcpy-ssse3-rep.S
- 7fb613361c i386: Use _CET_NOTRACK in memcpy-ssse3.S
- 77a8ae0948 i386: Use _CET_NOTRACK in memset-sse2-rep.S
- 00e7b76a8f i386: Use _CET_NOTRACK in memset-sse2.S
- 90d15dc577 i386: Use _CET_NOTRACK in strcat-sse2.S
- f1574581c7 i386: Use _CET_NOTRACK in strcpy-sse2.S
- 4031d7484a i386/sub_n.S: Add a missing _CET_ENDBR to indirect jump
- target
-
Checked on i686-linux-gnu.
The dl-symbol-redir-ifunc.h redirects compiler-generated libcalls to
arch-specific memory implementations to avoid ifunc calls where it is not
yet possible. The memcmp-isa-default-impl.h aims to fix the same issue
by calling the specific memset implementation directly.
Using the memcmp symbol directly allows the compiler to inline the memset
calls (especially because _dl_tunable_set_hwcaps uses constants values),
generating better code.
Checked on x86_64-linux-gnu.
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
Since i686 provides the fortified wrappers for memcpy, mempcpy,
memmove, and memset on the same string implementation, the static
build tries to optimized it by not tying the fortified wrappers
to string routine (to avoid pulling the fortify function if
they are not required).
Checked on i686-linux-gnu building with different option:
default and --disable-multi-arch plus default, --disable-default-pie,
--enable-fortify-source={2,3}, and --enable-fortify-source={2,3}
with --disable-default-pie.
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
Similar to memcpy, mempcpy, and memmove there is no need for an
specific memset_chk-nonshared.S. It can be provided by
memset-ia32.S itself for static library.
Checked on i686-linux-gnu.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
The i386 string routines provide multiple internal definitions
for memcpy, memmove, and mempcpy chk routines:
$ objdump -t libc.a | grep __memcpy_chk
00000000 g F .text 0000000e __memcpy_chk
00000000 g F .text 00000013 __memcpy_chk
$ objdump -t libc.a | grep __mempcpy_chk
00000000 g F .text 0000000e __mempcpy_chk
00000000 g F .text 00000013 __mempcpy_chk
$ objdump -t libc.a | grep __memmove_chk
00000000 g F .text 0000000e __memmove_chk
00000000 g F .text 00000013 __memmove_chk
Although is not an issue for normal static builds, with fortify=3
glibc itself might use the fortify chk functions and thus static
build might fail with multiple definitions. For instance:
x86_64-glibc-linux-gnu-gcc -m32 -march=i686 -o [...]math/test-signgam-uchar-static -nostdlib -nostartfiles -static -static-pie [...]
x86_64-glibc-linux-gnu/bin/ld: [...]/libc.a(mempcpy-ia32.o):
in function `__mempcpy_chk': [...]/glibc-git/string/../sysdeps/i386/i686/mempcpy.S:32: multiple definition of `__mempcpy_chk';
[...]/libc.a(mempcpy_chk-nonshared.o):[...]/debug/../sysdeps/i386/mempcpy_chk.S:28: first defined here
collect2: error: ld returned 1 exit status
make[2]: *** [../Rules:298:
There is no need for mem*-nonshared.S, the __mem*_chk routines
are already provided by the assembly routines.
Checked on i686-linux-gnu with gcc 13 built with fortify=1,2,3 and
without fortify.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Based on feedback by Arsen Arsenović <arsen@gentoo.org>
Linux-6.1.38-gentoo-dist-hardened x86_64 AMD Ryzen 7 3800X 8-Core Processor
-march=x86-64-v2
Signed-off-by: Andreas K. Hüttel <dilfridge@gentoo.org>
If libc_hidden_builtin_{def,proto} isn't properly set for *_chk routines,
there are unwanted PLT entries in libc.so.
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
There's nothing Mach- or Hurd-specific about it; any port that ends
up with rtld pulling in strncpy will need this.
Signed-off-by: Sergey Bugaev <bugaevc@gmail.com>
Message-Id: <20230319151017.531737-15-bugaevc@gmail.com>
Although static linker can optimize it to local call, it follows the
internal scheme to provide hidden proto and definitions.
Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.org>
It also cleanups the multiple inclusion by leaving the ifunc
implementation to undef the weak_alias and libc_hidden_def.
Co-authored-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
Besides the option being gcc specific, this approach is still fragile
and not future proof since we do not know if this will be the only
optimization option gcc will add that transforms loops to memset
(or any libcall).
This patch adds a new header, dl-symbol-redir-ifunc.h, that can b
used to redirect the compiler generated libcalls to port the generic
memset implementation if required.
Checked on x86_64-linux-gnu and aarch64-linux-gnu.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Similar to 6720d36b66 for x86-64.
Clang cannot assemble movzx in the AT&T dialect mode. Change movzx to
movzbl, which follows the AT&T dialect and is used elsewhere in the
file.
gas -mtune= may change NOP generating patterns but -mtune=i686 has no
difference from the default by inspecting .o and .os files.
Note: Clang doesn't support -Wa,-mtune=i686.
commit c22eb807b0
Author: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Thu Jun 16 15:07:12 2022 -0700
x86: Rename generic functions with unique postfix for clarity
Changed the names of the strspn-c, strcspn-c, and strpbrk-c files
in a general refactor. It didn't change the include paths for the
i386 files breaking the i386 build. This commit fixes that.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Add a proper bounds check to __libc_ifunc_impl_list. This makes MAX_IFUNC
redundant and fixes several targets that will write outside the array.
To avoid unnecessary large diffs, pass the maximum in the argument 'i' to
IFUNC_IMPL_ADD - 'max' can be used in new ifunc definitions and existing
ones can be updated if desired.
Passes buildmanyglibc.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
These failures were caught while building glibc master for Fedora
Rawhide which is built with '-mtune=generic -msse2 -mfpmath=sse'
using gcc 11.3 (gcc-11.3.1-2.fc35) on a Cascadelake Intel Xeon
processor.
