mirror of
git://sourceware.org/git/glibc.git
synced 2024-11-21 01:12:26 +08:00
392b3f0971
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>
|
||
|---|---|---|
| .. | ||
| armv6 | ||
| armv6t2 | ||
| armv7 | ||
| be | ||
| bits | ||
| include/bits | ||
| le | ||
| nofpu | ||
| nptl | ||
| sys | ||
| __longjmp.S | ||
| add_n.S | ||
| addmul_1.S | ||
| aeabi_assert.c | ||
| aeabi_atexit.c | ||
| aeabi_errno_addr.c | ||
| aeabi_lcsts.c | ||
| aeabi_localeconv.c | ||
| aeabi_math.c | ||
| aeabi_mb_cur_max.c | ||
| aeabi_memclr.c | ||
| aeabi_memcpy.c | ||
| aeabi_memmove.c | ||
| aeabi_memset.c | ||
| aeabi_sighandlers.S | ||
| aeabi_unwind_cpp_pr1.c | ||
| arm-features.h | ||
| arm-ifunc.h | ||
| arm-mcount.S | ||
| arm-unwind-resume.S | ||
| atomic-machine.h | ||
| backtrace.c | ||
| bsd-_setjmp.S | ||
| bsd-setjmp.S | ||
| configure | ||
| configure.ac | ||
| crti.S | ||
| crtn.S | ||
| dl-irel.h | ||
| dl-lookupcfg.h | ||
| dl-machine-rel.h | ||
| dl-machine.h | ||
| dl-tls.h | ||
| dl-tlsdesc.h | ||
| dl-tlsdesc.S | ||
| dl-trampoline.S | ||
| elf-initfini.h | ||
| fclrexcpt.c | ||
| fedisblxcpt.c | ||
| feenablxcpt.c | ||
| fegetenv.c | ||
| fegetexcept.c | ||
| fegetmode.c | ||
| fegetround.c | ||
| feholdexcpt.c | ||
| fenv_private.h | ||
| fesetenv.c | ||
| fesetexcept.c | ||
| fesetmode.c | ||
| fesetround.c | ||
| feupdateenv.c | ||
| fgetexcptflg.c | ||
| find_exidx.c | ||
| fix-fp-int-convert-overflow.h | ||
| fpu_control.h | ||
| fraiseexcpt.c | ||
| framestate.c | ||
| fsetexcptflg.c | ||
| ftestexcept.c | ||
| gcc-compat.h | ||
| gccframe.h | ||
| get-rounding-mode.h | ||
| Implies | ||
| jmpbuf-unwind.h | ||
| ldbl-classify-compat.h | ||
| ldsodefs.h | ||
| libc-aeabi_read_tp.S | ||
| libc-tls.c | ||
| libm-test-ulps | ||
| libm-test-ulps-name | ||
| linkmap.h | ||
| machine-gmon.h | ||
| Makefile | ||
| math-tests-trap.h | ||
| math-use-builtins-sqrt.h | ||
| memcpy.S | ||
| memmove.S | ||
| memset.S | ||
| pointer_guard.h | ||
| preconfigure | ||
| preconfigure.ac | ||
| rt-aeabi_unwind_cpp_pr1.c | ||
| rt-arm-unwind-resume.S | ||
| rtld-global-offsets.sym | ||
| setfpucw.c | ||
| setjmp.S | ||
| sfp-machine.h | ||
| sotruss-lib.c | ||
| stackinfo.h | ||
| stap-probe-machine.h | ||
| start.S | ||
| static-stubs.c | ||
| strlen.S | ||
| sub_n.S | ||
| submul_1.S | ||
| sysdep.h | ||
| test-fpucw.c | ||
| tlsdesc.c | ||
| tlsdesc.sym | ||
| tst-armtlsdescextlazy.c | ||
| tst-armtlsdescextlazymod.c | ||
| tst-armtlsdescextnow.c | ||
| tst-armtlsdescextnowmod.c | ||
| tst-armtlsdescloc.c | ||
| tst-armtlsdesclocmod.c | ||
| tst-audit.h | ||
| tst-gnu2-tls2.h | ||
| unwind-arch.h | ||
| unwind-dw2-fde-glibc.c | ||
| unwind-pe.c | ||
| unwind-resume.c | ||
| unwind-resume.h | ||
| unwind.h | ||
| utmp-size.h | ||
| Versions | ||