mirror of
git://sourceware.org/git/glibc.git
synced 2025-02-11 12:50:58 +08:00
This patch replaces i386 assembly versions of e_powf with generic e_powf.c. For workload-spec2017.wrf, on Nehalem, it improves performance by: Before After Improvement reciprocal-throughput 230.855 78.3358 194% latency 231.685 94.1259 146% On Skylake, it improves performance by: Before After Improvement reciprocal-throughput 239.858 47.4713 405% latency 247.57 93.8798 163% On IvyBridge with --disable-multi-arch, it improves performance by: Before After Improvement reciprocal-throughput 269.078 63.3758 324% latency 271.473 102.091 165% * sysdeps/i386/fpu/e_powf.S: Removed. * sysdeps/i386/fpu/e_powf_log2_data.c: Likewise. * sysdeps/i386/fpu/w_powf.c: Likewise. * sysdeps/i386/fpu/libm-test-ulps: Updated for generic e_powf.c. * sysdeps/i386/i686/fpu/multiarch/libm-test-ulps: Likewise. * sysdeps/i386/i686/fpu/multiarch/Makefile (libm-sysdep_routines): Add e_powf-sse2. (CFLAGS-e_powf-sse2.c): New. * sysdeps/i386/i686/fpu/multiarch/e_powf-sse2.c: New file. * sysdeps/i386/i686/fpu/multiarch/e_powf.c: Likewise. |
||
---|---|---|
.. | ||
fpu | ||
i586 | ||
i686 | ||
i786 | ||
nptl | ||
sys | ||
____longjmp_chk.S | ||
__longjmp.S | ||
abort-instr.h | ||
add_n.S | ||
addmul_1.S | ||
asm-syntax.h | ||
atomic-machine.h | ||
backtrace.c | ||
bcopy.S | ||
bsd-_setjmp.S | ||
bsd-setjmp.S | ||
bzero.S | ||
cacheinfo.c | ||
configure | ||
configure.ac | ||
crti.S | ||
crtn.S | ||
dl-irel.h | ||
dl-lookupcfg.h | ||
dl-machine.h | ||
dl-procinfo.c | ||
dl-tls.h | ||
dl-tlsdesc.h | ||
dl-tlsdesc.S | ||
dl-trampoline.S | ||
ffs.c | ||
gccframe.h | ||
gmp-mparam.h | ||
htonl.S | ||
htons.S | ||
i386-mcount.S | ||
Implies | ||
init-arch.h | ||
jmpbuf-offsets.h | ||
jmpbuf-unwind.h | ||
ldbl2mpn.c | ||
ldsodefs.h | ||
link-defines.sym | ||
lshift.S | ||
machine-gmon.h | ||
Makefile | ||
malloc-alignment.h | ||
memchr.S | ||
memcmp.S | ||
memcopy.h | ||
memcpy_chk.S | ||
memcpy.S | ||
memmove_chk.S | ||
memmove.S | ||
mempcpy_chk.S | ||
mempcpy.S | ||
memset_chk.S | ||
memset.S | ||
memusage.h | ||
mp_clz_tab.c | ||
mul_1.S | ||
preconfigure | ||
pthread_spin_trylock.S | ||
rawmemchr.S | ||
rshift.S | ||
setfpucw.c | ||
setjmp.S | ||
stackguard-macros.h | ||
stackinfo.h | ||
start.S | ||
stpcpy.S | ||
stpncpy.S | ||
strcat.S | ||
strchr.S | ||
strchrnul.S | ||
strcspn.S | ||
string-inlines.c | ||
strlen.c | ||
strlen.S | ||
strpbrk.S | ||
strrchr.S | ||
strspn.S | ||
sub_n.S | ||
submul_1.S | ||
symbol-hacks.h | ||
sysdep.h | ||
tls-macros.h | ||
tlsdesc.c | ||
tlsdesc.sym | ||
tst-audit3.c | ||
tst-audit3.h | ||
tst-audit.h | ||
tst-auditmod3a.c | ||
tst-auditmod3b.c | ||
tst-ld-sse-use.sh | ||
tst-stack-align.h | ||
Versions |