H.J. Lu 80bb593563 x86-64: Add powf with FMA ...

For workload-spec2017.wrf, on Skylake, it improves performance by:

                           Before            After     Improvement
reciprocal-throughput      35.4713          27.3842       29%
latency                    82.4537          66.3175       24%

	* sysdeps/x86_64/fpu/multiarch/Makefile (libm-sysdep_routines):
	Add e_powf-fma.
	(CFLAGS-e_powf-fma.c): New.
	* sysdeps/x86_64/fpu/multiarch/e_powf-fma.c: New file.
	* sysdeps/x86_64/fpu/multiarch/e_powf.c: Likewise.

2017-10-22 08:08:00 -07:00

..

aarch64

[AARCH64] Rewrite elf_machine_load_address using _DYNAMIC symbol

2017-10-18 17:35:16 +01:00

alpha

Use libm_alias_double for dbl-64 fma.

2017-10-04 20:32:48 +00:00

arm

Update ARM libm-test-ulps.

2017-10-05 22:17:30 +00:00

generic

Add _Float128 function aliases.

2017-10-18 17:37:18 +00:00

gnu

hurd: Fix getifaddrs' and freeifaddrs' symbol exposition

2017-09-28 01:05:18 +02:00

hppa

ld.so: Replace (&bootstrap_map) with BOOTSTRAP_MAP

2017-10-03 01:55:12 -07:00

i386

i386: Replace assembly versions of e_logf with generic e_logf.c

2017-10-22 08:02:58 -07:00

ia64

Add bits/floatn.h defines for more _FloatN / _FloatNx types.

2017-10-20 21:42:51 +00:00

ieee754

Add bits/floatn.h defines for more _FloatN / _FloatNx types.

2017-10-20 21:42:51 +00:00

init_array

Update copyright dates with scripts/update-copyrights.

2017-01-01 00:14:16 +00:00

m68k

m68k: Update elf_machine_load_address for static PIE

2017-10-20 03:36:47 -07:00

mach

Introduce NO_RTLD_HIDDEN, make hurd use it instead of NO_HIDDEN

2017-10-03 01:33:38 +02:00

microblaze

Obsolete pow10 functions.

2017-09-01 21:13:18 +00:00

mips

Add bits/floatn.h defines for more _FloatN / _FloatNx types.

2017-10-20 21:42:51 +00:00

nios2

Enable unwind info in libc-start.c and backtrace.c

2017-09-19 15:07:58 +01:00

nptl

Remove add-ons mechanism.

2017-10-05 15:58:13 +00:00

posix

sysconf: Fix missing definition of UIO_MAXIOV on Linux [BZ #22321]

2017-10-20 04:10:15 +02:00

powerpc

Add bits/floatn.h defines for more _FloatN / _FloatNx types.

2017-10-20 21:42:51 +00:00

pthread

aio: Remove internal_function function attribute

2017-08-31 15:59:06 +02:00

s390

S390: Regenerate ULPs

2017-10-05 12:50:49 +02:00

sh

Enable unwind info in libc-start.c and backtrace.c

2017-09-19 15:07:58 +01:00

sparc

Fix TLS relocations against local symbols on powerpc32, sparc32 and sparc64

2017-10-13 16:14:16 -03:00

tile

Remove ancient __signbit inlines

2017-09-28 19:52:13 +01:00

unix

posix: Fix improper assert in Linux posix_spawn (BZ#22273)

2017-10-20 16:25:59 -02:00

wordsize-32

Build divdi3 only for architecture that required it

2017-04-06 15:14:34 -03:00

wordsize-64

posix: Consolidate Linux glob implementation

2017-09-08 16:34:02 +02:00

x86

Add bits/floatn.h defines for more _FloatN / _FloatNx types.

2017-10-20 21:42:51 +00:00

x86_64

x86-64: Add powf with FMA

2017-10-22 08:08:00 -07:00