Luna Lamb c0ff447edf Aarch64: Improve codegen in SVE exp and users, and update expf_inline ... Use unpredicted muls, and improve memory access. 7%, 3% and 1% improvement in throughput microbenchmark on Neoverse V1, for exp, exp2 and cosh respectively. Reviewed-by: Wilco Dijkstra <Wilco.Dijkstra@arm.com>		2025-02-13 18:16:54 +00:00
..
aarch64	Aarch64: Improve codegen in SVE exp and users, and update expf_inline	2025-02-13 18:16:54 +00:00
alpha	…
arc	math: Use tanpif from CORE-MATH	2025-02-12 16:31:57 -03:00
arm	math: Use tanpif from CORE-MATH	2025-02-12 16:31:57 -03:00
csky	…
generic	…
gnu	…
hppa	math: Use tanpif from CORE-MATH	2025-02-12 16:31:57 -03:00
htl	htl: stop exporting __pthread_default_barrierattr.	2025-02-10 01:39:17 +01:00
hurd	…
i386	math: Use tanpif from CORE-MATH	2025-02-12 16:31:57 -03:00
ieee754	math: Improve layout of exp/exp10 data	2025-02-13 18:16:54 +00:00
loongarch	math: Use tanpif from CORE-MATH	2025-02-12 16:31:57 -03:00
m68k	…
mach	hurd: Replace char foo[1024] with string_t	2025-02-10 20:10:59 +01:00
microblaze	…
mips	math: Use tanpif from CORE-MATH	2025-02-12 16:31:57 -03:00
nptl	…
or1k	math: Use tanpif from CORE-MATH	2025-02-12 16:31:57 -03:00
posix	…
powerpc	math: Use tanpif from CORE-MATH	2025-02-12 16:31:57 -03:00
pthread	…
riscv	math: Use tanpif from CORE-MATH	2025-02-12 16:31:57 -03:00
s390	math: Use tanpif from CORE-MATH	2025-02-12 16:31:57 -03:00
sh	…
sparc	math: Use tanpif from CORE-MATH	2025-02-12 16:31:57 -03:00
unix	…
wordsize-32	…
wordsize-64	…
x86	…
x86_64	math: Use tanpif from CORE-MATH	2025-02-12 16:31:57 -03:00