glibc/sysdeps
Wilco Dijkstra 4a733bf375 AArch64: Add optimized Q-register memcpy
Add a new memcpy using 128-bit Q registers - this is faster on modern
cores and reduces codesize.  Similar to the generic memcpy, small cases
include copies up to 32 bytes.  64-128 byte copies are split into two
cases to improve performance of 64-96 byte copies.  Large copies align
the source rather than the destination.

bench-memcpy-random is ~9% faster than memcpy_falkor on Neoverse N1,
so make this memcpy the default on N1 (on Centriq it is 15% faster than
memcpy_falkor).

Passes GLIBC regression tests.

Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2020-07-15 16:55:07 +01:00
..
aarch64 AArch64: Add optimized Q-register memcpy 2020-07-15 16:55:07 +01:00
alpha alpha: Use builtin sqrt{f} 2020-06-22 11:09:49 -03:00
arc ARC: Build Infrastructure 2020-07-10 16:08:45 -07:00
arm Rewrite abi-note.S in C. 2020-07-08 15:02:37 +01:00
csky semaphore: consolidate arch headers into a generic one 2020-05-06 13:07:12 -07:00
generic rtld: Avoid using up static TLS surplus for optimizations [BZ #25051] 2020-07-08 17:32:56 +01:00
gnu signal: Move sys_errlist to a compat symbol 2020-07-07 14:10:58 -03:00
hppa dl-runtime: reloc_{offset,index} now functions arch overide'able 2020-06-05 13:45:46 -07:00
htl htl: Move cleanup handling to non-private libc-lock 2020-06-28 00:13:57 +00:00
hurd hurd: Fix build-many-glibcs.py 2020-07-13 14:25:03 -03:00
i386 x86: Support usable check for all CPU features 2020-07-13 06:05:16 -07:00
ia64 ia64: Use generic exp10f 2020-06-19 12:08:52 -03:00
ieee754 Use C2x return value from getpayload of non-NaN (bug 26073). 2020-07-06 16:18:02 +00:00
m68k m68k: Use sqrt{f} builtin for coldfire 2020-06-22 11:09:50 -03:00
mach Remove --enable-obsolete-nsl configure flag 2020-07-08 17:25:57 +02:00
microblaze semaphore: consolidate arch headers into a generic one 2020-05-06 13:07:12 -07:00
mips mips: Use sqrt{f} builtin 2020-06-22 11:09:49 -03:00
nios2 semaphore: consolidate arch headers into a generic one 2020-05-06 13:07:12 -07:00
nptl nptl: Add pthread_attr_setsigmask_np, pthread_attr_getsigmask_np 2020-06-02 11:59:18 +02:00
posix hurd: Fix __writev_nocancel_nostatus 2020-06-14 17:45:04 +00:00
powerpc powerpc64: Fix calls when r2 is not used [BZ #26173] 2020-07-10 19:41:06 -03:00
pthread htl: Enable cancel*16 an cancel*20 tests 2020-06-29 00:16:33 +00:00
riscv riscv: Use sqrt{f} builtin 2020-06-22 11:09:50 -03:00
s390 S390: Optimize __memset_z196. 2020-06-26 09:45:11 +02:00
sh semaphore: consolidate arch headers into a generic one 2020-05-06 13:07:12 -07:00
sparc sparc: Use sqrt{f} builtin 2020-06-22 11:09:49 -03:00
unix Remove --enable-obsolete-rpc configure flag 2020-07-13 19:36:35 +02:00
wordsize-32 Update copyright dates with scripts/update-copyrights. 2020-01-01 00:14:33 +00:00
wordsize-64 Update copyright dates with scripts/update-copyrights. 2020-01-01 00:14:33 +00:00
x86 x86: Support usable check for all CPU features 2020-07-13 06:05:16 -07:00
x86_64 x86: Support usable check for all CPU features 2020-07-13 06:05:16 -07:00