Noah Goldstein 475b63702e x86: Double size of ERMS rep_movsb_threshold in dl-cacheinfo.h ... No bug. This patch doubles the rep_movsb_threshold when using ERMS. Based on benchmarks the vector copy loop, especially now that it handles 4k aliasing, is better for these medium ranged. On Skylake with ERMS: Size, Align1, Align2, dst>src,(rep movsb) / (vec copy) 4096, 0, 0, 0, 0.975 4096, 0, 0, 1, 0.953 4096, 12, 0, 0, 0.969 4096, 12, 0, 1, 0.872 4096, 44, 0, 0, 0.979 4096, 44, 0, 1, 0.83 4096, 0, 12, 0, 1.006 4096, 0, 12, 1, 0.989 4096, 0, 44, 0, 0.739 4096, 0, 44, 1, 0.942 4096, 12, 12, 0, 1.009 4096, 12, 12, 1, 0.973 4096, 44, 44, 0, 0.791 4096, 44, 44, 1, 0.961 4096, 2048, 0, 0, 0.978 4096, 2048, 0, 1, 0.951 4096, 2060, 0, 0, 0.986 4096, 2060, 0, 1, 0.963 4096, 2048, 12, 0, 0.971 4096, 2048, 12, 1, 0.941 4096, 2060, 12, 0, 0.977 4096, 2060, 12, 1, 0.949 8192, 0, 0, 0, 0.85 8192, 0, 0, 1, 0.845 8192, 13, 0, 0, 0.937 8192, 13, 0, 1, 0.939 8192, 45, 0, 0, 0.932 8192, 45, 0, 1, 0.927 8192, 0, 13, 0, 0.621 8192, 0, 13, 1, 0.62 8192, 0, 45, 0, 0.53 8192, 0, 45, 1, 0.516 8192, 13, 13, 0, 0.664 8192, 13, 13, 1, 0.659 8192, 45, 45, 0, 0.593 8192, 45, 45, 1, 0.575 8192, 2048, 0, 0, 0.854 8192, 2048, 0, 1, 0.834 8192, 2061, 0, 0, 0.863 8192, 2061, 0, 1, 0.857 8192, 2048, 13, 0, 0.63 8192, 2048, 13, 1, 0.629 8192, 2061, 13, 0, 0.627 8192, 2061, 13, 1, 0.62 Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com> Reviewed-by: H.J. Lu <hjl.tools@gmail.com>		2021-11-06 16:18:08 -05:00
..
aarch64	String: Add hidden defs for __memcmpeq() to enable internal usage	2021-10-26 16:51:29 -05:00
alpha	elf: Fix dynamic-link.h usage on rtld.c	2021-10-14 14:52:07 -03:00
arc	elf: Fix dynamic-link.h usage on rtld.c	2021-10-14 14:52:07 -03:00
arm	arm: Use have-mtls-dialect-gnu2 to check for ARM TLS descriptors support	2021-11-01 16:23:15 -03:00
csky	String: Add hidden defs for __memcmpeq() to enable internal usage	2021-10-26 16:51:29 -05:00
generic	x86_64: Add support for __memcmpeq using sse2, avx2, and evex	2021-10-27 13:03:46 -05:00
gnu	Remove "Contributed by" lines	2021-09-03 22:06:44 +05:30
hppa	elf: Fix dynamic-link.h usage on rtld.c	2021-10-14 14:52:07 -03:00
htl	htl: Reimplement GSCOPE	2021-09-16 01:04:17 +02:00
hurd	Update copyright dates with scripts/update-copyrights	2021-01-02 12:17:34 -08:00
i386	String: Add hidden defs for __memcmpeq() to enable internal usage	2021-10-26 16:51:29 -05:00
ia64	String: Add hidden defs for __memcmpeq() to enable internal usage	2021-10-26 16:51:29 -05:00
ieee754	Fixed inaccuracy of j0f (BZ #28185)	2021-10-05 13:45:37 +02:00
m68k	elf: Fix dynamic-link.h usage on rtld.c	2021-10-14 14:52:07 -03:00
mach	String: Add support for __memcmpeq() ABI on all targets	2021-10-26 16:51:29 -05:00
microblaze	elf: Fix dynamic-link.h usage on rtld.c	2021-10-14 14:52:07 -03:00
mips	ld.so: Initialize bootstrap_map.l_ld_readonly [BZ #28340]	2021-10-19 06:40:38 -07:00
nios2	elf: Fix dynamic-link.h usage on rtld.c	2021-10-14 14:52:07 -03:00
nptl	nptl: Use FUTEX_LOCK_PI2 when available	2021-10-01 08:09:13 -03:00
posix	posix: Remove spawni.c	2021-09-27 12:44:25 -03:00
powerpc	[powerpc] Tighten contraints for asm constant parameters	2021-11-03 09:17:28 -05:00
pthread	elf: Avoid deadlock between pthread_create and ctors [BZ #28357]	2021-10-04 15:07:05 +01:00
riscv	riscv: Build with -mno-relax if linker does not support R_RISCV_ALIGN	2021-11-03 09:25:06 -03:00
s390	String: Add hidden defs for __memcmpeq() to enable internal usage	2021-10-26 16:51:29 -05:00
sh	elf: Fix dynamic-link.h usage on rtld.c	2021-10-14 14:52:07 -03:00
sparc	String: Add hidden defs for __memcmpeq() to enable internal usage	2021-10-26 16:51:29 -05:00
unix	Fix compiler issue with mmap_internal	2021-10-29 09:21:37 -03:00
wordsize-32	Disable symbol hack in libc_nonshared.a	2021-09-27 07:46:25 -07:00
wordsize-64	Remove "Contributed by" lines	2021-09-03 22:06:44 +05:30
x86	x86: Double size of ERMS rep_movsb_threshold in dl-cacheinfo.h	2021-11-06 16:18:08 -05:00
x86_64	x86: Optimize memmove-vec-unaligned-erms.S	2021-11-06 16:18:03 -05:00