glibc/sysdeps/x86_64/multiarch/memset-avx2-unaligned-erms.S
H.J. Lu 7ebba91361 x86-64: Add AVX optimized string/memory functions for RTM
Since VZEROUPPER triggers RTM abort while VZEROALL won't, select AVX
optimized string/memory functions with

	xtest
	jz	1f
	vzeroall
	ret
1:
	vzeroupper
	ret

at function exit on processors with usable RTM, but without 256-bit EVEX
instructions to avoid VZEROUPPER inside a transactionally executing RTM
region.
2021-03-29 07:40:17 -07:00

29 lines
601 B
ArmAsm

#if IS_IN (libc)
# define VEC_SIZE 32
# define VEC(i) ymm##i
# define VMOVU vmovdqu
# define VMOVA vmovdqa
# define MEMSET_VDUP_TO_VEC0_AND_SET_RETURN(d, r) \
vmovd d, %xmm0; \
movq r, %rax; \
vpbroadcastb %xmm0, %ymm0
# define WMEMSET_VDUP_TO_VEC0_AND_SET_RETURN(d, r) \
vmovd d, %xmm0; \
movq r, %rax; \
vpbroadcastd %xmm0, %ymm0
# ifndef SECTION
# define SECTION(p) p##.avx
# endif
# ifndef MEMSET_SYMBOL
# define MEMSET_SYMBOL(p,s) p##_avx2_##s
# endif
# ifndef WMEMSET_SYMBOL
# define WMEMSET_SYMBOL(p,s) p##_avx2_##s
# endif
# include "memset-vec-unaligned-erms.S"
#endif