mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-27 07:20:11 +00:00
88b57b8ed4
Implement x86-64 memmove with unaligned load/store and rep movsb. Support 16-byte, 32-byte and 64-byte vector register sizes. When size <= 8 times of vector register size, there is no check for address overlap bewteen source and destination. Since overhead for overlap check is small when size > 8 times of vector register size, memcpy is an alias of memmove. A single file provides 2 implementations of memmove, one with rep movsb and the other without rep movsb. They share the same codes when size is between 2 times of vector register size and REP_MOVSB_THRESHOLD which is 2KB for 16-byte vector register size and scaled up by large vector register size. Key features: 1. Use overlapping load and store to avoid branch. 2. For size <= 8 times of vector register size, load all sources into registers and store them together. 3. If there is no address overlap bewteen source and destination, copy from both ends with 4 times of vector register size at a time. 4. If address of destination > address of source, backward copy 8 times of vector register size at a time. 5. Otherwise, forward copy 8 times of vector register size at a time. 6. Use rep movsb only for forward copy. Avoid slow backward rep movsb by fallbacking to backward copy 8 times of vector register size at a time. 7. Skip when address of destination == address of source. [BZ #19776] * sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Add memmove-sse2-unaligned-erms, memmove-avx-unaligned-erms and memmove-avx512-unaligned-erms. * sysdeps/x86_64/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Test __memmove_chk_avx512_unaligned_2, __memmove_chk_avx512_unaligned_erms, __memmove_chk_avx_unaligned_2, __memmove_chk_avx_unaligned_erms, __memmove_chk_sse2_unaligned_2, __memmove_chk_sse2_unaligned_erms, __memmove_avx_unaligned_2, __memmove_avx_unaligned_erms, __memmove_avx512_unaligned_2, __memmove_avx512_unaligned_erms, __memmove_erms, __memmove_sse2_unaligned_2, __memmove_sse2_unaligned_erms, __memcpy_chk_avx512_unaligned_2, __memcpy_chk_avx512_unaligned_erms, __memcpy_chk_avx_unaligned_2, __memcpy_chk_avx_unaligned_erms, __memcpy_chk_sse2_unaligned_2, __memcpy_chk_sse2_unaligned_erms, __memcpy_avx_unaligned_2, __memcpy_avx_unaligned_erms, __memcpy_avx512_unaligned_2, __memcpy_avx512_unaligned_erms, __memcpy_sse2_unaligned_2, __memcpy_sse2_unaligned_erms, __memcpy_erms, __mempcpy_chk_avx512_unaligned_2, __mempcpy_chk_avx512_unaligned_erms, __mempcpy_chk_avx_unaligned_2, __mempcpy_chk_avx_unaligned_erms, __mempcpy_chk_sse2_unaligned_2, __mempcpy_chk_sse2_unaligned_erms, __mempcpy_avx512_unaligned_2, __mempcpy_avx512_unaligned_erms, __mempcpy_avx_unaligned_2, __mempcpy_avx_unaligned_erms, __mempcpy_sse2_unaligned_2, __mempcpy_sse2_unaligned_erms and __mempcpy_erms. * sysdeps/x86_64/multiarch/memmove-avx-unaligned-erms.S: New file. * sysdeps/x86_64/multiarch/memmove-avx512-unaligned-erms.S: Likwise. * sysdeps/x86_64/multiarch/memmove-sse2-unaligned-erms.S: Likwise. * sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S: Likwise.
36 lines
1.2 KiB
Makefile
36 lines
1.2 KiB
Makefile
ifeq ($(subdir),csu)
|
|
tests += test-multiarch
|
|
gen-as-const-headers += ifunc-defines.sym
|
|
endif
|
|
|
|
ifeq ($(subdir),string)
|
|
|
|
sysdep_routines += strncat-c stpncpy-c strncpy-c strcmp-ssse3 \
|
|
strcmp-sse2-unaligned strncmp-ssse3 \
|
|
memcmp-sse4 memcpy-ssse3 memcpy-sse2-unaligned \
|
|
memmove-ssse3 \
|
|
memcpy-ssse3-back memmove-avx-unaligned \
|
|
memcpy-avx-unaligned \
|
|
memmove-ssse3-back \
|
|
memmove-avx512-no-vzeroupper strcasecmp_l-ssse3 \
|
|
strncase_l-ssse3 strcat-ssse3 strncat-ssse3\
|
|
strcpy-ssse3 strncpy-ssse3 stpcpy-ssse3 stpncpy-ssse3 \
|
|
strcpy-sse2-unaligned strncpy-sse2-unaligned \
|
|
stpcpy-sse2-unaligned stpncpy-sse2-unaligned \
|
|
strcat-sse2-unaligned strncat-sse2-unaligned \
|
|
strchr-sse2-no-bsf memcmp-ssse3 strstr-sse2-unaligned \
|
|
strcspn-c strpbrk-c strspn-c varshift memset-avx2 \
|
|
memset-avx512-no-vzeroupper \
|
|
memmove-sse2-unaligned-erms \
|
|
memmove-avx-unaligned-erms \
|
|
memmove-avx512-unaligned-erms
|
|
CFLAGS-varshift.c += -msse4
|
|
CFLAGS-strcspn-c.c += -msse4
|
|
CFLAGS-strpbrk-c.c += -msse4
|
|
CFLAGS-strspn-c.c += -msse4
|
|
endif
|
|
|
|
ifeq ($(subdir),wcsmbs)
|
|
sysdep_routines += wmemcmp-sse4 wmemcmp-ssse3 wmemcmp-c wcscpy-ssse3 wcscpy-c
|
|
endif
|