cc9f8349cb
This is a NEON acceleration method that can improve performance by approximately 20%. I got the following data from the centos 7.5 on Huawei's HISI1616 chip: [ 93.837726] xor: measuring software checksum speed [ 93.874039] 8regs : 7123.200 MB/sec [ 93.914038] 32regs : 7180.300 MB/sec [ 93.954043] arm64_neon: 9856.000 MB/sec [ 93.954047] xor: using function: arm64_neon (9856.000 MB/sec) I believe this code can bring some optimization for all arm64 platform. thanks for Ard Biesheuvel's suggestions. Signed-off-by: Jackie Liu <liuyun01@kylinos.cn> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
36 lines
1.5 KiB
Makefile
36 lines
1.5 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0
|
|
lib-y := clear_user.o delay.o copy_from_user.o \
|
|
copy_to_user.o copy_in_user.o copy_page.o \
|
|
clear_page.o memchr.o memcpy.o memmove.o memset.o \
|
|
memcmp.o strcmp.o strncmp.o strlen.o strnlen.o \
|
|
strchr.o strrchr.o tishift.o
|
|
|
|
ifeq ($(CONFIG_KERNEL_MODE_NEON), y)
|
|
obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o
|
|
CFLAGS_REMOVE_xor-neon.o += -mgeneral-regs-only
|
|
CFLAGS_xor-neon.o += -ffreestanding
|
|
endif
|
|
|
|
# Tell the compiler to treat all general purpose registers (with the
|
|
# exception of the IP registers, which are already handled by the caller
|
|
# in case of a PLT) as callee-saved, which allows for efficient runtime
|
|
# patching of the bl instruction in the caller with an atomic instruction
|
|
# when supported by the CPU. Result and argument registers are handled
|
|
# correctly, based on the function prototype.
|
|
lib-$(CONFIG_ARM64_LSE_ATOMICS) += atomic_ll_sc.o
|
|
CFLAGS_atomic_ll_sc.o := -ffixed-x1 -ffixed-x2 \
|
|
-ffixed-x3 -ffixed-x4 -ffixed-x5 -ffixed-x6 \
|
|
-ffixed-x7 -fcall-saved-x8 -fcall-saved-x9 \
|
|
-fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12 \
|
|
-fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15 \
|
|
-fcall-saved-x18 -fomit-frame-pointer
|
|
CFLAGS_REMOVE_atomic_ll_sc.o := -pg
|
|
GCOV_PROFILE_atomic_ll_sc.o := n
|
|
KASAN_SANITIZE_atomic_ll_sc.o := n
|
|
KCOV_INSTRUMENT_atomic_ll_sc.o := n
|
|
UBSAN_SANITIZE_atomic_ll_sc.o := n
|
|
|
|
lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
|
|
|
|
obj-$(CONFIG_CRC32) += crc32.o
|