mirror of
https://github.com/torvalds/linux.git
synced 2026-03-08 03:44:45 +01:00
8f3f06dfd6
The algorithms work on 64 bytes at a time, which is the L1 cache line size of all current and future LoongArch cores (that we care about), as confirmed by Huacai. The code is based on the generic int.uc algorithm, unrolled 4 times for LSX and 2 times for LASX. Further unrolling does not meaningfully improve the performance according to experiments. Performance numbers measured during system boot on a 3A5000 @ 2.5GHz: > raid6: lasx gen() 12726 MB/s > raid6: lsx gen() 10001 MB/s > raid6: int64x8 gen() 2876 MB/s > raid6: int64x4 gen() 3867 MB/s > raid6: int64x2 gen() 2531 MB/s > raid6: int64x1 gen() 1945 MB/s Comparison of xor() speeds (from different boots but meaningful anyway): > lasx: 11226 MB/s > lsx: 6395 MB/s > int64x4: 2147 MB/s Performance as measured by raid6test: > raid6: lasx gen() 25109 MB/s > raid6: lsx gen() 13233 MB/s > raid6: int64x8 gen() 4164 MB/s > raid6: int64x4 gen() 6005 MB/s > raid6: int64x2 gen() 5781 MB/s > raid6: int64x1 gen() 4119 MB/s > raid6: using algorithm lasx gen() 25109 MB/s > raid6: .... xor() 14439 MB/s, rmw enabled Acked-by: Song Liu <song@kernel.org> Signed-off-by: WANG Xuerui <git@xen0n.name> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
95 lines
3.4 KiB
Makefile
95 lines
3.4 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0
|
|
obj-$(CONFIG_RAID6_PQ) += raid6_pq.o
|
|
|
|
raid6_pq-y += algos.o recov.o tables.o int1.o int2.o int4.o \
|
|
int8.o int16.o int32.o
|
|
|
|
raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o avx512.o recov_avx512.o
|
|
raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o \
|
|
vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o
|
|
raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
|
|
raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o
|
|
raid6_pq-$(CONFIG_LOONGARCH) += loongarch_simd.o
|
|
|
|
hostprogs += mktables
|
|
|
|
ifeq ($(CONFIG_ALTIVEC),y)
|
|
altivec_flags := -maltivec $(call cc-option,-mabi=altivec)
|
|
# Enable <altivec.h>
|
|
altivec_flags += -isystem $(shell $(CC) -print-file-name=include)
|
|
|
|
ifdef CONFIG_CC_IS_CLANG
|
|
# clang ppc port does not yet support -maltivec when -msoft-float is
|
|
# enabled. A future release of clang will resolve this
|
|
# https://bugs.llvm.org/show_bug.cgi?id=31177
|
|
CFLAGS_REMOVE_altivec1.o += -msoft-float
|
|
CFLAGS_REMOVE_altivec2.o += -msoft-float
|
|
CFLAGS_REMOVE_altivec4.o += -msoft-float
|
|
CFLAGS_REMOVE_altivec8.o += -msoft-float
|
|
CFLAGS_REMOVE_vpermxor1.o += -msoft-float
|
|
CFLAGS_REMOVE_vpermxor2.o += -msoft-float
|
|
CFLAGS_REMOVE_vpermxor4.o += -msoft-float
|
|
CFLAGS_REMOVE_vpermxor8.o += -msoft-float
|
|
endif
|
|
endif
|
|
|
|
# The GCC option -ffreestanding is required in order to compile code containing
|
|
# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel)
|
|
ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
|
|
NEON_FLAGS := -ffreestanding
|
|
# Enable <arm_neon.h>
|
|
NEON_FLAGS += -isystem $(shell $(CC) -print-file-name=include)
|
|
ifeq ($(ARCH),arm)
|
|
NEON_FLAGS += -march=armv7-a -mfloat-abi=softfp -mfpu=neon
|
|
endif
|
|
CFLAGS_recov_neon_inner.o += $(NEON_FLAGS)
|
|
ifeq ($(ARCH),arm64)
|
|
CFLAGS_REMOVE_recov_neon_inner.o += -mgeneral-regs-only
|
|
CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only
|
|
CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only
|
|
CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only
|
|
CFLAGS_REMOVE_neon8.o += -mgeneral-regs-only
|
|
endif
|
|
endif
|
|
|
|
quiet_cmd_unroll = UNROLL $@
|
|
cmd_unroll = $(AWK) -v N=$* -f $(srctree)/$(src)/unroll.awk < $< > $@
|
|
|
|
targets += int1.c int2.c int4.c int8.c int16.c int32.c
|
|
$(obj)/int%.c: $(src)/int.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
CFLAGS_altivec1.o += $(altivec_flags)
|
|
CFLAGS_altivec2.o += $(altivec_flags)
|
|
CFLAGS_altivec4.o += $(altivec_flags)
|
|
CFLAGS_altivec8.o += $(altivec_flags)
|
|
targets += altivec1.c altivec2.c altivec4.c altivec8.c
|
|
$(obj)/altivec%.c: $(src)/altivec.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
CFLAGS_vpermxor1.o += $(altivec_flags)
|
|
CFLAGS_vpermxor2.o += $(altivec_flags)
|
|
CFLAGS_vpermxor4.o += $(altivec_flags)
|
|
CFLAGS_vpermxor8.o += $(altivec_flags)
|
|
targets += vpermxor1.c vpermxor2.c vpermxor4.c vpermxor8.c
|
|
$(obj)/vpermxor%.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
CFLAGS_neon1.o += $(NEON_FLAGS)
|
|
CFLAGS_neon2.o += $(NEON_FLAGS)
|
|
CFLAGS_neon4.o += $(NEON_FLAGS)
|
|
CFLAGS_neon8.o += $(NEON_FLAGS)
|
|
targets += neon1.c neon2.c neon4.c neon8.c
|
|
$(obj)/neon%.c: $(src)/neon.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
targets += s390vx8.c
|
|
$(obj)/s390vx%.c: $(src)/s390vx.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
quiet_cmd_mktable = TABLE $@
|
|
cmd_mktable = $(obj)/mktables > $@
|
|
|
|
targets += tables.c
|
|
$(obj)/tables.c: $(obj)/mktables FORCE
|
|
$(call if_changed,mktable)
|