mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-28 07:04:00 +08:00
474fd6e80f
Using vector registers is slightly faster: raid6: vx128x8 gen() 19705 MB/s raid6: vx128x8 xor() 11886 MB/s raid6: using algorithm vx128x8 gen() 19705 MB/s raid6: .... xor() 11886 MB/s, rmw enabled vs the software algorithms: raid6: int64x1 gen() 3018 MB/s raid6: int64x1 xor() 1429 MB/s raid6: int64x2 gen() 4661 MB/s raid6: int64x2 xor() 3143 MB/s raid6: int64x4 gen() 5392 MB/s raid6: int64x4 xor() 3509 MB/s raid6: int64x8 gen() 4441 MB/s raid6: int64x8 xor() 3207 MB/s raid6: using algorithm int64x4 gen() 5392 MB/s raid6: .... xor() 3509 MB/s, rmw enabled Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
131 lines
3.8 KiB
Makefile
131 lines
3.8 KiB
Makefile
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
|
|
raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o
|
|
raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o
|
|
raid6_pq-$(CONFIG_TILEGX) += tilegx8.o
|
|
raid6_pq-$(CONFIG_S390) += s390vx8.o
|
|
|
|
hostprogs-y += mktables
|
|
|
|
quiet_cmd_unroll = UNROLL $@
|
|
cmd_unroll = $(AWK) -f$(srctree)/$(src)/unroll.awk -vN=$(UNROLL) \
|
|
< $< > $@ || ( rm -f $@ && exit 1 )
|
|
|
|
ifeq ($(CONFIG_ALTIVEC),y)
|
|
altivec_flags := -maltivec $(call cc-option,-mabi=altivec)
|
|
endif
|
|
|
|
# The GCC option -ffreestanding is required in order to compile code containing
|
|
# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel)
|
|
ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
|
|
NEON_FLAGS := -ffreestanding
|
|
ifeq ($(ARCH),arm)
|
|
NEON_FLAGS += -mfloat-abi=softfp -mfpu=neon
|
|
endif
|
|
ifeq ($(ARCH),arm64)
|
|
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
|
|
|
|
targets += int1.c
|
|
$(obj)/int1.c: UNROLL := 1
|
|
$(obj)/int1.c: $(src)/int.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
targets += int2.c
|
|
$(obj)/int2.c: UNROLL := 2
|
|
$(obj)/int2.c: $(src)/int.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
targets += int4.c
|
|
$(obj)/int4.c: UNROLL := 4
|
|
$(obj)/int4.c: $(src)/int.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
targets += int8.c
|
|
$(obj)/int8.c: UNROLL := 8
|
|
$(obj)/int8.c: $(src)/int.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
targets += int16.c
|
|
$(obj)/int16.c: UNROLL := 16
|
|
$(obj)/int16.c: $(src)/int.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
targets += int32.c
|
|
$(obj)/int32.c: UNROLL := 32
|
|
$(obj)/int32.c: $(src)/int.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
CFLAGS_altivec1.o += $(altivec_flags)
|
|
targets += altivec1.c
|
|
$(obj)/altivec1.c: UNROLL := 1
|
|
$(obj)/altivec1.c: $(src)/altivec.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
CFLAGS_altivec2.o += $(altivec_flags)
|
|
targets += altivec2.c
|
|
$(obj)/altivec2.c: UNROLL := 2
|
|
$(obj)/altivec2.c: $(src)/altivec.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
CFLAGS_altivec4.o += $(altivec_flags)
|
|
targets += altivec4.c
|
|
$(obj)/altivec4.c: UNROLL := 4
|
|
$(obj)/altivec4.c: $(src)/altivec.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
CFLAGS_altivec8.o += $(altivec_flags)
|
|
targets += altivec8.c
|
|
$(obj)/altivec8.c: UNROLL := 8
|
|
$(obj)/altivec8.c: $(src)/altivec.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
CFLAGS_neon1.o += $(NEON_FLAGS)
|
|
targets += neon1.c
|
|
$(obj)/neon1.c: UNROLL := 1
|
|
$(obj)/neon1.c: $(src)/neon.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
CFLAGS_neon2.o += $(NEON_FLAGS)
|
|
targets += neon2.c
|
|
$(obj)/neon2.c: UNROLL := 2
|
|
$(obj)/neon2.c: $(src)/neon.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
CFLAGS_neon4.o += $(NEON_FLAGS)
|
|
targets += neon4.c
|
|
$(obj)/neon4.c: UNROLL := 4
|
|
$(obj)/neon4.c: $(src)/neon.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
CFLAGS_neon8.o += $(NEON_FLAGS)
|
|
targets += neon8.c
|
|
$(obj)/neon8.c: UNROLL := 8
|
|
$(obj)/neon8.c: $(src)/neon.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
targets += tilegx8.c
|
|
$(obj)/tilegx8.c: UNROLL := 8
|
|
$(obj)/tilegx8.c: $(src)/tilegx.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
targets += s390vx8.c
|
|
$(obj)/s390vx8.c: UNROLL := 8
|
|
$(obj)/s390vx8.c: $(src)/s390vx.uc $(src)/unroll.awk FORCE
|
|
$(call if_changed,unroll)
|
|
|
|
quiet_cmd_mktable = TABLE $@
|
|
cmd_mktable = $(obj)/mktables > $@ || ( rm -f $@ && exit 1 )
|
|
|
|
targets += tables.c
|
|
$(obj)/tables.c: $(obj)/mktables FORCE
|
|
$(call if_changed,mktable)
|