ae77cbc1e7
This change adds TILE-Gx SIMD instructions to the software raid (md), modeling the Altivec implementation. This is only for Syndrome generation; there is more that could be done to improve recovery, as in the recent Intel SSE3 recovery implementation. The code unrolls 8 times; this turns out to be the best on tilegx hardware among the set 1, 2, 4, 8 or 16. The code reads one cache-line of data from each disk, stores P and Q then goes to the next cache-line. The test code in sys/linux/lib/raid6/test reports 2008 MB/s data read rate for syndrome generation using 18 disks (16 data and 2 parity). It was 1512 MB/s before this SIMD optimizations. This is running on 1 core with all the data in cache. This is based on the paper The Mathematics of RAID-6. (http://kernel.org/pub/linux/kernel/people/hpa/raid6.pdf). Signed-off-by: Ken Steele <ken@tilera.com> Signed-off-by: Chris Metcalf <cmetcalf@tilera.com> Signed-off-by: NeilBrown <neilb@suse.de>
85 lines
2.4 KiB
Makefile
85 lines
2.4 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_TILEGX) += tilegx8.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 -mabi=altivec
|
|
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)
|
|
|
|
targets += tilegx8.c
|
|
$(obj)/tilegx8.c: UNROLL := 8
|
|
$(obj)/tilegx8.c: $(src)/tilegx.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)
|