raid6/altivec: Add vpermxor implementation for raid6 Q syndrome
PATCH v6 1/2 raid6/altivec: Add vpermxor implementation for raid6 Q syndrome
This patch uses the vpermxor instruction to optimise the raid6 Q syndrome. This instruction was made available with POWER8, ISA version 2.07. It allows for both vperm and vxor instructions to be done in a single instruction. This has been tested for correctness on a ppc64le vm with a basic RAID6 setup containing 5 drives.
The performance benchmarks are from the raid6test in the /lib/raid6/test directory. These results are from an IBM Firestone machine with ppc64le architecture. The benchmark results show a 35% speed increase over the best existing algorithm for powerpc (altivec). The raid6test has also been run on a big-endian ppc64 vm to ensure it also works for big-endian architectures.
Performance benchmarks:
raid6: altivecx4 gen() 18773 MB/s raid6: altivecx8 gen() 19438 MB/s raid6: vpermxor4 gen() 25112 MB/s raid6: vpermxor8 gen() 26279 MB/s
---
v6:
- added vpermxor files to .gitignore
- fixup whitespace
- added vpermxor objs to test/Makefile
v5:
- moved altivec.uc fix into other patch in series
--- include/linux/raid/pq.h | 4 ++ lib/raid6/.gitignore | 1 + lib/raid6/Makefile | 27 ++++++++++++- lib/raid6/algos.c | 4 ++ lib/raid6/test/Makefile | 17 +++++++- lib/raid6/vpermxor.uc | 104 ++++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 154 insertions(+), 3 deletions(-) create mode 100644 lib/raid6/vpermxor.uc
include/linux/raid/pq.h +4 -0
@@ -107,6 +107,10 @@ extern const struct raid6_calls raid6_avx512x2;extern const struct raid6_calls raid6_avx512x4;extern const struct raid6_calls raid6_tilegx8;extern const struct raid6_calls raid6_s390vx8; +extern const struct raid6_calls raid6_vpermxor1; +extern const struct raid6_calls raid6_vpermxor2; +extern const struct raid6_calls raid6_vpermxor4; +extern const struct raid6_calls raid6_vpermxor8;struct raid6_recov_calls {void (*data2)(int ,size_t ,int ,int ,void **);
lib/raid6/.gitignore +1 -0
@@ -4,3 +4,4 @@ int*.c tables.c neon?.c s390vx?.c +vpermxor*.c
lib/raid6/Makefile +26 -1
@@ -4,7 +4,8 @@ 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 +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 raid6_pq-$(CONFIG_TILEGX) += tilegx8.o raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o
@@ -88,6 +89,30 @@ $(obj)/altivec8.c: UNROLL := 8 $(obj)/altivec8.c: $(src)/altivec.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) +CFLAGS_vpermxor1.o += $(altivec_flags) +targets += vpermxor1.c +$(obj)/vpermxor1.c: UNROLL := 1 +$(obj)/vpermxor1.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE + $(call if_changed,unroll) + +CFLAGS_vpermxor2.o += $(altivec_flags) +targets += vpermxor2.c +$(obj)/vpermxor2.c: UNROLL := 2 +$(obj)/vpermxor2.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE + $(call if_changed,unroll) + +CFLAGS_vpermxor4.o += $(altivec_flags) +targets += vpermxor4.c +$(obj)/vpermxor4.c: UNROLL := 4 +$(obj)/vpermxor4.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE + $(call if_changed,unroll) + +CFLAGS_vpermxor8.o += $(altivec_flags) +targets += vpermxor8.c +$(obj)/vpermxor8.c: UNROLL := 8 +$(obj)/vpermxor8.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE + $(call if_changed,unroll) + CFLAGS_neon1.o += $(NEON_FLAGS) targets += neon1.c $(obj)/neon1.c: UNROLL := 1
lib/raid6/algos.c +4 -0
@@ -74,6 +74,10 @@ const struct raid6_calls * const raid6_algos[] = { &raid6_altivec2, &raid6_altivec4, &raid6_altivec8, + &raid6_vpermxor1, + &raid6_vpermxor2, + &raid6_vpermxor4, + &raid6_vpermxor8, #endif #if defined(CONFIG_TILEGX) &raid6_tilegx8,
lib/raid6/test/Makefile +15 -2
@@ -47,7 +47,8 @@ else gcc -c -x c - >&/dev/null && \ rm ./-.o && echo yes) ifeq ($(HAS_ALTIVEC),yes) - OBJS += altivec1.o altivec2.o altivec4.o altivec8.o + OBJS += altivec1.o altivec2.o altivec4.o altivec8.o \ + vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o endif endif ifeq ($(ARCH),tilegx)
@@ -97,6 +98,18 @@ altivec4.c: altivec.uc ../unroll.awk altivec8.c: altivec.uc ../unroll.awk $(AWK) ../unroll.awk -vN=8 < altivec.uc > $@ +vpermxor1.c: vpermxor.uc ../unroll.awk + $(AWK) ../unroll.awk -vN=1 < vpermxor.uc > $@ + +vpermxor2.c: vpermxor.uc ../unroll.awk + $(AWK) ../unroll.awk -vN=2 < vpermxor.uc > $@ + +vpermxor4.c: vpermxor.uc ../unroll.awk + $(AWK) ../unroll.awk -vN=4 < vpermxor.uc > $@ + +vpermxor8.c: vpermxor.uc ../unroll.awk + $(AWK) ../unroll.awk -vN=8 < vpermxor.uc > $@ + int1.c: int.uc ../unroll.awk $(AWK) ../unroll.awk -vN=1 < int.uc > $@
@@ -122,7 +135,7 @@ tables.c: mktables ./mktables > tables.c clean: - rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c neon*.c tables.c raid6test + rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c vpermxor*.c neon*.c tables.c raid6test rm -f tilegx*.c spotless: clean
lib/raid6/vpermxor.uc new file +104 -0
104 lines not on this page · raw message
Signature · 1 line
2.9.3
PATCH v6 2/2 lib/raid6: Build proper raid6test files on powerpc
Previously the raid6 test Makefile did not build the POWER specific files (altivec and vpermxor).
This patch fixes the bug, so that all appropriate files for powerpc are built.
This patch also fixes the missing and mismatched ifdef statements to allow the altivec.uc file to be built correctly.
---
v6:
- remove vpermxor objs from this patch
v5:
- moved altivec.uc fix into this patch
--- lib/raid6/altivec.uc | 3 +++ lib/raid6/test/Makefile | 5 +++-- 2 files changed, 6 insertions(+), 2 deletions(-)
lib/raid6/altivec.uc +3 -0
@@ -24,10 +24,13 @@ #include <linux/raid/pq.h> +#ifdef CONFIG_ALTIVEC + #include <altivec.h> #ifdef __KERNEL__ # include <asm/cputable.h> # include <asm/switch_to.h> +#endif /* __KERNEL__ */ /* * This is the C data type to use. We use a vector of
lib/raid6/test/Makefile +3 -2
@@ -44,9 +44,10 @@ else ifeq ($(HAS_NEON),yes) CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1 else HAS_ALTIVEC := $(shell printf '\#include <altivec.h>\nvector int a;\n' |\ - gcc -c -x c - >&/dev/null && \ - rm ./-.o && echo yes) + gcc -c -x c - >/dev/null && rm ./-.o && echo yes) ifeq ($(HAS_ALTIVEC),yes) + CFLAGS += -I../../../arch/powerpc/include + CFLAGS += -DCONFIG_ALTIVEC OBJS += altivec1.o altivec2.o altivec4.o altivec8.o \ vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o endif
Signature · 1 line
2.9.3
Quoted 29 lines · Matt Brown
This patch uses the vpermxor instruction to optimise the raid6 Q syndrome. This instruction was made available with POWER8, ISA version 2.07. It allows for both vperm and vxor instructions to be done in a single instruction. This has been tested for correctness on a ppc64le vm with a basic RAID6 setup containing 5 drives.
The performance benchmarks are from the raid6test in the
/lib/raid6/testdirectory. These results are from an IBM Firestone machine with ppc64le architecture. The benchmark results show a 35% speed increase over the best existing algorithm for powerpc (altivec). The raid6test has also been run on a big-endian ppc64 vm to ensure it also works for big-endian architectures.Performance benchmarks:
raid6: altivecx4 gen() 18773 MB/s raid6: altivecx8 gen() 19438 MB/s raid6: vpermxor4 gen() 25112 MB/s raid6: vpermxor8 gen() 26279 MB/sSigned-off-by Matt Brown <[email protected]>Reviewed-by Daniel Axtens <[email protected]>---
v6:
- added vpermxor files to .gitignore
- fixup whitespace
- added vpermxor objs to test/Makefile
v5:
- moved altivec.uc fix into other patch in series
Quoted 9 lines
--- include/linux/raid/pq.h | 4 ++ lib/raid6/.gitignore | 1 + lib/raid6/Makefile | 27 ++++++++++++- lib/raid6/algos.c | 4 ++ lib/raid6/test/Makefile | 17 +++++++- lib/raid6/vpermxor.uc | 104 ++++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 154 insertions(+), 3 deletions(-) create mode 100644 lib/raid6/vpermxor.uc
This version at least is not Cc'ed to any of the folks that get_maintainers.pl identifies for these files:
$ ./scripts/get_maintainer.pl -f lib/raid6 [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected]
This seems like mostly a list of random folks who've touched this code, but maybe some of them would have comments?
cheers
Quoted 54 lines · Michael Ellerman
Quoted 29 lines · Matt Brown
This patch uses the vpermxor instruction to optimise the raid6 Q syndrome. This instruction was made available with POWER8, ISA version 2.07. It allows for both vperm and vxor instructions to be done in a single instruction. This has been tested for correctness on a ppc64le vm with a basic RAID6 setup containing 5 drives.
The performance benchmarks are from the raid6test in the
/lib/raid6/testdirectory. These results are from an IBM Firestone machine with ppc64le architecture. The benchmark results show a 35% speed increase over the best existing algorithm for powerpc (altivec). The raid6test has also been run on a big-endian ppc64 vm to ensure it also works for big-endian architectures.Performance benchmarks:
raid6: altivecx4 gen() 18773 MB/s raid6: altivecx8 gen() 19438 MB/s raid6: vpermxor4 gen() 25112 MB/s raid6: vpermxor8 gen() 26279 MB/sSigned-off-by Matt Brown <[email protected]>Reviewed-by Daniel Axtens <[email protected]>---
v6:
- added vpermxor files to .gitignore
- fixup whitespace
- added vpermxor objs to test/Makefile
v5:
- moved altivec.uc fix into other patch in seriesQuoted 9 lines
--- include/linux/raid/pq.h | 4 ++ lib/raid6/.gitignore | 1 + lib/raid6/Makefile | 27 ++++++++++++- lib/raid6/algos.c | 4 ++ lib/raid6/test/Makefile | 17 +++++++- lib/raid6/vpermxor.uc | 104 ++++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 154 insertions(+), 3 deletions(-) create mode 100644 lib/raid6/vpermxor.ucThis version at least is not Cc'ed to any of the folks that get_maintainers.pl identifies for these files:
$ ./scripts/get_maintainer.pl -f lib/raid6 [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected]
Quoted 3 lines
This seems like mostly a list of random folks who've touched this code, but maybe some of them would have comments?
Ah my bad. I've CC'ed them into this email chain. Apologies for not including you guys in the original email. Here is a link to the patchworks patch:
http://patchwork.ozlabs.org/patch/797576/
Thanks,
Matt Brown
Quoted 14 lines · Matt Brown
This patch uses the vpermxor instruction to optimise the raid6 Q syndrome. This instruction was made available with POWER8, ISA version 2.07. It allows for both vperm and vxor instructions to be done in a single instruction. This has been tested for correctness on a ppc64le vm with a basic RAID6 setup containing 5 drives.
The performance benchmarks are from the raid6test in the
/lib/raid6/testdirectory. These results are from an IBM Firestone machine with ppc64le architecture. The benchmark results show a 35% speed increase over the best existing algorithm for powerpc (altivec). The raid6test has also been run on a big-endian ppc64 vm to ensure it also works for big-endian architectures.Performance benchmarks:
Quoted 8 lines
raid6: altivecx4 gen() 18773 MB/s raid6: altivecx8 gen() 19438 MB/s raid6: vpermxor4 gen() 25112 MB/s raid6: vpermxor8 gen() 26279 MB/sSigned-off-by Matt Brown <[email protected]>Reviewed-by Daniel Axtens <[email protected]>
Series applied to powerpc next, thanks.
https://git.kernel.org/powerpc/c/2de95953c4e6ad54c9bee5e6a5518d
cheers
Quoted 14 lines · Matt Brown
This patch uses the vpermxor instruction to optimise the raid6 Q syndrome. This instruction was made available with POWER8, ISA version 2.07. It allows for both vperm and vxor instructions to be done in a single instruction. This has been tested for correctness on a ppc64le vm with a basic RAID6 setup containing 5 drives.
The performance benchmarks are from the raid6test in the
/lib/raid6/testdirectory. These results are from an IBM Firestone machine with ppc64le architecture. The benchmark results show a 35% speed increase over the best existing algorithm for powerpc (altivec). The raid6test has also been run on a big-endian ppc64 vm to ensure it also works for big-endian architectures.Performance benchmarks:
Quoted 8 lines
raid6: altivecx4 gen() 18773 MB/s raid6: altivecx8 gen() 19438 MB/s raid6: vpermxor4 gen() 25112 MB/s raid6: vpermxor8 gen() 26279 MB/sSigned-off-by Matt Brown <[email protected]>Reviewed-by Daniel Axtens <[email protected]>
Series applied to powerpc next, thanks.
https://git.kernel.org/powerpc/c/751ba79cc552c146595cd439b21c4f
cheers