From 751ba79cc552c146595cd439b21c4ff8998c3b69 Mon Sep 17 00:00:00 2001 From: Matt Brown Date: Fri, 4 Aug 2017 13:42:32 +1000 Subject: lib/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 Signed-off-by: Matt Brown Reviewed-by: Daniel Axtens [mpe: Add VPERMXOR macro so we can build with old binutils] Signed-off-by: Michael Ellerman --- lib/raid6/test/Makefile | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'lib/raid6/test') diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile index be1010bdc435..ef6d0e00f189 100644 --- a/lib/raid6/test/Makefile +++ b/lib/raid6/test/Makefile @@ -48,7 +48,8 @@ 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) @@ -98,6 +99,18 @@ 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 > $@ @@ -123,7 +136,7 @@ tables.c: mktables ./mktables > tables.c clean: - rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c neon*.c tables.c raid6test + rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c vpermxor*.c neon*.c tables.c raid6test rm -f tilegx*.c spotless: clean -- cgit v1.2.3 From aa9532d4899ff14e50de10d261b761d157cd2ae3 Mon Sep 17 00:00:00 2001 From: Matt Brown Date: Fri, 4 Aug 2017 13:42:33 +1000 Subject: lib/raid6: Build proper raid6test files on powerpc Previously the raid6 test Makefile did not build the POWER specific files (altivec and vpermxor). This patch fixes the bug, so that all appropriate files for powerpc are built. This patch also fixes the missing and mismatched ifdef statements to allow the altivec.uc file to be built correctly. Signed-off-by: Matt Brown Signed-off-by: Michael Ellerman --- lib/raid6/test/Makefile | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'lib/raid6/test') diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile index ef6d0e00f189..5050e270c06b 100644 --- a/lib/raid6/test/Makefile +++ b/lib/raid6/test/Makefile @@ -45,9 +45,10 @@ else ifeq ($(HAS_NEON),yes) CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1 else HAS_ALTIVEC := $(shell printf '\#include \nvector int a;\n' |\ - gcc -c -x c - >&/dev/null && \ - rm ./-.o && echo yes) + gcc -c -x c - >/dev/null && rm ./-.o && echo yes) ifeq ($(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 -- cgit v1.2.3