mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-22 20:23:57 +08:00
7d11965ddb
Rebased/reworked a patch contributed by Rob Herring that uses NEON intrinsics to perform the RAID-6 syndrome calculations. It uses the existing unroll.awk code to generate several unrolled versions of which the best performing one is selected at boot time. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Nicolas Pitre <nico@linaro.org> Cc: hpa@linux.intel.com
120 lines
2.9 KiB
Makefile
120 lines
2.9 KiB
Makefile
#
|
|
# This is a simple Makefile to test some of the RAID-6 code
|
|
# from userspace.
|
|
#
|
|
|
|
CC = gcc
|
|
OPTFLAGS = -O2 # Adjust as desired
|
|
CFLAGS = -I.. -I ../../../include -g $(OPTFLAGS)
|
|
LD = ld
|
|
AWK = awk -f
|
|
AR = ar
|
|
RANLIB = ranlib
|
|
OBJS = int1.o int2.o int4.o int8.o int16.o int32.o recov.o algos.o tables.o
|
|
|
|
ARCH := $(shell uname -m 2>/dev/null | sed -e /s/i.86/i386/)
|
|
ifeq ($(ARCH),i386)
|
|
CFLAGS += -DCONFIG_X86_32
|
|
IS_X86 = yes
|
|
endif
|
|
ifeq ($(ARCH),x86_64)
|
|
CFLAGS += -DCONFIG_X86_64
|
|
IS_X86 = yes
|
|
endif
|
|
|
|
ifeq ($(ARCH),arm)
|
|
CFLAGS += -I../../../arch/arm/include -mfpu=neon
|
|
HAS_NEON = yes
|
|
endif
|
|
ifeq ($(ARCH),arm64)
|
|
CFLAGS += -I../../../arch/arm64/include
|
|
HAS_NEON = yes
|
|
endif
|
|
|
|
ifeq ($(IS_X86),yes)
|
|
OBJS += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o
|
|
CFLAGS += $(shell echo "vpbroadcastb %xmm0, %ymm1" | \
|
|
gcc -c -x assembler - >&/dev/null && \
|
|
rm ./-.o && echo -DCONFIG_AS_AVX2=1)
|
|
else ifeq ($(HAS_NEON),yes)
|
|
OBJS += neon.o neon1.o neon2.o neon4.o neon8.o
|
|
CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1
|
|
else
|
|
HAS_ALTIVEC := $(shell echo -e '\#include <altivec.h>\nvector int a;' |\
|
|
gcc -c -x c - >&/dev/null && \
|
|
rm ./-.o && echo yes)
|
|
ifeq ($(HAS_ALTIVEC),yes)
|
|
OBJS += altivec1.o altivec2.o altivec4.o altivec8.o
|
|
endif
|
|
endif
|
|
|
|
.c.o:
|
|
$(CC) $(CFLAGS) -c -o $@ $<
|
|
|
|
%.c: ../%.c
|
|
cp -f $< $@
|
|
|
|
%.uc: ../%.uc
|
|
cp -f $< $@
|
|
|
|
all: raid6.a raid6test
|
|
|
|
raid6.a: $(OBJS)
|
|
rm -f $@
|
|
$(AR) cq $@ $^
|
|
$(RANLIB) $@
|
|
|
|
raid6test: test.c raid6.a
|
|
$(CC) $(CFLAGS) -o raid6test $^
|
|
|
|
neon1.c: neon.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=1 < neon.uc > $@
|
|
|
|
neon2.c: neon.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=2 < neon.uc > $@
|
|
|
|
neon4.c: neon.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=4 < neon.uc > $@
|
|
|
|
neon8.c: neon.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=8 < neon.uc > $@
|
|
|
|
altivec1.c: altivec.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=1 < altivec.uc > $@
|
|
|
|
altivec2.c: altivec.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=2 < altivec.uc > $@
|
|
|
|
altivec4.c: altivec.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=4 < altivec.uc > $@
|
|
|
|
altivec8.c: altivec.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=8 < altivec.uc > $@
|
|
|
|
int1.c: int.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=1 < int.uc > $@
|
|
|
|
int2.c: int.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=2 < int.uc > $@
|
|
|
|
int4.c: int.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=4 < int.uc > $@
|
|
|
|
int8.c: int.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=8 < int.uc > $@
|
|
|
|
int16.c: int.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=16 < int.uc > $@
|
|
|
|
int32.c: int.uc ../unroll.awk
|
|
$(AWK) ../unroll.awk -vN=32 < int.uc > $@
|
|
|
|
tables.c: mktables
|
|
./mktables > tables.c
|
|
|
|
clean:
|
|
rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c neon*.c tables.c raid6test
|
|
|
|
spotless: clean
|
|
rm -f *~
|