forked from Minki/linux
6dd7a82cc5
Use the vector polynomial multiply-sum instructions in POWER8 to
speed up crc32c.
This is just over 41x faster than the slice-by-8 method that it
replaces. Measurements on a 4.1 GHz POWER8 show it sustaining
52 GiB/sec.
A simple btrfs write performance test:
dd if=/dev/zero of=/mnt/tmpfile bs=1M count=4096
sync
is over 3.7x faster.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
20 lines
703 B
Makefile
20 lines
703 B
Makefile
#
|
|
# powerpc/crypto/Makefile
|
|
#
|
|
# Arch-specific CryptoAPI modules.
|
|
#
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_PPC_SPE) += aes-ppc-spe.o
|
|
obj-$(CONFIG_CRYPTO_MD5_PPC) += md5-ppc.o
|
|
obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o
|
|
obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o
|
|
obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
|
|
obj-$(CONFIG_CRYPT_CRC32C_VPMSUM) += crc32c-vpmsum.o
|
|
|
|
aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o
|
|
md5-ppc-y := md5-asm.o md5-glue.o
|
|
sha1-powerpc-y := sha1-powerpc-asm.o sha1.o
|
|
sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
|
|
sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
|
|
crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
|