mirror of
https://github.com/torvalds/linux.git
synced 2024-11-16 00:52:01 +00:00
c970d42001
aria-avx512 implementation uses AVX512 and GFNI.
It supports 64way parallel processing.
So, byteslicing code is changed to support 64way parallel.
And it exports some aria-avx2 functions such as encrypt() and decrypt().
AVX and AVX2 have 16 registers.
They should use memory to store/load state because of lack of registers.
But AVX512 supports 32 registers.
So, it doesn't require store/load in the s-box layer.
It means that it can reduce overhead of store/load in the s-box layer.
Also code become much simpler.
Benchmark with modprobe tcrypt mode=610 num_mb=8192, i3-12100:
ARIA-AVX512(128bit and 256bit)
testing speed of multibuffer ecb(aria) (ecb-aria-avx512) encryption
tcrypt: 1 operation in 1504 cycles (1024 bytes)
tcrypt: 1 operation in 4595 cycles (4096 bytes)
tcrypt: 1 operation in 1763 cycles (1024 bytes)
tcrypt: 1 operation in 5540 cycles (4096 bytes)
testing speed of multibuffer ecb(aria) (ecb-aria-avx512) decryption
tcrypt: 1 operation in 1502 cycles (1024 bytes)
tcrypt: 1 operation in 4615 cycles (4096 bytes)
tcrypt: 1 operation in 1759 cycles (1024 bytes)
tcrypt: 1 operation in 5554 cycles (4096 bytes)
ARIA-AVX2 with GFNI(128bit and 256bit)
testing speed of multibuffer ecb(aria) (ecb-aria-avx2) encryption
tcrypt: 1 operation in 2003 cycles (1024 bytes)
tcrypt: 1 operation in 5867 cycles (4096 bytes)
tcrypt: 1 operation in 2358 cycles (1024 bytes)
tcrypt: 1 operation in 7295 cycles (4096 bytes)
testing speed of multibuffer ecb(aria) (ecb-aria-avx2) decryption
tcrypt: 1 operation in 2004 cycles (1024 bytes)
tcrypt: 1 operation in 5956 cycles (4096 bytes)
tcrypt: 1 operation in 2409 cycles (1024 bytes)
tcrypt: 1 operation in 7564 cycles (4096 bytes)
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
119 lines
5.2 KiB
Makefile
119 lines
5.2 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0
|
|
#
|
|
# x86 crypto algorithms
|
|
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
|
|
twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
|
|
twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
|
|
twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o
|
|
twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o twofish_avx_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
|
|
serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
|
|
obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
|
|
serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
|
|
obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o
|
|
serpent-avx-x86_64-y := serpent-avx-x86_64-asm_64.o serpent_avx_glue.o
|
|
obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
|
|
serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_DES3_EDE_X86_64) += des3_ede-x86_64.o
|
|
des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
|
|
camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
|
|
obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += camellia-aesni-avx-x86_64.o
|
|
camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o camellia_aesni_avx_glue.o
|
|
obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
|
|
camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
|
|
blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CAST5_AVX_X86_64) += cast5-avx-x86_64.o
|
|
cast5-avx-x86_64-y := cast5-avx-x86_64-asm_64.o cast5_avx_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o
|
|
cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o
|
|
aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o
|
|
chacha-x86_64-y := chacha-avx2-x86_64.o chacha-ssse3-x86_64.o chacha_glue.o
|
|
chacha-x86_64-$(CONFIG_AS_AVX512) += chacha-avx512vl-x86_64.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
|
|
aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
|
|
aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
|
|
sha1-ssse3-y := sha1_avx2_x86_64_asm.o sha1_ssse3_asm.o sha1_ssse3_glue.o
|
|
sha1-ssse3-$(CONFIG_AS_SHA1_NI) += sha1_ni_asm.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
|
|
sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o
|
|
sha256-ssse3-$(CONFIG_AS_SHA256_NI) += sha256_ni_asm.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
|
|
sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += libblake2s-x86_64.o
|
|
libblake2s-x86_64-y := blake2s-core.o blake2s-glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
|
|
ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_POLYVAL_CLMUL_NI) += polyval-clmulni.o
|
|
polyval-clmulni-y := polyval-clmulni_asm.o polyval-clmulni_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
|
|
crc32c-intel-y := crc32c-intel_glue.o
|
|
crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
|
|
crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o
|
|
crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o
|
|
poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o
|
|
targets += poly1305-x86_64-cryptogams.S
|
|
|
|
obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
|
|
nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o
|
|
obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o
|
|
nhpoly1305-avx2-y := nh-avx2-x86_64.o nhpoly1305-avx2-glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SM3_AVX_X86_64) += sm3-avx-x86_64.o
|
|
sm3-avx-x86_64-y := sm3-avx-asm_64.o sm3_avx_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SM4_AESNI_AVX_X86_64) += sm4-aesni-avx-x86_64.o
|
|
sm4-aesni-avx-x86_64-y := sm4-aesni-avx-asm_64.o sm4_aesni_avx_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_SM4_AESNI_AVX2_X86_64) += sm4-aesni-avx2-x86_64.o
|
|
sm4-aesni-avx2-x86_64-y := sm4-aesni-avx2-asm_64.o sm4_aesni_avx2_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64) += aria-aesni-avx-x86_64.o
|
|
aria-aesni-avx-x86_64-y := aria-aesni-avx-asm_64.o aria_aesni_avx_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_ARIA_AESNI_AVX2_X86_64) += aria-aesni-avx2-x86_64.o
|
|
aria-aesni-avx2-x86_64-y := aria-aesni-avx2-asm_64.o aria_aesni_avx2_glue.o
|
|
|
|
obj-$(CONFIG_CRYPTO_ARIA_GFNI_AVX512_X86_64) += aria-gfni-avx512-x86_64.o
|
|
aria-gfni-avx512-x86_64-y := aria-gfni-avx512-asm_64.o aria_gfni_avx512_glue.o
|
|
|
|
quiet_cmd_perlasm = PERLASM $@
|
|
cmd_perlasm = $(PERL) $< > $@
|
|
$(obj)/%.S: $(src)/%.pl FORCE
|
|
$(call if_changed,perlasm)
|
|
|
|
# Disable GCOV in odd or sensitive code
|
|
GCOV_PROFILE_curve25519-x86_64.o := n
|