c70f4abef0
Implements an x86_64 assembler driver for the Poly1305 authenticator. This single block variant holds the 130-bit integer in 5 32-bit words, but uses SSE to do two multiplications/additions in parallel. When calling updates with small blocks, the overhead for kernel_fpu_begin/ kernel_fpu_end() negates the perfmance gain. We therefore use the poly1305-generic fallback for small updates. For large messages, throughput increases by ~5-10% compared to poly1305-generic: testing speed of poly1305 (poly1305-generic) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 4080026 opers/sec, 391682496 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 6221094 opers/sec, 597225024 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9609750 opers/sec, 922536057 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1459379 opers/sec, 420301267 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2115179 opers/sec, 609171609 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3729874 opers/sec, 1074203856 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 593000 opers/sec, 626208000 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1081536 opers/sec, 1142102332 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 302077 opers/sec, 628320576 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 554384 opers/sec, 1153120176 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 278715 opers/sec, 1150536345 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 140202 opers/sec, 1153022070 bytes/sec testing speed of poly1305 (poly1305-simd) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 3790063 opers/sec, 363846076 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 5913378 opers/sec, 567684355 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9352574 opers/sec, 897847104 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1362145 opers/sec, 392297990 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2007075 opers/sec, 578037628 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3709811 opers/sec, 1068425798 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 566272 opers/sec, 597984182 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1111657 opers/sec, 1173910108 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 288857 opers/sec, 600823808 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 590746 opers/sec, 1228751888 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 301825 opers/sec, 1245936902 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 153075 opers/sec, 1258896201 bytes/sec Benchmark results from a Core i5-4670T. Signed-off-by: Martin Willi <martin@strongswan.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
99 lines
4.3 KiB
Makefile
99 lines
4.3 KiB
Makefile
#
|
|
# Arch-specific CryptoAPI modules.
|
|
#
|
|
|
|
avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no)
|
|
avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
|
|
$(comma)4)$(comma)%ymm2,yes,no)
|
|
|
|
obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
|
|
obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o
|
|
obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_DES3_EDE_X86_64) += des3_ede-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
|
|
obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha20-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
|
|
obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
|
|
|
|
obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
|
|
obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
|
|
obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
|
|
obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
|
|
obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
|
|
obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o
|
|
obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o
|
|
|
|
# These modules require assembler to support AVX.
|
|
ifeq ($(avx_supported),yes)
|
|
obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += \
|
|
camellia-aesni-avx-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_CAST5_AVX_X86_64) += cast5-avx-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o
|
|
endif
|
|
|
|
# These modules require assembler to support AVX2.
|
|
ifeq ($(avx2_supported),yes)
|
|
obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
|
|
obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
|
|
obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
|
|
endif
|
|
|
|
aes-i586-y := aes-i586-asm_32.o aes_glue.o
|
|
twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
|
|
salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o
|
|
serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
|
|
|
|
aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o
|
|
des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o
|
|
camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
|
|
blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
|
|
twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
|
|
twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
|
|
salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o
|
|
chacha20-x86_64-y := chacha20-ssse3-x86_64.o chacha20_glue.o
|
|
serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
|
|
|
|
ifeq ($(avx_supported),yes)
|
|
camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \
|
|
camellia_aesni_avx_glue.o
|
|
cast5-avx-x86_64-y := cast5-avx-x86_64-asm_64.o cast5_avx_glue.o
|
|
cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o
|
|
twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o \
|
|
twofish_avx_glue.o
|
|
serpent-avx-x86_64-y := serpent-avx-x86_64-asm_64.o \
|
|
serpent_avx_glue.o
|
|
endif
|
|
|
|
ifeq ($(avx2_supported),yes)
|
|
camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o
|
|
chacha20-x86_64-y += chacha20-avx2-x86_64.o
|
|
serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
|
|
endif
|
|
|
|
aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
|
|
aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o
|
|
ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
|
|
sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
|
|
poly1305-x86_64-y := poly1305-sse2-x86_64.o poly1305_glue.o
|
|
ifeq ($(avx2_supported),yes)
|
|
sha1-ssse3-y += sha1_avx2_x86_64_asm.o
|
|
endif
|
|
crc32c-intel-y := crc32c-intel_glue.o
|
|
crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
|
|
crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o
|
|
sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o
|
|
sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o
|
|
crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o
|