linux/arch/x86/crypto/Makefile
Tianjia Zhang 930ab34d90 crypto: x86/sm3 - add AVX assembly implementation
This patch adds AVX assembly accelerated implementation of SM3 secure
hash algorithm. From the benchmark data, compared to pure software
implementation sm3-generic, the performance increase is up to 38%.

The main algorithm implementation based on SM3 AES/BMI2 accelerated
work by libgcrypt at:
https://gnupg.org/software/libgcrypt/index.html

Benchmark on Intel i5-6200U 2.30GHz, performance data of two
implementations, pure software sm3-generic and sm3-avx acceleration.
The data comes from the 326 mode and 422 mode of tcrypt. The abscissas
are different lengths of per update. The data is tabulated and the
unit is Mb/s:

update-size |     16      64     256    1024    2048    4096    8192
------------+-------------------------------------------------------
sm3-generic | 105.97  129.60  182.12  189.62  188.06  193.66  194.88
sm3-avx     | 119.87  163.05  244.44  260.92  257.60  264.87  265.88

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2022-01-28 16:51:11 +11:00

106 lines
4.6 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) += blake2s-x86_64.o
blake2s-x86_64-y := blake2s-shash.o
obj-$(if $(CONFIG_CRYPTO_BLAKE2S_X86),y) += libblake2s-x86_64.o
libblake2s-x86_64-y := blake2s-core.o blake2s-glue.o
obj-$(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-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
crc32c-intel-y := crc32c-intel_glue.o
crc32c-intel-$(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
quiet_cmd_perlasm = PERLASM $@
cmd_perlasm = $(PERL) $< > $@
$(obj)/%.S: $(src)/%.pl FORCE
$(call if_changed,perlasm)