diff options
| author | Martin Willi <martin@strongswan.org> | 2018-11-20 17:30:48 +0100 |
|---|---|---|
| committer | Herbert Xu <herbert@gondor.apana.org.au> | 2018-11-29 16:27:04 +0800 |
| commit | cee7a36ecb5bafef8c87fb2c10641e6125044154 (patch) | |
| tree | 7e52243f3733ef595aeaa7df6094a8db30fb3747 /arch/x86/crypto/Makefile | |
| parent | 059c2a4d8e164dccc3078e49e7f286023b019a98 (diff) | |
crypto: x86/chacha20 - Add a 8-block AVX-512VL variant
This variant is similar to the AVX2 version, but benefits from the AVX-512
rotate instructions and the additional registers, so it can operate without
any data on the stack. It uses ymm registers only to avoid the massive core
throttling on Skylake-X platforms. Nontheless does it bring a ~30% speed
improvement compared to the AVX2 variant for random encryption lengths.
The AVX2 version uses "rep movsb" for partial block XORing via the stack.
With AVX-512, the new "vmovdqu8" can do this much more efficiently. The
associated "kmov" instructions to work with dynamic masks is not part of
the AVX-512VL instruction set, hence we depend on AVX-512BW as well. Given
that the major AVX-512VL architectures provide AVX-512BW and this extension
does not affect core clocking, this seems to be no problem at least for
now.
Signed-off-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch/x86/crypto/Makefile')
| -rw-r--r-- | arch/x86/crypto/Makefile | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index a4b0007a54e1..ce4e43642984 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -8,6 +8,7 @@ OBJECT_FILES_NON_STANDARD := y 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) +avx512_supported :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,yes,no) sha1_ni_supported :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,yes,no) sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no) @@ -103,6 +104,10 @@ ifeq ($(avx2_supported),yes) morus1280-avx2-y := morus1280-avx2-asm.o morus1280-avx2-glue.o endif +ifeq ($(avx512_supported),yes) + chacha20-x86_64-y += chacha20-avx512vl-x86_64.o +endif + 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 ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o |