From 089223aa3b554e5c9a07d9176470308dab10ac8a Mon Sep 17 00:00:00 2001 From: Jussi Kivilinna Date: Thu, 10 Mar 2022 21:36:34 +0200 Subject: SHA512: Add AVX512 implementation * LICENSES: Add 'cipher/sha512-avx512-amd64.S'. * cipher/Makefile.am: Add 'sha512-avx512-amd64.S'. * cipher/sha512-avx512-amd64.S: New. * cipher/sha512.c (USE_AVX512): New. (do_sha512_transform_amd64_ssse3, do_sha512_transform_amd64_avx) (do_sha512_transform_amd64_avx2): Add ASM_EXTRA_STACK to return value only if assembly routine returned non-zero value. [USE_AVX512] (_gcry_sha512_transform_amd64_avx512) (do_sha512_transform_amd64_avx512): New. (sha512_init_common) [USE_AVX512]: Use AVX512 implementation if HW feature supported. --- Benchmark on Intel Core i3-1115G4 (tigerlake): Before: | nanosecs/byte mebibytes/sec cycles/byte auto Mhz SHA512 | 1.51 ns/B 631.6 MiB/s 6.17 c/B 4089 After (~29% faster): | nanosecs/byte mebibytes/sec cycles/byte auto Mhz SHA512 | 1.16 ns/B 819.0 MiB/s 4.76 c/B 4090 GnuPG-bug-id: T4460 Signed-off-by: Jussi Kivilinna --- configure.ac | 1 + 1 file changed, 1 insertion(+) (limited to 'configure.ac') diff --git a/configure.ac b/configure.ac index 27d72141..cf255bf3 100644 --- a/configure.ac +++ b/configure.ac @@ -2942,6 +2942,7 @@ if test "$found" = "1" ; then GCRYPT_ASM_DIGESTS="$GCRYPT_ASM_DIGESTS sha512-ssse3-amd64.lo" GCRYPT_ASM_DIGESTS="$GCRYPT_ASM_DIGESTS sha512-avx-amd64.lo" GCRYPT_ASM_DIGESTS="$GCRYPT_ASM_DIGESTS sha512-avx2-bmi2-amd64.lo" + GCRYPT_ASM_DIGESTS="$GCRYPT_ASM_DIGESTS sha512-avx512-amd64.lo" ;; i?86-*-*) # Build with the assembly implementation -- cgit v1.2.1