summaryrefslogtreecommitdiff
path: root/configure.ac
diff options
context:
space:
mode:
authorJussi Kivilinna <jussi.kivilinna@iki.fi>2022-03-10 21:36:34 +0200
committerJussi Kivilinna <jussi.kivilinna@iki.fi>2022-03-10 22:26:16 +0200
commit089223aa3b554e5c9a07d9176470308dab10ac8a (patch)
tree76989cf83a83168f31901222b1291a34f38bd857 /configure.ac
parentd820d27a3bce6365523fbcb6ec607b23dd4ca4e2 (diff)
downloadlibgcrypt-089223aa3b554e5c9a07d9176470308dab10ac8a.tar.gz
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 <jussi.kivilinna@iki.fi>
Diffstat (limited to 'configure.ac')
-rw-r--r--configure.ac1
1 files changed, 1 insertions, 0 deletions
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