It optimizes the RSA-2k/3k/4k via the AVXIFMA ISA on Sierra Forest.
The performance improvements of 1.8x-2.2x are observed in the speed
tests of sign and decryption operations on this CPU.
Reviewed-by: Neil Horman <nhorman@openssl.org>
Reviewed-by: Saša Nedvědický <sashan@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/25751)
Inspired by BoringSSL fix by David Benjamin.
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Paul Dale <pauli@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/18510)
The symbols renamed are:
RSAZ_amm52x20_x1_256
RSAZ_amm52x20_x2_256
rsaz_avx512ifma_eligible
RSAZ_mod_exp_avx512_x2
Additionally, RSAZ_exp52x20_x2_256 was made static
Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
(Merged from https://github.com/openssl/openssl/pull/15445)
with AVX512_IFMA + AVX512_VL instructions, primarily for RSA CRT private key
operations. It uses 256-bit registers to avoid CPU frequency scaling issues.
The performance speedup for RSA2k signature on ICL is ~2x.
Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/13750)
Make the include guards consistent by renaming them systematically according
to the naming conventions below
For the public header files (in the 'include/openssl' directory), the guard
names try to match the path specified in the include directives, with
all letters converted to upper case and '/' and '.' replaced by '_'. For the
private header files files, an extra 'OSSL_' is added as prefix.
Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/9333)
A small rearrangement so the inclusion of rsaz_exp.h would be
unconditional, but what that header defines becomes conditional.
This solves the weirdness where rsaz_exp.h gets in and out of the
dependency list for bn_exp.c, depending on the present architecture.
Reviewed-by: Rich Salz <rsalz@openssl.org>