[PATCH 1/2] Add generic SHA3 implementation

Werner Koch wk at gnupg.org
Tue Aug 11 19:38:44 CEST 2015


On Sun,  9 Aug 2015 17:51, jussi.kivilinna at iki.fi said:

> Patch adds generic implementation for SHA3. Currently missing with this

Thanks.  With AVX and SSSE3 disabled SHA3-256 is actually faster than
SHA256:
                |  nanosecs/byte   mebibytes/sec   cycles/byte
 SHA1           |      3.27 ns/B     291.2 MiB/s      7.53 c/B
 SHA256         |      7.45 ns/B     128.0 MiB/s     17.14 c/B
 SHA512         |      4.68 ns/B     203.9 MiB/s     10.76 c/B
 SHA3-256       |      5.70 ns/B     167.3 MiB/s     13.11 c/B
 SHA3-512       |     10.66 ns/B     89.46 MiB/s     24.52 c/B

The only question is whether tehre is a need for SHA-3 at all.  The
SHAKE functions will probably be used by newer protocols but I doubt that
there will be rush for SHA3.  Having it in Libgcryt is Good Thing, though.


Shalom-Salam,

   Werner

-- 
Die Gedanken sind frei.  Ausnahmen regelt ein Bundesgesetz.




More information about the Gcrypt-devel mailing list