phc-discussions - Optimized versions for ARM?

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <CAOLP8p4GG+gCctkz6ZPavA=xasn8j2eFNP6cho5ipHo7O32TcQ@mail.gmail.com>
Date: Mon, 27 Apr 2015 19:43:49 -0700
From: Bill Cox <waywardgeek@...il.com>
To: "discussions@...sword-hashing.net" <discussions@...sword-hashing.net>
Subject: Optimized versions for ARM?

Milan is generously benchmarking on PowerPC, but isn't that a mostly dead
architecture?  ARM is the one I want to see.  The PowerPC versions run the
reference code, rather than optimized code, while the reference code was
never meant for benchmarking.  I try to ignore the pretty PowerPC graphs
(which are especially pretty with the new colors!), since I know they
aren't showing me the real picture.

Can we ask the authors to provide optimized ARM versions?  Maybe we don't
need this from Makwa and Parallel, since they don't really have
competitors, but it would be great to have at least Argon2, Lyra2, POMELO,
and Yescrypt.  Battcrypt and Pufferfish would be nice as well.

I hate to ask the authors to do that much work, since they've already
generously donated a crazy amount of time.  However, for the good of the
world, we need to know how these algorithms perform on a smartphone.  We
also need attacker-optimized GPU code.

Frankly, this is a major reason I was not terribly upset that TwoCats did
not make it to the final round :-)

Bill

Content of type "text/html" skipped