phc-discussions - Argon optimized implementation

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: <CALW8-7+voinJFGj6Oben4aigJ6P3vBD-09GTEa5r-OQhVVb-LA@mail.gmail.com>
Date: Fri, 11 Apr 2014 20:34:04 +0200
From: Dmitry Khovratovich <khovratovich@...il.com>
To: "discussions@...sword-hashing.net" <discussions@...sword-hashing.net>, 
	Alex Biryukov - UNI <alex.biryukov@....lu>
Subject: Argon optimized implementation

Hi all,

we have developed an optimized implementation of Argon for the CPUs
equipped with AES-NI instructions:
https://github.com/khovratovich/Argon/tree/master/Argon-Optimized

There are both Linux and Windows versions, which are for the moment
identical, thanks to portable intrinsics.

Running it with parameter "-benchmark" gives performance benchmarks for 2^d
MBytes of memory and different number of threads (from 1 to 16).

On our own machines (Ivy and Sandy Bridge) the optimized Argon runs as
follows:
64 MB: 8 cpb with 4 threads, 16 cpb with 1 thread
1 GB:  9 cpb with 4 threads, 20 cpb with 1 thread

We would appreciate anyone benchmarking Argon on other hardware.

Comments are welcome!

-- 
Best regards,
Alex Biryukov
Dmitry Khovratovich

Content of type "text/html" skipped