phc-discussions - Argon2d vs Argon2ds GPU benchmarks?

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]

Date: Wed, 16 Sep 2015 09:57:14 +0000
From: Jean-Philippe Aumasson <jeanphilippe.aumasson@...il.com>
To: "discussions@...sword-hashing.net" <discussions@...sword-hashing.net>
Subject: Argon2d vs Argon2ds GPU benchmarks?

The latest version of the Argon2 specs (1.2.1) proposes Argon2ds, a tweaked
version of Argon2d:
"
3. The S-box-with-multiply transformation (almost identical to Solar
Designer's MaxForm) is added to improve the GPU resistance in a new mode
Argon2ds. It is optional as well, and probably subject to change after we
test it on GPU.
"
http://thread.gmane.org/gmane.comp.security.phc/3310

Argon2ds uses the GenerateSbox function defined at
https://github.com/khovratovich/Argon2/blob/3d7566f4cdb64a8953b5aac71a3d7074ae27ae5f/Source/Core/argon2-ref-core.cpp#L153

Is anyone planning/willing to benchmark Argon2d vs Argon2ds? Would help
understand the actual benefits of this tweak.

Content of type "text/html" skipped