phc-discussions - Re: [PHC] winner selection

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

Message-ID: <CAOLP8p5fXcZFmWX2Qq7nKG4z5V0jYCpOx8PoSNr7vrN71aFz3Q@mail.gmail.com>
Date: Fri, 17 Apr 2015 08:55:26 -0700
From: Bill Cox <waywardgeek@...il.com>
To: "discussions@...sword-hashing.net" <discussions@...sword-hashing.net>
Subject: Re: [PHC] winner selection

On Fri, Apr 17, 2015 at 6:48 AM, Thomas Pornin <pornin@...et.org> wrote:

> I totally agree that Makwa is not completely comparable to bcrypt here,
> because with bcrypt it is rather obvious that the CPU wins (though
> people have tried, the GPU is still substantially lagging behind).
> However it is still unclear whether GPU can be _more_ than merely
> comparable to CPU, when counted in dollars. As long as the GPU is not
> more efficient than the CPU, then Makwa still fulfills the required
> property (i.e. defender's hardware is optimal).
>

Makwa's GPU defense is irrelevant to me, since I can simply compute Makwa
hashes with an FPGA, and it's ASIC defense is even worse.

All I would do is pipeline the heck out of the computation, doing something
like 2048 Makwa hashes in parallel.  My FPGA would crush any CPU.

This means that we should _always_ delegate Makwa hashes.  It is possible
to also use these Makwa hashing farms to secure a crypto-coin block chain,
making this a big win in a lot of ways, IMO.

Bill

Content of type "text/html" skipped