crypt-dev - Re: Bcrypt functionalities implementation in hardware

Openwall GNU/*/Linux 3.0 - a small security-enhanced Linux distro for servers

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

Date: Thu, 28 Apr 2011 16:18:10 -0300
From: Yuri Gonzaga <yuriggc@...il.com>
To: crypt-dev@...ts.openwall.com
Subject: Re: Bcrypt functionalities implementation in hardware

 Thank you for your answer.

EksBlowfishSetup(cost, salt, key)
>    state <- InitState()
>    state <- *ExpandKey*(state, salt, key)
>  *  repeat(2^cost)
> **      state <- ExpandKey(state, 0, salt)
> **      state <- ExpandKey(state, 0, key)
> *   return state

I have a question:
If I already have the hardware available to compute ExpandKey(), why don't I
compute in hardware the call outside the loop as well?

On the other hand, InitState() can take advantage of software and
communication and avoiding storage of initial PI value in hardware.

What do you think about it?

Regards,

Yuri Gonzaga

[ CONTENT OF TYPE text/html SKIPPED ]