[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20140626031219.GA21021@openwall.com>
Date: Thu, 26 Jun 2014 07:12:19 +0400
From: Solar Designer <solar@...nwall.com>
To: discussions@...sword-hashing.net
Subject: Re: [PHC] TwoCats multiplication chain
On Wed, Jun 25, 2014 at 01:05:04PM +0200, Thomas Pornin wrote:
> Since, for password hashing, we want code which is faster on a PC than
> on a FPGA, we should build up on operations that work best on a PC and
> worst on a FPGA. From this point of view, using CLMUL looks like a
> not-so-good idea.
I fully agree if we s/FPGA/ASIC/g above. For FPGAs, I am not so sure.
In modern FPGAs, there are usually many 18x18 multipliers (and we can
build larger multipliers from those). I don't know if it's possible and
cheap to use them in carry-less mode, or if this would mean spending
other resources. So I wouldn't be surprised if CLMUL actually turns out
to be less FPGA-friendly than traditional MUL.
Perhaps someone with experience of implementing elliptic curves in FPGA
can comment on this.
Alexander
Powered by blists - more mailing lists