Date: Sun, 10 Nov 2013 09:45:51 +0400 From: Solar Designer <solar@...nwall.com> To: john-dev@...ts.openwall.com Subject: Re: ZedBoard: bcrypt On Wed, Nov 06, 2013 at 12:45:28PM +0100, Katja Malvoni wrote: > I was thinking about putting code which does loads and stores to shared > BRAM in arbiter so it's implemented only once and not once per core. But > this would add additional delay cycle to RAM which holds S-boxes. In this > case, total delay would be 3 cycles so 3 instances per core would be > necessary. This may be fine. I don't see why it takes an extra cycle rather than uses up a port, though. > > BTW, I think we have a carry chain across cells, on LUTs outputs. > > Is it being used for Blowfish's 32-bit addition? [...] > I think it is being used. Attached table contains additions and xors for L > and R calculation. And image is screenshot of one of additions placed in > MUXCY cell which is part of CARRY4. Thanks! Alexander
Powered by blists - more mailing lists
Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.