Date: Sat, 04 Aug 2012 23:42:05 +0200 From: magnum <john.magnum@...hmail.com> To: john-dev@...ts.openwall.com Subject: Re: sunmd5 On 2012-08-04 23:21, jfoug wrote: >> From: magnum [mailto:john.magnum@...hmail.com] >> >>> Also, each round, there is copying from a flat buffer, back into >>> a MMX_COEF buffer, for each candidate. I would love to avoid >>> this, but since you have no idea if a candidate will use the 1 >>> block, or the 25 block crypt on any given round, I do not see any >>> way around that issue. >> >> That sounds expensive. Some cleverness here might be the key. > > I agree, but I see no way. > > You have: > > Outs > > In[PARA*COEF] > InBig[PARA*COEF]. Could you not just use one In[PARA*COEF] and always use that? I.e. for 1-limb runs you just use In. Maybe that would not help much though. And on another thought I guess that would mean we blow the first part of the long constant. On the other hand we only need to repair it once per crypt_all(). Oh well, I guess I should look at the code, or at least the format, before coming up with confusing ideas :-P magnum
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.