Date: Mon, 01 Jun 2015 14:22:40 +0200 From: magnum <john.magnum@...hmail.com> To: john-dev@...ts.openwall.com Subject: Re: Interleaving of intrinsics On 2015-06-01 13:37, magnum wrote: > Here's a somewhat unrelated note: While MD4/5 just use the w pad, > SHA1 and SHA2 use w internally. We handle this differently in all > three: SHA1 keeps a sliding window of tmpR and some EXPAND macros > (Jim did this, for a 10% boost of Simon's original code that had w). > SHA256 seems to manage with just tmp1 and the R() macro. This was incorrect, I think SHA256 effectively does it similar to SHA1. > And SHA512 actually use an expensive w. This should be looked > into. I'll have a peak at Alain's code again. Maybe SHA1 and SHA512 > could do it more like SHA256 does it? Looking at reference code, I'm not sure why we use w nor a smaller rolling temp for any of them. Is this for not re-doing rotates or something? 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.