Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date: Thu, 7 Mar 2013 00:19:47 +0100
From: magnum <john.magnum@...hmail.com>
To: john-dev@...ts.openwall.com
Subject: Re: NetNTLMv1 and MSCHAPv2

On 6 Mar, 2013, at 19:58 , magnum <john.magnum@...hmail.com> wrote:
> By the way, are we not very vulnerable to false sharing now, with this tiny crypt_key array?

Maybe I can expect OpenMP to do the right things as long as I use a high enough keys_per_crypt? Let's say I have 4 cores running but the work load per core is 32 keys. Assuming 64 byte cache line size, if core one gets indexes 0-31 and core two 32-63 and so on, they would not fight over cache lines at all. Then again, we should ideally align the array to MEM_ALIGN_CACHE.

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.