[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CABob6ir85mzYC-pe_Cyx3j3=ePWrKBPF68+_GcWVZy6NLCsD6g@mail.gmail.com>
Date: Sat, 11 Aug 2012 02:43:39 +0200
From: Lukas Odzioba <lukas.odzioba@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: Current -fixes GPU formats vs TS
2012/8/11 Solar Designer <solar@...nwall.com>:
> Here's a guess: maybe the sequential writes to that memory - all at once -
> prevent cache line loads from it later, when we make partial writes first
> (different portions by different threads).
Sounds reasonable.
I tried to run computeprof, but this way I wasn't able to reproduce
speedup, and max-min of 18 tests was grater (10k c/s)
Lukas
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.
