|
Message-ID: <e194257e81fc6df1f2e7366b1691c640@smtp.hushmail.com> Date: Tue, 21 Aug 2012 20:30:06 +0200 From: magnum <john.magnum@...hmail.com> To: john-dev@...ts.openwall.com Subject: Re: OpenCL optimization trick for md* On 2012-08-21 18:51, Alain Espinosa wrote: > Hi. Share some small OpenCL optimization i will use in next Hash Suite. Thanks! These are already in place in some of the formats, and often ifdef'ed like this (they harm nvidia performance, at least this one): #ifdef cl_nv_pragma_unroll #define NVIDIA #endif ... #ifdef NVIDIA #define F(x,y,z) (z ^ (x & (y ^ z))) #else #define F(x,y,z) bitselect(z, y, x) #endif But someone should check all formats. I tried variants like the below for a quick check: $ grep -H -n "&" opencl/*cl|sed 's/ //g'|grep '.^(.&(.^.)' $ grep -H -n "&" opencl/*cl|sed 's/ //g'|grep '((.&(.|.))|(.&.))' 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.