Date: Tue, 10 Jul 2012 09:23:11 +0530 From: Sayantan Datta <std2048@...il.com> To: john-dev@...ts.openwall.com Subject: Re: bf_kernel.cl Hi Alexander, On Tue, Jul 10, 2012 at 8:16 AM, Solar Designer <solar@...nwall.com> wrote: > Shouldn't we expect more like a 50% improvement, based on the speeds for > the implementation using global memory that you had before? Compared to > your LDS-using implementation, we're adding uses of computing and memory > resources that would otherwise be completely idle. > We are still not capable of utilizing 100% of the hardware. With the implemantation I mentioned we are using 50% of the total resources available but I have some control on how the work groups get shecduled. The resource utilization can be pushed to an upper limit of 75% using two different kernel but this will involve AMD's hardware to do all the scheduling, over which I won't have much control. Regards, Sayantan Content of type "text/html" skipped
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.