[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Date: Tue, 21 Feb 2012 21:28:54 +0100
From: magnum <john.magnum@...hmail.com>
To: john-dev@...ts.openwall.com
Subject: OpenCL vs CUDA
Is this a general difference you see too?
Benchmarking: CRYPTMD5-OPENCL [MD5-based CRYPT]... DONE
Raw: 147803 c/s real, 49267 c/s virtual
Benchmarking: cuda-cryptmd5 [MD5-based CRYPT]... DONE
Raw: 258048 c/s real, 258048 c/s virtual
(both formats use the exact same test vector)
Is this due to Lukas' version being better optimised at the moment, or
is it due to NVidia's OpenCL stuff not being up to par with CUDA?
For phpass, both versions run at almost exactly the same speed:
Benchmarking: PHPASS-OPENCL [PORTABLE-MD5]... DONE
Raw: 256984 c/s real, 129113 c/s virtual
Benchmarking: cuda-phpass [PORTABLE-MD5]... DONE
Raw: 252438 c/s real, 252438 c/s virtual
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.
