Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 13 Aug 2012 08:11:52 +0400
From: Solar Designer <solar@...nwall.com>
To: john-dev@...ts.openwall.com
Subject: Re: bf-opencl fails self-test on CPU

magnum, Sayantan -

On Mon, Aug 13, 2012 at 08:33:45AM +0530, Sayantan Datta wrote:
> OpenCL platform 0: Intel(R) OpenCL, 1 device(s).
> Using device 0:         Intel(R) Core(TM) i5-2500 CPU @ 3.30GHz
> Compilation log: :116:59: warning: unknown attribute 'max_constant_size'
> ignored
> :117:46: warning: unknown attribute 'max_constant_size' ignored
> :122:60: warning: unknown attribute 'max_constant_size' ignored
> Build started
> Kernel <blowfish> was not vectorized

BTW, is there any way to target future Intel CPUs (those with AVX2)
with Intel's OpenCL SDK and see if this kernel would be vectorized then?
Of course, we won't be able to run it yet, except maybe on their SDE.

> Now I really doubt there is anything equivalent to LDS on a CPU.

There is not, yet the SDK might e.g. choose to place "local" allocations
closer together, assuming that they're accessed more frequently than
"global" ones and should not possibly be in the same cache lines (so
that a "local" load does not unnecessarily pull in any "global" data).

Alexander

Powered by blists - more mailing lists

Your e-mail address:

Powered by Openwall GNU/*/Linux - Powered by OpenVZ