Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Fri, 20 Apr 2012 16:48:22 +0200
From: Lukas Odzioba <lukas.odzioba@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: [Off-topic] Experiments!

2012/4/20 magnum <john.magnum@...hmail.com>:
> I'm starting to get really frustrated too. Not only our formats are
> immature, all OpenCL SDK's and tools are too. Bugs, weird "features",
> undocumented behavior. An example: after days of trying to figure out
> why I could not bump global work size in RAR, it turned out that
> "__global const" is apparently treated as "__constant" by nvidia - thus
> getting a serious size limitation. But the end result was not warnings
> or build errors - just a crashing runtime. This is unacceptable, I'm
> thinking maybe I should focus on CUDA until OpenCL is more mature.

CUDA has it's own "features" too :). Sometimes even "i++;" is not working.
Also using global (declared out of function) pointers does not work at all.
In general gpu programming for now it is not so pleasant as cpu programming.

Lukas

Powered by blists - more mailing lists

Your e-mail address:

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