[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Tue, 16 Sep 2014 21:14:46 +0200
From: magnum <john.magnum@...hmail.com>
To: john-users@...ts.openwall.com
Subject: Re: nVidia Maxwell support (especially descrypt)?
On 2014-09-11 10:39, Solar Designer wrote:
> On Thu, Sep 11, 2014 at 09:54:39AM +0200, magnum wrote:
>> For example, it fails
>> building under later AMD drivers due to excessive use of 'goto'. Some
>> other drivers commit suic^Wsegfault while trying to sort it out. I
>> believe using goto in an OpenCL kernel is really begging for problems.
>
> I'd say it's a compiler problem, but yes we may have to workaround it by
> stopping to use goto, even though this kernel's uses of goto are
> reasonable.
Claudio found this:
http://www.khronos.org/message_boards/showthread.php/6457-Error-E010-Irreducible-ControlFlow-Detected
"Re: Error:E010:Irreducible ControlFlow Detected
That means you have some goto jumping into the middle of a loop. OpenCL
compilers are not required to support this kind of unstructured code.
Even on compiler that support it, it may hurt performance quite a bit."
(David Garcia is member of the OpenCL standard committee)
I can't see any place where we are jumping *into* a loop though, just
out of loops. But that message is precisely what 14.6beta emits when it
throws in the towel.
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.
