Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Thu, 03 May 2012 11:51:32 +0200
From: magnum <john.magnum@...hmail.com>
To: john-dev@...ts.openwall.com
Subject: Re: Nvidia compiler verbosity

On 05/02/2012 10:59 PM, magnum wrote:
>> Let me know if you guys would like to have this on default version (only
>> if REPORT_OPENCL_WARNINGS is defined).
> 
> Yes, I think it should default to be activated when
> REPORT_OPENCL_WARNINGS is defined. Perhaps we should undefine that when
> releasing Jumbo (the pragma unroll output is mostly annoying once you
> know it works)
> 
>>     sprintf(include, "-I %s %s %s%d %s %s", path_expand(pathname),
>>             get_device_type(dev_id) == CL_DEVICE_TYPE_CPU ?
>>             "-DDEVICE_IS_CPU" : "",
>>                 "-DDEVICE_INFO=", device_info,
>> + =>                gpu_nvidia(device_info) ? "-cl-nv-verbose" : "",
>>             "-cl-strict-aliasing -cl-mad-enable");

I committed the above for now (plus an extra %s in the format string).
It currently is always enabled so that's a to-do.

> When I tried this earlier I never ever got any output. Some googling
> indicated there might be some kind of PTX caching so it will only show
> up with new code, but some rewriting just to avoid a cache hit did not
> do the trick. Do you always get the output, even if running same kernel
> two times in a row?

When I first ran all formats after adding this, I got the output. On
subsequent occasions I do not. If this is due to caching I would really
like to know what files to delete to clear the cache. I saw a suggestion
for a path somewhere but it was for windows. Maybe I should strace clcc
on bull.

magnum

Powered by blists - more mailing lists

Your e-mail address:

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