<div class="gmail_quote">On Mon, Sep 5, 2011 at 15:22, Chris Wilson <span dir="ltr"><<a href="mailto:chris@chris-wilson.co.uk">chris@chris-wilson.co.uk</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<div class="im">On Mon, 5 Sep 2011 14:56:42 -0300, Eugeni Dodonov <<a href="mailto:eugeni@dodonov.net">eugeni@dodonov.net</a>> wrote:<br>
> From: Eugeni Dodonov <<a href="mailto:eugeni.dodonov@intel.com">eugeni.dodonov@intel.com</a>><br>
><br>
> This tool is based on ideas from intel_gpu_top, top and powertop<br>
> applications, combining them into one continous profiler which generates<br>
> human-readable output further processable by gnuplot and similar<br>
> applications.<br>
><br>
> It can be used either in continuous monitoring way (e.g., like top<br>
> and powertop, it will run until stopped), or could be used to execute and<br>
> profile specific applications with parameters.<br>
<br>
</div>Ok, this looks like a useful extension to intel_gpu_top (until the day<br>
arrives when we have a real, integrated profiler!). I don't see the need<br>
for a separate utility with lots of code duplicated just for a couple of<br>
extra features. Care to respin as a patch against intel_gpu_top? (I want<br>
to resist the temptation of making a second perf... especially as I'd<br>
like to make all this information available through perf!)<br></blockquote><div><br>Sure, will do.<br></div></div><br>-- <br>Eugeni Dodonov<a href="http://eugeni.dodonov.net/" target="_blank"></a><br>