<html>
<head>
<base href="https://bugs.freedesktop.org/">
</head>
<body>
<p>
<div>
<b><a class="bz_bug_link
bz_status_NEW "
title="NEW - OpenCL/Clover: AMD Turks: corrupt output buffer (depending on dimension order?)"
href="https://bugs.freedesktop.org/show_bug.cgi?id=103586#c13">Comment # 13</a>
on <a class="bz_bug_link
bz_status_NEW "
title="NEW - OpenCL/Clover: AMD Turks: corrupt output buffer (depending on dimension order?)"
href="https://bugs.freedesktop.org/show_bug.cgi?id=103586">bug 103586</a>
from <span class="vcard"><a class="email" href="mailto:vedran@miletic.net" title="Vedran Miletić <vedran@miletic.net>"> <span class="fn">Vedran Miletić</span></a>
</span></b>
<pre>(In reply to Dave Gilbert from <a href="show_bug.cgi?id=103586#c6">comment #6</a>)
<span class="quote">> (In reply to Jan Vesely from <a href="show_bug.cgi?id=103586#c5">comment #5</a>)
> > (In reply to Dave Gilbert from <a href="show_bug.cgi?id=103586#c4">comment #4</a>)
> > > Created <span class=""><a href="attachment.cgi?id=135313" name="attach_135313" title="foo.link-0.ll">attachment 135313</a> <a href="attachment.cgi?id=135313&action=edit" title="foo.link-0.ll">[details]</a></span>
> > > foo.link-0.ll
> > >
> > > That's all 3 of the debug files it produced.
> > > (I wasn't sure which were the llvm and which the isa dumps; I guess the asm
> > > is the isa? and the ll's are both llvm dumps?)
> >
> > yes. the first .ll is from compilation step, the other one is from linking
> > step.
> >
> > .ll dump looks correct.
> > .asm also looks correct.
> >
> > you can try producing multiple asm dumps for working and non-working runs.
> > But I don't think that the llvm is the culprit here.
> >
> > Can you try waiting for the kernel execution to complete explicitly before
> > mapping the buffer?
> > Ideally call clFinish() on line 63.
>
> Since I'm on the C++ binding (probably a mistake) I used:
> queue.finish();
>
> and it seems to be working.
>
> (This also corresponds possibly to what I'm seeing on a more complex kernel;
> with a more complex kernel I'm seeing on a whole pile of data on the last
> few Z slices as being bogus suggesting it's not finished).
>
> Dave</span >
This reminds me of a certain issue I experienced with OpenMM. Is it limited to
Turks, or it happens on SI+ cards?</pre>
</div>
</p>
<hr>
<span>You are receiving this mail because:</span>
<ul>
<li>You are the assignee for the bug.</li>
<li>You are the QA Contact for the bug.</li>
</ul>
</body>
</html>