<html>
<head>
<base href="https://bugs.freedesktop.org/">
</head>
<body>
<p>
<div>
<b><a class="bz_bug_link
bz_status_ASSIGNED "
title="ASSIGNED - dEQP-VK tests running very long time"
href="https://bugs.freedesktop.org/show_bug.cgi?id=110432#c10">Comment # 10</a>
on <a class="bz_bug_link
bz_status_ASSIGNED "
title="ASSIGNED - dEQP-VK tests running very long time"
href="https://bugs.freedesktop.org/show_bug.cgi?id=110432">bug 110432</a>
from <span class="vcard"><a class="email" href="mailto:lemody@gmail.com" title="Tapani Pälli <lemody@gmail.com>"> <span class="fn">Tapani Pälli</span></a>
</span></b>
<pre>Created <span class=""><a href="attachment.cgi?id=144127" name="attach_144127" title="force no unroll heuristics hack">attachment 144127</a> <a href="attachment.cgi?id=144127&action=edit" title="force no unroll heuristics hack">[details]</a></span> <a href='page.cgi?id=splinter.html&bug=110432&attachment=144127'>[review]</a>
force no unroll heuristics hack
Here's a patch that refuses to unroll when certain alu ops are met. Not sure
how much sense this makes but i seems whenever these nir_op_u2u8 and
nir_op_i2i8 are around enough then dEQP issue happens. Perhaps there's a bigger
picture/pattern to this so that the heuristic could be improved, I'll take a
look at that. Any comments/tips are welcome! :)</pre>
</div>
</p>
<hr>
<span>You are receiving this mail because:</span>
<ul>
<li>You are the QA Contact for the bug.</li>
</ul>
</body>
</html>