<html>
<head>
<base href="https://bugs.freedesktop.org/">
</head>
<body><table border="1" cellspacing="0" cellpadding="8">
<tr>
<th>Bug ID</th>
<td><a class="bz_bug_link
bz_status_NEW "
title="NEW - Nearly 10% performance drop in SynMark CSCloth from "i965: Emit CS stall before MEDIA_VFE_STATE""
href="https://bugs.freedesktop.org/show_bug.cgi?id=104100">104100</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>Nearly 10% performance drop in SynMark CSCloth from "i965: Emit CS stall before MEDIA_VFE_STATE"
</td>
</tr>
<tr>
<th>Product</th>
<td>Mesa
</td>
</tr>
<tr>
<th>Version</th>
<td>git
</td>
</tr>
<tr>
<th>Hardware</th>
<td>Other
</td>
</tr>
<tr>
<th>OS</th>
<td>All
</td>
</tr>
<tr>
<th>Status</th>
<td>NEW
</td>
</tr>
<tr>
<th>Severity</th>
<td>normal
</td>
</tr>
<tr>
<th>Priority</th>
<td>medium
</td>
</tr>
<tr>
<th>Component</th>
<td>Drivers/DRI/i965
</td>
</tr>
<tr>
<th>Assignee</th>
<td>intel-3d-bugs@lists.freedesktop.org
</td>
</tr>
<tr>
<th>Reporter</th>
<td>eero.t.tamminen@intel.com
</td>
</tr>
<tr>
<th>QA Contact</th>
<td>intel-3d-bugs@lists.freedesktop.org
</td>
</tr></table>
<p>
<div>
<pre>Following commit drops performance in SynMark CSCloth test, as expected:
-----------------------------------------------------
commit 55a97db52347f62111a24715078c6035380d3e19
Author: Kenneth Graunke <<a href="mailto:kenneth@whitecape.org">kenneth@whitecape.org</a>>
AuthorDate: Tue Oct 31 09:57:54 2017 -0700
Commit: Matt Turner <<a href="mailto:mattst88@gmail.com">mattst88@gmail.com</a>>
CommitDate: Mon Dec 4 10:02:46 2017 -0800
i965: Emit CS stall before MEDIA_VFE_STATE.
This fixes hangs on GFXBench 5's Aztec Ruins benchmark.
Unfortunately, it regresses OglCSCloth performance by about 10%. There
are some ideas for fixing that.
The Vulkan driver already emits this stall.
Reviewed-by: Matt Turner <<a href="mailto:mattst88@gmail.com">mattst88@gmail.com</a>>
-----------------------------------------------------
The drop is:
* 8-9% on SKL GT4e
* 5-6% on KBL GT3e
* 3-4% on SKL & KBL GT2
* within (largish) variance on BDW GT2 & GT3
On HSW GT it would seem to actually improve perf marginally.
Latter is interesting because Kenneth's trial fix for the performance
regression (verified to fix it):
<a href="https://cgit.freedesktop.org/~kwg/mesa/commit/?h=vfe-stall-3&id=ab9bff0ac43f0d878106ba124e84edca9b359c8a">https://cgit.freedesktop.org/~kwg/mesa/commit/?h=vfe-stall-3&id=ab9bff0ac43f0d878106ba124e84edca9b359c8a</a>
Is according to Kenneth causing problems on HSW. Maybe it could be applied
only on newer GENs?</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>