<html>
<head>
<base href="https://bugs.freedesktop.org/">
</head>
<body>
<p>
<div>
<b><a class="bz_bug_link
bz_status_NEW "
title="NEW - [SKL] Up to 20% performance regression in GpuTest Triangle, due to 2x higher CPU power usage"
href="https://bugs.freedesktop.org/show_bug.cgi?id=107410#c11">Comment # 11</a>
on <a class="bz_bug_link
bz_status_NEW "
title="NEW - [SKL] Up to 20% performance regression in GpuTest Triangle, due to 2x higher CPU power usage"
href="https://bugs.freedesktop.org/show_bug.cgi?id=107410">bug 107410</a>
from <span class="vcard"><a class="email" href="mailto:eero.t.tamminen@intel.com" title="Eero Tamminen <eero.t.tamminen@intel.com>"> <span class="fn">Eero Tamminen</span></a>
</span></b>
<pre>(In reply to Eero Tamminen from <a href="show_bug.cgi?id=107410#c8">comment #8</a>)
<span class="quote">> (In reply to Srinivas Pandruvada from <a href="show_bug.cgi?id=107410#c6">comment #6</a>)
> > If this fixes, try the attached patch.
>
> I'm running the full set of benchmarks with this, so it takes a while.
> I'll report results tomorrow.</span >
Yes, the attached patch fixed all the regressions.
(In reply to Eero Tamminen from <a href="show_bug.cgi?id=107410#c0">comment #0</a>)
<span class="quote">> There were no improvements in any 3D benchmarks from this, but I noticed
> small increase in SIMD CPU copy and large increase in SIMD CPU read
> performance. However, that was only on SKL GT2, not GT4e, so it may be
> unrelated.</span >
The fix patch regressed Unigine Valley slightly. On closer look Valley had
actually increased with original change (by 1.0-1.5%), but only on SKL GT2.
I.e. there was actually one platform with one 3D benchmark where the initial
change improved perf slightly (without any noticeable increase in CPU power
usage).
-> I assume the SKL GT2 CPU read performance (25%) improvement was also due to
original change, but the improvement is very much a corner case [1].
[1] SKL-i5 6600K has 4 real cores. CPU read (performance with 64MB block
improved with the original change *only* in following cases:
- SSE2 with 4 threads
- SSE4.1 with 6 threads
- AVX1/2 with 6 threads
It didn't improve when the number of running SIMD threads was smaller or larger
that those.</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>
<li>You are on the CC list for the bug.</li>
</ul>
</body>
</html>