<html>
<head>
<base href="https://bugs.freedesktop.org/" />
</head>
<body>
<p>
<div>
<b><a class="bz_bug_link
bz_status_NEW "
title="NEW --- - 100% CPU usage"
href="https://bugs.freedesktop.org/show_bug.cgi?id=66928#c7">Comment # 7</a>
on <a class="bz_bug_link
bz_status_NEW "
title="NEW --- - 100% CPU usage"
href="https://bugs.freedesktop.org/show_bug.cgi?id=66928">bug 66928</a>
from <span class="vcard"><a class="email" href="mailto:Thomas.Freitag@alfa.de" title="Thomas Freitag <Thomas.Freitag@alfa.de>"> <span class="fn">Thomas Freitag</span></a>
</span></b>
<pre>(In reply to <a href="show_bug.cgi?id=66928#c5">comment #5</a>)
<span class="quote">> Could it be that Your caching of GfxICCBasedColorSpace doesn't work
> correctly, Albert? </span >
Sorry, Albert, my mistake: had an old callgrind file flying around and
kcacheground took it, it was produced prior Your changes ... :-(
I profiled now also page 3, and definitely, the time is wasted in
cmsDoTransform. BUT: the call stack is
GfxImageColorMap::getRGB (!!!)
GfxICCBaseColorSpace::getRGB
GfxColorTransform::doTransform
cmsDoTransfrom
called round about 22 million times for page 3, where 256 calls should be
sufficient if we cache the results in GfxImageColorMap, but probably we the
need to cache GfxImageColorMap, too. But let me first try to cache the RGB
results in GfxImageColorMap....</pre>
</div>
</p>
<hr>
<span>You are receiving this mail because:</span>
<ul>
<li>You are the assignee for the bug.</li>
</ul>
</body>
</html>