<p dir="ltr"><br>
On Mar 7, 2016 12:03 AM, "Sebastian Huber" <<a href="mailto:sebastian.huber@embedded-brains.de">sebastian.huber@embedded-brains.de</a>> wrote:<br>
><br>
> Hello,<br>
><br>
><br>
> On 06/03/16 19:17, Joel Sherrill wrote:<br>
>><br>
>> Sebastian may have more general SMP ideas but the initial push for SMP gave us great support on a subset of BSPs and architectures and left gaps on others.<br>
><br>
><br>
> working on SMP improvements is a bit difficult currently since I will work in this area nearly full time in the next half a year or so. I hope that Darshit Shah will work on the SMP scheduler optimizations for the arbitrary processor affinities in GSoC 2016.<br>
><br>
> Adding SMP support to a specific BSP for an architecture that already supports SMP (ARM, PowerPC, SPARC) is not enough for a GSoC project. Even adding SMP support to new architectures shouldn't be a big deal.</p>
<p dir="ltr">The x86 has enough issues to keep someone busy for a summer. </p>
<p dir="ltr">Also just because you can do something quickly doesn't mean a student can. :)<br></p>
<p dir="ltr">> -- <br>
> Sebastian Huber, embedded brains GmbH<br>
><br>
> Address : Dornierstr. 4, D-82178 Puchheim, Germany<br>
> Phone : +49 89 189 47 41-16<br>
> Fax : +49 89 189 47 41-09<br>
> E-Mail : <a href="mailto:sebastian.huber@embedded-brains.de">sebastian.huber@embedded-brains.de</a><br>
> PGP : Public key available on request.<br>
><br>
> Diese Nachricht ist keine geschäftliche Mitteilung im Sinne des EHUG.<br>
><br>
</p>