===Week 6 report===<br><br>==This week==<br>* I got quite a few scenes through <a href="http://ba.org">ba.org</a>: <a href="http://blenderartists.org/forum/showthread.php?t=159928">http://blenderartists.org/forum/showthread.php?t=159928</a><br>
You can see latest runs on:<br><a href="http://andresp.no-ip.org/soc2009/btest/html/test_real">http://andresp.no-ip.org/soc2009/btest/html/test_real</a><br><a href="http://andresp.no-ip.org/soc2009/btest/html/test_concept">http://andresp.no-ip.org/soc2009/btest/html/test_concept</a><br>
The "text_rocks" and "Geko_TVC_ToolBoard_05" render incorrectly/crash.. but that already happens on trunk2.5 (broken is taking care of it)<br>* "Remembering the past" slowdown was caused by a particles bug<br>
*Coded an Object Level BIH<br>*Implemented Object Level SAH during build<br>*Tested a few heuristics (hint, last hint) and did some other improvements (like tree building (although still not nlogn), raycast)<br>*Reverted the SUN & HEMI lights to have the same behaviour as trunk<br>
<br>==Next week==<br>Keep working on data structures<br>Look on SSE<br>Fix bugs<br><br>==Questions==<br>I was told gcc auto vectorization isnt that great and I would probably need to code specific SSE (SIMD). Any pointers on this and how to integrate SSE on blender are welcome.<br>
<br>Like:<br>would it be possible todo runtime switch between code? (this would mean having a part of code compiled with -sse and during runtime decide which version to execute?)<br>would it be possible to rely on auto vectorization and then having sse binaries distributed?<br>
<br>==Schedule==<br>I would say some nice level of optimization as already been reached.<br>
And all that's left is: more optimization! and bug fixing.<br><br>As I said before I will have a summer break from 20july to 31july, so this is the last full week before that.<br><br>