[sldev] RFC: Vectorisation control patch

[Dzonatas]

Paul TBBle Hampson wrote:
>>  general loops
>>     
> Are you now saying that that's not the case? That it would be worth
> trying to find some speed gain in the viewer by throwing some time into
> the code?
>   

That is a bit different. "General loops" is what I pointed out.

To answer your question, consider that there was around a 20% gain in 
code designed with SSE optimizations, and later another 10% gain came 
from just a few simple untangled headers and inline code, it appears 
that later is more of a win even if both are actually a win.

=)

-- 
Power to Change the Void
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.secondlife.com/pipermail/sldev/attachments/20070817/e81f152e/attachment.htm