Hi Glenn and Robert,
thank you for your suggestion.
I have written a little stress test application to try different
PrimitiveSet sizes,
but so fat it's providing inconsistent results with respect to my previous
benchmark (and in line to what I expected).
I wasn't able to isolate a culprit so
Hi Riccardo,
I'm a surprised you saw a significant change in performance, in
particular for the worse, this suggest that the merging has some kind
of error in it or the driver isn't handling the larger sized
primitives efficiently for some reason.
One thing of note is that both the draw dispatch
Riccardo,
In my experience VBOs that are too large will reduce performance (on NVIDIA
at least). So you need to cap the size you use for each draw call. OSG's
MergeGeometryVisitor has a parameter for "target number of vertices" that
defaults to 10K per primitive set. On modern cards this can
3 matches
Mail list logo