On Wed, May 1, 2013 at 10:36 PM, Карпов Роман <[email protected]> wrote:
> I would like to implement SIMD triangle intersection. Also it is
> interesting to implement AVX intrinsics, but it is require either 8-ary BVH
> or ray packets for effective use of 8 simultaneous operations.
>
> So I think it could be useful to implement n-ary BVH instead of just QBVH.
> Where n is multiples in powers of 2.
>
> Also I would like to implement "Multithreaded BVH build with spatial splits
> option enabled"
> and several specialized BVH traversal functions, but only if I would have
> enough time.
>
> At the moment I am working on my degree project "Ray tracing in real time
> on the CPU and GPU" until mid-June, right before coding phase of GSOC will
> begin. In this work I implement QBVH and use SIMD as maximum as possible.
> Also it would render on CPU and GPU at the same time.

Sounds good. Remember the application submission deadline is in less
than two days.

Brecht.
_______________________________________________
Bf-committers mailing list
[email protected]
http://lists.blender.org/mailman/listinfo/bf-committers

Reply via email to