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
