https://community.intel.com/t5/Intel-Embree-Ray-Tracing-Kernels/One-RTCDevice-per-RTCScene/m-p/1599892#M998 <P>I have a renderer with a two-tiered acceleration structure (Top-level "TLAS" and base-level "BLAS").&nbsp; I have switched to using Embree for the BLAS, but am continuing to maintain the TLAS (it allows me to construct a more complex scene graph with transformation nodes, which allows me to modify individual pieces of geometry without needing to reconstruct the BLAS.&nbsp; It also allows me to use double precision rays, and simply transform them into a "local frame" and cast down to single precision prior to intersecting the Embree `RTCScene`).</P><P>&nbsp;</P><P>To keep things simple, my library has a `Universe` class which contains all models and the TLAS, and a `Model` class which contains the geometry and BLAS.&nbsp; The `Universe` stores a single `RTCDevice` which each `Model` is given when constructing the `BLAS` (and so each `RTCScene` shares a single `RTCDevice`).&nbsp;&nbsp;</P><P>&nbsp;</P><P>I am wondering if instead, I could just have every `Model` have its own `RTCDevice`.&nbsp; Is there a limit, or any performance penalties for doing this?</P> Wed, 22 May 2024 20:10:42 GMT crgnam 2024-05-22T20:10:42Z https://community.intel.com/t5/Intel-Embree-Ray-Tracing-Kernels/One-RTCDevice-per-RTCScene/m-p/1599892#M998 <P>I have a renderer with a two-tiered acceleration structure (Top-level "TLAS" and base-level "BLAS").&nbsp; I have switched to using Embree for the BLAS, but am continuing to maintain the TLAS (it allows me to construct a more complex scene graph with transformation nodes, which allows me to modify individual pieces of geometry without needing to reconstruct the BLAS.&nbsp; It also allows me to use double precision rays, and simply transform them into a "local frame" and cast down to single precision prior to intersecting the Embree `RTCScene`).</P><P>&nbsp;</P><P>To keep things simple, my library has a `Universe` class which contains all models and the TLAS, and a `Model` class which contains the geometry and BLAS.&nbsp; The `Universe` stores a single `RTCDevice` which each `Model` is given when constructing the `BLAS` (and so each `RTCScene` shares a single `RTCDevice`).&nbsp;&nbsp;</P><P>&nbsp;</P><P>I am wondering if instead, I could just have every `Model` have its own `RTCDevice`.&nbsp; Is there a limit, or any performance penalties for doing this?</P> Wed, 22 May 2024 20:10:42 GMT https://community.intel.com/t5/Intel-Embree-Ray-Tracing-Kernels/One-RTCDevice-per-RTCScene/m-p/1599892#M998 crgnam 2024-05-22T20:10:42Z