Abstract / Description of output
Simultaneous BVH traversal, as a dynamic task of pair-wise proximity tests, poses several challenges in terms of parallelization using GPUs. It is a highly dynamic and data-dependent problem which can induce control-flow divergence and inefficient data-access patterns. We present a simple solution using the bulk-synchronous parallel model to ensure a uniform mode of execution, and balanced workloads across GPU threads. The method is easy to implement, fast and operates entirely on the GPU by relying on a topology-centred work expansion scheme to ensure large concurrent workloads. We demonstrate speedups of upto 7.1× over the widely used “streams” model for GPU based parallel collision detection.
| Original language | English |
|---|---|
| Title of host publication | I3D '18 Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games |
| Place of Publication | Montreal, Quebec, Canada |
| Publisher | ACM |
| Pages | 4:1-4:9 |
| Number of pages | 9 |
| ISBN (Electronic) | 978-1-4503-5705-0 |
| DOIs | |
| Publication status | Published - 15 May 2018 |
| Event | ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games - Ubisoft Montreal, Montreal, Canada Duration: 15 May 2018 → 18 May 2018 http://i3dsymposium.github.io/2018/ |
Conference
| Conference | ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games |
|---|---|
| Abbreviated title | I3D2018 |
| Country/Territory | Canada |
| City | Montreal |
| Period | 15/05/18 → 18/05/18 |
| Internet address |
Keywords / Materials (for Non-textual outputs)
- collision detection
- parallel computing
- GPU
- BVH
- BSP