On-the-fly Vertex Reuse for Massively-Parallel Software Geometry Processing

Michael Kenzel, Bernhard Kerbl, Wolfgang Tatzgern, Elena Ivanchenko, Dieter Schmalstieg, and Markus Steinberger:
Proceedings of the ACM on Computer Graphics and Interaction Techniques (HPG'18), 2018

Shading Rate Visualization
Game Scene Rendering: The Witcher Wild Hunt screenshot courtesy of CD PROJEKT S.A.; used with permission
Inner and Outer Mesh Envelopes

Abstract

Due to its flexibility, compute mode is becoming more and more attractive as a way to implement many of the algorithms part of a state-of-the-art rendering pipeline. A key problem commonly encountered in graphics applications is streaming vertex and geometry processing. In a typical triangle mesh, the same vertex is on average referenced six times. To avoid redundant computation during rendering, a post-transform cache is traditionally employed to reuse vertex processing results. However, such a vertex cache can generally not be implemented efficiently in software and does not scale well as parallelism increases. We explore alternative strategies for reusing per-vertex results on-the-fly during massively-parallel software geometry processing. Given an input stream divided into batches, we analyze the effectiveness of sorting, hashing, and intra-threadgroup communication for identifying and exploiting local reuse potential. We design and present four vertex reuse strategies tailored to modern GPU architectures. We demonstrate that, in a variety of applications, these strategies not only achieve effective reuse of vertex processing results, but can boost performance by up to 2–3x compared to a naïve approach. Curiously, our experiments also show that our batch-based approaches exhibit behavior similar to the OpenGL implementation on current graphics hardware.

Resources

bibtex

@article{Kenzel:2018:OVR,
author = {Kenzel, Michael and Kerbl, Bernhard and Tatzgern, Wolfgang and Ivanchenko, Elena and Schmalstieg, Dieter and Steinberger, Markus},
title = {On-the-fly Vertex Reuse for Massively-Parallel Software Geometry Processing},
journal = {Proc. ACM Comput. Graph. Interact. Tech.},
issue_date = {August 2018},
volume = {1},
number = {2},
month = aug,
year = {2018},
articleno = {28},
numpages = {17},
doi = {10.1145/3233303},
publisher = {ACM},
address = {New York, NY, USA},
}