Data Parallel Multi-GPU Path Tracing using Ray Queue Cycling

Simple item page
dc.contributor.authorWald, Ingoen_US
dc.contributor.authorJaros, Milanen_US
dc.contributor.authorZellmann, Stefanen_US
dc.contributor.editorBikker, Jaccoen_US
dc.contributor.editorGribble, Christiaanen_US
dc.date.accessioned2023-06-25T09:04:16Z
dc.date.available2023-06-25T09:04:16Z
dc.date.issued2023
dc.description.abstractWe propose a novel approach to data-parallel path tracing on single-node/multi-GPU hardware that builds on ray forwarding, but which aims-above all else-at generality and practicability. We do this by avoiding any attempts at reducing the number of traces or forward operations performed, and instead focus on always using all GPUs' aggregate compute and bandwidth to effectively trace each ray on every GPU. We show that-counter-intuitively-this is both feasible and desirable; and that when run on typical data-center/cloud hardware, the resulting framework not only achieves good performance and scalability, but also comes with significantly fewer limitations, assumptions, or preprocessing requirements than existing techniques.en_US
dc.description.number8
dc.description.sectionheadersDistributed and Cloud-Based Rendering
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume42
dc.identifier.doi10.1111/cgf.14873
dc.identifier.issn1467-8659
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14873
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14873
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.titleData Parallel Multi-GPU Path Tracing using Ray Queue Cyclingen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v42i8_06_14873.pdf
Size:
4.45 MB
Format:
Adobe Portable Document Format
Download
Collections
42-Issue 8
High-Performance Graphics 2023