Název:	Bandwidth and memory efficiency in real-time ray tracing
Autoři:	Lousada, Pedro Costa, Vasco Pereira, João M.
Citace zdrojového dokumentu:	Journal of WSCG. 2017, vol. 25, no. 1, p. 49-57.
Datum vydání:	2017
Nakladatel:	Václav Skala - UNION Agency
Typ dokumentu:	článek article
URI:	wscg.zcu.cz/WSCG2017/!_2017_Journal_WSCG-No-1.pdf http://hdl.handle.net/11025/26279
ISSN:	1213-6972 (print) 1213-6980 (CD-ROM) 1213-6964 (on-line)
Klíčová slova:	sledování paprsku;hierarchie ohraničujících objemů;paralelizace;GPU;kvantování;paměť
Klíčová slova v dalším jazyce:	ray tracing;bounding volume hierarchy;parallelization;GPU;quantization;memory
Abstrakt v dalším jazyce:	Real time ray tracing has been given a lot of attention in recent years in the academic and research community. Several novel algorithms have appeared that parallelize different aspects of the ray tracing algorithm through the use of a GPU. Among these, the creation of Bounding Volume Hierarchies (BVHs). We believe that recent approaches have failed to consider the performance impact of memory accesses in GPU and how their cost affects the overall performance of the application. In this work we show that by reducing memory bandwidth and footprint we are able to achieve significant improvements in BVH traversal times. We do this by compressing the BVH and the triangle mesh in a parallel manner after its creation, in each frame, and then decompressing it as needed while traversing the BVH.
Práva:	© Václav Skala - UNION Agency
Vyskytuje se v kolekcích:	Volume 25, Number 1 (2017)

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.