Stream compaction for deferred shading

Jared Hoberock, Victor Lu, Yuntao Jia, John C Hart

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The GPU leverages SIMD efficiency when shading because it rasterizes a triangle at a time, running the same shader on all of its fragments. Ray tracing sacrifices this shader coherence, and the result is that SIMD units often must run different shaders simultaneously resulting in serialization. We study this problem and define a new measure called heterogeneous efficiency to measure SIMD divergence among multiple shaders of different complexities in a ray tracing application. We devise seven different algorithms for scheduling shaders onto SIMD processors to avoid divergence. In all but simply shaded scenes, we show the expense of sorting shaders pays off with better overall shading performance.

Original languageEnglish (US)
Title of host publicationProceedings of the HPG 2009
Subtitle of host publicationConference on High-Performance Graphics 2009
Pages173-180
Number of pages8
DOIs
StatePublished - Nov 27 2009
EventHPG 2009: Conference on High-Performance Graphics 2009 - New Orleans, LA, United States
Duration: Aug 1 2009Aug 3 2009

Publication series

NameProceedings of the HPG 2009: Conference on High-Performance Graphics 2009

Other

OtherHPG 2009: Conference on High-Performance Graphics 2009
CountryUnited States
CityNew Orleans, LA
Period8/1/098/3/09

Fingerprint

Ray tracing
Compaction
Sorting
Scheduling
Graphics processing unit

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Graphics and Computer-Aided Design
  • Hardware and Architecture
  • Software

Cite this

Hoberock, J., Lu, V., Jia, Y., & Hart, J. C. (2009). Stream compaction for deferred shading. In Proceedings of the HPG 2009: Conference on High-Performance Graphics 2009 (pp. 173-180). (Proceedings of the HPG 2009: Conference on High-Performance Graphics 2009). https://doi.org/10.1145/1572769.1572797

Stream compaction for deferred shading. / Hoberock, Jared; Lu, Victor; Jia, Yuntao; Hart, John C.

Proceedings of the HPG 2009: Conference on High-Performance Graphics 2009. 2009. p. 173-180 (Proceedings of the HPG 2009: Conference on High-Performance Graphics 2009).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hoberock, J, Lu, V, Jia, Y & Hart, JC 2009, Stream compaction for deferred shading. in Proceedings of the HPG 2009: Conference on High-Performance Graphics 2009. Proceedings of the HPG 2009: Conference on High-Performance Graphics 2009, pp. 173-180, HPG 2009: Conference on High-Performance Graphics 2009, New Orleans, LA, United States, 8/1/09. https://doi.org/10.1145/1572769.1572797
Hoberock J, Lu V, Jia Y, Hart JC. Stream compaction for deferred shading. In Proceedings of the HPG 2009: Conference on High-Performance Graphics 2009. 2009. p. 173-180. (Proceedings of the HPG 2009: Conference on High-Performance Graphics 2009). https://doi.org/10.1145/1572769.1572797
Hoberock, Jared ; Lu, Victor ; Jia, Yuntao ; Hart, John C. / Stream compaction for deferred shading. Proceedings of the HPG 2009: Conference on High-Performance Graphics 2009. 2009. pp. 173-180 (Proceedings of the HPG 2009: Conference on High-Performance Graphics 2009).
@inproceedings{5540d694ad0f4607a076d96c6d176989,
title = "Stream compaction for deferred shading",
abstract = "The GPU leverages SIMD efficiency when shading because it rasterizes a triangle at a time, running the same shader on all of its fragments. Ray tracing sacrifices this shader coherence, and the result is that SIMD units often must run different shaders simultaneously resulting in serialization. We study this problem and define a new measure called heterogeneous efficiency to measure SIMD divergence among multiple shaders of different complexities in a ray tracing application. We devise seven different algorithms for scheduling shaders onto SIMD processors to avoid divergence. In all but simply shaded scenes, we show the expense of sorting shaders pays off with better overall shading performance.",
author = "Jared Hoberock and Victor Lu and Yuntao Jia and Hart, {John C}",
year = "2009",
month = "11",
day = "27",
doi = "10.1145/1572769.1572797",
language = "English (US)",
isbn = "9781605586038",
series = "Proceedings of the HPG 2009: Conference on High-Performance Graphics 2009",
pages = "173--180",
booktitle = "Proceedings of the HPG 2009",

}

TY - GEN

T1 - Stream compaction for deferred shading

AU - Hoberock, Jared

AU - Lu, Victor

AU - Jia, Yuntao

AU - Hart, John C

PY - 2009/11/27

Y1 - 2009/11/27

N2 - The GPU leverages SIMD efficiency when shading because it rasterizes a triangle at a time, running the same shader on all of its fragments. Ray tracing sacrifices this shader coherence, and the result is that SIMD units often must run different shaders simultaneously resulting in serialization. We study this problem and define a new measure called heterogeneous efficiency to measure SIMD divergence among multiple shaders of different complexities in a ray tracing application. We devise seven different algorithms for scheduling shaders onto SIMD processors to avoid divergence. In all but simply shaded scenes, we show the expense of sorting shaders pays off with better overall shading performance.

AB - The GPU leverages SIMD efficiency when shading because it rasterizes a triangle at a time, running the same shader on all of its fragments. Ray tracing sacrifices this shader coherence, and the result is that SIMD units often must run different shaders simultaneously resulting in serialization. We study this problem and define a new measure called heterogeneous efficiency to measure SIMD divergence among multiple shaders of different complexities in a ray tracing application. We devise seven different algorithms for scheduling shaders onto SIMD processors to avoid divergence. In all but simply shaded scenes, we show the expense of sorting shaders pays off with better overall shading performance.

UR - http://www.scopus.com/inward/record.url?scp=70450189090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70450189090&partnerID=8YFLogxK

U2 - 10.1145/1572769.1572797

DO - 10.1145/1572769.1572797

M3 - Conference contribution

AN - SCOPUS:70450189090

SN - 9781605586038

T3 - Proceedings of the HPG 2009: Conference on High-Performance Graphics 2009

SP - 173

EP - 180

BT - Proceedings of the HPG 2009

ER -