Battlefield V Star Wars Battlefront II FIFA 18 The Sims Madden NFL 18 Electronic Arts Home Electronics Arts Home

Subscribe & Save

Join EA Access Join Origin Access

Future Directions for Compute-for-Graphics

SEED - Future Worlds

The past few years have seen a sharp increase in the complexity of rendering algorithms used in modern game engines. Large portions of the rendering work are increasingly written in GPU computing languages, and decoupled from the conventional “one-to-one” pipeline stages for which shading languages were designed.

Following Tim Foley’s talk from SIGGRAPH 2016’s Open Problems course on shading language directions, SEED's Andrew Lauritzen explores example rendering algorithms that we want to express in a composable, reusable and performance-portable manner. We argue that a few key constraints in GPU computing languages inhibit these goals, some of which are rooted in hardware limitations. The presentation concludes with a call to action detailing specific improvements we would like to see in GPU compute languages, as well as the underlying graphics hardware.

This presentation was originally created for the Open Problems in Real-Time Rendering course for SIGGRAPH 2017.

Future Directions for Compute-for-Graphics from Electronic Arts / DICE.

Related News

DD18 Presentation - Raytracing in Hybrid Real-Time Rendering

SEED
Jul 6, 2018

Self-Learning Agents Play Battlefield 1

SEED
Jun 8, 2018

GDC 2018 Presentation Slides - Creativity of Rules and Patterns

SEED
Mar 29, 2018
Games Games Library News Playtesting Studios facebook twitter youtube instagram twitch Browse Games Latest News Help Center EA Forums About Us Careers United States United Kingdom Australia France Deutschland Italia 日本 Polska Brasil Россия España Ceska Republika Canada (En) Canada (Fr) Danmark Suomi Mexico Nederland Norge Sverige 中国 대한민국 Legal Online Service Updates User Agreement Privacy & Cookie Policy (Your Privacy Rights)