RI Seminar: Kayvon Fatahalian: Evolving the OpenGL Graphics Pipeline

RI Seminar: Kayvon Fatahalian
Evolving the OpenGL Graphics Pipeline in Pursuit of Real-Time, Film-Quality Rendering
Kayvon Fatahalian
Assistant Professor
Computer Science Department, Carnegie Mellon University
September 23, 2011
Abstract
In the past fifteen years the capabilities of real-time graphics systems have increased rapidly as a
result of domain-influenced co-design of algorithms, programming interfaces, and heterogeneous,
parallel hardware (GPUs). Despite these improvements, rendering geometrically complex, film-
quality scenes at interactive rates remains beyond the capabilities of current systems. Current
GPU implementations not only require additional compute capability to handle high-resolution
surfaces represented by pixel-sized "micropolygons", fundamental system operations such as
geometry processing, surface visibility, and shading execute inefficiently under this workload.
In this talk I will describe an evolution of the OpenGL graphics pipeline that significantly in-
creases system efficiency when rendering micropolygons. The redesign modifies rendering al-
gorithms, GPU hardware, and programming abstractions to increase parallelism and eliminate
redundant work while preserving the graphics pipeline's simple parallel programming model and
the throughput-optimized design of GPU processing cores. This talk focuses on the challenges
of real-time graphics, but it is exciting to consider how future computational cameras and mobile
computer vision tasks will soon benefit from similar levels of system optimization.
Additional Information
Host: Adrien Treuille
Speaker Biography
Kayvon Fatahalian is an Assistant Professor in the Computer Science Department at Carnegie Mellon University.
His research focuses on the design of programming abstractions and efficient parallel systems for computer-intensive applications such as interactive computer graphics.