I am a Ph.D. student in the Computer Graphics Lab at Stanford University under the advisement of Professor Pat Hanrahan. I am most interested in applying high-performance computation to problems in the creative arts and natural sciences. This interest has guided me toward projects involving interactive rendering systems, parallel architectures and software programming models, and domain-specific programming abstractions. I strongly believe that better use (and better understanding) of computing technologies in the artistic, scientific, and public policy arenas has enormous potential to catalyze progress in these important fields.
At Stanford I've participated in a few projects, namely BrookGPU (abstracting the GPU as a stream processor), the Merrimac Streaming Supercomputer, Sequoia (a programming language for exposed communication parallel machines), and GRAMPS (a system for constructing custom rendering pipelines). My thesis research involves the design of a micropolygon rendering pipeline for producing cinematic quality images in real time on future graphics platforms. I will be defending in the fall of 2009. Occasionally, I post notes on my graphics architecture blog.
Publications

DiagSplit: Parallel, Crack-Free, Adaptive Tessellation for Micropolygon Rendering
Matthew Fisher, Kayvon Fatahalian, Solomon Boulos, Kurt Akeley, William R. Mark, Pat Hanrahan
ACM SIGGRAPH Asia 2009
Data-Parallel Rasterization of Micropolygons with Defocus and Motion Blur
Kayvon Fatahalian, Edward Luong, Solomon Boulos, Kurt Akeley, William R. Mark, Pat Hanrahan
High Performance Graphics 2009
GRAMPS: A Programming Model for Graphics Pipelines
Jeremy Sugerman, Kayvon Fatahalian, Solomon Boulos, Kurt Akeley, Pat Hanrahan
ACM Transactions on Graphics (TOG) January 2009
A Closer Look at GPUs
Kayvon Fatahalian and Mike Houston
Communications of the ACM. Vol. 51, No. 10 (October 2008)
(also published as "GPUs: A Closer Look": ACM Queue. March/April. 2008)
Compilation for Explicitly Managed Memory Hierarchies
Timothy J. Knight, Ji Young Park, Manman Ren, Mike Houston, Mattan Erez, Kayvon Fatahalian, Alex Aiken, William J. Dally, Pat Hanrahan
PPOPP 2007
Sequoia: Programming the Memory Hierarchy
Kayvon Fatahalian, Timothy J. Knight, Mike Houston, Mattan Erez, Daniel R Horn, Larkhoon Leem, Ji Young Park, Manman Ren, Alex Aiken, William J. Dally, Pat Hanrahan
Supercomputing 2006
Understanding the Efficiency of GPU Algorithms for Matrix-Matrix Multiplication
Kayvon Fatahalian, Jeremy Sugerman, Pat Hanrahan
Graphics Hardware 2004
Brook for GPUs: Stream Computing on Graphics Hardware
Ian Buck, Tim Foley, Daniel Horn, Jeremy Sugerman, Kayvon Fatahalian, Mike Houston, Pat Hanrahan
ACM SIGGRAPH 2004
Precomputing Interactive Dynamic Deformable Scenes
Doug L. James and Kayvon Fatahalian
ACM SIGGRAPH 2003
Real-Time Global Illumination of Deformable Objects
Undergraduate Senior Research Thesis (Carnegie Mellon University). 2003.
Advised by Professor Doug L. James
Talks and Posters

From Shader Code to a Teraflop: How a Shader Core Works
Kayvon Fatahalian
ACM SIGGRAPH 2008 Class: Beyond Programmable Shading: Fundamentals
Programming Cell and a Cluster of PCs with Sequoia
Workshop on Edge Computing Using New Commodity Architectures, May 2006
[Extended Abstract]
Industry Stints

I spent two summers with the (now defunct) startup Agillion. I have been through the Cambridge version of the IBM Extreme Blue internship experience, and have spent three summers at NVIDIA, where I assisted with projects ranging from driver software development to compute programming model design work in the architecture group. In 2006 I spent a great summer working with Pixar's Renderman group in Seattle. As a grad student at Stanford I've done a little consulting on topics related to my research, most notably with the startup Peakstream (now part of Google).
Neat Little Projects

GPUBench: How much does your GPU bench?
Several of us in the Stanford graphics lab built up a suite of microbenchmarks that (back in the day) told you about everything you'll ever want to know about GPU performance.
Rendering Jellyfish
A project done with Tim Foley in Stanford's CS348B Advanced Rendering course.
Indelible
A first attempt to create an animated short.