Christophe Gyurgyik (or simply, Chris) is a PhD candidate at Stanford University advised by Fred Kjolstad. His interests include programming language and compiler design. His current work focuses on developing abstractions that enable the performance engineer (read: computer science expert) to optimize data structures while preserving productivity for the application user (read: non computer science expert).
Previously, he worked at Google on the XLA (Accelerated Linear Algebra) compiler and the TPU (Tensor Processing Unit). Prior to industry, his research centered on Calyx, a compiler infrastructure for languages that target hardware accelerators and CIRCT, an experimental compiler to improve hardware design tools. This work was completed under Cornell University’s CAPRA, spearheaded by Rachit Nigam and Adrian Sampson.
In his free time, Christophe enjoys climbing, surfing, and reading.
Both Scion (layout polymorphism for BVHs) and Bonsai (mechanized compiler techniques for tree traversals) have been conditionally accepted to PLDI!
Invited talk on acceleration structure layout polymorphism for the Stanford Software Research Lunch.
Invited talk on acceleration structure layout polymorphism for the Stanford Pervasive Parallelism Lab.
Invited talk on acceleration structure layout polymorphism for the Stanford Portal center.
Passed my qualifying examination, with committee members Fredrik Kjolstad, Alex Aiken, Sara Achour. Read about it here.