Memory Access Protocols: Certified Data-Race Freedom for GPU Kernels

Tiago Cogumbreiro, Julien Lange, Dennis Liew Zhen Rong, Hannah Zicarelli

Research output: Contribution to journalArticlepeer-review

1 Downloads (Pure)


GPUs offer parallelism as a commodity, but they are difficult to
program correctly. Static analyzers that guarantee data-race freedom
(DRF) are essential to help programmers establish the correctness
of their programs (kernels). However, existing approaches produce
too many false alarms and struggle to handle larger programs. To
address these limitations we formalize a novel compositional analysis for
DRF, based on memory access protocols. These protocols are behavioral types that codify the way threads interact over shared memory.
Our work includes fully mechanized proofs of our theoretical results,
the first mechanized proofs in the field of DRF analysis for GPU
kernels. Our theory is implemented in Faial, a tool that outperforms
the state-of-the-art. Notably, it can correctly verify at least 1.42×
more real-world kernels, and it exhibits a linear growth in 4 out of
5 experiments, while others grow exponentially in all 5 experiments.
Original languageEnglish
Journal Formal Methods in System Design
Publication statusPublished - 26 May 2023

Cite this