G
Ganesh Gopalakrishnan
Researcher at University of Utah
Publications - 233
Citations - 4408
Ganesh Gopalakrishnan is an academic researcher from University of Utah. The author has contributed to research in topics: Formal verification & Model checking. The author has an hindex of 33, co-authored 225 publications receiving 4127 citations.
Papers
More filters
Proceedings ArticleDOI
Performance analysis and optimization of asynchronous circuits
TL;DR: This work adapts the theory of generalized timed Petri-nets (GTPN) for analyzing and comparing asynchronous circuits ranging from purely control-oriented circuits to those with data dependent control.
Proceedings ArticleDOI
GKLEE: concolic verification and test generation for GPUs
TL;DR: This work provides a new framework called GKLEE that can analyze C++ GPU programs, locating the aforesaid correctness and performance bugs and describes previously unknown bugs and performance issues that it detected on commercial SDK kernels.
Proceedings ArticleDOI
Scalable SMT-based verification of GPU kernel functions
Guodong Li,Ganesh Gopalakrishnan +1 more
TL;DR: The first comprehensive symbolic verifier for kernels written in CUDA C is contributed, called the 'Prover of User GPU programs (PUG), which efficiently and automatically analyzes real-world kernels using Satisfiability Modulo Theories (SMT) tools, detecting bugs such as data races, incorrectly synchronized barriers, bank conflicts, and wrong results.
Proceedings ArticleDOI
GPU Concurrency: Weak Behaviours and Programming Assumptions
Jade Alglave,Mark Batty,Alastair F. Donaldson,Ganesh Gopalakrishnan,Jeroen Ketema,Daniel Poetzl,Tyler Sorensen,John Wickerson +7 more
TL;DR: A model of Nvidia GPU hardware is proposed, which correctly models every behaviour witnessed in the authors' experiments, and is a variant of SPARC Relaxed Memory Order (RMO), structured following the GPU concurrency hierarchy.
Book ChapterDOI
Rigorous Estimation of Floating-Point Round-off Errors with Symbolic Taylor Expansions
TL;DR: A new approach called Symbolic Taylor Expansions is developed that avoids this difficulty, and a new tool called FPTaylor is implemented embodying this approach, using rigorous global optimization instead of the more familiar interval arithmetic, affine arithmetic, and/or SMT solvers.