Simulee: Detecting CUDA Synchronization Bugs via Memory-Access ModelingTechnical
While CUDA has become a mainstream parallel computing platform and programming model for general-purpose GPU computing, how to effectively and efficiently detect CUDA synchronization bugs remains a challenging open problem. In this paper, we establish the first lightweight CUDA synchronization bug detection framework, namely Simulee, to model CUDA program execution by interpreting the corresponding LLVM bytecode and collecting the memory-access information for automatically detecting general CUDA synchronization bugs. To evaluate the effectiveness and efficiency of Simulee, we construct a benchmark with 7 popular CUDA-related projects from GitHub, upon which we conduct an extensive set of experiments. The experimental results suggest that Simulee can detect 21 out of the 24 manually identified bugs in our preliminary study and also 24 previously unknown bugs among all projects, 10 of which have already been confirmed by the developers. Furthermore, Simulee significantly outperforms state-of-the-art approaches for CUDA synchronization bug detection.
Sat 11 JulDisplayed time zone: (UTC) Coordinated Universal Time change
15:00 - 16:00 | A26-Bugs and RepairJournal First / Technical Papers at Goguryeo Chair(s): Davide Falessi California Polytechnic State University | ||
15:00 12mTalk | Simulee: Detecting CUDA Synchronization Bugs via Memory-Access ModelingTechnical Technical Papers Mingyuan Wu Southern University of Science and Technology, Yicheng Ouyang Southern University of Science and Technology, Husheng Zhou The University of Texas at Dallas, Lingming Zhang The University of Texas at Dallas, Cong Liu UT Dallas, Yuqun Zhang Southern University of Science and Technology | ||
15:12 8mTalk | Fine-Grained Dynamic Resource Allocation for Big-Data ApplicationsJ1 Journal First Luciano Baresi Politecnico di Milano, Alberto Leva Politecnico di Milano, Giovanni Quattrocchi Politecnico di Milano | ||
15:20 8mTalk | The Assessor's Dilemma: Improving Bug Repair via Empirical Game TheoryJ1 Journal First Carlos Gavidia-Calderon University College London, Federica Sarro University College London, UK, Mark Harman Facebook and University College London, Earl T. Barr University College London, UK Link to publication DOI Pre-print Media Attached | ||
15:28 8mTalk | FixMiner: Mining Relevant Fix Patterns for Automated Program RepairJ1 Journal First Anil Koyuncu University of Luxembourg, Luxembourg, Kui Liu Huawei Software Engineering Application Technology Lab, Tegawendé F. Bissyandé SnT, University of Luxembourg, Dongsun Kim Furiosa.ai, Jacques Klein University of Luxembourg, SnT, Martin Monperrus KTH Royal Institute of Technology, Yves Le Traon University of Luxembourg Pre-print | ||
15:36 8mTalk | IntRepair: Informed Repairing of Integer OverflowsJ1 Journal First Paul Muntean TU Munich, Martin Monperrus KTH Royal Institute of Technology, Hao Sun Unaffiliated, Jens Grossklags Technical University of Munich, Claudia Eckert Technical University of Munich | ||
15:44 12mTalk | DLFix: Context-based Code Transformation Learning for Automated Program RepairTechnical Technical Papers Yi Li New Jersey Institute of Technology, USA, Shaohua Wang New Jersey Institute of Technology, USA, Tien N. Nguyen University of Texas at Dallas | ||