Coverage-guided tensor compiler fuzzing with joint IR-pass mutationPre-recorded
In the past decade, Deep Learning (DL) systems have been widely deployed in various application domains to facilitate our daily life, e.g., natural language processing, healthcare, activity recognition, and autonomous driving. Meanwhile, it is extremely challenging to ensure the correctness of DL systems (e.g., due to their intrinsic nondeterminism), and bugs in DL systems can cause serious consequences and may even threaten human lives. In the literature, researchers have explored various techniques to test, analyze, and verify DL models, since their quality directly affects the corresponding system behaviors. Recently, researchers have also proposed novel techniques for testing the underlying operator-level DL libraries (such as TensorFlow and PyTorch), which provide general binary implementations for each high-level DL operator and are the foundation for running DL models on different hardware platforms. However, there is still limited work targeting the reliability of the emerging tensor compilers (also known as DL compilers), which aim to automatically compile high-level tensor computation graphs directly into high-performance binaries for better efficiency, portability, and scalability than traditional operator-level libraries. Therefore, in this paper, we target the important problem of tensor compiler testing, and have proposed Tzer, a practical fuzzing technique for the widely used TVM tensor compiler. Tzer focuses on mutating the low-level Intermediate Representation (IR) for TVM due to the limited mutation space for the high-level IR. More specifically, Tzer leverages both general-purpose and tensor-compiler-specific mutators guided by coverage feedback for diverse and evolutionary IR mutation; furthermore, since tensor compilers provide various passes (i.e., transformations) for IR optimization, Tzer also performs pass mutation in tandem with IR mutation for more effective fuzzing. Our experimental results show that Tzer substantially outperforms existing fuzzing techniques on tensor compiler testing, with 75% higher coverage and 50% more valuable tests than the 2nd-best technique. Also, different components of Tzer have been validated via ablation study. To date, Tzer has detected 49 previously unknown bugs for TVM, with 37 bugs confirmed and 25 bugs fixed (PR merged).
Wed 30 NovDisplayed time zone: Auckland, Wellington change
04:00 - 05:30 | Session 1V-OOPSLA at Virtual Airmeet Room Chair(s): Amal Ahmed Northeastern University, USA, Jan Vitek Northeastern University | ||
04:00 15mTalk | Generic Go to Go: Dictionary-Passing, Monomorphisation, and HybridPre-recorded V-OOPSLA Stephen Ellis Imperial College London, Shuofei Zhu Pennsylvania State University, Nobuko Yoshida University of Oxford, Linhai Song Pennsylvania State University DOI | ||
04:15 15mResearch paper | Coverage-guided tensor compiler fuzzing with joint IR-pass mutationPre-recorded V-OOPSLA Jiawei Liu University of Illinois at Urbana-Champaign, Yuxiang Wei Tongji University, Sen Yang Fudan University, Yinlin Deng University of Illinois at Urbana-Champaign, Lingming Zhang University of Illinois at Urbana-Champaign DOI | ||
04:30 15mTalk | Modular Verification of Op-Based CRDTs in Separation Logic V-OOPSLA Abel Nieto Aarhus University, Léon Gondelman Aarhus University, Alban Reynaud ENS Lyon, Amin Timany Aarhus University, Lars Birkedal Aarhus University DOI | ||
04:45 15mTalk | Monadic and Comonadic Aspects of Dependency Analysis V-OOPSLA Pritam Choudhury University of Pennsylvania DOI | ||
05:00 30mLive Q&A | Q&A for Session 1 V-OOPSLA |