Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation
Jiawei Liu, Yuxiang Wei, Sen Yang, Yinlin Deng, Lingming Zhang

TL;DR
This paper introduces Tzer, a coverage-guided fuzzing tool for tensor compilers like TVM, which mutates low-level IR and performs pass mutation to effectively discover bugs, significantly improving testing coverage and bug detection.
Contribution
Tzer is the first fuzzing technique targeting tensor compiler IR mutation, combining general-purpose and tensor-specific mutators with pass mutation for enhanced bug detection.
Findings
Tzer achieves 75% higher coverage than existing methods.
Tzer detects 49 previously unknown bugs in TVM.
37 bugs confirmed and 25 fixed through Tzer's testing.
Abstract
In the past decade, Deep Learning (DL) systems have been widely deployed in various domains to facilitate our daily life. 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 for running various DL models on many platforms. However, there is still limited work targeting the reliability of the emerging tensor compilers, which aim to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsParallel Computing and Optimization Techniques · Software Testing and Debugging Techniques · Advanced Neural Network Applications
