PolyJuice: Detecting Mis-compilation Bugs in Tensor Compilers with Equality Saturation Based Rewriting
Tensor compilers are essential for deploying deep learning applications across various hardware platforms. While powerful, they are inherently complex and present significant challenges in ensuring correctness. This paper introduces PolyJuice, an automatic detection tool for identifying mis-compilat...
Gespeichert in:
| Veröffentlicht in: | Proceedings of ACM on programming languages Jg. 8; H. OOPSLA2; S. 1309 - 1335 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
New York, NY, USA
ACM
08.10.2024
|
| Schlagworte: | |
| ISSN: | 2475-1421, 2475-1421 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Tensor compilers are essential for deploying deep learning applications across various hardware platforms. While powerful, they are inherently complex and present significant challenges in ensuring correctness. This paper introduces PolyJuice, an automatic detection tool for identifying mis-compilation bugs in tensor compilers. Its basic idea is to construct semantically-equivalent computation graphs to validate the correctness of tensor compilers. The main challenge is to construct equivalent graphs capable of efficiently exploring the diverse optimization logic during compilation. We approach it from two dimensions. First, we propose arithmetic and structural equivalent rewrite rules to modify the dataflow of a tensor program. Second, we design an efficient equality saturation based rewriting framework to identify the most simplified and the most complex equivalent computation graphs for an input graph. After that, the outcome computation graphs have different dataflow and will likely experience different optimization processes during compilation. We applied it to five well-tested industrial tensor compilers, namely PyTorch Inductor, OnnxRuntime, TVM, TensorRT, and XLA, as well as two well-maintained academic tensor compilers, EinNet and Hidet. In total, PolyJuice detected 84 non-crash mis-compilation bugs, out of which 49 were confirmed with 20 fixed. |
|---|---|
| AbstractList | Tensor compilers are essential for deploying deep learning applications across various hardware platforms. While powerful, they are inherently complex and present significant challenges in ensuring correctness. This paper introduces PolyJuice, an automatic detection tool for identifying mis-compilation bugs in tensor compilers. Its basic idea is to construct semantically-equivalent computation graphs to validate the correctness of tensor compilers. The main challenge is to construct equivalent graphs capable of efficiently exploring the diverse optimization logic during compilation. We approach it from two dimensions. First, we propose arithmetic and structural equivalent rewrite rules to modify the dataflow of a tensor program. Second, we design an efficient equality saturation based rewriting framework to identify the most simplified and the most complex equivalent computation graphs for an input graph. After that, the outcome computation graphs have different dataflow and will likely experience different optimization processes during compilation. We applied it to five well-tested industrial tensor compilers, namely PyTorch Inductor, OnnxRuntime, TVM, TensorRT, and XLA, as well as two well-maintained academic tensor compilers, EinNet and Hidet. In total, PolyJuice detected 84 non-crash mis-compilation bugs, out of which 49 were confirmed with 20 fixed. |
| ArticleNumber | 317 |
| Author | Go, Gwihwan Qian, Bingzhou Zhou, Chijin Zhang, Quan Li, Shanshan Jiang, Yu |
| Author_xml | – sequence: 1 givenname: Chijin orcidid: 0000-0002-6446-247X surname: Zhou fullname: Zhou, Chijin email: tlock.chijin@gmail.com organization: Tsinghua University, Beijing, China – sequence: 2 givenname: Bingzhou orcidid: 0009-0004-6522-4133 surname: Qian fullname: Qian, Bingzhou email: azykamail@gmail.com organization: National University of Defense Technology, Changsha, China – sequence: 3 givenname: Gwihwan orcidid: 0009-0001-0461-9674 surname: Go fullname: Go, Gwihwan email: iejw1914@gmail.com organization: Tsinghua University, Beijing, China – sequence: 4 givenname: Quan orcidid: 0000-0001-7778-4243 surname: Zhang fullname: Zhang, Quan email: zhangq20@mails.tsinghua.edu.cn organization: Tsinghua University, Beijing, China – sequence: 5 givenname: Shanshan orcidid: 0000-0003-0798-974X surname: Li fullname: Li, Shanshan email: shanshanli@nudt.edu.cn organization: National University of Defense Technology, Changsha, China – sequence: 6 givenname: Yu orcidid: 0000-0003-0955-503X surname: Jiang fullname: Jiang, Yu email: jiangyu198964@126.com organization: Tsinghua University, Beijing, China |
| BookMark | eNptkEtLw0AURgepYK3FvavZuYrOK5nGnbb1RUXRug4386gjaVJnJpT-e-1DEXF1L3znHi7fIerUTW0QOqbkjFKRnvNskMtU7qEuEzJNqGC082s_QP0Q3gkhNOdiwPMusk9NtbpvnTIXeGSiUdHVM_zgQqKa-cJVEF1T46t2FrCr8dTUofF4uImMD3jp4hsef7RQubjCLxBbv7uAYDR-Nkvv1sYjtG-hCqa_mz30ej2eDm-TyePN3fBykgCTMiZaUiatpiljmjBBudCl4szkoHJblqVlXJeQKTtQVgiwqQZmCNeZsYpklPIeOt16lW9C8MYWC-_m4FcFJcW6oWLX0BeZ_CGVi5vfowdX_cOfbHlQ8x_pd_gJr51zPg |
| CitedBy_id | crossref_primary_10_1145_3716497 |
| Cites_doi | 10.1145/3597503.3623343 10.1145/3434304 10.1145/3548606.3560624 10.1145/3324884.3416571 10.1145/3324884.3416572 10.1145/2491956.2462176 10.1145/3627703.3629562 10.1145/3600006.3613139 10.1145/3600006.3613140 10.1109/ICSE48619.2023.00024 10.1145/2737924.2737959 10.1145/3341301.3359662 10.1145/3510003.3510165 10.1145/1480881.1480915 10.5281/zenodo.12671619 10.1145/3510003.3510092 10.1109/MICRO50266.2020.00044 10.1145/3445814.3446707 10.1145/3540250.3549123 10.1145/3453483.3454038 10.1145/3632900 10.1145/3586027 10.1145/3540250.3549107 10.1109/TPDS.2020.3030548 10.1145/2384616.2384628 10.1145/3503222.3507764 10.1145/3368089.3409761 10.1145/3551349.3560431 10.1145/3597503.3639112 10.1145/3527317 10.1145/3591239 10.1145/3468264.3468591 10.14722/ndss.2019.23263 10.1145/3341301.3359630 10.1145/3519939.3523428 10.1145/1993498.1993532 10.1145/3489048.3522655 10.1145/3622819 10.1145/2594291.2594334 |
| ContentType | Journal Article |
| Copyright | Owner/Author |
| Copyright_xml | – notice: Owner/Author |
| DBID | AAYXX CITATION |
| DOI | 10.1145/3689757 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2475-1421 |
| EndPage | 1335 |
| ExternalDocumentID | 10_1145_3689757 3689757 |
| GroupedDBID | AAKMM AAYFX ACM ADPZR AIKLT ALMA_UNASSIGNED_HOLDINGS GUFHI LHSKQ M~E OK1 ROL AAYXX AEFXT AEJOY AKRVB CITATION |
| ID | FETCH-LOGICAL-a277t-d7127fd1522d024134dbc32e9ac9fbbbf23dba6cf8cf44af5da2e03d6efc06113 |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001356867600003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2475-1421 |
| IngestDate | Sat Nov 29 07:48:01 EST 2025 Tue Nov 18 22:23:45 EST 2025 Fri Feb 21 01:26:37 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | OOPSLA2 |
| Keywords | Fuzzing Equality Saturation Tensor Compiler Testing ML System |
| Language | English |
| License | This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike International 4.0 License. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-a277t-d7127fd1522d024134dbc32e9ac9fbbbf23dba6cf8cf44af5da2e03d6efc06113 |
| ORCID | 0000-0002-6446-247X 0009-0004-6522-4133 0000-0003-0798-974X 0000-0003-0955-503X 0009-0001-0461-9674 0000-0001-7778-4243 |
| OpenAccessLink | https://dl.acm.org/doi/10.1145/3689757 |
| PageCount | 27 |
| ParticipantIDs | crossref_primary_10_1145_3689757 crossref_citationtrail_10_1145_3689757 acm_primary_3689757 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-10-08 |
| PublicationDateYYYYMMDD | 2024-10-08 |
| PublicationDate_xml | – month: 10 year: 2024 text: 2024-10-08 day: 08 |
| PublicationDecade | 2020 |
| PublicationPlace | New York, NY, USA |
| PublicationPlace_xml | – name: New York, NY, USA |
| PublicationTitle | Proceedings of ACM on programming languages |
| PublicationTitleAbbrev | ACM PACMPL |
| PublicationYear | 2024 |
| Publisher | ACM |
| Publisher_xml | – name: ACM |
| References | Theodoros Theodoridis, Manuel Rigger, and Zhendong Su. 2022. Finding missed optimizations through the lens of dead code elimination. In 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2022. ACM. Lianmin Zheng, Zhuohan Li, Hao Zhang, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, Yuanzhong Xu, Danyang Zhuo, Eric P. Xing, Joseph E. Gonzalez, and Ion Stoica. 2022. Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022. Haoyang Ma, Qingchao Shen, Yongqiang Tian, Junjie Chen, and Shing-Chi Cheung. 2023. Fuzzing Deep Learning Compilers with HirGen. In 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA 2023. Nvidia. 2023. NVIDIA TensorRT. https://developer.nvidia.com/tensorrt (visited on September 1, 2023) microsoft. 2023. ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator. https://github.com/microsoft/onnxruntime (visited on September 1, 2023) open std. 2023. ISO/IEC 9899:TC3. https://www.open-std.org/jtc1/sc22/wg14/www/docs/n1256.pdf (visited on September 1, 2023) Ningxin Zheng, Huiqiang Jiang, Quanlu Zhang, Zhenhua Han, Lingxiao Ma, Yuqing Yang, Fan Yang, Chengruidong Zhang, Lili Qiu, Mao Yang, and Lidong Zhou. 2023. PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation. In 29th Symposium on Operating Systems Principles, SOSP 2023. Chijin Zhou, Quan Zhang, Lihua Guo, Mingzhe Wang, Yu Jiang, Qing Liao, Zhiyong Wu, Shanshan Li, and Bin Gu. 2023. Towards Better Semantics Exploration for Browser Fuzzing. Proc. ACM Program. Lang., 7, OOPSLA2 (2023), 604–631. 2024. PolyJuice: Detecting Mis-Compilation Bugs in Tensor Compilers with Equality Saturation Based Rewriting. Zenodo. https://doi.org/10.5281/zenodo.12671619 10.5281/zenodo.12671619 Cong Li, Yanyan Jiang, Chang Xu, and Zhendong Su. 2023. Validating JIT Compilers via Compilation Space Exploration. In 29th Symposium on Operating Systems Principles, SOSP 2023. Mingzhe Wang, Jie Liang, Chijin Zhou, Zhiyong Wu, Xinyi Xu, and Yu Jiang. 2022. Odin: on-demand instrumentation with on-the-fly recompilation. In 43rd ACM SIGPLAN International Conference on Programming Language Design and Implementation, PLDI 2022. Liyan Zheng, Haojie Wang, Jidong Zhai, Muyan Hu, Zixuan Ma, Tuowei Wang, Shuhong Huang, Xupeng Miao, Shizhi Tang, Kezhao Huang, and Zhihao Jia. 2023. EINNET: Optimizing Tensor Programs with Derivation-Based Transformations. In 17th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2023. Wookeun Jung, Thanh Tuan Dao, and Jaejin Lee. 2021. DeepCuts: a deep learning optimization framework for versatile GPU workloads. In 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, PLDI 2021. Chen Zhang, Lingxiao Ma, Jilong Xue, Yining Shi, Ziming Miao, Fan Yang, Jidong Zhai, Zhi Yang, and Mao Yang. 2023. Cocktailer: Analyzing and Optimizing Dynamic Control Flow in Deep Learning. In 17th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2023. Manuel Rigger and Zhendong Su. 2020. Testing Database Engines via Pivoted Query Synthesis. In 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020. Haojie Wang, Jidong Zhai, Mingyu Gao, Zixuan Ma, Shizhi Tang, Liyan Zheng, Yuanzhi Li, Kaiyuan Rong, Yuanyong Chen, and Zhihao Jia. 2021. PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections. In 15th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2021. Pavel Panchekha, Alex Sanchez-Stern, James R. Wilcox, and Zachary Tatlock. 2015. Automatically improving accuracy for floating point expressions. In 36th ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2015. Alexa VanHattum, Rachit Nigam, Vincent T. Lee, James Bornholt, and Adrian Sampson. 2021. Vectorization for digital signal processors via equality saturation. In 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2021. Mingzhe Wang, Zhiyong Wu, Xinyi Xu, Jie Liang, Chijin Zhou, Huafeng Zhang, and Yu Jiang. 2021. Industry Practice of Coverage-Guided Enterprise-Level DBMS Fuzzing. In 43rd IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice, ICSE (SEIP) 2021. Qianyu Guo, Xiaofei Xie, Yi Li, Xiaoyu Zhang, Yang Liu, Xiaohong Li, and Chao Shen. 2020. Audee: Automated Testing for Deep Learning Frameworks. In 35th IEEE/ACM International Conference on Automated Software Engineering, ASE 2020. Mingzhe Wang, Jie Liang, Chijin Zhou, Zhiyong Wu, Jingzhou Fu, Zhuo Su, Qing Liao, Bin Gu, Bodong Wu, and Yu Jiang. 2024. Data Coverage for Guided Fuzzing. In 33rd USENIX Security Symposium, USENIX Security 2024. Chijin Zhou, Mingzhe Wang, Jie Liang, Zhe Liu, and Yu Jiang. 2020. Zeror: Speed Up Fuzzing with Coverage-sensitive Tracing and Scheduling. In 35th IEEE/ACM International Conference on Automated Software Engineering, ASE 2020. Ross Tate, Michael Stepp, Zachary Tatlock, and Sorin Lerner. 2009. Equality saturation: a new approach to optimization. In 36th ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages, POPL 2009. Lukas Bernhard, Tobias Scharnowski, Moritz Schloegel, Tim Blazytko, and Thorsten Holz. 2022. JIT-Picking: Differential Fuzzing of JavaScript Engines. In 2022 ACM SIGSAC Conference on Computer and Communications Security, CCS 2022. Sameer Kulkarni and John Cavazos. 2012. Mitigating the compiler optimization phase-ordering problem using machine learning. In 27th Annual ACM SIGPLAN Conference on Object-Oriented Programming, Systems, Languages, and Applications, OOPSLA 2012. The IEEE and The Open Group. 2023. diff - compare two files. https://pubs.opengroup.org/onlinepubs/009604499/utilities/diff.html (visited on September 1, 2023) Chijin Zhou, Quan Zhang, Mingzhe Wang, Lihua Guo, Jie Liang, Zhe Liu, Mathias Payer, and Yu Jiang. 2022. Minerva: browser API fuzzing with dynamic mod-ref analysis. In 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2022. Jiawei Liu, Yuxiang Wei, Sen Yang, Yinlin Deng, and Lingming Zhang. 2022. Coverage-guided tensor compiler fuzzing with joint IR-pass mutation. Proc. ACM Program. Lang., 6, OOPSLA1 (2022), 1–26. Xuejun Yang, Yang Chen, Eric Eide, and John Regehr. 2011. Finding and understanding bugs in C compilers. In 32nd ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2011. James K. Reed, Zachary DeVito, Horace He, Ansley Ussery, and Jason Ansel. 2022. torch.fx: Practical Program Capture and Transformation for Deep Learning in Python. In Proceedings of Machine Learning and Systems 2022, MLSys 2022. Junru Shao, Xiyou Zhou, Siyuan Feng, Bohan Hou, Ruihang Lai, Hongyi Jin, Wuwei Lin, Masahiro Masuda, Cody Hao Yu, and Tianqi Chen. 2022. Tensor Program Optimization with Probabilistic Programs. In NeurIPS. Weisi Luo, Dong Chai, Xiaoyue Run, Jiang Wang, Chunrong Fang, and Zhenyu Chen. 2021. Graph-based Fuzz Testing for Deep Learning Inference Engines. In 43rd IEEE/ACM International Conference on Software Engineering, ICSE 2021. tvm. 2023. PR: Fix a bug of iter map floormod(x,2) simplify. https://github.com/apache/tvm/pull/14571 (visited on September 1, 2023) Junming Cao, Bihuan Chen, Chao Sun, Longjie Hu, Shuaihong Wu, and Xin Peng. 2022. Understanding performance problems in deep learning systems. In 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2022. Seulbae Kim, Meng Xu, Sanidhya Kashyap, Jungyeon Yoon, Wen Xu, and Taesoo Kim. 2019. Finding semantic bugs in file systems with an extensible fuzzing framework. In 27th ACM Symposium on Operating Systems Principles, SOSP 2019. Yaoyao Ding, Cody Hao Yu, Bojian Zheng, Yizhi Liu, Yida Wang, and Gennady Pekhimenko. 2023. Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs. In 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, ASPLOS 2023. Shaohua Li and Zhendong Su. 2023. Accelerating Fuzzing through Prefix-Guided Execution. Proc. ACM Program. Lang., 7, OOPSLA1 (2023), 1–27. Hao Sun, Yiru Xu, Jianzhong Liu, Yuheng Shen, Nan Guan, and Yu Jiang. 2024. Finding Correctness Bugs in eBPF Verifier with Structured and Sanitized Program. In 19th European Conference on Computer Systems, EuroSys 2024. Jiawei Liu, Jinkun Lin, Fabian Ruffy, Cheng Tan, Jinyang Li, Aurojit Panda, and Lingming Zhang. 2023. NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers. In 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, ASPLOS 2023. Zhihao Jia, Oded Padon, James Thomas, Todd Warszawski, Matei Zaharia, and Alex Aiken. 2019. TASO: optimizing deep learning computation with automatic generation of graph substitutions. In 27th ACM Symposium on Operating Systems Principles, SOSP 2019. Mingzhen Li, Yi Liu, Xiaoyan Liu, Qingxiao Sun, Xin You, Hailong Yang, Zhongzhi Luan, Lin Gan, Guangwen Yang, and Depei Qian. 2021. The Deep Learning Compiler: A Comprehensive Survey. IEEE Trans. Parallel Distributed Syst., 32, 3 (2021), 708–727. Jingzhou Fu, Jie Liang, Zhiyong Wu, Mingzhe Wang, and Yu Jiang. 2022. Griffin : Grammar-Free DBMS Fuzzing. In 37th IEEE/ACM International Conference on Automated Software Engineering, ASE 2022. Jonathan Ragan-Kelley, Connelly Barnes, Andrew Adams, Sylvain Paris, Frédo Durand, and Saman P. Amarasinghe. 2013. Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines. In 34th ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2013. Paul E Black. 1999. Algorithms and theory of Black Paul E (e_1_2_1_3_1) Zhu Hongyu (e_1_2_1_76_1) 2022 Reuther Albert (e_1_2_1_42_1) 2020 Wang Mingzhe (e_1_2_1_58_1) 2021 Zheng Lianmin (e_1_2_1_69_1) 2022 e_1_2_1_60_1 Wang Mingzhe (e_1_2_1_56_1) 2024 The IEEE and The Open Group (e_1_2_1_13_1) 2023 Zhou Chijin (e_1_2_1_74_1) 2025 e_1_2_1_20_1 e_1_2_1_66_1 (e_1_2_1_38_1) 2023 e_1_2_1_24_1 e_1_2_1_45_1 e_1_2_1_62_1 e_1_2_1_22_1 Reed James K. (e_1_2_1_41_1) 2022 Shao Junru (e_1_2_1_44_1) 2022 e_1_2_1_28_1 e_1_2_1_49_1 e_1_2_1_26_1 e_1_2_1_47_1 Liu Jiawei (e_1_2_1_27_1) 2023; 2 (e_1_2_1_48_1) 2023 Unger Colin (e_1_2_1_51_1) 2022 e_1_2_1_71_1 Rigger Manuel (e_1_2_1_43_1) 2020 Wang Haojie (e_1_2_1_53_1) 2021 Luo Weisi (e_1_2_1_29_1) 2021 IEC (e_1_2_1_34_1) 2023 Pal Anjali (e_1_2_1_35_1) 2023 e_1_2_1_54_1 e_1_2_1_8_1 e_1_2_1_6_1 e_1_2_1_12_1 e_1_2_1_73_1 e_1_2_1_4_1 Ding Yaoyao (e_1_2_1_7_1) 2023; 2 e_1_2_1_10_1 e_1_2_1_52_1 Zheng Liyan (e_1_2_1_70_1) 2023 e_1_2_1_75_1 e_1_2_1_2_1 e_1_2_1_16_1 e_1_2_1_14_1 e_1_2_1_37_1 Chen Tianqi (e_1_2_1_5_1) 2018 Jia Zhihao (e_1_2_1_15_1) 2019 Wang Mingzhe (e_1_2_1_55_1) 2021 Zheng Lianmin (e_1_2_1_68_1) 2020 Mohan Jayashree (e_1_2_1_32_1) 2018 e_1_2_1_65_1 e_1_2_1_40_1 e_1_2_1_23_1 e_1_2_1_46_1 e_1_2_1_61_1 Zhang Chen (e_1_2_1_64_1) 2023 e_1_2_1_21_1 (e_1_2_1_39_1) 2023 NVIDIA (e_1_2_1_33_1) 2023 Zhao Jie (e_1_2_1_67_1) 2022 e_1_2_1_25_1 Ma Haoyang (e_1_2_1_30_1) 2023 Kjolstad Fredrik (e_1_2_1_18_1) 2017 e_1_2_1_57_1 e_1_2_1_72_1 e_1_2_1_1_1 e_1_2_1_11_1 (e_1_2_1_50_1) 2023 e_1_2_1_17_1 (e_1_2_1_31_1) 2023 e_1_2_1_36_1 Yang Yichen (e_1_2_1_63_1) 2021 e_1_2_1_59_1 e_1_2_1_9_1 e_1_2_1_19_1 |
| References_xml | – reference: Yaoyao Ding, Cody Hao Yu, Bojian Zheng, Yizhi Liu, Yida Wang, and Gennady Pekhimenko. 2023. Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs. In 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, ASPLOS 2023. – reference: Lianmin Zheng, Zhuohan Li, Hao Zhang, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, Yuanzhong Xu, Danyang Zhuo, Eric P. Xing, Joseph E. Gonzalez, and Ion Stoica. 2022. Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022. – reference: Colin Unger, Zhihao Jia, Wei Wu, Sina Lin, Mandeep Baines, Carlos Efrain Quintero Narvaez, Vinay Ramakrishnaiah, Nirmal Prajapati, Patrick S. McCormick, Jamaludin Mohd-Yusof, Xi Luo, Dheevatsa Mudigere, Jongsoo Park, Misha Smelyanskiy, and Alex Aiken. 2022. Unity: Accelerating DNN Training Through Joint Optimization of Algebraic Transformations and Parallelization. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022. – reference: Haojie Wang, Jidong Zhai, Mingyu Gao, Zixuan Ma, Shizhi Tang, Liyan Zheng, Yuanzhi Li, Kaiyuan Rong, Yuanyong Chen, and Zhihao Jia. 2021. PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections. In 15th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2021. – reference: Hao Sun, Yiru Xu, Jianzhong Liu, Yuheng Shen, Nan Guan, and Yu Jiang. 2024. Finding Correctness Bugs in eBPF Verifier with Structured and Sanitized Program. In 19th European Conference on Computer Systems, EuroSys 2024. – reference: Ningxin Zheng, Huiqiang Jiang, Quanlu Zhang, Zhenhua Han, Lingxiao Ma, Yuqing Yang, Fan Yang, Chengruidong Zhang, Lili Qiu, Mao Yang, and Lidong Zhou. 2023. PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation. In 29th Symposium on Operating Systems Principles, SOSP 2023. – reference: Jiawei Liu, Yuxiang Wei, Sen Yang, Yinlin Deng, and Lingming Zhang. 2022. Coverage-guided tensor compiler fuzzing with joint IR-pass mutation. Proc. ACM Program. Lang., 6, OOPSLA1 (2022), 1–26. – reference: Alexa VanHattum, Rachit Nigam, Vincent T. Lee, James Bornholt, and Adrian Sampson. 2021. Vectorization for digital signal processors via equality saturation. In 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2021. – reference: Pavel Panchekha, Alex Sanchez-Stern, James R. Wilcox, and Zachary Tatlock. 2015. Automatically improving accuracy for floating point expressions. In 36th ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2015. – reference: Chijin Zhou, Mingzhe Wang, Jie Liang, Zhe Liu, and Yu Jiang. 2020. Zeror: Speed Up Fuzzing with Coverage-sensitive Tracing and Scheduling. In 35th IEEE/ACM International Conference on Automated Software Engineering, ASE 2020. – reference: Manuel Rigger and Zhendong Su. 2020. Testing Database Engines via Pivoted Query Synthesis. In 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020. – reference: Yihong Zhang, Yisu Remy Wang, Oliver Flatt, David Cao, Philip Zucker, Eli Rosenthal, Zachary Tatlock, and Max Willsey. 2023. Better Together: Unifying Datalog and Equality Saturation. Proc. ACM Program. Lang., 7, PLDI (2023), 468–492. – reference: Chijin Zhou, Quan Zhang, Mingzhe Wang, Lihua Guo, Jie Liang, Zhe Liu, Mathias Payer, and Yu Jiang. 2022. Minerva: browser API fuzzing with dynamic mod-ref analysis. In 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2022. – reference: Jonathan Ragan-Kelley, Connelly Barnes, Andrew Adams, Sylvain Paris, Frédo Durand, and Saman P. Amarasinghe. 2013. Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines. In 34th ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2013. – reference: Chijin Zhou, Quan Zhang, Lihua Guo, Mingzhe Wang, Yu Jiang, Qing Liao, Zhiyong Wu, Shanshan Li, and Bin Gu. 2023. Towards Better Semantics Exploration for Browser Fuzzing. Proc. ACM Program. Lang., 7, OOPSLA2 (2023), 604–631. – reference: Hao Guan, Ying Xiao, Jiaying Li, Yepang Liu, and Guangdong Bai. 2023. A Comprehensive Study of Real-World Bugs in Machine Learning Model Optimization. In 45th IEEE/ACM International Conference on Software Engineering, ICSE 2023. – reference: Wookeun Jung, Thanh Tuan Dao, and Jaejin Lee. 2021. DeepCuts: a deep learning optimization framework for versatile GPU workloads. In 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, PLDI 2021. – reference: Jie Liang, Zhiyong Wu, Jingzhou Fu, Mingzhe Wang, Chengnian Sun, and Yu Jiang. 2024. Mozi: Discovering DBMS Bugs via Configuration-Based Equivalent Transformation. In 46th IEEE/ACM International Conference on Software Engineering, ICSE 2024. – reference: Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph E. Gonzalez, and Ion Stoica. 2020. Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020. USENIX Association. – reference: Vu Le, Mehrdad Afshari, and Zhendong Su. 2014. Compiler validation via equivalence modulo inputs. In 35th ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2014. – reference: Cong Li, Yanyan Jiang, Chang Xu, and Zhendong Su. 2023. Validating JIT Compilers via Compilation Space Exploration. In 29th Symposium on Operating Systems Principles, SOSP 2023. – reference: Xuejun Yang, Yang Chen, Eric Eide, and John Regehr. 2011. Finding and understanding bugs in C compilers. In 32nd ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2011. – reference: Zhihao Jia, Oded Padon, James Thomas, Todd Warszawski, Matei Zaharia, and Alex Aiken. 2019. TASO: optimizing deep learning computation with automatic generation of graph substitutions. In 27th ACM Symposium on Operating Systems Principles, SOSP 2019. – reference: Max Willsey, Chandrakana Nandi, Yisu Remy Wang, Oliver Flatt, Zachary Tatlock, and Pavel Panchekha. 2021. egg: Fast and extensible equality saturation. Proc. ACM Program. Lang., 5, POPL (2021), 1–29. – reference: Douglas M. Priest. 1992. On properties of floating point arithmetics: numerical stability and the cost of accurate computations. Ph. D. Dissertation. USA. UMI Order No. GAX93-30692 – reference: Chen Zhang, Lingxiao Ma, Jilong Xue, Yining Shi, Ziming Miao, Fan Yang, Jidong Zhai, Zhi Yang, and Mao Yang. 2023. Cocktailer: Analyzing and Optimizing Dynamic Control Flow in Deep Learning. In 17th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2023. – reference: Jayashree Mohan, Ashlie Martinez, Soujanya Ponnapalli, Pandian Raju, and Vijay Chidambaram. 2018. Finding Crash-Consistency Bugs with Bounded Black-Box Crash Testing. In 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2018. – reference: Yinlin Deng, Chunqiu Steven Xia, Chenyuan Yang, Shizhuo Dylan Zhang, Shujing Yang, and Lingming Zhang. 2024. Large language models are edge-case generators: Crafting unusual programs for fuzzing deep learning libraries. In 46th IEEE/ACM International Conference on Software Engineering, ICSE 2024. – reference: Qianyu Guo, Xiaofei Xie, Yi Li, Xiaoyu Zhang, Yang Liu, Xiaohong Li, and Chao Shen. 2020. Audee: Automated Testing for Deep Learning Frameworks. In 35th IEEE/ACM International Conference on Automated Software Engineering, ASE 2020. – reference: Jiawei Liu, Jinkun Lin, Fabian Ruffy, Cheng Tan, Jinyang Li, Aurojit Panda, and Lingming Zhang. 2023. NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers. In 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, ASPLOS 2023. – reference: microsoft. 2023. ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator. https://github.com/microsoft/onnxruntime (visited on September 1, 2023) – reference: open std. 2023. ISO/IEC 9899:TC3. https://www.open-std.org/jtc1/sc22/wg14/www/docs/n1256.pdf (visited on September 1, 2023) – reference: Tensorflow. 2023. https://www.tensorflow.org/xla. https://www.tensorflow.org/xla (visited on September 1, 2023) – reference: Jie Zhao, Xiong Gao, Ruijie Xia, Zhaochuang Zhang, Deshi Chen, Lei Chen, Renwei Zhang, Zhen Geng, Bin Cheng, and Xuefeng Jin. 2022. Apollo: Automatic Partition-based Operator Fusion through Layer by Layer Optimization. In Proceedings of Machine Learning and Systems 2022, MLSys 2022. – reference: Zan Wang, Ming Yan, Junjie Chen, Shuang Liu, and Dongdi Zhang. 2020. Deep learning library testing via effective model generation. In 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2020. – reference: Jie Zhao and Peng Di. 2020. Optimizing the Memory Hierarchy by Compositing Automatic Transformations on Computations and Data. In 53rd Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2020. – reference: Seulbae Kim, Meng Xu, Sanidhya Kashyap, Jungyeon Yoon, Wen Xu, and Taesoo Kim. 2019. Finding semantic bugs in file systems with an extensible fuzzing framework. In 27th ACM Symposium on Operating Systems Principles, SOSP 2019. – reference: Mingzhe Wang, Jie Liang, Chijin Zhou, Zhiyong Wu, Jingzhou Fu, Zhuo Su, Qing Liao, Bin Gu, Bodong Wu, and Yu Jiang. 2024. Data Coverage for Guided Fuzzing. In 33rd USENIX Security Symposium, USENIX Security 2024. – reference: Mingzhe Wang, Jie Liang, Chijin Zhou, Zhiyong Wu, Xinyi Xu, and Yu Jiang. 2022. Odin: on-demand instrumentation with on-the-fly recompilation. In 43rd ACM SIGPLAN International Conference on Programming Language Design and Implementation, PLDI 2022. – reference: tvm. 2023. PR: Fix a bug of iter map floormod(x,2) simplify. https://github.com/apache/tvm/pull/14571 (visited on September 1, 2023) – reference: Thomas Koehler, Andrés Goens, Siddharth Bhat, Tobias Grosser, Phil Trinder, and Michel Steuwer. 2024. Guided Equality Saturation. Proc. ACM Program. Lang., 8, POPL (2024), 1727–1758. – reference: Junru Shao, Xiyou Zhou, Siyuan Feng, Bohan Hou, Ruihang Lai, Hongyi Jin, Wuwei Lin, Masahiro Masuda, Cody Hao Yu, and Tianqi Chen. 2022. Tensor Program Optimization with Probabilistic Programs. In NeurIPS. – reference: Hongyu Zhu, Ruofan Wu, Yijia Diao, Shanbin Ke, Haoyu Li, Chen Zhang, Jilong Xue, Lingxiao Ma, Yuqing Xia, Wei Cui, Fan Yang, Mao Yang, Lidong Zhou, Asaf Cidon, and Gennady Pekhimenko. 2022. ROLLER: Fast and Efficient Tensor Compilation for Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022. – reference: Paul E Black. 1999. Algorithms and theory of computation handbook, "Levenshtein distance". CRC press. https://www.nist.gov/dads/HTML/Levenshtein.html – reference: Nvidia. 2023. NVIDIA TensorRT. https://developer.nvidia.com/tensorrt (visited on September 1, 2023) – reference: HyungSeok Han, DongHyeon Oh, and Sang Kil Cha. 2019. CodeAlchemist: Semantics-Aware Code Generation to Find Vulnerabilities in JavaScript Engines. In 26th Annual Network and Distributed System Security Symposium, NDSS 2019. – reference: Dongwei Xiao, Zhibo Liu, Yuanyuan Yuan, Qi Pang, and Shuai Wang. 2022. Metamorphic Testing of Deep Learning Compilers. Proc. ACM Meas. Anal. Comput. Syst., 6, 1 (2022), 15:1–15:28. – reference: Mingzhe Wang, Jie Liang, Chijin Zhou, Yu Jiang, Rui Wang, Chengnian Sun, and Jiaguang Sun. 2021. RIFF: Reduced Instruction Footprint for Coverage-Guided Fuzzing. In 2021 USENIX Annual Technical Conference, USENIX ATC 2021. – reference: Yichen Yang, Phitchaya Mangpo Phothilimthana, Yisu Remy Wang, Max Willsey, Sudip Roy, and Jacques Pienaar. 2021. Equality Saturation for Tensor Graph Superoptimization. In Proceedings of Machine Learning and Systems 2021, MLSys 2021. – reference: Ross Tate, Michael Stepp, Zachary Tatlock, and Sorin Lerner. 2009. Equality saturation: a new approach to optimization. In 36th ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages, POPL 2009. – reference: Haoyang Ma, Qingchao Shen, Yongqiang Tian, Junjie Chen, and Shing-Chi Cheung. 2023. Fuzzing Deep Learning Compilers with HirGen. In 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA 2023. – reference: Albert Reuther, Peter Michaleas, Michael Jones, Vijay Gadepally, Siddharth Samsi, and Jeremy Kepner. 2020. Survey of Machine Learning Accelerators. In 2020 IEEE High Performance Extreme Computing Conference, HPEC 2020. – reference: Theodoros Theodoridis, Manuel Rigger, and Zhendong Su. 2022. Finding missed optimizations through the lens of dead code elimination. In 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2022. ACM. – reference: Shaohua Li and Zhendong Su. 2023. Accelerating Fuzzing through Prefix-Guided Execution. Proc. ACM Program. Lang., 7, OOPSLA1 (2023), 1–27. – reference: The IEEE and The Open Group. 2023. diff - compare two files. https://pubs.opengroup.org/onlinepubs/009604499/utilities/diff.html (visited on September 1, 2023) – reference: Qingchao Shen, Haoyang Ma, Junjie Chen, Yongqiang Tian, Shing-Chi Cheung, and Xiang Chen. 2021. A comprehensive study of deep learning compiler bugs. In 29th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2021. – reference: Mingzhe Wang, Zhiyong Wu, Xinyi Xu, Jie Liang, Chijin Zhou, Huafeng Zhang, and Yu Jiang. 2021. Industry Practice of Coverage-Guided Enterprise-Level DBMS Fuzzing. In 43rd IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice, ICSE (SEIP) 2021. – reference: 2024. PolyJuice: Detecting Mis-Compilation Bugs in Tensor Compilers with Equality Saturation Based Rewriting. Zenodo. https://doi.org/10.5281/zenodo.12671619 10.5281/zenodo.12671619 – reference: Cong Li, Yanyan Jiang, Chang Xu, and Zhendong Su. 2023. Validating JIT Compilers via Compilation Space Exploration. In 29th Symposium on Operating Systems Principles, SOSP 2023, Koblenz, Germany, October 23-26, 2023. – reference: Jingzhou Fu, Jie Liang, Zhiyong Wu, Mingzhe Wang, and Yu Jiang. 2022. Griffin : Grammar-Free DBMS Fuzzing. In 37th IEEE/ACM International Conference on Automated Software Engineering, ASE 2022. – reference: Weisi Luo, Dong Chai, Xiaoyue Run, Jiang Wang, Chunrong Fang, and Zhenyu Chen. 2021. Graph-based Fuzz Testing for Deep Learning Inference Engines. In 43rd IEEE/ACM International Conference on Software Engineering, ICSE 2021. – reference: Anjali Pal, Brett Saiki, Ryan Tjoa, Cynthia Richey, Amy Zhu, Oliver Flatt, Max Willsey, Zachary Tatlock, and Chandrakana Nandi. 2023. Equality Saturation Theory Exploration à la Carte. Proc. ACM Program. Lang., 7, OOPSLA2 (2023), 1034–1062. – reference: Mingzhen Li, Yi Liu, Xiaoyan Liu, Qingxiao Sun, Xin You, Hailong Yang, Zhongzhi Luan, Lin Gan, Guangwen Yang, and Depei Qian. 2021. The Deep Learning Compiler: A Comprehensive Survey. IEEE Trans. Parallel Distributed Syst., 32, 3 (2021), 708–727. – reference: PyTorch. 2023. Glow - Compiler for Neural Network hardware accelerators. https://github.com/pytorch/glow (visited on September 1, 2023) – reference: Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Q. Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2018. – reference: James K. Reed, Zachary DeVito, Horace He, Ansley Ussery, and Jason Ansel. 2022. torch.fx: Practical Program Capture and Transformation for Deep Learning in Python. In Proceedings of Machine Learning and Systems 2022, MLSys 2022. – reference: Zhihao Jia, James Thomas, Todd Warszawski, Mingyu Gao, Matei Zaharia, and Alex Aiken. 2019. Optimizing DNN Computation with Relaxed Graph Substitutions. In Proceedings of Machine Learning and Systems 2019, MLSys 2019. – reference: Jiannan Wang, Thibaud Lutellier, Shangshu Qian, Hung Viet Pham, and Lin Tan. 2022. EAGLE: Creating Equivalent Graphs to Test Deep Learning Libraries. In 44th IEEE/ACM 44th International Conference on Software Engineering, ICSE 2022. – reference: Jiazhen Gu, Xuchuan Luo, Yangfan Zhou, and Xin Wang. 2022. Muffin: Testing Deep Learning Libraries via Neural Architecture Fuzzing. In 44th IEEE/ACM 44th International Conference on Software Engineering, ICSE 2022. – reference: PyTorch. 2023. Accelerated CPU Inference with PyTorch Inductor using torch.compile. https://pytorch.org/blog/accelerated-cpu-inference/ (visited on September 1, 2023) – reference: Chijin Zhou, Quan Zhang, Bingzhou Qian, and Yu Jiang. 2025. Janus: Detecting Rendering Bugs in Web Browsers via Visual Delta Consistency. In 47th IEEE/ACM International Conference on Software Engineering, ICSE 2025. – reference: Fredrik Kjolstad, Shoaib Kamil, Stephen Chou, David Lugato, and Saman P. Amarasinghe. 2017. The tensor algebra compiler. Proc. ACM Program. Lang., 1, OOPSLA (2017), 77:1–77:29. – reference: Junming Cao, Bihuan Chen, Chao Sun, Longjie Hu, Shuaihong Wu, and Xin Peng. 2022. Understanding performance problems in deep learning systems. In 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2022. – reference: Lukas Bernhard, Tobias Scharnowski, Moritz Schloegel, Tim Blazytko, and Thorsten Holz. 2022. JIT-Picking: Differential Fuzzing of JavaScript Engines. In 2022 ACM SIGSAC Conference on Computer and Communications Security, CCS 2022. – reference: Liyan Zheng, Haojie Wang, Jidong Zhai, Muyan Hu, Zixuan Ma, Tuowei Wang, Shuhong Huang, Xupeng Miao, Shizhi Tang, Kezhao Huang, and Zhihao Jia. 2023. EINNET: Optimizing Tensor Programs with Derivation-Based Transformations. In 17th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2023. – reference: Sameer Kulkarni and John Cavazos. 2012. Mitigating the compiler optimization phase-ordering problem using machine learning. In 27th Annual ACM SIGPLAN Conference on Object-Oriented Programming, Systems, Languages, and Applications, OOPSLA 2012. – ident: e_1_2_1_6_1 doi: 10.1145/3597503.3623343 – volume-title: ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator. https://github.com/microsoft/onnxruntime (visited on year: 2023 ident: e_1_2_1_31_1 – ident: e_1_2_1_60_1 doi: 10.1145/3434304 – volume-title: PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections. In 15th USENIX Symposium on Operating Systems Design and Implementation, OSDI year: 2021 ident: e_1_2_1_53_1 – volume-title: Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI year: 2022 ident: e_1_2_1_69_1 – volume-title: Proc. ACM Program. Lang., 7, OOPSLA2 year: 2023 ident: e_1_2_1_35_1 – volume-title: Data Coverage for Guided Fuzzing. In 33rd USENIX Security Symposium, USENIX Security year: 2024 ident: e_1_2_1_56_1 – volume-title: diff - compare two files. https://pubs.opengroup.org/onlinepubs/009604499/utilities/diff.html (visited on year: 2023 ident: e_1_2_1_13_1 – ident: e_1_2_1_2_1 doi: 10.1145/3548606.3560624 – ident: e_1_2_1_11_1 doi: 10.1145/3324884.3416571 – volume: 2 volume-title: NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers. In 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems year: 2023 ident: e_1_2_1_27_1 – volume-title: Proceedings of Machine Learning and Systems 2021 year: 2021 ident: e_1_2_1_63_1 – ident: e_1_2_1_72_1 doi: 10.1145/3324884.3416572 – volume-title: Graph-based Fuzz Testing for Deep Learning Inference Engines. In 43rd IEEE/ACM International Conference on Software Engineering, ICSE year: 2021 ident: e_1_2_1_29_1 – volume-title: Survey of Machine Learning Accelerators. In 2020 IEEE High Performance Extreme Computing Conference, HPEC year: 2020 ident: e_1_2_1_42_1 – volume-title: PR: Fix a bug of iter map floormod(x,2) simplify. https://github.com/apache/tvm/pull/14571 (visited on year: 2023 ident: e_1_2_1_50_1 – volume-title: Proceedings of Machine Learning and Systems 2019 year: 2019 ident: e_1_2_1_15_1 – ident: e_1_2_1_40_1 doi: 10.1145/2491956.2462176 – volume: 2 volume-title: Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs. In 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems year: 2023 ident: e_1_2_1_7_1 – volume-title: 47th IEEE/ACM International Conference on Software Engineering, ICSE year: 2025 ident: e_1_2_1_74_1 – ident: e_1_2_1_46_1 doi: 10.1145/3627703.3629562 – ident: e_1_2_1_71_1 doi: 10.1145/3600006.3613139 – ident: e_1_2_1_22_1 doi: 10.1145/3600006.3613140 – volume-title: Unity: Accelerating DNN Training Through Joint Optimization of Algebraic Transformations and Parallelization. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI year: 2022 ident: e_1_2_1_51_1 – ident: e_1_2_1_10_1 doi: 10.1109/ICSE48619.2023.00024 – volume-title: Cocktailer: Analyzing and Optimizing Dynamic Control Flow in Deep Learning. In 17th USENIX Symposium on Operating Systems Design and Implementation, OSDI year: 2023 ident: e_1_2_1_64_1 – volume-title: Fuzzing Deep Learning Compilers with HirGen. In 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA year: 2023 ident: e_1_2_1_30_1 – volume-title: ROLLER: Fast and Efficient Tensor Compilation for Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI year: 2022 ident: e_1_2_1_76_1 – volume-title: Finding Crash-Consistency Bugs with Bounded Black-Box Crash Testing. In 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI year: 2018 ident: e_1_2_1_32_1 – ident: e_1_2_1_36_1 doi: 10.1145/2737924.2737959 – volume-title: Proceedings of Machine Learning and Systems 2022 year: 2022 ident: e_1_2_1_41_1 – volume-title: Industry Practice of Coverage-Guided Enterprise-Level DBMS Fuzzing. In 43rd IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice, ICSE (SEIP) year: 2021 ident: e_1_2_1_58_1 – ident: e_1_2_1_17_1 doi: 10.1145/3341301.3359662 – ident: e_1_2_1_54_1 doi: 10.1145/3510003.3510165 – ident: e_1_2_1_47_1 doi: 10.1145/1480881.1480915 – ident: e_1_2_1_1_1 doi: 10.5281/zenodo.12671619 – ident: e_1_2_1_9_1 doi: 10.1145/3510003.3510092 – volume-title: https://www.tensorflow.org/xla. https://www.tensorflow.org/xla (visited on year: 2023 ident: e_1_2_1_48_1 – ident: e_1_2_1_66_1 doi: 10.1109/MICRO50266.2020.00044 – ident: e_1_2_1_52_1 doi: 10.1145/3445814.3446707 – ident: e_1_2_1_23_1 doi: 10.1145/3600006.3613140 – ident: e_1_2_1_4_1 doi: 10.1145/3540250.3549123 – ident: e_1_2_1_16_1 doi: 10.1145/3453483.3454038 – ident: e_1_2_1_19_1 doi: 10.1145/3632900 – ident: e_1_2_1_37_1 – volume-title: Cody Hao Yu, and Tianqi Chen year: 2022 ident: e_1_2_1_44_1 – ident: e_1_2_1_25_1 doi: 10.1145/3586027 – volume-title: https://www.open-std.org/jtc1/sc22/wg14/www/docs/n1256.pdf (visited on year: 2023 ident: e_1_2_1_34_1 – volume-title: Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI year: 2020 ident: e_1_2_1_68_1 – ident: e_1_2_1_75_1 doi: 10.1145/3540250.3549107 – ident: e_1_2_1_24_1 doi: 10.1109/TPDS.2020.3030548 – volume-title: Proc. ACM Program. Lang., 1, OOPSLA year: 2017 ident: e_1_2_1_18_1 – ident: e_1_2_1_20_1 doi: 10.1145/2384616.2384628 – volume-title: Proceedings of Machine Learning and Systems 2022 year: 2022 ident: e_1_2_1_67_1 – volume-title: TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI year: 2018 ident: e_1_2_1_5_1 – volume-title: https://developer.nvidia.com/tensorrt (visited on year: 2023 ident: e_1_2_1_33_1 – volume-title: EINNET: Optimizing Tensor Programs with Derivation-Based Transformations. In 17th USENIX Symposium on Operating Systems Design and Implementation, OSDI year: 2023 ident: e_1_2_1_70_1 – volume-title: RIFF: Reduced Instruction Footprint for Coverage-Guided Fuzzing. In 2021 USENIX Annual Technical Conference, USENIX ATC year: 2021 ident: e_1_2_1_55_1 – ident: e_1_2_1_49_1 doi: 10.1145/3503222.3507764 – ident: e_1_2_1_59_1 doi: 10.1145/3368089.3409761 – ident: e_1_2_1_8_1 doi: 10.1145/3551349.3560431 – volume-title: Algorithms and theory of computation handbook, "Levenshtein distance ident: e_1_2_1_3_1 – ident: e_1_2_1_26_1 doi: 10.1145/3597503.3639112 – ident: e_1_2_1_28_1 doi: 10.1145/3527317 – ident: e_1_2_1_65_1 doi: 10.1145/3591239 – volume-title: Accelerated CPU Inference with PyTorch Inductor using torch.compile. https://pytorch.org/blog/accelerated-cpu-inference/ (visited on year: 2023 ident: e_1_2_1_38_1 – ident: e_1_2_1_45_1 doi: 10.1145/3468264.3468591 – ident: e_1_2_1_12_1 doi: 10.14722/ndss.2019.23263 – ident: e_1_2_1_14_1 doi: 10.1145/3341301.3359630 – ident: e_1_2_1_57_1 doi: 10.1145/3519939.3523428 – volume-title: Glow - Compiler for Neural Network hardware accelerators. https://github.com/pytorch/glow (visited on year: 2023 ident: e_1_2_1_39_1 – ident: e_1_2_1_62_1 doi: 10.1145/1993498.1993532 – ident: e_1_2_1_61_1 doi: 10.1145/3489048.3522655 – ident: e_1_2_1_73_1 doi: 10.1145/3622819 – ident: e_1_2_1_21_1 doi: 10.1145/2594291.2594334 – volume-title: 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI year: 2020 ident: e_1_2_1_43_1 |
| SSID | ssj0001934839 |
| Score | 2.2977936 |
| Snippet | Tensor compilers are essential for deploying deep learning applications across various hardware platforms. While powerful, they are inherently complex and... |
| SourceID | crossref acm |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 1309 |
| SubjectTerms | Software and its engineering Software testing and debugging |
| SubjectTermsDisplay | Software and its engineering -- Software testing and debugging |
| Title | PolyJuice: Detecting Mis-compilation Bugs in Tensor Compilers with Equality Saturation Based Rewriting |
| URI | https://dl.acm.org/doi/10.1145/3689757 |
| Volume | 8 |
| WOSCitedRecordID | wos001356867600003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2475-1421 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001934839 issn: 2475-1421 databaseCode: M~E dateStart: 20170101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Nb9MwFLfK4MCFjwFifMkHxAVFNI5dJ9y6MUBo3TpRpIlL5cQ2C-rSqWvWwYEzfzbvxY4bVTvAgUsUOS-25PfT-_J7z4S85IxLkwoVSfR0ODMiylNuwFUp4swMVGx1w-kDeXiYnpxk417vd1sLczmTVZVeXWXn_5XVMAbMxtLZf2B3mBQG4B2YDk9gOzz_ivHj-ezHpxovcwdn_53BQwIMB4zKiwjzx0uX_PZ6t_7WpMJOwI-dLxq5AAJi4avd9l2xJQgWbPzp_wCFh8WMK-yD5BWeN2vHQQ02mSHDvREeQvjcrzNcvo2LBhP-6-m8duf95fcyIPS4dAHZXfjnJ1CE9KAmovthVZ6u1nAOwe7j2g_68AXjLn-uAzifEt-IPACOiGLuaqZb-Zx2YHh0NP58MGQdiQs6OOtob3C5xfWagWMTjWSQZtJ1xN5os-2_3CA3mRQZJgeOfnWidVnCwZR0Vdc41xtPj0ZNcdYxajrWyeQeuePdCjp0cLhPeqbaJnfbKzuol-APiA3oeEsDNugGNihig5YVddigARsUsUFbbNA1NmiDDRqw8ZB8eb8_2fsY-as2IsWkXEZaxkxaDcYc0308auU6LxJmMlVkNs9zyxKdq0Fh08JyrqzQipl-ogfGFmARxskjslXNK_OYUJtY1dfghzIgZSDeherHVoAjkWrQKGyHbMOOTc9dM5Wp38cd8qrdwWnhu9PjJSmzqaucF2tCGgjbOTZInly7wlNye42_Z2RruajNc3KruFyWF4sXDbv_AO-Ufk4 |
| linkProvider | ISSN International Centre |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=PolyJuice%3A+Detecting+Mis-compilation+Bugs+in+Tensor+Compilers+with+Equality+Saturation+Based+Rewriting&rft.jtitle=Proceedings+of+ACM+on+programming+languages&rft.au=Zhou%2C+Chijin&rft.au=Qian%2C+Bingzhou&rft.au=Go%2C+Gwihwan&rft.au=Zhang%2C+Quan&rft.date=2024-10-08&rft.pub=ACM&rft.eissn=2475-1421&rft.volume=8&rft.issue=OOPSLA2&rft.spage=1309&rft.epage=1335&rft_id=info:doi/10.1145%2F3689757&rft.externalDocID=3689757 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2475-1421&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2475-1421&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2475-1421&client=summon |