Write a Blog >>
PLDI 2021
Sun 20 - Sat 26 June 2021 PLDI
Wed 23 Jun 2021 13:50 - 13:55 at PLDI-A - Talks 2A: Machine Learning
Thu 24 Jun 2021 01:50 - 01:55 at PLDI-A - Talks 2A: Machine Learning

Deep Neural Networks (DNNs) have emerged as the core enabler of many major applications on mobile devices. To achieve high accuracy, DNN models have become increasingly deep with hundreds or even thousands of operator layers, leading to high memory and computational requirements for inference. Operator fusion (or kernel/layer fusion) is key optimization in many state-of-the-art DNN execution frameworks, such as TensorFlow, TVM, and MNN, that aim to improve the efficiency of the DNN inference. However, these frameworks usually adopt fusion approaches based on certain patterns that are too restrictive to cover the diversity of operators and layer connections, especially those seen in many extremely deep models. Polyhedral-based loop fusion techniques, on the other hand, work on a low-level view of the computation without operator-level information, and can also miss potential fusion opportunities. To address this challenge, this paper proposes a novel and extensive loop fusion framework called DNNFusion. The basic idea of this work is to work at an operator view of DNNs, but expand fusion opportunities by developing a classification of both individual operators and their combinations. In addition, DNNFusion includes 1) a novel mathematical-property-based graph rewriting framework to reduce evaluation costs and facilitate subsequent operator fusion, 2) an integrated fusion plan generation that leverages the high-level analysis and accurate light-weight profiling, and 3) additional optimizations during fusion code generation. DNNFusion is extensively evaluated on 15 DNN models with varied types of tasks, model sizes, and layer counts. The evaluation results demonstrate that DNNFusion finds up to $8.8 \times$ higher fusion opportunities, outperforms four state-of-the-art DNN execution frameworks with $9.3\times$ speedup. The memory requirement reduction and speedups can enable the execution of many of the target models on mobile devices and even make them part of a real-time application.

Wed 23 Jun

Displayed time zone: Eastern Time (US & Canada) change

13:30 - 14:05
Talks 2A: Machine LearningPLDI at PLDI-A +12h
13:30
5m
Talk
Learning to Find Naming Issues with Big Code and Small Supervision
PLDI
Jingxuan He ETH Zurich, Cheng-Chun Lee EPFL, Veselin Raychev DeepCode, Martin Vechev ETH Zurich
DOI
13:35
5m
Talk
Fast and Precise Certification of Transformers
PLDI
Gregory Bonaert ETH Zurich, Dimitar I. Dimitrov ETH Zurich, Maximilian Baader ETH Zurich, Martin Vechev ETH Zurich
DOI
13:40
5m
Talk
Web Question Answering with Neurosymbolic Program Synthesis
PLDI
Qiaochu Chen University of Texas at Austin, USA, Aaron Lamoreaux University of Texas at Austin, Xinyu Wang University of Michigan, Greg Durrett University of Texas at Austin, USA, Osbert Bastani University of Pennsylvania, Isil Dillig University of Texas at Austin
DOI
13:45
5m
Talk
Robustness Certification with Generative Models
PLDI
Matthew Mirman ETH Zurich, Alexander Hägele ETH Zurich, Timon Gehr ETH Zurich, Pavol Bielik ETH Zurich, Martin Vechev ETH Zurich
Link to publication DOI
13:50
5m
Talk
DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion
PLDI
Wei Niu College of William & Mary, Jiexiong Guan College of William & Mary, Yanzhi Wang Northeastern University, Gagan Agrawal Augusta University, Bin Ren College of William & Mary
DOI
13:55
5m
Talk
Vectorized Secure Evaluation of Decision Forests
PLDI
Raghav Malik Purdue University, Vidush Singhal Purdue University, Benjamin Gottfried Purdue University, Milind Kulkarni Purdue University
DOI Pre-print
14:00
5m
Talk
AKG: Automatic Kernel Generation for Neural Processing Units using Polyhedral Transformations
PLDI
Jie Zhao State Key Laboratory of Mathematical Engineering and Advanced Computing, Bojie Li Huawei Technologies, Wang Nie Huawei Technologies, Zhen Geng Huawei Technologies, Renwei Zhang Huawei Technologies, Xiong Gao Huawei Technologies, Bin Cheng Huawei Technologies, Chen Wu Huawei, Yun Cheng Huawei Technologies, Zheng Li Huawei Technologies, Peng Di Huawei Technologies, Kun Zhang Huawei Technologies, Xuefeng Jin Huawei Technologies
DOI

Thu 24 Jun

Displayed time zone: Eastern Time (US & Canada) change

01:30 - 02:05
Talks 2A: Machine LearningPLDI at PLDI-A
01:30
5m
Talk
Learning to Find Naming Issues with Big Code and Small Supervision
PLDI
Jingxuan He ETH Zurich, Cheng-Chun Lee EPFL, Veselin Raychev DeepCode, Martin Vechev ETH Zurich
DOI
01:35
5m
Talk
Fast and Precise Certification of Transformers
PLDI
Gregory Bonaert ETH Zurich, Dimitar I. Dimitrov ETH Zurich, Maximilian Baader ETH Zurich, Martin Vechev ETH Zurich
DOI
01:40
5m
Talk
Web Question Answering with Neurosymbolic Program Synthesis
PLDI
Qiaochu Chen University of Texas at Austin, USA, Aaron Lamoreaux University of Texas at Austin, Xinyu Wang University of Michigan, Greg Durrett University of Texas at Austin, USA, Osbert Bastani University of Pennsylvania, Isil Dillig University of Texas at Austin
DOI
01:45
5m
Talk
Robustness Certification with Generative Models
PLDI
Matthew Mirman ETH Zurich, Alexander Hägele ETH Zurich, Timon Gehr ETH Zurich, Pavol Bielik ETH Zurich, Martin Vechev ETH Zurich
Link to publication DOI
01:50
5m
Talk
DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion
PLDI
Wei Niu College of William & Mary, Jiexiong Guan College of William & Mary, Yanzhi Wang Northeastern University, Gagan Agrawal Augusta University, Bin Ren College of William & Mary
DOI
01:55
5m
Talk
Vectorized Secure Evaluation of Decision Forests
PLDI
Raghav Malik Purdue University, Vidush Singhal Purdue University, Benjamin Gottfried Purdue University, Milind Kulkarni Purdue University
DOI Pre-print
02:00
5m
Talk
AKG: Automatic Kernel Generation for Neural Processing Units using Polyhedral Transformations
PLDI
Jie Zhao State Key Laboratory of Mathematical Engineering and Advanced Computing, Bojie Li Huawei Technologies, Wang Nie Huawei Technologies, Zhen Geng Huawei Technologies, Renwei Zhang Huawei Technologies, Xiong Gao Huawei Technologies, Bin Cheng Huawei Technologies, Chen Wu Huawei, Yun Cheng Huawei Technologies, Zheng Li Huawei Technologies, Peng Di Huawei Technologies, Kun Zhang Huawei Technologies, Xuefeng Jin Huawei Technologies
DOI