The 29th International Symposium on High-Performance Parallel and Distributed Computing

Stockholm, Sweden, June 23-26, 2020

Conference Program

Tentative Program Agenda

HPDC will be hosting a virtual conference this year. The conference will feature a live welcome and introduction at the start of the conference on 10:00 AM EDT, June 23rd, 2020. This introduction will feature a welcome by the general co-chairs and the technical program co-chairs that summarizes the program, as well as a one-minute madness session that provides a preview of every paper in the conference. Keynote talks and papers will be pre-recorded by speakers and posted on the web (linked below). Full paper talks are 25 minutes and short paper talks are 10 minutes. Each paper speaker will host a live interactive Q&A session via Slack over the course of the conference to answer questions about their work. We are looking forward to interacting with everyone virtually in June, and please check back as we update our plans for the program!

Live Welcome and Introduction (10:00 AM EDT, June 23rd, 2020)
General Co-Chairs Welcome
Technical Program Co-Chairs Introduction
One-minute Madness Session (details to come!)
Session Chair: Dimitrios Nikolopoulos (Virginia Tech, USA)
Cognitive Discovery: Accelerating Technical R&D with AI,
Costas Bekas, Citadel Securities.
High Performance is all about Minimizing Data Movement,
Mary Hall, University of Utah.
Improving Accuracy and Efficiency
Session Chair: Kirk Cameron (Virginia Tech, USA)
Best Paper Award Candidate
Spying on the Floating Point Behavior of Existing, Unmodified Scientific Applications,
Peter Dinda, Alex Bernat, Conor Hetland, Northwestern University.
Best Paper Award Candidate
High Accuracy Matrix Computations on Neural Engines: a Study of QR Factorization and its Applications,
Shaoshuai Zhang, Elaheh Baharlouei, Panruo Wu, University of Houston.
Space-Efficient k-d Tree-Based Storage Format for Sparse Tensors (short paper),
Ivan Šimeček, Claudio Kozický, Daniel Langr, Pavel Tvrdík, Czech Technical University in Prague.
Practical Distributed Programming in C++ (short paper),
Maurizio Drocco, IBM Research; Vito Giovanni Castellana, Marco Minutoli, Pacific Northwest National Laboratory.
Up in the Clouds
Session Chair: Jeff Chase (Duke University, USA)
Modeling The Temporally Constrained Preemptions of Transient Cloud VMs,
JCS Kadupitige, Vikram Jadhao, Prateek Sharma, Indiana University.
Cloud-scale VM-deflation for Running Interactive Applications On Transient Servers,
Alexander Fuerst, Indiana University; Ahmed Ali-Eldin, University of Massachusetts Amherst and Chalmers University of Technology; Prashant Shenoy, University of Massachusetts Amherst; Prateek Sharma, Indiana University.
funcX: A Federated Function Serving Fabric for Science,
Ryan Chard, Argonne National Laboratory; Yadu Babuji, Zhuozhao Li, Tyler Skluzacek, Anna Woodard, Ben Blaiszik, University of Chicago; Ian Foster, Argonne National Laboratory and University of Chicago; Kyle Chard, University of Chicago.
Big Data Management
Session Chair: Jay Lofstead (Sandia National Laboratories, USA)
Towards HPC I/O Performance Prediction through Large-scale Log Analysis,
Sunggon Kim, Seoul National University; Alex Sim, Kesheng Wu, Suren Byna, Lawrence Berkeley National Laboratory;Yongseok Son, Chung-Ang University; Hyeonsang Eom, Seoul National University.
Significantly Improving Lossy Compression for HPC Datasets with Second-Order Prediction and Parameter Optimization,
Kai Zhao, University of California, Riverside; Sheng Di, Argonne National Laboratory; Xin Liang, Sihuan Li, University of California, Riverside; Dingwen Tao, Washington State University; Zizhong Chen, University of California, Riverside; Franck Cappello, Argonne National Laboratory.
Best Paper Award Candidate
DCDB Wintermute: Enabling Online and Holistic Operational Data Analytics on HPC Systems,
Alessio Netti, Micha Müller, Carla Guillen, Michael Ott, Daniele Tafani, Leibniz Supercomputing Centre; Gence Ozer, Martin Schulz, Technical University of Munich.
Distributed Learning
Session Chair: Tian Guo (Worcester Polytechnic Institute, USA)
FFT-based Gradient Sparsification for the Distributed Training of Deep Neural Networks,
Linnan Wang, Brown University Wei Wu, Los Alamos National Laboratory; Junyu Zhang, University of Minnesota, Twin Cities; Hang Liu, Stevens Institute of Technology; George Bosilca, University of Tennessee; Maurice Herlihy, Rodrigo Fonseca, Brown University.
TIFL: A Tier-based Federated Learning System,
Zheng Chai, George Mason University; Ahsan Ali, University of Nevada at Reno; Syed Zawad, University of Nevada at Reno;Stacey Truex, Georgia Institute of Technology; Ali Anwar, Nathalie Baracaldo, Yi Zhou, Heiko Ludwig, IBM Research - Almaden Feng Yan, University of Nevada at Reno; Yue Cheng, George Mason University.
Enabling Adaptivity
Session Chair: Ana Gainaru (Vanderbilt University, USA)
PAC: Paged Adaptive Coalescer for 3D-Stacked Memory,
Xi Wang, Texas Tech University; John D. Leidel, Tactical Computing Labs; Brody Williams, Yong Chen, Texas Tech University.
Aquila: Adaptive Parallel Computation of Graph Connectivity Queries,
Yuede Ji, H. Howie Huang, George Washington University.
ASA - The Adaptive Scheduling Architecture(short paper),
Abel Souza, Umeå University; Kristiaan Pelckmans, Uppsala University; Devarshi Ghoshal, Lavanya Ramakrishnan, Lawrence Berkeley National Laboratory; Johan Tordsson, Umeå University & Elastisys .
Orchestrating Fault Prediction with Live Migration and Checkpointing(short paper),
Subhendu Behera, North Carolina State University; Lipeng Wan, Oak Ridge National Laboratory; Frank Mueller, North Carolina State University; Matthew Wolf, Scott Klasky, Oak Ridge National Laboratory.
Exploiting GPUs
Session Chair: Shuaiwen Leon Song (University of Sydney, Australia)
KubeShare: A Framework to Manage GPUs as First-Class and Shared Resources in Container Cloud,
Ting-An Yeh, Hung-Hsin Chen, Jerry Chou, National Tsing Hua University.
Efficient GPU Memory Management for Nonlinear DNNs,
Donglin Yang, Dazhao Cheng, University of North Carolina at Charlotte.
gRemote: API-Forwarding Powered Cloud Rendering(short paper),
Dongjie Tang, Yun Wang, Linsheng Li, Shanghai Jiao Tong University; Jiacheng Ma, University of Michigan; Xue Liu, McGill University; Zhengwei Qi, Haibing Guan, Shanghai Jiao Tong University.
An Efficient Technique for Large Mini-batch Challenge of DNNs Training on Large Scale Cluster(short paper),
Akihiko Kasagi, Akihiro Tabuchi, Masafumi Yamazaki, Takumi Honda, Masahiro Miwa, Naoto Fukumoto, Tsuguchika Tabaru, Atsushi Ike, Kohta Nakashima, Fujitsu Laboratories ltd.
High Performance Networking
Session Chair: Swaroop Pophale (Oak Ridge National Lab, USA)
RECANS: Low-Latency Network Function Chains with Hierarchical State Sharing,
Jian Zhao, Shujun Zhuang, Jian Li, Haibing Guan, Shanghai Jiao Tong University.
Boosting FIB Caching Performance with Aggregation,
Garegin Grigoryan, Rochester Institute of Technology; Yaoqing Liu, Fairleigh Dickinson University; Minseok Kwon, Rochester Institute of Technology.
Closing Remarks