IPDPS 2017 CONFERENCE Home
SEARCH IPDPS
IPDPS 2017 Advance Program
Go
Proceedings & Mobile App Advance Program Workshops PhD Forum
The following program is slightly modified from the version posted on March 8, 2017. We apologize for any inconvenience due to changes in the assignment of papers to sessions. Please visit the IPDPS website regularly for updates. Authors who have corrections should send email
[email protected] giving full details.
2017 REGISTRATION
Industry & Exhibits Registration NVIDIA Tutorial Organization Program Committee Call for Papers (CLOSED)
MONDAY - 29 May 2017
March 27th Deadline for Advance Registration
DAYS • Monday • Tuesday • Wednesday • Thursday • Friday
Registration Details
MONDAY WORKSHOPS ALL DAY* * See each individual workshop program for schedule details
Student Travel (CLOSED) Author Resources Hotel GENERAL IPDPS INFO
IPDPS 2017 WORKSHOPS – MONDAY 29 MAY HCW
1
Heterogeneity in Computing Workshop
TWEETS BY @IPDPS
RAW
2
About IPDPS
Reconfigurable Architectures Workshop
Conference Archive Babbage Award
HiComb
3
Steering Committee Contact IPDPS
4
EduPar
NSF/TCPP W. on Parallel and Distributed Computing Education
5
ParLearning
Parallel and Distributed Computing for Machine Learning and Big Data Analytics
SPONSORS
Technical Committee on Parallel Processing IN COOPERATION WITH
SIGARCH & SIGHPC
6
PDCO
Parallel / Distributed Computing and Optimization
7
GABB
Graph Algorithms Building Blocks
8
AsHES
Accelerators and Hybrid Exascale Systems
9
HIPS
High Level Programming Models and Supporting Environments
APDCM
10
IEEE Computer Society Technical Committee on Computer Architecture IEEE Computer Society Technical Committee on Distributed Processing
Tweets by @IPDPS
High Performance Computational Biology
Proceedings Library
Advances in Parallel and Distributed Computational Models
11
HPPAC
High-Performance, Power-Aware Computing
12
HPBDC
High-Performance Big Data Computing
IPDPS @IPDPS Less than 10 days before the end of the reduced registration fee. Deadline March 27. ipdps.org/ipdps2018/2018… Mar 18, 2018
IPDPS @IPDPS
IPDPS 2018 (Vancouver 21-25 May) Advance Program & Author Resources to be posted by Valentine's Day Feb 12, 2018
IPDPS @IPDPS
Still a few days to submit your best papers to one of our workshops! ipdps.org/ipdps2018/2018… Feb 6, 2018
IPDPS @IPDPS
DIAMOND INDUSTRY PARTNER Reception 6:00 PM -7:30 PM
FOLLOW IPDPS
IPDPS - TCPP Welcome Reception
Tweets by @IPDPS IPDPS 2016 REPORT
TUESDAY - 30 May 2017 DAYS • Monday • Tuesday • Wednesday • Thursday • Friday
® Intel, the Intel logo are trademarks or registered trademarks of Intel Corporation or its subsidiaries in the United States and other Countries.
GOLD INDUSTRY PARTNER
Opening Session 8:00 AM - 8:30 AM
Opening Session
Keynote Session 8:30 AM - 9:30 AM
Keynote Speech
May 23-27, 2016 Chicago Hyatt Regency Chicago, Illinois USA
Session Chair: Marc Snir Tandy Warnow University of Illinois Computational Challenges in Constructing the Tree of Life Abstract: Estimating the Tree of Life is one of the grand computational challenges in Science, and has applications to many areas of science and biomedical research. Read more
Morning Break 9:30 AM -10:00 AM PhD Forum Starts on Tuesday
PhD Forum Posters
All Day
Industry Exhibits
Parallel Technical Sessions 1, 2, 3, & 4 10:00 AM - 12:00 PM
Sesson 1
On Display All Day Tuesday and Wednesday More details to be announced
Graph Algorithms Session Chair: Joseph Jaja Monitoring Properties of Large, Distributed, Dynamic Graphs Gal Yehuda, Daniel Keren and Islam Akaria Parallel Construction of Suffix Trees and the All-Nearest-SmallerValues Problem Patrick Flick and Srinivas Aluru The Reverse Cuthill-McKee Algorithm in Distributed-Memory Ariful Azad, Mathias Jacquelin, Aydin Buluc and Esmond Ng SlimSell: A Vectorizable Graph Representation for Breadth-First Search Maciej Besta, Florian Marending, Edgar Solomonik and Torsten Hoefler Session 2
Computational Biology Session Chair: Cynthia A Phillips SWhybrid: A Hybrid-Parallel Framework for Large-Scale Protein Sequence Haidong Lan, Weiguo Liu, Yongchao Liu and Bertil Schmidt PUNAS: A Parallel Ungapped-Alignment-Featured Seed Verification Algorithm for Next-Generation Sequencing Read Alignment Yuandong Chan, Kai Xu, Haidong Lan, Weiguo Liu, Yongchao Liu and Bertil Schmidt Eliminating Irregularities of Protein Sequence Search on Multicore Architectures Jing Zhang, Sanchit Misra, Hao Wang and Wu-Chun Feng Communication Optimization on GPU: A Case Study of Sequence Alignment Algorithms Jie Wang, Xinfeng Xie and Jason Cong Session 3
Caches Session Chair: Sanjeev Baskiyar Elastic-Cache: GPU Cache Architecture for Efficient Fine- and Coarse-Grained Cache-Line Management Bingchao Li, Jizhou Sun, Murali Annavaram and Nam Sung Kim Content-Aware Non-Volatile Cache Replacement Qi Zeng and Jih-Kwon Peir DEFT-Cache: A Cost-effective and Highly Reliable SSD Cache for RAID Storage Jiguang Wan, Wei Wu, Ling Zhan, Qing Yang, Xiaoyang Qu and Changsheng Xie Adaptive Software Caching for Efficient NVRAM Data Persistence Pengcheng Li, Dhruva R. Chakrabarti, Chen Ding and Liang Yuan Session 4
Cloud & OS Session Chair: Ümit Çatalyürek Container-Based Cloud Platform for Mobile Computation Offloading Song Wu, Chao Niu, Jia Rao, Hai Jin and Xiaohai Dai Enhancing Datacenter Resource Management through Temporal Logic Constraints Hao He, Jiang Hu and Dilma Da Silva High-Performance Virtual Machine Migration Framework for MPI Applications on SR-IOV enabled InfiniBand Clusters Jie Zhang, Xiaoyi Lu and Dhabaleswar K. (DK) Panda Argo NodeOS: Toward Unified Resource Management for Exascale Swann Perarnau, Judicael A. Zounmevo, Matthieu Dreher, Brian C. Van Essen, Roberto Gioiosa, Kamil Iskra, Maya B. Gokhale, Kazutomo Yoshii and Pete Beckman Parallel Technical Sessions 5, 6, 7, & 8 1:30 PM - 3:30 PM
Session 5
Distributed Algorithms Session Chair: Pierre Fraigniaud Rational Fair Consensus in the GOSSIP Model Andrea Clementi, Luciano Gualà, Guido Proietti and Giacomo Scornavacca Leader Election in a Smartphone Peer-to-Peer Network Calvin Newport Leader Election in Asymmetric Labeled Unidirectional Rings Karine Altisen, Ajoy K. Datta, Stéphane Devismes, Anaïs Durand and Lawrence L. Larmore Tight Load Balancing via Randomized Local Search Petra Berenbrink, Peter Kling, Christopher Liaw and Abbas Mehrabian Session 6
Numerical Simulation Session Chair: Alex Pothen Large Scale Manycore-Aware PIC Simulation with Efficient Particle Binning Hiroshi Nakashima, Yoshiki Summura, Keisuke Kikura and Yohei Miyake Optimization and parallelization of B-spline based orbital evaluations in QMC on multi/many-core shared memory processors Amrita Mathuriya, Ye Luo, Anouar Benali, Luke Shulenburger and Jeongnim Kim One-Way Wave Equation Migration at Scale on GPUs using Directive-Based Programming Kshitij Mehta, Maxime Hugues, Oscar Hernandez, Henri Calandra and David E. Bernholdt Towards highly scalable Ab Initio Molecular Dynamics (AIMD) simulations on the Intel Knights Landing manycore processor Eric Bylaska, Wibe De Jong and Mathias Jacquelin Session 7
Novel Architectures Session Chair: CJ Newburn General Purpose Task-Dependence Management Hardware for Task-based Dataflow Programming Models Xubin Tan, Jaume Bosch, Miquel Vidal, Carlos Álvarez, Daniel Jiménez-González, Eduard Ayguadé and Mateo Valero Accelerating Graph and Machine Learning Workloads Using a Shared Memory Multicore Architecture with Auxiliary Support for inHardware Explicit Messaging Halit Dogan, Masab Ahmad, Farrukh Hijaz, Brian Kahne, Peter Wilson and Omer Khan Respin: Rethinking Near-Threshold Multiprocessor Design with NonVolatile Memory Xiang Pan, Anys Bacha and Radu Teodorescu MOCHA: Morphable locality and compression aware architecture for convolutional neural networks Syed M. A. H. Jafri, Ahmed Hemani, Kolin Paul and Naeem Abbas
Session 8
Performance Modeling and Tuning Session Chair: Jeffrey Vetter Autotuning Stencil Computations with Structural Ordinal Regression Learning Biagio Cosenza, Juan J. Durillo, Stefano Ermon and Ben Juurlink Capability Models for Manycore Memory Systems: A Case-Study with Xeon Phi KNL Sabela Ramos and Torsten Hoefler Apollo: Reusable Models for Fast, Dynamic Tuning of InputDependent Code David Beckingsale, Olga Pearce, Ignacio Laguna and Todd Gamblin Generating Performance Models for Irregular Applications Ryan Friese, Nathan R. Tallent, Abhinav Vishnu, Darren J. Kerbyson and Adolfy Hoisie Afternoon Break 3:30 PM - 4:00 PM Parallel Technical Sessions 9, 10, 11, & 12 4:00 PM - 6:00 PM
Session 9
Communication & Coordination Session Chair: Sergio Rajbaum Bounded Reordering Allows Efficient Reliable Message Transmission Keishla D Ortiz-Lopez and Jennifer L. Welch Dynamic Adaptation in Wireless Networks Under Comprehensive Interference Via Carrier Sense Magnus M. Halldórsson, Tigran Tonoyan, Yuexuan Wang and Dongxiao Yu Fault-Tolerant Online Packet Scheduling on Parallel Channels Paweł Garncarek, Tomasz Jurdziński and Krzysztof Loryś Corrected Gossip Algorithms for Fast Reliable Broadcast on Unreliable Systems Torsten Hoefler, Amnon Barak, Amnon Shiloh and Zvi Drezner Session 10
Tools 1 Session Chair: Murali Annavaram Dr-BW: Identifying Bandwidth Contention in NUMA Architectures with Supervised Learning Hao Xu, Shasha Wen, Alfredo Gimenez, Todd Gamblin and Xu Liu Data Centric Performance Measurement Techniques for Chapel Programs Hui Zhang and Jeffrey K. Hollingsworth A Parallel FastTrack Data Race Detector on Multi-core Systems Young Wn Song and Yann-Hang Lee Localized Fault Recovery for Nested Fork-Join Programs Gokcen Kestor, Sriram Krishnamoorthy and Wenjing Ma Session 11
Networks Session Chair: Matthias Blumrich Exploring DataVortex Systems for Irregular Applications Roberto Gioiosa, Antonino Tumeo, Jian Yin, Thomas Warfel, David Haglin and Santiago Betelu DC2-MTCP: Light-weight Coding for Efficient Multi-path Transmission in Data Center Network Jiyan Sun, Yan Zhang, Xin Wang, Shihan Xiao, Zhen Xu, Hongjing Wu, Xin Chen and Yanni Han A Scalable and Resilient Microarchitecture Based on Multiport Binding for High-radix Router Design Yi Dai, Kefei Wang, Gang Qu, Liquan Xiao, Dezun Dong and Xingyun Qi Partitioning Low-diameter Networks to Eliminate Inter-job Interference Nikhil Jain, Abhinav Bhatele, Xiang Ni, Todd Gamblin and Laxmikant V. Kale Session 12
Libraries & Frameworks Session Chair: Costin Iancu Accelerating Spark Datasets by inlining deserialization Jan Wróblewski, Kazuaki Ishizaki, Hiroshi Inoue and Moriyoshi Ohara MRapid: An Efficient Short Job Optimizer on Hadoop Hong Zhang, Hai Huang and Liqiang Wang Accommodating Thread-Level Heterogeneity in Coupled Parallel Applications Samuel K. Gutiérrez, Kei Davis, Dorian C. Arnold, Randal S. Baker, Robert W. Robey, Patrick McCormick, Daniel Holladay, Jon A. Dahl, R. Joe Zerr, Florian Weik and Christoph Junghans Multi-GPU Graph Analytics Yuechao Pan, Yangzihao Wang, Yuduo Wu, Carl Yang and John D. Owens Industry Tutorial 7:00 PM -9:00 PM
NVIDIA Tutorial/Workshop: Deep Learning Presenter: Julie Bernauer Senior Solutions Architect for Machine Learning and Deep Learning at NVIDIA Corporation For details, see here (PDF).
WEDNESDAY - 31 May 2017 DAYS • Monday • Tuesday • Wednesday • Thursday • Friday Keynote Session 8:30 AM – 9:30 AM
Keynote Speech Session Chair: Michela Taufer Mark Seager Intel A scalable system architecture to addressing the next generation of predictive simulation workflows with coupled compute and data intensive applications Abstract: Trends in the emerging digital economy are pushing the virtual representation of products and services. Read more
Morning Break 9:30 AM - 10:00 AM PhD Forum Starts on Tuesday
PhD Forum Posters On Display All Day Tuesday and Wednesday More details to be announced
All Day
Industry Exhibits
Parallel Technical Sessions 13, 14, 15, & 16 10:00 AM - 12:00 PM
Session 13
Motion Planning & Similarity Search Session Chair: Allan Sussman Fault-Tolerant Robot Gathering Problems on Graphs With Arbitrary Appearing Times Manuel Alcántara, Armando Castañeda, David Flores-Peñaloza and Sergio Rajsbaum Distributed Vehicle Routing Approximation Akhil Krishnan, Mikhail Markov and Borzoo Bonakdarpour O(log N)-Time Complete Visibility for Asynchronous Robots with Lights Gokarna Sharma, Ramachandran Vaidyanathan, Jerry L. Trahan, Costas Busch and Suresh Rai Similarity Search on Automata Processors Vincent T. Lee, Justin Kotalik, Carlo C. del Mundo, Armin Alaghi, Luis Ceze and Mark Oskin Session 14
Applications Session Chair: Timothy G Mattson 26 PFLOPS Stencil Computations for Atmospheric Modeling on Sunway TaihuLight Yulong Ao, Chao Yang, Xinliang Wang, Wei Xue and Haohuan Fu Yulong Ao, Chao Yang, Xinliang Wang, Wei Xue, Haohuan Fu, Fangfang Liu, Lin Gan, Ping Xu and Wenjing Ma Image-Domain Gridding on Graphics Processors Bram Veenboer, Matthias Petschow and John W. Romein Aces4: A Platform for Computational Chemistry Calculations with Extremely Large Block-Sparse Arrays Beverly A. Sanders, Jason N. Byrd, Nakul Jindal, Victor F. Lotrich, Dmitry Lyakh, Ajith Perera and Rodney J. Bartlett PhiOpenSSL: Using Xeon Phi Coprocessor for Efficient Cryptography Calculation Shun Yao and Dantong Yu Session 15
Tools 2 Session Chair: Jeff Hollingsworth Directive-Based Partitioning and Pipelining for Graphics Processing Units Xuewen Cui, Thomas R. W. Scogland, Bronis R. de Supinski and Wu-chun Feng ScalaIOExtrap: Elastic I/O Tracing and Extrapolation Xiaoqing Luo, Frank Mueller, Philip Carns, Jonathan Jenkins, Robert Latham, Robert Ross and Shane Snyder SimProf: A Sampling Framework for Data Analytic Workloads Jen-Cheng Huang, Lifeng Nai, Pranith Kumar, Hyojong Kim and Hyesoon Kim PaPar: A Parallel Data Partitioning Framework for Big Data Applications Hao Wang, Jing Zhang, Da Zhang, Sarunya Pumma and Wu-Chun Feng
Session 16
Data and Graph Analytics Session Chair: Aydin Buluc swDNN: A Library for Accelerating Deep Learning Applications on Sunway TaihuLight Jiarui Fang, Haohuan Fu, Wenlai Zhao, Bingwei Chen, Weijie Zheng and Guangwen Yang Community Detection on the GPU Md. Naim, Fredrik Manne, Mahantesh Halappanavar and Antonino Tumeo Scalable Graph Traversal on Sunway TaihuLight with Ten Million Cores Heng Lin, Xiongchao Tang, Bowen Yu, Youwei Zhuo, Wenguang Chen, Jidong Zhai, Wanwang Yin and Weimin Zheng Partitioning Trillion-edge Graphs in Minutes George M. Slota, Sivasankaran Rajamanickam, Kamesh Madduri and Karen Devin
Parallel Technical Sessions 17, 18, 19, & 20 1:30 PM – 3:30 PM
Session 17
Linear Algebra Session Chair: Olivier Baumont Generating Families of Practical Fast Matrix Multiplication Algorithms Jianyu Huang, Leslie Rice, Devin A. Matthews and Robert A. van de Geijn Bidiagonalization with Parallel Tiled Algorithms Mathieu Faverge, Julien Langou, Yves Robert and Jack Dongarra Communication-Avoiding Parallel Algorithms for Solving Triangular Systems of Linear Equations Tobias Wicky, Edgar Solomonik and Torsten Hoefler A work-efficient parallel sparse matrix-sparse vector multiplication algorithm Ariful Azad and Aydin Buluç Session 18
Power Management Session Chair: Frank Mueller Power Efficient Sharing-Aware GPU Data Management Abdulaziz Tabbakh, Murali Annavaram and Xuehai Qian Fly-Over: A Light-Weight Distributed Power-Gating Mechanism for Energy-Efficient Networks-on-Chip Rahul Boyapati, Jiayi Huang, Ningyuan Wang, Kyung Hoon Kim, Ki Hwan Yum and Eun Jung Kim RCube: A Power Efficient and Highly Available Network for Data Centers Zhenhua Li and Yuanyuan Yang Cooling-Aware Job Scheduling and Node Allocation for Overprovisioned HPC Systems Thang Cao, Wei Huang, Yuan He and Masaaki Kondo Session 19
Scheduling Session Chair: Emmanuel Jeannot Algorithms for hierarchical and semi-partitioned parallel scheduling Vincenzo Bonifaci, Gianlorenzo D'Angelo and Alberto MarchettiSpaccamela Efficient and Deterministic Scheduling for Parallel State Machine Replication Odorico M. Mendizabal, Rudá S. T. De Moura, Fernando Luís Dotti and Fernando Pedone Dynamic memory-aware task-tree scheduling Guillaume Aupy, Clément Brasseur and Loris Marchal Approximation Proofs of a Fast and Efficient List Scheduling Algorithm for Task-Based Runtime Systems on Multicores and GPUs Olivier Beaumont, Lionel Eyraud-Dubois and Suraj Kumar Session 20
Code Optimization Session Chair: Stephen Olivier Automatic Collapsing of Non-Rectangular Loops Philippe Clauss, Ervin Altıntaş and Matthieu Kuhn HOMP: Automated Distribution of Parallel Loops and Data in Highly Parallel Accelerator-Based Systems Yonghong Yan, Jiawen Liu, Kirk W. Cameron and Mariam Umar Multigrain Parallelism: Bridging Coarse-Grain Parallel Programs and Fine-Grain Event-Driven Multithreading Jaime Arteaga, Stéphane Zuckerman and Guang R. Gao Improving the integration of task nesting and dependencies in OpenMP Josep M. Perez, Vicenç Beltran, Jesus Labarta and Eduard Ayguade Afternoon Break 3:30 PM - 4:00 PM All Conference Plenary Event 4:00 PM – 5:00 PM
Report to IPDPS Community
PhD Forum Special Session 5:30 PM – 7:00 PM
Posters on Display
Reception 6:00 PM – 7:00 PM
Details to be announced
Symposium Banquet After 7:00 PM
Details to be announced
Updates on the road ahead for IPDPS
IPDPS Attendees Invited to View Posters and Talk with Student Presenters
THURSDAY - 1 June 2017 DAYS • Monday • Tuesday • Wednesday • Thursday • Friday Keynote Session 8:30 AM - 9:30 AM
Keynote Speech Session Chair: Viktor Prassana Mateo Valero Barcelona Supercomputing Center Runtime Aware Architectures Abstract: In the last years the traditional ways to keep the increase of hardware performance to the rate predicted by the Moore's Law vanished. When uni-cores were the... Read More
Morning Break 9:30 AM - 10:00 AM PhD Forum
PhD Forum Student Program Details to be announced
All Day
Industry Exhibits
PLENARY SESSION: Best Papers 10:00 AM - 12:00 PM
Best Papers
Parallel Technical Sessions 21, 22, 23 & 24 1:30 PM - 3:30 PM
Session 21
Session Chair: Marc Snir Reducing Pagerank Communication via Propagation Blocking Scott Beamer, Krste Asanoviç and David Patterson Clustering Throughput Optimization on the GPU Michael Gowanlock, Cody M. Rude, David M. Blair, Justin D. Li and Victor Pankratius FlexVC: Flexible Virtual Channel Management in Low-Diameter Networks Pablo Fuentes, Enrique Vallejo, Ramón Beivide, Cyriel Minkenberg and Mateo Valero Relaxations for High-Performance Message Passing on Massively Parallel SIMT Processors Benjamin Klenk, Holger Fröning, Hans Eberle and Larry Dennison
Algorithms Session Chair: Mathias Jaquelin The SEPO Model of Computation to Enable Larger-than-Memory Hash Tables for GPU-accelerated Big Data Analytics Reza Mokhtari and Michael Stumm Elastic Consistent Hashing for Distributed Storage Systems Wei Xie and Yong Chen An NlogN Parallel Fast Direct Solver for Kernel Metrices Chenhan D. Yu, William March and George Biros A robust parallel preconditioner for indefinite systems using hierarchical matrices and randomized sampling Pieter Ghysels, Xiaoye Sherry Li, Christopher Gorman and FrancoisHenry Rouet Session 22
Coordination Session Chair: Phil Carns FFQ: A Fast Single-Producer/Multiple-Consumer Concurrent FIFO Queue Sergei Arnautov, Pascal Felber, Christof Fetzer and Bohdan Trach Scalable Lock-Free Vector with Combining Ivan Walulya and Philippas Tsigas Automatic-Signal Monitors with Multi-Object Synchronization Wei-Lun Hung and Vijay K. Garg Optimal Algorithms for a Mesh-Connected Computer with Limited Additional Global Bandwidth Yujie An and Quentin Stout Session 23
Power Management 2 Session Chair: Bronis de Supinski An Adaptive Core-specific Runtime for Energy Efficiency Sridutt Bhalachandra, Allan Porterfield, Stephen Olivier and Jan Prins Production Hardware Overprovisioning: Real-world Performance Optimization using an Extensible Power-aware Resource Management Framework Ryuichi Sakamoto, Thang Cao, Masaaki Kondo, Koji Inoue, Masatsugu Ueda, Tapasya Patki, Daniel Ellsworth, Barry Rountree and Martin Schulz Co-Run Scheduling with Power Cap on Integrated CPU-GPU Systems Qi Zhu, Bo Wu, Xipeng Shen, Li Shen and Zhiying Wang Characterizing and Modeling Power and Energy for Extreme-Scale In-situ Visualization Vignesh Adhinarayanan, Wu-Chun Feng, David Rogers, James Ahrens and Scott Pakin Session 24
MPI Session Chair: Beverly Sanders Application Level Reordering of Remote Direct Memory Access Operations Costin Iancu and Wim Lavrijsen Toucan - A Translator for Communication Tolerant MPI Applications Sergio Martin, Marsha J. Berger and Scott B. Baden Memory Compression Techniques for Network Address Management in MPI Yanfei Guo, Charles Archer, Michael Blocksome, Scott Parker, Wesley Bland, Ken Raffenetti and Pavan Balaji Transparent Caching for RMA Systems Salvatore Di Girolamo, Flavio Vella and Torsten Hoefler Application Level Reordering of Remote Direct Memory Access Operations Costin Iancu and Wim Lavrijsen
Afternoon Break 3:30 PM - 4:00 PM Parallel Technical Sessions 25, 26, 27 & 28 4:00 PM - 6:00 PM
Session 25
ML & Tensors Session Chair: Torsten Hoefler When Neurons Fail El Mahdi El Mhamdi and Rachid Guerraoui On Optimizing Distributed Tucker Decomposition for Dense Tensors Venkatesan T. Chakaravarthy, Jee W. Choi, Douglas J. Joseph, Xing Liu, Prakash Murali, Yogish Sabharwal and Dheeraj Sreedhar Model-Driven Sparse CP Decomposition for High-Order Tensors Jiajia Li, Jee Choi, Ioakeim Perros, Jimeng Sun and Richard Vuduc Sparse Tensor Factorization on Many-Core Processors with HighBandwidth Memory Shaden Smith, Jongsoo Park and George Karypis
Session 26
Resource Management Session Chair: Pavan Balaji Proximity-Aware Balanced Allocations in Cache Networks Ali Pourmiri, Mahdi Jafari Siavoshani and Seyed Pooya Shariatpanahi Addressing Performance Heterogeneity in MapReduce Clusters with Elastic Tasks Wei Chen, Jia Rao and Xiaobo Zhou Autonomic Resource Management for Program Orchestration in Large-scale Data Analysis Masahiro Tanaka, Kenjiro Taura and Kentaro Torisawa Mimir: Memory-Efficient and Scalable MapReduce for Large Supercomputing Systems Tao Gao, Yanfei Guo, Boyu Zhang, Pietro Cicotti, Yutong Lu, Pavan Balaji and Michela Taufer Session 27
Compression & Memoization Session Chair: Yves Robert Elastic Data Compression with Improved Performance and Space Efficiency for Flash-based Storage Systems Bo Mao, Hong Jiang, Suzhen Wu, Yaodong Yang and Zaifa Xi E²MC: Entropy Encoding based Memory Compression for GPUs Sohan Lal, Jan Lucas and Ben Juurlink Significantly Improving Lossy Compression for Scientific Data Sets Based on Multidimensional Prediction and Error-Controlled Quantization Dingwen Tao, Sheng Di, Zizhong Chen and Franck Cappello ATM: Approximate Task Memoization in the Runtime System Iulian Brumar, Marc Casas, Miquel Moretó Planas, Gurindar S. Sohi and Mateo Valero Cortés Session 28
Persistent Memory Session Chair: Swann Perarneau Design and Implementation of Papyrus: Parallel Aggregate Persistent Storage Jungwon Kim, Kittisak Sajjapongse, Seyong Lee and Jeffrey Vetter Language-Based Optimizations for Persistence on Nonvolatile Main Memory Systems Joel Denny, Seyong Lee and Jeffrey Vetter MetaKV: A Key-Value Store for Metadata Management of Distributed Burst Buffers Teng Wang, Adam Moody, Yue Zhu, Kathryn Mohror, Kento Sato, Tanzima Islam and Weikuan Yu Parallelism and Garbage Collection aware I/O Scheduler with Improved SSD Performance Jiayang Guo, Yiming Hu and Bo Mao
FRIDAY - 2 June 2017 DAYS • Monday • Tuesday • Wednesday • Thursday • Friday FRIDAY WORKSHOPS ALL DAY* * See each individual workshop program for schedule details
IPDPS 2017 WORKSHOPS – FRIDAY 2 JUNE 13
CHIUW
Chapel Implementers and Users Workshop
LSPP
Large-Scale Parallel Processing: Practices and Experiences (cancelled)
14
PDSEC
Parallel and Distributed Scientific and Engineering Computing
15
JSSPP
Job Scheduling Strategies for Parallel Processors Proposal
16
DPDNS
Dependable Parallel, Distributed and Network-centric Systems
17
IPDRM
Emerging Parallel and Distributed Runtime Systems and Middleware
18
iWAPT
International Workshop on Automatic Performance Tunings
19
ParSocial
Parallel and Distributed Processing for Computational Social System
20
BigDataEco
Big Data Regional Innovation Hubs and Spokes: Accelerating the Big Data Innovation Ecosystem
21
GraML
Graph Algorithms and Machine Learning
22
EMBRACE
Evolvable Methods for Benchmarking Realism and Community Engagement
23
REPPAR
Reproducibility in Parallel Computing
IPDPS 2017 Tuesday KEYNOTE SPEAKER Tandy Warnow University of Illinois Computational Challenges in Constructing the Tree of Life Abstract: Estimating the Tree of Life is one of the grand computational challenges in Science, and has applications to many areas of science and biomedical research. Despite intensive research over the last several decades, many problems remain inadequately solved. Relatively small datasets can take hundreds of CPU years (e.g., the Avian Phylogenomics Project analysis of just 48 bird genomes used more than 200 CPU years to construct its tree), and larger datasets will require much more time. Thus, the estimation of the Tree of Life, which contains millions of species each with a genome containing millions of nucleotides, will depend on both novel algorithmic designs and effective use of high performance and distributed computing platforms. Bio: Tandy Warnow is the Founder Professor of Engineering at the University of Illinois at UrbanaChampaign, where she is a faculty member in Computer Science and in Bioengineering. Tandy received her PhD in Mathematics at UC Berkeley under the direction of Gene Lawler, and did postdoctoral training with Simon Tavaré and Michael Waterman at USC. She received the National Science Foundation Young Investigator Award in 1994, the David and Lucile Packard Foundation Award in Science and Engineering in 1996, a Radcliffe Institute Fellowship in 2006, and a Guggenheim Foundation Fellowship for 2011. She was elected a fellow of the Association for Computing Machinery (ACM) in 2015, and of the International Society for Computational Biology (ISCB) in 2017. Her current research focuses on phylogeny and alignment estimation for very large datasets (10,000 to 1,000,000 sequences), estimating species trees and phylogenetic networks from collections of gene trees, and metagenomics. http://ws.engr.illinois.edu/directory/viewphoto.aspx?id=44946&s=215&type=portrait
IPDPS 2017 Wednesday KEYNOTE SPEAKER Mark Seager Intel A scalable system architecture to addressing the next generation of predictive simulation workflows with coupled compute and data intensive applications Abstract: Trends in the emerging digital economy are pushing the virtual representation of products and services. Creating these digital twins requires a combination of real time data ingestion, simulation of physical products under real world conditions, service delivery optimization and data analytics as well as ML/DL anomaly detection and decision making. Quantification of Uncertainty in the simulations will also be a compute and data intensive workflow that will drive the simulation improvement cycle. Future high-end computing systems designs need to comprehend these types of complex workflows and provide a flexible framework for optimizing the design and operations under dynamic load conditions for them. Bio: Mark leads Intel® Scalable System Framework (SSF) strategy for Intel’s Scalable Datacenter Solutions Group and Directs Intel’s contributions to the Open Compute Platforms (opencompute.org). At Intel he is working on an ecosystem approach to develop and build HPC systems with Exascale capabilities. Before moving to Intel, he was assistant department head for Advanced Computing Technology within the Integrated Computing and Communications department at Lawrence Livermore National Laboratory. He joined LLNL in 1983 and has been working in parallel processing ever since. Mark was instrumental in the development and deployment of the BlueGene/L and Purple systems at LLNL for the Advanced Simulation and Computing program within the USA National Nuclear Security Administration. He was also instrumental in the development and deployment of ASC White and Blue-Pacific systems and numerous world class Linux clusters. He has won numerous awards including the prestigious Edward Teller Award for "major contributions to the state-of-the-art in high performance computing." In 2015 he was promoted to Intel Fellow. Mark and Jan Seager breed and raise Arabian horses, with one national championship win in 2013. He received a BS degree in mathematics and astrophysics from the University of New Mexico at Albuquerque and a PhD in numerical analysis from the University of Texas at Austin.
IPDPS 2017 Thursday KEYNOTE SPEAKER Mateo Valero Barcelona Supercomputing Center Runtime Aware Architectures Abstract: In the last years the traditional ways to keep the increase of hardware performance to the rate predicted by the Moore's Law vanished. When uni-cores were the norm, hardware design was decoupled from the software stack thanks to a well-defined Instruction Set Architecture (ISA). This simple interface allowed developing applications without worrying too much about the underlying hardware, while computer architects proposed techniques to aggressively exploit Instruction-Level Parallelism (ILP) in superscalar processors. Current multi-cores are designed as simple symmetric multiprocessors on a chip. While these designs are able to compensate the clock frequency stagnation, they face multiple problems in terms of power consumption, programmability, resilience or memory. The solution is to give more responsibility to the runtime system and to let it tightly collaborate with the hardware. The runtime has to drive the design of future multi-cores architectures. In this talk, we introduce an approach towards a Runtime-Aware Architecture (RAA), a massively parallel architecture designed from the runtime's perspective. RAA aims at supporting the activity the parallel runtime system in three ways: First, to enable fine-grain tasking and support the opportunities it offers; second, to improve the performance of the memory subsystem by exposing hybrid hierarchies to the runtime system and, third, to improve performance by using vector units. During the talk, we will give a general overview of the problems RAA aims to solve and provide some examples of hardware components supporting the activity of the runtime system in the context of multi-core chips. Bio: Mateo Valero is a professor in the Computer Architecture Department at UPC, in Barcelona. His research interests are focused on high performance architectures. He has published approximately 700 papers, has served in the organization of more than 300 International Conferences and has given more than 500 invited talks. He is the director of the Barcelona Supercomputing Centre, the National Centre of Supercomputing in Spain. Prof. Valero has been honored with several awards, including the Eckert-Mauchly Award 2007 by the IEEE and ACM; Seymour Cray Award 2015 by IEEE; Harry Goode Award 2009 by IEEE: ACM Distinguished Service Award 2012; Euro-Par Achievement Award 2015; the Spanish National Julio Rey Pastor award; the Spanish National Award “Leonardo Torres Quevedo”; the “King Jaime I” given by Generalitat Valenciana; the Research Award by the Catalan Foundation for Research and Innovation; and the “Aragón Award” 2008 given by the Government of Aragón. He has been named Honorary Doctor by the Universities of Chalmers, Belgrade, Las Palmas de Gran Canaria, Zaragoza, Complutense de Madrid, Cantabria, Granada and by the University of Veracruz and CINVESTAV (Mexico). He is a "Hall of the Fame" member of the ICT European Program (selected as one of the 25 most influential European researchers in IT during the period 19832008, Lyon, November 2008); Honoured with Creu de Sant Jordi 2016 by Generalitat de Catalunya. It is the highest recognition granted by the Government. In December 1994, Professor Valero became a founding member of the Royal Spanish Academy of Engineering. In 2005 he was elected Correspondant Academic of the Spanish Royal Academy of Science, in 2006 a member of the Royal Spanish Academy of Doctors, in 2008 a member of the Academia Europaea and in 2012 Correspondant Academic of the Mexican Academy of Sciences. He is a Fellow of the IEEE, Fellow of the ACM and an Intel Distinguished Research Fellow. In 1998 he won a “Favourite Son” Award of his home town, Alfamén (Zaragoza) and in 2006, his native town of Alfamén named their Public College after him.
Copyright © IPDPS. All rights reserved.
REPORT ON IPDPS 2016