Wednesday, August 24th

Conference program

• 8:30-9:00 Opening Session: Brigitte Plateau, administratrice générale de Grenoble INP
• 9:00-10:00 Keynote 1
  Workload resampling – a new paradigm of using workload trace data for performance evaluation
  Dror Feitelson (the Hebrew university, Jerusalem, Israel)
• 10:00-10:30 Coffee Break
• 10:30-12:30 Session 1A | 5. Parallel and Distributed Data Management and Analytics (1∕2) / 9. Multicore and Manycore Parallelism (1∕2)
  • Efficient Large Outer Joins over MapReduce Long Cheng and Spyros Kotoulas
  • GraphIn: An Online High Performance Incremental Graph Processing Framework Dipanjan Sengupta, Narayanan Sundaram, Xia Zhu, Theodore L. Willke, Jeffrey Young, Matthew Wolf and Karsten Schwan
  • A Sharing-Aware Memory Management Unit for Online Mapping in Multi-Core Architectures Eduardo Cruz, Matthias Diener, Laércio L. Pilla and Philippe Navaux
  • GreenBST: Energy-efficient concurrent search tree Ibrahim Umar, Otto Anshus and Phuong Ha
• 10:30-12:30 Session 1B | 2. Performance and Power Modeling, Prediction and Evaluation
  • Addressing Material Science Challenges Using GPU-accelerated POWER8 Nodes Thorsten Hater, Paul F Baumeister, Dirk Pleiter, Rudolf Zeller, Marcel Bornemann, Markus Buehler and Benjamin Krill;
  • Performance Prediction and Ranking of SpMV Kernels on GPU Architectures Christoph Lehnert, Rudolf Berrendorf, Jan P. Ecker and Florian Mannuss
  • Power Consumption Modeling and Prediction in a Hybrid CPU-GPU-MIC Supercomputer Alina Sirbu and Ozalp Babaoglu
  • The Impact of Voltage-Frequency Scaling for the Matrix-Vector Product on the IBM POWER8 Sandra Catalan, A. Cristiano I. Malossi, Costas Bekas and Enrique S. Quintana-Orti
• 10:30-12:30 Session 1C | 6. Cluster and Cloud Computing
  • An Autonomic Parallel Strategy for the Projection of Ecological Niche Models in Heterogeneous Computational Environments Fernanda Oliveira Passos and Vinod Rebello
  • Slurm-V: Extending Slurm for Building Efficient HPC Cloud with SR-IOV and IVShmem Jie Zhang, Xiaoyi Lu, Sourav Chakraborty and Dhabaleswar Panda
  • Towards Network-Aware Service Placement in Community Network Micro-Clouds Mennan Selimi, Davide Vega, Felix Freitag and Luís Veiga
  • Industrial talk: Heating as a cloud-service, a position paper Yanik Ngoko (Qarnot Computing)
• 12:30-14:00 Lunch
• 14:00-16:00 Session 2A | 8. Parallel and Distributed Programming, Interfaces, Languages
  • Automatic Verification of Self-Consistent MPI Performance Guidelines Sascha Hunold, Alexandra Carpen-Amarie, Felix Donatus Lübbe and Jesper Larsson Träff
  • CBPQ: High Performance Lock-Free Priority Queue Anastasia Braginsky, Nachshon Cohen and Erez Petrank
  • ParallelME: A Parallel Mobile Engine to explore heterogeneity in mobile computing architectures Guilherme Andrade, Wilson de Carvalho, Alberto Albuquerque, Renato Utsch, Pedro Caldeira, Leonardo Rocha, Fabricio Ferracioli, Michael Frank, Dorgival Guedes and Renato Ferreira
  • Industrial talk: NCCL: optimized primitives for collective multi-GPU communication Gunter Röth (NVIDIA)
• 14:00-16:00 Session 2B | 3. Scheduling and Load Balancing (1∕2)
  • Controlling and Assessing Correlations of Cost Matrices in Heterogeneous Scheduling Louis-Claude Canon, Pierre-Cyrille Héam and Laurent Philippe
  • Cuboid Partitioning for Parallel Matrix Multiplication on Heterogeneous Platforms Olivier Beaumont, Lionel Eyraud-Dubois and Thomas Lambert;
  • FPT Approximation Algorithm for Scheduling with Memory Constraints Sébastien Morais, Eric Angel, Cédric Chevalier, Franck Ledoux and Damien Regnault
  • HeSP: a simulation framework for solving the task scheduling-partitioning problem on heterogeneous architectures Antón Rey, Francisco D. Igual and Manuel Prieto-Matías;
• 16:00-16:30 Coffee Break
• 16:30-18:00 Session 3A | 5. Parallel and Distributed Data Management and Analytics (2∕2)
  • High Performance Parallel Summed-Area Table Kernels for Multi-Core and Many-Core Systems Angelos Papatriantafyllou and Dimitris Sacharidis
  • Lightweight multi-language bindings for Apache Spark Luca Salucci, Daniele Bonetta and Walter Binder
  • Toward a General I/O Arbitration Framework for netCDF based Big Data Processing Jianwei Liao, Balazs Gerofi, Guo-Yuan Lien, Seiya Nishizawa, Takemasa Miyoshi, Hirofumi Tomita and Yutaka Ishikawa
• 16:30-18:00 Session 3B | 3. Scheduling and Load Balancing (2∕2)
  • Non-Preemptive Scheduling with Setup Times: a PTAS Klaus Jansen and Felix Land
  • Penalized Graph Partitioning for Static and Dynamic Load Balancing Tim Kiefer, Dirk Habich and Wolfgang Lehner
  • Scheduling MapReduce Jobs under Multi-Round Precedences Dimitris Fotakis, Ioannis Milis, Orestis Papadigenopoulos, Vasilis Vassalos and Georgios Zois
• 16:30-18:00 Session 3C | 7. Distributed Systems and Algorithms
  • Design and Verification of Distributed Phasers Karthik Murthy, Sri Raj Paul, Kuldeep S. Meel, Tiago Cogumbreiro and John Mellor-Crummey
  • Exploring Partial Replication to Improve Lightweight Silent Data Corruption Detection for HPC Applications Eduardo Berrocal, Leonardo Bautista Gomez, Sheng Di, Zhiling Lan and Franck Cappello
  • Industrial talk: Improved System Utilization respecting jobs needs under strict Power Budget Yiannis Georgiou, David Glesser, Dineshkumar Rajagopal (Atos/Bull)