Workshops and Conference Program

The Euro-Par 2015 program can be downloaded as PDF .


Workshops Program

Note that some workshops may hold shorter sessions within the slots allocated in the following table. Please check the full program made available on the workshop websites for details.

Monday, Aug 24, 2015

Time / Room EI 1 EI 2 EI 3 EI 3A EI 4 EI 5
09:00 - 10:30 Resilience Euro-EDUPAR OMHI PADABS BigDataCloud
10:30 - 11:00 Coffee Break
11:00 - 12:30 Resilience Euro-EDUPAR OMHI PADABS BigDataCloud
12:30 - 14:00 Lunch Break
14:00 - 16:00 LSDVE Resilience Euro-EDUPAR PADABS
16:00 - 16:30 Coffee Break
16:30 - 18:00 LSDVE Resilience Euro-EDUPAR PADABS
18:15 - 19:00 Workshop Organizers Meeting

Tuesday, Aug 25, 2015

Time / Room EI 1 EI 2 EI 3 EI 3A EI 4 EI 5
09:00 - 10:30 PELGA HeteroPar VHPC ROME REPPAR
10:30 - 11:00 Coffee Break
11:00 - 12:30 PELGA HeteroPar VHPC ROME REPPAR
12:30 - 14:00 Lunch Break
14:00 - 16:00 PELGA UCHPC HeteroPar REPPAR
16:00 - 16:30 Coffee Break
16:30 - 18:00 PELGA UCHPC HeteroPar REPPAR
19:00 Welcome Reception

Conference Program

Tuesday, Aug 25, 2015

19:00 Welcome Reception

Wednesday, Aug 26, 2015

08:45 - 09:00 Welcome Session, Opening Remarks
09:00 - 10:00 Keynote 1
10:00 - 10:30 Coffee Break
10:30 - 12:00 Session 1A
Topic 3
Session 1B
Topic 13
Session 1C
Topic 2
12:00 - 13:30 Lunch Break
13:30 - 15:30 Session 2A
Topic 3
Session 2B
Topic 13
Session 2C
Topic 5, Topic 6
15:30 - 16:00 Coffee Break
16:00 - 18:00 Session 3A
Topic 12, Topic 7
Session 3B
Topic 1, Topic 8
Session 3C
Topic 4

Thursday, Aug 27, 2015

09:00 - 10:00 Keynote 2
10:00 - 10:30 Coffee Break
10:30 - 12:00 Session 4: Distinguished Papers
12:00 - 13:30 Lunch Break
13:30 - 15:30 Session 5A
Topic 3
Session 5B
Topic 9, Topic 13
15:30 - 16:00 Coffee Break
16:00 - 17:30 Panel
Conference Banquet

Friday, Aug 28, 2015

09:00 - 10:30 Session 6A
Topic 10
Session 6B
Topic 9
Session 6C
Topic 12
10:30 - 11:00 Coffee Break
11:00 - 12:00 Keynote 3
12:00 - 12:30 Euro-Par 2016 Preview, Closing Session



Wednesday, Aug 26, 2015

Keynote 1 (Lecture hall EI 7), 09:00 - 10:00

Chair: Jesper Larsson Träff

Concurrent Systems: Hybrid Object Implementations and Abortable Objects
Michel Raynal


Session 1A (Lecture hall EI 7), 10:30 - 12:00

T3: Scheduling and Load Balancing

Chair: Rizos Sakellariou

Concurrent Priority Queues are not Good Priority Schedulers
Andrew Lenharth, Donald Nguyen and Keshav Pingali

Load Balancing Prioritized Tasks via Work-Stealing
Shams Imam and Vivek Sarkar

Moody Scheduling for Speculative Parallelization
Alvaro Estebanez, Diego R. Llanos, David Orden and Belen Palop


Session 1B (Lecture hall EI 9), 10:30 - 12:00

T13: Accelerator Computing

Chair: Jens Breitbart

Effective Barrier Synchronization on Intel Xeon Phi Coprocessor
Andrey Rodchenko, Andy Nisbet, Antoniu Pop and Mikel Lujan

High-Performance and Scalable Design of MPI-3 RMA on Xeon Phi Clusters
Mingzhe Li, Khaled Hamidouche, Xiaoyi Lu, Jian Lin and Dhabaleswar Panda

Iterative Sparse Triangular Solves for Preconditioning
Hartwig Anzt, Edmond Chow and Jack Dongarra


Session 1C (Lecture hall EI 10), 10:30 - 12:00

T2: Performance Modeling, Prediction and Evaluation

Chair: Felix Wolf

Online Automated Reliability Classification of Queueing Models for Streaming Processing using Support Vector Machines
Jonathan Beard, Cooper Epstein and Roger Chamberlain

Low-overhead detection of memory access patterns and their time evolution
Harald Servat, German Llort, Juan Gonzalez Garcia, Judit Giménez and Jesús Labarta

Automatic On-line Detection of MPI Application Structure with Event Flow Graphs
Xavier Aguilar, Karl Fuerlinger and Erwin Laure


Session 2A (Lecture hall EI 7), 13:30 - 15:30

T3: Scheduling and Load Balancing

Chair: Olivier Beaumont

Locality and Balance for Communication-Aware Thread Mapping in Multicore Systems
Matthias Diener, Eduardo Cruz, Marco Antonio Zanata Alves, Mohammad Alhakeem, Philippe Navaux and Hans-Ulrich Heiss

Hardware Round-Robin Scheduler for Single-ISA Asymmetric Multi-Core
Nikola Markovic, Daniel Nemirovsky, Veljko Milutinovic, Osman Unsal, Mateo Valero and Adrian Cristal

A Multi-Level Hypergraph Partitioning Algorithm using Rough Set Clustering
Foad Lotfifar and Matthew Johnson

A Duplicate-Free State-Space Model for Optimal Task Scheduling
Michael Orr and Oliver Sinnen


Session 2B (Lecture hall EI 9), 13:30 - 15:30

T13: Accelerator Computing

Chair: Roger Chamberlain

High Performance Multi-GPU SpMV for Multi-component PDE-based Applications
Ahmad Abdelfattah, Hatem Ltaief and David Keyes

Improving Performance of Convolutional Neural Networks by Separable Filters on GPU
Hao-Ping Kang and Che-Rung Lee

Systematic Fusion of CUDA Kernels for Iterative Sparse Linear System Solvers
Jose I. Aliaga, Joaquin Pérez and Enrique S. Quintana-Orti

Efficient Execution of Multiple CUDA Applications using Transparent Suspend, Resume and Migration
Taichiro Suzuki, Akira Nukada and Satoshi Matsuoka


Session 2C (Lecture hall EI 10), 13:30 - 15:30

T5: Parallel and Distributed Data Management

T6: Grid, Cluster and Cloud Computing

Chair: Frédéric Desprez

Performance impacts with Reliable Parallel File Systems at Exascale level
Ramon Nou, Alberto Miranda and Toni Cortes

Rapid Tomographic Image Reconstruction via Large-Scale Parallelization
Tekin Bicer, Doga Gursoy, Rajkumar Kettimuthu, Francesco De Carlo, Gagan Agrawal and Ian T. Foster

VMPlaceS A Generic Tool to Investigate and Compare VM Placement Algorithms
Adrien Lèbre, Jonathan Pastor and Mario Südholt

Software consolidation as an efficient energy and cost saving solution for a SaaS/PaaS cloud model
Alain Tchana, Noel de Palma, Ibrahim Safieddine and Daniel Hagimont


Session 3A (Lecture hall EI 7), 16:00 - 18:00

T7: Distributed Systems and Algorithms

T12: Numerical Methods and Applications

Chair: Marian Vajteršic

DFEP: Distributed Funding-based Edge Partitioning
Alessio Guerrieri and Alberto Montresor

A Connectivity Model for Agreement in Dynamic Systems
Carlos Gómez-Calzado, Arnaud Casteigts, Alberto Lafuente and Mikel Larrea

Behavioral Non-Portability in Scientific Numeric Computing
Yijia Gu, Thomas Wahl, Mahsa Bayati and Miriam Leeser

Exploiting Task-Based Parallelism in Bayesian Uncertainty Quantification
Panagiotis Hadjidoukas, Panagiotis Angelikopoulos, Lina Kulakova, Costas Papadimitriou and Petros Koumoutsakos


Session 3B (Lecture hall EI 9), 16:00 - 18:00

T1: Support Tools and Environments

T8: Parallel and Distributed Programming, Interfaces and Languages

Chair: Karl Fuerlinger

PR-STM: Priority Rule Based Software Transactions on the GPU
Qi Shen, Craig Sharp, William Blewitt, Gary Ushaw and Graham Morgan

Leveraging MPI-3 Shared-Memory Extensions for Efficient PGAS Runtime Systems
Huan Zhou, Kamran Idrees and José Gracia

Event-Action Mappings for Parallel Tools Infrastructures
Tobias Hilbrich, Martin Schulz, Holger Brunst, Joachim Protze, Bronis R. de Supinski and Matthias S. Mueller

MPI Thread-level Checking for MPI+OpenMP Applications
Emmanuelle Saillard, Patrick Carribault and Denis Barthou


Session 3C (Lecture hall EI 10), 16:00 - 18:00

T4: Architecture and Compilers

Chair: Michael Philippsen

Optimizing Task Parallelism with Library-Semantics-Aware Compilation
Peter Thoman, Stefan Moosbrugger and Thomas Fahringer

Automatic Data Layout Optimizations for GPUs
Klaus Kofler, Biagio Cosenza and Thomas Fahringer

Data Layout Optimization for Portable Performance
Kamal Sharma, Ian Karlin, Jeff Keasler, James McGraw and Vivek Sarkar


Thursday, Aug 27, 2015

Keynote 2 (Lecture hall EI 7), 09:00 - 10:00

Chair: Christian Lengauer

Runtime Aware Architectures
Mateo Valero


Session 4: Distinguished Papers (Lecture hall EI 7), 10:30 - 12:00

Chair: Martin Schulz

Fast Parallel Suffix Array on the GPU
Leyuan Wang, Sean Baxter and John Owens

A Practical Transactional Memory Interface
Shahar Timnat, Maurice Herlihy and Erez Petrank


Session 5A (Lecture hall EI 7), 13:30 - 15:30

T3: Scheduling and Load Balancing

Chair: Denis Trystram

On the Heterogeneity Bias of Cost Matrices when Assessing Scheduling Algorithms
Louis-Claude Canon and Laurent Philippe

Allocating jobs with periodic demands
Olivier Beaumont, Ikbel Belaid, Lionel Eyraud-Dubois and Juan-Angel Lorenzo-Del-Castillo

Non-preemptive Throughput Maximization for Speed-Scaling with Power-Down
Eric Angel, Evripidis Bampis, Vincent Chau and Kim Thang Nguyen

Scheduling tasks from selfish multi-tasks agents
Johanne Cohen and Fanny Pascual


Session 5B (Lecture hall EI 9), 13:30 - 15:30

T9: Multicore and Manycore Programming

T13: Accelerator Computing

Chair: Siegfried Benkner

Targeting the Parallella
Spiros N. Agathos, Alexandros Papadogiannakis and Vassilios V. Dimakopoulos

Accelerating Lattice Boltzmann Applications with OpenACC
Enrico Calore, Jiri Kraus, Sebastiano F. Schifano and Raffaele Tripiccione

A Multicore Parallelization of Continuous Skyline Queries on Data Streams
Tiziano De Matteis, Salvatore Di Girolamo and Gabriele Mencagli

A Fast and Scalable Graph Coloring Algorithm for Multi-core and Many-core Architectures
Georgios Rokos, Gerard Gorman and Paul Kelly


Panel (Lecture hall EI 7), 16:00 - 17:30

Moderator: Raffaele Tripiccione

The Future of Parallel, Distributed and High-Performance Computing, in Europe
Raffaele Tripiccione, Piero Altoe, Wolfgang Nagel, Keshav Pingali, Michel Raynal


Friday, Aug 28, 2015

Session 6A (Lecture hall EI 7), 09:00 - 10:30

T10: Theory and Algorithms for Parallel Computation

Chair: Robert Elsässer

Efficient Nested Dissection for Multicore Architectures
Dominique Lasalle and George Karypis

Scheduling Trees of Malleable Tasks for Sparse Linear Algebra
Abdou Guermouche, Loris Marchal, Bertrand Simon and Frédéric Vivien

Elastic Tasks: Unifying Task Parallelism and SPMD Parallelism with an Adaptive Runtime
Alina Sbirlea, Kunal Agrawal and Vivek Sarkar


Session 6B (Lecture hall EI 9), 09:00 - 10:30

T9: Multicore and Manycore Programming

Chair: Thomas Fahringer

Scalable Data-driven PageRank: Algorithms, System Issues & Lessons Learned
Joyce Whang, Andrew Lenharth and Inderjit Dhillon

A Composable Deadlock-free Approach to Object-based Isolation
Shams Imam, Jisheng Zhao and Vivek Sarkar

How Many Threads Will Be Too Many? On the Scalability of OpenMP Implementations
Christian Iwainsky, Sergei Shudler, Alexandru Calotoiu, Alexandre Strube, Michael Knobloch, Christian Bischof and Felix Wolf


Session 6C (Lecture hall EI 10), 09:00 - 10:30

T12: Numerical Methods and Applications

Chair: Wilfried Gansterer

Semi-Discrete Matrix-Free Formulation of 3D Elastic Full Waveform Inversion Modeling
Stephen Moore, Devi Sudheer Chunduri, Sergiy Zhuk, Tigran Tchrakian, Ewout van den Berg, Albert Akhriev, Alberto Costa Nogueira Junior, Andrew Rawlinson and Lior Horesh

10,000 performance models per minute - scalability of the UG4 simulation framework
Andreas Vogel, Alexandru Calotoiu, Alexandre Strube, Sebastian Reiter, Arne Nägel, Felix Wolf and Gabriel Wittum

Parallelization of an advection-diffusion problem arising in edge plasma physics using hybrid MPI/OpenMP programming
Matthieu Kuhn, Guillaume Latu, Nicolas Crouseilles and Stéphane Genaud


Keynote 3 (Lecture hall EI 7), 11:00 - 12:00

Chair: Luc Bougé

Self-stabilizing distributed data structures
Christian Scheideler


NEWS


31.08.2015

Keynote Talks (PDF) online


Workshop Organizers Meeting:
Monday, August 24th,
18:15 - 19:00, room EI 3A


13.08.2015

Conference program as PDF


07.07.2015

Conference program online


11.06.2015

BEWARE: Fake conference organizers try to sell you hotel rooms.