Euro-Par 2015: Parallel Processing: 21st International Conference on Parallel and Distributed Computing, Vienna, Austria, August 24-28, 2015, Proceedings

Front Matter....Pages I-XXXV
Front Matter....Pages 1-1
Concurrent Systems: Hybrid Object Implementations and Abortable Objects....Pages 3-15
Runtime-Aware Architectures....Pages 16-27
Front Matter....Pages 29-29
MPI Thread-Level Checking for MPI+OpenMP Applications....Pages 31-42
Event-Action Mappings for Parallel Tools Infrastructures....Pages 43-54
Front Matter....Pages 55-55
Low-Overhead Detection of Memory Access Patterns and Their Time Evolution....Pages 57-69
Automatic On-Line Detection of MPI Application Structure with Event Flow Graphs....Pages 70-81
Online Automated Reliability Classification of Queueing Models for Streaming Processing Using Support Vector Machines....Pages 82-93
Front Matter....Pages 95-95
A Duplicate-Free State-Space Model for Optimal Task Scheduling....Pages 97-108
On the Heterogeneity Bias of Cost Matrices When Assessing Scheduling Algorithms....Pages 109-121
Hardware Round-Robin Scheduler for Single-ISA Asymmetric Multi-core....Pages 122-134
Moody Scheduling for Speculative Parallelization....Pages 135-146
Allocating Jobs with Periodic Demand Variations....Pages 147-158
A Multi–level Hypergraph Partitioning Algorithm Using Rough Set Clustering....Pages 159-170
Non-preemptive Throughput Maximization for Speed-Scaling with Power-Down....Pages 171-182
Scheduling Tasks from Selfish Multi-tasks Agents....Pages 183-195
Locality and Balance for Communication-Aware Thread Mapping in Multicore Systems....Pages 196-208
Priority Queues Are Not Good Concurrent Priority Schedulers....Pages 209-221
Load Balancing Prioritized Tasks via Work-Stealing....Pages 222-234
Front Matter....Pages 235-235
Optimizing Task Parallelism with Library-Semantics-Aware Compilation....Pages 237-249
Data Layout Optimization for Portable Performance....Pages 250-262
Front Matter....Pages 235-235
Automatic Data Layout Optimizations for GPUs....Pages 263-274
Front Matter....Pages 275-275
Performance Impacts with Reliable Parallel File Systems at Exascale Level....Pages 277-288
Rapid Tomographic Image Reconstruction via Large-Scale Parallelization....Pages 289-302
Front Matter....Pages 303-303
Software Consolidation as an Efficient Energy and Cost Saving Solution for a SaaS/PaaS Cloud Model....Pages 305-316
VMPlaceS: A Generic Tool to Investigate and Compare VM Placement Algorithms....Pages 317-329
Front Matter....Pages 331-331
A Connectivity Model for Agreement in Dynamic Systems....Pages 333-345
DFEP: Distributed Funding-Based Edge Partitioning....Pages 346-358
Front Matter....Pages 359-359
PR-STM: Priority Rule Based Software Transactions for the GPU....Pages 361-372
Leveraging MPI-3 Shared-Memory Extensions for Efficient PGAS Runtime Systems....Pages 373-384
Front Matter....Pages 385-385
A Practical Transactional Memory Interface....Pages 387-401
A Multicore Parallelization of Continuous Skyline Queries on Data Streams....Pages 402-413
A Fast and Scalable Graph Coloring Algorithm for Multi-core and Many-core Architectures....Pages 414-425
A Composable Deadlock-Free Approach to Object-Based Isolation....Pages 426-437
Scalable Data-Driven PageRank: Algorithms, System Issues, and Lessons Learned....Pages 438-450
How Many Threads will be too Many? On the Scalability of OpenMP Implementations....Pages 451-463
Front Matter....Pages 465-465
Efficient Nested Dissection for Multicore Architectures....Pages 467-478
Scheduling Trees of Malleable Tasks for Sparse Linear Algebra....Pages 479-490
Elastic Tasks: Unifying Task Parallelism and SPMD Parallelism with an Adaptive Runtime....Pages 491-503
Front Matter....Pages 505-505
Semi-discrete Matrix-Free Formulation of 3D Elastic Full Waveform Inversion Modeling....Pages 507-518
10,000 Performance Models per Minute – Scalability of the UG4 Simulation Framework....Pages 519-531
Front Matter....Pages 505-505
Exploiting Task-Based Parallelism in Bayesian Uncertainty Quantification....Pages 532-544
Parallelization of an Advection-Diffusion Problem Arising in Edge Plasma Physics Using Hybrid MPI/OpenMP Programming....Pages 545-557
Behavioral Non-portability in Scientific Numeric Computing....Pages 558-569
Front Matter....Pages 571-571
Fast Parallel Suffix Array on the GPU....Pages 573-587
Effective Barrier Synchronization on Intel Xeon Phi Coprocessor....Pages 588-600
High Performance Multi-GPU SpMV for Multi-component PDE-Based Applications....Pages 601-612
Accelerating Lattice Boltzmann Applications with OpenACC....Pages 613-624
High-Performance and Scalable Design of MPI-3 RMA on Xeon Phi Clusters....Pages 625-637
Improving Performance of Convolutional Neural Networks by Separable Filters on GPU....Pages 638-649
Iterative Sparse Triangular Solves for Preconditioning....Pages 650-661
Targeting the Parallella....Pages 662-674
Systematic Fusion of CUDA Kernels for Iterative Sparse Linear System Solvers....Pages 675-686
Efficient Execution of Multiple CUDA Applications Using Transparent Suspend, Resume and Migration....Pages 687-699
Back Matter....Pages 701-703