This book constitutes the refereed proceedings of the 18th European MPI Users' Group Meeting on Recent Advances in the Message Passing Interface, EuroMPI 2011, held in Santorini, Greece, in September 2011. The 28 revised full papers presented together with 10 posters were carefully reviewed and selected from 66 submissions. Topics covered are communication; I/O; networking, and implementation issues and improvements; algorithms and tools; interaction with hardware; applications and performance evaluation; fault and tolerance.
Author(s): Michael Resch (auth.), Yiannis Cotronis, Anthony Danalis, Dimitrios S. Nikolopoulos, Jack Dongarra (eds.)
Series: Lecture Notes in Computer Science 6960
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 2011
Language: English
Pages: 358
Tags: Algorithm Analysis and Problem Complexity; Computer Communication Networks; Software Engineering; Programming Techniques; Computer Systems Organization and Communication Networks; Simulation and Modeling
Front Matter....Pages -
Experience of a PRACE Center....Pages 1-4
Achieving Exascale Computing through Hardware/Software Co-design....Pages 5-7
Will MPI Remain Relevant?....Pages 8-8
Exascale Algorithms for Generalized MPI_Comm_split....Pages 9-18
Order Preserving Event Aggregation in TBONs....Pages 19-28
Using MPI Derived Datatypes in Numerical Libraries....Pages 29-38
Improving MPI Applications Performance on Multicore Clusters with Rank Reordering....Pages 39-49
Multi-core and Network Aware MPI Topology Functions....Pages 50-60
Scalable Node Allocation for Improved Performance in Regular and Anisotropic 3D Torus Supercomputers....Pages 61-70
Improving the Average Response Time in Collective I/O....Pages 71-80
OMPIO: A Modular Software Architecture for MPI I/O....Pages 81-89
Design and Evaluation of Nonblocking Collective I/O Operations....Pages 90-98
Optimizing MPI One Sided Communication on Multi-core InfiniBand Clusters Using Shared Memory Backed Windows....Pages 99-109
A uGNI-Based MPICH2 Nemesis Network Module for the Cray XE....Pages 110-119
Using Triggered Operations to Offload Rendezvous Messages....Pages 120-129
pupyMPI - MPI Implemented in Pure Python....Pages 130-139
Scalable Memory Use in MPI: A Case Study with MPICH2....Pages 140-149
Performance Expectations and Guidelines for MPI Derived Datatypes....Pages 150-159
The Analysis of Cluster Interconnect with the Network_Tests2 Toolkit....Pages 160-169
Parallel Sorting with Minimal Data....Pages 170-177
Scaling Performance Tool MPI Communicator Management....Pages 178-187
Per-call Energy Saving Strategies in All-to-All Communications....Pages 188-197
Data Redistribution Using One-sided Transfers to In-Memory HDF5 Files....Pages 198-207
RCKMPI – Lightweight MPI Implementation for Intel’s Single-chip Cloud Computer (SCC)....Pages 208-217
Hybrid OpenMP-MPI Turbulent Boundary Layer Code Over 32k Cores....Pages 218-227
CAF versus MPI - Applicability of Coarray Fortran to a Flow Solver....Pages 228-236
The Impact of Injection Bandwidth Performance on Application Scalability....Pages 237-246
Impact of Kernel-Assisted MPI Communication over Scientific Applications: CPMD and FFTW....Pages 247-254
A Log-Scaling Fault Tolerant Agreement Algorithm for a Fault Tolerant MPI....Pages 255-263
Fault Tolerance in an Industrial Seismic Processing Application for Multicore Clusters....Pages 264-271
libhashckpt: Hash-Based Incremental Checkpointing Using GPU’s....Pages 272-281
Noncollective Communicator Creation in MPI....Pages 282-291
Evaluation of Interpreted Languages with Open MPI....Pages 292-301
Leveraging C++ Meta-programming Capabilities to Simplify the Message Passing Programming Model....Pages 302-311
Portable and Scalable MPI Shared File Pointers....Pages 312-314
Improvement of the Bandwidth of Cross-Site MPI Communication Using Optical Fiber....Pages 315-317
Performance Tuning of SCC-MPICH by Means of the Proposed MPI-3.0 Tool Interface....Pages 318-320
Design and Implementation of Key Proposed MPI-3 One-Sided Communication Semantics on InfiniBand....Pages 321-324
Scalable Distributed Consensus to Support MPI Fault Tolerance....Pages 325-328
Run-Through Stabilization: An MPI Proposal for Process Fault Tolerance....Pages 329-332
Integrating MPI with Asynchronous Task Parallelism....Pages 333-336
Performance Evaluation of Thread-Based MPI in Shared Memory....Pages 337-338
MPI-DB, A Parallel Database Services Software Library for Scientific Computing....Pages 339-341
Scalable Runtime for MPI: Efficiently Building the Communication Infrastructure....Pages 342-344
Writing Parallel Libraries with MPI - Common Practice, Issues, and Extensions....Pages 345-355
Back Matter....Pages -
