Ebook: Recent Advances in the Message Passing Interface: 17th European MPI Users’ Group Meeting, EuroMPI 2010, Stuttgart, Germany, September 12-15, 2010. Proceedings

This book constitutes the proceedings of the 17th European MPI User's Group Meeting on Recent Advances in the Message Passing Interface held in Stuttgart in September 2010.

---

This book constitutes the proceedings of the 17th European MPI User's Group Meeting on Recent Advances in the Message Passing Interface held in Stuttgart in September 2010.
Content:
Front Matter....Pages -
A Scalable MPI_Comm_split Algorithm for Exascale Computing....Pages 1-10
Enabling Concurrent Multithreaded MPI Communication on Multicore Petascale Systems....Pages 11-20
Toward Performance Models of MPI Implementations for Understanding Application Scaling Issues....Pages 21-30
PMI: A Scalable Parallel Process-Management Interface for Extreme-Scale Systems....Pages 31-41
Run-Time Analysis and Instrumentation for Communication Overlap Potential....Pages 42-49
Efficient MPI Support for Advanced Hybrid Programming Models....Pages 50-61
An HDF5 MPI Virtual File Driver for Parallel In-situ Post-processing....Pages 62-71
Automated Tracing of I/O Stack....Pages 72-81
MPI Datatype Marshalling: A Case Study in Datatype Equivalence ....Pages 82-91
Design of Kernel-Level Asynchronous Collective Communication....Pages 92-101
Network Offloaded Hierarchical Collectives Using ConnectX-2’s CORE-Direct Capabilities....Pages 102-112
An In-Place Algorithm for Irregular All-to-All Communication with Limited Memory....Pages 113-121
Massively Parallel Finite Element Programming....Pages 122-131
Parallel Zero-Copy Algorithms for Fast Fourier Transform and Conjugate Gradient Using MPI Datatypes....Pages 132-141
Parallel Chaining Algorithms....Pages 142-151
Precise Dynamic Analysis for Slack Elasticity: Adding Buffering without Adding Bugs....Pages 152-159
Implementing MPI on Windows: Comparison with Common Approaches on Unix....Pages 160-169
Compact and Efficient Implementation of the MPI Group Operations....Pages 170-178
Characteristics of the Unexpected Message Queue of MPI Applications....Pages 179-188
Dodging the Cost of Unavoidable Memory Copies in Message Logging Protocols....Pages 189-197
Communication Target Selection for Replicated MPI Processes....Pages 198-207
Transparent Redundant Computing with MPI....Pages 208-218
Checkpoint/Restart-Enabled Parallel Debugging....Pages 219-228
Load Balancing for Regular Meshes on SMPs with MPI....Pages 229-238
Adaptive MPI Multirail Tuning for Non-uniform Input/Output Access....Pages 239-248
Using Triggered Operations to Offload Collective Communication Operations....Pages 249-256
Second-Order Algorithmic Differentiation by Source Transformation of MPI Code....Pages 257-264
Locality and Topology Aware Intra-node Communication among Multicore CPUs....Pages 265-274
Transparent Neutral Element Elimination in MPI Reduction Operations....Pages 275-284
Use Case Evaluation of the Proposed MPIT Configuration and Performance Interface....Pages 285-288
Two Algorithms of Irregular Scatter/Gather Operations for Heterogeneous Platforms....Pages 289-293
Measuring Execution Times of Collective Communications in an Empirical Optimization Framework....Pages 294-297
Dynamic Verification of Hybrid Programs....Pages 298-301
Challenges and Issues of Supporting Task Parallelism in MPI....Pages 302-305
Back Matter....Pages -

---

This book constitutes the proceedings of the 17th European MPI User's Group Meeting on Recent Advances in the Message Passing Interface held in Stuttgart in September 2010.
Content:
Front Matter....Pages -
A Scalable MPI_Comm_split Algorithm for Exascale Computing....Pages 1-10
Enabling Concurrent Multithreaded MPI Communication on Multicore Petascale Systems....Pages 11-20
Toward Performance Models of MPI Implementations for Understanding Application Scaling Issues....Pages 21-30
PMI: A Scalable Parallel Process-Management Interface for Extreme-Scale Systems....Pages 31-41
Run-Time Analysis and Instrumentation for Communication Overlap Potential....Pages 42-49
Efficient MPI Support for Advanced Hybrid Programming Models....Pages 50-61
An HDF5 MPI Virtual File Driver for Parallel In-situ Post-processing....Pages 62-71
Automated Tracing of I/O Stack....Pages 72-81
MPI Datatype Marshalling: A Case Study in Datatype Equivalence ....Pages 82-91
Design of Kernel-Level Asynchronous Collective Communication....Pages 92-101
Network Offloaded Hierarchical Collectives Using ConnectX-2’s CORE-Direct Capabilities....Pages 102-112
An In-Place Algorithm for Irregular All-to-All Communication with Limited Memory....Pages 113-121
Massively Parallel Finite Element Programming....Pages 122-131
Parallel Zero-Copy Algorithms for Fast Fourier Transform and Conjugate Gradient Using MPI Datatypes....Pages 132-141
Parallel Chaining Algorithms....Pages 142-151
Precise Dynamic Analysis for Slack Elasticity: Adding Buffering without Adding Bugs....Pages 152-159
Implementing MPI on Windows: Comparison with Common Approaches on Unix....Pages 160-169
Compact and Efficient Implementation of the MPI Group Operations....Pages 170-178
Characteristics of the Unexpected Message Queue of MPI Applications....Pages 179-188
Dodging the Cost of Unavoidable Memory Copies in Message Logging Protocols....Pages 189-197
Communication Target Selection for Replicated MPI Processes....Pages 198-207
Transparent Redundant Computing with MPI....Pages 208-218
Checkpoint/Restart-Enabled Parallel Debugging....Pages 219-228
Load Balancing for Regular Meshes on SMPs with MPI....Pages 229-238
Adaptive MPI Multirail Tuning for Non-uniform Input/Output Access....Pages 239-248
Using Triggered Operations to Offload Collective Communication Operations....Pages 249-256
Second-Order Algorithmic Differentiation by Source Transformation of MPI Code....Pages 257-264
Locality and Topology Aware Intra-node Communication among Multicore CPUs....Pages 265-274
Transparent Neutral Element Elimination in MPI Reduction Operations....Pages 275-284
Use Case Evaluation of the Proposed MPIT Configuration and Performance Interface....Pages 285-288
Two Algorithms of Irregular Scatter/Gather Operations for Heterogeneous Platforms....Pages 289-293
Measuring Execution Times of Collective Communications in an Empirical Optimization Framework....Pages 294-297
Dynamic Verification of Hybrid Programs....Pages 298-301
Challenges and Issues of Supporting Task Parallelism in MPI....Pages 302-305
Back Matter....Pages -
....