Improving MPI communication overlap with collaborative polling

Authors:
Sylvain Didelot;Patrick Carribault;Marc Pérache;William Jalby
Affiliations:
Exascale Computing Research Center, Versailles, Francniversité de Versailles Saint-Quentin-en-Yvelines (UVSQ), Versailles, France;DAM, DIF, CEA, Arpajon, Francxascale Computing Research Center, Versailles, France;DAM, DIF, CEA, Arpajon, Francxascale Computing Research Center, Versailles, France;Exascale Computing Research Center, Versailles, Francniversité de Versailles Saint-Quentin-en-Yvelines (UVSQ), Versailles, France
Venue:
EuroMPI'12 Proceedings of the 19th European conference on Recent Advances in the Message Passing Interface
Year:
2012

Citing 10
Cited 1

Optimizing threaded MPI execution on SMP clusters

ICS '01 Proceedings of the 15th international conference on Supercomputing
Analyzing the Impact of Overlap, Offload, and Independent Progress for Message Passing Interface Applications

International Journal of High Performance Computing Applications
Implementation and design analysis of a network messaging module using virtual interface architecture

CLUSTER '04 Proceedings of the 2004 IEEE International Conference on Cluster Computing
Lock-Free Asynchronous Rendezvous Design for MPI Point-to-Point Communication

Proceedings of the 15th European PVM/MPI Users' Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface
MPC-MPI: An MPI Implementation Reducing the Overall Memory Consumption

Proceedings of the 16th European PVM/MPI Users' Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface
ConnectX-2 InfiniBand Management Queues: First Investigation of the New Support for Network Offloaded Collective Operations

CCGRID '10 Proceedings of the 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing
Optimizing bandwidth limited problems using one-sided communication and overlap

IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
The Impact of Application's Micro-Imbalance on the Communication-Computation Overlap

PDP '11 Proceedings of the 2011 19th International Euromicro Conference on Parallel, Distributed and Network-Based Processing
Performance evaluation of thread-based MPI in shared memory

EuroMPI'11 Proceedings of the 18th European MPI Users' Group conference on Recent advances in the message passing interface
Open issues in MPI implementation

ACSAC'07 Proceedings of the 12th Asia-Pacific conference on Advances in Computer Systems Architecture

Improving MPI communication overlap with collaborative polling

Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

With the rise of parallel applications complexity, the needs in term of computational power are continually growing. Recent trends in High-Performance Computing (HPC) have shown that improvements in single-core performance will not be sufficient to face the challenges of an Exascale machine: we expect an enormous growth of the number of cores as well as a multiplication of the data volume exchanged across compute nodes. To scale applications up to Exascale, the communication layer has to minimize the time while waiting for network messages. This paper presents a message progression based on Collaborative Polling which allows an efficient auto-adaptive overlapping of communication phases by performing computing. This approach is new as it increases the application overlap potential without introducing overheads of a threaded message progression.