Scaling MPI to short-memory MPPs such as BG/L
Proceedings of the 20th annual international conference on Supercomputing
Proceedings of the 2006 ACM/IEEE conference on Supercomputing
Overview of the Blue Gene/L system architecture
IBM Journal of Research and Development
Investigations on InfiniBand: efficient network buffer utilization at scale
PVM/MPI'07 Proceedings of the 14th European conference on Recent Advances in Parallel Virtual Machine and Message Passing Interface
Scalability of communicators and groups in MPI
Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing
Compact and efficient implementation of the MPI group operations
EuroMPI'10 Proceedings of the 17th European MPI users' group meeting conference on Recent advances in the message passing interface
Scalable memory use in MPI: a case study with MPICH2
EuroMPI'11 Proceedings of the 18th European MPI Users' Group conference on Recent advances in the message passing interface
| Hi-index | 0.00 |
In this paper we explore various sparse data storage techniques in order to reduce the amount of memory required for MPI groups and communicators. The idea behind the approach is to exploit similarities between the objects and thus store only the difference between the original process group and the resulting one. For each technique, we detail the memory saved compared to the currently used implementations, and present a runtime decision routine capable of choosing dynamically the most efficient technique for each scenario. Furthermore, we evaluate the performance impact of the new structures using point-to-point benchmarks as well as an application scenario over InfiniBand, Myrinet and Gigabit Ethernet networks.