The implementation of MPI-2 one-sided communication for the NEC SX-5
Proceedings of the 2000 ACM/IEEE conference on Supercomputing
Single sided MPI implementations for SUN MPIr
Proceedings of the 2000 ACM/IEEE conference on Supercomputing
Performance of the CRAY T3E multiprocessor
SC '97 Proceedings of the 1997 ACM/IEEE conference on Supercomputing
IEEE Standard for Scalable Coherent Interface, Science: IEEE Std. 1596-1992
IEEE Standard for Scalable Coherent Interface, Science: IEEE Std. 1596-1992
Affordable Scalability Using Multi-Cubes
SCI: Scalable Coherent Interface, Architecture and Software for High-Performance Compute Clusters
ScaMPI-Design and Implementation
SCI: Scalable Coherent Interface, Architecture and Software for High-Performance Compute Clusters
Implementing MPI's One-Sided Communications for WMPI
Proceedings of the 6th European PVM/MPI Users' Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface
MPI Optimization for SMP Based Clusters Interconnected with SCI
Proceedings of the 7th European PVM/MPI Users' Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface
Collective Communication on Dedicated Clusters of Workstations
Proceedings of the 6th European PVM/MPI Users' Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface
Active messages: an efficient communication architecture for multiprocessors
Active messages: an efficient communication architecture for multiprocessors
Hi-index | 0.00 |
In this paper we present the Scali ShMem - ScaShMem - library, a compatibilitylibraryfor CraySHMEM. SHMEM is a popular application programmers interface for MPP (Massive Parallel Processor) programming, but has previouslyb een limited to MPPs from CrayInc. and SGI Inc. ScaShMem is layered on top of Scali's MPI implementation; ScaMPI, using multiple threads enabled byScaMPI's thread-hot & -safe features. Since ScaShMem is layered on top of MPI, one-sided communication of SHMEM can be mixed with MPI message passing. Near native Scali MPI performance is demonstrated for ScaShMem, justifying porting SHMEM applications to a price favorable cluster environment.