Distributed shared memory on IBM SP2

Ramesh, Shruti; Lakshmi, R. Jaya; Govindarajan, Raghav

doi:10.1109/icpads.1997.652571

Cited by 1 publication

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basis for shared memory programming is formed by a global memory space, which is not physically available on clusters and other distributed memory architectures. To enable shared memory style programming on such machines, an early approach was to build a virtual or distributed shared memory layer on top of the distributed memory [6], [25], [24]. Therefore, the Partitioned Global Address Space (PGAS) model [22], was proposed and is gaining popularity.…”

Section: Introductionmentioning

confidence: 99%

DART-MPI: An MPI-based Implementation of a PGAS Runtime System

Zhou,

Mhedheb,

Idrees

et al. 2015

Preprint

View full text Add to dashboard Cite

A Partitioned Global Address Space (PGAS) approach treats a distributed system as if the memory were shared on a global level. Given such a global view on memory, the user may program applications very much like shared memory systems. This greatly simplifies the tasks of developing parallel applications, because no explicit communication has to be specified in the program for data exchange between different computing nodes. In this paper we present DART, a runtime environment, which implements the PGAS paradigm on largescale high-performance computing clusters. A specific feature of our implementation is the use of one-sided communication of the Message Passing Interface (MPI) version 3 (i.e. MPI-3) as the underlying communication substrate. We evaluated the performance of the implementation with several low-level kernels in order to determine overheads and limitations in comparison to the underlying MPI-3.

show abstract

Section: Introductionmentioning

confidence: 99%