A Multiprotocol Communication Support for the Global Address Space Programming Model on the IBM SP
نویسندگان
چکیده
The paper describes an efficient communication support for the global address space programming model on the IBM SP, a commercial example of the SMP (symmetric multi-processor) clusters. Our approach integrates shared memory with active messages, threads and remote memory copy between nodes. The shared memory operations offer substantial performance improvement over LAPI, IBM one-sided communication library, within an SMP node. Based on the experiments with the SPLASH-2 LU benchmark and a molecular dynamics simulation, our multiprotocol support for the global address space is found to improve performance and scalability of applications. This approach could also be used in optimizing the MPI-2 one-sided communication on the SMP clusters.
منابع مشابه
Analysis of a Contractile Torus Simulation in Titanium
The purpose of this paper is to analyze the use of the Titanium language, a high-performance Java dialect, and parallel programming practices on an application of the Immersed Boundary (IB) Method for simulating biological processes. We will compare two Titanium implementations of the IB Method in terms of performance, developer productivity, and use of Titanium features. The first implementati...
متن کاملCo-array Fortran Performance and Potential: An NPB Experimental Study
Co-array Fortran (CAF) is an emerging model for scalable, global address space parallel programming that consists of a small set of extensions to the Fortran 90 programming language. Compared to MPI, the widely-used messagepassing programming model, CAF’s global address space programming model simplifies the development of single-program-multiple-data parallel programs by shifting the burden fo...
متن کاملA scalable replay-based infrastructure for the performance analysis of one-sided communication
Partitioned global address space (PGAS) languages combine the convenient abstraction of shared memory with the notion of affinity, extending multi-threaded programming to large-scale systems with physically distributed memory. However, in spite of their obvious advantages, PGAS languages still lack appropriate tool support for performance analysis, one of the reasons why their adoption is still...
متن کاملData Distribution Analysis and Optimization for Pointer-Based Distributed Programs
High Performance Fortran (HPF) provides distributed arrays to eeciently support a global name space on distributed memory architectures. The distributed data structures supported by HPF, however , are only limited to array constructs, and do not extend to pointer-based distributed structures. With the support of distributed pointers and class abstractions in parallel C++-like languages, applica...
متن کاملOSPRI: An Optimized One-Sided Communication Runtime for Leadership-Class Machines
Partitioned Global Address Space (PGAS) programming models provide a convenient approach to implementing complex scientific applications by providing access to a large, globally accessible address space. This paper describes the design, implementation and performance of a new one-sided communication library that attempts to meet the needs of PGAS models, particularly Global Arrays, but hopefull...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2000