A programming methodology for dual-tier multicomputers

doi:10.1109/32.842948

A programming methodology for dual-tier multicomputers

2000-03-01

15

PRE

AI

DOI：10.1109/32.842948

Original

Original request for help

Save

Abstract

En 中文

Hierarchically organized ensembles of shared memory multiprocessors possess a richer and more complex model of locality than previous generation multicomputers with single processor nodes. These dual-tier computers introduce many new factors into the programmer's performance model. We present a methodology for implementing block-structured numerical applications on dual-tier computers and a run-time infrastructure, called KeLP2, that implements the methodology. KeLP2 supports two levels of locality and parallelism via hierarchical SPMD control flow, run-time geometric meta-data, and asynchronous collective communication. KeLP applications can effectively overlap communication with computation under conditions where nonblocking point-to-point message passing fails to do so. KeLP's abstractions hide considerable detail without sacrificing performance and dual-tier applications written in KeLP consistently outperform equivalent single-tier implementations written in MPI. We describe the KeLP2 model and show how it facilitates the implementation of five block-structured applications specially formulated to hide communication latency on dual-tiered architectures. We support our arguments with empirical data from applications running on various single- and dual-tier multicomputers. KeLP2 supports a migration path from single-tier to dual-tier platforms and we illustrate this capability with a detailed programming example.

Keywords:

dual-tier parallel computers

hierarchical parallelism

KeLP

block-structured scientific applications

scientific application requirements

C plus plus framework

SMP clusters

A programming methodology for dual-tier multicomputers

Abstract

Journal

Organization