ISU Electrical and Computer Engineering Archives

Performance effects of node mapping on the IBM BlueGene/L machine

Smith, Brian (2005) Performance effects of node mapping on the IBM BlueGene/L machine. Masters thesis, Iowa State University.

Full text available as:

Postscript - Archive staff only - Requires a viewer, such as GhostView

Abstract

The IBM BlueGene/L (BG/L) supercomputer is a new machine consisting of up to 65536 relatively modest compute nodes connected with three application-level networks – a high-performance point-to-point 3D torus network, a global combining/broadcast tree network for collective operations, and a global interrupt/barrier network for extremely fast global barriers. The BG/L control system allows the user to assign MPI logical ranks to physical torus coordinates at run-time in an arbitrary manner as long as all nodes are uniquely included in the mapping. This presents the possibility of increasing application performance with very little e.ort. This thesis investigates the performance e.ects of node mapping with several benchmarks and scienti.c codes using a variety of existing and new mapping strategies. The benchmarks are the NAS parallel benchmarks, the Ames Laboratory Classical Molecular Dynamics code (ALCMD), and the General Atomic and Molecular Electronic Structure System (GAMESS) application. The NAS benchmarks are short, easy to understand, and fairly well known. ALCMD has an interesting communication pattern that should bene.t from a good mapping strategy. GAMESS is one application that is not necessarily well-suited for running on BlueGene because it requires a large amount of compute power and memory per node. However, it provides an interesting data point for performance of applications that were not designed for a particular system and the possible bene.ts of mapping on such applications. The mappings investigated were the stock permutations (XYZ, XZY, etc), Gray-code based mesh mappings, random maps, variations on Gray-code maps for embedding 2D meshes in the 3D torus, and three maps designed for GAMESS. Performance results are presented for node mappings on several BG/L partition sizes.

EPrint Type:Thesis (Masters)
Subjects:Computer Engineering > SOFTWARE SYSTEMS > Parallel and Distributed Computing
ID Code:130
Identification Number:TR-2005-01-1
Deposited By:Mr Brian Smith
Deposited On:25 January 2005

Archive Staff Only: edit this record