BlueGene/L applications: Parallelism On a Massive Scale
- 1 February 2008
- journal article
- research article
- Published by SAGE Publications in The International Journal of High Performance Computing Applications
- Vol. 22 (1) , 33-51
Abstract
BlueGene/L (BG/L), developed through a partnership between IBM and Lawrence Livermore National Laboratory (LLNL), is currently the world's largest system both in terms of scale, with 131,072 processors, and absolute performance, with a peak rate of 367 Tflop/s. BG/L has led the last four Top500 lists with a Linpack rate of 280.6 Tflop/s for the full machine installed at LLNL and is expected to remain the fastest computer in the next few editions. However, the real value of a machine such as BG/L derives from the scientific breakthroughs that real applications can produce by successfully using its unprecedented scale and computational power. In this paper, we describe our experiences with eight large scale applications on BG/ L from several application domains, ranging from molecular dynamics to dislocation dynamics and turbulence simulations to searches in semantic graphs. We also discuss the challenges we faced when scaling these codes and present several successful optimization techniques. All applications show excellent scaling behavior, even at very large processor counts, with one code even achieving a sustained performance of more than 100 Tflop/s, clearly demonstrating the real success of the BG/L design.Keywords
This publication has 15 references indexed in Scilit:
- Beyond Finite-Size Scaling in Solidification SimulationsPhysical Review Letters, 2006
- Evaluating high‐performance computersConcurrency and Computation: Practice and Experience, 2005
- Quantum-based atomistic simulation of materials properties in transition metalsJournal of Physics: Condensed Matter, 2002
- Parallelization of structured, hierarchical adaptive mesh refinement algorithmsComputing and Visualization in Science, 2000
- First-principles theory of Ta up to 10 Mbar pressure: Structural and mechanical propertiesPhysical Review B, 1998
- A parallelization of Dijkstra's shortest path algorithmLecture Notes in Computer Science, 1998
- A Randomized Parallel Algorithm for Single-Source Shortest PathsJournal of Algorithms, 1997
- From silicon to RNA: The coming of age of ab initio molecular dynamicsSolid State Communications, 1997
- Angular forces and melting in bcc transition metals: A case study of molybdenumPhysical Review B, 1994
- Analytic representation of multi-ion interatomic potentials in transition metalsPhysical Review B, 1990