2006 Fiscal Year Final Research Report Summary
Software distributed shared memory systems with performance scalability for supercluster systems
| Project/Area Number |
16300004
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Software
|
|---|
| Research Institution | The University of Electro-Communications |
|---|
Principal Investigator |
YUBA Toshitsugu The University of Electro-Communications, Graduate School of Information Systems, Professor, 大学院情報システム学研究科, 教授 (50251723)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
HONDA Hiroki Tokyo Institute of Technology, Graduate School of Information Systems, Associate Professor, 大学院情報システム学研究科, 助教授 (20199574)
KISE Kenji Tokyo Institute of Technology, Graduate School of Information Science and Technology, Assistant Professor, 大学院情報理工学研究科, 講師 (50323887)
KATAGIRI Takahiro Tokyo Institute of Technology, Graduate School of Information Systems, Research Associate, 大学院情報システム学研究科, 助手 (40345434)
TSUKAMOTO Michiharu Tokyo University of Technology, Faculty of Media Science, Professor, メディア学部, 教授 (90386764)
|
|---|
| Project Period (FY) |
2004 – 2006
|
| Keywords | Software distributed shared memory / Cluster computing / Performance scalability / Parallel processing / Data consistency model / Performance evaluation |
|---|
| Research Abstract |
A high-performance software distributed shared memory (DSM) system with performance scalability, named Mocha, was implemented as an experimental prototype aiming at the usefulness of supercluster systems. The current version of Mocha works on a 32 node cluster on the Linux environment. The source program has been opened in public domain via web. A scheme for suppressing communication overhead, which is mainly caused by maintaining data consistency among shared data located at distributed memories, is proposed and slotted in Mocha. The effectiveness is evaluated by using some benchmark programs. A tool for performance debugging of application programs and constructing an efficient software DSM, named S-Cat, was implemented, which has such functions as showing visually communication locus among processors during execution process of an application program. S-Cat was used in efficient implementation of Mocha and performance tuning of application programs on Mocha.
The main research results are as follows:
1.Implementation of a low communication overhead software DSM, named Mocha
2.Comparison study of different software DSMs on the same cluster
3.Proposal of coarse-grain parallel processing on software DSM
4.Construction of a visualization tool for software DSM, named S-Cat
5.Proposal of parallel processing on graphic processor and off-the-shelf processor
Some technical issues toward realization of high-performance software DSMs for supercluster systems are made clear. "Hierarchical paradigm" for controlling multiple clusters was proposed, but its usefulness cannot be verified during this research period.
|
