Using cache optimizing compiler for managing software cache on distributed shared memory system

Takeshi Nanri, Hiroyuki Sato, Masaaki Shimasaki

研究成果: 会議への寄与タイプ論文

3 引用 (Scopus)

抄録

On distributed shared memory (DSM) system, the optimization of memory access is very important for achieving good performance. In this paper we propose an optimizing compiler which controls a software cache system implemented on DSM. The software cache consists of static part related with compiler and dynamic part related with cache-managing runtime routines. Our compiler controls static part of the software cache by using information from static analysis. For applications whose behavior can only be dynamically determined, the compiler uses dynamic part of the software cache. We also propose application of RISC-oriented optimization techniques to parallel applications on our software cache system. We evaluate the efficiency of our compiler and RISC-oriented optimization techniques on distributed parallel machine, CM-5. Our results show that the compiler and the optimizations considerably improve the performance of basic linear algebra routines: matrix multiply, Cholesky decomposition and Gaussian elimination.

元の言語英語
ページ312-318
ページ数7
出版物ステータス出版済み - 1 1 1997
イベントProceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97 - Seoul, South Korea
継続期間: 4 28 19975 2 1997

会議

会議Proceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97
Seoul, South Korea
期間4/28/975/2/97

Fingerprint

Computer systems
Data storage equipment
Reduced instruction set computing
Linear algebra
Static analysis
Decomposition

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

これを引用

Nanri, T., Sato, H., & Shimasaki, M. (1997). Using cache optimizing compiler for managing software cache on distributed shared memory system. 312-318. 論文発表場所 Proceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97, Seoul, South Korea, .

Using cache optimizing compiler for managing software cache on distributed shared memory system. / Nanri, Takeshi; Sato, Hiroyuki; Shimasaki, Masaaki.

1997. 312-318 論文発表場所 Proceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97, Seoul, South Korea, .

研究成果: 会議への寄与タイプ論文

Nanri, T, Sato, H & Shimasaki, M 1997, 'Using cache optimizing compiler for managing software cache on distributed shared memory system', 論文発表場所 Proceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97, Seoul, South Korea, 4/28/97 - 5/2/97 pp. 312-318.
Nanri T, Sato H, Shimasaki M. Using cache optimizing compiler for managing software cache on distributed shared memory system. 1997. 論文発表場所 Proceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97, Seoul, South Korea, .
Nanri, Takeshi ; Sato, Hiroyuki ; Shimasaki, Masaaki. / Using cache optimizing compiler for managing software cache on distributed shared memory system. 論文発表場所 Proceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97, Seoul, South Korea, .7 p.
@conference{3f0146705b504364b009536e8c75449a,
title = "Using cache optimizing compiler for managing software cache on distributed shared memory system",
abstract = "On distributed shared memory (DSM) system, the optimization of memory access is very important for achieving good performance. In this paper we propose an optimizing compiler which controls a software cache system implemented on DSM. The software cache consists of static part related with compiler and dynamic part related with cache-managing runtime routines. Our compiler controls static part of the software cache by using information from static analysis. For applications whose behavior can only be dynamically determined, the compiler uses dynamic part of the software cache. We also propose application of RISC-oriented optimization techniques to parallel applications on our software cache system. We evaluate the efficiency of our compiler and RISC-oriented optimization techniques on distributed parallel machine, CM-5. Our results show that the compiler and the optimizations considerably improve the performance of basic linear algebra routines: matrix multiply, Cholesky decomposition and Gaussian elimination.",
author = "Takeshi Nanri and Hiroyuki Sato and Masaaki Shimasaki",
year = "1997",
month = "1",
day = "1",
language = "English",
pages = "312--318",
note = "Proceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97 ; Conference date: 28-04-1997 Through 02-05-1997",

}

TY - CONF

T1 - Using cache optimizing compiler for managing software cache on distributed shared memory system

AU - Nanri, Takeshi

AU - Sato, Hiroyuki

AU - Shimasaki, Masaaki

PY - 1997/1/1

Y1 - 1997/1/1

N2 - On distributed shared memory (DSM) system, the optimization of memory access is very important for achieving good performance. In this paper we propose an optimizing compiler which controls a software cache system implemented on DSM. The software cache consists of static part related with compiler and dynamic part related with cache-managing runtime routines. Our compiler controls static part of the software cache by using information from static analysis. For applications whose behavior can only be dynamically determined, the compiler uses dynamic part of the software cache. We also propose application of RISC-oriented optimization techniques to parallel applications on our software cache system. We evaluate the efficiency of our compiler and RISC-oriented optimization techniques on distributed parallel machine, CM-5. Our results show that the compiler and the optimizations considerably improve the performance of basic linear algebra routines: matrix multiply, Cholesky decomposition and Gaussian elimination.

AB - On distributed shared memory (DSM) system, the optimization of memory access is very important for achieving good performance. In this paper we propose an optimizing compiler which controls a software cache system implemented on DSM. The software cache consists of static part related with compiler and dynamic part related with cache-managing runtime routines. Our compiler controls static part of the software cache by using information from static analysis. For applications whose behavior can only be dynamically determined, the compiler uses dynamic part of the software cache. We also propose application of RISC-oriented optimization techniques to parallel applications on our software cache system. We evaluate the efficiency of our compiler and RISC-oriented optimization techniques on distributed parallel machine, CM-5. Our results show that the compiler and the optimizations considerably improve the performance of basic linear algebra routines: matrix multiply, Cholesky decomposition and Gaussian elimination.

UR - http://www.scopus.com/inward/record.url?scp=0030677014&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030677014&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0030677014

SP - 312

EP - 318

ER -