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

Takeshi Nanri, Hiroyuki Sato, Masaaki Shimasaki

Research output: Contribution to conferencePaper

3 Citations (Scopus)

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.

Original languageEnglish
Pages312-318
Number of pages7
Publication statusPublished - Jan 1 1997
EventProceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97 - Seoul, South Korea
Duration: Apr 28 1997May 2 1997

Conference

ConferenceProceedings of the 1997 2nd High Performance Computing on the Information Superhighway, HPC Asia'97
CitySeoul, South Korea
Period4/28/975/2/97

Fingerprint

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

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

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

Research output: Contribution to conferencePaper

Nanri, T, Sato, H & Shimasaki, M 1997, 'Using cache optimizing compiler for managing software cache on distributed shared memory system', Paper presented at 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. Paper presented at 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. Paper presented at 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 -