DAME: An environment for preserving the efficiency of data-parallel computations on distributed systems

被引：5
作者：
Colajanni, M
Cermele, M
机构：
[1] Department of Computer Engineering, University of Rome Tor Vergata
[2] IEEE Computer Society, ACM, Society for Computer Simulation
[3] Dipto. di Info., Sistemi e Prod., Univ. di Roma Tor Vergata, I-00133 Roma, Via della Ricerca Scientifica
来源：
IEEE CONCURRENCY | 1997年 / 5卷 / 01期
关键词：
D O I：
10.1109/4434.580447
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
DAME (Data Migration Environment) uses transparent supports to overcome inefficiencies in data-parallel programming. These supports hide irregular network topology, dynamically adapt the data distribution to platform conditions, and mask the consequent nonuniform distribution to the programmer. The authors compare DAME's performance with that of some popular frameworks. They begin by discussing DAME's three main design goals: efficiency, transparency, and scalability. Next, they describe the five supports that DAME gives the programmer: virtual topology, data distribution, data management, interprocess communication, and workload reconfiguration. Then, they present the results they obtained from experiments using 10 workstations that provide a hardware-heterogeneous, data-homogeneous, nonuniform platform. The results show that DAME provides a virtual Single-Program, Multiple-DATA machine that overcomes most of the differences that distinguish a parallel virtual machine from an ideal SPMD machine.
引用
收藏
页码：41 / &
页数：16
相关论文
共 14 条
[1]   A CASE FOR NOW (NETWORKS OF WORKSTATIONS) [J].
ANDERSON, TE ;
CULLER, DE ;
PATTERSON, DA .
IEEE MICRO, 1995, 15 (01) :54-64
[2]   ADAPTIVE PARALLELISM AND PIRANHA [J].
CARRIERO, N ;
FREEMAN, E ;
GELERNTER, D ;
KAMINSKY, D .
COMPUTER, 1995, 28 (01) :40-49
[3]  
Casas J., 1994, Proceedings Supercomputing '94 (Cat. No.94CH34819), P390, DOI 10.1109/SUPERC.1994.344302
[4]  
CERMELE M, 1996, RI9612 U ROM TOR VER
[5]  
CERMELE M, 1997, P IEEE HET COMP WORK
[6]  
CERMELE M, 1997, IN PRESS PARALLEL CO, V23
[7]  
CHOI J, 1992, 4TH P S FRONT MASS P, P120
[8]  
Clermont P., 1994, Proceedings Eighth International Parallel Processing Symposium (Cat. No.94TH0652-8), P682, DOI 10.1109/IPPS.1994.288230
[9]  
GEIST A, 1993, ORNLTM12187
[10]   PROGRAMMING FOR PARALLELISM [J].
KARP, AH .
COMPUTER, 1987, 20 (05) :43-57
12