PARALLEL I/O AS A PARALLEL APPLICATION

被引:3
|
作者
MOYER, SA
SUNDERAM, VS
机构
[1] DEPARTMENT OF MATHEMATICS AND COMPUTER SCIENCE, EMORY UNIVERSITY, ATLANTA
关键词
D O I
10.1177/109434209500900203
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Metacomputing environments provide a software platform for implementing parallel applications utilizing networked computing resources. Such programming environments offer a cost-effective alternative to parallel machines for many classes of problems. Unfortunately, most metacomputing environments either provide no I/O facilities, or serialize all I/O requests and thus limit application performance and scalability. PIOUS is a parallel file system designed to incorporate true parallel I/O into existing metacomputing environments. Because PIOUS is itself a parallel application, the functionality of a given metacomputing environment is extended without modification. This paper examines the PIOUS software architecture and programming model and presents preliminary results from a prototype PIOUS implementation. Performance results are encouraging, demonstrating the potential of the PIOUS architecture for achieving scalable file system bandwidth in a network computing environment.
引用
收藏
页码:95 / 107
页数:13
相关论文
共 50 条
  • [41] PARALLEL ALTERNATIVES FOR THE SUPERCOMPUTER I/O BOTTLENECK
    SILVERMAN, I
    COMPUTER DESIGN, 1987, 26 (06): : 60 - 60
  • [42] Visualization and parallel I/O at extreme scale
    Ross, R. B.
    Peterka, T.
    Shen, H-W
    Hong, Y.
    Ma, K-L
    Yu, H.
    Moreland, K.
    SCIDAC 2008: SCIENTIFIC DISCOVERY THROUGH ADVANCED COMPUTING, 2008, 125
  • [43] A parallel DSP with memory and I/O processors
    Srini, VP
    Thendean, J
    Ueng, SZ
    Rabaey, JM
    PARALLEL AND DISTRIBUTED METHODS FOR IMAGE PROCESSING II, 1998, 3452 : 2 - 13
  • [44] Remote parallel I/O in grid environments
    Berrendorf, Rudolf
    Hermanns, Marc-Andre
    Seidel, Jan
    PARALLEL PROCESSING AND APPLIED MATHEMATICS, 2006, 3911 : 212 - 219
  • [45] Performance research of the distributed parallel server system with distributed parallel I/O interface
    Liu, Xin-Song
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2002, 30 (12): : 1808 - 1810
  • [46] FULLY PARALLEL MESH I/O USING PETSC DMPLEX WITH AN APPLICATION TO WAVEFORM MODELING
    Hapla, Vaclav
    Knepley, Matthew G.
    Afanasiev, Michael
    Boehm, Christian
    van Driel, Martin
    Krischer, Lion
    Fichtner, Andreas
    SIAM JOURNAL ON SCIENTIFIC COMPUTING, 2021, 43 (02): : C127 - C153
  • [47] Automatic Cloud I/O Configurator for I/O Intensive Parallel Applications
    Zhai, Jidong
    Liu, Mingliang
    Jin, Ye
    Ma, Xiaosong
    Chen, Wenguang
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2015, 26 (12) : 3275 - 3288
  • [48] Pattern Matching and I/O Replay for POSIX I/O in Parallel Programs
    Kluge, Michael
    Knuepfer, Andreas
    Mueller, Matthias
    Nagel, Wolfgang F.
    EURO-PAR 2009: PARALLEL PROCESSING, PROCEEDINGS, 2009, 5704 : 45 - 56
  • [49] Iteration Based Collective I/O Strategy for Parallel I/O Systems
    Wang, Zhixiang
    Shi, Xuanhua
    Jin, Hai
    Wu, Song
    Chen, Yong
    2014 14TH IEEE/ACM INTERNATIONAL SYMPOSIUM ON CLUSTER, CLOUD AND GRID COMPUTING (CCGRID), 2014, : 287 - 294
  • [50] I/O optimization in the checkpointing of OpenMP parallel applications
    Losada, Nuria
    Martin, Maria J.
    Rodriguez, Gabriel
    Gonzalez, Patricia
    23RD EUROMICRO INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED, AND NETWORK-BASED PROCESSING (PDP 2015), 2015, : 222 - 229