Experiences using the cray multi-threaded architecture (MTA-2)

被引:0
|
作者
Anderson, W [1 ]
Rosenberg, R [1 ]
Lanzagorta, M [1 ]
机构
[1] USN, Res Lab, Stennis Space Ctr, MS 39529 USA
关键词
D O I
10.1109/DODUGC.2003.1253421
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The Naval Research Laboratory has recently installed and is operating a 40-processor Cray Multi-Threaded Architecture (MTA-2) computer. The MTA-2 with its hardware support for multi-threading and large uniformly accessible memory offers a promising new paradigm in parallel computing, especially for large problems. In order to evaluate the machine, four typical applications whose structures would lend themselves to the MTA were selected and evaluated in terms of the level of effort and reprogramming required in contrast to the benefits in running in an MTA environment. The amount of changes required to port the code ranged from very little to a substantial rewrite of portions of the code. Performance improvements ranging from a factor of two to more than 10 over the previous implementations were noted.
引用
收藏
页码:378 / 383
页数:6
相关论文
共 50 条
  • [31] Testing Multi-Threaded Applications Using Answer Set Programming
    Xue, Xiaozhen
    Siami-Namini, Sima
    Namin, Akbar Siami
    INTERNATIONAL JOURNAL OF SOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERING, 2018, 28 (08) : 1151 - 1175
  • [32] Accelerating String Matching Using Multi-threaded Algorithm on GPU
    Lin, Cheng-Hung
    Tsai, Sheng-Yu
    Liu, Chen-Hsiung
    Chang, Shih-Chieh
    Shyu, Jyuo-Min
    2010 IEEE GLOBAL TELECOMMUNICATIONS CONFERENCE GLOBECOM 2010, 2010,
  • [33] Efficient Multi-threaded Crawling Using In Memory Data Structures
    Abdeen, Mohammad A. R.
    INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2020, 20 (02): : 88 - 92
  • [34] Towards multi-threaded local tabling using a common table space
    Areias, Miguel
    Rocha, Ricardo
    THEORY AND PRACTICE OF LOGIC PROGRAMMING, 2012, 12 : 427 - 443
  • [35] FlowProf: Profiling Multi-threaded Programs using Information-Flow
    Al Nahian, Ahamed
    Demsky, Brian
    PROCEEDINGS OF THE 33RD ACM SIGPLAN INTERNATIONAL CONFERENCE ON COMPILER CONSTRUCTION, CC 2024, 2024, : 137 - 149
  • [36] Improved MPI Multi-threaded performance using OFI Scalable Endpoints
    Gopalakrishnan, Aravind
    Cabral, Matias A.
    Erwin, James P.
    Ganapathi, Ravindra Babu
    2019 IEEE SYMPOSIUM ON HIGH-PERFORMANCE INTERCONNECTS (HOTI 2019), 2019, : 36 - 39
  • [37] Multi-threaded modularity based graph clustering using the multilevel paradigm
    LaSalle, Dominique
    Karypis, George
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2015, 76 : 66 - 80
  • [38] Using Cycle Stacks to Understand Scaling Bottlenecks in Multi-Threaded Workloads
    Heirman, Wim
    Carlson, Trevor E.
    Che, Shuai
    Skadron, Kevin
    Eeckhout, Lieven
    2011 IEEE INTERNATIONAL SYMPOSIUM ON WORKLOAD CHARACTERIZATION (IISWC), 2011, : 38 - 49
  • [39] Multi-threaded Fast Distance Field Computation Using Spatial Partition
    MIN De-heng
    JIA Shi-yu
    ZHANG Xiao-yun
    科技视界, 2015, (08) : 153 - 154
  • [40] A Multi-Threaded Approach to Using Asynchronous C Libraries with Java']Java
    Gates, John
    Deich, William
    SOFTWARE AND CYBERINFRASTRUCTURE FOR ASTRONOMY III, 2014, 9152