Performance Evaluation of Intel® Transactional Synchronization Extensions for High-Performance Computing

被引:66
|
作者
Yoo, Richard M. [1 ]
Hughes, Christopher J. [1 ]
Lai, Konrad [2 ]
Rajwar, Ravi [2 ]
机构
[1] Intel Labs, Parallel Comp Lab, Santa Clara, CA 95054 USA
[2] Intel Architecture Grp, Intel Architecture Dev Grp, Hillsboro, OR 97124 USA
来源
2013 INTERNATIONAL CONFERENCE FOR HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS (SC) | 2013年
关键词
Transactional Memory; High-Performance Computing;
D O I
10.1145/2503210.2503232
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Intel has recently introduced Intel (R) Transactional Synchronization Extensions (Intel (R) TSX) in the Intel 4th Generation Core (TM) Processors. With Intel TSX, a processor can dynamically determine whether threads need to serialize through lock-protected critical sections. In this paper, we evaluate the first hardware implementation of Intel TSX using a set of high-performance computing (HPC) workloads, and demonstrate that applying Intel TSX to these workloads can provide significant performance improvements. On a set of real-world HPC workloads, applying Intel TSX provides an average speedup of 1.41x. When applied to a parallel user-level TCP/IP stack, Intel TSX provides 1.31x average bandwidth improvement on network intensive applications. We also demonstrate the ease with which we were able to apply Intel TSX to the various workloads.
引用
收藏
页数:11
相关论文
共 50 条
  • [41] THE HIGH-PERFORMANCE COMPUTING INITIATIVE
    BROWN, GE
    PHOTONICS SPECTRA, 1991, 25 (07) : 79 - 80
  • [42] High-performance computing - an overview
    Vienna Univ, Vienna, Austria
    Comput Phys Commun, 1-2 (16-35):
  • [43] Thoughts on high-performance computing
    Xuejun Yang
    National Science Review, 2014, 1 (03) : 332 - 333
  • [44] HIGH-PERFORMANCE COMPUTING AND COMMUNICATIONS
    STEVENS, R
    FUTURE GENERATION COMPUTER SYSTEMS, 1994, 10 (2-3) : 159 - 167
  • [45] Challenges in High-Performance Computing
    Navaux P.O.A.
    Lorenzon A.F.
    Serpa M.S.
    Journal of the Brazilian Computer Society, 2023, 29 (01) : 51 - 62
  • [46] HIGH-PERFORMANCE COMPUTING AND PHYSICS
    ORSZAG, SA
    ZABUSKY, NJ
    PHYSICS TODAY, 1993, 46 (03) : 22 - 23
  • [47] AN INTEGRATED HIGH-PERFORMANCE SYNCHRONIZATION PROCESSOR
    HOVENS, PJM
    VANDENELZEN, JC
    SIMONS, MH
    SMEULERS, W
    ULTEE, J
    VANDEWATERLAAT, ACJG
    IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 1985, 31 (03) : 119 - 123
  • [48] High-Performance Computing in Edge Computing Networks
    Tu, Wanqing
    Pop, Florin
    Jia, Weijia
    Wu, Jie
    Iacono, Mauro
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2019, 123 : 230 - 230
  • [49] An evaluation environment for high-performance computing combining supercomputing and cloud
    Gotoh, Yusuke
    Kotani, Toshihiro
    INTERNATIONAL JOURNAL OF GRID AND UTILITY COMPUTING, 2023, 14 (01) : 29 - 36
  • [50] Performance evaluation of Amazon Elastic Compute Cloud for NASA high-performance computing applications
    Mehrotra, Piyush
    Djomehri, Jahed
    Heistand, Steve
    Hood, Robert
    Jin, Haoqiang
    Lazanoff, Arthur
    Saini, Subhash
    Biswas, Rupak
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2016, 28 (04): : 1041 - 1055