Speculative Read Write Locks

被引:2
|
作者
Issa, Shady [1 ]
Romano, Paolo [1 ]
Lopes, Tiago [1 ]
机构
[1] Univ Lisbon, Inst Super Tecn, INESC ID, Lisbon, Portugal
关键词
SYNCHRONIZATION;
D O I
10.1145/3274808.3274825
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Hardware Transactional Memory (HTM) has recently entered the realm of mainstream computing thanks to its integration in processors commercialized by major industrial manufacturers. HTM provides highly-efficient, hardware-assisted synchronization mechanisms for concurrent programs. Unfortunately, though, existing HTM implementations also suffer from severe limitations that are inherently related to their best-effort, hardware-based design. This work introduces SpRWL (Speculative Read Write Lock), a HTM-based implementation of read-write locks that provides a key benefit: allowing readers to execute outside the scope of hardware transactions, thus, effectively sparing them from any HTM-related limitation. SpRWL is the first HTM-based read-write lock implementation to support the concurrent execution of uninstrumented readers, while assuming a standard transaction demarcation API that is universally supported by any HTM implementation. Via an extensive experimental study, we show that SpRWL can achieve striking performance gains (up to 16x) with respect to state of the art read-write lock implementations based not only on pessimistic/lock-based schemes, but also on HTM-based techniques that exploit specific hardware mechanisms currently supported solely by a restricted number of architectures.
引用
收藏
页码:214 / 226
页数:13
相关论文
共 50 条
  • [1] A FAIR BANKER ALGORITHM FOR READ AND WRITE LOCKS
    HENSGEN, DA
    SIMS, DL
    CHARLEY, D
    INFORMATION PROCESSING LETTERS, 1993, 48 (03) : 131 - 137
  • [2] Relaxed Synchronization with Ordered Read-Write Locks
    Gustedt, Jens
    Jeanvoine, Emmanuel
    EURO-PAR 2011: PARALLEL PROCESSING WORKSHOPS, PT I, 2012, 7155 : 387 - 397
  • [3] Iterative computations with ordered read-write locks
    Clauss, Pierre-Nicolas
    Gustedt, Jens
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2010, 70 (05) : 496 - 504
  • [4] Tip #8: Performing multiple read/write locks
    Abramson, Tomer
    C/C++ Users Journal, 2002, 20 (05):
  • [5] Experimenting Iterative Computations with Ordered Read-Write Locks
    Clauss, Pierre-Nicolas
    Gustedt, Jens
    PROCEEDINGS OF THE 18TH EUROMICRO CONFERENCE ON PARALLEL, DISTRIBUTED AND NETWORK-BASED PROCESSING, 2010, : 155 - 162
  • [6] Formal verification of concurrent programs with read-write locks
    Fu, Ming
    Zhang, Yu
    Li, Yong
    FRONTIERS OF COMPUTER SCIENCE IN CHINA, 2010, 4 (01): : 65 - 77
  • [7] Formal verification of concurrent programs with read-write locks
    Ming Fu
    Yu Zhang
    Yong Li
    Frontiers of Computer Science in China, 2010, 4 : 65 - 77
  • [8] A mobile cache consistency protocol using shareable read/write time locks
    Vora, A
    Tari, Z
    Bertok, P
    Lai, K
    NINTH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS, PROCEEDINGS, 2002, : 284 - 290
  • [9] Token-based read/write-locks for distributed mutual exclusion
    Wagner, C
    Mueller, F
    EURO-PAR 2000 PARALLEL PROCESSING, PROCEEDINGS, 2000, 1900 : 1185 - 1195
  • [10] Read write
    Tauzin, Isabelle
    BULLETIN HISPANIQUE, 2008, 110 (01): : 393 - 395