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
来源
MIDDLEWARE'18: PROCEEDINGS OF THE 2018 ACM/IFIP/USENIX MIDDLEWARE CONFERENCE | 2018年
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] Relaxed Synchronization with Ordered Read-Write Locks
    Gustedt, Jens
    Jeanvoine, Emmanuel
    EURO-PAR 2011: PARALLEL PROCESSING WORKSHOPS, PT I, 2012, 7155 : 387 - 397
  • [2] Iterative computations with ordered read-write locks
    Clauss, Pierre-Nicolas
    Gustedt, Jens
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2010, 70 (05) : 496 - 504
  • [3] 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
  • [4] The cost of concurrent, low-contention Read&Modify&Write
    Busch, C
    Mavronicolas, M
    Spirakis, P
    THEORETICAL COMPUTER SCIENCE, 2005, 333 (03) : 373 - 400
  • [5] Anonymous Read/Write Memory: Leader Election and De-anonymization
    Godard, Emmanuel
    Imbs, Damien
    Raynal, Michel
    Taubenfeld, Gadi
    STRUCTURAL INFORMATION AND COMMUNICATION COMPLEXITY, SIROCCO 2019, 2019, 11639 : 246 - 261
  • [6] Mutex-Based De-anonymization of an Anonymous Read/Write Memory
    Godard, Emmanuel
    Imbs, Damien
    Raynal, Michel
    Taubenfeld, Gadi
    NETWORKED SYSTEMS, NETYS 2019, 2019, 11704 : 311 - 326
  • [7] Automated Refactoring from Synchronized Locks to Reentrant Locks
    Zhang, Yang
    Zhang, Dongwen
    Wang, Huiyong
    INTERNATIONAL JOURNAL OF GRID AND DISTRIBUTED COMPUTING, 2016, 9 (06): : 71 - 81
  • [8] Mutable locks: Combining the best of spin and sleep locks
    Marotta, Romolo
    Tiriticco, Davide
    Di Sanzo, Pierangelo
    Pellegrini, Alessandro
    Ciciani, Bruno
    Quaglia, Francesco
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2020, 32 (22)
  • [9] Reciprocating Locks
    Dice, Dave
    Kogan, Alex
    PROCEEDINGS OF THE 2025 THE 30TH ACM SIGPLAN ANNUAL SYMPOSIUM ON PRINCIPLES AND PRACTICE OF PARALLEL PROGRAMMING, PPOPP 2025, 2025, : 85 - 98
  • [10] Malthusian Locks
    Dice, Dave
    PROCEEDINGS OF THE TWELFTH EUROPEAN CONFERENCE ON COMPUTER SYSTEMS (EUROSYS 2017), 2017, : 314 - 327