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 35 条
[1]  
[Anonymous], 2005, PODC'05: Proceedings of the twenty-fourth annual ACM symposium on Principles of distributed computing
[2]  
[Anonymous], 2007, VLDB
[3]   Concurrent Updates with RCU: Search Tree as an Example [J].
Arbel, Maya ;
Attiya, Hagit .
PROCEEDINGS OF THE 2014 ACM SYMPOSIUM ON PRINCIPLES OF DISTRIBUTED COMPUTING (PODC'14), 2014, :196-205
[4]   Subtleties of transactional memory atomicity semantics [J].
Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA, United States .
IEEE Comput. Archit. Lett., 2006, 2
[5]   Reader-Writer Synchronization for Shared-Memory Multiprocessor Real-Time Systems [J].
Brandenburg, Bjoern B. ;
Anderson, James H. .
PROCEEDINGS OF THE 21ST EUROMICRO CONFERENCE ON REAL-TIME SYSTEMS, 2009, :184-193
[6]  
Calciu I., 2014, 9 ACM SIGPLAN WKSHP
[7]  
Clements AT, 2012, ASPLOS XVII: SEVENTEENTH INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS, P199
[8]  
Corbet J, 2016, BIG READER LOCKS
[9]   CONCURRENT CONTROL WITH READERS AND WRITERS [J].
COURTOIS, PJ ;
HEYMANS, F ;
PARNAS, DL .
COMMUNICATIONS OF THE ACM, 1971, 14 (10) :667-&
[10]  
Dice D., 2014, ABS14076968