2017 IEEE 16th International Symposium on Network Computing and Applications (NCA) 2017
DOI: 10.1109/nca.2017.8171349
|View full text |Cite
|
Sign up to set email alerts
|

Prompt application-transparent transaction revalidation in software transactional memory

Abstract: Software Transactional Memory (STM) allows encapsulating shared-data accesses within transactions, executed with atomicity and isolation guarantees. The assessment of the consistency of a running transaction is performed by the STM layer at specific points of its execution, such as when a read or write access to a shared object occurs, or upon a commit attempt. However, performance and energy efficiency issues may arise when no shared-data read/write operation occurs for a while along a thread running a transa… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
1
1

Relationship

2
0

Authors

Journals

citations
Cited by 2 publications
(4 citation statements)
references
References 5 publications
0
4
0
Order By: Relevance
“…Many proposals focus on designing, optimizing, or tuning the conflict detection and management algorithms used by STM implementations. 4,[8][9][10][11][12]17 Other studies proposed compiler-based and runtime techniques which use statistics collected at runtime to identify performance bottlenecks and to guide tuning decisions (e.g., Wu et al 25 ). Further, autonomic-computing approaches for mapping threads to the different cores in multi-core machines, as well as machine learning-based techniques for improving the performance of STM application at runtime have been studied (e.g., Xiao et al 26 and Zhou et al 27 ).…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…Many proposals focus on designing, optimizing, or tuning the conflict detection and management algorithms used by STM implementations. 4,[8][9][10][11][12]17 Other studies proposed compiler-based and runtime techniques which use statistics collected at runtime to identify performance bottlenecks and to guide tuning decisions (e.g., Wu et al 25 ). Further, autonomic-computing approaches for mapping threads to the different cores in multi-core machines, as well as machine learning-based techniques for improving the performance of STM application at runtime have been studied (e.g., Xiao et al 26 and Zhou et al 27 ).…”
Section: Related Workmentioning
confidence: 99%
“…In particular, the latter aspect requires the programmer's care to write transactional code that is idempotent in writing thread-private data, thus increasing the complexity level. Concerning the performance issue, a great effort has been made by researchers to limit the performance impact of STM and to improve the STM performance through various approaches, spanning from alternative conflict detection and resolution algorithms, 4,[8][9][10][11] to dynamic concurrency control and dynamic tuning, 12,13 and to transaction scheduling techniques. [14][15][16][17][18][19][20][21][22] However, one approach that has been less explored is the partial abort of transactions, particularly with the goal of designing effective runtime mechanisms to make this approach viable and transparent on off-the-shelf systems.…”
Section: Introductionmentioning
confidence: 99%
“…In [12] the transaction validity check is triggered periodically, via an ad-hoc operating system support integrated within Linux. Differently from this proposal, our model-based readvalidation scheme does not need special support within the operating system, thus being of wider applicability.…”
Section: Related Workmentioning
confidence: 99%
“…Differently from this proposal, our model-based readvalidation scheme does not need special support within the operating system, thus being of wider applicability. Also, the solution in [12] does not rely on any prediction scheme for choosing at which points to attempt transaction validation. The validation task is triggered independently of the probability that the transaction has become invalid.…”
Section: Related Workmentioning
confidence: 99%