McRT-STM

Saha, Badal C.; Adl-Tabatabai, Ali-Reza; Hudson, Richard L.; Minh, Chi Cao; Hertzberg, Benjamin C.

doi:10.1145/1122971.1123001

Cited by 308 publications

(23 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e two most common options are sometimes referred to as "undo logging" [Harris et al, 2006, Saha et al, 2006a, in which changes are made "in place," but old values are buffered for writeback on abort, and "redo logging" [Dice et al, 2006, Harris andFraser, 2003], in which new values are buffered for write-back on commit. e two most common options are sometimes referred to as "undo logging" [Harris et al, 2006, Saha et al, 2006a, in which changes are made "in place," but old values are buffered for writeback on abort, and "redo logging" [Dice et al, 2006, Harris andFraser, 2003], in which new values are buffered for write-back on commit.…”

Section: Dimensions Of the Stm Design Spacementioning

confidence: 99%

Shared-Memory Synchronization

Scott¹

2013

Synthesis Lectures on Computer Architecture

View full text Add to dashboard Cite

Synthesis Lectures on Computer Architecture publishes 50-to 100-page publications on topics pertaining to the science and art of designing, analyzing, selecting and interconnecting hardware components to create computers that meet functional, performance and cost goals. e scope will largely follow the purview of premier computer architecture conferences, such as ISCA, HPCA, MICRO, and ASPLOS. ABSTRACTSince the advent of time sharing in the 1960s, designers of concurrent and parallel systems have needed to synchronize the activities of threads of control that share data structures in memory. In recent years, the study of synchronization has gained new urgency with the proliferation of multicore processors, on which even relatively simple user-level programs must frequently run in parallel.is lecture offers a comprehensive survey of shared-memory synchronization, with an emphasis on "systems-level" issues. It includes sufficient coverage of architectural details to understand correctness and performance on modern multicore machines, and sufficient coverage of higher-level issues to understand how synchronization is embedded in modern programming languages.e primary intended audience is "systems programmers"-the authors of operating systems, library packages, language run-time systems, concurrent data structures, and server and utility programs. Much of the discussion should also be of interest to application programmers who want to make good use of the synchronization mechanisms available to them, and to computer architects who want to understand the ramifications of their design decisions on systems-level code.

show abstract

Section: Dimensions Of the Stm Design Spacementioning

confidence: 99%

Shared-Memory Synchronization

Scott¹

2013

Synthesis Lectures on Computer Architecture

View full text Add to dashboard Cite

show abstract

“…Our implementation approach is similar to that of the McRT software transactional memory (STM) system [19]. McRT associates with each object (or word, the granularity being determined on a per-type basis) a transaction record.…”

Section: Stm Implementationmentioning

confidence: 99%

Closed and open nested atomic actions for Java

Chapman

Hosking

Moss

et al. 2014

Proceedings of the 2014 International Conference on Principles and Practices of Programming on the Java Platform: Virtual Machi

View full text Add to dashboard Cite

We describe the design and prototype implementation of a dialect of Java, XJ, that supports both closed and open nested transactions. As we have previously advocated, open nesting most naturally attaches to the class as the primary abstraction mechanism of Java. The resulting design allows natural expression of layered abstractions for concurrent data structures, while promoting improved concurrency for operations on those abstractions. Moreover, we describe our approach to constructing a prototype implementation of XJ that runs on standard Java virtual machines, by grafting support for transactions onto both application code and library code via load-time bytecode rewriting, for full execution coverage. We rely on extensions to the javac compiler, a JVMTI run-time agent to intercept and rewrite Java classes as they are loaded into the virtual machine, and a run-time library that tracks and manages all transaction meta-data. The resulting prototype will allow further exploration of implementation alternatives for open and closed nested transactions in Java. Our design also addresses the issue of internal deadlock caused by accessing the same data in both closed and open nesting fashion by carefully disallowing such access.

show abstract

“…Shavit and Touitou [5] then proposed software transactional memory (STM) where TM is implemented only with a software method. There have been many studies on implementations of STM [11]- [17].…”

Section: Related Workmentioning

confidence: 99%

An Experiment on Performing DSTM Applications in a Public Cloud

Yoshino

Aritsugi

2012

2012 41st International Conference on Parallel Processing Workshops

View full text Add to dashboard Cite

Performing distributed software transactional memory (DSTM) applications in a public cloud is investigated in this paper. Transactions are introduced in DSTM for simplifying parallel programming in distributed environments. DSTM is thus a promising alternative to lock-based programming models. Cloud computing attracts attention as a new way for commercial applications and for processing largescale data. However, to our knowledge, there is no study of executing DSTM applications using public clouds. In this paper, we report an experiment on performing DSTM applications in a public cloud. We also try to construct a performance model by adapting a TM performance model to DSTM in order to decide which cloud resources to be chosen in executing DSTM applications. Experimental results show that there are strong and weak points our DSTM model has in deciding machine types and the number of machines for performance.

show abstract

McRT-STM

Cited by 308 publications

References 25 publications

Shared-Memory Synchronization

Shared-Memory Synchronization

Closed and open nested atomic actions for Java

An Experiment on Performing DSTM Applications in a Public Cloud

Contact Info

Product

Resources

About