Optimizing memory transactions

Harris, Tim; Pleško, M.; Shinnar, Avraham; Tarditi, David

doi:10.1145/1133981.1133984

Cited by 192 publications

(145 citation statements)

References 17 publications

Supporting

Mentioning

122

Contrasting

Order By: Relevance

“…In managed code, it appears possible to use run-time sandboxing to contain any erroneous behavior in doomed transactions [6,11]. For unmanaged code, or as an alternative for managed environments, we present three mechanisms to avoid the inconsistencies that give rise to the problem in the first place.…”

Section: Preventing the Doomed Transaction Problemmentioning

confidence: 99%

Ordering-Based Semantics for Software Transactional Memory

Spear

Dalessandro

Marathe

et al. 2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

It has been widely suggested that memory transactions should behave as if they acquired and released a single global lock. Unfortunately, this behavior can be expensive to achieve, particularly whenas in the natural publication/privatization idiom-the same data are accessed both transactionally and nontransactionally. To avoid overhead, we propose selective strict serializability (SSS) semantics, in which transactions have a global total order, but nontransactional accesses are globally ordered only with respect to explicitly marked transactions. Our definition of SSS formally characterizes the permissible behaviors of an STM system without recourse to locks. If all transactions are marked, then SSS, singlelock semantics, and database-style strict serializability are equivalent.We evaluate several SSS implementations in the context of a TL2-like STM system. We also evaluate a weaker model, selective flow serializability (SFS), which is similar in motivation to the asymmetric lock atomicity of Menon et al. We argue that ordering-based semantics are conceptually preferable to lock-based semantics, and just as efficient.

show abstract

Section: Preventing the Doomed Transaction Problemmentioning

confidence: 99%

Ordering-Based Semantics for Software Transactional Memory

Spear

Dalessandro

Marathe

et al. 2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Lower-level semantics embody various strategies for the implementation of these constructs. For instance, those lowerlevel semantics can include optimistic concurrent execution of transactions, with in-place updates to memory, conflict detection, and roll-backs [11]. In particular, the implementation of AME for C# on Bartok-STM relies on these features.…”

Section: Further Workmentioning

confidence: 99%

“…We also define and study a simple static type system that indicates whether yielding is possible in a piece of code. A practical version of this type system has been implemented for an extension of C# on Bartok-STM [11].…”

Section: Introductionmentioning

confidence: 99%

Automatic Mutual Exclusion and Atomicity Checks

Abadi

2008

Concurrency, Graphs and Models

View full text Add to dashboard Cite

Abstract. This paper provides an introduction to the Automatic Mutual Exclusion (AME) programming model and to its formal study, through the AME calculus. AME resembles cooperative multithreading; in the intended implementations, however, software transactional memory supports the concurrent execution of atomic fragments. This paper also studies simple dynamic and static mechanisms for atomicity checks in AME.

show abstract

“…Recent proposals from Microsoft Research [9,10] focus on word-based STM using Haskell and C#. The C# STM uses aggressive compiler optimization to reduce overheads, while the Haskell TM focuses on rich semantics for composability.…”

Section: Related Workmentioning

confidence: 99%

Conflict Detection and Validation Strategies for Software Transactional Memory

Spear

Marathe

Scherer

et al. 2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In a software transactional memory (STM) system, conflict detection is the problem of determining when two transactions cannot both safely commit. Validation is the related problem of ensuring that a transaction never views inconsistent data, which might potentially cause a doomed transaction to exhibit irreversible, externally visible side effects. Existing mechanisms for conflict detection vary greatly in their degree of speculation and their relative treatment of read-write and write-write conflicts. Validation, for its part, appears to be a dominant factor-perhaps the dominant factor-in the cost of complex transactions.We present the most comprehensive study to date of conflict detection strategies, characterizing the tradeoffs among them and identifying the ones that perform the best for various types of workload. In the process we introduce a lightweight heuristic mechanism-the global commit counter-that can greatly reduce the cost of validation and of single-threaded execution. The heuristic also allows us to experiment with mixed invalidation, a more opportunistic interleaving of reading and writing transactions. Experimental results on a 16-processor SunFire machine running our RSTM system indicate that the choice of conflict detection strategy can have a dramatic impact on performance, and that the best choice is workload dependent. In workloads whose transactions rarely conflict, the commit counter does little to help (and can even hurt) performance. For less scalable applications, however-those in which STM performance has traditionally been most problematic-it can improve transaction throughput many fold.

show abstract

Optimizing memory transactions

Cited by 192 publications

References 17 publications

Ordering-Based Semantics for Software Transactional Memory

Ordering-Based Semantics for Software Transactional Memory

Automatic Mutual Exclusion and Atomicity Checks

Conflict Detection and Validation Strategies for Software Transactional Memory

Contact Info

Product

Resources

About