Low-overhead software transactional memory with progress guarantees and strong semantics

Zhang, Minjia; Huang, Juan; Cao, Man; Bond, Michael D.

doi:10.1145/2858788.2688510

Cited by 5 publications

(11 citation statements)

References 65 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transactional memory [26] aims to simplify concurrent programming. Though the performance of transactional memory systems has been extensively optimized [22], overheads due to bookkeeping and false conflicts can lead to unsatisfactory performance [6,7], even in high-performance TMs like TL2 [12] and LarkTM [52].…”

Section: Related Workmentioning

confidence: 99%

Type-aware transactions for faster concurrent code

Herman

Inala

Huang

et al. 2016

Proceedings of the Eleventh European Conference on Computer Systems

View full text Add to dashboard Cite

It is often possible to improve a concurrent system's performance by leveraging the semantics of its datatypes. We build a new software transactional memory (STM) around this observation. A conventional STM tracks read-and writesets of memory words; even simple operations can generate large sets. Our STM, which we call STO, tracks abstract operations on transactional datatypes instead. Parts of the transactional commit protocol are delegated to these datatypes' implementations, which can use datatype semantics, and new commit protocol features, to reduce bookkeeping, limit false conflicts, and implement efficient concurrency control. We test these ideas on the STAMP benchmark suite for STM applications and on our own prior work, the Silo high-performance in-memory database, observing large performance improvements in both systems.

show abstract

Section: Related Workmentioning

confidence: 99%

Type-aware transactions for faster concurrent code

Herman

Inala

Huang

et al. 2016

Proceedings of the Eleventh European Conference on Computer Systems

View full text Add to dashboard Cite

show abstract

“…Controlling (enforcing) dependences: Runtime support includes transactional memory (e.g., [28,62]), memory model enforcement (e.g., [44,50]), and deterministic execution (e.g., [5,43]).…”

Section: Tracking Cross-thread Dependencesmentioning

confidence: 99%

“…Prior work introduces an STM that uses biased reader-writer locks that employ strict dependence tracking [62]. We call this STM the ST-based STM.…”

Section: St-based Stmmentioning

confidence: 99%

“…Guaranteeing progress. The ST-based STM guarantees progress by detecting all conflicts eagerly and then aborting the younger transaction [54,62]. However, the RT-based STM cannot guarantee progress, since any transaction that fails read validation must abort.…”

Section: Rt-based Stmmentioning

confidence: 99%

“…Transactional memory enforces atomicity, avoiding several challenges associated with using fine-grained locking [13,21,28,30,31,33,40,41,47,51,59,62]. However, existing runtime support is impractical: it relies on unrealistic custom hardware, adds high overhead, or has other serious limitations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Relaxed dependence tracking for parallel runtime support

Zhang

Biswas

Bond

2016

Proceedings of the 25th International Conference on Compiler Construction

Self Cite

View full text Add to dashboard Cite

It is notoriously difficult to achieve both correctness and scalability for many shared-memory parallel programs. To improve correctness and scalability, researchers have developed various kinds of parallel runtime support such as multithreaded record & replay and software transactional memory. Existing forms of runtime support slow programs significantly in order to track an execution's cross-thread dependences accurately. This paper investigates the potential for runtime support to hide latency introduced by dependence tracking, by tracking dependences in a relaxed way-meaning that not all dependences are tracked accurately. The key challenge in relaxing dependence tracking is to preserve both the program's semantics and the runtime support's guarantees. We present an approach called relaxed dependence tracking (RT) and demonstrate its potential by building two types of RT-based runtime support. Our evaluation shows that RT hides much of the latency incurred by dependence tracking, although RT-based runtime support incurs costs and complexity in order to handle relaxed dependence information. By demonstrating how to relax dependence tracking to hide latency while preserving correctness, this work shows the potential for addressing a key cost of dependence tracking, thus advancing knowledge in the design of parallel runtime support.

show abstract

Partial aborts for transactions via first-class continuations

LeMatthew¹,

FluetMatthew²

2015

SIGPLAN Not.

View full text Add to dashboard Cite

Software transactional memory (STM) has proven to be a useful abstraction for developing concurrent applications, where programmers denote transactions with an atomic construct that delimits a collection of reads and writes to shared mutable references. The runtime system then guarantees that all transactions are observed to execute atomically with respect to each other. Traditionally, when the runtime system detects that one transaction conflicts with another, it aborts one of the transactions and restarts its execution from the beginning. This can lead to problems with both execution time and throughput. In this paper, we present a novel approach that uses first-class continuations to restart a conflicting transaction at the point of a conflict, avoiding the re-execution of any work from the beginning of the transaction that has not been compromised. In practice, this allows transactions to complete more quickly, decreasing execution time and increasing throughput. We have implemented this idea in the context of the Manticore project, an ML-family language with support for parallelism and concurrency. Crucially, we rely on constant-time continuation capturing via a continuation-passing-style (CPS) transformation and heap-allocated continuations. When comparing our STM that performs partial aborts against one that performs full aborts, we achieve a decrease in execution time of up to 31% and an increase in throughput of up to 351%.

show abstract

Low-overhead software transactional memory with progress guarantees and strong semantics

Cited by 5 publications

References 65 publications

Type-aware transactions for faster concurrent code

Type-aware transactions for faster concurrent code

Relaxed dependence tracking for parallel runtime support

Partial aborts for transactions via first-class continuations

Contact Info

Product

Resources

About