Lee-TM: A Non-trivial Benchmark Suite for Transactional Memory

Ansari, Mohammad; Kotselidis, Christos; Watson, Ian; Kirkham, Chris; Luján, Mikel; Jarvis, Kim

doi:10.1007/978-3-540-69501-1_21

Cited by 49 publications

(39 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 3 compares the performance of SwissTM, TL2, and TinySTM in the STAMP benchmark suite workloads. 4 SwissTM outperforms TL2 in all STAMP workloads, for all thread counts, excluding the vacation benchmark under low contention where TL2 and SwissTM have the same performance. SwissTM outperforms TL2 by over 50% with eight threads for the bayes, intruder, and yada benchmarks (being almost twice as fast as TL2 in yada), and by over 20% in kmeans (both variants) and labyrinth, while being about 10% faster than TL2 in genome, ssca2, and vacation under high contention.…”

Section: Evaluating Swisstmmentioning

confidence: 87%

See 1 more Smart Citation

On the correctness of transactional memory

Guerraoui

Kapalka

2008

Proceedings of the 13th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming

340

380

View full text Add to dashboard Cite

Transactional memory (TM) is an appealing abstraction for programming multi-core systems. Potential target applications for TM, such as business software and video games, are likely to involve complex data structures and large transactions, requiring specific software solutions (STM). So far, however, STMs have been mainly evaluated and optimized for smaller scale benchmarks.We revisit the main STM design choices from the perspective of complex workloads and propose a new STM, which we call SwissTM. In short, SwissTM is lock-and word-based and uses (1) optimistic (commit-time) conflict detection for read/write conflicts and pessimistic (encounter-time) conflict detection for write/write conflicts, as well as (2) a new two-phase contention manager that ensures the progress of long transactions while inducing no overhead on short ones. SwissTM outperforms state-of-theart STM implementations, namely RSTM, TL2, and TinySTM, in our experiments on STMBench7, STAMP, Lee-TM and red-black tree benchmarks.Beyond SwissTM, we present the most complete evaluation to date of the individual impact of various STM design choices on the ability to support the mixed workloads of large applications.

show abstract

Section: Evaluating Swisstmmentioning

confidence: 87%

“…Lee-TM [4] is a benchmark that offers large, realistic workloads and is based on Lee's circuit routing algorithm. The algorithm takes pairs of points (e.g., of an integrated circuit) as its input and produces non-intersecting routes between them.…”

Section: Stamp Stampmentioning

confidence: 99%

On the correctness of transactional memory

Guerraoui

Kapalka

2008

Proceedings of the 13th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming

340

380

View full text Add to dashboard Cite

show abstract

“…Figure 3 compares the performance of SwissTM, TL2, and TinySTM in the STAMP benchmark suite workloads. 3 SwissTM outperforms TL2 in all STAMP workloads, for all thread counts, excluding the vacation benchmark under low contention where TL2 and SwissTM have the same performance. SwissTM outperforms TL2 by over 50% with eight threads for the bayes, intruder, and yada benchmarks (being almost twice as fast as TL2 in yada), and by over 20% in kmeans (both variants) and labyrinth, while being about 10% faster than TL2 in genome, ssca2, and vacation under high contention.…”

Section: Evaluating Swisstmmentioning

confidence: 87%

“…Lee-TM [3] is a benchmark that offers large, realistic workloads and is based on Lee's circuit routing algorithm. The algorithm takes pairs of points (e.g., of an integrated circuit) as its input and produces non-intersecting routes between them.…”

Section: Stm Benchmarksmentioning

confidence: 99%

Stretching transactional memory

2009

View full text Add to dashboard Cite

Transactional memory (TM) is an appealing abstraction for programming multi-core systems. Potential target applications for TM, such as business software and video games, are likely to involve complex data structures and large transactions, requiring specific software solutions (STM). So far, however, STMs have been mainly evaluated and optimized for smaller scale benchmarks.We revisit the main STM design choices from the perspective of complex workloads and propose a new STM, which we call SwissTM. In short, SwissTM is lock-and word-based and uses (1) optimistic (commit-time) conflict detection for read/write conflicts and pessimistic (encounter-time) conflict detection for write/write conflicts, as well as (2) a new two-phase contention manager that ensures the progress of long transactions while inducing no overhead on short ones. SwissTM outperforms state-of-the-art STM implementations, namely RSTM, TL2, and TinySTM, in our experiments on STMBench7, STAMP, Lee-TM and red-black tree benchmarks.Beyond SwissTM, we present the most complete evaluation to date of the individual impact of various STM design choices on the ability to support the mixed workloads of large applications.

show abstract

“…Usually they are based on the use of software implementations of transactional memory, with varying results in terms of performance. Examples of such efforts include Delaunay triangulation [10], minimum spanning forest of sparse graphs [11] Lee routing algorithm [12], multiplayer game servers such as QuakeTM [13] and Atomic Quake [14] (based on a lock-based version of Quake [15]) and SynQuake [16]; or benchmarks (STMBench7 [17], STAMP [18] and RMS-TM [19], all of them composed of a number of applications representative of a variety of application domains.…”

Section: Survey Of Prior Work Supporting Tm Use Cases Usability and mentioning

confidence: 99%

Towards Transactional Memory for OpenMP

Wong¹,

Ayguadé²,

Gottschlich

et al. 2014

Using and Improving OpenMP for Devices, Tasks, and More

View full text Add to dashboard Cite

other members of the WG21 SG5 Transactional Memory Sub-Group Abstract. The OpenMP specification lacks a shared memory concurrency mechanism that is composable. None of the OpenMP concurrency mechanisms, such as OMP critical, locks, or atomics support composition. In this paper, we motivate the need for transactional memory (TM) in OpenMP chiefly to support composition of realistic programs. However, we also consider whether TM is easier to program than locks; the use-case for TM; and whether a software-only TM can outperform traditional locking through a survey of recent publications. This paper advances upon previous proposals of OpenMP TM by introducing a new construct specifically to handle irrevocable actions, which is also composable. It also proposes a pure atomic transaction construct as well as the concept of transaction safety. Further, we examine how our proposed construct integrates with current OpenMP constructs.

show abstract

Lee-TM: A Non-trivial Benchmark Suite for Transactional Memory

Cited by 49 publications

References 14 publications

On the correctness of transactional memory

On the correctness of transactional memory

Stretching transactional memory

Towards Transactional Memory for OpenMP

Contact Info

Product

Resources

About