Understanding and overcoming parallelism bottlenecks in ForkJoin applications

Pinto, Gustavo; Canino, Anthony; Castor, Fernando; Xu, Guoqing; Liu, Yu David

doi:10.1109/ase.2017.8115687

Cited by 12 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of them analyze the data dependences in concurrency [63,69] . Furthermore, the code understanding is used to solve problems in refactoring and performance optimization [60,70] . To the best of our knowledge, there has no technique that aims at thread control dependences yet.…”

Section: Understanding Concurrent Programsmentioning

confidence: 99%

Tracking runtime concurrent dependences in java threads using thread control profiling

Wang

2019

Journal of Systems and Software

View full text Add to dashboard Cite

More than 75% of recent Java projects include some form of concurrent programming. Due to complex interactions between multi-threads, concurrent programs are often harder to understand and test than single threaded programs. To facilitate understanding and testing of concurrent programs, we developed a new profiling method called TCP (Thread Control Profiling). Outputs of TCP presents frequencies of control dependence, which includes thread creation, thread synchronization, interruption, and so on, of the executed thread. TCP first performs static analysis of detailed concurrency syntax and semantics of Java to construct the profiling graph model TCDG (Thread Control Dependence Graph). TCDG is then used for instrumentation and for generating profiles. We have evaluated TCP using a case study and a few experiments. The case study shows that TCP method can effectively prioritize test cases for testing concurrent programs. One experiment shows that outputs from TCP facilitate developers' understanding of concurrent code. Other experiments evaluate various possible overheads introduced by the TCP method. Results show that TCP can provide rich and useful information with reasonable costs.

show abstract

Section: Understanding Concurrent Programsmentioning

confidence: 99%

Tracking runtime concurrent dependences in java threads using thread control profiling

Wang

2019

Journal of Systems and Software

View full text Add to dashboard Cite

show abstract

“…Energy-saving proposals started mainly with hardware before considering software [7]. Since then, many studies have addressed energy efficiency related to software, such as the impact of programming languages and data structures [32,35], and the study of parallel programming frameworks [37].…”

Section: Related Workmentioning

confidence: 99%

Energy awareness and energy efficiency in internet of things middleware: a systematic literature review

et al. 2022

View full text Add to dashboard Cite

The Internet of Things (IoT) is characterized by a myriad of physical devices, together with high heterogeneity in both software and hardware. Middleware platforms have been proposed in order to alleviate such heterogeneity, providing relevant services and easing application development. In IoT systems, energy consumption is a key concern due to the proliferation of devices and their limited battery capacity. IoT middleware platforms can play an important role in providing applications with strategies, and support, for energy-awareness and energy efficiency. Although there is a significant existing body of work related to IoT middleware, there is, as yet, no complementary overview of the state-of-the-art on how these platforms can contribute to energy efficiency and energy-awareness in IoT systems. This paper provides such an overview in the form of a systematic literature review (SLR). The SLR was This work is a contribution to the Energy4Climate Interdisciplinary Center (E4C) of IP Paris and École des Ponts ParisTech, supported by 3rd Programme d'Investissements d'Avenir [ANR-18-EUR-0006-02]. It has been funded by the "Futur & Ruptures" program from Institut Mines Télécom, Fondation Mines-Télécom and Institut Carnot.

show abstract

“…Another area Chappie may provide essential support for is energy testing and debugging, an emerging research direction [6,7,12,23,27,38,40,42,46]. As energy and performance often go hand in hand, this direction may unify with performance bug studies [4,17,33,44] to provide comprehensive software lifecycle support for software non-functional properties.…”

Section: Related Workmentioning

confidence: 99%