English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Task-based programming models have demonstrated their efficiency in thedevelopment of scientific applications on modern high-performance platforms.They allow delegation of the management of parallelization to the runtimesystem (RS), which is in charge of the data coherency, the scheduling, and theassignment of the work to the computational units. However, some applicationshave a limited degree of parallelism such that no matter how efficient the RSimplementation, they may not scale on modern multicore CPUs. In this paper, wepropose using speculation to unleash the parallelism when it is uncertain ifsome tasks will modify data, and we formalize a new methodology to enablespeculative execution in a graph of tasks. This description is partiallyimplemented in our new C++ RS called SPETABARU, which is capable of executingtasks in advance if some others are not certain to modify the data. We studythe behavior of our approach to compute Monte Carlo and replica exchange MonteCarlo simulations.

Increasing the Degree of Parallelism Using Speculative Execution in Task-based Runtime Systems