A Hierarchical Distributed Runtime Resource Management Scheme for NoC-Based Many-Cores

Tsoutsouras, Vasileios; Anagnostopoulos, Iraklis; Masouros, Dimosthenis; Soudris, Dimitrios

doi:10.1145/3182173

Cited by 11 publications

(16 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare the MA paradigm with state-of-the-art works that implement distributed management approaches: cluster-based management (CBM) [10], and per-application management (PAM) [25]. The first experiment (Section 5.1) compares the management approaches using task mapping as case-study.…”

Section: Resultsmentioning

confidence: 99%

“…PAM [9,25] assigns one manager core (M) per application. The manager is dynamically created when an application is loaded.…”

Section: Resource Management Organizationsmentioning

confidence: 99%

“…PAM is fully distributed and conceptually more flexible than CBM since each manager is in charge of one application. We identify the following drawbacks of this approach: (i) it is most suitable for systems that assume applications with many tasks [25], which keeps the management overhead per task low (i.e., applications having a small number of tasks will lead to an excessive amount of resources dedicated to management); (ii) the dynamic creation of new managers imposes complex synchronization protocols to take systemic actions since managers are more focused on the applications' goals than system goals.…”

Section: Resource Management Organizationsmentioning

confidence: 99%

“…The CBM approach in [10] supports a wide range of management roles, while the PAM work [25] focuses on task mapping. This experiment addresses dynamic task mapping, allowing a fair comparison between the three distributed management approaches.…”

Section: Case-study: Task Mappingmentioning

confidence: 99%

See 3 more Smart Citations

Modular and Distributed Management of Many-Core SoCs

Ruaro

Sant'Ana

Jantsch

et al. 2020

ACM Trans. Comput. Syst.

View full text Add to dashboard Cite

Many-Core Systems-on-Chip increasingly require Dynamic Multi-objective Management (DMOM) of resources. DMOM uses different management components for objectives and resources to implement comprehensive and self-adaptive system resource management. DMOMs are challenging because they require a scalable and well-organized framework to make each component modular, allowing it to be instantiated or redesigned with a limited impact on other components. This work evaluates two state-of-the-art distributed management paradigms and, motivated by their drawbacks, proposes a new one called Management Application (MA) , along with a DMOM framework based on MA. MA is a distributed application, specific for management, where each task implements a management role. This paradigm favors scalability and modularity because the management design assumes different and parallel modules, decoupled from the OS. An experiment with a task mapping case study shows that MA reduces the overhead of management resources (-61.5%), latency (-66%), and communication volume (-96%) compared to state-of-the-art per-application management. Compared to cluster-based management (CBM) implemented directly as part of the OS, MA is similar in resources and communication volume, increasing only the mapping latency (+16%). Results targeting a complete DMOM control loop addressing up to three different objectives show the scalability regarding system size and adaptation frequency compared to CBM, presenting an overall management latency reduction of 17.2% and an overall monitoring messages’ latency reduction of 90.2%.

show abstract

Section: Resultsmentioning

confidence: 99%

“…PAM [9,25] assigns one manager core (M) per application. The manager is dynamically created when an application is loaded.…”

Section: Resource Management Organizationsmentioning

confidence: 99%

Section: Resource Management Organizationsmentioning

confidence: 99%

Section: Case-study: Task Mappingmentioning

confidence: 99%

See 2 more Smart Citations

Modular and Distributed Management of Many-Core SoCs

Ruaro

Sant'Ana

Jantsch

et al. 2020

ACM Trans. Comput. Syst.

View full text Add to dashboard Cite

show abstract

“…3], shows the hierarchical task mapping approach. In [37], a runtime distributed task mapping approach DRTRM has been proposed. DRTRM is based on the scheme of local managers and controllers.…”

Section: A Dynamic (Run-time) Mapping Techniques In Nocmentioning

confidence: 99%

Performance Evaluation of Application Mapping Approaches for Network-on-Chip Designs

et al. 2020

View full text Add to dashboard Cite

Network-on-chip (NoC) is evolving as a better substitute for incorporating a large number of cores on a single system-on-chip (SoC). The dependency on multi-core systems to accomplish the highperformance constraints of composite embedded applications is on the rise. This leads to the realization of efficient mapping approaches for such complex applications. The significance of efficient application mapping approaches has increased ever since the embedded applications have become more complex and performance-oriented. This paper presents the detailed comparative analysis and categorization of application mapping approaches with current trends in NoC design implementation. These approaches target to improve the performance of the whole system by optimizing communication cost, energy, power consumption, and latency. Apart from the categorization of the discussed approaches, comparison of communication cost, power, energy, and latency of the NoC system carried out on real applications like VOPD and MPEG4. Moreover, the best technique identified in each category based on the evaluation of performance results. INDEX TERMS Network-on-Chip, application mapping, NoC design, VOPD, System-on-Chip. I. INTRODUCTION System-on-Chip (SoC) is an archetype for the design and implementation of on-chip circuits that can support multiple systems on a single chip. The ever-rising number of processing cores on a single chip has made the efficiency of onchip designs as one of the major aspects in evaluating the average performance of embedded SoC. To fulfill the performance needs and to provide flexibility in the designs the field of Network on Chip (NoC) has emerged that separates the communication from the computation. Many surveys [1]-[7] are published in general and textbooks are also available on the topic [8]-[10]. There is still a need to solve more advanced research problems in NoC. Application mapping on NoC architecture has a prominent place among all the research problems which can be arbitrated from the published The associate editor coordinating the review of this manuscript and approving it for publication was Eyuphan Bulut. papers and current trends. This survey assumes a textbooklevel acquaintance of NoC terminology. The aim is to provide a comprehensive overview of all the aspects of application mapping (task graph generation, scheduling, optimization techniques, simulation setup, and performance evaluation metrics). The organization of this survey is as follows; first, we provide the reader the need and overview of application mapping in NoC presented in Section I. A detailed review and calcification of application mapping techniques in NoCs are discussed in Section II. The current and latest trends in application mapping are summarized in Section III. In Section IV performance comparison and the points that can create the difference between these techniques are highlighted. Finally, Section VI concludes this paper. A. MOTIVATION AND SCOPE Mostly synthetic traffic patterns are used to imitate the functionalities of rea...

show abstract