Are virtual channels the bottleneck of priority-aware wormhole-switched NoC-based many-cores?

2016 IEEE 22nd International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)

2016

Flit-level preemptions via virtual channels have been proposed as one viable method to implement priority preemptive arbitration policies in NoC routers, and integrate NoCs in the hard real-time domain. In recent years, researchers have explored several aspects of priority-preemptive NoCs, such as different arbitration techniques, different priority assignmen tmethods (where applicable) and different workload mapping approaches, all with the common objective to use interconnect mediums more efficiently. Yet, the impact of different routing techniques on such a model is still an unexplored topic. Motivated by this reality, in this work we study the effects of routing flexibility on wormhole-switched priority-preemptive NoCs. Abstract-Flit-level preemptions via virtual channels have been proposed as one viable method to implement prioritypreemptive arbitration policies in NoC routers, and integrate NoCs in the hard real-time domain. In recent years, researchers have explored several aspects of priority-preemptive NoCs, such as different arbitration techniques, different priority assignment methods (where applicable) and different workload mapping approaches, all with the common objective to use interconnect mediums more efficiently. Yet, the impact of different routing techniques on such a model is still an unexplored topic. Motivated by this reality, in this work we study the effects of routing flexibility on wormhole-switched priority-preemptive NoCs.

Section: Related Workmentioning

confidence: 99%

On Routing Flexibility of Wormhole-Switched Priority-Preemptive NoCs

Nikolic

Pinho

2016 IEEE 22nd International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)

2016

“…Mathematically, it represents an infinite series of intervals, such as: [100,140), [200,240),.... This extension is expressive enough to represent strictly periodic tasks.…”

Section: Modelling Load Temporal Behaviourmentioning

confidence: 99%

“…H is the hop number between source and destination cores. The remaining terms of Equation (5.4) can be computed with equations [61,100]:…”

Section: Proposed Approach 87mentioning

confidence: 99%

Dynamic Resource Allocation in Embedded, High-Performance and Cloud Computing

Dynamic Resource Allocation in Embedded, High-Performance and Cloud Computing

Dziurzański

Singh

2016

The "River Publishers Series in Information Science and Technology" covers research which ushers the 21st Century into an Internet and multimedia era. Multimedia means the theory and application of filtering, coding, estimating, analyzing, detecting and recognizing, synthesizing, classifying, recording, and reproducing signals by digital and/or analog devices or techniques, while the scope of "signal" includes audio, video, speech, image, musical, multimedia, data/content, geophysical, sonar/radar, bio/medical, sensation, etc. Networking suggests transportation of such multimedia contents among nodes in communication and/or computer networks, to facilitate the ultimate Internet.Theory, technologies, protocols and standards, applications/services, practice and implementation of wired/wireless networking are all within the scope of this series. Based on network and communication science, we further extend the scope for 21st Century life through the knowledge in robotics, machine learning, embedded systems, cognitive science, pattern recognition, quantum/biological/molecular computation and information processing, biology, ecology, social science and economics, user behaviors and interface, and applications to health and society advance.Books published in the series include research monographs, edited volumes, handbooks and textbooks. The books provide professionals, researchers, educators, and advanced students in the field with an invaluable insight into the latest research and developments.

“…They can therefore easily be applied to thousands of individuals across hundreds of generations. Following this trend, Ayari et al proposed the use of custom genetic operators to make better use of schedulability models as search guides in GAs [3], and Nikolic et al proposed the minimisation of NoC virtual channels by using schedulability models to guide a simulated annealing heuristic [10]. The possibilities of multi-objective optimisation of search heuristics were investigated in [12], which combines a schedulability model based on [13], and the energy macromodel from [11].…”

Section: Introductionmentioning

confidence: 99%

“…Among the works referenced above, most of them either consider hard real-time constraints over task computation latencies [3] or over NoC communication latencies [9], [10]. Sayuti [12] was the first to consider constraints over end-to-end latencies (i.e.…”

Section: Introductionmentioning

confidence: 99%

Memory-Aware Genetic Algorithms for Task Mapping on Hard Real-Time Networks-on-Chip

Still

2018 26th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)

2018

Abstract-The problem of mapping hard real-time tasks onto networks-on-chip has previously been successfully addressed by genetic algorithms. However, none of the existing problem formulations consider memory constraints. State-of-the-art genetic mappers are therefore able to find fully-schedulable mappings which are incompatible with the memory limitations of realistic platforms. In this paper, we extend the problem formulation and devise a memory architecture, in the form of private local memories. We then propose three memory models of increasing complexity and realism, and evaluate the impact these additional constraints pose to the genetic search. We conduct extensive experiments using tasks and communications from a realistic benchmark application, and compare the proposed approach against a state-of-the-art baseline mapper.