Critical-Path-First based allocation of real-time streaming applications on 2D mesh-type multi-cores

Ali, Hazem Ismail; Pinho, Luís Miguel; Åkesson, Benny

doi:10.1109/rtcsa.2013.6732220

Cited by 7 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The initial phase is inspired by the mapping algorithm of dataflow applications on many-core platforms [1], where the objective is to map the mega-task-set τ on the platform Π in such a way that heavily communicating megatasks are mapped as close to each other as possible. This strategy should help in reducing contentions and provide a "good" starting point (initial solution) for further optimisations during subsequent phases.…”

Section: Mapping Methods Overviewmentioning

confidence: 99%

“…The main criteria of the initial phase is to map communicating mega-tasks near to each other by using a core selection methodology proposed by Ali et al [1], that proved to decrease communication overhead and response time of applications. This methodology consists of two main functions, spiral move and find nearest core, as shown in Figure 4.…”

Section: Initial Phasementioning

confidence: 99%

See 1 more Smart Citation

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

Nikolic

Ali

Petters

et al. 2013

Proceedings of the 21st International Conference on Real-Time Networks and Systems

View full text Add to dashboard Cite

Preemptions via virtual channels have been proposed as a means to introduce the notion of priorities and real-time concepts in wormhole-switched NoC-based architectures. This work presents a holistic approach, which utilises a novel three-staged mapping method in order to assess what should be the physical characteristics of the platform (and its interconnect), such that real-time guarantees can be provided, assuming a given workload. We estimate the "gap" between platform characteristics required for the real-time analysis and those of currently available many-core platforms and propose to employ the existing feature of many-core platforms in order to significantly reduce this gap. The experiments demonstrate that virtual channels, an essential prerequisite for the real-time analysis, are not the bottleneck. The approach presented in this paper can help system designers to select/design the most suitable platform for a given workload, such that all temporal constraints are met and over-dimensioning is avoided.

show abstract

Section: Mapping Methods Overviewmentioning

confidence: 99%

Section: Initial Phasementioning

confidence: 99%

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

Nikolic

Ali

Petters

et al. 2013

Proceedings of the 21st International Conference on Real-Time Networks and Systems

View full text Add to dashboard Cite

show abstract

“…The energy saving of simulation results was up to 25% and 2% in dynamic and static scheduling algorithms, respectively. In 2013, a technical report by Ali et al 10 presented critical-path-first (CPF) heuristic algorithm on two-dimensional (2D) mesh multi-core processors. The critical path was associated with the highest impact on the execution time.…”

Section: Introductionmentioning

confidence: 99%

Energy-aware path strategy for embedded network

Fan

2017

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Silent and autonomous work drives embedded systems to closely connect human on daily life. Recently, more and more embedded systems join service chain to form greatly embedded networks. In addition, low-cost and speed time-tomarket characteristics make the increase in embedded network being exponential. As a result, a new battleground of energy saving become a significant challenge as a huge amount of embedded systems collaborate with tasks. To combat energy consumption, we propose an energy-aware path strategy to achieve energy saving. It is designed for system level so as to early examine energy utilization. Our contribution focuses on modeling-embedded network by path matrix. Improving energy evaluation takes dynamic and static energy into consideration. Presenting a new approach on energy distribution evolves from XY coordination to circle domain. The advantages consist of fast modeling various paths and calculating energy consumption. The effectiveness of the proposed method is verified by a set of benchmarks, and the results achieve energy saving for intricacy path of embedded networks.

show abstract

“…Dataflow applications traditionally use static scheduling techniques, i.e. Time Division Multiple Access (TDMA) [2], [4]- [8], however, they have recently been shown to work well also with real-time scheduling techniques [9]- [12], run-time budget schedulers [13], [14] and non-starvation-free schedulers [15].…”

Section: Introductionmentioning

confidence: 99%

Generalized Extraction of Real-Time Parameters for Homogeneous Synchronous Dataflow Graphs

Ali

Åkesson

Pinho

2015

2015 23rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing

Self Cite

View full text Add to dashboard Cite

Many embedded multi-core systems incorporate both dataflow applications with timing constraints and traditional real-time applications. Applying real-time scheduling techniques on such systems provides real-time guarantees that all running applications will execute safely without violating their deadlines. However, to apply traditional realtime scheduling techniques on such mixed systems, a unified model to represent both types of applications running on the system is required. Several earlier works have addressed this problem and solutions have been proposed that address acyclic graphs, implicit-deadline models or are able to extract timing parameters considering specific scheduling algorithms.In this paper, we present an algorithm for extracting real-time parameters (offsets, deadlines and periods) that are independent of the schedulability analysis, other applications running in the system, and the specific platform. The proposed algorithm: 1) enables applying traditional real-time schedulers and analysis techniques on cyclic or acyclic Homogeneous Synchronous Dataflow (HSDF) applications with periodic sources, 2) captures overlapping iterations, which is a main characteristic of the execution of dataflow applications, 3) provides a method to assign offsets and individual deadlines for HSDF actors, and 4) is compatible with widely used deadline assignment techniques, such as NORM and PURE. The paper proves the correctness of the proposed algorithm through formal proofs and examples. Abstract-Many embedded multi-core systems incorporate both dataflow applications with timing constraints and traditional real-time applications. Applying real-time scheduling techniques on such systems provides real-time guarantees that all running applications will execute safely without violating their deadlines. However, to apply traditional real-time scheduling techniques on such mixed systems, a unified model to represent both types of applications running on the system is required. Several earlier works have addressed this problem and solutions have been proposed that address acyclic graphs, implicit-deadline models or are able to extract timing parameters considering specific scheduling algorithms.In this paper, we present an algorithm for extracting real-time parameters (offsets, deadlines and periods) that are independent of the schedulability analysis, other applications running in the system, and the specific platform. The proposed algorithm: 1) enables applying traditional real-time schedulers and analysis techniques on cyclic or acyclic Homogeneous Synchronous Dataflow (HSDF) applications with periodic sources, 2) captures overlapping iterations, which is a main characteristic of the execution of dataflow applications, 3) provides a method to assign offsets and individual deadlines for HSDF actors, and 4) is compatible with widely used deadline assignment techniques, such as NORM and PURE. The paper proves the correctness of the proposed algorithm through formal proofs and examples.

show abstract

Critical-Path-First based allocation of real-time streaming applications on 2D mesh-type multi-cores

Cited by 7 publications

References 34 publications

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

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

Energy-aware path strategy for embedded network

Generalized Extraction of Real-Time Parameters for Homogeneous Synchronous Dataflow Graphs

Contact Info

Product

Resources

About