Abstract:Abstract-The FSM-SADF model of computation allows to find a tight bound on the throughput of firm real-time applications by capturing dynamic variations in scenarios. We explore an FSM-SADF programming model, and propose three different alternatives for scenario switching. The best candidate for our CompSOC platform was implemented, and experiments confirm that the tight throughput bound results in a reduced resource budget. This comes at the cost of a predictable overhead at runtime as well as increased commu… Show more
“…In [3], the FSM-SADF model is presented as another analysis model for adaptive streaming applications. To implement an application modeled and analyzed with FSM-SADF, two programming models have been proposed in [9] and [10]. In [9], the programming model is constructed by merging the SDF graphs of all scenarios into a single graph which may be larger than the FSM-SADF analysis graph.…”
Section: Related Workmentioning
confidence: 99%
“…To implement an application modeled and analyzed with FSM-SADF, two programming models have been proposed in [9] and [10]. In [9], the programming model is constructed by merging the SDF graphs of all scenarios into a single graph which may be larger than the FSM-SADF analysis graph. Then, to enable switching to a new scenario, all actors in all scenarios are constantly kept active while only those actors belonging to the identified new scenario by a detecting actor(s) will be executed after switching.…”
It has been shown that the mode-aware dataflow (MADF) is an advantageous analysis model for adaptive streaming applications. However, no attention has been paid on how to implement and execute an application, modeled and analyzed with the MADF model, on a Multi-Processor System-on-Chip, such that the properties of the analysis model are preserved. Therefore, in this paper, we consider this matter and propose a generic parallel implementation and execution approach for adaptive streaming applications modeled with MADF. Our approach can be easily realized on top of existing operating systems while supporting the utilization of a wider range of schedules. In particular, we demonstrate our approach on LITMUS RT as one of the existing real-time extensions of the Linux kernel. Finally, to show the practical applicability of our approach and its conformity to the analysis model, we present a case study using a real-life adaptive streaming application.
“…In [3], the FSM-SADF model is presented as another analysis model for adaptive streaming applications. To implement an application modeled and analyzed with FSM-SADF, two programming models have been proposed in [9] and [10]. In [9], the programming model is constructed by merging the SDF graphs of all scenarios into a single graph which may be larger than the FSM-SADF analysis graph.…”
Section: Related Workmentioning
confidence: 99%
“…To implement an application modeled and analyzed with FSM-SADF, two programming models have been proposed in [9] and [10]. In [9], the programming model is constructed by merging the SDF graphs of all scenarios into a single graph which may be larger than the FSM-SADF analysis graph. Then, to enable switching to a new scenario, all actors in all scenarios are constantly kept active while only those actors belonging to the identified new scenario by a detecting actor(s) will be executed after switching.…”
It has been shown that the mode-aware dataflow (MADF) is an advantageous analysis model for adaptive streaming applications. However, no attention has been paid on how to implement and execute an application, modeled and analyzed with the MADF model, on a Multi-Processor System-on-Chip, such that the properties of the analysis model are preserved. Therefore, in this paper, we consider this matter and propose a generic parallel implementation and execution approach for adaptive streaming applications modeled with MADF. Our approach can be easily realized on top of existing operating systems while supporting the utilization of a wider range of schedules. In particular, we demonstrate our approach on LITMUS RT as one of the existing real-time extensions of the Linux kernel. Finally, to show the practical applicability of our approach and its conformity to the analysis model, we present a case study using a real-life adaptive streaming application.
“…An existing FSM-SADF programming model splits off oneactor detector scenarios in a similar way [7]. There all actors fire but execute the encapsulated functions conditionally based on a scenario identifier token.…”
Section: Related Workmentioning
confidence: 99%
“…before it fires. The behaviour during runtime can be matched to the analysis steps listed in Subsection III-C as follows: (a) the output port of Sw is connected to the FIFO towards df ; (b) Sw fires and consumes all of its tokens (4 in III-C); (c) Sw produces tokens into the connected FIFO (5); (d) execution of S full continues as usual (6,7,8,1).…”
Section: A Switch and Select Implementationmentioning
Abstract-The FSM-SADF model of computation is especially suitable for analysing real-time applications with inputdependent behaviour such as different modes, variable execution times and scalable parallelism. Although FSM-SADF specifies which scenario transitions are possible, it does not specify how and when they are decided at runtime. Multiple actors of a scenario, e.g. video stream header parsing, may have to fire before it is known which scenario the application is in. We solve this causality dilemma with a concept for executing a sequence of scenarios, and demonstrate an implementation on multiple processors with rolling static-order scheduling. We furthermore present a platform-aware analysis model that covers concept and implementation, and integrate the contributions in a toolflow. A proof-of-concept confirms the low overhead of the implementation and the exact timing analysis of our model.
“…However, during mode change, the contexts of runnables that are executed on different cores in two subsequent modes need to be migrated from one core to another and the time of this migration shall be bounded, as hard real-time systems are considered in this paper. Therefore, the worst case switching time has to be assumed to provide the timing guarantees [8]. To migrate all involved runnables' contexts during a required interval, some additional requirements for the available communication bandwidth can be imposed.…”
In this paper, a novel resource allocation approach dedicated to hard real-time systems with distinctive operational modes is proposed. The aim of this approach is to reduce the energy dissipation of the computing cores by either powering them off or switching them into energy-saving states while still guaranteeing to meet all timing constraints. The approach is illustrated with two industrial applications, an engine control management and an engine control unit. Moreover, the amount of data to be migrated during the mode change is minimised. Since the number of processing cores and their energy dissipation are often negatively correlated with the amount of data to be migrated during the mode change, there is some trade-off between these values, which is also analysed in this paper.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.