In this paper, we propose novel low-energy scheduling algorithms with low computational complexities for the heterogeneous Body A rea Network (BAN) systems, considering task graphs with deadlines (timing constraints) ...
详细信息
ISBN:
(纸本)9780769529752
In this paper, we propose novel low-energy scheduling algorithms with low computational complexities for the heterogeneous Body A rea Network (BAN) systems, considering task graphs with deadlines (timing constraints) and precedence relationships to satisfy. Our proposed novel scheme, referred to as "critical-path information track-and-up-date ", analyses the critical-paths, identifies the slack and distributes it over tasks such that the overall energy consumption is minimised. Our dynamic scheduling algorithm utilises the results from the static scheduling algorithm and attempts to aggressively reduce the energy consumption. Simulations for the task graph for a typical BAN application show that our static and dynamic scheduling algorithms deliver 25% and 15% more energy savings respectively Compared to typical slack reclamation based scheduling algorithms.
the importance of accounting for interrupts in multiprocessor real-time schedulability analsysis is discussed: three interrupt accounting methods, two of which are newly described here, are analyzed and compared.
ISBN:
(纸本)9780769537870
the importance of accounting for interrupts in multiprocessor real-time schedulability analsysis is discussed: three interrupt accounting methods, two of which are newly described here, are analyzed and compared.
In this paper, we show how code can be generated at different levels of abstraction from a single source description. To this end, we use a model-driven development tool called Averest that is based on a synchronous p...
详细信息
ISBN:
(纸本)9781479908516
In this paper, we show how code can be generated at different levels of abstraction from a single source description. To this end, we use a model-driven development tool called Averest that is based on a synchronous programming language. We illustrate our approach by means of a case study from the domain of distributed real-time automotive embeddedsystems. this paper focuses thereby mainly on the use of the Averest toolkit to generate code at different levels of abstraction.
In this paper we develop a novel real-time instruction-level loop scheduling technique to reduce leakage energy consumption for applications with loops on VLIW architecture. We first prove that the scheduling problem ...
详细信息
ISBN:
(纸本)9780769529752
In this paper we develop a novel real-time instruction-level loop scheduling technique to reduce leakage energy consumption for applications with loops on VLIW architecture. We first prove that the scheduling problem withthe minimum leakage energy consumption within a timing constraint is NP-complete. then, LEMLS (Leakage Energy Minimization Loop Scheduling) algorithm is designed to repeatedly regroup a loop based on rotation scheduling [3], and decrease leakage energy integrating with leakage power reduction mechanism. We conduct experiments on a set of DSP benchmarks based on the power model of the VLIW processors in [12]. the results show that our algorithm achieves significant leakage energy saving compared with list scheduling and the algorithm in [19].
Multi-core platforms are becoming the dominant computing architecture for next generation embeddedsystems. Nevertheless, designing, programming, and analyzing such systems is not easy and a solid methodology is still...
详细信息
ISBN:
(纸本)9780769537870
Multi-core platforms are becoming the dominant computing architecture for next generation embeddedsystems. Nevertheless, designing, programming, and analyzing such systems is not easy and a solid methodology is still missing. In this paper, we propose two powerful abstractions to model the computing power of a parallel machine, which provide a general interface for developing and analyzing real-timeapplications in isolation, independently of the physical platform. the proposed abstractions can be applied on top of different types of service mechanisms, such as periodic servers, static partitions, and P-fair time partitions. In addition, we developed the schedulability analysis of a set of real-time tasks on top of a parallel machine that is compliant withthe proposed abstractions.
Soft real-time sporadic multiprocessor task systems are considered that include processing pipelines. Conditions are presented for guaranteeing bounded deadline tardiness in such systems under global EDF or FIFO sched...
详细信息
ISBN:
(纸本)9780769537870
Soft real-time sporadic multiprocessor task systems are considered that include processing pipelines. Conditions are presented for guaranteeing bounded deadline tardiness in such systems under global EDF or FIFO scheduling. "Early-releasing" is applied to make pipeline scheduling work-conserving. this lessens job response times in lightly-loaded systems.
Many optimal uniprocessor schedulers, such as Earliest Deadline First (EDF) and Rate Monotonic (RM), do not have a good schedulability bound on multiprocessor systems. In this paper we study an on-line algorithm Earli...
详细信息
ISBN:
(纸本)9780769529752
Many optimal uniprocessor schedulers, such as Earliest Deadline First (EDF) and Rate Monotonic (RM), do not have a good schedulability bound on multiprocessor systems. In this paper we study an on-line algorithm Earliest Deadline First until Zero laxity (EDZL) for multiprocessor systems. A set of tasks scheduled by EDZL is scheduled using EDF until a job experiences a zero laxity. To avoid the job from missing its deadline, the priority of the job is immediately promoted to the highest priority. We derive the schedulability bound of 3/2+vertical bar u(max)-1/2 vertical bar for two-processor systems, where u(max) is the maximum utilization of an individual task in the given task set. We also discuss the best known upper bound and lower bound on EDZL schedulability conditions.
the use of cloud computing in different application areas is growing fast. More and more functions are being moved into the cloud in order to take advantage of cloud computing strengths such as scalability, resources ...
详细信息
ISBN:
(纸本)9781479966493
the use of cloud computing in different application areas is growing fast. More and more functions are being moved into the cloud in order to take advantage of cloud computing strengths such as scalability, resources on demand, and usage based cost models. However, most types of embeddedsystems are still in an early phase of cloud adoption, with a few exceptions found in e.g., data storage and user interfaces. In this paper we present a number of challenges and opportunities when introducing cloud computing into embeddedsystems. In particular, we look at embeddedsystems with requirements on timing predictability, i.e., real-timesystems. In the paper we conclude that it is possible to move a complete soft real-time system into the cloud. Moreover we see an upcoming development in cloud computing to potentially allow for hard real-timesystems to be moved to the cloud.
Doubling the number of processing cores on a single processor chip with each technology generation has become conventional wisdom. While future manycore processors promise to offer much increased computational through...
详细信息
ISBN:
(纸本)9780769529752
Doubling the number of processing cores on a single processor chip with each technology generation has become conventional wisdom. While future manycore processors promise to offer much increased computational throughput under a given power envelope, sharing critical on-chip resources, such as caches and coreto-core interconnects, poses challenges to guaranteeing predictable performance to an application program. this paper focuses on the problem of sharing on-chip caching capacity among multiple programs scheduled together, especially at the L2 cache level. Specifically, two design aspects of a large shared L2 cache are considered: (1) non-uniform cache access latency and (2) cache contention. We observe that boththe aspects have to do with where, among many cache slices, a cache block is mapped to, and present an OS-based approach to managing the on-chip L2 cache memory by carefully mapping data to a cache at the page granularity. We show that a reasonable extension to the OS memory management subsystem and simple architectural support enable enforcing high-level policies to achieve application performance isolation and improve program performance predictability thereof.
Graphics processing units (GPUs) are becoming increasingly important in today's platforms as their increased generality allows for them to be used as powerfill co-processors. In this paper;we explore possible appl...
详细信息
ISBN:
(纸本)9780769545028
Graphics processing units (GPUs) are becoming increasingly important in today's platforms as their increased generality allows for them to be used as powerfill co-processors. In this paper;we explore possible applications for GPUs in real-timesystems, discuss the limitations and constraints imposed by current GPU technology, and present a summary of our research addressing many such constraints.
暂无评论