Response Time Bounds for G-EDF without Intra-Task Precedence Constraints

Erickson, Jeremy P.; Anderson, James H.

doi:10.1007/978-3-642-25873-2_10

Cited by 12 publications

(6 citation statements)

References 8 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5.3). Similar to our work, analyses of scheduling algorithms that allow jobs within a single task to run concurrently are presented in [12,26]. However, both these works consider global scheduling algorithms which, as mentioned earlier, entail high overheads especially in distributed memory architectures.…”

Section: Related Workmentioning

confidence: 89%

“…However, both these works consider global scheduling algorithms which, as mentioned earlier, entail high overheads especially in distributed memory architectures. In addition, in both [12] and [26] the potential of exploiting job parallelism to achieve higher energy efficiency is not explored.…”

Section: Related Workmentioning

confidence: 99%

“…Third step (lines [11][12][13][14][15][16][17] The final step assigns all the remaining tasks, which could not be allocated as fixed tasks. Considering the processor list in reversed order {π M , π M−1 , .…”

Section: First Step (Lines 1-5)mentioning

confidence: 99%

See 2 more Smart Citations

Energy efficient semi-partitioned scheduling for embedded multiprocessor streaming systems

Cannella

Stefanov

2016

Des Autom Embed Syst

View full text Add to dashboard Cite

In this paper, we study the problem of energy minimization when mapping streaming applications with throughput constraints to homogeneous multiprocessor systems in which voltage and frequency scaling is supported with a discrete set of operating voltage/frequency modes. We propose a soft real-time semi-partitioned scheduling algorithm which allows an even distribution of the utilization of tasks among the available processors. In turn, this enables processors to run at a lower frequency, which yields to lower energy consumption. We show on a set of real-life applications that our semi-partitioned scheduling approach achieves significant energy savings compared to a purely partitioned scheduling approach and an existing semi-partitioned one, EDF-os, on average by 36 % (and up to 64 %) when using the lowest frequency which guarantees schedulability and is supported by the system. By using a periodic frequency switching scheme that preserves schedulability, instead of this lowest supported fixed frequency, we obtain an additional energy saving up to 18 %. Although the throughput of applications is unchanged by the proposed semi-partitioned approach, the mentioned energy savings come at the cost of increased memory requirements and latency of applications.Keywords Energy efficient multiprocessor scheduling · Energy-efficient design · Real-time multiprocessor scheduling · Model-based design · Embedded streaming systems

show abstract

Section: Related Workmentioning

confidence: 89%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Energy efficient semi-partitioned scheduling for embedded multiprocessor streaming systems

Cannella

Stefanov

2016

Des Autom Embed Syst

View full text Add to dashboard Cite

show abstract

“…In this section, we establish two results that enable prior work to be leveraged to establish response-time bounds for DAG-based task systems. First, we show that, under the obi-task model with arbitrary offset settings, per-task response-time bounds can be derived by exploiting prior work pertaining to a task model called the npc-sporadic task model ("npc" stands for "no precedence constraints"-this refers to the lack of precedence constraints among jobs of the same task) [14,27]. Second, we show that, by properly setting offsets, any DAG-based task system can be transformed to a corresponding obi-task system.…”

Section: Response-time Boundsmentioning

confidence: 99%

Reducing Response-Time Bounds for DAG-Based Task Systems on Heterogeneous Multicore Platforms

Yang

Anderson

2016

Proceedings of the 24th International Conference on Real-Time Networks and Systems

Self Cite

View full text Add to dashboard Cite

This paper considers for the first time end-to-end response-time analysis for DAG-based real-time task systems implemented on heterogeneous multicore platforms. The specific analysis problem that is considered was motivated by an industrial collaboration involving wireless cellular base stations. The DAG-based systems considered herein allow intra-task parallelism: while each invocation of a task (i.e., DAG node) is sequential, successive invocations of a task may execute in parallel. In the proposed analysis, this characteristic is exploited to reduce response-time bounds. Additionally, there is some leeway in choosing how to set tasks' relative deadlines. It is shown that by resolving such choices holistically via linear programming, response-time bounds can be further reduced. Finally, in the considered use case, DAGs are defined based upon just a few templates and individually often have quite low utilizations. It is shown that, by combining many such DAGs into one of higher utilization, response-time bounds can often be drastically lowered. The effectiveness of these techniques is demonstrated via both casestudy and schedulability experiments.

show abstract

“…In devising such counterexamples, the goal is to ensure that a certain low-priority task is unable to make use of processors made available to it in parallel, thereby causing its response times to grow without bound. This relaxed task model has in fact been considered previously in work directed at using G-EDF in HRT [2] and SRT systems [10,12]. The latter work showed that allowing intra-task parallelism enables much lower tardiness bounds to be derived.…”

mentioning

confidence: 91%

Tardiness Bounds for Fixed-Priority Global Scheduling without Intra-Task Precedence Constraints

Voronov

Anderson

Yang³

2018

Proceedings of the 26th International Conference on Real-Time Networks and Systems

Self Cite

View full text Add to dashboard Cite

Fixed-priority multicore schedulers are often preferable to dynamicpriority ones because they entail less overhead, are easier to implement, and enable certain tasks to be favored over others. Under global fixed-priority (G-FP) scheduling, as applied to the standard sporadic task model, response times for low-priority tasks may be unbounded, even if total task-system utilization is low. In this paper, it is shown that this negative result can be circumvented if different jobs of the same task are allowed to execute in parallel. In particular, a response-time bound is presented for task systems that allow intra-task parallelism. This bound merely requires that total utilization does not exceed the overall processing capacity-individual task utilizations need not be further restricted. This result implies that G-FP is optimal for scheduling soft real-time tasks that require bounded tardiness, if intra-task parallelism is allowed. CCS CONCEPTS • Computer systems organization → Real-time systems;

show abstract

Response Time Bounds for G-EDF without Intra-Task Precedence Constraints

Cited by 12 publications

References 8 publications

Energy efficient semi-partitioned scheduling for embedded multiprocessor streaming systems

Energy efficient semi-partitioned scheduling for embedded multiprocessor streaming systems

Reducing Response-Time Bounds for DAG-Based Task Systems on Heterogeneous Multicore Platforms

Tardiness Bounds for Fixed-Priority Global Scheduling without Intra-Task Precedence Constraints

Contact Info

Product

Resources

About