Multiprocessor DSP scheduling in system-on-a-chip architectures

Gai, Paolo; Abeni, Luca; Buttazzo, Giorgio

doi:10.1109/emrts.2002.1019203

Cited by 25 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The locking protocol itself is a non-preemptive scheduler: it is non-preemptive since lock ownership cannot be arbitrarily revoked. Gai et al observed this in [18], where they cast the problem of scheduling a uniprocessor with a single non-preemptive digital signal processor as a synchronization problem. We also took this perspective in developing GPUSync, a single synchronization-based framework that allows us to explore every high-level category described in Sec.…”

Section: Introductionmentioning

confidence: 95%

Exploring the Multitude of Real-Time Multi-GPU Configurations

Elliott

Anderson

2014

2014 IEEE Real-Time Systems Symposium

View full text Add to dashboard Cite

Abstract-Motivated by computational capacity and power efficiency, techniques for integrating graphics processing units (GPUs) into real-time systems have become an active area of research. While much of this work has focused on single-GPU systems, multiple GPUs may be used for further benefits. Similar to CPUs in multiprocessor systems, GPUs in multi-GPU systems may be managed using partitioned, clustered, or global methods, independent of CPU organization. This gives rise to many combinations of CPU/GPU organizational methods that, when combined with additional GPU management options, results in thousands of "reasonable" configuration choices. In this paper, we explore real-time schedulability of several categories of configurations for multiprocessor, multi-GPU systems that are possible under GPUSync, a recently proposed highly configurable real-time GPU management framework. Our analysis includes the careful consideration of GPU-related overheads. We show system configuration strongly affects realtime schedulability. We also identify which configurations offer the best schedulability in order to guide the implementation of GPU-based real-time systems and future research.

show abstract

Section: Introductionmentioning

confidence: 95%

Exploring the Multitude of Real-Time Multi-GPU Configurations

Elliott

Anderson

2014

2014 IEEE Real-Time Systems Symposium

View full text Add to dashboard Cite

show abstract

“…The system has been presented to be effective and efficient in several practical cases. Simple emergent behavior patterns can also be applied to the communication between multicore system ( [7]). On the other hand the system uses high levels of computing power and energy which would prevent its use for the simple robotic entities which compose the collaborative robotic environment.…”

Section: Related Workmentioning

confidence: 99%

Evaluation of fish shoal inspired movement in collaborative robotic environments

Cioarga

Micea

Creţu

et al. 2010

2010 IEEE Instrumentation &Amp; Measurement Technology Conference Proceedings

View full text Add to dashboard Cite

In this paper we consider the evaluation of fish shoal inspired movement in collaborative robotic environments. Based on two new metrics, the polarization and the cohesion, a navigation and obstacle avoidance environment composed of LEGO Mindstorm NXT robots has been implemented and evaluated. A set of experiments have been conducted using the LEGO robotic set, targeting specific emergent behavior patterns such as flash expansion and fountain effect (which are typical fish shoal evasive maneuvers). These experimental results prove the quality of the metrics when used for the evaluation and validation of fish shoal inspired models for navigation and obstacle avoidance in complex movement applications which demand collaborative intelligence.Index Terms-fish shoal inspired movement, behaviorbased systems, robotic collectives, robotic navigation, obstacle avoidance.

show abstract

“…It is because that the lower priority task execution in the processor is forbidden even the processor is idle, when there is a higher priority task being executed in the co-processor. On the other hand, for system utilization improvement, the forbidden condition has to be relaxed, which causes that the priority inversion goes out of control [4,5].…”

Section: Introductionmentioning

confidence: 99%

On-line task scheduling for dual-core real-time embedded systems

Chen

Chang

Cheng

2009

2009 7th IEEE International Conference on Industrial Informatics

View full text Add to dashboard Cite

On-line task scheduling is a very challenging issue for dual-core real-time embedded systems, because to control priority inversion and to manage system utilization are fundamentally at odds with each other. We propose an on-line dual-core scheduling framework for dynamic workloads with real-time constraints. The processor and the co-processor are dedicated to separate schedulers with different scheduling policies, and precedence constraints among tasks are dealt with the interaction between the two schedulers. We have shown that our proposed scheduling can achieve a good balance between high system utilization and stable task response under realistic workloads.

show abstract

Multiprocessor DSP scheduling in system-on-a-chip architectures

Cited by 25 publications

References 8 publications

Exploring the Multitude of Real-Time Multi-GPU Configurations

Exploring the Multitude of Real-Time Multi-GPU Configurations

Evaluation of fish shoal inspired movement in collaborative robotic environments

On-line task scheduling for dual-core real-time embedded systems

Contact Info

Product

Resources

About