SRP-Slack Management Techniques for Real Time Distributed Embedded Systems
1) This work presents a novel slack management technique, the Service-Rate-Proportionate (SRP) Slack Distribution, for real-time distributed embedded systems to reduce energy consumption. The proposed SRP-based Slack Distribution Technique has been considered with EDF and Rate-Based scheduling schemes that are most commonly used with embedded systems. A fault-tolerant mechanism has also been incorporated into the proposed technique in order to utilize the available dynamic slack to maintain checkpoints and provide for rollbacks on faults. Results show that, in comparison to contemporary techniques, the proposed SRP Slack Distribution Technique achieves about 29 percent more performance/overhead improvement benefits when validated with random and real-world benchmarks.
2) In multimode distributed systems, active task sets are assigned to their distributed components for realizing one or more functions. Many of these systems encounter runtime task variations at the input and across the system while processing their tasks in real time. Very few efforts have been made to address energy efficient scheduling in these types of distributed systems. In this paper, we propose an analytical model for energy efficient scheduling in distributed real-time embedded systems to handle time-varying task inputs. A new slack distribution scheme is introduced and adopted during the schedule of the task sets in the system. The slack distribution is made according to the service demand at the nodes which affects the energy consumption in the system. The active component at a node periodically determines the service rate and applies voltage scaling according to the dynamic traffic condition observed at various network nodes. The proposed approach uses a comprehensive traffic description function at nodes and provides adequate information about the worst-case traffic behavior anywhere in the distributed network, thereby enhancing the system power management capabilities. We evaluate the proposed technique using several benchmarks employing an event driven simulator and demonstrate its performance for multimode applications. Experimental results indicate significant energy savings in various examples and case studies.
- S. Acharya and R. Mahapatra, “A Dynamic Slack Management Technique for Real-Time Distributed Embedded System,” IEEE Transactions on Computer, Volume 57, Issue 2, pp. 215-230, Dec 2008.
- R. Mahapatra and W. Zhao., "An Energy efficient Slack Distribution Technique for Multimode Distributed Real-time embedded Systems", IEEE Transaction on Parallel and Distributed Systems Volume 16, Issue 7, pp.650 – 662, July 2005.
Reliability Aware Dynamic Power Management
In recent literature it has been reported that Dynamic Power Management (DPM) may lead to decreased reliability in real-time embedded systems. The ever-shrinking device sizes contribute further to this problem. In this paper, we present a reliability aware power management algorithm that aims at reducing energy consumption while preserving the overall system reliability. The idea behind the proposed scheme is to utilize the dynamic slack to scale down processes while ensuring that the overall system reliability does not reduce drastically. The proposed algorithm employs a proportional feedback controller to keep track of the overall miss ratio of a system of tasks and provide additional level of fault-tolerance based on demand. It was tested with both real world and synthetic task sets and simulation results have been presented. Both fixed and dynamic priority scheduling policies have been considered for demonstration of results.
- R. Sridharan; N. Gupta; R. Mahapatra, "Feedback-controlled reliability-aware power management for real-time embedded systems," Proceedings of 45th ACM/IEEE Design Automation Conference, DAC, pp. 185-190, 8-13 June 2008.
Stochastic Fault Modeling in Real Time Embedded Systems
Real-time embedded systems are characterized by their need to complete task executions within their scheduled deadlines. Task scheduling could get complicated due to the occurrence of faults in such systems. Traditionally, researchers have accounted for faults by assuming a constant number of faults occurring in the system. However, such an assumption may lead the system designers to rather pessimistic estimates on tasks’ response times. In this paper, the occurrence of faults has been modeled as a stochastic process with a Poisson distribution having a mean inter-arrival rate of λ. The usefulness of the model has been evaluated in terms of estimated task response time, energy consumption and loss of predictability for two periodic real-time embedded task sets, one real-world and another synthetic. It has been shown that the proposed approach can achieve up to 40% improvement in terms of the estimated energy savings and task response time with very minimal loss of predictability in the system of about 0.001 % as compared to the systems with constant number faults.
- R. Sridharan and R. Mahapatra, "Analysis of Real-time Embedded Applications in the Presence of Stochastic Fault Model," Proceedings of ACM/IEEE International Conference on VLSI Design, pp. 83-88, 6-10 January 2007.
Cache Partitioning for Predictable Performance in Real Time Embedded Systems
The usage of cache memories in time-critical applications has been limited as caches introduce unpredictable execution behavior. Cache partitioning techniques have been developed to reduce the impact of unpredictability owing to context switch effects. However, partitioning reduces the cache size available for each task resulting in capacity related cache misses. This paper introduces a fully associative cache architecture for multi-tasking applications where effective partition sizes are increased by tag compression in the cache. The proposed scheme uses a few don’t care cells in its least significant bits of the tag to aggregate multiple tag entries into a single entry. The experimental results indicate that the proposed scheme is context switch resilient when eight different real-time benchmarks use the cache concurrently. Further, this cache architecture requires less time and less energy to perform tag table search compared to contemporary fully associative caches of the same size.
A. Chousein and R. Mahapatra, "Fully Associative Cache Partitioning with Don't Care Bits for Real-time Applications", 11th IEEE Real-Time and Embedded Technology and Applications Symposium RTAS, pp. 35-38, April 2005.