Soft error-aware design optimization of low power and time-constrained embedded systems

Shafik,; Al-Hashimi,; Chakrabarty, Krishnendu

doi:10.1109/date.2010.5457042

Cited by 8 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simulation Workloads. We generate 39 different event analytic dataflows using the Random Task and Resource Graph (RTRG) utility [22], with 4 − 50 vertices each and a fan-out of up to 5 edges. We uniformly sample and assign one of the benchmarked CEP queries to each vertex.…”

Section: Resultsmentioning

confidence: 99%

Adaptive Energy-Aware Scheduling of Dynamic Event Analytics Across Edge and Cloud Resources

Ghosh

Komma

Simmhan

2018

2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)

View full text Add to dashboard Cite

The growing deployment of sensors as part of Internet of Things (IoT) is generating thousands of event streams. Complex Event Processing (CEP) queries offer a useful paradigm for rapid decision-making over such data sources. While often centralized in the Cloud, the deployment of capable edge devices on the field motivates the need for cooperative event analytics that span Edge and Cloud computing. Here, we identify a novel problem of query placement on edge and Cloud resources for dynamically arriving and departing analytic dataflows. We define this as an optimization problem to minimize the total makespan for all event analytics, while meeting energy and compute constraints of the resources. We propose 4 adaptive heuristics and 3 rebalancing strategies for such dynamic dataflows, and validate them using detailed simulations for 100 − 1000 edge devices and VMs. The results show that our heuristics offer O(seconds) planning time, give a valid and high quality solution in all cases, and reduce the number of query migrations. Furthermore, rebalance strategies when applied in these heuristics have significantly reduced the makespan by around 20 − 25%.

show abstract

Section: Resultsmentioning

confidence: 99%

Adaptive Energy-Aware Scheduling of Dynamic Event Analytics Across Edge and Cloud Resources

Ghosh

Komma

Simmhan

2018

2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)

View full text Add to dashboard Cite

show abstract

“…Another approach that targets Single-Event Upsets (SEUs) mitigation is proposed by Shafik et al [2010]. In this approach, task mapping and voltage scaling are utilized to minimize the power consumption while improving the reliability in a homogeneous MPSoC.…”

Section: Hw/sw Reliability Managementmentioning

confidence: 99%

Ocean

Sabry

Atienza

Catthoor

2014

ACM Trans. Embed. Comput. Syst.

View full text Add to dashboard Cite

Recent process technology advances trigger reliability issues that degrade the Quality-of-Service (QoS) required by embedded Systems-on-Chip (SoCs). To maintain the required QoS with acceptable overheads, we propose OCEAN, a novel cross-layer error mitigation. OCEAN enforces on-chip SRAMs reliability with a fault-tolerant buffer. We utilize this buffer to protect a portion of the processed data used to restore from runtime error. We optimally select the buffer size to minimize the energy overhead, with timing and area constraints. OCEAN achieves full error mitigation with 10.1% average energy overhead compared to baseline operation that does not include any error correction capability, and 65% energy savings, compared to a cross-layer error mitigation mechanism. ACM Reference Format:Mohamed M. Sabry, David Atienza, and Francky Catthoor. 2014. OCEAN: An optimized HW/SW reliability mitigation approach for scratchpad memories in real-time SoCs.

show abstract

“…Experimental Setup 1) DAG Generation and Static Characteristics: Our evaluation considers a broad collection of synthetically generated DAGs composed out of the CEP queries introduced and benchmarked above. We use the Random Task and Resource Graph (RTRG) tool [39], developed for embedded systems research, to generate dataflows with different numbers of CEP queries (vertices). We generate DAGs with a maximum vertex out-degree of 1-5 edges.…”

Section: B Observations and Analysismentioning

confidence: 99%

Distributed Scheduling of Event Analytics across Edge and Cloud

Ghosh

Simmhan

2018

ACM Trans. Cyber-Phys. Syst.

View full text Add to dashboard Cite

Internet of Things (IoT) domains generate large volumes of high velocity event streams from sensors, which need to be analyzed with low latency to drive decisions. Complex Event Processing (CEP) is a Big Data technique to enable such analytics, and is traditionally performed on Cloud Virtual Machines (VM). Leveraging captive IoT edge resources in combination with Cloud VMs can offer better performance, flexibility and monetary costs for CEP. Here, we formulate an optimization problem for energy-aware placement of CEP queries, composed as an analytics dataflow, across a collection of edge and Cloud resources, with the goal of minimizing the end-to-end latency for the dataflow. We propose a Genetic Algorithm (GA) meta-heuristic to solve this problem, and compare it against a brute-force optimal algorithm (BF). We perform detailed real-world benchmarks on the compute, network and energy capacity of edge and Cloud resources. These results are used to define a realistic and comprehensive simulation study that validates the BF and GA solutions for 45 diverse CEP dataflows, LAN and WAN setup, and different edge resource availability. We compare the GA and BF solutions against random and Cloud-only baselines for different configurations, for a total of 1764 simulation runs. Our study shows that GA is within 97% of the optimal BF solution that takes hours, maps dataflows with 4 − 50 queries in 1 − 26 secs, and only fails to offer a feasible solution ≤ 20% of the time.A common information processing architecture is to move data from thousands or millions of edge devices centrally into public Clouds, where CEP or other analytics engines hosted on Virtual Machines (VM) can process the incoming streams, and data can be persisted for mining and visualization 1 2 . Here, the edge devices serve as "dumb" sensors that transmit the data to the Cloud for centralized analytics.However, moving event streams from the edge to the Cloud introduces data transfer latency, and the public network may become a bandwidth bottleneck for large deployments. There are associated monetary costs for the use of Cloud VMs and network. Edge devices are getting powerful, energy-efficient, and affordable. Their use is widespread as gateways in IoT deployments, and offer captive computing at low/no cost. Lastly, having a hub and spoke model where all data is ingested to the Cloud does not give us any fine-grained control over where data from the IoT deployment can go.In this article, we propose approaches for distributed event-based analytics across edge and Cloud resources to support IoT applications. We consider a deployment with multiple event streams generated at the edge at high frequency, an analytics dataflow composed of CEP queries that should execute over these streams, and multiple edge devices and public Cloud VMs to perform the queries. Our goal is to find a distributed placement of these queries onto the edge and Cloud resources to minimize the endto-end latency for performing the event analytics. This placement must meet constraints of thro...

show abstract

Soft error-aware design optimization of low power and time-constrained embedded systems

Cited by 8 publications

References 13 publications

Adaptive Energy-Aware Scheduling of Dynamic Event Analytics Across Edge and Cloud Resources

Adaptive Energy-Aware Scheduling of Dynamic Event Analytics Across Edge and Cloud Resources

Ocean

Distributed Scheduling of Event Analytics across Edge and Cloud

Contact Info

Product

Resources

About