Toward a Fault-Tolerance Framework for COTS Many-Core Systems

Munk, Peter; Alhakeem, Mohammad Shadi; Lisicki, Raphael; Parzyjegla, Helge; Richling, Jan; Heiß, Hans-Ulrich

doi:10.1109/edcc.2015.32

Cited by 10 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In case of failures, instead of task remapping to sustain the number of redundant tasks, the authors propose to preserve the mapping and adjust the functionality of the included voter task. N Modular Redundancy (NMR) is the main fault tolerance mechanism in [28], targetting commercial many-core SoCs such as [3]. Transient faults in PEs are encountered by comparing the output of the N-times replicated task and repairing any instance that exhibits output divergence.…”

Section: Related Workmentioning

confidence: 99%

“…To mitigate such silent errors, the designer can take advantage of our proposed hierarchical design, in order to employ fault resilient deployment of the application, e.g. redundant execution of its tasks [28,29].…”

Section: Target Application Modelmentioning

confidence: 99%

“…It must be highlighted that the described infrastructure is proposed in order to mitigate faults of the administrative tasks of a hierarchical resource management scheme, such as the presented Controllers and Managers. Regarding worker nodes executing the parallel workload, a failed worker is similar to a shrink operation, while the existence of a Manager per application allows the adoption of intra-application error resilient resource management techniques such as Double or Triple Modular Redundancy [28,29], which can be seamlessly integrated in SoftRM.…”

Section: Fault Tolerance Infrastructure 431 Workload-aware Paxos Almentioning

confidence: 99%

See 2 more Smart Citations

SoftRM

Tsoutsouras

Masouros

Xydis

et al. 2017

ACM Trans. Embed. Comput. Syst.

View full text Add to dashboard Cite

Many-core systems are envisioned to leverage the ever-increasing demand for more powerful computing systems. To provide the necessary computing power, the number of Processing Elements integrated onchip increases and NoC based infrastructures are adopted to address the interconnection scalability. The advent of these new architectures surfaces the need for more sophisticated, distributed resource management paradigms, which in addition to the extreme integration scaling, make the new systems more prone to errors manifested both at hardware and software. In this work, we highlight the need for Run-Time Resource management to be enhanced with fault tolerance features and propose SoftRM, a resource management framework which can dynamically adapt to permanent failures in a self-organized, workload-aware manner. Self-organization allows the resource management agents to recover from a failure in a coordinated way by electing a new agent to replace the failed one, while workload awareness optimizes this choice according to the status of each core. We evaluate the proposed framework on Intel Single-chip Cloud Computer (SCC), a NoC based many-core system and customize it to achieve minimum interference on the resource allocation process. We showcase that its workload-aware features manage to utilize free resources in more that 90% of the conducted experiments. Comparison with relevant state-of-the-art fault tolerant frameworks shows decrease of up to 67% in the imposed overhead on application execution. CCS Concepts: • General and reference → Cross-computing tools and techniques; • Computer systems organization → Multicore architectures; • Networks → Network on chip; • Computing methodologies → Self-organization;

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Target Application Modelmentioning

confidence: 99%

Section: Fault Tolerance Infrastructure 431 Workload-aware Paxos Almentioning

confidence: 99%

See 1 more Smart Citation

SoftRM

Tsoutsouras

Masouros

Xydis

et al. 2017

ACM Trans. Embed. Comput. Syst.

View full text Add to dashboard Cite

show abstract

“…To guarantee hard real-time constraints during task migration, a methodology is proposed in [23]. However, a costly schedulability analysis is performed during run-time.…”

Section: Related Workmentioning

confidence: 99%

“…Similarly to [23], we split a runnable's context into two parts: (i) invariant, which is not modified at run-time and (ii) dynamic, including all volatile memory locations. We assume that an upper bound of the dynamic part size of all runnables is known in advance.…”

Section: Application Modelmentioning

confidence: 99%

Multi-criteria resource allocation in modal hard real-time systems

2017

View full text Add to dashboard Cite

In this paper, a novel resource allocation approach dedicated to hard real-time systems with distinctive operational modes is proposed. The aim of this approach is to reduce the energy dissipation of the computing cores by either powering them off or switching them into energy-saving states while still guaranteeing to meet all timing constraints. The approach is illustrated with two industrial applications, an engine control management and an engine control unit. Moreover, the amount of data to be migrated during the mode change is minimised. Since the number of processing cores and their energy dissipation are often negatively correlated with the amount of data to be migrated during the mode change, there is some trade-off between these values, which is also analysed in this paper.

show abstract

Dynamic Fault Tolerance Through Resource Pooling

Fuchs

Murillo

Plaat

et al. 2018

2018 NASA/ESA Conference on Adaptive Hardware and Systems (AHS)

View full text Add to dashboard Cite

Miniaturized satellites are currently not considered suitable for critical, high-priority, and complex multi-phased missions, due to their low reliability. As hardware-side fault tolerance (FT) solutions designed for larger spacecraft can not be adopted aboard very small satellites due to budget, energy, and size constraints, we developed a hybrid FT-approach based upon only COTS components, commodity processor cores, library IP, and standard software. This approach facilitates fault detection, isolation, and recovery in software, and utilizes fault-coverage techniques across the embedded stack within a multiprocessor system-on-chip (MPSoC). This allows our FPGA-based proofof-concept implementation to deliver strong fault-coverage even for missions with a long duration, but also to adapt to varying performance requirements during the mission. The operator of a spacecraft utilizing this approach can define performance profiles, which allow an on-board computer (OBC) to trade between processing capacity, fault coverage, and energy consumption using simple heuristics. The software-side FT approach developed also offers advantages if deployed aboard larger spacecraft through spare resource pooling, enabling an OBC to more efficiently handle permanent faults. This FT approach in part mimics a critical biological system's ability to tolerate faults, adapt to permanent failure, and enables graceful aging of an MPSoC.

show abstract

Toward a Fault-Tolerance Framework for COTS Many-Core Systems

Cited by 10 publications

References 13 publications

SoftRM

SoftRM

Multi-criteria resource allocation in modal hard real-time systems

Dynamic Fault Tolerance Through Resource Pooling

Contact Info

Product

Resources

About