ISIS Neutron and Muon Source Data Journal

Reliability Evaluation of Parallel Processor for Automotive and HPC Applications

Abstract: We will evaluate the reliability of modern parallel devices deployed in self-driving carsto dynamically identify/classify objects.Major hardware vendors have focused their research teams on delivering the fastest hardware/software Neural Network (NN) solution, providing a significant edge over competitors.NN algorithms map efficiently to parallel devices, exploiting theirability to support data and thread-level parallelism. Parallel devices can detect obstacles in a scene in near real-time, a critical task in next-generation self-driving cars. Researchers have been overly focused on the performance, while neglecting other critical aspects, particularly reliability, in their quest to deliver the most performant configuration. We then need to precisely evaluate the error rate of these systems, and ChipIR is the most suitable beam line for our scope.

Principal Investigator: Dr Paolo Rech
Experimenter: Mr Ogun Kibar
Experimenter: Ms Charu Kalra
Local Contact: Dr Carlo Cazzaniga

DOI: 10.5286/ISIS.E.RB1800030

ISIS Experiment Number: RB1800030

Publisher: STFC ISIS Neutron and Muon Source

Data format: RAW/Nexus
Select the data format above to find out more about it.

Data Citation

The recommended format for citing this dataset in a research publication is as:
[author], [date], [title], [publisher], [doi]

For Example:
Dr Paolo Rech et al; (2018): Reliability Evaluation of Parallel Processor for Automotive and HPC Applications, STFC ISIS Neutron and Muon Source, https://doi.org/10.5286/ISIS.E.RB1800030

Data is released under the CC-BY-4.0 license.