STE||AR Seminar: Local Failure Local Recovery

This month Dr. Keita Teranishi, a researcher at Sandia Livermore National Lab, presented his research on fault tolerance and resilience to the STE||AR Group.

Dr. Teranishi works with our team on a grant named “Infrastructure Development for Analyszing Resilience with Asynchronous Many Task (AMT) Programming Models” supported by the DoE Award-NA000352. In this talk, he presents the theoretical framework supporting our work namely: the existing resilient parallel programming models, the Local Failure Local Recovery (LFLR) technique, and the efficiency and scalability of LFLR.

A link to the video and accompanying slides can be found below:



GD Star Rating
Be Sociable, Share!

Leave a Reply

Your email address will not be published. Required fields are marked *