J
Jason Mars
Researcher at University of Michigan
Publications - 94
Citations - 5735
Jason Mars is an academic researcher from University of Michigan. The author has contributed to research in topics: Server & Computer science. The author has an hindex of 33, co-authored 88 publications receiving 4436 citations. Previous affiliations of Jason Mars include Google & University of Virginia.
Papers
More filters
Proceedings ArticleDOI
Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge
TL;DR: Neurosurgeon, a lightweight scheduler to automatically partition DNN computation between mobile devices and datacenters at the granularity of neural network layers is designed, finding that a fine-grained, layer-level computation partitioning strategy based on the data and computation variations of each layer within a DNN has significant latency and energy advantages over the status quo approach.
Proceedings ArticleDOI
Bubble-Up: increasing utilization in modern warehouse scale computers via sensible co-locations
TL;DR: Bubble-Up is presented, a characterization methodology that enables the accurate prediction of the performance degradation that results from contention for shared resources in the memory subsystem and can predict the performance interference between co-locate applications with an accuracy within 1% to 2% of the actual performance degradation.
Proceedings ArticleDOI
Bubble-flux: precise online QoS management for increased utilization in warehouse scale computers
TL;DR: B Bubble-Flux is presented, an integrated dynamic interference measurement and online QoS management mechanism to provide accurate QoS control and maximize server utilization.
Proceedings ArticleDOI
The Architectural Implications of Autonomous Driving: Constraints and Acceleration
TL;DR: With accelerator-based designs, this work is able to build an end-to-end autonomous driving system that meets all the design constraints, and explore the trade-offs among performance, power and the higher accuracy enabled by higher resolution cameras.
Proceedings ArticleDOI
An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction
Stefan Larson,Anish Mahendran,Joseph Peper,Christopher Clarke,Andrew Lee,Parker Hill,Jonathan K. Kummerfeld,Kevin Leach,Michael A. Laurenzano,Lingjia Tang,Jason Mars +10 more
TL;DR: A new dataset is introduced that includes queries that are out-of-scope—i.e., queries that do not fall into any of the system’s supported intents, posing a new challenge because models cannot assume that every query at inference time belongs to a system-supported intent class.