PREMA: A Predictive Multi-Task Scheduling Algorithm For Preemptible Neural Processing Units
Year: 2020
Type: conference-paper
Abstract: To amortize cost, cloud vendors providing DNN acceleration as a service to end-users employ consolidation and virtualization to share the underlying resources among multiple DNN service requests. This paper makes a case for a "preemptible" neural processing unit (NPU) and a "predictive" multi-task scheduler to meet the latency demands of high-priority inference while maintaining high throughput. We evaluate both the mechanisms that enable NPUs to be preemptible and the policies that utilize them to meet scheduling objectives. We show that preemptive NPU multi-tasking can achieve an average 7.8×, 1.4×, and 4.8× improvement in latency, throughput, and SLA satisfaction, respectively.
Authors: Yujeong Choi, Minsoo Rhu
Institution: Korea Advanced Institute of Science and Technology
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G3338737308, G8190487336
OpenAlex ID: W2972585271
