PREMA: A Predictive Multi-Task Scheduling Algorithm For Preemptible Neural Processing Units

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 "predictiv...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings - International Symposium on High-Performance Computer Architecture pp. 220 - 233
Main Authors: Choi, Yujeong, Rhu, Minsoo
Format: Conference Proceeding
Language:English
Published: IEEE 01.02.2020
Subjects:
Computer architecture
Google
Graphics processing units
Random access memory
Servers
Task analysis
Throughput
ISSN:2378-203X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2378-203X
DOI:10.1109/HPCA47549.2020.00027