PARIS and ELSA: An Elastic Scheduling Algorithm for Reconfigurable Multi-GPU Inference Servers

TL;DR

This paper introduces PARIS and ELSA, a reconfigurable multi-GPU inference system that optimizes GPU partitioning and scheduling to improve latency and utilization in cloud ML inference servers.

Contribution

It proposes a novel GPU partitioning algorithm and an elastic scheduling method specifically designed for reconfigurable GPU architectures in inference servers.

Findings

Achieves high resource utilization with low latency.

Effectively balances throughput and latency in multi-GPU inference.

Demonstrates significant performance improvements over traditional setups.

Abstract

In cloud machine learning (ML) inference systems, providing low latency to end-users is of utmost importance. However, maximizing server utilization and system throughput is also crucial for ML service providers as it helps lower the total-cost-of-ownership. GPUs have oftentimes been criticized for ML inference usages as its massive compute and memory throughput is hard to be fully utilized under low-batch inference scenarios. To address such limitation, NVIDIA's recently announced Ampere GPU architecture provides features to "reconfigure" one large, monolithic GPU into multiple smaller "GPU partitions". Such feature provides cloud ML service providers the ability to utilize the reconfigurable GPU not only for large-batch training but also for small-batch inference with the potential to achieve high resource utilization. In this paper, we study this emerging GPU architecture with reconfigurability to develop a high-performance multi-GPU ML inference server. Our first proposition is a sophisticated partitioning algorithm for reconfigurable GPUs that systematically determines a heterogeneous set of multi-granular GPU partitions, best suited for the inference server's deployment. Furthermore, we co-design an elastic scheduling algorithm tailored for our heterogeneously partitioned GPU server which effectively balances low latency and high GPU utilization.