Serverless computing is a new pay-per-use cloud service paradigm that automates resource scaling for stateless functions and can potentially facilitate bursty machine learning serving. Batching is critical for latency performance and cost-effectiveness of machine learning inference, but unfortunately it is not supported by existing serverless platforms due to their stateless design. Our experiments show that without batching, machine learning serving cannot reap the benefits of serverless computing. In this paper, we present BATCH, a framework for supporting efficient machine learning serving on serverless platforms. BATCH uses an optimizer to provide inference tail latency guarantees and cost optimization and to enable adaptive batching support. We prototype BATCH atop of AWS Lambda and popular machine learning inference systems. The evaluation verifies the accuracy of the analytic optimizer and demonstrates performance and cost advantages over the state-of-the-art method MArk and the state-of-the-practice tool SageMaker.

Batch: Machine learning inference serving on serverless platforms with adaptive batching

Riccardo Pinciroli;
2020-01-01

Abstract

Serverless computing is a new pay-per-use cloud service paradigm that automates resource scaling for stateless functions and can potentially facilitate bursty machine learning serving. Batching is critical for latency performance and cost-effectiveness of machine learning inference, but unfortunately it is not supported by existing serverless platforms due to their stateless design. Our experiments show that without batching, machine learning serving cannot reap the benefits of serverless computing. In this paper, we present BATCH, a framework for supporting efficient machine learning serving on serverless platforms. BATCH uses an optimizer to provide inference tail latency guarantees and cost optimization and to enable adaptive batching support. We prototype BATCH atop of AWS Lambda and popular machine learning inference systems. The evaluation verifies the accuracy of the analytic optimizer and demonstrates performance and cost advantages over the state-of-the-art method MArk and the state-of-the-practice tool SageMaker.
2020
9781728199986
Batching, Cloud, Cost-effective, Inference, Machine-learning-as-a-service (MLaaS), Modeling, Optimization, Prediction, Serverless, Service Level Objective (SLO), Serving
File in questo prodotto:
File Dimensione Formato  
2020_SC20_2020_Ali.pdf

non disponibili

Tipologia: Versione Editoriale (PDF)
Licenza: Non pubblico
Dimensione 763 kB
Formato Adobe PDF
763 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12571/27484
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 97
  • ???jsp.display-item.citation.isi??? 81
social impact