RecSSD: Near data processing for solid state drive based recommendation inference

Mark Wilkening, Udit Gupta, Samuel Hsia, Caroline Trippel, Carole Jean Wu, David Brooks, Gu Yeon Wei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Neural personalized recommendation models are used across a wide variety of datacenter applications including search, social media, and entertainment. State-of-the-art models comprise large embedding tables that have billions of parameters requiring large memory capacities. Unfortunately, large and fast DRAM-based memories levy high infrastructure costs. Conventional SSD-based storage solutions offer an order of magnitude larger capacity, but have worse read latency and bandwidth, degrading inference performance. RecSSD is a near data processing based SSD memory system customized for neural recommendation inference that reduces end-to-end model inference latency by 2× compared to using COTS SSDs across eight industry-representative models.

Original languageEnglish (US)
Title of host publicationProceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2021
PublisherAssociation for Computing Machinery
Pages717-729
Number of pages13
ISBN (Electronic)9781450383172
DOIs
StatePublished - Apr 19 2021
Externally publishedYes
Event26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2021 - Virtual, Online, United States
Duration: Apr 19 2021Apr 23 2021

Publication series

NameInternational Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS

Conference

Conference26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2021
Country/TerritoryUnited States
CityVirtual, Online
Period4/19/214/23/21

Keywords

  • near data processing
  • neural networks
  • solid state drives

ASJC Scopus subject areas

  • Software
  • Information Systems
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'RecSSD: Near data processing for solid state drive based recommendation inference'. Together they form a unique fingerprint.

Cite this