@inproceedings{22fe6f59161a4050a1e1dca8d07f2c42,
title = "RecSSD: Near data processing for solid state drive based recommendation inference",
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.",
keywords = "near data processing, neural networks, solid state drives",
author = "Mark Wilkening and Udit Gupta and Samuel Hsia and Caroline Trippel and Wu, {Carole Jean} and David Brooks and Wei, {Gu Yeon}",
note = "Funding Information: We would like to thank the anonymous reviewers for their thoughtful comments and suggestions. We would also like to thank Glenn Holloway for his valuable technical support. This work was sponsored in part by National Science Foundation Graduate Research Fellowships (NSFGRFP), and the ADA (Applications Driving Architectures) Center. Publisher Copyright: {\textcopyright} 2021 ACM.; 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2021 ; Conference date: 19-04-2021 Through 23-04-2021",
year = "2021",
month = apr,
day = "19",
doi = "10.1145/3445814.3446763",
language = "English (US)",
series = "International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS",
publisher = "Association for Computing Machinery",
pages = "717--729",
booktitle = "Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2021",
}