%0 Journal Article %J ASPLOS 2021: Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems %D 2021 %T RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference %A Wilkening, Mark %A Udit Gupta %A Hsia, Samuel %A Caroline Trippel %A Carole-Jean Wu %A David Brooks %A Gu-Yeon Wei %X Neural personalized recommendationmodelsareusedacrossawide Samuel Hsia Harvard University Cambridge, Massachusetts, USA shsia@g.harvard.edu David Brooks Harvard University Cambridge, Massachusetts, USA dbrooks@eecs.harvard.edu USA. ACM, New York, NY, USA, 13 pages. https://doi.org/10.1145/3445814. 3446763 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. %B ASPLOS 2021: Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems %P 717–729 %G eng %U https://doi.org/10.48550/arXiv.2102.00075