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 2X compared to using COTS SSDs across eight industry-representative models.
@article{arxiv.2102.00075,
title = {RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference},
author = {Mark Wilkening and Udit Gupta and Samuel Hsia and Caroline Trippel and Carole-Jean Wu and David Brooks and Gu-Yeon Wei},
journal= {arXiv preprint arXiv:2102.00075},
year = {2021}
}