RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference

01/29/2021
by   Mark Wilkening, et al.
0

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.

READ FULL TEXT

page 7

page 10

research
10/12/2020

MicroRec: Efficient Recommendation Inference by Hardware and Data Structure Solutions

Deep neural networks are widely used in personalized recommendation syst...
research
01/08/2020

DeepRecSys: A System for Optimizing End-To-End At-scale Neural Recommendation Inference

Neural personalized recommendation is the corner-stone of a wide collect...
research
12/30/2019

RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing

Personalized recommendation systems leverage deep learning models and ac...
research
04/12/2018

On Using Non-Volatile Memory in Apache Lucene

Apache Lucene is a widely popular information retrieval library used to ...
research
02/18/2022

iMARS: An In-Memory-Computing Architecture for Recommendation Systems

Recommendation systems (RecSys) suggest items to users by predicting the...
research
10/17/2022

A GPU-specialized Inference Parameter Server for Large-Scale Deep Recommendation Models

Recommendation systems are of crucial importance for a variety of modern...
research
07/23/2018

NullaNet: Training Deep Neural Networks for Reduced-Memory-Access Inference

Deep neural networks have been successfully deployed in a wide variety o...

Please sign up or login with your details

Forgot password? Click here to reset