RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference
arXiv:2102.00075
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 2X compared to using COTS SSDs across eight industry-representative models.
References in corpus (10)
- Deep Learning Recommendation Model for Personalization and Recommendation Systems
- Neural Collaborative Filtering
- Basic Performance Measurements of the Intel Optane DC Persistent Memory Module
- Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems
- Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications
- Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems
- Bandana: Using Non-volatile Memory for Storing Deep Learning Models
- DeepRecSys: A System for Optimizing End-To-End At-scale Neural Recommendation Inference
- The Architectural Implications of Facebook's DNN-based Personalized Recommendation
- RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing