RecSSD：基于推荐推理的固态硬盘近数据处理
RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference
摘要：
神经个性化推荐模型用于各种数据中心应用，包括搜索、社交媒体和娱乐。最先进的模型包括具有数十亿个参数的大型嵌入表，这些参数需要大的存储容量。不幸的是，基于DRAM的大而快的存储器征收高的基础设施成本。传统的基于SSD的存储解决方案提供了一个数量级的更大容量，但具有更差的读取延迟和带宽，从而降低了推理性能。RecSSD是一种基于近数据处理的SSD存储系统，专为神经推荐推理而定制，与使用COTS SSD相比，在八个行业代表性模型上将端到端模型推理延迟减少了2倍。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
