Near Data Processing for Solid State Drive Based Recommendation Inference
Reading group: Lamboro Henon presented "Near Data Processing for Solid State Drive Based Recommendation Inference" (ASPLOS'21) at 4A312 the 3/12/2021 at 10h00.
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 2× compared to using COTS SSDs across eight industry-representative models.