FlashEmbedding: Storing embedding tables in SSD for large-scale recommender systems
Journal
APSys 2021 - Proceedings of the 12th ACM SIGOPS Asia-Pacific Workshop on Systems
Pages
9月16日
Date Issued
2020
Author(s)
Abstract
We present FlashEmbedding, a hardware/software co-design solution for storing embedding tables on SSDs for large-scale recommendation inference under memory capacity-limited systems. FlashEmbedding leverages an embedding semantic-aware SSD, an embedding-oriented software cache, and pipeline techniques to improve the overall performance. We evaluate the performance of FlashEmbedding with our FPGA-based prototype SSD on a real-world public dataset. FlashEmbedding achieves up to 17.44× lower latency in embedding lookups and 2.89× lower end-to-end latency than baseline solution in a memory capacity-limted system. © 2021 ACM.
Subjects
Embedding; Recommender systems; Solid-state drive (SSD)
SDGs
Other Subjects
Hardware-software codesign; Recommender systems; Semantics; Design solutions; Embeddings; Hardware/software codesign; Large-scales; Memory capacity; Performance; Semantic-aware; Software caches; Software pipeline; Solid-state drive; Embeddings
Type
conference paper