iMARS: an in-memory-computing architecture for recommendation systems
iMARS: an in-memory-computing architecture for recommendation systems
复制标题
DOI：
10.1145/3489517.3530478
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Mengyuan Li;Ann Franchesca Laguna;D. Reis;Xunzhao Yin;M. Niemier;X. Hu
中科院分区：
文献类型：
--
作者：
Mengyuan Li;Ann Franchesca Laguna;D. Reis;Xunzhao Yin;M. Niemier;X. Hu
Recommendation systems (RecSys) suggest items to users by predicting their preferences based on historical data. Typical RecSys handle large embedding tables and many embedding table related operations. The memory size and bandwidth of the conventional computer architecture restrict the performance of RecSys. This work proposes an in-memory-computing (IMC) architecture (iMARS) for accelerating the filtering and ranking stages of deep neural network-based RecSys. iMARS leverages IMC-friendly embedding tables implemented inside a ferroelectric FET based IMC fabric. Circuit-level and system-level evaluation show that iMARS achieves 16.8x (713x) end-to-end latency (energy) improvement compared to the GPU counterpart for the MovieLens dataset.
