CLAY: CXL-based Scalable NDP Architecture Accelerating Embedding Layers
Sungmin Yun, Hwayong Nam, Kwanhee Kyung, Jaehyun Park, Byeongho Kim, Yongsuk Kwon, Eojin Lee, Jung Ho Ahn · 2024
An embedding layer is one of the most critical building blocks of deep neural networks, especially for recommender systems and graph neural networks. The embedding layer dominates a large portion of the total execution time due to its large memory requirements and little data reuse in operations. To accelerate the embedding layers, dual in-line memory module (DIMM) based near-data processing architectures have been proposed. They amplify bandwidth by adding a processing unit to the DIMM’s buffer. However, prior architectures have less capacity scalability due to the limited number of memory channels. Crucially, they are limited in performance improvement due to the load imbalance problem and the limitations of DIMM-based memory systems with a multi-drop bus structure between the processing units and the host.