Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
RecSSD: near data processing for solid state drive based recommendation inference
ASPLOS '21: Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating SystemsApril 2021, pp 717–729https://doi.org/10.1145/3445814.3446763Neural 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 ...
- research-articleApril 2021
Training for multi-resolution inference using reusable quantization terms
ASPLOS '21: Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating SystemsApril 2021, pp 845–860https://doi.org/10.1145/3445814.3446741Low-resolution uniform quantization (e.g., 4-bit bitwidth) for both Deep Neural Network (DNN) weights and data has emerged as an important technique for efficient inference. Departing from conventional quantization, we describe a novel training approach ...