Deep Neural Networks (DNNs) are witnessing increased adoption in multiple domains owing to their high accuracy in solving real-world problems. However, this high accuracy has been achieved by building deeper networks, posing a fundamental challenge to the low latency inference desired by user-facing applications. Current low latency solutions trade-off on accuracy or fail to exploit the inherent temporal locality in prediction serving workloads. We observe that caching hidden layer outputs of the DNN can introduce a form of late-binding where inference requests only consume the amount of computation needed. This enables a mechanism for achieving low latencies, coupled with an ability to exploit temporal locality. However, traditional caching approaches incur high memory overheads and lookup latencies, leading us to design learned caches - caches that consist of simple ML models that are continuously updated. We present the design of GATI, an end-to-end prediction serving system that incorporates learned caches for low-latency DNN inference. Results show that GATI can reduce inference latency by up to 7.69X on realistic workloads.
@article{arxiv.2101.07344,
title = {Accelerating Deep Learning Inference via Learned Caches},
author = {Arjun Balasubramanian and Adarsh Kumar and Yuhan Liu and Han Cao and Shivaram Venkataraman and Aditya Akella},
journal= {arXiv preprint arXiv:2101.07344},
year = {2021}
}