Accelerating Deep Learning Inference via Learned Caches
arXiv:2101.07344
Abstract
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.
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Distilling the Knowledge in a Neural Network
- Overcoming catastrophic forgetting in neural networks
- Achieving Human Parity on Automatic Chinese to English News Translation
- The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
- Archipelago: A Scalable Low-Latency Serverless Platform
- Learning Anytime Predictions in Neural Networks via Adaptive Loss Balancing
- Accelerating Deep Learning Inference via Freezing