Chrion: Optimizing Recurrent Neural Network Inference by Collaboratively Utilizing CPUs and GPUs

Deploying deep learning models in cloud clusters provides efficient and prompt inference services to accommodate the widespread application of deep learning. These clusters are usually equipped with host CPUs and accelerators with distinct responsibilities to handle serving requests, i.e. generalpur...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-07
Main Authors: Cai, Zinuo, Wang, Hao, Song, Tao, Yang, Hua, Ma, Ruhui, Guan, Haibing
Format: Article
Language:English
Subjects:
Clusters
Computation
Computer memory
Deep learning
Graph theory
Inference
Network latency
Neural networks
Optimization
Partitions (mathematics)
Recurrent neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deploying deep learning models in cloud clusters provides efficient and prompt inference services to accommodate the widespread application of deep learning. These clusters are usually equipped with host CPUs and accelerators with distinct responsibilities to handle serving requests, i.e. generalpurpose CPUs for input preprocessing and domain-specific GPUs for forward computation. Recurrent neural networks play an essential role in handling temporal inputs and display distinctive computation characteristics because of their high inter-operator parallelism. Hence, we propose Chrion to optimize recurrent neural network inference by collaboratively utilizing CPUs and GPUs. We formulate the model deployment in the CPU-GPU cluster as an NP-hard scheduling problem of directed acyclic graphs on heterogeneous devices. Given an input model in the ONNX format and user-defined SLO requirement, Chrion firstly preprocesses the model by model parsing and profiling, and then partitions the graph to select execution devices for each operator. When an online request arrives, Chrion performs forward computation according to the graph partition by executing the operators on the CPU and GPU in parallel. Our experimental results show that the execution time can be reduced by 19.4% at most in the latency-optimal pattern and GPU memory footprint by 67.5% in the memory-optimal pattern compared with the execution on the GPU.
ISSN:2331-8422