Accelerating Mobile Inference through Fine-Grained CPU-GPU Co-Execution

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Zhuojin, Paolieri, Marco, Golubchik, Leana
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912912515268608
author Li, Zhuojin
Paolieri, Marco
Golubchik, Leana
author_facet Li, Zhuojin
Paolieri, Marco
Golubchik, Leana
contents Deploying deep neural networks on mobile devices is increasingly important but remains challenging due to limited computing resources. On the other hand, their unified memory architecture and narrower gap between CPU and GPU performance provide an opportunity to reduce inference latency by assigning tasks to both CPU and GPU. The main obstacles for such collaborative execution are the significant synchronization overhead required to combine partial results, and the difficulty of predicting execution times of tasks assigned to CPU and GPU (due to the dynamic selection of implementations and parallelism level). To overcome these obstacles, we propose both a lightweight synchronization mechanism based on OpenCL fine-grained shared virtual memory (SVM) and machine learning models to accurately predict execution times. Notably, these models capture the performance characteristics of GPU kernels and account for their dispatch times. A comprehensive evaluation on four mobile platforms shows that our approach can quickly select CPU-GPU co-execution strategies achieving up to 1.89x speedup for linear layers and 1.75x speedup for convolutional layers (close to the achievable maximum values of 2.01x and 1.87x, respectively, found by exhaustive grid search on a Pixel~5 smartphone).
format Preprint
id arxiv_https___arxiv_org_abs_2510_21081
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Accelerating Mobile Inference through Fine-Grained CPU-GPU Co-Execution
Li, Zhuojin
Paolieri, Marco
Golubchik, Leana
Machine Learning
Distributed, Parallel, and Cluster Computing
Performance
Deploying deep neural networks on mobile devices is increasingly important but remains challenging due to limited computing resources. On the other hand, their unified memory architecture and narrower gap between CPU and GPU performance provide an opportunity to reduce inference latency by assigning tasks to both CPU and GPU. The main obstacles for such collaborative execution are the significant synchronization overhead required to combine partial results, and the difficulty of predicting execution times of tasks assigned to CPU and GPU (due to the dynamic selection of implementations and parallelism level). To overcome these obstacles, we propose both a lightweight synchronization mechanism based on OpenCL fine-grained shared virtual memory (SVM) and machine learning models to accurately predict execution times. Notably, these models capture the performance characteristics of GPU kernels and account for their dispatch times. A comprehensive evaluation on four mobile platforms shows that our approach can quickly select CPU-GPU co-execution strategies achieving up to 1.89x speedup for linear layers and 1.75x speedup for convolutional layers (close to the achievable maximum values of 2.01x and 1.87x, respectively, found by exhaustive grid search on a Pixel~5 smartphone).
title Accelerating Mobile Inference through Fine-Grained CPU-GPU Co-Execution
topic Machine Learning
Distributed, Parallel, and Cluster Computing
Performance
url https://arxiv.org/abs/2510.21081