A Novel Throughput Enhancement Method for Deep Learning Applications on Mobile Devices With Heterogeneous Processors

A Novel Throughput Enhancement Method for Deep Learning Applications on Mobile Devices With Heterogeneous Processors

Contemporary smartphones integrate dedicated AI accelerators alongside CPUs and GPUs, in response to the growing demand for deep learning applications. While existing software development kits (SDKs) for these devices provide neural network optimization techniques, they often lack system-level optim...

Full description

Bibliographic Details
Main Authors: Choonghoon Park, Soonhoi Ha
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Mobile devices
heterogeneous processors
quantization
pipelining
design space exploration
Online Access:https://ieeexplore.ieee.org/document/10464274/

Internet

https://ieeexplore.ieee.org/document/10464274/

Similar Items