CNN Accelerator Performance Dependence on Loop Tiling and the Optimum Resource-Constrained Loop Tiling

CNN Accelerator Performance Dependence on Loop Tiling and the Optimum Resource-Constrained Loop Tiling

This paper analyzes the dependence of the convolutional neural network (CNN) accelerator performance on loop tiling. More specifically, based on the closed-form expression of the CNN accelerator performance, the dependence on the tile sizes is characterized by the derivative, the asymptote and the s...

Full description

Saved in:
Bibliographic Details
Main Authors: Chester Sungchung Park, Sungkyung Park
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Closed-form expression
CNN accelerator
communication
computation
hardware resource
loop tiling
Online Access:https://ieeexplore.ieee.org/document/10849540/
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items