Modeling and Library Support for Early-Stage Exploration of Sparse Tensor Accelerator Designs

Modeling and Library Support for Early-Stage Exploration of Sparse Tensor Accelerator Designs

Techniques, like pruning and dimension reduction, and characteristics of data for applications, like natural language processing and object detection, introduce sparsity in deep learning models inherently. Sparse tensor accelerators leverage sparsity (0’s) in data in order to remove ineff...

Full description

Bibliographic Details
Main Authors: Whoi Ree Ha, Hyunjun Kim, Yunheung Paek
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
AI accelerators
design space exploration
sparsity-aware accelerators
sparse tensor accelerators
Online Access:https://ieeexplore.ieee.org/document/10130157/

Similar Items

Similar Items