Exploiting Neural-Network Statistics for Low-Power DNN Inference
Specialized compute blocks have been developed for efficient nn execution. However, due to the vast amount of data and parameter movements, the interconnects and on-chip memories form another bottleneck, impairing power and performance. This work addresses this bottleneck by contributing a low-power...
Saved in:
Main Authors: | Lennart Bamberg, Ardalan Najafi, Alberto Garcia-Ortiz |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Open Journal of Circuits and Systems |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10498075/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
INTELLIGENT LOW-POWER SMART HOME ARCHITECTURE
by: CORNEL POPESCU, et al.
Published: (2018-09-01) -
A Low-Power Streaming Speech Enhancement Accelerator for Edge Devices
by: Ci-Hao Wu, et al.
Published: (2024-01-01) -
Quaternary Neural Belief Propagation Decoding of Quantum LDPC Codes With Overcomplete Check Matrices
by: Sisi Miao, et al.
Published: (2025-01-01) -
Power of emperor in Russian legal discourse of second half of 19th– early 20th centuries: justification and options for interpretation
by: I. G. Adoneva, et al.
Published: (2021-02-01) -
An efficient loop tiling framework for convolutional neural network inference accelerators
by: Hongmin Huang, et al.
Published: (2022-01-01)