Codr Computation And Data Reuse Aware Cnn Accelerator
ASecurity
**arXiv ID:** 2104.09798 **Authors:** Alireza Khadem, Haojie Ye, Trevor Mudge **Published:** 2021-04-20T07:20:17Z **Abstract:** Computation and Data Reuse is critical for the resource-limited Convolutional Neural Network (CNN) accelerators. This paper presents Universal Computation Reuse to exploit weight sparsity, repetition, and similarity simultaneously in a convolutional layer. Moreover, CoDR decreases the cost of weight memory access by proposing a customized Run-Length Encoding scheme a...
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of Codr Computation And Data Reuse Aware Cnn Accelerator?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-codr-computation-and-data-reuse-aware-cnn-accelera)
# CoDR: Computation and Data Reuse Aware CNN Accelerator
**arXiv ID:** 2104.09798
**Authors:** Alireza Khadem, Haojie Ye, Trevor Mudge
**Published:** 2021-04-20T07:20:17Z
**Abstract:**
Computation and Data Reuse is critical for the resource-limited Convolutional Neural Network (CNN) accelerators. This paper presents Universal Computation Reuse to exploit weight sparsity, repetition, and similarity simultaneously in a convolutional layer. Moreover, CoDR decreases the cost of weight memory access by proposing a customized Run-Length Encoding scheme and the number of memory accesses to the intermediate results by introducing an input and output stationary dataflow. Compared to two recent compressed CNN accelerators with the same area of 2.85 mm^2, CoDR decreases SRAM access by 5.08x and 7.99x, and consumes 3.76x and 6.84x less energy.
## Skill Description
This skill is generated from the arXiv paper: CoDR: Computation and Data Reuse Aware CNN Accelerator (2104.09798).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2104.09798](http://arxiv.org/abs/2104.09798v1)