Abstract
Constant coefficient multipliers are widely used in digital signal processing and machine learning architectures. Researchers have proposed HBU-CCM (hybrid binary-unary constant coefficient multiplier), which is an approximate method that outperforms conventional binary and FloPoCo-KCM (table-based real multiplier) methods in terms of hardware cost at the expense of accuracy due to aliasing issues. SimBU (self-similarity-based hybrid binary-unary) is another method that was recently proposed to implement general nonlinear functions using self-similarities leading to few hardware resources. In this work, we use a simplified version of the SimBU algorithm to address the aliasing issues of HBU-CCM and improve accuracy. We also implement a convolution kernel for a Gaussian blurring filter to evaluate our method and compare it to previous works. Our method outperforms conventional binary and FloPoCo-KCM methods in terms of hardware cost with desired accuracy and with no aliasing error as opposed to HBU-CCM.
Original language | English (US) |
---|---|
Title of host publication | 2023 42nd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2023 - Proceedings |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9798350315592 |
DOIs | |
State | Published - 2023 |
Externally published | Yes |
Event | 42nd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2023 - San Francisco, United States Duration: Oct 28 2023 → Nov 2 2023 |
Publication series
Name | IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD |
---|---|
ISSN (Print) | 1092-3152 |
Conference
Conference | 42nd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2023 |
---|---|
Country/Territory | United States |
City | San Francisco |
Period | 10/28/23 → 11/2/23 |
Bibliographical note
Publisher Copyright:© 2023 IEEE.