Retrospective: A CORDIC Based Configurable Activation Function for NN Applications
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917268536950784 |
|---|---|
| author | Kokane, Omkar Raut, Gopal Ullah, Salim Lokhande, Mukul Teman, Adam Kumar, Akash Vishvakarma, Santosh Kumar |
| author_facet | Kokane, Omkar Raut, Gopal Ullah, Salim Lokhande, Mukul Teman, Adam Kumar, Akash Vishvakarma, Santosh Kumar |
| contents | A CORDIC-based configuration for the design of Activation Functions (AF) was previously suggested to accelerate ASIC hardware design for resource-constrained systems by providing functional reconfigurability. Since its introduction, this new approach for neural network acceleration has gained widespread popularity, influencing numerous designs for activation functions in both academic and commercial AI processors. In this retrospective analysis, we explore the foundational aspects of this initiative, summarize key developments over recent years, and introduce the DA-VINCI AF tailored for the evolving needs of AI applications. This new generation of dynamically configurable and precision-adjustable activation function cores promise greater adaptability for a range of activation functions in AI workloads, including Swish, SoftMax, SeLU, and GeLU, utilizing the Shift-and-Add CORDIC technique. The previously presented design has been optimized for MAC, Sigmoid, and Tanh functionalities and incorporated into ReLU AFs, culminating in an accumulative NEURIC compute unit. These enhancements position NEURIC as a fundamental component in the resource-efficient vector engine for the realization of AI accelerators that focus on DNNs, RNNs/LSTMs, and Transformers, achieving a quality of results (QoR) of 98.5%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14354 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Retrospective: A CORDIC Based Configurable Activation Function for NN Applications Kokane, Omkar Raut, Gopal Ullah, Salim Lokhande, Mukul Teman, Adam Kumar, Akash Vishvakarma, Santosh Kumar Hardware Architecture Artificial Intelligence Computer Vision and Pattern Recognition Emerging Technologies Image and Video Processing A CORDIC-based configuration for the design of Activation Functions (AF) was previously suggested to accelerate ASIC hardware design for resource-constrained systems by providing functional reconfigurability. Since its introduction, this new approach for neural network acceleration has gained widespread popularity, influencing numerous designs for activation functions in both academic and commercial AI processors. In this retrospective analysis, we explore the foundational aspects of this initiative, summarize key developments over recent years, and introduce the DA-VINCI AF tailored for the evolving needs of AI applications. This new generation of dynamically configurable and precision-adjustable activation function cores promise greater adaptability for a range of activation functions in AI workloads, including Swish, SoftMax, SeLU, and GeLU, utilizing the Shift-and-Add CORDIC technique. The previously presented design has been optimized for MAC, Sigmoid, and Tanh functionalities and incorporated into ReLU AFs, culminating in an accumulative NEURIC compute unit. These enhancements position NEURIC as a fundamental component in the resource-efficient vector engine for the realization of AI accelerators that focus on DNNs, RNNs/LSTMs, and Transformers, achieving a quality of results (QoR) of 98.5%. |
| title | Retrospective: A CORDIC Based Configurable Activation Function for NN Applications |
| topic | Hardware Architecture Artificial Intelligence Computer Vision and Pattern Recognition Emerging Technologies Image and Video Processing |
| url | https://arxiv.org/abs/2503.14354 |