TY - GEN
T1 - Retrospective
T2 - 28th IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2025
AU - Kokane, Omkar
AU - Raut, Gopal
AU - Ullah, Salim
AU - Lokhande, Mukul
AU - Teman, Adam
AU - Kumar, Akash
AU - Vishvakarma, Santosh Kumar
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025/1/1
Y1 - 2025/1/1
N2 - 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 resourceefficient 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%.
AB - 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 resourceefficient 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%.
KW - Activation Function
KW - AI accelerators
KW - CORDIC
KW - Reconfigurable Computing
KW - Transformers
UR - https://www.scopus.com/pages/publications/105016118400
U2 - 10.1109/ISVLSI65124.2025.11130218
DO - 10.1109/ISVLSI65124.2025.11130218
M3 - Conference contribution
AN - SCOPUS:105016118400
T3 - Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI
BT - IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2025 - Conference Proceedings
PB - Institute of Electrical and Electronics Engineers
Y2 - 6 July 2025 through 9 July 2025
ER -