EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Agentic Design of Approximate DFT Digital IP Cores on TSMC 28 nm CMOS ASIC Technology with Verification on RF-SoC

Manushi Shihara de Silva, R. J. Cintra, Arjuna Madanayake

Electronics · 07.11.2026 · 15 (21) · 5180

DOI: 10.3390/electronics15215180 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 07.11.2026. Verfasst von Manushi Shihara de Silva und 2 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. National Science Foundation, Brazilian CNPq.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence (AI)-based digital integrated circuit (IC) design is exploding in the chip industry. Agent-based digital logic design is considered the next paradigm in computer architecture at the chip level. In this work, we explore the domain specialization of a Claude-based AI agent on the specific topic of Fast Fourier transform (FFT) algorithms, using butterfly architectures for sparse factorized matrix-vector realization of discrete Fourier transform (DFT) applied to the hardware realization of the novel special case of approximate DFT with corresponding sparse factorizations. Unlike FFTs, which are well-known and commonly described in the literature and public hardware description language (HDL) code bases, approximate discrete Fourier transforms (ADFTs) are a new approach to frequency computation in the discrete time domain that scales as O(N) arithmetic (multiplication) operations. HDL code implementation of these factorizations is not available in public repositories, and while the contents of the proprietary training corpus of Claude cannot be inspected, this absence makes it unlikely that the algorithm is represented in the training data. No retraining or fine-tuning of the model is done in this work; instead, we specialize a general-purpose AI agent through prompting at design time using our published ADFT matrices and their sparse factorizations. The agent combines this provisioned domain knowledge with its existing knowledge of FFT theory, including Cooley–Tukey butterfly networks, to adapt standard FFT algorithms for the ADFT use case as the number of frequency points N scales to large values. We verify mathematical performance as well as digital logic correctness as the AI agent scaled design complexity starting from small values of N to larger values, progressively, in a controlled and systematic way. Finally, the agent-generated HDL source code is synthesized as reusable intellectual property (IP) blocks across both an AMD Xilinx Zynq UltraScale+ radio-frequency system-on-chip (RF-SoC) (ZCU216 evaluation platform) and 28 nm TSMC application-specific integrated circuit (ASIC) process design kit (PDK). The results demonstrate that a single AI-generated design description successfully re-targets multiple physical implementation flows, validating the feasibility of automated AI agents for specialized electronic design automation (EDA) workflows.

Förderung

  • U.S. National Science Foundation
  • Brazilian CNPq

Zitieren

APA

Silva, M. S. D., Cintra, R. J., & Madanayake, A. (2026). Agentic Design of Approximate DFT Digital IP Cores on TSMC 28 nm CMOS ASIC Technology with Verification on RF-SoC. Electronics, 15(21), 5180. https://doi.org/10.3390/electronics15215180

Vancouver

Silva MSD, Cintra RJ, Madanayake A. Agentic Design of Approximate DFT Digital IP Cores on TSMC 28 nm CMOS ASIC Technology with Verification on RF-SoC. Electronics. 2026;15(21):5180. doi:10.3390/electronics15215180

BibTeX
@article{Silva2026,
  author = {Silva, Manushi Shihara de and Cintra, R. J. and Madanayake, Arjuna},
  title = {Agentic Design of Approximate DFT Digital IP Cores on TSMC 28 nm CMOS ASIC Technology with Verification on RF-SoC},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {21},
  pages = {5180},
  doi = {10.3390/electronics15215180}
}
Kostenlos starten →