pith. sign in

arxiv: 2601.14541 · v4 · submitted 2026-01-20 · 💻 cs.LG · cs.AI· cs.AR

Report for NSF Workshop on AI for Electronic Design Automation

Deming Chen , Vijay Ganesh , Weikai Li , Yingyan Celine Lin , Yong Liu , Subhasish Mitra , David Z. Pan , Ruchir Puri
show 2 more authors
Jason Cong Yizhou Sun
This is my paper

Pith reviewed 2026-05-16 12:33 UTC · model grok-4.3

classification 💻 cs.LG cs.AIcs.AR
keywords AI for EDAElectronic Design AutomationHardware SynthesisMachine LearningWorkshop ReportDesign VerificationNSF RecommendationsChip Design Acceleration
0
0 comments X

The pith

NSF should fund AI-EDA collaborations, data infrastructure, and workforce programs to shorten hardware design cycles.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The report summarizes a 2024 workshop that explored how machine learning methods can address bottlenecks in electronic design automation. It organizes the discussion around four themes covering physical design, high-level synthesis, optimization tools, and verification. The central recommendation is that targeted NSF investments in joint research, datasets, compute resources, and training will enable faster design turnaround and more capable hardware systems. A sympathetic reader would see this as a call to treat AI as a practical lever for scaling complex chip development beyond current manual and heuristic limits.

Core claim

The workshop report claims that AI techniques spanning large language models, graph neural networks, reinforcement learning, and neurosymbolic approaches can be applied across physical synthesis, high-level logic synthesis, optimization, and test/verification to reduce design turnaround time, and that NSF should therefore foster cross-community collaboration, invest in foundational AI methods tailored to EDA, build robust data and scalable compute infrastructures, and support workforce development to democratize access to advanced hardware design capabilities.

What carries the argument

Four workshop themes that map specific AI methods (LLMs for code generation, GNNs for physical layout, RL for optimization) onto EDA stages from high-level synthesis through manufacturing and verification.

If this is right

  • Design turnaround times for complex chips can be shortened by applying LLMs to RTL generation and pragma insertion.
  • AI-augmented SAT solvers and verification tools can improve coverage and reduce escape of bugs in hardware.
  • Better data infrastructures will allow graph-based and reinforcement-learning models to optimize physical synthesis and DFM steps.
  • Workforce programs will expand the pool of engineers who can use these AI tools, lowering barriers to custom hardware.
  • Combined investments will support next-generation systems whose scale exceeds what current manual EDA flows can handle.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the data infrastructure recommendations succeed, open EDA datasets could become a standard benchmark resource similar to ImageNet for vision.
  • Integration of AI across all four themes may create end-to-end differentiable design pipelines that jointly optimize logic, layout, and testability.
  • Security and reliability challenges listed in the verification theme suggest that AI methods will need explicit adversarial robustness guarantees before widespread adoption in safety-critical hardware.

Load-bearing premise

That the collected views of workshop participants correctly identify the highest-impact problems and that following the listed recommendations will produce measurable gains in design speed and hardware performance.

What would settle it

A controlled comparison, five years after NSF implements the recommended data and compute programs, showing no statistically significant reduction in average time from RTL to tape-out for designs of comparable complexity.

read the original abstract

This report distills the discussions and recommendations from the NSF Workshop on AI for Electronic Design Automation (EDA), held on December 10, 2024 in Vancouver alongside NeurIPS 2024. Bringing together experts across machine learning and EDA, the workshop examined how AI-spanning large language models (LLMs), graph neural networks (GNNs), reinforcement learning (RL), neurosymbolic methods, etc.-can facilitate EDA and shorten design turnaround. The workshop includes four themes: (1) AI for physical synthesis and design for manufacturing (DFM), discussing challenges in physical manufacturing process and potential AI applications; (2) AI for high-level and logic-level synthesis (HLS/LLS), covering pragma insertion, program transformation, RTL code generation, etc.; (3) AI toolbox for optimization and design, discussing frontier AI developments that could potentially be applied to EDA tasks; and (4) AI for test and verification, including LLM-assisted verification tools, ML-augmented SAT solving, security/reliability challenges, etc. The report recommends NSF to foster AI/EDA collaboration, invest in foundational AI for EDA, develop robust data infrastructures, promote scalable compute infrastructure, and invest in workforce development to democratize hardware design and enable next-generation hardware systems. The workshop information can be found on the website https://ai4eda-workshop.github.io/.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 2 minor

Summary. This manuscript is a report distilling discussions from the NSF Workshop on AI for Electronic Design Automation held December 10, 2024, in Vancouver. It organizes content into four themes—(1) AI for physical synthesis and design-for-manufacturing, (2) AI for high-level and logic-level synthesis, (3) the AI toolbox for optimization and design, and (4) AI for test and verification—and derives five policy recommendations for NSF: fostering AI/EDA collaboration, investing in foundational AI for EDA, developing robust data infrastructures, promoting scalable compute infrastructure, and investing in workforce development.

Significance. If the reported expert consensus holds, the document provides a timely, actionable roadmap for NSF investment that could accelerate integration of LLMs, GNNs, RL, and neurosymbolic methods into EDA flows. This has the potential to shorten design turnaround, democratize hardware design, and support next-generation systems. The report’s value lies in its synthesis of cross-community input rather than new empirical results.

minor comments (2)
  1. [Recommendations] The five recommendations are presented as a list without explicit cross-references to the four workshop themes; adding one sentence per recommendation that cites the relevant theme(s) would make the linkage between discussion and policy suggestion more transparent.
  2. [Theme descriptions] The abstract states that the workshop examined “AI-spanning large language models (LLMs), graph neural networks (GNNs), reinforcement learning (RL), neurosymbolic methods, etc.”; the body should include at least one concrete example per theme of how a specific technique was discussed, to avoid leaving the claim at a high level of generality.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive assessment of the workshop report and for recommending minor revision. The document synthesizes expert discussions from the NSF Workshop on AI for EDA into actionable recommendations for NSF investment. No specific major comments were provided in the report, so we interpret the minor revision request as an opportunity to enhance clarity, formatting, or minor details without altering the core content or recommendations.

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The document is a descriptive workshop report summarizing discussions across four themes and distilling them into NSF policy recommendations. It contains no equations, derivations, fitted parameters, predictions, or formal claims that could reduce to inputs by construction. No self-citations function as load-bearing justifications for any mathematical or uniqueness result, and the content is a straightforward distillation of expert consensus without self-referential loops or renamed known results.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a policy-oriented workshop summary with no mathematical models, free parameters, axioms, or invented entities; the content rests entirely on the reported expert discussions.

pith-pipeline@v0.9.0 · 5575 in / 1139 out tokens · 32397 ms · 2026-05-16T12:33:23.293718+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

53 extracted references · 53 canonical work pages

  1. [1]

    A graph placement methodology for fast chip design,

    A. Mirhoseini, A. Goldie, M. Yazgan, J. W. Jiang, E. Songhori, S. Wang, Y .-J. Lee, E. Johnson, O. Pathak, A. Novaet al., “A graph placement methodology for fast chip design,”Nature, vol. 594, no. 7862, pp. 207– 212, 2021

    work page 2021

  2. [2]

    DNN-Opt: An RL inspired optimization for analog circuit sizing using deep neural networks,

    A. F. Budak, P. Bhansali, B. Liu, N. Sun, D. Z. Pan, and C. V . Kashyap, “DNN-Opt: An RL inspired optimization for analog circuit sizing using deep neural networks,” in2021 58th ACM/IEEE Design Automation Conference (DAC). IEEE, 2021, pp. 1219–1224

    work page 2021

  3. [3]

    A timing engine inspired graph neural network model for pre-routing slack prediction,

    Z. Guo, M. Liu, J. Gu, S. Zhang, D. Z. Pan, and Y . Lin, “A timing engine inspired graph neural network model for pre-routing slack prediction,” inProceedings of the 59th ACM/IEEE Design Automation Conference, 2022, pp. 1207–1212

    work page 2022

  4. [4]

    DRC-Coder: Automated drc checker code generation using LLM autonomous agent,

    C.-C. Chang, C.-T. Ho, Y . Li, Y . Chen, and H. Ren, “DRC-Coder: Automated drc checker code generation using LLM autonomous agent,” inProceedings of the 2025 International Symposium on Physical Design (ISPD ’25). Austin, TX, USA: ACM, March 2025, pp. 143–151

    work page 2025

  5. [5]

    DREAM-GAN: Advanc- ing dreamplace towards commercial-quality using generative adversarial learning,

    Y .-C. Lu, H. Ren, H.-H. Hsiao, and S. K. Lim, “DREAM-GAN: Advanc- ing dreamplace towards commercial-quality using generative adversarial learning,” inProceedings of the 2023 International Symposium on Physical Design, 2023, pp. 141–148. JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 11

    work page 2023

  6. [6]

    DREAM- Place: Deep learning toolkit-enabled GPU acceleration for modern VLSI placement,

    Y . Lin, S. Dhar, W. Li, H. Ren, B. Khailany, and D. Z. Pan, “DREAM- Place: Deep learning toolkit-enabled GPU acceleration for modern VLSI placement,” inProceedings of the 56th Annual Design Automation Conference 2019, 2019, pp. 1–6

    work page 2019

  7. [7]

    INSTA: An ultra-fast, differentiable, statistical static timing analysis engine for industrial physical design applications,

    Y .-C. Lu, Z. Guo, K. Kunal, R. Liang, and H. Ren, “INSTA: An ultra-fast, differentiable, statistical static timing analysis engine for industrial physical design applications,” in2025 62nd ACM/IEEE Design Automation Conference (DAC). IEEE, 2025, pp. 1–7

    work page 2025

  8. [8]

    A data-driven, congestion- aware and open-source timing-driven FPGA placer accelerated by GPUs,

    Z. Xiong, R. S. Rajarathnam, and D. Z. Pan, “A data-driven, congestion- aware and open-source timing-driven FPGA placer accelerated by GPUs,” in2024 IEEE 32nd Annual International Symposium on Field- Programmable Custom Computing Machines (FCCM). IEEE, 2024, pp. 115–125

    work page 2024

  9. [9]

    Machine learning based lithographic hotspot detection with critical-feature extraction and clas- sification,

    D. Ding, X. Wu, J. Ghosh, and D. Z. Pan, “Machine learning based lithographic hotspot detection with critical-feature extraction and clas- sification,” in2009 IEEE international conference on IC design and technology. IEEE, 2009, pp. 219–222

    work page 2009

  10. [10]

    LithoGAN: End- to-end lithography modeling with generative adversarial networks,

    W. Ye, M. B. Alawieh, Y . Lin, and D. Z. Pan, “LithoGAN: End- to-end lithography modeling with generative adversarial networks,” in Proceedings of the 56th Annual Design Automation Conference 2019, 2019, pp. 1–6

    work page 2019

  11. [11]

    NeurOLight: A physics-agnostic neural operator enabling parametric photonic device simulation,

    J. Gu, Z. Gao, C. Feng, H. Zhu, R. Chen, D. Boning, and D. Pan, “NeurOLight: A physics-agnostic neural operator enabling parametric photonic device simulation,”Advances in Neural Information Processing Systems, vol. 35, pp. 14 623–14 636, 2022

    work page 2022

  12. [12]

    AnalogCoder: Analog circuit design via training-free code generation,

    Y . Lai, S. Lee, G. Chen, S. Poddar, M. Hu, D. Z. Pan, and P. Luo, “AnalogCoder: Analog circuit design via training-free code generation,” inProceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 1, 2025

    work page 2025

  13. [13]

    PulseRF: Physics-augmented ml modeling and synthesis for high-frequency RFIC design,

    H. Chae, H. Yu, S. Li, and D. Z. Pan, “PulseRF: Physics-augmented ml modeling and synthesis for high-frequency RFIC design,” inIEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2024, pp. 1–9

    work page 2024

  14. [14]

    Design rule checking with a CNN based feature extractor,

    L. Francisco, T. Lagare, A. Jain, S. Chaudhary, M. Kulkarni, D. Sardana, W. R. Davis, and P. Franzon, “Design rule checking with a CNN based feature extractor,” inProceedings of the 2020 ACM/IEEE Workshop on Machine Learning for CAD, 2020, pp. 9–14

    work page 2020

  15. [15]

    Automated accelerator optimization aided by graph neural networks,

    A. Sohrabizadeh, Y . Bai, Y . Sun, and J. Cong, “Automated accelerator optimization aided by graph neural networks,” inProceedings of the 59th ACM/IEEE Design Automation Conference, 2022, pp. 55–60

    work page 2022

  16. [16]

    AutoDSE: Enabling software programmers to design efficient FPGA accelerators,

    A. Sohrabizadeh, C. H. Yu, M. Gao, and J. Cong, “AutoDSE: Enabling software programmers to design efficient FPGA accelerators,”ACM Transactions on Design Automation of Electronic Systems (TODAES), vol. 27, no. 4, pp. 1–27, 2022

    work page 2022

  17. [17]

    Robust GNN-based representation learning for HLS,

    A. Sohrabizadeh, Y . Bai, Y . Sun, and J. Cong, “Robust GNN-based representation learning for HLS,” in2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 2023, pp. 1–9

    work page 2023

  18. [18]

    Cross-modality program representation learning for electronic design automation with high-level synthesis,

    Z. Qin, Y . Bai, A. Sohrabizadeh, Z. Ding, Z. Hu, Y . Sun, and J. Cong, “Cross-modality program representation learning for electronic design automation with high-level synthesis,” inProceedings of the 2024 ACM/IEEE International Symposium on Machine Learning for CAD, 2024, pp. 1–12

    work page 2024

  19. [19]

    Efficient task transfer for HLS DSE,

    Z. Ding, A. Sohrabizadeh, W. Li, Z. Qin, Y . Sun, and J. Cong, “Efficient task transfer for HLS DSE,” inProceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, 2024, pp. 1–9

    work page 2024

  20. [20]

    Hierarchical mixture of experts: Generalizable learning for high-level synthesis,

    W. Li, D. Wang, Z. Ding, A. Sohrabizadeh, Z. Qin, J. Cong, and Y . Sun, “Hierarchical mixture of experts: Generalizable learning for high-level synthesis,” inProceedings of the AAAI Conference on Artificial Intelli- gence, vol. 39, no. 17, 2025, pp. 18 476–18 484

    work page 2025

  21. [21]

    Source-to-source optimization for HLS,

    J. Cong, M. Huang, P. Pan, Y . Wang, and P. Zhang, “Source-to-source optimization for HLS,” inFPGAs for Software Programmers. Springer, 2016, pp. 137–163

    work page 2016

  22. [22]

    ScaleHLS: A new scalable high-level synthesis framework on multi-level intermediate representation,

    H. Ye, C. Hao, J. Cheng, H. Jeong, J. Huang, S. Neuendorffer, and D. Chen, “ScaleHLS: A new scalable high-level synthesis framework on multi-level intermediate representation,” in2022 IEEE international symposium on high-performance computer architecture (HPCA). IEEE, 2022, pp. 741–755

    work page 2022

  23. [23]

    HIDA: A hierarchical dataflow compiler for high-level synthesis,

    H. Ye, H. Jun, and D. Chen, “HIDA: A hierarchical dataflow compiler for high-level synthesis,” inProceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1, 2024, pp. 215–230

    work page 2024

  24. [24]

    Allo: A programming model for composable accelerator design,

    H. Chen, N. Zhang, S. Xiang, Z. Zeng, M. Dai, and Z. Zhang, “Allo: A programming model for composable accelerator design,”Proceedings of the ACM on Programming Languages, vol. 8, no. PLDI, pp. 593–620, 2024

    work page 2024

  25. [25]

    Stream-HLS: Towards automatic dataflow acceleration,

    S. Basalama and J. Cong, “Stream-HLS: Towards automatic dataflow acceleration,” inProceedings of the 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays, 2025, pp. 103–114

    work page 2025

  26. [26]

    A unified framework for automated code transformation and pragma insertion,

    S. Pouget, L.-N. Pouchet, and J. Cong, “A unified framework for automated code transformation and pragma insertion,” inProceedings of the 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays, 2025, pp. 187–198

    work page 2025

  27. [27]

    GPT4AIGChip: Towards next-generation AI accelerator design au- tomation via large language models,

    Y . Fu, Y . Zhang, Z. Yu, S. Li, Z. Ye, C. Li, C. Wan, and Y . C. Lin, “GPT4AIGChip: Towards next-generation AI accelerator design au- tomation via large language models,” in2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 2023, pp. 1–9

    work page 2023

  28. [28]

    MG-Verilog: Multi- grained dataset towards enhanced LLM-assisted Verilog generation,

    Y . Zhang, Z. Yu, Y . Fu, C. Wan, and Y . C. Lin, “MG-Verilog: Multi- grained dataset towards enhanced LLM-assisted Verilog generation,” in 2024 IEEE LLM Aided Design Workshop (LAD). IEEE, 2024, pp. 1–5

    work page 2024

  29. [29]

    To- wards a comprehensive benchmark for high-level synthesis targeted to FPGAs,

    Y . Bai, A. Sohrabizadeh, Z. Qin, Z. Hu, Y . Sun, and J. Cong, “To- wards a comprehensive benchmark for high-level synthesis targeted to FPGAs,”Advances in Neural Information Processing Systems, vol. 36, pp. 45 288–45 299, 2023

    work page 2023

  30. [30]

    An iteratively-refined dataset for high-level synthesis functional verification through LLM- aided bug injection,

    L. J. Wan, H. Ye, J. Wang, M. Jha, and D. Chen, “An iteratively-refined dataset for high-level synthesis functional verification through LLM- aided bug injection,” in2024 IEEE LLM Aided Design Workshop (LAD). IEEE, 2024, pp. 1–6

    work page 2024

  31. [31]

    LLM4HWDesign contest: Construct- ing a comprehensive dataset for LLM-assisted hardware code generation with community efforts,

    Z. Yu, C. Li, Y . Zhang, M. Liu, N. Pinckney, W. Zhou, H. Yang, R. Liang, H. Ren, and Y . C. Lin, “LLM4HWDesign contest: Construct- ing a comprehensive dataset for LLM-assisted hardware code generation with community efforts,” inProceedings of the 43rd IEEE/ACM Inter- national Conference on Computer-Aided Design, 2024, pp. 1–5

    work page 2024

  32. [32]

    Pyramid: Machine learning framework to estimate the optimal timing and resource usage of a high-level synthesis design,

    H. M. Makrani, F. Farahmand, H. Sayadi, S. Bondi, S. M. P. Dinakarrao, H. Homayoun, and S. Rafatirad, “Pyramid: Machine learning framework to estimate the optimal timing and resource usage of a high-level synthesis design,” in2019 29th International Conference on Field Programmable Logic and Applications (FPL). IEEE, 2019, pp. 397– 403

    work page 2019

  33. [33]

    OpenLS-DGF: An adaptive open-source dataset generation framework for machine learning tasks in logic syn- thesis,

    L. Ni, R. Wang, M. Liu, X. Meng, X. Lin, J. Liu, G. Luo, Z. Chu, W. Qian, X. Yanget al., “OpenLS-DGF: An adaptive open-source dataset generation framework for machine learning tasks in logic syn- thesis,”IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2025

    work page 2025

  34. [34]

    DRiLLS: Deep reinforcement learning for logic synthesis,

    A. Hosny, S. Hashemi, M. Shalan, and S. Reda, “DRiLLS: Deep reinforcement learning for logic synthesis,” in2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC). IEEE, 2020, pp. 581–586

    work page 2020

  35. [35]

    AISYN: AI-driven rein- forcement learning-based logic synthesis framework,

    G. Pasandi, S. Pratty, and J. Forsyth, “AISYN: AI-driven rein- forcement learning-based logic synthesis framework,”arXiv preprint arXiv:2302.06415, 2023

    work page arXiv 2023

  36. [36]

    LSOracle: A logic synthesis framework driven by arti- ficial intelligence,

    W. L. Neto, M. Austin, S. Temple, L. Amaru, X. Tang, and P.-E. Gaillardon, “LSOracle: A logic synthesis framework driven by arti- ficial intelligence,” in2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD). IEEE, 2019, pp. 1–6

    work page 2019

  37. [37]

    INVICTUS: Optimizing boolean logic circuit synthesis via synergistic learning and search,

    A. B. Chowdhury, M. Romanelli, B. Tan, R. Karri, and S. Garg, “INVICTUS: Optimizing boolean logic circuit synthesis via synergistic learning and search,”arXiv preprint arXiv:2305.13164, 2023

    work page arXiv 2023

  38. [38]

    Gamora: Graph learning based symbolic reasoning for large-scale boolean networks,

    N. Wu, Y . Li, C. Hao, S. Dai, C. Yu, and Y . Xie, “Gamora: Graph learning based symbolic reasoning for large-scale boolean networks,” in 2023 60th ACM/IEEE Design Automation Conference (DAC). IEEE, 2023, pp. 1–6

    work page 2023

  39. [39]

    IC/ASIC functional verification trend report – 2024,

    H. Foster, “IC/ASIC functional verification trend report – 2024,” Siemens EDA and Wilson Research Group, Tech. Rep., Feb 2025, white paper. [Online]. Available: https://verificationacademy.com/topic s/planning-measurement-and-analysis/wrg-industry-data-and-trends/20 24-siemens-eda-and-wilson-research-group-ic-asic-functional-verificat ion-trend-report/

    work page 2024

  40. [40]

    G-QED: Generalized QED pre-silicon verification beyond non-interfering hardware accelerators,

    S. Chattopadhyay, K. Devarajegowda, B. Zhao, F. Lonsing, B. A. D’Agostino, I. Vavelidou, V . D. Bhatt, S. Prebeck, W. Ecker, C. Trip- pel, C. Barrett, and S. Mitra, “G-QED: Generalized QED pre-silicon verification beyond non-interfering hardware accelerators,” in2023 60th ACM/IEEE Design Automation Conference (DAC), 2023, pp. 1–6

    work page 2023

  41. [41]

    Silent data corruption by 10×test escapes threatens reliable computing,

    S. Mitra, S. Banerjee, M. Dixon, M. Fuller, R. Govindaraju, P. Hochschild, E. X. Liu, B. Parthasarathy, and P. Ranganathan, “Silent data corruption by 10×test escapes threatens reliable computing,”IEEE Design & Test, 2025

    work page 2025

  42. [42]

    CLEAR cross-layer resilience: A retrospective,

    E. Cheng, H. Cho, S. Mirkhani, L. Szafaryn, J. Abraham, P. Bose, C.- Y . Cher, K. Lilja, K. Skadron, M. Stanet al., “CLEAR cross-layer resilience: A retrospective,”IEEE Design & Test, 2024

    work page 2024

  43. [43]

    Chip-Chat: Challenges and opportunities in conversational hardware design,

    J. Blocklove, S. Garg, R. Karri, and H. Pearce, “Chip-Chat: Challenges and opportunities in conversational hardware design,” in2023 ACM/IEEE 5th Workshop on Machine Learning for JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 12 CAD (MLCAD). IEEE, Sep. 2023, p. 1–6. [Online]. Available: http://dx.doi.org/10.1109/MLCAD58807.2023.10299874

    work page doi:10.1109/mlcad58807.2023.10299874 2021

  44. [44]

    Chipgpt: How far are we from natural language hardware design,

    K. Chang, Y . Wang, H. Ren, M. Wang, S. Liang, Y . Han, H. Li, and X. Li, “ChipGPT: How far are we from natural language hardware design,” 2025. [Online]. Available: https://arxiv.org/abs/2305.14019

    work page arXiv 2025

  45. [45]

    Rome was not built in a single step: Hierarchical prompting for LLM-based chip design,

    A. Nakkab, S. Q. Zhang, R. Karri, and S. Garg, “Rome was not built in a single step: Hierarchical prompting for LLM-based chip design,” inProceedings of the 2024 ACM/IEEE International Symposium on Machine Learning for CAD, 2024, pp. 1–11

    work page 2024

  46. [46]

    RTLLM: An open-source benchmark for design RTL generation with large language model,

    Y . Lu, S. Liu, Q. Zhang, and Z. Xie, “RTLLM: An open-source benchmark for design RTL generation with large language model,” in 2024 29th Asia and South Pacific Design Automation Conference (ASP- DAC). IEEE, 2024, pp. 722–727

    work page 2024

  47. [47]

    VerilogEval: Evaluating large language models for Verilog code generation,

    M. Liu, N. Pinckney, B. Khailany, and H. Ren, “VerilogEval: Evaluating large language models for Verilog code generation,” 2023. [Online]. Available: https://arxiv.org/abs/2309.07544

    work page arXiv 2023

  48. [48]

    VerilogCoder: Autonomous Verilog coding agents with graph-based planning and abstract syntax tree (AST)- based waveform tracing tool,

    C.-T. Ho, H. Ren, and B. Khailany, “VerilogCoder: Autonomous Verilog coding agents with graph-based planning and abstract syntax tree (AST)- based waveform tracing tool,” inProceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 1, 2025, pp. 300–307

    work page 2025

  49. [49]

    OPL4GPT: An application space exploration of optimal programming language for hardware design by LLM,

    K. Tasnia and S. Rahman, “OPL4GPT: An application space exploration of optimal programming language for hardware design by LLM,” in Proceedings of the 30th Asia and South Pacific Design Automation Conference, 2025, pp. 981–987

    work page 2025

  50. [50]

    New verification unlocks AI-boosted chip design,

    S. Mitra, “New verification unlocks AI-boosted chip design,” Presen- tation at the NSF Workshop on AI for Electronic Design Automation, Vancouver, BC, Dec. 2024, invited talk

    work page 2024

  51. [51]

    Machine learning and logic: A new frontier in artificial intelligence,

    V . Ganesh, S. A. Seshia, and S. Jha, “Machine learning and logic: A new frontier in artificial intelligence,”Formal Methods in System Design, vol. 60, no. 3, pp. 426–451, 2022

    work page 2022

  52. [52]

    Exponential recency weighted average branching heuristic for SAT solvers,

    J. H. Liang, V . Ganesh, P. Poupart, and K. Czarnecki, “Exponential recency weighted average branching heuristic for SAT solvers,” in Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, ser. AAAI’16. AAAI Press, 2016, p. 3434–3440

    work page 2016

  53. [53]

    RLSF: Fine-tuning LLMs via symbolic feedback,

    P. Jha, P. Jana, P. Suresh, A. Arora, and V . Ganesh, “RLSF: Fine-tuning LLMs via symbolic feedback,”arXiv preprint arXiv:2405.16661, 2024. Deming Chen.Deming Chen is the Abel Bliss Professor in the Grainger College of Engineering at the University of Illinois Urbana-Champaign. His research interests include machine learning and AI, system-level design me...

    work page arXiv 2024