Machine Learning Methods and Tools for Hardware Design
HiPEAC 2027 Workshop
January 18
14:00 - 17:00
Etive Room
SEC • Glasgow
Unlocking the Potential of AI/ML in Hardware Design
Modern hardware design is outgrowing traditional EDA workflows due to exploding design complexity, tighter time-to-market pressure, and nanoscale physical constraints that limit classical heuristics. AI/ML offer a promising path forward, already being applied across the design flow with notable successes like DeepMind's AlphaChip (RL-based floorplanning) and NVIDIA's ChipNeMo (a hardware-focused LLM), yet the field remains fragmented due to unresolved issues in generalizability, tool integration, dataset availability, and the academic-to-industrial gap—challenges that the AI4HW workshop aims to address by uniting AI and hardware researchers to share progress and drive more intelligent, automated, scalable design flows.
Invited Speakers
Call for Presentations
We welcome informal contributions from industry and academia, especially work in progress and lessons learned from applying AI/ML in real design flows.
Topics of interest
- Performance and efficiency modeling based on AI
- AI-driven architecture design and space exploration (DSE)
- AI for IC and IC for AI
Deadline: 02-11-2026 AoE
No formal proceedings.
Accepted contributions include a 5 minute presentation followed by discussion. Submit a one-page PDF abstract with the title, presenter name(s), affiliation, and a short description of the challenge, insight, or lesson you would like to discuss. No template is required. All presenters and participants must register for the HiPEAC conference to attend.
Program
Open Flows, Better Models: Why AI for Hardware Needs Open-Source EDA
Christian Pilato • TBA
Machine learning, including large language models, is increasingly being applied across the hardware design flow, from high-level synthesis to physical implementation. Building better models requires diverse training data, reliable feedback from design tools, and the ability to generalize across designs and technologies. This talk argues that open-source EDA provides essential infrastructure for meeting these needs. Open tools, designs, and PDKs can support systematic generation of datasets spanning multiple abstraction levels and enable tool feedback to guide model training and refinement. They also allow researchers to explore how tool versions, configurations, and target technologies affect design outcomes, helping develop models that remain effective beyond a single experimental setup. Reproducible flows provide a common basis for measuring these improvements. The talk will discuss open challenges in data quality, scalability, and transfer to industrial flows, highlighting the role of European open-source EDA initiatives.
AI/ML-Driven Design of RF and mm-Wave Circuits and Systems: Advances and Future Trends
Fábio Passos • TBA
The growing complexity of hardware systems for next-generation wireless communication, sensing, and satellite applications is challenging traditional design methodologies. Artificial intelligence (AI) and machine learning (ML) are emerging as key enablers for accelerating hardware development, reducing design effort, and improving design efficiency. In particular, RF and millimeter-wave circuits pose unique challenges due to their nonlinearities, large design spaces, expensive electromagnetic simulations, and sensitivity to process, voltage, and temperature variations. This talk reviews recent advances in AI/ML-driven design methodologies for RF and mm-Wave circuits and systems, covering device modeling, passive device synthesis, electromagnetic-aware optimization, circuit sizing, layout generation, and system-level co-design. Using RF and mm-Wave design as a representative case study, the talk discusses how AI can be integrated across the hardware design flow and highlights emerging trends toward end-to-end and autonomous design environments, as well as the key challenges and opportunities ahead.
TBA