MLCAD25-Contest
ReSynthAI: Physical-Aware Logic Resynthesis for Timing Optimization Using AI
Join the exciting MLCAD 2025 Contest and showcase your innovative skills in combining artificial intelligence with electronic design automation (EDA). This year’s challenge, ReSynthAI, focuses on Physical-Aware Logic Resynthesis aimed at timing optimization.
Contest Overview
Participants are tasked with leveraging AI techniques, including supervised, unsupervised, and reinforcement learning, to perform logic resynthesis. The challenge emphasizes the importance of physical awareness, ensuring that decisions made post-logic synthesis improve the post-global route quality of results as shown in the figure below.
The transformations at the netlist level include gate sizing, buffer insertion, Vt swaps, gate cloning, and combinational logic restructuring.
We have released the content details, please find the information in MLCAD25-Contest-Scripts-Benchmarks.
Please find the contest description here.
Contest Challenges Include:
- Applying machine learning techniques (supervised, unsupervised, reinforcement learning) for logic resynthesis.
- Ensuring physical awareness in resynthesis and ensuring routability without congestion overflows.
- Demonstrating timing improvements post global route by performing netlist optimizations post logic synthesis.
Updates:
We have extended the alpha submission deadline to June 15th.
Why Participate?
- Showcase your AI-driven EDA innovations and state-of-the-art algorithms for physical-aware logic resynthesis.
- Apply for travel grants (available for eligible participants) to MLCAD 2025.
- Winners will receive high-performance NVIDIA GPUs as prizes!
Registration, Participants List, and Important Dates
Registration
- Registration opens: March 15, 2025
- Registration deadline: April 23, 2025
- Registrations closed.
Participants List:
If you have any questions about registration, please feel free to contact us through the email provided at the end of the page.
| Team ID | Team Name | Affiliation |
|---|---|---|
| team1 | reinforcedAg | Texas A&M University |
| team2 | SlugSignal | UCSC |
| team3 | dzzz | The Chinese University of Hong Kong |
| team4 | Blue Team | UCSC |
| team5 | BluePhone | Independent |
| team6 | Netlist Ninjas | Nirma University |
| team7 | BW4A | upm |
| team8 | drexel-ice | Drexel university |
| team9 | ssatyendras | IMEC |
| team10 | PACE | University of Maryland, College Park |
| team11 | SeDA | UNIST (South Korea) |
| team12 | X_PhyicalSynthesis | Fudan University |
| team13 | CSDL | Pohang University of Science and Technology |
| team14 | ASEEC Lab | University of California, Davis |
| team15 | DibFan | UT Austin |
| team16 | delftBlue | Delft University of Technology |
| team17 | Slug Cricket | UCSC |
| team18 | SGCAD | Sogang university |
| team19 | AI4Semi | Samsung Semiconductor |
| team20 | Randomize | Fudan University |
| team21 | CDA | TUM |
| team22 | Alrwave | Fudan University |
| team23 | PhyMap | Fudan University |
| team24 | ChandraMind | Arizona State University* |
| team25 | LOGIC101 | Arizona State University* |
| team26 | Physical AI | Arizona State University* |
Contest Timeline
| Milestone | Date |
|---|---|
| Contest Begins | April 23, 2025 |
| Registration Closes | April 23, 2025 |
| Alpha Submission Deadline | June 15, 2025 |
| Beta Submission Deadline | July 15, 2025 |
| Final Submission Deadline | August 10, 2025 |
| Results Announcement | September 2025 |
Prizes
Top-performing teams will receive NVIDIA GPUs as awards! These can be used for further research!
Contest Details
We have released the content details, please find the information in MLCAD25-Contest-Scripts-Benchmarks.
About MLCAD
The International Workshop on Machine Learning for CAD (MLCAD) is the leading venue dedicated to advancing research at the intersection of machine learning and electronic design automation (EDA). It provides a unique platform for collaboration between academia and industry, fostering innovation and driving progress in AI-driven CAD solutions.
Join the contest, push the boundaries of EDA, and lead the future of AI in chip design!
Acknowledgement
We thank NVIDIA for sponsoring the contest, GPU awards, and their involvement in organizing it.
Contest organizers
| Name | Affiliation |
|---|---|
| Atmadip Dey | ASU |
| Vikram Gopalakrishnan | ASU |
| Rongjian Liang | NVIDIA |
| Yanqing Zhang | NVIDIA |
| Haoxing (Mark) Ren | NVIDIA |
| Vidya A Chhabria | ASU |
For questions, reach out to mlcad2025-contest@googlegroups.com
*Please note that these teams are not from the research groups organizing the contest. ASU and NVIDIA research teams will not be eligible for prizes even if there are participants from these institutions.