Huang wins IEEE/ACM ICCAD most influential paper award

Tsung-Wei (TW) Huang, an assistant professor of electrical and computer engineering at the University of Wisconsin-Madison, is the recipient of the 2024 ICCAD 10-Year Retrospective Most Influential Paper Award from the IEEE/ACM International Conference on Computer Aided Design, held in New Jersey in late October 2024.

The award recognizes a paper Huang co-authored with Martin Wong, his then PhD advisor at the University of Illinois Urbana-Champaign, published in 2015. That paper introduced OpenTimer, a novel algorithmic analysis tool Huang created to aid in the design of integrated circuits, or computer chips. The tool allows a chip designer to make sure that all of the various signals on a chip arrive in the right sequence and at the right speed to make the whole design function correctly.

While the algorithm presented in the paper was—and is—very useful to chip designers, that’s not the only reason the paper has been impactful for over a decade. “We presented the paper to multiple companies such as IBM, Cadence, Synopsys, Intel, TSMC and others and they liked the idea,” Huang says. “Then we started to think this solution might not just be beneficial for these companies, but also the broader community.”

Huang made the decision to make the technology open source, which was an unusual choice at the time, when most computer engineers closely guarded their code. That decision turned out to be a great one. Not only did many companies in the chip industry start using the tool, other researchers and computer scientists utilized it too, developing a community around OpenTimer. Over the last decade, they have helped Huang refine the tool, which he has tweaked and upgraded using GPU accelerators. In fact, he earned a prestigious National Science Foundation CAREER Award in 2022 to improve and maintain the project. 

More recently, Huang has expanded the idea even further, taking the core of OpenTimer to create TaskFlow, a tool that uses the algorithm to schedule a mix of computing resources, like GPUs, CPUs and field programmable gate arrays so they can efficiently work together to accelerate things like machine learning, quantum circuit simulation and circuit design automation problems.

Huang says the award is particularly meaningful because it not only awards the paper’s impact inside academia but also recognizes its influence on industry and society as a whole. He also says it imparts an important lesson to other researchers. “It’s definitely an encouragement, not just to me, but also students. A lot of them want to do quick work so they can get published right away, so a lot of times they ignore the potential of their work,” says Huang. “It’s an inspiration for them to think about what kind of impact their work could have on society over 10 years.”