Event
SC26 BoF: Analog Computing for Science: From Emerging Technologies to a Shared Research Agenda
Wednesday, November 18, 2026, 5:15 pm – 6:45 pm CST, Room W178ab
Analog computing is re-emerging as a broad approach to scientific computation, offering opportunities beyond energy efficiency, including low-latency physical dynamics, reduced data movement, computation integrated with sensing, and new methods for simulation, optimization, and artificial intelligence. Yet progress remains fragmented across physical substrates, applications, architectures, mathematics, and software. This highly interactive BoF brings the SC community together to identify challenges, promising workloads, shared infrastructure, and opportunities for collaboration. Building on the DOE ASCR report Basic Research Needs for Analog Computing for Science, participants will prioritize research directions and help shape a community agenda for analog and hybrid analog-digital computing.
When and Where
- Date: Wednesday, November 18, 2026
- Time: 5:15 pm – 6:45 pm CST
- Room: W178ab, McCormick Place, Chicago, USA (Google Maps)
- Program entry: SC26 conference program
The session takes place in person only.
Why This BoF
As conventional digital scaling faces growing limits in power, data movement, and time-to-solution, analog and hybrid analog-digital systems exploit the continuous dynamics of physical systems — electrical, photonic, mechanical, chemical, biological, and other substrates. Different communities, however, often use incompatible terminology, precision and error models, benchmarks, performance metrics, and evaluation methodologies.
SC convenes exactly the ecosystem needed to evaluate analog computing at the system level: application scientists who know high-value workloads and accuracy requirements, applied mathematicians, architects and systems researchers, software and compiler developers, computing facilities, and industry. Rather than promoting analog computing as a replacement for digital systems, the session focuses on defensible system-level advantages and practical integration into heterogeneous scientific workflows. We will explicitly discuss limitations as well — noise and variability, precision and uncertainty, analog-digital interfaces, scalability, manufacturability, programmability, and the possibility that conversion, calibration, or integration costs outweigh component-level gains.
Starting Point: The Six Priority Research Directions
The discussion uses the six Priority Research Directions (PRDs) of the DOE ASCR report as a starting framework, which participants are invited to challenge, extend, and prioritize:
- Mathematical foundations
- High-performance analog systems
- Novel device primitives
- Analog computing integrated with sensing and the edge
- Natural and unconventional computing substrates
- Full-stack co-design, software, and benchmarking
Format
The BoF is a facilitated community working session rather than a conventional panel. About 75% of the time is reserved for interaction with the audience.
- Welcome and framing. Introduction to the BoF and a brief recap of the PRDs.
- Live poll. Which PRD topics matter most to you? The results steer the discussion.
- Provocations. Each discussion lead brings one or two slides on the report: What did we do well — and what did we miss? Controversial points are welcome.
- Open discussion. Direct, one-to-one exchange between the audience and the discussion leads.
- Wrap-up. A visible summary of key ideas, community-ranked priorities, and next steps.
Intended Outcomes
- Community-ranked research priorities
- Candidate workload and benchmark categories
- Gaps in software and evaluation infrastructure
- Concrete options for follow-on working groups or recurring meetings
A public summary documenting areas of agreement, disagreement, and next steps will be published here after SC26.
Session Leaders
- Dr. Antonino Tumeo, PNNL — moderator
- Dr. Johannes Gebert, HLRS, University of Stuttgart
- Dr. Suma George Cardwell, Sandia National Laboratories
- Prof. Sara Achour, Stanford University and Unconventional AI
- Prof. Josef Weidendorfer, TUD Dresden University of Technology
- Dr. Talya Vaknin, LightSolver
- Dr. Michael Förtsch, Q.ANT GmbH
- Dr. Connah Johnson, Pacific Northwest National Laboratory (PNNL)
Who Should Attend
Everyone working on, or curious about, analog and unconventional computing in HPC: application scientists, applied mathematicians and algorithm developers, computer architects, software and compiler researchers, computing center staff, funding agencies, and vendors. The predecessor BoF at ISC 2025 attracted around 80 participants — we look forward to continuing the conversation at SC26.