Sustainable Computing with Neuromorphic and Quantum-Inspired Technologies

“Sustainable Computing with Neuromorphic and Quantum-Inspired Technologies”

This workshop is the winner of the CECAM-Lorentz Competition 2025-26, which is part of the collaboration between CECAM-HQ and the Lorentz Center. Quoting the Competition Review Board:

“This is a strong proposal connecting current developments in application of computer science and the urgency of moving to (and maintaining) a sustainable society.”

Aims

In this workshop we aim to develop a common methodology for systematic exploration, optimization and integration of emerging neuromorphic and quantum-inspired technologies to address cutting edge use cases in computational science that have no sustainable solution with existing digital hardware. One tangible result will be a roadmap paper describing the developed methodology. This will be written on the basis of keynote lectures, discussions and writing sessions lead by experts in science and industry.

Description

Solving the grand computational challenges relies on high-performance computing. However, the energy cost of such computing systems increases tremendously, which already limits the problems we can realistically compute in an affordable and sustainable way. Moreover, some scientific use cases, such as radio astronomy, molecular simulation and particle physics, feature such extreme dataflows that existing digital hardware does not provide a scalable solution.

Neuromorphic and other quantum-inspired computing hardware offers great potential as an accelerator for such highly demanding tasks. The advantage stems from the co-location of memory and processing. This strongly reduces the amount of data transfer between processing and memory, offering fundamental scalings improvements that enable both faster and more energy-efficient solutions.

In this CECAM-Lorentz workshop key experts in challenging computational use cases, join forces with both leading academic and industrial experts in emerging neuromorphic and quantum-inspired computing paradigms and key experts in programming models and profiling. Together they will develop common methodology for sustainable scientific computing with emerging neuromorphic and quantum-inspired hardware.

Main topics include

• Computational and data science challenges
• Ethical challenges
• Spiking Hardware
• Probabilistic and Reversible computing
• Analog and Digital in-memory computing
• Integration, programming models and profiling challenges

The program features plenary talks, discussion and writing sessions, featuring participants from involved through Computational Science NL and from industry (AxelaraAI, Innatera, HourSec, IMChip, IBM,SpiNNclould). As a results of the writing sessions, a roadmap will be written with immediate actions for joint research proposals and publications.