Evolutionary Mapping of Neural Networks to Spatial Accelerators

Pierro, Alessandro ; Yik, Jason ; Timcheck, Jonathan ; Lindauer, Marius ; Hüllermeier, Eyke und Wever, Marcel (10. July 2026): Evolutionary Mapping of Neural Networks to Spatial Accelerators. Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '26), San Jose, Costa Rica, 13. - 17. July 2026. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 329-337

Abstract

Spatial accelerators, composed of arrays of compute-memory integrated units, offer an attractive platform for deploying inference workloads with low latency and low energy consumption. However, fully exploiting their architectural advantages typically requires careful, expert-driven mapping of computational graphs to distributed processing elements. In this work, we automate this process by framing the mapping challenge as a black-box optimization problem. We introduce the first evolutionary, hardware-in-the-loop mapping framework for neuromorphic accelerators, enabling users without deep hardware knowledge to deploy workloads more efficiently. On Intel's Loihi 2, our method achieves up to 35% reduction in total latency compared to default heuristics on two sparse multilayer perceptron networks. We further demonstrate the scalability of our approach to multi-chip systems and observe an up to 40% gain in energy efficiency, without explicitly optimizing for it.

• Item Type: Conference or Workshop Item (Paper)
• EU Funded Grant Agreement Number: 101041029
• Faculties: Mathematics, Computer Science and Statistics > Computer Science > Artificial Intelligence and Machine Learning
• Subjects: 000 Computer science, information and general works > 004 Data processing computer science
• ISBN: 979-8-4007-2487-9
• Language: English