Emerging scope and design challenges for approximate computing: optimizing accuracy-PPA trade-offs and beyond
Published in ACM Transactions on Embedded Computing Systems, 2025
This article examines the emerging challenges in Approximate Computing, especially focusing on optimizing the trade-offs between output accuracy and non-functional metrics: Power, Performance, and Area (PPA). It analyses the current scope of approximate computing techniques, identifies limitations in existing methods, and proposes design considerations and research directions for pushing beyond present trade-offs. The work also highlights future challenges, including new abstractions, tool support, hardware-software co-design, and benchmarking for accuracy-PPA optimization.
Recommended citation: Sahoo, S. S., Deveautour, B., Traiola, M., Gu, C., Wu, Y., Japa, A., Ullah, S. & Kumar, A. (2025). “Emerging scope and design challenges for approximate computing: optimizing accuracy-PPA trade-offs and beyond.” ACM Transactions on Embedded Computing Systems. (Accepted 5 June 2025).
Download Paper | Download Slides | Download Bibtex