Approximate arithmetic
Application-aware operators and accelerators that trade imperceptible quality loss for power, area, and performance gains.
← All research fields
Research field 01
Emerging Computing
How can new models of computation become practical, measurable, and useful at system scale?
Perspective
I explore how application tolerance and new computing paradigms can deliver meaningful energy and performance gains. The work connects arithmetic, memory, architecture, and workload behavior—without assuming that every operation must be exact or every system must follow a conventional von Neumann path.
Neuromorphic systems
Spiking models and soft-logic architectures for sparse, event-driven computation.
Memory-oriented design
Architecture choices that recognize memory behavior, nonvolatile devices, and data movement as first-class constraints.
Relevant publications
Selected work in this field.
Salim Ullah, Siva Satyendra Sahoo, and Akash Kumar, AxO-ReQ: Redundancy-Aware Approximate Multipliers for Reliable Quantized Neural Acceleration, in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. Accepted for CASES (ESWeek) 2026.
Salim Ullah, Sahoo, Siva Satyendra, and Akash Kumar. AxOSpike: Spiking Neural Networks-driven Approximate Operator Design. in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 43, no. 11, pp. 3324-3335, Nov. 2024, doi: 10.1109/TCAD.2024.3443000.
[IEEE TCAS-I '24]Siva Satyendra Sahoo, Salim Ullah, Soumyo Bhattachrjee, and Akash Kumar. 2024. AxOCS: Scaling FPGA-Based Approximate Operators Using Configuration Supersampling. IEEE Transactions on Circuits and Systems I: Regular Papers doi: 10.1109/TCSI.2024.3385333.
Salim Ullah, Siva Satyendra Sahoo, Can Li, Chao Li, Liu Liu, Tomas Sousa Pereira, Bo Wen, Xunzhao Yin, Armin Darjani, Nima Kavand, Chakravarthy Bodla, Rupa Yashaswi Panduga, Aniruddh Holemadlu, Johannes Maly, Jonathan Förste, Samarth Vadia, Xiaobo Sharon Hu, and Akash Kumar, Special Session: Circuit and Architecture Design with Emerging Computing Paradigms, in Proceedings of the 2025 IEEE/ACM International Conference on Computer-Aided Design (ICCAD ’25), Munich, Germany.
Siva Satyendra Sahoo, Bastien Deveautour, Marcello Traiola, Chongyan Gu, Yun Wu, Aditya Japa, Salim Ullah, and Akash Kumar, Special Session: Emerging scope and design challenges for approximate computing: optimizing accuracy-PPA trade-offs and beyond, in Proceedings of the 2025 ACM/IEEE International Conference on Compilers, Architectures, and Synthesis for Embedded Systems (CASES, ESWEEK ’25), Taipei, Taiwan. Association for Computing Machinery, New York, NY, USA, 1–10. DOI:https://doi.org/10.1145/3742872.3757056.
[MOCAST '25]Salim Ullah, Siva Satyendra Sahoo and Akash Kumar, Special Session: Approximate Arithmetic Circuits Enabling Energy-Efficient Edge Computing, 2025 14th International Conference on Modern Circuits and Systems Technologies (MOCAST ’25), Dresden, Germany, 2025, pp. 1-6, doi: 10.1109/MOCAST65744.2025.11083734.