PhD internship, Master internship - Leuven | Just now
RISC-V CPU Power and Performance Modelling for imec’s Future Semiconductor Technologies
As semiconductor technologies and chip architectures are becoming increasingly complex, understanding the interaction between technology and architecture is essential for optimizing performance, power and area of a chip. Technology-architecture co-optimization[1] allows to explore different trade-offs early in the design states to predict the behaviour of chips using future technology before they are fabricated. This requires modelling tools that can capture the right level of detail of a design to make accurate predictions.
This internship will focus on evaluating the impact of future semiconductor technologies on RISC-V CPU microarchitecture performance and power by developing and integrating multi-fidelity modelling approaches ranging from high-level microarchitectural models to RTL-level power simulations.
One particular area of interest is understanding how the complexity of an out-of-order CPU core and uncore microarchitectural structures [2] affect achievable clock frequency, power consumption, and silicon area. The clock frequency of a wide out-of-order superscalar is limited by a few wire-dominated structures [2], namely register renaming, the wakeup and select logic of the issue window, and the bypass logic. Palacharla et al.[2] quantified how these structures’ delay scales with issue width and window size. Their study measured delay only, yet the issue logic is also a major energy consumer [3][4], and the load-store queue (LSQ) are based on complex RAM/CAM structures that scale poorly with capacity and port count [5]. There is little open, reproducible, RTL-grounded complexity data for a modern high-performance core.
Objectives:
Develop and evaluate technology-aware RISC-V CPU microarchitecture models
Correlate key microarchitectural structures with equivalent RTL implementations
Characterize their power, performance and area scaling across imec’s future semiconductor technologies
Communicate and disseminate research findings through technical presentations, scientific publications, and potential patents.
Candidate Profile:
Pursuing Masters or PhD in Computer Science/Engineering or equivalent.
Knowledge of CPU microarchitecture.
Experience with modelling and simulation tools.
Some experience with RTL.
Experience with EDA synthesis and simulations tools is a plus.
Enthusiasm and curiosity for research and computer architecture
Strong technical motivation and results driven mindset.
The project will be supervised by researchers at imec in the Compute System Architecture department. imec is a world-renowned research center for nano-electronics and digital technologies, based in Leuven, Belgium. The student is expected to work from the imec Leuven, Belgium campus full time for a period of 6-9 months, beginning as soon as possible.
References
[1] M. Brunion et al., "CMOS 2.0 - Redefining the Future of Scaling," 2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD), Munich, Germany, 2025, pp. 1-8, doi: 10.1109/ICCAD66269.2025.11240655.
[2] S. Li, J. H. Ahn, R. D. Strong, J. B. Brockman, D. M. Tullsen and N. P. Jouppi, "McPAT: An integrated power, area, and timing modeling framework for multicore and manycore architectures," 2009 42nd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), New York, NY, USA, 2009, pp. 469-480.
[3] Lakshminarasimhan, Kartik, et al. "The forward slice core microarchitecture." Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques. 2020.
[4] S. Palacharla, N. P. Jouppi, and J. E. Smith, “Complexity-Effective Superscalar Processors,” ISCA 1997.
[5] D. Folegnani and A. González, “Energy-Effective Issue Logic,” ISCA 2001.
[6] I. Park, C. L. Ooi, and T. N. Vijaykumar, “Reducing Design Complexity of the Load/Store Queue,” MICRO 2003.
Type of internship: PhD internship, Master internship
Duration: 6 - 9 months
Required educational background: Electrotechnics/Electrical Engineering, Computer Science
Supervising scientist(s): For further information or for application, please contact Kartik Lakshminarasimhan (Kartik.Lakshminarasimhan@imec.be)
The reference code for this position is 2026-INT-336. Mention this reference code in your application.
Imec allowance will be provided.
Applications should include the following information: