An RV32IM Processor with a Fuzzy Logic Branch Prediction Unit and Selective Execution

Sonia Munezero; Nicasio Maguu Muchuka; Peter Kamita Kihato

doi:10.48084/etasr.16946

Authors

Sonia Munezero Department of Electrical & Electronics Engineering, Pan African University Institute for Basic Sciences, Technology, and Innovation (PAUSTI), Juja, Kenya
Nicasio Maguu Muchuka Department of Electrical & Control Engineering, Egerton University, Nakuru, Kenya
Peter Kamita Kihato Department of Electrical and Electronics Engineering, Jomo Kenyatta University of Agriculture and Technology (JKUAT), Juja, Kenya

Volume: 16 | Issue: 2 | Pages: 33016-33023 | April 2026 | https://doi.org/10.48084/etasr.16946

Received: 14 December 2025 | Revised: 8 January 2026 | Accepted: 17 January 2026 | Online: 4 April 2026

Corresponding author: Sonia Munezero

Abstract

The Reduced Instruction Set Computer V (RISC-V) 32-bit architecture with an Integer base instruction set and Multiplication and Division extension (RV32IM) is widely adopted in embedded systems; however, pipeline control hazards limit its performance. Conventional branch prediction techniques exhibit limited accuracy under complex, irregular control-flow patterns. This work proposes the integration of the Fuzzy Logic Branch Prediction Unit (FLBPU) into a five-stage RV32IM pipeline. The FLBPU uses an adaptive fuzzy inference system, considering instruction type and global branch history, to calculate prediction confidence dynamically. This confidence metric controls speculative execution via a Selective Execution Technique (SET). The design also incorporates a hazard control unit and enhanced dependency analysis. On a Xilinx Zynq UltraScale+ Field-Programmable Gate Array (FPGA) at 100 MHz, the design was tested with 83 instructions executed over 135 cycles, achieving an Instructions Per Cycle (IPC) of 0.615. The FLBPU processed 32 branch instructions, predicting all 32 branches with 26 correct predictions and 6 mispredictions, yielding an 18.75% misprediction rate and 81.25% branch prediction accuracy. Accuracy progression was observed as follows: branches one to four had 0% accuracy during the initial learning phase; branches five to fifteen showed gradual improvement from 0% to 60% accuracy; branch 24 reached 75% accuracy; and branch 32 achieved 81.25% accuracy. Post-synthesis hardware utilization was 3,385 Lookup Tables (LUTs), 5,387 Flip-Flops (FFs), and 5 Digital Signal Processing (DSP) blocks, with an on-chip power consumption of 0.309 W.

Keywords:

RISC-V, branch prediction, fuzzy logic, adaptive systems, FPGA implementation, pipeline hazards, embedded processors, computer architecture

Downloads

Download data is not yet available.

References

E. Cui, T. Li, and Q. Wei, "RISC-V Instruction Set Architecture Extensions: A Survey," IEEE Access, vol. 11, pp. 24696–24711, 2023. DOI: https://doi.org/10.1109/ACCESS.2023.3246491

W. Yang, J. Gao, Q. Li, and J. Zhang, "Design of RISC-V out-of-order processor based on segmented exclusive or Gshare branch prediction," Microelectronics Journal, vol. 152, Oct. 2024, Art. no. 106334. DOI: https://doi.org/10.1016/j.mejo.2024.106334

D. Li, S. Zhao, X. Zhang, X. Fan, J. Zhou, and Z. Wang, "Design of a Hybrid Branch Prediction Architecture for Risc-V Processors," in 2025 IEEE 14th International Conference on Communications, Circuits and Systems, Wuhan, China, 2025, pp. 160–164. DOI: https://doi.org/10.1109/ICCCAS65806.2025.11102589

L. Li, L. Xing, X. Peng, and Y. Duan, "Research and Design of a Dynamic Branch Predictor Based on the RISC-V Instruction Set," in 2025 4th International Symposium on Semiconductor and Electronic Technology, Xi'an, China, 2025, pp. 324–328. DOI: https://doi.org/10.1109/ISSET66828.2025.11184914

A. Aoun, M. Masadeh, and S. Tahar, "ML-based Load Value Approximator for Efficient Multimedia Processing," ACM Transactions on Multimedia Computing, Communications and Applications, vol. 21, no. 7, July 2025, Art. no. 210. DOI: https://doi.org/10.1145/3736582

Z. Jin, H. Di, T. Hu, and P. Wang, "Real-Time Optimization of RISC-V Processors Based on Branch Prediction and Division Data Dependency," Applied Sciences, vol. 15, no. 2, Jan. 2025, Art. no. 632. DOI: https://doi.org/10.3390/app15020632

A. Saveau, "Branch Prediction in Hardcaml for a RISC-V 32im CPU." arXiv, Jan. 04, 2024.

T. M. Ignatius, S. Bora, and R. P. Palathinkal, "Impact of Pipelining on Low Power IoT applicable RISC-V ISA Core Micro-architectures," in 2024 IEEE 17th International Symposium on Embedded Multicore/Many-core Systems-on-Chip, Kuala Lumpur, Malaysia, 2024, pp. 223–230. DOI: https://doi.org/10.1109/MCSoC64144.2024.00045

S. Ahmed and A. B. M. Harun-Ur-Rashid, "Design, Implementation and Verification of Five Stage Pipeline RISC-V Core (RV32I ISA)," in 2025 International Conference on Electrical, Computer and Communication Engineering, Chittagong, Bangladesh, 2025, pp. 1–6. DOI: https://doi.org/10.1109/ECCE64574.2025.11013913

Q. Zhai et al., "Instruction Level Parallelism Optimizations in a High-Performance Dual-Issue RISC-V Processor for Real-Time Control Systems," in 2025 IEEE International Symposium on Circuits and Systems, London, United Kingdom, 2025, pp. 1–5. DOI: https://doi.org/10.1109/ISCAS56072.2025.11043760

M. Rogenmoser et al., "SentryCore: A RISC-V Co-Processor System for Safe, Real-Time Control Applications." arXiv, May 16, 2024.

R. Tedeschi et al., "CVA6S+: A Superscalar RISC-V Core with High-Throughput Memory Architecture." arXiv, May 08, 2025.

M.-H. Yen, Y.-H. Lin, T.-F. Lin, Y.-H. Chen, Y.-F. Ku, and C.-T. Kao, "Chip Design of Multithreaded and Pipelined RISC-V Microcontroller Unit," Engineering Proceedings, vol. 89, no. 1, Feb. 2025, Art. no. 31. DOI: https://doi.org/10.3390/engproc2025089031

Y. Xiang et al., "A Lightweight RISC-V Multi-Core Interaction Framework For Embedded Real-Time Applications," in 2025 IEEE International Symposium on Circuits and Systems, London, United Kingdom, 2025, pp. 1–5. DOI: https://doi.org/10.1109/ISCAS56072.2025.11044187

R. Olowoniyi, S. Du, R. Baartmans, V. Agostinelli, and L. Chen, "RTL Microarchitecture Optimizations for Reducing Pipeline Hazards in Small RISC Cores." ResearchGate, May 01, 2025, [Online]. Available: https://www.researchgate.net/publication/395173023_RTL_Microarchitecture_Optimizations_for_Reducing_Pipeline_Hazards_in_Small_RISC_Cores.

M. Z. Naveed, M. Amar, A. Hussain, and Z. A. Awan, "Design & Implementation of 5-Stage 32-bit RISC-V Pipeline Processor on FPGA," in 9th Multidisciplinary Student Research & Innovation Conference, Wah Cantt, Pakistan, 2024.

A. Singh, A. Kumar, A. Singh, R. A. Reddy, and K. N. Pushpalatha, "Design and Implementation of RISC-V ISA (RV32IM) on FPGA," International Journal of VLSI & Signal Processing, vol. 10, no. 2, pp. 17–21, July 2023. DOI: https://doi.org/10.14445/23942584/IJVSP-V10I2P103

A. Tiwari, P. Guha, G. Trivedi, N. Gupta, N. Jayaraj, and J. Pidanic, "IndiRA: Design and Implementation of a Pipelined RISC-V Processor," in 2023 33rd International Conference Radioelektronika, Pardubice, Czech Republic, 2023, pp. 1–6. DOI: https://doi.org/10.1109/RADIOELEKTRONIKA57919.2023.10109058

M. Baloch, A. A. Jumani, A. A. Memon, A. M. Shaikh, and Z. A. Memon, "The FPGA-Based Design of an Optimal Fuzzy Logic Controller for Hybrid Renewable Energy Systems," Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 28420–28426, Dec. 2025. DOI: https://doi.org/10.48084/etasr.12538

M. Y. Allani, D. Mezghani, F. Tadeo, and A. Mami, "FPGA Implementation of a Robust MPPT of a Photovoltaic System Using a Fuzzy Logic Controller Based on Incremental and Conductance Algorithm," Engineering, Technology & Applied Science Research, vol. 9, no. 4, pp. 4322–4328, Aug. 2019. DOI: https://doi.org/10.48084/etasr.2771

A. Batashev, "Dissecting RISC-V Performance: Practical PMU Profiling and Hardware-Agnostic Roofline Analysis on Emerging Platforms," in 17th International Conference on Parallel Computing Technologies, Almaty, Kazakhstan, 2025, pp. 153–168. DOI: https://doi.org/10.1007/978-3-032-06751-7_11