pith. sign in

arxiv: 2601.08428 · v1 · submitted 2026-01-13 · 📡 eess.SP · cs.AR

Bio-RV: Low-Power Resource-Efficient RISC-V Processor for Biomedical Applications

Vijay Pratap Sharma , Annu Kumar , Mohd Faisal Khan , Mukul Lokhande , Santosh Kumar Vishvakarma This is my paper

Pith reviewed 2026-05-16 15:10 UTC · model grok-4.3

classification 📡 eess.SP cs.AR
keywords RISC-Vbiomedical processorlow-power designmulti-cycle coreFPGA prototypeimplantable systemsresource efficientASIC implementation
0
0 comments X

The pith

Bio-RV is a multi-cycle RV32I RISC-V core built for ultra-low-power biomedical control with a 708-LUT footprint.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents Bio-RV as a compact RISC-V processor meant for tasks such as accelerator coordination and pacemaker control inside safety-critical biomedical systems. It uses a multi-cycle RV32I design that adds explicit execution control and external instruction loading so firmware can be deployed and tested in a controlled way. The architecture deliberately favors deterministic timing and easy integration with sensing, pacing, and telemetry modules rather than maximum speed. Post-layout results in 180 nm CMOS at 50 MHz indicate the hardware choices produce a small area that supports minimal energy use.

Core claim

Bio-RV is a multi-cycle RV32I core that provides explicit execution control and external instruction loading with capabilities that enable controlled firmware deployment, ASIC bring-up, and post-silicon testing. In addition to coordinating accelerator configuration and data transmission in heterogeneous systems, Bio-RV is designed to function as a lightweight host controller, handling interfaces with pacing, sensing, electrogram (EGM), telemetry, and battery management modules. With 708 LUTs and 235 flip-flops on FPGA prototypes, Bio-RV, implemented in a 180 nm CMOS technology, operate at 50 MHz and feature a compact hardware footprint. According to post-layout results, the proposed architec

What carries the argument

The multi-cycle RV32I core with explicit execution control and external instruction loading, which supplies deterministic timing and flexible host-controller integration for biomedical SoCs.

If this is right

  • Bio-RV can serve as the host controller that configures accelerators and moves data inside heterogeneous biomedical SoCs.
  • External instruction loading supports safe firmware updates and post-silicon verification without on-chip memory changes.
  • The deterministic execution model fits the timing requirements of pacemaker pacing and electrogram sensing loops.
  • Implementation at 50 MHz in 180 nm CMOS keeps the hardware small enough for battery-powered implantable systems.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same lightweight control core could be reused in other ultra-low-power embedded domains such as wireless sensor nodes if power data confirm the savings.
  • Adding formal verification of the explicit execution control would strengthen claims for safety-critical use.
  • The architecture's emphasis on integration flexibility suggests it could become a standard interface block between digital control and analog front-ends in mixed-signal chips.

Load-bearing premise

That the reported LUT and flip-flop counts together with post-layout alignment to minimal energy use are sufficient to guarantee suitability for safety-critical biomedical systems.

What would settle it

A power measurement taken during representative pacing or sensing operations that exceeds the energy budget of an implantable device would disprove the minimal-energy claim.

Figures

Figures reproduced from arXiv: 2601.08428 by Annu Kumar, Mohd Faisal Khan, Mukul Lokhande, Santosh Kumar Vishvakarma, Vijay Pratap Sharma.

Figure 1
Figure 1. Figure 1: Typical TinyML SoC architecture for biomedical iPacE-CHIP applications, highlighting the Bio-RV host processor and interfaced accelerator [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Detailed Data-path for the proposed Bio-RV processor [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Final GDS-II layout of the Bio-RV implemented in 180 nm CMOS [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
read the original abstract

This work presents Bio-RV, a compact and resource-efficient RISC-V processor intended for biomedical control applications, such as accelerator-based biomedical SoCs and implantable pacemaker systems. The proposed Bio-RV is a multi-cycle RV32I core that provides explicit execution control and external instruction loading with capabilities that enable controlled firmware deployment, ASIC bring-up, and post-silicon testing. In addition to coordinating accelerator configuration and data transmission in heterogeneous systems, Bio-RV is designed to function as a lightweight host controller, handling interfaces with pacing, sensing, electrogram (EGM), telemetry, and battery management modules. With 708 LUTs and 235 flip-flops on FPGA prototypes, Bio-RV, implemented in a 180 nm CMOS technology, operate at 50 MHz and feature a compact hardware footprint. According to post-layout results, the proposed architectural decisions align with minimal energy use. Ultimately, Bio-RV prioritises deterministic execution, minimal hardware complexity, and integration flexibility over peak computing speed to meet the demands of ultra-low-power, safety-critical biomedical systems.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The manuscript presents Bio-RV, a multi-cycle RV32I RISC-V core intended as a lightweight host controller for biomedical SoCs and implantable devices such as pacemakers. It reports an FPGA prototype using 708 LUTs and 235 flip-flops, a 50 MHz operating frequency in 180 nm CMOS, explicit execution control, external instruction loading, and the claim that post-layout results align with minimal energy use while prioritizing deterministic execution and integration flexibility over peak performance.

Significance. A verified, compact RV32I core with the reported resource footprint and deterministic features could serve as a practical building block for heterogeneous biomedical systems where area and predictability matter more than throughput. However, the absence of any quantitative power, energy, or comparison data means the central low-power claim cannot yet be assessed for significance.

major comments (2)
  1. [Abstract] Abstract: The statement that 'the proposed architectural decisions align with minimal energy use' is unsupported because no power consumption figures (average/peak power in µW, energy per instruction, leakage/dynamic split), supply voltage, activity factor, or baseline comparisons (e.g., to Ibex or PicoRV32 in 180 nm) are provided anywhere in the manuscript. Resource counts and frequency alone do not establish energy efficiency for a multi-cycle core.
  2. [Results] Implementation and Results sections: The post-layout results are invoked to support the minimal-energy claim, yet the manuscript contains no tables or figures reporting synthesized area, power, or timing numbers, nor any verification methodology (simulation, test vectors, or safety-critical checks) that would allow the reader to evaluate suitability for implantable applications.
minor comments (1)
  1. [Abstract] The abstract contains a subject-verb agreement error ('Bio-RV ... operate at 50 MHz').

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed review. We address each major comment below and agree that the manuscript would benefit from additional quantitative support for the low-power claims.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The statement that 'the proposed architectural decisions align with minimal energy use' is unsupported because no power consumption figures (average/peak power in µW, energy per instruction, leakage/dynamic split), supply voltage, activity factor, or baseline comparisons (e.g., to Ibex or PicoRV32 in 180 nm) are provided anywhere in the manuscript. Resource counts and frequency alone do not establish energy efficiency for a multi-cycle core.

    Authors: We acknowledge that the current manuscript does not include explicit power figures or comparisons, making the abstract statement unsupported by data. The phrasing reflected the intent of the multi-cycle design to reduce dynamic power through lower switching activity and compact resources, but we agree this requires substantiation. In the revised version we will remove the claim from the abstract and add post-layout power estimates (including dynamic/leakage breakdown at the target voltage and frequency) together with brief comparisons to other RV32I cores in 180 nm. revision: yes

  2. Referee: [Results] Implementation and Results sections: The post-layout results are invoked to support the minimal-energy claim, yet the manuscript contains no tables or figures reporting synthesized area, power, or timing numbers, nor any verification methodology (simulation, test vectors, or safety-critical checks) that would allow the reader to evaluate suitability for implantable applications.

    Authors: We agree that the manuscript should present the post-layout numbers and verification details explicitly. Although the design was synthesized and placed-and-routed in 180 nm CMOS, these quantitative results and the test methodology were omitted from the text. The revised manuscript will include a table reporting area, timing, and power metrics from the post-layout flow, plus an expanded description of the verification approach (directed test vectors, functional simulation coverage, and the deterministic execution properties that support predictability in safety-critical contexts). revision: yes

Circularity Check

0 steps flagged

No circularity: descriptive hardware report without derivations or fitted predictions

full rationale

The paper is a direct implementation report of a multi-cycle RV32I RISC-V core for biomedical use. It states resource counts (708 LUTs, 235 flip-flops), clock frequency (50 MHz), and process node (180 nm) from FPGA prototypes and post-layout results, then infers that architectural choices align with minimal energy use. No equations, parameter fitting, predictive models, or derivation chains exist. No self-citations, uniqueness theorems, or ansatzes are invoked to justify claims. The central statements are empirical descriptions of the synthesized design rather than reductions of outputs to inputs by construction. This is a standard non-circular hardware paper.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The design rests on the standard RISC-V RV32I specification and conventional multi-cycle processor implementation techniques; no new entities or fitted parameters are introduced.

axioms (2)
  • standard math The core correctly implements the RV32I instruction set architecture
    Invoked when claiming RV32I compliance and deterministic execution.
  • domain assumption Post-layout simulation in 180 nm CMOS accurately predicts silicon behavior for power and timing
    Used to support the minimal energy use claim.

pith-pipeline@v0.9.0 · 5500 in / 1262 out tokens · 24626 ms · 2026-05-16T15:10:27.113488+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

29 extracted references · 29 canonical work pages

  1. [1]

    Hamsa-di: A low-power dual-issue risc-v core targeting energy-efficient embedded systems,

    Y . Kra, Y . Shoshan, Y . Rudin, and A. Teman, “Hamsa-di: A low-power dual-issue risc-v core targeting energy-efficient embedded systems,” IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 71, no. 1, pp. 223–236, 2024

    work page 2024

  2. [2]

    Flex-pe: Flexible and simd multiprecision processing element for ai workloads,

    M. Lokhande, G. Raut, and S. K. Vishvakarma, “Flex-pe: Flexible and simd multiprecision processing element for ai workloads,”IEEE Transactions on V ery Large Scale Integration (VLSI) Systems, vol. 33, no. 6, pp. 1610–1623, 2025

    work page 2025

  3. [3]

    Design of a cnn accelerator for multitask eeg signal classification based on risc-v,

    W. Shi, H. Qin, J. Wu, and J. Mai, “Design of a cnn accelerator for multitask eeg signal classification based on risc-v,”IEEE Transactions on V ery Large Scale Integration (VLSI) Systems, pp. 1–9, 2025

    work page 2025

  4. [4]

    Low power single cycle risc v processor for biomedical applications,

    P. Ganesh, M. Rajasekaran, T. Arunprasath, K. Ramaraj, G. Vishu- varthanan, and V . Muneeswran, “Low power single cycle risc v processor for biomedical applications,” in2024 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DIS- COVER), pp. 176–180, 2024

    work page 2024

  5. [5]

    Siwa: a risc-v rv32i based micro-controller for implantable medical applications,

    R. Garcia-Ramirez, A. Chacon-Rodriguez, R. Castro-Gonzalez, A. Ar- naud, M. Miguez, J. Gak, R. Molina-Robles, G. Madrigal- Boza, M. Oviedo-Hernandez, E. Solera-Bolanos, D. Salazar-Sibaja, D. Sanchez-Jimenez, M. Fonseca-Rodriguez, J. Arrieta-Solorzano, and R. Rimolo-Donadio, “Siwa: a risc-v rv32i based micro-controller for implantable medical applications,...

    work page 2020

  6. [6]

    An energy consumption benchmark for a low-power risc-v core aimed at implantable medical devices,

    R. Molina-Robles, A. Arnaud, M. Miguez, J. Gak, A. Chac ´on- Rodr´ıguez, and R. Garc´ıa-Ram´ırez, “An energy consumption benchmark for a low-power risc-v core aimed at implantable medical devices,”IEEE Embedded Systems Letters, vol. 15, no. 2, pp. 57–60, 2023

    work page 2023

  7. [7]

    A risc-v 32-bit microprocessor based on two-dimensional semiconductors,

    M. Ao, X. Zhou, X. Kong, S. Gou, S. Chen, X. Dong, Y . Zhu, Q. Sun, Z. Zhang, J. Zhang,et al., “A risc-v 32-bit microprocessor based on two-dimensional semiconductors,”Nature, pp. 1–8, 2025

    work page 2025

  8. [8]

    Bendable non-silicon risc-v microprocessor,

    E. Ozer, J. Kufel, S. Prakash, A. Raisiardali, O. Kindgren, R. Wong, N. Ng, D. Jausseran, F. Alkhalil, D. Kong,et al., “Bendable non-silicon risc-v microprocessor,”Nature, vol. 634, no. 8033, pp. 341–346, 2024

    work page 2024

  9. [9]

    Cheshire: A lightweight, linux-capable risc-v host platform for domain-specific accel- erator plug-in,

    A. Ottaviano, T. Benz, P. Scheffler, and L. Benini, “Cheshire: A lightweight, linux-capable risc-v host platform for domain-specific accel- erator plug-in,”IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 70, no. 10, pp. 3777–3781, 2023

    work page 2023

  10. [10]

    A mixed-precision risc-v processor for extreme-edge dnn inference,

    G. Ottavi, A. Garofalo, G. Tagliavini, F. Conti, L. Benini, and D. Rossi, “A mixed-precision risc-v processor for extreme-edge dnn inference,” in2020 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), pp. 512–517, 2020

    work page 2020

  11. [11]

    A fully integrated 5-mw, 0.8-gbps energy-efficient chip-to- chip data link for ultralow-power iot end-nodes in 65-nm cmos,

    H. Okuhara, A. Elnaqib, M. Dazzi, P. Palestri, S. Benatti, L. Benini, and D. Rossi, “A fully integrated 5-mw, 0.8-gbps energy-efficient chip-to- chip data link for ultralow-power iot end-nodes in 65-nm cmos,”IEEE Transactions on V ery Large Scale Integration (VLSI) Systems, vol. 29, no. 10, pp. 1800–1811, 2021

    work page 2021

  12. [12]

    A heterogeneous risc-v based soc for secure nano-uav navigation,

    L. Valente, A. Nadalini, A. H. C. Veeran, M. Sinigaglia, B. S ´a, N. Wistoff, Y . Tortorella, S. Benatti, R. Psiakis, A. Kulmala, B. Moham- mad, S. Pinto, D. Palossi, L. Benini, and D. Rossi, “A heterogeneous risc-v based soc for secure nano-uav navigation,”IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 71, no. 5, pp. 2266–2279, 2024

    work page 2024

  13. [13]

    Open source heterogeneous socs for artificial intelligence: The pulp platform experience,

    F. Conti, A. Garofalo, D. Rossi, G. Tagliavini, and L. Benini, “Open source heterogeneous socs for artificial intelligence: The pulp platform experience,”IEEE Solid-State Circuits Magazine, vol. 17, no. 2, pp. 49– 60, 2025

    work page 2025

  14. [14]

    Bit-serial risc-v cpu core,

    A. Chopde, V . Shingde, T. Bhagwat, and S. Yadav, “Bit-serial risc-v cpu core,” in2024 IEEE Pune Section International Conference (PuneCon), pp. 1–5, 2024

    work page 2024

  15. [15]

    Scalable and risc-v programmable near-memory com- puting architectures for edge nodes,

    M. Caon, C. Chon ´e, P. D. Schiavone, A. Levisse, G. Masera, M. Martina, and D. Atienza, “Scalable and risc-v programmable near-memory com- puting architectures for edge nodes,”IEEE Transactions on Emerging Topics in Computing, pp. 1–15, 2025

    work page 2025

  16. [16]

    Siwa: A custom risc-v based system on chip (soc) for low power medical applications,

    R. Garcia-Ramirez, A. Chacon-Rodriguez, R. Molina-Robles, R. Castro- Gonzalez, E. Solera-Bolanos, G. Madrigal-Boza, M. Oviedo-Hernandez, D. Salazar-Sibaja, D. Sanchez-Jimenez, M. Fonseca-Rodriguez,et al., “Siwa: A custom risc-v based system on chip (soc) for low power medical applications,”Microelectronics journal, vol. 98, p. 104753, 2020

    work page 2020

  17. [17]

    A low-power low-area soc based in risc-v processor for iot applications,

    R. Serrano, M. Sarmiento, C. Duran, K.-D. Nguyen, T.-T. Hoang, K. Ishibashi, and C.-K. Pham, “A low-power low-area soc based in risc-v processor for iot applications,” in2021 18th International SoC Design Conference (ISOCC), pp. 375–376, 2021

    work page 2021

  18. [18]

    The berkeley out-of-order machine (boom): An industry-competitive, synthesizable, parameterized risc-v processor,

    C. Celio, D. A. Patterson, and K. Asanovi ´c, “The berkeley out-of-order machine (boom): An industry-competitive, synthesizable, parameterized risc-v processor,” Jun 2015

    work page 2015

  19. [19]

    The rocket chip generator,

    K. Asanovi ´c, R. Avizienis, J. Bachrach, S. Beamer, D. Biancolin, C. Celio, H. Cook, D. Dabbelt, J. Hauser, A. Izraelevitz, S. Karandikar, B. Keller, D. Kim, J. Koenig, Y . Lee, E. Love, M. Maas, A. Magyar, H. Mao, M. Moreto, A. Ou, D. A. Patterson, B. Richards, C. Schmidt, S. Twigg, H. V o, and A. Waterman, “The rocket chip generator,” Apr 2016

    work page 2016

  20. [20]

    A system- on-chip platform for the internet of things featuring a 32-bit risc-v based microcontroller,

    C. Duran, A. Amaya, R. Torres, J. Ardila, L. Rueda, G. Castillo, A. Agudelo, C. Rojas, L. Chaparro, H. Hurtado,et al., “A system- on-chip platform for the internet of things featuring a 32-bit risc-v based microcontroller,” in2017 IEEE 8th Latin American Symposium on Circuits & Systems (LASCAS), pp. 1–4, IEEE, 2017

    work page 2017

  21. [21]

    Slow and steady wins the race? a comparison of ultra- low-power risc-v cores for internet-of-things applications,

    P. D. Schiavone, F. Conti, D. Rossi, M. Gautschi, A. Pullini, E. Flamand, and L. Benini, “Slow and steady wins the race? a comparison of ultra- low-power risc-v cores for internet-of-things applications,” in2017 27th International Symposium on Power and Timing Modeling, Optimization and Simulation (PATMOS), pp. 1–8, IEEE, 2017

    work page 2017

  22. [22]

    Shakti: An open-source processor ecosystem,

    N. Gala, G. S. Madhusudan, P. George, A. Sahoo, A. Menon, and V . Kamakoti, “Shakti: An open-source processor ecosystem,”ACM Transactions on Applied Perception, vol. V , no. N, pp. 1–16, 2018

    work page 2018

  23. [23]

    A 32-bit risc- v axi4-lite bus-based microcontroller with 10-bit sar adc,

    C. Duran, D. L. Rueda, G. Castillo, A. Agudelo, C. Rojas, L. Chaparro, H. Hurtado, J. Romero, W. Ramirez, H. Gomez,et al., “A 32-bit risc- v axi4-lite bus-based microcontroller with 10-bit sar adc,” in2016 IEEE 7th Latin American Symposium on Circuits & Systems (LASCAS), pp. 315–318, IEEE, 2016

    work page 2016

  24. [24]

    Leveraging risc-v for hw/sw co-design of flexible and efficient tinyml socs,

    A. Garofalo and L. Benini, “Leveraging risc-v for hw/sw co-design of flexible and efficient tinyml socs,”IEEE Design & Test, pp. 1–1, 2025

    work page 2025

  25. [25]

    Optimization and deployment of deep neural networks for ppg-based blood pressure estimation targeting low- power wearables,

    A. Burrello, F. Carlucci, G. Pollo, X. Wang, M. Poncino, E. Macii, L. Benini, and D. J. Pagliari, “Optimization and deployment of deep neural networks for ppg-based blood pressure estimation targeting low- power wearables,” in2024 IEEE Biomedical Circuits and Systems Conference (BioCAS), pp. 1–5, 2024

    work page 2024

  26. [26]

    Gapses: Versatile smart glasses for comfortable and fully-dry acquisition and parallel ultra-low-power processing of eeg and eog,

    S. Frey, M. A. Lucchini, V . Kartsch, T. M. Ingolfsson, A. H. Bernardi, M. Segessenmann, J. Osieleniec, S. Benatti, L. Benini, and A. Cos- settini, “Gapses: Versatile smart glasses for comfortable and fully-dry acquisition and parallel ultra-low-power processing of eeg and eog,” IEEE Transactions on Biomedical Circuits and Systems, vol. 19, no. 3, pp. 616...

    work page 2025

  27. [27]

    An energy-efficient asic for wireless body sensor networks in medical applications,

    X. Zhang, H. Jiang, L. Zhang, C. Zhang, Z. Wang, and X. Chen, “An energy-efficient asic for wireless body sensor networks in medical applications,”IEEE transactions on biomedical circuits and systems, vol. 4, no. 1, pp. 11–18, 2009

    work page 2009

  28. [28]

    A batteryless sensor asic for implantable bio-impedance applications,

    S. Rodriguez, S. Ollmar, M. Waqar, and A. Rusu, “A batteryless sensor asic for implantable bio-impedance applications,”IEEE transactions on biomedical circuits and systems, vol. 10, no. 3, pp. 533–544, 2015

    work page 2015

  29. [29]

    Wimagine: wireless 64-channel ecog recording implant for long term clinical applications,

    C. S. Mestais, G. Charvet, F. Sauter-Starace, M. Foerster, D. Ratel, and A. L. Benabid, “Wimagine: wireless 64-channel ecog recording implant for long term clinical applications,”IEEE transactions on neural systems and rehabilitation engineering, vol. 23, no. 1, pp. 10–21, 2014

    work page 2014