EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FPGA validated RISC V system on chip with a custom systolic array accelerator for edge AI inference

Srujan Sateesh Kalagi, K. R. Vinay Kumar, Shashank Dharamshetty, N. Ramavenkateswaran, V. Kiran

Discover Artificial Intelligence · 24.08.2026 · 6 (1)

DOI: 10.1007/s44163-026-02003-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Discover Artificial Intelligence, online erschienen am 24.08.2026. Verfasst von Srujan Sateesh Kalagi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: RV College Of Engineering.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Running deep-learning inference on constrained edge hardware calls for architectures that cut both latency and memory traffic at once—not one at the expense of the other. This paper describes a complete FPGA-validated RISC-V SoC in which a five-stage RV32IM processor works alongside a custom $$4{\times }4$$ output-stationary systolic MAC array. An AXI4 crossbar ties the two parts together, and a scatter–gather DMA engine moves operand tiles and results so the processor stays free for control work during inference. Rather than adding custom opcodes, the accelerator is exposed through memory-mapped registers, which means existing RISC-V toolchains need no modification at all. The target device is the Xilinx Artix-7 XC7A35T on a Digilent Basys 3 board. Both Vivado XSim simulation and on-board runs confirm that a $$4{\times }4$$ matrix multiply finishes in 320 ns at 100 MHz, giving a compute-phase throughput of 1.16 GOPS. The systolic compute phase completes in $$3N{-}1 = 11$$ cycles (110 ns); the full end-to-end tile latency including AXI handshaking is 320 ns. After place-and-route the design uses 39.5% LUTs (8214 of 20,800), 17.8% DSP48E1 slices (16 of 90), and 16.0% BRAM (8 of 50) on the XC7A35T, with a total on-chip power of 148 mW and a compute-phase efficiency of 7.86 GOPS/W. The processing elements natively operate on INT8 quantised inputs sign-extended to 18 bits to match the DSP48E1’s narrower multiplier port, with 64-bit accumulators preventing overflow across a full tile. Two propositions are formally proved: the first establishes that the output-stationary schedule reduces computation cycles by $$\Theta (N^{2}/3)$$ relative to a naïve, unblocked sequential CPU execution, and the second shows a factor- N reduction in weight-memory reads under the same naïve baseline assumption. The design is validated for functional correctness on physical silicon; power, DMA-overlap, and sustained-throughput figures are estimates derived from Vivado post-implementation analysis and the analytical performance model rather than direct on-board measurement. Among open RISC-V accelerator designs the proposed SoC stands out by combining plain Verilog source, operation on the lower-cost Artix-7 without any embedded ARM host, memory-mapped control that keeps the compiler unmodified, DMA-driven transfers, and a closed-form performance model that matches the measured numbers.

Förderung

  • RV College Of Engineering

Zitieren

APA

Kalagi, S. S., Kumar, K. R. V., Dharamshetty, S., Ramavenkateswaran, N., & Kiran, V. (2026). FPGA validated RISC V system on chip with a custom systolic array accelerator for edge AI inference. Discover Artificial Intelligence, 6(1). https://doi.org/10.1007/s44163-026-02003-7

Vancouver

Kalagi SS, Kumar KRV, Dharamshetty S, Ramavenkateswaran N, Kiran V. FPGA validated RISC V system on chip with a custom systolic array accelerator for edge AI inference. Discover Artificial Intelligence. 2026;6(1). doi:10.1007/s44163-026-02003-7

BibTeX
@article{Kalagi2026,
  author = {Kalagi, Srujan Sateesh and Kumar, K. R. Vinay and Dharamshetty, Shashank and Ramavenkateswaran, N. and Kiran, V.},
  title = {FPGA validated RISC V system on chip with a custom systolic array accelerator for edge AI inference},
  journal = {Discover Artificial Intelligence},
  year = {2026},
  volume = {6},
  number = {1},
  doi = {10.1007/s44163-026-02003-7}
}
Kostenlos starten →