Comparative Analysis of HLS- and RTL-Based SHA-256 Accelerators on a Zynq FPGA: Performance, Power, and Resource Utilization
International Journal of Advances in Engineering and Pure Sciences · 30.06.2026 · 38 (2) · 272-280
DOI: 10.7240/jeps.1864699 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advances in Engineering and Pure Sciences, online erschienen am 30.06.2026. Verfasst von Sezen Bal. Die Arbeit nennt 21 Literaturangaben.
Abstract (Originalsprache)
The Secure Hash Algorithm (SHA)-256 is a widely used cryptographic hash function in modern information security systems. This study presents the design and comparative analysis of a SHA-256 hardware accelerator implemented on a Field Programmable Gate Array (FPGA) using two hardware development methodologies: a Register Transfer Level (RTL)-based Hardware Description Language (HDL, Verilog) approach and a High-Level Synthesis (HLS) approach. In the HLS-based methodology, the SHA-256 core was developed in the C programming language and synthesized into an Advanced eXtensible Interface (AXI)-compliant Intellectual Property (IP) core using an HLS tool, followed by system integration in the Vivado design environment. In contrast, the RTL-based approach involved designing an equivalent SHA-256 IP core fully described at the RTL level using Verilog and integrating it into the same system architecture. Verification of the HLS-based design was performed using C-level simulations and C/RTL co-simulations, while the RTL-based design was functionally verified using a dedicated testbench in the Vivado environment. Both hardware accelerators were integrated with a processor system using the Vivado Block Design tool and implemented on the Python Productivity for Zynq (PYNQ)-Z1 FPGA platform operating at a target clock frequency of 100 MHz. Post-implementation results indicate that the HLS-based design consumed more hardware resources, whereas the RTL-based design achieved a more resource-efficient implementation. Both designs met timing constraints and provided approximately a 16× performance improvement compared to a software-based SHA-256 implementation. Overall, the results highlight the trade-off between development efficiency and hardware optimization offered by HLS and RTL approaches, respectively.
Zitieren
APA
Bal, S. (2026). Comparative Analysis of HLS- and RTL-Based SHA-256 Accelerators on a Zynq FPGA: Performance, Power, and Resource Utilization. International Journal of Advances in Engineering and Pure Sciences, 38(2), 272-280. https://doi.org/10.7240/jeps.1864699
Vancouver
Bal S. Comparative Analysis of HLS- and RTL-Based SHA-256 Accelerators on a Zynq FPGA: Performance, Power, and Resource Utilization. International Journal of Advances in Engineering and Pure Sciences. 2026;38(2):272-280. doi:10.7240/jeps.1864699
BibTeX
@article{Bal2026,
author = {Bal, Sezen},
title = {Comparative Analysis of HLS- and RTL-Based SHA-256 Accelerators on a Zynq FPGA: Performance, Power, and Resource Utilization},
journal = {International Journal of Advances in Engineering and Pure Sciences},
year = {2026},
volume = {38},
number = {2},
pages = {272--280},
doi = {10.7240/jeps.1864699}
}
EUVIMED