Frank Callaly
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Frank Callaly has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Abishek Bupathi
University of Galway, Galway, Ireland
1 shared publication - Adnan Elahi
Translational Medical Device Laboratory, University of Galway, Galway, Ireland
1 shared publication Alex Cucos
1 shared publication- Declan O'Loughlin
Electronic and Electrical Engineering, Trinity College Dublin, D02 PN40 Dublin, Ireland
1 shared publication - Fearghal Morgan
University of Galway, Galway, Ireland
1 shared publication - John Byrne
University of Galway, Galway, Ireland
1 shared publication
Latest Publications
- Open Access
- 21 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
HDLGen-ChatGPT Case Study: RISC-V Processor VHDL and Verilog Model - Testbench and EDA Project Generation
This paper presents the open source HDLGen-ChatGPT application, working in tandem with ChatGPT-3.5, the free online large language model (LLM) chat interface. The tools enable fast digital systems design and test specification capture, and automatic generation of both VHDL and Verilog models, and testbenches, and AMD Vivado and Intel Quartus Electronic Design Automation (EDA) projects. EDA tools check the generated HDL syntax, simulate and synthesise HDL models, and follow the steps to FPGA hardware prototyping. The tools exploit a formal, top-down design and test specification documentation process, domain knowledge, and the flexibility of LLMs, for HDL code generation. Results are included for a hierarchical RV32I RISC-V processor design. Process steps are illustrated for the RISC-V 32 × 32-bit register bank component. The process typically requires only minimal manual HDL capture or editing, and often none at all. URLs to tutorial videos for the complete RISC-V design are provided on the GitHub project repository. The paper evaluates the results and provides HDLGen-ChatGPT and ChatGPT usage recommendations. The tools can be applied in digital systems training programmes, with reduced emphasis on the assessment of HDL model and testbench capture and generation, while maintaining strong emphasis on the assessment of system design, test planning and documentation, HDL simulation verification/debug, and analysis of synthesised netlists.
- 21 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessHDLGen-ChatGPT Case Study: RISC-V Processor VHDL and Verilog Model - Testbench and EDA Project Generation
This paper presents the open source HDLGen-ChatGPT application, working in tandem with ChatGPT-3.5, the free online large language model (LLM) chat interface. The tools enable fast digital systems design and test specification capture, and automatic generation of both VHDL and Verilog models, and testbenches, and AMD Vivado and Intel Quartus Electronic Design Automation (EDA) projects. EDA tools check the generated HDL syntax, simulate and synthesise HDL models, and follow the steps to FPGA hardware prototyping. The tools exploit a formal, top-down design and test specification documentation process, domain knowledge, and the flexibility of LLMs, for HDL code generation. Results are included for a hierarchical RV32I RISC-V processor design. Process steps are illustrated for the RISC-V 32 × 32-bit register bank component. The process typically requires only minimal manual HDL capture or editing, and often none at all. URLs to tutorial videos for the complete RISC-V design are provided on the GitHub project repository. The paper evaluates the results and provides HDLGen-ChatGPT and ChatGPT usage recommendations. The tools can be applied in digital systems training programmes, with reduced emphasis on the assessment of HDL model and testbench capture and generation, while maintaining strong emphasis on the assessment of system design, test planning and documentation, HDL simulation verification/debug, and analysis of synthesised netlists.
- Open Access
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21583994,p. 1-2
Biometric Access Control for Digital Media Streams in Home Networks
Methods for controlling access to digital media content in the home environment using biometric sensing techniques are described. A wireless rebroadcast system for IP-TV content was retrofitted with a combination of fingerprint authentication and face recognition modules. Family members are enrolled and new individuals may be added to the system by a master user. Access to content requires fingerprint based authentication from a wireless PDA and the system also checks dynamically if it can recognize enrolled uses amongst those "sitting on the couch".
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21583994,p. 1-2
Open AccessBiometric Access Control for Digital Media Streams in Home Networks
Methods for controlling access to digital media content in the home environment using biometric sensing techniques are described. A wireless rebroadcast system for IP-TV content was retrofitted with a combination of fingerprint authentication and face recognition modules. Family members are enrolled and new individuals may be added to the system by a master user. Access to content requires fingerprint based authentication from a wireless PDA and the system also checks dynamically if it can recognize enrolled uses amongst those "sitting on the couch".