Glamočanin, Ognjen
Shrivastava, Shashwat
Yao, Jinwei
Ardo, Nour
Payer, Mathias
Stojilović, Mirjana
Funding for this research was provided by:
Swiss National Science Foundation (182428, 182428)
EPFL Lausanne
Article History
Received: 14 January 2023
Accepted: 26 July 2023
First Online: 4 October 2023
Statements and Declarations
:
: Open access funding provided by EPFL Lausanne. This work is partially supported by the Swiss National Science Foundation (grant No. 182428).
: The authors have no competing interests as defined by Springer, or other interests that might be perceived to influence the results and/or discussion reported in this paper.
: Each named author has substantially contributed to conducting the underlying research and drafting this manuscript. Ognjen Glamočanin, Mathias Payer, and Mirjana Stojilović wrote the manuscript. Mirjana Stojilović created Figs. 1–6. Shashwat Shrivastava created Figs. 10–12 and worked on the ML aspects of the project. Jinwei Yao worked on instruction template generation and ML code. Nour Ardo worked on the initial FPGA infrastructure. Ognjen Glamočanin implemented the final FPGA infrastructure and the ML code, recorded the traces, ran the ML profiling, and created the remaining figures. All authors reviewed the final version of the manuscript.
: We make the FPGA designs, associated software, and ML code openly available for the reproducibility of the experiments and the results in this work [CitationRef removed].
: This research does not involve human and/or animal studies.4