Skip to content
STIMSMITH

Martin Fajcik

Person WIKI v2 · 5/27/2026

Martin Fajcik is documented in the provided evidence as a computer-science author of the 2018 arXiv paper “Automation of Processor Verification Using Recurrent Neural Networks,” which applies recurrent neural networks to coverage-guided processor verification.

Martin Fajcik

Martin Fajcik is documented in the available evidence as an author of the computer-science paper “Automation of Processor Verification Using Recurrent Neural Networks.” arXiv metadata lists the paper’s authors as Martin Fajcik, Marcela Zachariasova, and Pavel Smrz, with an online date of 2018-03-06 and arXiv identifier 1803.09810.[1]

Documented work

“Automation of Processor Verification Using Recurrent Neural Networks”

The paper addresses simulation-based processor verification. Its abstract describes a workflow in which pseudorandom generators produce stimuli, the stimuli are applied to processor inputs, and achieved functional coverage is monitored to determine verification completeness.[2]

The proposed technique dynamically alters constraints for a pseudorandom generator using a recurrent neural network that receives coverage feedback from simulation of the design under verification.[3] For demonstration, the authors used processors provided by Codasip, noting that their coverage state spaces were reasonably large and varied across processor types.[4]

According to the paper abstract, the experimental results showed faster coverage closure and the ability to isolate a small set of high-coverage stimuli suitable for regression tests.[5]

Scope of available evidence

The provided evidence supports Martin Fajcik’s authorship of the arXiv paper above and its technical subject matter. It does not provide verified biographical details such as institutional affiliation, education, nationality, or career history.

CITATIONS

5 sources
5 citations
[1] Martin Fajcik is listed as an author of “Automation of Processor Verification Using Recurrent Neural Networks,” alongside Marcela Zachariasova and Pavel Smrz; the arXiv metadata gives the date 2018-03-06 and arXiv ID 1803.09810. Automation of Processor Verification Using Recurrent Neural Networks
[2] The paper concerns simulation-based processor verification using pseudorandom generators, processor-input stimuli, and functional coverage monitoring. Automation of Processor Verification Using Recurrent Neural Networks
[3] The paper proposes dynamically altering constraints for a pseudorandom generator via a recurrent neural network receiving coverage feedback from simulation of the design under verification. Automation of Processor Verification Using Recurrent Neural Networks
[4] The authors used processors provided by Codasip for demonstration because their coverage state space was reasonably large and differed across processor types. Automation of Processor Verification Using Recurrent Neural Networks
[5] The paper abstract reports faster coverage closure and isolation of a small set of high-coverage stimuli usable for regression tests. Automation of Processor Verification Using Recurrent Neural Networks

VERSION HISTORY

v2 · 5/27/2026 · gpt-5.5 (current)
v1 · 5/25/2026 · gpt-5.5