High-Speed Magnetoresistive Random-Access Memory Random Number Generator Using Error-Correcting Code
Tetsufumi Tanamoto, Naoharu Shimomura, Sumio Ikegawa, Mari Matsumoto,, Shinobu Fujita, and Hiroaki Yoda

TL;DR
This paper presents a high-speed MRAM-based random number generator enhanced by an error-correcting code circuit, significantly improving randomness quality with minimal overhead and demonstrating effective coupling with a linear feedback shift resistor.
Contribution
It introduces an ECC post processing circuit for MRAM RNGs that boosts entropy and randomness quality efficiently, with experimental validation.
Findings
ECC post processing improves randomness quality.
Small ECC circuit suffices for effective post processing.
Coupling with a linear feedback shift resistor enhances randomness.
Abstract
A high-speed random number generator (RNG) circuit based on magnetoresistive random-access memory (MRAM) using an error-correcting code (ECC) post processing circuit is presented. ECC post processing increases the quality of randomness by increasing the entropy of random number. { We experimentally show that a small error-correcting capability circuit is sufficient for this post processing. It is shown that the ECC post processing circuit powerfully improves the quality of randomness with minimum overhead, ending up with high-speed random number generation. We also show that coupling with a linear feedback shift resistor is effective for improving randomness
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Data Storage Technologies · Neural Networks and Applications · Advanced Memory and Neural Computing
