DesignCon is part of the Informa Markets Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Welcome to the DesignCon 2020 agenda and presentation download site. Here you can view and download conference and/or Chiphead Theater presentations before, during, and after the event. If you’re looking for a presentation from a specific session that you’re unable to find here, it is likely because the presenter has not provided permission for external use or has not yet shared their presentation with us. Please check back after the event for a more complete catalogue of available presentations.

Automatic Channel Condition Detection & Tuning Using Machine Learning Surrogate Models for 56G PAM4 Channels

Chris Cheng  (Distinguished Technologist, HP Enterprise)

Yongjin Choi  (Master Technologist, HP Enterprise)

Yasin Damgaci  (EXPERT ENGINEER, HP Enterprise)

Matt Reagor  (Director of Engineering, Rigetti Computing)

Location: Ballroom G

Date: Wednesday, January 29

Time: 2:00pm - 2:40pm

Track: 14. Machine Learning for Microelectronics, Signaling & System Design, 07. Optimizing High-Speed Serial Design

Format: Technical Session

Pass Type: 2-Day Pass, All-Access Pass, Alumni All-Access Pass - Get your pass now!

Vault Recording: TBD

Audience Level: All

Follow up on our previous paper on accelerating channel optimization using principal component analysis. We create families of surrogate models in the reduced dimension PCA space based on various channel conditions. When a new system topology is encountered, random points within the PCA space is sampled. The resulting performance is compared against the families of surrogate models and the closest solution is considered the nearest channel condition model. The optimal operating can then be easily set based on precomputed optimal setting for that surrogate model. Alternatively, the precompute settings can be used as seed values for circuit level auto tuning.


Automatic channel identification
Automatic channel tuning
Principal component analysis vector space
Polynomial chaotic expansion surrogate models

Intended Audience

Principal component analysis, Surrogate model , PAM-4 SerDes, channel optimization