Show simple item record

dc.contributor.authorRayas-Sánchez, José E.
dc.contributor.authorRangel-Patiño, Francisco E.
dc.contributor.authorMercado-Casillas, Benjamin
dc.contributor.authorLeal-Romo, Felipe
dc.contributor.authorChávez-Hurtado, José L.
dc.date.accessioned2020-05-18T23:53:13Z
dc.date.available2020-05-18T23:53:13Z
dc.date.issued2020-02-26
dc.identifier.citationJ. E. Rayas-Sánchez, F. E. Rangel-Patiño, B. Mercado-Casillas, F. Leal-Romo, and J. L. Chávez-Hurtado, Machine learning techniques and space mapping approaches to enhance signal and power integrity in high-speed links and power delivery networks. IEEE Latin American Symp. Circuits and Systems Dig. (LASCAS 2020), San Jose, Costa Rica, Feb. 2020, pp.1-4. http://dx.doi.org/10.1109/LASCAS45839.2020.9068994es_MX
dc.identifier.isbn978-1-7281-3428-4
dc.identifier.issn2330-9954
dc.identifier.urihttps://hdl.handle.net/11117/6222
dc.descriptionEnhancing signal integrity (SI) and reliability in modern computer platforms heavily depends on the post-silicon validation of high-speed input/output (HSIO) links, which implies a physical layer (PHY) tuning process where equalization techniques are employed. On the other hand, the interaction between SI and power delivery networks (PDN) is becoming crucial in the computer industry, imposing the need of computationally expensive models to also ensure power integrity (PI). In this paper, surrogate-based optimization (SBO) methods, including space mapping (SM), are applied to efficiently tune equalizers in HSIO links using lab measurements on industrial post-silicon validation platforms, speeding up the PHY tuning process while enhancing eye diagram margins. Two HSIO interfaces illustrate the proposed SBO/SM techniques: USB3 Gen 1 and SATA Gen 3. Additionally, a methodology based on parameter extraction is described to develop fast PDN lumped models for low-cost SI-PI co-simulation; a dual data rate (DDR) memory sub-system illustrates this methodology. Finally, we describe a surrogate modeling methodology for efficient PDN optimization, comparing several machine learning techniques; a PDN voltage regulator with dual power rail remote sensing illustrates this last methodology.es_MX
dc.description.sponsorshipITESO, A.C.es_MX
dc.language.isoenges_MX
dc.publisherIEEEes_MX
dc.rights.urihttp://quijote.biblio.iteso.mx/licencias/CC-BY-NC-ND-2.5-MX.pdfes_MX
dc.subjectBroydenes_MX
dc.subjectDDRes_MX
dc.subjectDoEes_MX
dc.subjectEqualizationes_MX
dc.subjectEthernetes_MX
dc.subjectEye Diagrames_MX
dc.subjectHSIOes_MX
dc.subjectImpedance Profilees_MX
dc.subjectKriginges_MX
dc.subjectParameter Extractiones_MX
dc.subjectPCIees_MX
dc.subjectPDNes_MX
dc.subjectPHYes_MX
dc.subjectPost-silicon Validationes_MX
dc.subjectPower Integrityes_MX
dc.subjectSATAes_MX
dc.subjectSignal Integrityes_MX
dc.subjectSI-PI co-simulationes_MX
dc.subjectSpace Mappinges_MX
dc.subjectSurrogatees_MX
dc.subjectSystem Margininges_MX
dc.subjectUSBes_MX
dc.subjectVoltage Regulatores_MX
dc.titleMachine learning techniques and space mapping approaches to enhance signal and power integrity in high-speed links and power delivery networkses_MX
dc.typeinfo:eu-repo/semantics/conferencePaperes_MX
dc.type.versioninfo:eu-repo/semantics/acceptedVersiones_MX


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record