PCIe Gen6 physical layer equalization tuning by using unsupervised and supervised machine learning techniques

Vista sencilla de ítem
dc.contributor.authorRangel-Patiño, Francisco
dc.contributor.authorViveros-Wacher, Andrés
dc.contributor.authorRayas-Sánchez, José E.
dc.contributor.authorVega-Ochoa, Édgar
dc.contributor.authorShival, Hemanth
dc.contributor.authorRodríguez-Saenz, Sofía
dc.date.accessioned2024-01-25T16:19:48Z
dc.date.available2024-01-25T16:19:48Z
dc.date.issued2023-12
dc.descriptionEver faster applications triggered the development of the new PCIe Gen6 specification, reaching 64 GT/s data rates with PAM4 modulation. This brings new challenges for the physical channel design, where equalization (EQ) plays a key role. PCIe specification defines an EQ process at the transmitter (Tx) and the receiver (Rx). Current post-silicon validation practices consist of finding optimal subsets of Tx and Rx coefficients by measuring the eye diagram at the Rx across many different channels. However, these practices are very time consuming since they require massive lab measurements. In this paper, we propose machine learning techniques to cluster post-silicon data from different channels and feed those clusters to Gaussian process regression (GPR) models. We then optimize each GPR surrogate to obtain the optimal tuning settings for each identified cluster. Our methodology is validated by using MATLAB SerDes Toolbox simulations of the functional eye diagram of a Gen6 link.es_MX
dc.description.sponsorshipITESO, A.C.es_MX
dc.identifier.citationF. Rangel-Patiño, A. Viveros-Wacher, S. Rodríguez-Saenz, J.E. Rayas-Sánchez, E. Vega-Ochoa, and H. Shival, “PCIe Gen6 physical layer equalization tuning by using unsupervised and supervised machine learning techniques,” in IEEE MTT-S Latin America Microwave Conf. (LAMC-2023), San Jose, Costa Rica, Dec. 2023, pp. 105-108.es_MX
dc.identifier.isbn979-8-3503-1641-4
dc.identifier.urihttps://hdl.handle.net/11117/10725
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.subjectClusteringes_MX
dc.subjectEqualizationes_MX
dc.subjectEqualization Mapses_MX
dc.subjectEye-diagrames_MX
dc.subjectFIRes_MX
dc.subjectGPRes_MX
dc.subjectHSIOes_MX
dc.subjectHigh-speed Linkses_MX
dc.subjectMetamodelses_MX
dc.subjectOptimizationes_MX
dc.subjectPCIees_MX
dc.subjectPost-silicon Validationes_MX
dc.subjectReceiveres_MX
dc.subjectSignal Integrityes_MX
dc.subjectTransmitteres_MX
dc.subjectTuninges_MX
dc.titlePCIe Gen6 physical layer equalization tuning by using unsupervised and supervised machine learning techniqueses_MX
dc.typeinfo:eu-repo/semantics/articlees_MX
dc.type.versioninfo:eu-repo/semantics/publishedVersiones_MX

Archivos

Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Rangel_23Dec_PCIe_Gen6_Phy_Eq_by_ML_author_ver.pdf
Tamaño:
1.01 MB
Formato:
Adobe Portable Document Format
Descripción:
Descargar

Colecciones

DESI - Artículos y ponencias con arbitraje