BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//SemiWiki - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://semiwiki.com
X-WR-CALDESC:Events for SemiWiki
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20250309T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20251102T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20260308T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20261101T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20270314T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20271107T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260421T090000
DTEND;TZID=America/Los_Angeles:20260421T100000
DTSTAMP:20260403T132932
CREATED:20260401T065505Z
LAST-MODIFIED:20260401T065640Z
UID:368025-1776762000-1776765600@semiwiki.com
SUMMARY:Webinar: Understanding UALink Architecture: A Protocol Deep Dive
DESCRIPTION:As AI workloads scale into the thousands of accelerators and hundreds of terabytes of distributed memory\, traditional interconnects cannot deliver the deterministic latency\, bandwidth efficiency\, or memory semantic operations required for modern training clusters. UALink provides a purpose built accelerator fabric leveraging 224G SerDes\, fixed 64 byte flits\, compressed transaction formats\, and high efficiency TL/DLL aggregation to achieve predictable\, low overhead load/store communication across large GPU pools. With multi virtual channel flow control\, source ordered routing\, and integrated AES GCM encryption via UALinkSec\, the architecture is engineered for high performance\, secure AI fabrics. \nThis session will review a breakdown of how UALink enables scalable memory pooling\, reduces communication overhead\, and supports pod  and rack scale GPU integration. We will examine the behavior of the UPLI\, Transaction Layer\, and Data Link Layer and discuss silicon level implementation considerations for accelerators and switches. \nWhat you’ll learn: \n\nHow UALink implements low latency\, memory semantic GPU to GPU communication\nInternal structure of 64 byte flits\, compressed request/response formats\, and TL/DLL packing\nHow multi VC flow control\, link level retry\, and RS FEC ensure deterministic\, lossless throughput\nThe role of UALinkSec in enforcing end to end AES GCM encryption and authentication\nHow UALink enables scalable memory pooling and GPU clustering across pods and racks\nSystem level design considerations for integrating UALink controllers\, PHYs\, and switches\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nFeatured Speaker\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nDiwakar Kumaraswamy \nSr. Staff Technical Product Manager \nWith over 15 years of experience in Application Engineering and SoC design\, Diwakar has built a career spanning FPGA development\, global IP support\, and technical leadership. Beginning at CoreEL Technologies with Xilinx FPGA implementations and corporate training\, he went on to lead customer success for PCIe\, CXL\, AMBA\, and other interface IP at Synopsys\, followed by NoC architecture work at Intel. Now a Technical Product Manager at Synopsys\, he drives high-speed interconnect solutions—such as Ethernet\, PCIe\, and UALink—for next-generation AI infrastructure. \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nREGISTER HERE
URL:https://semiwiki.com/event/webinar-understanding-ualink-architecture-a-protocol-deep-dive/
LOCATION:Online
ATTACH;FMTTYPE=image/jpeg:https://semiwiki.com/wp-content/uploads/2026/03/Synopsys-understanding-ualink-architecture-webinar-1200x628-1.jpeg
END:VEVENT
END:VCALENDAR