BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260202T201804Z
LOCATION:276
DTSTART;TZID=America/Chicago:20251116T113000
DTEND;TZID=America/Chicago:20251116T114500
UID:submissions.supercomputing.org_SC25_sess197_ws_hpcsysp102@linklings.co
 m
SUMMARY:Multi-rail RoCE, Now with more BGP!
DESCRIPTION:Benjamin Matthews (National Science Foundation National Center
  for Atmospheric Research (NSF NCAR))\n\nHeterogeneous compute nodes conta
 ining multiple accelerators and Ethernet network injections have become co
 mmon in recent years. Despite this, additional network injections beyond t
 he first are often only utilized by application middleware such as MPI or 
 NCCL supporting an RDMA API. We explain why traditional Etherchannel can't
  support this usecase. We further propose an alternative network configura
 tion which allows these hardware resources to be utilized both by RDMA app
 lication middleware such as MPI as well as other applications which utiliz
 e the OS provided sockets API rather than a kernel bypass API. This allows
  user applications using less HPC focused (but potentially more portable) 
 APIs as well as parallel filesystems and other tools to also benefit from 
 the additional networking hardware available in this type of compute node.
 \n\nRecording: Livestreamed, Recorded\n\nRegistration Category: Technical 
 Program Reg Pass, Workshop Reg Pass\n\nSession Chairs: Michael Hartman (St
 anford University) and Jay Blair (Procter and Gamble Company, ASRC)\n\n
END:VEVENT
END:VCALENDAR