BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240116T191658Z
LOCATION:503-504
DTSTART;TZID=America/Denver:20231114T103000
DTEND;TZID=America/Denver:20231114T110000
UID:submissions.supercomputing.org_SC23_sess248_exforum122@linklings.com
SUMMARY:The Cost of Flexibility and Security in Cloud-Based HPC – A Case S
 tudy Running EDA Workloads with Confidential Computing Technology
DESCRIPTION:Exhibitor Forum\n\nMengmei Ye and Derren Dunn (IBM TJ Watson R
 esearch Center)\n\nDesign of modern very large scale integrated circuits (
 VLSI) using electronic design automation (EDA) is an increasingly compute 
 intensive and complex endeavor. Because of typical product cycles in chip 
 design, EDA is an excellent candidate for offloading bursts of computation
 s to cloud-based resources when close to design deadlines, to reduce infra
 structure cost and improve flexibility by offering virtually unlimited com
 putational power on-demand. However, running EDA workloads poses significa
 nt security risks, due to the designers’ intellectual property (IP) and hi
 gh-value foundry process design kits (PDKs). The cost of a leaked propriet
 ary design is measured in millions of dollars, loss of competitiveness and
  brand damage. To guarantee security of these highly valuable assets, all 
 data and computations in the EDA workloads must be secured. Traditionally,
  encryption has been an effective solution to protect data at rest and in 
 motion; however, data in use has so far seen less secure solutions based m
 ostly on virtualization. Emerging confidential computing techniques can im
 prove this aspect by providing truly isolated and encrypted environments f
 or the computations. However, as of today, there is no comprehensive study
  on the challenges of running HPC workloads in confidential enclaves, and 
 on how to deploy confidential computing in the public cloud. This talk foc
 uses on EDA workloads as a proxy to generic HPC workloads that need thousa
 nds of cores, high-bandwidth network communication and shared storage. We 
 present our experience at running cloud-native EDA workloads in confidenti
 al VMs through the use of Confidential Containers, that allows a zero-effo
 rt conversion of cloud-native workloads. We will briefly discuss existing 
 and novel mechanisms to integrate the data-in-use protection of Confidenti
 al Containers with secure private/shared storage and network. Then, we wil
 l focus on measuring and characterizing the performance overhead of protec
 ting data in every stage of the computation.\n\nTag: Architecture and Netw
 orks, Cloud Computing\n\nRegistration Category: Tech Program Reg Pass, Exh
 ibits Reg Pass\n\nSession Chair: Jane Herriman (Lawrence Livermore Nationa
 l Laboratory (LLNL))
END:VEVENT
END:VCALENDAR