BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241120T082409Z
LOCATION:HG D 1.2
DTSTART;TZID=Europe/Stockholm:20240603T143000
DTEND;TZID=Europe/Stockholm:20240603T163000
UID:submissions.pasc-conference.org_PASC24_sess125@linklings.com
SUMMARY:MS2F - Confidential Computing in HPC
DESCRIPTION:Minisymposium\n\nHPC continues to be commoditised and democrat
 ised, with HPC-as-a-service, workflow-based HPC, and a growing number of H
 PC and AI use cases, whilst the largest scale computing resources are simu
 ltaneously concentrated into fewer sites capable of meeting the vast power
 , infrastructure, and financial requirements of exascale systems. As such,
  HPC service operators are required to cater to an ever-widening variety o
 f users with diverse workloads and potentially sensitive data, and so the 
 ability to protect and isolate confidential workloads in multi-tenant HPC 
 environments is becoming increasingly important. There exist many differen
 t HPC or near-HPC workloads which currently cannot run on public or federa
 ted cloud environments for various reasons. While the concerns often origi
 nate from legal aspects, such as regulatory requirements, protection of in
 tellectual property (algorithms or data) or protection of personal data, t
 he solution must be provided on the platform level. In this minisymposium,
  we intend to capture the current state of Confidential Computing in HPC, 
 ranging from direct application and workflows to deployment and low-level 
 implementation. We illustrate the impact of mitigation techniques on HPC a
 rchitectures. We also explore possible advancements and alternatives to si
 licon-based trust regions, by looking at more fundamental mathematical top
 ics, such as Homomorphic Encryption.\n\nThe LUMI Case: Towards High Perfor
 mance Confidential Computing with Containers\n\nTim Dykes and Martin Matth
 iesen will discuss the topic of confidential high performance computing fr
 om both the platform vendor and operational perspectives in the context of
  Europe's HPC Flagship LUMI. The talk will initially outline the requireme
 nt for secure workloads in HPC, highlighting the cha...\n\n\nMartin Matthi
 esen (CSC - IT Center for Science) and Timothy Dykes (HPE)\n--------------
 -------\nPanel Discussion: Sensitive Data in HPC – How Secure Can It Be?\n
 \nIn this roundtable, the speakers of the Minisymposium and additional gue
 sts will discuss with the audience the question “How secure can handling s
 ensitive data in HPC be?”, with an introduction given by  Martin Matthiese
 n (CSC – IT Center for Science, Finland), moderated  by Tizian...\n\n\nMar
 tin Matthiesen (CSC - IT Center for Science), Tiziano Müller and Timothy D
 ykes (HPE), Stefan Lankes (RWTH Aachen University), and Roberto Avanzi (Un
 iversity of Haifa)\n---------------------\nCryptographic Protection of Ran
 dom Access Memory for High Performance Confidential Computing\n\nConfident
 ial Computing safeguards data in use against unauthorized access or modifi
 cation, including by privileged software. Architectures like Intel SGX, AM
 D SEV, Arm CCA, and IBM Ultravisor implement this protection through acces
 s control policies. In some cases, they also employ cryptographic mem...\n
 \n\nRoberto Avanzi (University of Haifa)\n---------------------\nUnikernel
 s as a Platform for Confidential Supercomputing?\n\nThe domain of high-per
 formance computing is currently experiencing a paradigm shift known as "co
 nvergent computing":\nCloud providers are now able to provide supercompute
 r-like performance, and HPC centers are improving their utilization with m
 ulti-tenancy models, blurring the line between these doma...\n\n\nStefan L
 ankes and Jonathan Klimt (RWTH Aachen University)\n\nDomain: Computational
  Methods and Applied Mathematics\n\nSession Chairs: Timothy Dykes (HPE) an
 d Tiziano Müller (HPE)
END:VEVENT
END:VCALENDAR