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:20260422T000712Z
LOCATION:505
DTSTART;TZID=America/Denver:20231116T164500
DTEND;TZID=America/Denver:20231116T170000
UID:submissions.supercomputing.org_SC23_sess310_drs121@linklings.com
SUMMARY:High Performance Serverless for HPC and Clouds
DESCRIPTION:Marcin Copik (ETH Zürich)\n\nFunction-as-a-Service (FaaS) comp
 uting brought a fundamental shift in resource management. It allowed for n
 ew and better solutions to the problem of low resource utilization, an iss
 ue that has been known in data centers for decades. The problem persists a
 s the frequently changing resource availability cannot be addressed entire
 ly with techniques such as persistent cloud allocations and batch jobs. Th
 e elastic fine-grained tasking and largely unconstrained scheduling of Faa
 S create new opportunities. Still, modern serverless platforms struggle to
  achieve the high performance needed for the most demanding and latency-cr
 itical workloads. Furthermore, many applications cannot be “FaaSified” wit
 hout non-negligible loss in performance, and the short and stateless funct
 ions employed in FaaS must be easy to program, debug, and optimize. By sol
 ving the fundamental performance challenges of FaaS, we can build a fast a
 nd efficient programming model that brings innovative cloud techniques int
 o HPC data centers, allowing users to benefit from pay-as-you-go billing a
 nd helping operators to decrease running costs and their environmental imp
 act. My PhD research attempts to bridge the gap between high-performance p
 rogramming and modern FaaS computing frameworks. I have been working on ta
 ilored solutions for different levels of the FaaS computing stack: from co
 mputing and network devices to high-level optimizations and efficient syst
 em designs.\n\nTag: Accelerators, Applications, Cloud Computing, Data Comp
 ression, Heterogeneous Computing, I/O and File Systems, Reproducibility, S
 oftware Engineering\n\nRegistration Category: Tech Program Reg Pass\n\nSes
 sion Chairs: André Brinkmann (Johannes Gutenberg University Mainz) and Xub
 in He (Temple University, Department of Computer and Information Sciences)
 \n\n
END:VEVENT
END:VCALENDAR