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:20260202T201321Z
LOCATION:265
DTSTART;TZID=America/Chicago:20251116T140000
DTEND;TZID=America/Chicago:20251116T173000
UID:submissions.supercomputing.org_SC25_sess226@linklings.com
SUMMARY:14th International Workshop on Runtime and Operating Systems for S
 upercomputers (ROSS 2025)
DESCRIPTION:With increasing levels of parallelism, increased heterogeneity
 , energy and memory constraints coupled with emerging post-Moore computing
  architectures like quantum and neuromorphic, a reevaluation of current ap
 proaches for extreme-scale operating systems and runtime environments is n
 eeded. ROSS is a workshop aimed at identifying looming problems and discus
 sing promising research solutions in the area of runtime and operating sys
 tems for extreme-scale supercomputers. Specifically, ROSS focuses on princ
 iples and techniques to design, implement, optimize, or operate runtime an
 d operating systems for extreme-scale supercomputers and cloud environment
 s. In addition to typical workshop publications, we encourage novel and po
 ssibly immature ideas, provided that they are interesting and on-topic. We
 ll argued position papers are also welcome.\n\nExtending the C++ Execution
  Control Library to Support Dynamic Parallel Runtime Systems\n\nThe releas
 e of the C++26 execution control library (senders and receivers) provides 
 a uniform interface for coordinating asynchronous work on heterogeneous ba
 ckends.\nThat said, the standardization of senders and receivers is just a
  starting point toward structured parallelism and composable heteroge...\n
 \n\nIan Henriksen, Jan Ciesko, and Stephen L. Olivier (Sandia National Lab
 oratories)\n---------------------\n14th International Workshop on Runtime 
 and Operating Systems for Supercomputers (ROSS 2025)\n\nWith increasing le
 vels of parallelism, increased heterogeneity, energy and memory constraint
 s coupled with emerging post-Moore computing architectures like quantum an
 d neuromorphic, a reevaluation of current approaches for extreme-scale ope
 rating systems and runtime environments is needed.\n \nROSS is...\n\n\nKur
 t B. Ferreira (Sandia National Laboratories, University of New Mexico); Ba
 lazs Gerofi (Intel Corporation, RIKEN Center for Computational Science (R-
 CCS)); Torsten Hoefler (ETH Zürich); and Jack Lange (Oak Ridge National La
 boratory (ORNL), University of Pittsburgh)\n---------------------\nInvited
  Talk: Multikernel: Kernel-to-Kernel Isolation with Elastic Resource Manag
 ement\n\nModern HPC and AI workloads challenge fundamental limitations in 
 traditional operating system designs. Shared kernels introduce unpredictab
 le performance interference, virtualization imposes unacceptable overhead,
  and monolithic architectures waste resources on unnecessary features.<br>
 <br>Multikern...\n\n\nCong Wang (Multikernel Technologies)\n--------------
 -------\nAssessing Page Reclamation Mechanisms for Linux\n\nPage reclamati
 on is critical for system performance. However, understanding and quantify
 ing inner workings of reclamation policies remains challenging. In this wo
 rk, we present a comprehensive analysis of Linux's Two-Queue LRU (2QLRU) a
 nd Multi-Generational LRU (MGLRU) policies using a lightweight p...\n\n\nS
 haochang Liu and Jie Ren (College of William & Mary)\n--------------------
 -\nReproducible Performance Evaluation of OpenMP and SYCL Workloads under 
 Noise Injection\n\nPerformance instability caused by unpredictable system 
 noise remains a persistent challenge in high-performance and parallel comp
 uting. This work presents a reproducible methodology to characterize this 
 variability through noise injection, tested using workloads implemented in
  OpenMP and SYCL to com...\n\n\nChristoffer Persson, Mathias Pretot, Minyu
  Cui, and Miquel Pericas (Chalmers University of Technology and University
  of Gothenburg)\n---------------------\nAfternoon Break - Workshop on Runt
 ime and Operating Systems for Supercomputers (ROSS 2025)\n----------------
 -----\nInvited Talk:  State-of-the-Art Communication Software for Supercom
 puters and Its Applications\n\n<br>This talk will focus on high-performanc
 e communication software for GPU supercomputers.  It will explain NCCL and
  NVSHMEM, including their historical context from MPI and SHMEM.  The func
 tionality and performance will be demonstrated through an example from lin
 ear algebra.  Real world results fr...\n\n\nJeff Hammond (NVIDIA)\n\nRecor
 ding: Livestreamed, Recorded\n\nRegistration Category: Technical Program R
 eg Pass, Workshop Reg Pass\n\nSession Chairs: Kurt B. Ferreira (Sandia Nat
 ional Laboratories, University of New Mexico); Balazs Gerofi (Intel Corpor
 ation, RIKEN Center for Computational Science (R-CCS)); Torsten Hoefler (E
 TH Zürich, Microsoft Corporation); and John Lange (Oak Ridge National Labo
 ratory (ORNL), University of Pittsburgh)
END:VEVENT
END:VCALENDAR