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:20260202T201312Z
LOCATION:264
DTSTART;TZID=America/Chicago:20251116T140000
DTEND;TZID=America/Chicago:20251116T173000
UID:submissions.supercomputing.org_SC25_sess204@linklings.com
SUMMARY:Sustainable Supercomputing
DESCRIPTION:Sustainable supercomputing is a pressing topic for our communi
 ty, industry, and governments. Supercomputing has an ever-increasing need 
 for computational cycles while facing the increasing challenges of deliver
 ing performance/Watt advances within the context of climate change, the dr
 ive towards net-zero, and geo-political-economic pressures. Improving supe
 rcomputing sustainability provides many opportunities considering an end-t
 o-end, holistic view of the HPC system, facility, site, and broader enviro
 nment. All elements of the HPC system must be considered, from low-level c
 ircuits, up the software stack and beyond to power/cooling systems. The dr
 ive towards more sustainable supercomputing requires measurements, metrics
 , goals, and improvement processes. This workshop will gather users, resea
 rchers, and developers to address the opportunities and challenges of supe
 rcomputing sustainability. Topics include, but are not limited to: • Deplo
 yment of supercomputing systems • Data center efficiency • Software tools 
 for measuring energy efficiency throughout the supercomputing system • Sta
 ndardization of measurement/reporting of key sustainability metrics and em
 issions\n\nSustainable Supercomputing\n\nSustainable supercomputing is a p
 ressing topic for our community, industry, and governments. Supercomputing
  has an ever-increasing need for computational cycles while facing the inc
 reasing challenges of delivering performance/Watt advances within the cont
 ext of climate change, the drive towards net-...\n\n\nMike Woodacre (Hewle
 tt Packard Enterprise (HPE)), Michele Weiland (Edinburgh Parallel Computin
 g Centre (EPCC)), Fumiyoshi Shoji (RIKEN Center for Computational Science 
 (R-CCS)), Pekka Manninen (CSC - IT Center for Science), Jim Rogers (Oak Ri
 dge National Laboratory (ORNL)), and Cate Berard (U.S. Department of Energ
 y)\n---------------------\nMolten Chloride Small Modular Reactor Performan
 ce Characteristics for Data Center Operation\n\nSmall modular reactors (SM
 Rs) require a smaller physical footprint than conventional large nuclear r
 eactors while still providing high reliability in power generation and the
 y are frequently discussed in the context of providing power for data cent
 ers. Molten chloride reactors represent a new type o...\n\n\nMatthew Ander
 son (Idaho National Laboratory), Daniel Yankura (North Carolina State Univ
 ersity), and Matthew Sgambati and Mauricio Tano Retamales (Idaho National 
 Laboratory)\n---------------------\nModeling the Carbon Footprint of HPC: 
 The Top 500 and EasyC\n\nClimate change is a critical concern for HPC syst
 ems, but GHG protocol carbon-emission accounting methodologies are difficu
 lt for a single system, and effectively infeasible for a collections of sy
 stems.\nAs a result, there is no HPC-wide carbon reporting, and even the l
 argest HPC sites do not do it....\n\n\nVarsha Rao and Andrew A. Chien (Uni
 versity of Chicago)\n---------------------\nImproving Supercomputer Usage 
 with Aging Awareness\n\nLifetime of electronic devices has a critical impa
 ct on their environmental footprint. In addition, the high-demand by AI co
 mpanies of GPU has reduced tremendously their availability for supercomput
 ing centers. Consequently, improving the duration of CPUs and GPUs is beco
 ming a major issue in High P...\n\n\nRobin Boezennec (Inria Rennes); Fanny
  Dufossé (Université Grenoble Alpes, INRIA, CNRS, Grenoble INP); Guillaume
  Pallez (Inria Rennes); and Alix Tremodeux (ENS de Lyon)\n----------------
 -----\nEnergy-Aware HPC Scheduling with LLM-Based Power Prediction\n\nAs t
 he increasing energy consumption of High-Performance Computing (HPC) syste
 ms places greater strain on electric grid infrastructure, operational stra
 tegies for load balancing become critically important. Energy-aware schedu
 ling offers a promising solution by enabling HPC systems to function as ac
 ...\n\n\nKevin Menear (National Renewable Energy Laboratory (NREL)); Alex 
 Wilkinson (University of Warwick); Tim Dykes and Utz-Uwe Haus (HPE, EMEA R
 esearch Lab); and Dmitry Duplyakin (National Renewable Energy Laboratory (
 NREL))\n---------------------\nA Framework for Mapping the Effective and S
 ustainable Use of Energy\n\nSteve Dean\n---------------------\nRun-time En
 ergy-Efficiency Optimization for AI and HPC Workloads\n\nEffective power m
 anagement is crucial for balancing high performance and environmental impa
 ct in the exascale era, particularly for datacenters dominated by massivel
 y parallel GPU systems due to the rise of AI. While many strategies rely o
 n deep application knowledge, there is a growing need for app...\n\n\nGabr
 iel Hautreux (LIRMM, Univ. Montpellier, CNRS; CINES) and Abdoulaye Gamatié
  and Gilles Sassatelli (LIRMM, Univ. Montpellier, CNRS)\n-----------------
 ----\nBridging the Gap: User-Centric Energy Monitoring for Policy-Driven A
 pplication Optimization in HPC Data Centers\n\nApplication energy optimiza
 tion in HPC data centers face two critical gaps. Systematic methodologies 
 that connect data center policies to application decisions and accessible 
 monitoring tools that enable data-driven optimization. We address both gap
 s through two complementary pillars. First, we pres...\n\n\nWoong Shin (Oa
 k Ridge National Laboratory (ORNL)); Karl W. Schulz (Advanced Micro Device
 s, Inc. (AMD)); Arthur F. Lorenzon (Federal University of Rio Grande do Su
 l); Matthias Maiterth (Oak Ridge National Laboratory (ORNL)); Bruno Villas
 enor Alvarez and Jordà Polo (Advanced Micro Devices, Inc. (AMD)); Aditya K
 ashi, Hao Lu, Nicholson Koukpaizan, Antigoni Georgiadou, Matthew Norman, W
 ael Elwasif, Michael Matheson, and Feiyi Wang (Oak Ridge National Laborato
 ry (ORNL)); Nicholas Frontiere (Argonne National Laboratory (ANL)); and Sa
 rp Oral, Thomas Beck, and Bronson Messer (Oak Ridge National Laboratory (O
 RNL))\n---------------------\nHPC Digital Twins for Evaluating Scheduling 
 Policies, Incentive Structures and their Impact on Power and Cooling\n\nSc
 hedulers are critical for optimal resource utilization in high-performance
  computing. Traditional methods to evaluate schedulers are limited to post
 -deployment analysis, or simulators, which do not model associated infrast
 ructure. In this work, we present the first-of-its-kind integration of sch
 ed...\n\n\nMatthias Maiterth and Wesley H. Brewer (Oak Ridge National Labo
 ratory (ORNL)); Jaya S. Kuruvella, Arunavo Dey, and Tanzima Z. Islam (Texa
 s State University); Rashadul Kabir (Colorado State University); Kevin Men
 ear and Dmitry Duplyakin (National Renewable Energy Laboratory); Tapasya P
 atki (Lawrence Livermore National Laboratory (LLNL)); and Terry Jones and 
 Feiyi Wang (Oak Ridge National Laboratory (ORNL))\n---------------------\n
 EAS-Sim: A Framework and its Methodology for the Co-Design of Multi-Object
 ive, Energy-Aware Schedulers for AI Clusters\n\nThe explosive growth of la
 rge-scale Deep Learning (DL) models has made energy consumption a first-or
 der operational cost and constraint in modern High-Performance Computing (
 HPC) datacenters. Existing DL schedulers, however, are largely single-obje
 ctive and energy oblivious, struggling to balance th...\n\n\nRoblex NANA T
 CHAKOUTE and Claude TADONKI (Centre de recherche en informatique (CRI), Mi
 nes Paris - PSL University)\n---------------------\nOptimizing Microgrid C
 omposition for Sustainable Data Centers\n\nAs computing energy demand cont
 inues to grow and electrical grid infrastructure struggles to keep pace, a
 n increasing number of data centers are being planned with colocated micro
 grids that integrate on-site renewable generation and energy storage. Howe
 ver, while existing research has examined the t...\n\n\nJulius Irion, Phil
 ipp Wiesner, Jonathan Bader, and Odej Kao (TU Berlin)\n-------------------
 --\nAfternoon Break - Sustainable Supercomputing\n---------------------\nE
 MLIO: Minimizing I/O Latency and Energy Consumption for Large-Scale AI Tra
 ining\n\nLarge-scale deep learning workloads increasingly face I/O bottlen
 ecks as datasets exceed local storage and GPU compute outpaces network and
  disk speeds. While recent systems optimize data-loading time, they often 
 ignore I/O energy costs—a critical factor at scale. We present EMLIO, an E
 fficien...\n\n\nMd Hasibul Jamil (University at Buffalo SUNY), MD S. Q. Zu
 lkar Nine (Tennessee Technological University), and Tevfik Kosar (Universi
 ty at Buffalo (SUNY))\n\nRecording: Livestreamed, Recorded\n\nRegistration
  Category: Technical Program Reg Pass, Workshop Reg Pass\n\nSession Chairs
 : Mike Woodacre (Hewlett Packard Enterprise (HPE)); Michèle Weiland (EPCC,
  The University of Edinburgh; The University of Edinburgh); Fumiyoshi Shoj
 i (RIKEN Center for Computational Science (R-CCS), Center for Computationa
 l Science); Pekka Manninen (CSC - IT Center for Science; University of Hel
 sinki, Finland); James H. Rogers (Oak Ridge National Laboratory (ORNL)); a
 nd Cate Berard (US Department of Energy)
END:VEVENT
END:VCALENDAR