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:20250822T115805Z
LOCATION:Room 5.0A52
DTSTART;TZID=Europe/Stockholm:20250618T140000
DTEND;TZID=Europe/Stockholm:20250618T160000
UID:submissions.pasc-conference.org_PASC25_sess127@linklings.com
SUMMARY:MS6A - Improving Energy Efficiency of HPC Systems through SW
DESCRIPTION:Energy and power challenges increase as High-Performance Compu
 ting and AI scale to meet rapid industry and research demands. These chall
 enges include higher CO2 emissions, increased energy costs, and strain on 
 the power infrastructure. HPC centers are looking to reduce energy consump
 tion and enhance energy efficiency by optimizing resource utilization and 
 managing their workloads more efficiently. Efforts to improve energy effic
 iency often focus on hardware advancements, such as microarchitectures, in
 tra-core parallelism, vectorization, and accelerators for critical workloa
 ds. These innovations reduced idle power and improved execution but have a
 lso introduced challenges like swift power variations. Data center infrast
 ructure, rack design, and cooling techniques have also progressed. Liquid 
 cooling, especially direct hot-water cooling, has gained traction for its 
 cost-saving potential. Although such hardware improvements are impressive,
  they cannot fully address energy challenges due to their limited adaptabi
 lity to workloads. Complementary software solutions provide a global view 
 of system status and energy usage, support dynamic adaptation across the s
 tack, enable long-term predictions of resource use, and deliver actionable
  insights on workload optimizations to users. Research on power-steering r
 untimes and monitoring tools has contributed to user-facing analytics tool
 s. The rapid progress of AI techniques opens additional opportunities for 
 energy efficiency and optimization in HPC systems.\n\nSMART Energy Efficie
 ncy with EAR Software\n\nCurrent Data Centres require sophisticated softwa
 re tools for monitoring, management,\noptimization and data analytics. Sev
 eral projects are currently addressing the topic of designing\nthe require
 d software stack to provide all these features. Having all of them in sing
 le tools is\nvery complex becaus...\n\n\nJulita Corbalan (Barcelona Superc
 omputing Center, Energy Aware Solutions); Marco D'Amico (Energy Aware Solu
 tions); and Oriol Visal (Barcelona Supercomputing Center, Energy Aware SOl
 utions)\n---------------------\nFrom Operational Data Monitoring to Operat
 ional Data Analytics Chatbots\n\nWith generative artificial intelligence c
 hallenging the computational demand supremacy of scientific computing, dat
 a centers are experiencing unprecedented growth in both scale and volume. 
 Computing efficiency has never been more critical to humankind, the econom
 y, and society. Operational Data Anal...\n\n\nAndrea Bartolini (University
  of Bologna)\n---------------------\nDatacenter Power Monitoring and Manag
 ement Using MERIC SW Suite\n\nAn HPC system can be optimized for energy ef
 ficiency at several levels, while the highest level of dynamicity comes fr
 om the power management of computing components controlled at the job leve
 l. Complex parallel applications show different hardware requirements duri
 ng their execution. Energy-efficie...\n\n\nOndrej Vysocky (IT4Innovations 
 National Supercomputing Center)\n---------------------\nMonitoring and Ana
 lysis of Energy Consumption in HPC Systems\n\nEnergy efficiency is a criti
 cal challenge in modern data centers facing an ever-growing scale and comp
 lexity. This talk presents energy monitoring and analysis strategies emplo
 yed in the data center of the TU Dresden. The focus is on how energy consu
 mption and other metrics are measured and analyzed...\n\n\nMario Bielert (
 ZIH, CIDS, TU Dresden)\n\nDomain: Engineering, Computational Methods and A
 pplied Mathematics\n\nSession Chair: Lubomir Riha (IT4Innovations National
  Supercomputing Center, VSB-TU Ostrava)
END:VEVENT
END:VCALENDAR