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:20250822T115810Z
LOCATION:Room 5.0A52
DTSTART;TZID=Europe/Stockholm:20250616T143000
DTEND;TZID=Europe/Stockholm:20250616T163000
UID:submissions.pasc-conference.org_PASC25_sess138@linklings.com
SUMMARY:MS2A - Sustainable Scientific Computing
DESCRIPTION:In scientific computing and beyond, we are all used to optimiz
 ing time-to-solution in our computations and to use computers to their ful
 lest power. Yet, the world is facing a climate crisis and we must all stri
 ve to minimize our energy footprint. The power consumption constraint for 
 large-scale computing (aka exascale computing limited by 20MW) encourages 
 scientists to revise the architectural design of hardware but also of appl
 ications, their underlying algorithms, as well as the working/ storage pre
 cision. By improving energy efficiency, we contribute to sustainable scien
 tific computing. Developing energy-efficient scientific computing applicat
 ions is nontrivial and requires expertise in several different areas: algo
 rithms and applications, programming languages and compilers, numerical ve
 rification, and computer architecture. In this minisymposium, we aim to di
 scuss challenges in designing and implementing energy-efficient mixed-prec
 ision algorithms with the assistance of computer arithmetic tools, energy 
 efficiency modeling, hardware-software co-design in light of the end of Mo
 ore's law, and potential for automating energy-saving techniques. Key topi
 cs include establishing energy-to-solution as a HPC metric following our i
 nitial attempt https://zenodo.org/records/13306639, exploring energy optim
 ization opportunities from algorithmic derivation and across computing sta
 cks, and enhancing tools to aid energy-efficient software development.\n\n
 Probabilistic Error Analysis of Limited-Precision Stochastic Rounding\n\nC
 lassical probabilistic rounding error analysis is well suited to stochasti
 c rounding (SR), yielding strong results for floating-point algorithms rel
 ying on summation. For many numerical linear algebra algorithms, one can p
 rove probabilistic error bounds that grow as $\mathcal{O}(\sqrt{n}u)$, whe
 re ...\n\n\nEl-Mehdi El arar (University of Rennes, INRIA)\n--------------
 -------\nNumerical Optimization Targeting Energy-Efficient Scientific Comp
 uting\n\nMixed-precision computing has the potential to significantly redu
 ce the cost of exascale computations, but determining when and how to impl
 ement it in programs can be challenging.\nWe propose a methodology for ena
 bling mixed-precision with the help of computer arithmetic tools, roofline
  model, and co...\n\n\nRoman Iakymchuk (Uppsala University, Umeå Universit
 y)\n---------------------\nExploring Numerical Accuracy and Mixed-Precisio
 n with Verificarlo and Stochastic Rounding\n\nReducing the energy cost of 
 computer simulations is critical. While numerical precision must be suffic
 ient to yield reliable scientific insights, lower precision can significan
 tly reduce energy consumption and computation time. We present Verificarlo
  (https://github.com/verificarlo/verificarlo), an ...\n\n\nPablo de Olivei
 ra Castro (UVSQ, Université Paris-Saclay)\n---------------------\nSustaina
 ble Supercomputing: An Overview of Activities at EPCC\n\nImproving the env
 ironmental sustainability of scientific computing has been a key concern f
 or EPCC, the supercomputing centre at the University of Edinburgh, for man
 y years. This talk will give an overview of the operational measures that 
 have been implemented in our data centre and on our systems, ...\n\n\nMich
 ele Weiland (EPCC, The University of Edinburgh)\n\nDomain: Climate, Weathe
 r, and Earth Sciences, Engineering, Computational Methods and Applied Math
 ematics\n\nSession Chair: Roman Iakymchuk (Uppsala University, Umeå Univer
 sity)
END:VEVENT
END:VCALENDAR