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:20191206T142455Z
LOCATION:Booth N-230
DTSTART;TZID=Europe/Stockholm:20180626T151500
DTEND;TZID=Europe/Stockholm:20180626T154500
UID:isc_hpc_ISC High Performance 2018_sess144_proj111@linklings.com
SUMMARY:(PP15) Energy Efficient Computing Research at STFC Hartree Centre
DESCRIPTION:Project Poster\n\n(PP15) Energy Efficient Computing Research a
 t STFC Hartree Centre\n\nBane\n\nThe ever-increasing use of ICT has a sign
 ificant impact on the environment, due to both Carbon emissions running cl
 oud/data centres, PCs and embedded devices, but also the footprint during 
 the manufacture and disposal of ICT equipment. The latter category is not 
 only embodied emissions but also covers use of water and of exotic materia
 ls, for example.\n\nGlobal figures for ICT’s operational Carbon footprint 
 are hard to quantify. However, based on data such as the estimated rise in
  US-based cloud datacentres from 70 billion kW-hr (1.8% of total US energy
  consumption) in 2014 to 73b kW-hrs in 2020 (Zakarya et al, 2017) there is
  broad agreement that action needs to be taken.\n\nTo help tackle the prob
 lem, STFC Hartree Centre undertakes research in to energy efficient comput
 ing. We summarise our current situation – including recent InnovateUK-fund
 ed and H2020-funded work - and discuss the planned approach to hierarchies
  in measuring & monitoring and how these underlie capabilities to predict 
 and to reduce energy consumed whether by specific CPU instructions, by a s
 pecific algorithm/implementation, by how job scheduler runs a set of jobs 
 or by a data centre’s layout design, or by changing any of CPU, algorithm,
  scheduler or data centre. Our proposed research covers not only physical 
 sciences (arts of measurement and prediction) and mathematics (statistical
  analysis of measurements and predictions) but also social science areas i
 ncluding maximising user acceptance of power capping. We aim to fund this 
 research via UK EPRSC Fellowship and explore topics in a Royal Society Sci
 entific Meeting.\n\nPasses: Conference Pass, Exhibition Pass, Computer Arc
 hitecture, Energy consumption, HPC Centre Planning and Operations, Perform
 ance Tools, Scheduling\n\nTag: Conference Pass, Exhibition Pass, Computer 
 Architecture, Energy consumption, HPC Centre Planning and Operations, Perf
 ormance Tools, Scheduling
URL:https://2018.isc-program.com/presentation/?id=proj111&sess=sess144
END:VEVENT
END:VCALENDAR