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:20210518T152158Z
LOCATION:Analog 1\, 2
DTSTART;TZID=Europe/Stockholm:20190619T101000
DTEND;TZID=Europe/Stockholm:20190619T110000
UID:isc_hpc_ISC High Performance 2019_sess251_post141@linklings.com
SUMMARY:(RP27) Memory First : A Performance Tuning Strategy Focusing on Me
 mory Access Patterns
DESCRIPTION:HPC in Asia\n\n(RP27) Memory First : A Performance Tuning Stra
 tegy Focusing on Memory Access Patterns\n\nEbata, Egawa, Isobe, Takaki, Ta
 kizawa\n\nAs many scientific applications are memory-bound, a key to achie
 ving high sustained performance on a modern HPC system is to fully exploit
  the system’s memory bandwidth. Indeed, the sustained memory bandwidth of 
 an application could be much lower than the theoretical peak bandwidth of 
 the system for various reasons due to underlying memory architectures. For
  example, a certain memory access pattern may cause frequent access confli
 cts at memory channels and/or banks, and thus lead to a longer access late
 ncy. This poster hence discusses a memory-centric performance tuning strat
 egy, Memory First. Usually, a whole application is first written and then 
 optimized for a particular system, often resulting in major code modificat
 ions for memory-aware tuning. On the other hand, in the Memory First strat
 egy, memory access patterns capable of achieving high sustained memory ban
 dwidths on a target system are first investigated. Then, unlike the conven
 tional strategy, a tiny benchmark code achieving a high sustained memory b
 andwidth is developed, while keeping a target application’s behavior in mi
 nd. Finally, the code is modified to work as the target application. While
  application coding is well established in matured application areas such 
 as CFD, memory-aware tuning is likely to become more painful in practice. 
 This is because the latter has to be developed for every new architecture 
 in a try-and-error fashion. Therefore, giving a higher priority to memory-
 aware tuning can result in a lower tuning cost in modern HPC systems with 
 advanced memory technologies, such as NEC SX-Aurora TSUBASA.\n\nPasses: Co
 nference Pass\n\nTag: Computer Architecture, Performance Analysis and Opti
 mization, Scientific Software Development
URL:https://2019.isc-program.com/presentation/?id=post141&sess=sess251
END:VEVENT
END:VCALENDAR

