BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Code Optimization
DTSTART:20260428T070000Z
DTEND:20260428T110000Z
DTSTAMP:20260424T164400Z
UID:indico-event-404@spectra-indico-teszt.hinfra.hu
DESCRIPTION:Attention to the quality of code in terms of its computational
  efficiency is a rather important aspect of using HPC system effectively.
 In the introduction\, we will cover how to quantify performance\, and how 
 to dimension computations to ensure optimal use of the compute resources.
  \nIn order to write efficient scientific code\, the developer should be
  familiar with a number of important aspects of modern CPU architecture.T
 he impact of the NUMA memory architecture\, vectorization and out-of-order
  execution will be discussed. The NUMA memory architecture also has its i
 mpact at the level of a compute node\, while the interconnect properties 
 will determine performance of distributed applications.Several tools will 
 help the developer to profile his application to discover performance hot 
 spots\, and make informed decisions on how to improve the efficiency of th
 e code\, or the use of resources.\n\nhttps://spectra-indico-teszt.hinfra.h
 u/event/404/
URL:https://spectra-indico-teszt.hinfra.hu/event/404/
END:VEVENT
END:VCALENDAR