BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000712Z
LOCATION:302
DTSTART;TZID=America/Denver:20231112T083000
DTEND;TZID=America/Denver:20231112T170000
UID:submissions.supercomputing.org_SC23_sess224_tut116@linklings.com
SUMMARY:Performance Tuning with the Roofline Model on GPUs and CPUs
DESCRIPTION:JaeHyuk Kwack (Argonne National Laboratory (ANL)), Magnus Stre
 ngert (NVIDIA Corporation), Neil Mehta (Lawrence Berkeley National Laborat
 ory (LBNL)), Alexei Kalinin (Intel Corporation), Xiaomin Lu (AMD), and Nic
 holson Koukpaizan (Oak Ridge National Laboratory (ORNL))\n\nThe Roofline p
 erformance model offers an insightful and intuitive method for extracting 
 the key execution characteristics of HPC applications and comparing them a
 gainst the performance ­bounds of modern CPUs and GPUs. Its ability to abs
 tract the complexity of memory hierarchies and identify the most profitabl
 e optimization techniques have made Roofline­-based analysis increasingly 
 popular in the HPC community. Although different flavors of the Roofline m
 odel have been developed to deal with various definitions of memory data m
 ovement, there remains a need for a systematic methodology when applying t
 hem to analyze applications running on multicore and accelerated systems. 
 The tutorial aims to bridge this gap on both CPUs and GPUs by both exposin
 g the fundamental aspects behind different Roofline modeling principles as
  well as providing several practical use­ case scenarios that highlight th
 eir efficacy for application optimization. This tutorial presents a unique
  combination of instruction to Roofline by its creator, hands-on instructi
 on in using Roofline within Intel’s, NVIDIA’s, and AMD’s production perfor
 mance tools, and discussions of real-world Roofline use cases at ALCF, NER
 SC, and OLCF computing centers. The tutorial presenters have a long histor
 y of collaborating on the Roofline model and have presented several Roofli
 ne-­based tutorials.\n\nTag: Accelerators, Heterogeneous Computing, Perfor
 mance Measurement, Modeling, and Tools, Performance Optimization, Software
  Engineering\n\nRegistration Category: Tutorial Reg Pass\n\n
END:VEVENT
END:VCALENDAR