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:20250522T212947Z
LOCATION:Hyatt Regency\, Capitol Ballroom 1
DTSTART;TZID=America/Denver:20240801T090000
DTEND;TZID=America/Denver:20240801T093000
UID:siggraph_SIGGRAPH 2024_sess459_bof_190@linklings.com
SUMMARY:The Truth About Computing System Performance Benchmarks
DESCRIPTION:Brigit Valencia (Standard Performance Evaluation Corporation (
 SPEC), Compel PR (acting as submitter - not presenter)) and Ross Cunniff (
 NVIDIA)\n\nComputing system performance benchmarks are essential for allow
 ing hardware vendors to gauge the power of their solutions and compare the
 ir performance to the competition. They also help buyers compare products 
 and purchase ones that meet their needs. However, not all benchmarks are e
 qually effective. This talk exposes key performance benchmarking myths and
  dives into the requirements for creating benchmarks that work for the ent
 ire industry. Topics include how some benchmarks backfire and fuel custome
 r dissatisfaction, how to define and measure performance to meet industry 
 needs, the critical elements of good performance benchmarks, and how to de
 sign them.\n\nInterest Area: Research & Education\n\nRecording: Not Livest
 reamed, Not Recorded\n\nKeyword: Research\n\nRegistration Category: Full C
 onference, Full Conference Supporter, Experience, Exhibitor Full Conferenc
 e, Exhibitor Experience\n\n
END:VEVENT
END:VCALENDAR
