BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Denver
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:MDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231105T010000
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:MST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20231117T151128Z
UID:7B5F6888-3A79-4735-A16C-7DADBF475BD1
DTSTART;TZID=America/Denver:20231116T183000
DTEND;TZID=America/Denver:20231116T203000
DESCRIPTION:Abstract:\n\nFor decades\, Moore’s Law has delivered the abil
 ity to integrate an exponentially increasing number of devices in the same
  silicon area at a roughly constant cost. This has enabled tremendous leve
 ls of integration\, where the capabilities of computer systems that previo
 usly occupied entire rooms can now fit on a single integrated circuit.\n\n
 In recent times\, the steady drum beat of Moore’s Law has started to slo
 w down. Whereas device density historically doubled every 18-24 months\, t
 he rate of recent silicon process advancements has declined. While improve
 ments in device scaling continue\, albeit at a reduced pace\, the industry
  is simultaneously observing increases in manufacturing costs. In response
 \, the industry is now seeing a trend toward reversing direction on the tr
 aditional march toward more integration. Instead\, multiple industry and a
 cademic groups are advocating that systems on chips (SoCs) be “disintegr
 ated” into multiple smaller “chiplets.” This talk details the techno
 logy challenges that motivated AMD to use chiplets\, the technical solutio
 ns we developed for our products\, and how we expanded the use of chiplets
  from individual processors to multiple product families. From this founda
 tion\, we will look toward the future of chiplet and 3D architectures that
  will require multi-disciplinary innovation across package technology\, si
 licon design\, accelerators\, and the software to exploit them.\n\nSpeaker
 (s): Samuel\, \n\nBldg: Coy Barn Conference Center\, 1075 Woodward Way\, W
 oodward Corporate Campus\, Fort Collins\, Colorado\, United States\, 80524
 \, Virtual: https://events.vtools.ieee.org/m/380847
LOCATION:Bldg: Coy Barn Conference Center\, 1075 Woodward Way\, Woodward Co
 rporate Campus\, Fort Collins\, Colorado\, United States\, 80524\, Virtual
 : https://events.vtools.ieee.org/m/380847
ORGANIZER:mag10co@hotmail.com
SEQUENCE:17
SUMMARY:“How and Why 2.5D and 3D Integration is Revolutionizing Silicon D
 esign”
URL;VALUE=URI:https://events.vtools.ieee.org/m/380847
X-ALT-DESC:Description: &lt;br /&gt;&lt;p&gt;Abstract:&lt;/p&gt;\n&lt;p&gt;For decades\, Moore&amp;rsqu
 o\;s Law has delivered the ability to integrate an exponentially increasin
 g number of devices in the same silicon area at a roughly constant cost.&amp;n
 bsp\; This has enabled tremendous levels of integration\, where the capabi
 lities of computer systems that previously occupied entire rooms can now f
 it on a single integrated circuit.&lt;/p&gt;\n&lt;p&gt;In recent times\, the steady dr
 um beat of Moore&amp;rsquo\;s Law has started to slow down.&amp;nbsp\; Whereas dev
 ice density historically doubled every 18-24 months\, the rate of recent s
 ilicon process advancements has declined.&amp;nbsp\; While improvements in dev
 ice scaling continue\, albeit at a reduced pace\, the industry is simultan
 eously observing increases in manufacturing costs.&amp;nbsp\; In response\, th
 e industry is now seeing a trend toward reversing direction on the traditi
 onal march toward more integration.&amp;nbsp\; Instead\, multiple industry and
  academic groups are advocating that systems on chips (SoCs) be &amp;ldquo\;di
 sintegrated&amp;rdquo\; into multiple smaller &amp;ldquo\;chiplets.&amp;rdquo\;&amp;nbsp\;
  This talk details the technology challenges that motivated AMD to use chi
 plets\, the technical solutions we developed for our products\, and how we
  expanded the use of chiplets from individual processors to multiple produ
 ct families.&amp;nbsp\; From this foundation\, we will look toward the future 
 of chiplet and 3D architectures that will require multi-disciplinary innov
 ation across package technology\, silicon design\, accelerators\, and the 
 software to exploit them.&lt;/p&gt;\n&lt;p&gt;&amp;nbsp\;&lt;/p&gt;
END:VEVENT
END:VCALENDAR

