BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250204T045008Z
UID:BE3F7EC4-4526-4D8E-8563-3DA0A443BE7C
DTSTART;TZID=America/Los_Angeles:20240520T170000
DTEND;TZID=America/Los_Angeles:20240520T183000
DESCRIPTION:Speaker: Chris Cheng\, Distinguished Technologist\, Hewlett Pac
 kard Enterprise\n\nAbstract:\nGenerative AI and Large language models (LLM
 ) with domain knowledge enhancements will fundamentally change the way we 
 design hardware. In this talk we will start with the basic concept of tran
 sformer with encoder and decoder. We will discuss how domain knowledge can
  be injected into LLM through retrieval augmented generation (RAG) and fin
 e tuning. We will also discuss the concept of LLM agent where complex desi
 gn tasks can be done by the agent through planning\, action with other too
 ls and reasoning. An even more advanced technique will involve the LLM opt
 imizing a design through optimization by prompt. We will conclude with the
  concept of foundational models for signal integrity and power integrity a
 s an example of how we can tie LLM and Generative AI to complete a complex
  engineering design task.\n\nSpeaker Bio:\nChris Cheng is a Distinguished 
 Technologist at the Storage Division of Hewlett-Packard Enterprise. He is 
 responsible for managing all high speed\, analog/mixed signal designs and 
 hardware machine learning development within the Storage Division. He also
  held senior engineering positions in SUN Microsystems where he developed 
 the original GTL system bus with Bill Gunning. He was a Principal Engineer
  in Intel where he led high speed processor bus design team. He was the fi
 rst hardware engineer in 3PAR and guided their high-speed design effort un
 til it was acquired by Hewlett Packard.\n\nRoom: SCDI 3301\, Bldg: Sobrato
  Campus for Discovery and Innovation\, 500 El Camino Real\, Santa Clara\, 
 California\, United States\, 95053
LOCATION:Room: SCDI 3301\, Bldg: Sobrato Campus for Discovery and Innovatio
 n\, 500 El Camino Real\, Santa Clara\, California\, United States\, 95053
ORGANIZER:geochen1@yahoo.com
SEQUENCE:17
SUMMARY:Large Language Models and Generative AI for High Performance System
 s 
URL;VALUE=URI:https://events.vtools.ieee.org/m/420026
X-ALT-DESC:Description: &lt;br /&gt;&lt;div dir=&quot;ltr&quot;&gt;&lt;strong&gt;Speaker: &lt;/strong&gt;Chri
 s Cheng\, Distinguished Technologist\, Hewlett Packard Enterprise&lt;/div&gt;\n&lt;
 div dir=&quot;ltr&quot;&gt;\n&lt;div&gt;&amp;nbsp\;&lt;/div&gt;\n&lt;div&gt;&amp;nbsp\;&lt;/div&gt;\n&lt;div&gt;&lt;strong&gt;Abstr
 act:&lt;/strong&gt;&lt;/div&gt;\n&lt;div&gt;&amp;nbsp\; &amp;nbsp\; Generative AI and Large language
  models (LLM) with domain knowledge enhancements will fundamentally change
  the way we design hardware. In this talk we&amp;nbsp\;will start with the bas
 ic concept of transformer with encoder and decoder. We will&amp;nbsp\;discuss 
 how domain knowledge can be injected into LLM through retrieval augmented&amp;
 nbsp\;generation (RAG) and fine tuning. We will also discuss the concept o
 f LLM agent where&amp;nbsp\;complex design tasks can be done by the agent thro
 ugh planning\, action with other&amp;nbsp\;tools and reasoning. An even more a
 dvanced technique will involve the LLM optimizing&amp;nbsp\;a design through o
 ptimization by prompt. We will conclude with the concept of&amp;nbsp\;foundati
 onal models for signal integrity and power integrity as an example of how 
 we&amp;nbsp\;can tie LLM and Generative AI to complete a complex engineering d
 esign task.&lt;/div&gt;\n&lt;div&gt;&amp;nbsp\;&lt;/div&gt;\n&lt;div&gt;&amp;nbsp\;&lt;/div&gt;\n&lt;/div&gt;\n&lt;div di
 r=&quot;ltr&quot;&gt;&lt;strong&gt;Speaker Bio:&lt;/strong&gt;&lt;/div&gt;\n&lt;div&gt;&amp;nbsp\; &amp;nbsp\; &lt;strong&gt;
 Chris Cheng&lt;/strong&gt; is a Distinguished Technologist at the Storage Divisi
 on of Hewlett-Packard Enterprise. He is responsible for managing all high 
 speed\, analog/mixed signal designs and hardware machine learning developm
 ent within the Storage Division. He also held senior engineering positions
  in SUN Microsystems where he developed the original GTL system bus with B
 ill Gunning. He was a Principal Engineer in Intel where he led high speed 
 processor bus design team. He was the first hardware engineer in 3PAR and 
 guided their high-speed design effort until it was acquired by Hewlett Pac
 kard.&lt;/div&gt;\n&lt;p&gt;&amp;nbsp\;&lt;/p&gt;
END:VEVENT
END:VCALENDAR

