BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240626T180002Z
LOCATION:3006\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20240626T133000
DTEND;TZID=America/Los_Angeles:20240626T150000
UID:dac_DAC 2024_sess182@linklings.com
SUMMARY:Large Language Model - Revolutionizing the Entire Computing Paradi
 gm
DESCRIPTION:Special Session (Research)\n\nLarge Language Models (LLMs) are
  fundamental machine learning models that use advanced algorithms to compr
 ehend, process, and optimize natural language. These models are typically 
 trained on vast amounts of data to learn patterns and use that in the proc
 essing and optimization phase. Due to the advent of LLMs, computing platfo
 rms are revolutionizing. This includes traditional Semiconductors as well 
 as computing at both Cloud and Edge. In this session, we propose to have t
 hree complementary technologies that will cover this spectrum. In the firs
 t talk, the authors will discuss the LLM techniques that can be deployed f
 or High-Level Synthesis Optimization and Verification. This approach enhan
 ces the efficiency and accessibility of AI accelerator development and ser
 ves as a bridge between AI algorithmic advancements and hardware innovatio
 n. The researchers in the second talk believe in and observe the importanc
 e of High-quality HDL in the design process. They will present that carefu
 l selection, filtering, and augmentation of data across HDLs can yield pow
 erful LLM (and other) models that surpass current state-of-the-art models.
  This technique can be used to train various models for circuit design rel
 ated activities. The final talk is about leveraging the extraordinary capa
 bilities of Large Language Models to revolutionize AI accelerator design a
 nd enhance its accessibility.\n\nOrganizer: Sabya Das, Synopsys\n\nInvited
 : New Solutions on LLM Acceleration, Optimization, and Application\n\nLarg
 e Language Models (LLMs) have revolutionized a wide range of applications 
 with their strong human-like understanding and creativity. Due to the cont
 inuously growing model size and complexity, LLM training and deployment ha
 ve shown significant challenges, which often results in extremely high com
 ...\n\n\nDeming Chen (University of Illinois at Urbana-Champaign)\n-------
 --------------\nInvited: HDL-GPT: High Quality HDL Is All You Need\n\nThis
  talk presents Hardware Description Language Generative Pre-Trained Transf
 ormers (HDL-GPT), a novel approach that leverages the vast repository of o
 pen-source Hardware Description Language (HDL) codes to train superior qua
 lity large code models. The core premise of this research is the hypothesi
 ...\n\n\nGanapathy Parthasarathy (Synopsys)\n---------------------\nInvite
 d: LLM4AIGChip: Harnessing Large Language Models Towards Automation of AI 
 Accelerator Design\n\n"In the rapidly evolving field of Artificial Intelli
 gence (AI), the demand for efficient AI hardware accelerators is increasin
 gly paramount. However, the complex and labor-intensive process of designi
 ng these accelerators presents significant challenges, hindering the pace 
 of development in line wit...\n\n\nYingyan (Celine) Yin (Georgia Institute
  of Technology)\n\nTopic: AI\n\nSession Chair: Cong (Callie) Hao (Georgia 
 Institute of Technology)
END:VEVENT
END:VCALENDAR