Institute of Chips and AI
(Invitation Only)
Tuesday, November 19, 2024
8:30 AM - 5:30 PM
Computer History Museum
1401 N Shoreline Blvd
Mountain View, California 94043
Next-Gen Chip Design | AI-Driven Innovation
The Institute of Chips and AI, a pioneering initiative from the Purdue College of Engineering, is poised to redefine the future of semiconductor and AI research. The Institute's official launch will take place on November 19th in Mountain View, California in the heart of Silicon Valley.
Spearheaded by Director Professor Kaushik Roy and Co-Director Professor Anand Raghunathan, this newly established institute is a cornerstone of Purdue Engineering's 150th anniversary, focusing on Semiconductors, AI, and Autonomy. The institute's launch on November 19th will celebrate Purdue Engineering's ambitious leap into cutting-edge research in these transformative fields. The event will feature a distinguished roster of top AI industry leaders and offer opportunities to connect with key industry figures, Purdue faculty, prominent alumni, and others. Join us as we celebrate this groundbreaking initiative!
About
At the Institute for CHIPS and AI, we're at the forefront of a transformative era where chip design and artificial intelligence converge. Our mission is to harness innovative chip technology to power the future of AI while leveraging AI itself to streamline and enhance chip design processes. This virtuous cycle not only drives cutting-edge advancements but also addresses the growing complexities and costs associated with developing state-of-the-art semiconductors.
The Institute for CHIPS and AI is Purdue University's bold move to emphasize our commitment to advancing semiconductor and AI research. Purdue is uniquely positioned to lead this initiative, backed by a rich history of excellence in both AI and chip research. With over 50 PhD graduates making significant contributions in academia and industry, our institute builds on a legacy of groundbreaking projects such as the SRC/DARPA Center for Brain-Inspired Computing.
Agenda
| Tuesday, November 19, 2024 | |||
|---|---|---|---|
| Time | Location | Topic | Speaker(s)/Participant(s) |
8:30-9:00 am |
Grand Lobby |
Breakfast and Registration |
All registered participants |
9:00-9:10 am |
Hahn Auditorium |
Welcome |
Kaushik Roy |
Welcome Video |
Mung Chiang |
||
Welcome Video |
Todd Young |
||
9:10-9:20 a.m. |
Hahn Auditorium |
Purdue AI Overview |
Arvind Raman |
9:20-9:50 a.m. |
Hahn Auditorium |
Purdue Chips & AI Research Highlights |
Kaushik Roy |
9:50-10:10 a.m. |
Hahn Auditorium |
Keynote: Accelerating GenAI computing through Semiconductor Innovations |
Mukesh Khare Talk DetailsThe semiconductor industry is projected to reach $1T globally by 2030. Much of the growth is fueled by increasing compute demands from artificial intelligence. The increasing demand on the compute used to build, tune and deploy generative AI models is in turn driving significant opportunity to innovate at the semiconductor technology level. This talk will highlight IBM's innovation in advanced semiconductor and AI technology to secure our future in this exciting new chapter for AI. |
10:10-10:20 a.m. |
Hahn Auditorium |
SEMI Overview |
Ajit Manocha |
10:20-10:40 a.m. |
Hahn Auditorium |
Keynote: Deploying AI from the Cloud to Client for a Transformative Future |
Vamsi Boppana |
10:45-11:05 a.m. |
Hahn Auditorium |
Keynote: ML4ML: The intriguing interplay between Machine Learning and Moore's Law |
Partha Ranganathan Talk DetailsWe are at an exciting time in the industry. The exploding demand for computing for new AI/ML workloads, at the same time Moore's Law is slowing down, and the resulting combination of opportunity and scarcity, have together triggered a wave of new innovations. In this talk, we will discuss some recent new ideas resulting from the synergistic interplay between machine learning and Moore's law. We will present how hardware/software co-design has enabled innovative custom silicon and software-defined hardware, to support a new "Moore's law for ML", and the exciting opportunities ahead. Reciprocally, ML techniques have also been transformative in improving the design and efficiency of existing infrastructure, extending generational performance improvements of new hardware. We will discuss some key innovations in this area, as well as the significant opportunities ahead for more such applications of "ML for Moore's Law." |
| Break: 11:05-11:30 a.m. | |||
11:30-12:30 p.m. |
Hahn Auditorium |
Panel: Chips for AI |
Moderator: Kaushik Roy |
| Lunch: 12:30 p.m.-1:30 p.m. | |||
1:30-1:50 p.m. |
Hahn Auditorium |
Keynote: Unleashing the Potential of Memory-Centric Computing |
Hoshik Kim Talk DetailsIn the era of accelerating computing demands and increasing data deluge, traditional computing architectures are facing significant challenges. Memory-centric computing offers a promising solution by rethinking the design of computing systems around memory as the primary performance driver. In this keynote, I will explore the concept of memory-centric computing, its potential benefits, and the latest advancements in memory technologies that are enabling this paradigm shift. I will discuss how memory-centric computing can unlock new levels of performance, efficiency, and scalability, and highlight the opportunities and challenges for industry and academia to collaborate and drive innovation in this exciting field. Join me as we unleash the potential of memory-centric computing and shape the future of computing |
1:50-2:10 p.m. |
Hahn Auditorium |
Keynote: The future of AR/VR technologies |
Barbara De Salvo |
| Break: 2:10-2:45 p.m. | |||
2:45-3:45 p.m. |
Hahn Auditorium |
Panel: AI for Chips |
Moderator: Anand Raghunathan |
3:45-4:00 p.m. |
Hahn Auditorium |
Purdue Education and Workforce Highlights |
Vijay Raghunathan |
4:00-5:30 p.m. |
Grand Lobby |
Reception and Student Posters |
All registered participants |
