Advance Program
Tutorials: Sunday, August 25, 2024
| Title | Presenters |
|---|---|
|
Breakfast/Registration |
|
|
Tutorial 1: AI Assisted Hardware Design - Will AI Elevate or Replace Hardware Engineers? Chair: Bryan Chin, UCSD |
|
|
Introduction |
Bryan Chin, UCSD |
|
Overview of AI in Chip Design |
Mark Ren, NVIDIA |
|
Model Customization and Inference |
Stelios Diamantidis, Synopsys |
|
Coffee Break (1/2 hr) |
|
|
Tutorial 1: AI Assisted Hardware Design - Will AI Elevate or Replace Hardware Engineers? Chair: Bryan Chin, UCSD |
|
|
AI assisted RTL Design |
Hanxian Huang, UCSD |
|
Increasing Chip Design Productivity |
Hans Bouwmeester, PrimisAI |
|
Future Directions & Panel Discussion |
|
|
Lunch (1 hr 15 min) |
|
|
Tutorial 2: The Cooling of Hot Chips: How thermal technology is keeping up with the AI revolution Chair: Seshu Madhavapeddy, Frore Systems |
|
|
Thermal techniques for higher data center compute density |
Tom Garvens, Supermicro |
|
Thermal challenges of Edge Devices |
Nader Nikfar, Qualcomm |
|
Coffee Break (1/2 hr) |
|
|
Tutorial 2: The Cooling of Hot Chips: How thermal technology is keeping up with the AI revolution Chair: Seshu Madhavapeddy, Frore Systems |
|
|
Solid-state active cooling helps maintain Moore’s Law |
Prabhu Sathyamurthy, Frore Systems |
|
Applications for thermo-electric cooling |
Jesse Edwards, Phononic |
|
Reception |
Conference Day 1: Monday, August 26, 2024
| Title | Presenters |
|---|---|
|
Breakfast/Registration |
|
|
Welcome |
|
|
General Chair Welcome |
Ron Diamant, General Chair |
|
Progam Co-Chairs Welcome |
Rob Aitken & Larry Yang, PC Co-Chairs |
|
High-Performance Processors Part 1 Chair: Doug Carmean |
|
|
Snapdragon X Elite Qualcomm Oryon CPU: Design & Architecture Overview |
Gerard Williams, Qualcomm |
|
Lunar Lake: Powering the Next Generation of AI PCs |
Arik Gihon, Intel |
|
The next-generation ~5.5GHz IBM Z Processor and AI Inferencing Accelerator chipset |
Christian Jacobi, IBM |
|
Coffee Break |
|
|
Specialized Processors Chair: Renu Raman |
|
|
Envise-Beta: a light-based AI inference accelerator |
Darius Bunandar, Lightmatter |
|
SK Hynix AI-Specific Computing Memory Solution: From AiM device to Heterogeneous AiMX-xPU System for Comprehensive LLM Inference |
Guhyun Kim, SK Hynix |
|
Built for the Edge: The next generation Granite Rapids D |
Praveen Mosur, Intel |
|
Lunch (1 hr 15 min) |
|
|
Keynote #1 Chair: Ralph Wittig |
|
|
Keynote |
Trevor Cai, OpenAI |
|
AI Processors Part 1 Chair: Pradeep Dubey |
|
|
NVIDIA Blackwell GPU: Advancing Generative AI and Accelerated Computing |
Ajay Tirumala and Raymond Wong, NVIDIA |
|
SambaNova SN40L RDU: Breaking the Barrier of Trillion+ Parameter Scale Gen AI Computing |
Raghu Prabhakar, SambaNova |
|
Coffee Break (1/2 hr) |
|
|
AI Processors Part 2 Chair: David Weaver |
|
|
Intel Gaudi 3 AI Accelerator: Architected for Gen AI Training and Inference |
Eitan Joshua, Intel |
|
AMD Instinct MI300X Generative AI Accelerator and Platform Architecture |
Alan Smith and Vamsi Krishna Alla, AMD |
|
An AI Compute ASIC with Optical Attach to Enable Next Generation Scale-up Architectures |
Manish Mehta, Rajiv Pancholy, Sheng Zhang, Anand Ramaswamy and Greg Winn, Broadcom |
|
RNGD: A Tensor Contraction Processor |
Sang Min Lee and Minho Kim, Furiosa |
|
Reception |
Conference Day 2: Tuesday, August 27, 2024
| Title | Presenters |
|---|---|
|
Breakfast/Registration |
|
|
AI Processors Part 3 Chair: Yasuo Ishii |
|
|
Next Generation AMD Versal AI Edge Series for Vision and Automotive |
Jeffrey Chu, Tomai Knopp and Sagheer Ahmad, AMD |
|
Onyx: A Programmable Accelerator for Sparse Tensor Algebra |
Kalhan Koul, Stanford |
|
Next Gen MTIA - Meta’s Recommendation Inference Accelerator |
Olivia Wu, Meta |
|
Coffee Break |
|
|
Networking Processors Chair: Jae W. Lee |
|
|
DOJO: An Exa-Scale Lossy AI Network using the Tesla Transport Protocol over Ethernet (TTPoE) |
Eric Quinnell, Tesla |
|
ACF-S: An 8-Tbit/s SuperNIC for High-Performance Data Movement in AI & Accelerated Compute Networks |
Rochan Sankar, Enfabrica |
|
4 Tbit/s Optical Compute Interconnect Chiplet for XPU-to-XPU Connectivity |
Saeed Fathololoumi, Intel |
|
Lunch (1 hr 15 min) |
|
|
Keynote #2 Chair: Ian Bratt |
|
|
Keynote |
Victor Peng, AMD |
|
High-Performance Processors Part 2 Chair: Nhon Quach |
|
|
Impactful Silicon for Near Memory Compute and Memory Expansion |
Howard Borchew and Wilson Snyder, Marvell |
|
XiangShan: An Open-Source Project for High-Performance RISC-V Processors Meeting Industrial-Grade Standards |
Kaifan Wang, Chinese Academy of Sciences |
|
Coffee Break (1/2 hr) |
|
|
High-Performance Processors Part 3 Chair: Lingjie Xu |
|
|
AmpereOne: Sustainable Computing for AI & Cloud Native Workloads |
Atiq Bajwa and Matthew Erler, Ampere Computing |
|
Inside MAIA 100 |
Sherry Xu, Microsoft |
|
AMD Next Generation “Zen 5” Core |
Brad Cohen and Mike Clark, AMD |
|
MN-Core 2: Second-generation processor of MN-Core architecture for AI and general-purpose HPC applications |
Jun Makino, Preferred Networks |
|
IEEE TCMM Awards |
|
|
IEEE TCMM Awards |
Gabriel Southern, TCMM Chair |
|
Closing Remarks |
|
|
Closing Remarks |
Jan-Willem van de Waerdt, Vice Chair |