Conference

Conference Day 1: Monday, August 24th, 2026

Title Affiliation
Breakfast/registration
 
Welcome
 
Session: CPU 1

Chair: Ian Bratt
 
The future IBM Z & LinuxONE Processor and AI Inference Acceleration Chipset
IBM
Intel Core Series 3, codename Wildcat Lake
Intel
NVIDIA’s Vera CPU
NVIDIA
Break
 
Session: CPU 2

Chair: Gabriel Southern
 
Next-Generation Arm-based CPU FUJITSU-MONAKA for green AI data center
Fujitsu
Arm AGI : A Disaggregated, Chiplet-Based Server SoC for scalable coherency and memory Bandwidth in the Terabyte/s Era
Arm
Diamond Rapids: Next Generation Intel Xeon CPU
Intel
Lunch
 
Keynote 1

Chair: Borivoje Nikolic
 
Keynote announcement coming soon
 
Session: Automotive

Chair: Yasuo Ishii
 
Eagle-N: Chiplet-Based SoC for Scalable Automotive AI
BOS Semiconductors
Waymo sensor fusion processor
Waymo
Break
 
Session: GPU

Chair: Pradeep Dubey
 
NVIDIA Rubin GPU: Driving the Era of Agentic AI
NVIDIA
AMD Instinct MI400 Series GPU Architecture
AMD
System Architecture of the AMD MI400 Series GPU
AMD
Crescent Island: GPU Designed for Agentic AI Inference
Intel
TCMM Awards
 
TCMM Awards
 
Reception
 

Conference Day 2: Tuesday, August 25th, 2026

Title Affiliation
Breakfast/registration
 
Session: FPGA

Chair: Thierry Tambe
 
AMD Industry 1st Adaptive SoC/FPGA with PQC, Advanced Memory Features, and PCIe Connectivity
AMD
Versal RF
AMD
Session: Memory

Chair: Jae W. Lee
 
Samsung LPDDR5X-PIM with In-memory Processing
Samsung
XCENA MX1 CXL Computational Memory Device
XCENA
Break
 
Session: Networking & Interconnect

Chair: Greg Papadopoulos
 
Thor Ultra: An Ethernet NIC Chip Optimized for AI & HPC
Broadcom
NVIDIA Spectrum-X Multiplane Network Architecture
NVIDIA
Massively Parallel Optical I/O Powered by Ultra-High-Density Micro-LEDs
Mojo Vision
NVIDIA BlueField-4 Processor Powers the AI Factory Operating System
NVIDIA
Lunch
 
Keynote 2

Chair: Cliff Young
 
Keynote announcement coming soon
 
Session: AI 1

Chair: Sherry Xu
 
MTIA 400: Architecture for GenAI + Recommendation Systems, Training
Meta
Break
 
Session: AI 2

Chair: John Wright
 
LPX: A Heterogeneous GPU-LPU
NVIDIA
The Cerebras Rack-Scale Architecture for Wafer Scale Engine
Cerebras
MAIA 200: A Data Center Scale AI system - MAIA-200 Accelerator
Microsoft
Break
 
Session: AI 3

Chair: Brucek Khailany
 
Dataflow at Scale: the SN50 RDU
SambaNova
The Eighth Generation TPU Family: Two Chips Optimized for Training and Serving in the Agentic Era
Google
Vice-Chair closing remarks
 
Vice-Chair closing remarks