Silicon Feeds

Conference

RSS
sources all
categories onlyConference ×
tags all
clear all
Hot Chips · YouTube talks hotchipsvideos

HC2026-K: Compute in Motion: Challenges of Autonomous Driving

Keynote, Hot Chips 2026, Monday, August 24, 2026 Daniel Rosenband, Waymo Chair: Cliff Young, Google Daniel gives an overview of the challenges that Waymo has faced in their 13-year journey to create cars that can safely drive themselves even in the face of extremely unusual and difficult driving situations. He also…

Hot Chips · YouTube talks hotchipsvideos

HC2025-T2.2: AI Kernel Programming (part 2)

Tutorial 2, part 2, Hot Chips 2025, Sunday, August 24, 2025. Organizer: Fredrik Kjolstad, Stanford Domain specific languages for GPU kernels and automatic kernel authoring with LLMs Tri Dao, Princeton / Together AI Programming techniques for implementing ML models on GPUs Zihao Jia, CMU

Hot Chips · YouTube talks hotchipsvideos

HC2025-T2.1: AI Kernel Programming (part 1)

Tutorial 2, part 1, Hot Chips 2025, Sunday, August 24, 2025. Organizer: Fredrik Kjolstad, Stanford Introduction Fredrik Kjolstad, Stanford Decoupling Performance from Correctness with User-Schedulable Kernel Languages Andrew Adams, Adobe Research Pallas: Using JAX to write custom kernels for GPUs and TPUs Sharad…

Hot Chips · YouTube talks hotchipsvideos

HC2025-T1.2: Datacenter Racks (part 2)

Tutorial 1, part 2, Hot Chips 2025, Sunday, August 24, 2025. Organizer: Ralph Wittig, AMD This half of the tutorial consists of three full case studies of rack development at different companies. There is a group Q&A at the end. Case study: Nvidia GB200NVL72 John Norton, NVIDIA Case study: Meta’s Catalina (NVL72)…

Hot Chips · YouTube talks hotchipsvideos

HC2025-T1.1: Datacenter Racks (part 1)

Tutorial 1, part 1, Hot Chips 2025, Sunday, August 24, 2025. Organizer: Ralph Wittig, AMD This half of the tutorial is organized by topic. There is a group Q&A at the end. How AI workloads shape rack system architecture Frank Helms, AMD Scaling fabric technologies Darrin Vallis, AMD Liquid cooling with Google…

Hot Chips · YouTube talks hotchipsvideos

HC2025-S8: Machine Learning 2

Session 8, Hot Chips 2025, Tuesday, August 26, 2025. Chair: Pradeep Dubey, Intel NVIDIA’s GB10 SoC: AI Supercomputer On Your Desk Andi Skende, NVIDIA 4th Gen AMD CDNA™ Generative AI Architecture Powering AMD Instinct™ MI350 Series GPUs and Platforms Michael Floyd & Michael Steffen, AMD Ironwood: Delivering best in…

Hot Chips · YouTube talks hotchipsvideos

HC2025-S7: Machine Learning 1

Session 7, Hot Chips 2025, Tuesday, August 26, 2025. Chair: Ronny Krashinsky, NVIDIA Memory: (Almost) the Only Thing That Matters Mark Kuemerle, Marvell Corsair - An In-memory Computing Chiplet Architecture for Inference-time Compute Acceleration Sudeep Bhoja, d-Matrix UB-Mesh: Huawei’s Next-Gen AI SuperComputer with…

Hot Chips · YouTube talks hotchipsvideos

HC2025-S6: Power / Methodology

Session 6, Hot Chips 2025, Tuesday, August 26, 2025. Chair: Jae W. Lee, SNU ECAM Enabled Advanced Thermal Management Solutions for the AI Data Center Michael Matthews, Fabric8Labs Everactive Self-Powered SoC with Energy Harvesting, Wakeup Receiver, and Energy-Aware Subsystem Ben Calhoun, Everactive Taping Out Three…

Hot Chips · YouTube talks hotchipsvideos

HC2025-S5: Optical

Session 5, Hot Chips 2025, Tuesday, August 26, 2025. Chair: Borivoje Nikolic, UC Berkeley Celestial AI Photonic Fabric Module (PF Module) - The world’s first SoC with in-die Optical IO Phil Winterbottom, Celestial AI A UCIe Optical I/O Retimer Chiplet for AI Scale-up Fabrics Vladimir Stojanovic, Ayar Labs Passage…

Hot Chips · YouTube talks hotchipsvideos

HC2025-S4: Networking

Session 4, Hot Chips 2025, Monday, August 25, 2025. Chair: Sherry Xu, Microsoft Intel Mount Morgan Infrastructure Processing Unit (IPU) Patrick Fleming, Intel AMD Pensando™ Pollara 400 AI NIC Architecture and Application Kevin Chu, AMD NVIDIA ConnectX-8 SuperNIC: A Programmable RoCE Architecture for AI Data Centers…

Hot Chips · YouTube talks hotchipsvideos

HC2025-S3: Graphics

Session 3, Hot Chips 2025, Monday, August 25, 2025. Chair: Lavanya Subramanian, OpenAI AMD RDNA 4 and Radeon RX 9000 Series GPU Andy Pomianowski & Laks Pappu, AMD RTX 5090: Designed for the Age of Neural Rendering Marc Blackstein, NVIDIA Specialized SoC enabling low-power ‘World Lock Rendering’ in Augmented and Mixed…

Hot Chips · YouTube talks hotchipsvideos

HC2025-S2: Security

Session 2, Hot Chips 2025, Monday, August 25, 2025. Chair: Greg Papadopoulos, NEA Presto: A RISC-V-Compatible SoC for Unified Multi-Scheme FHE Acceleration over Module Lattice Luchang Lei & Hongyang Jia, Tsinghua University Azure Secure Hardware Architecture: Establishing a Robust Security Foundation for Cloud…

Hot Chips · YouTube talks hotchipsvideos

HC2025-S1: CPUs

Session 1, Hot Chips 2025, Monday, August 25, 2025. Chair: Gabriel Southern, Qualcomm Cuzco: A High-Performance RISC-V RVA23 Compatible CPU IP Ty Garibay & Shashank Nemawarkar, Condor Computing PEZY-SC4s: The Fourth Generation MIMD Many-core Processor with High Energy Efficiency and Flexibility for HPC and AI…

Hot Chips · YouTube talks hotchipsvideos

HC2025-K2: Up and Running with Rapidus

How Japan and Cutting-Edge Technologies are Transforming Semiconductor Manufacturing Keynote 2, Hot Chips 2025, Tuesday, August 26, 2025 Dr. Atsuyoshi Koike, Rapidus Chair: Yasuo Ishii, Tenstorrent Dr. Koike, the CEO of Rapidus, presents his view of how silicon technology can change the world and role of the Rapidus…

Hot Chips · YouTube talks hotchipsvideos

HC2025-K1: Predictions for the Next Phase of AI

Keynote 1, Hot Chips 2025, Monday, August 25, 2025 Noam Shazeer, GDM VP, Engineering, Google Chair: Cliff Young, Google Noam, one of the authors of the original transformer paper that helped start the current wave of AI development, takes a look at how AI has developed and then makes some predictions about where it…