Hotchips 2024

Summary

  • [[ HotChips2024_GC_remarks.pdf ]]
  • The Journey to AI Pervasiveness, Victor Peng, AMD
    • [[ HC2024.AMD.VPeng.pdf ]]

Topics

AI Assisted Hardware Design

  • [[ 1-HC2024.ucsd.BryanChin.v02.pdf ]]
    • Bryan Chin, UCSD
  • Introduction to AI for Chip Design, Mark Ren, Nvidia
    • [[ 2-HC2024.nvidia.MarkRen.Intro.v04.pdf ]]
  • AI- Assisted Chip Design Tutorial, Stelios Diamantidis, Synopsys
    • [[ 3-HC24.synopsys.SteliosDiamantidis.v03.pdf ]]
  • EDA AI-Agent, Hans Bouwmeester, PrimisAI
    • [[ 4-HC24.PrimisAI.Hans_Bouwmeester.v4.pdf ]]
  • Domain-adaptive LLMs for Chip Design, Hanxian Huang, UCSD
    • [[ 5-HC24.ucsd.HanxianHuang.v02.pdf ]]
  • LLM Agents for Chip Design, Mark Ren, Nvidia
    • [[ 6-HC2024.nvidia.MarkRen.agent.v04.pdf ]]
  • Picasso: Diffusion Accelerator, Sungyeob Yoo, KAIST
    • [[ 3_HC2024.Poster.KAIST.SungyeobYoo.v02 merged.pdf ]]
  • IBM Telum2 processor and IBM Spyre Accelerator chip for AI, Chris Berry, IBM
    • [[ 04_HC2024.IBM.CBerry.final.pdf ]]
  • SK hynix AI-Specific Computing Memory Solution, Guhyun Kim, SK Hynix
    • [[ 11_HC2024.SKhynix.GuhyunKim.rev920240822.pdf ]]
  • Intel Xeon 6 SoC, Praveen Mosur, Intel
    • [[ 14_HC2024.Intel.Xeon_6_SoC.Praveen.Mosur.pdf ]]
  • MN-Core 2: MN-Core Arch for AI and HPC application, Jun Makino, Preferred Networks
    • [[ 15_HC2024.Preferred.Makino.final.pdf ]]
  • Tesla Transport Protocol over Ethernet (TTPoE), Eric Quinnel, Tesla
    • [[ 17_HC2024_Tesla_TTPoE_v5.pdf ]]
  • AMD Versal AI Edge Gen2 for vision and automotive, Tomai Knopp, AMD
    • [[ 21_HC2024.AMD.KnoppChu.final.pdf ]]
  • NeuGPU: Neural GPU for mobile AR/VR devices, Junha Ryu, KAIST
    • [[ 22_HC2024.Poster.KAIST.Ryu.v3.pdf ]]
  • AMD MI300X Generative AI Accelerator and Platform Arch, Alan Smith, AMD
    • [[ 23_HC2024.AMD.MI300X.ASmith(MI300X).v1.Final.20240817.pdf ]]
  • Zen 5 core, Brad Cohen, AMD
    • [[ 24_HC2024.AMD.Cohen.Subramony.final.pdf ]]
  • Qualcomm ORYON CPU, Gerard Williams, Qualcomm
    • [[ 25_HC2024.Qualcomm.GWilliams.pdf ]]
  • Space-Mate: Real-time SLAM Processor, Gwangtae Park, KAIST
    • [[ 28_HC2024.Poster.KAIST.Park.v2.pdf ]]
  • 香山：高性能 RISC-V 处理器, 王凯帆, 中科院计算所
    • [[ 29_HC2024.ChineseAcademy.XiangShan.Kaifan.final.pdf ]]
  • Low power LLM Processor for On-device AI, Sanyeob Kim, KAIST
    • [[ 35_HC2024.Poster.KAIST.SangyeobKim.v01.pdf ]]
  • SN40L RDU: Breaking Barrier of Trillion+ Parameter Scale Gen AI Computing, Raghu Prabhakar, SambaNova Systems
    • [[ 48_HC2024.Sambanova.Prabhakar.final-withoutvideo.pdf ]]
  • Luna Lake Architecture Session, Arik Gihon, Intel
    • [[ 56_HC2024.Intel.AGihon.pdf ]]
  • Intel Gaudi 3 AI Accelerator, Roman Kaplan, Intel
    • [[ 60_HC2024.Intel.RomanKaplan.Gaudi3-0826.pdf ]]
  • An AI Compute ASIC with Optical Attach to Enable Next Gen Scale-Up Arch, Manish Mehta, Broadcom
    • [[ 61_HC2024.Broadcom.ManishMehta.v2-NO-VIDEO.pdf ]]
  • 4 Tb/s Optical Compute Interconnect Chiplet for XPU-to-XPU Connectivity, Saeed Fathololoumi, Intel
    • [[ 62_HC2024.Intel.Fathololoumi.Final.pdf ]]

AI Chip Architecture

  • Sustainable Computing for AI & Cloud, Matthew Erler, Ampere
    • [[ 70_HC2024.AmpereComputing.Erler.final(for website).pdf ]]
  • Wafer-Scale AI: GPU Impossible Performance, Sean Lie, Cerebras
    • [72_HC2024.Cerebras.Sean.v03.final.pdf]]
  • Inside Maia 100, Sherry Xu, Microsoft
    • [[ 81_HC2024.Microsoft.Xu.Ramakrishnan.final.v2.pdf ]]
  • Next Gen MTIA - Inference Accelerator, Mahesh Maddury, Meta
    • [[ 82_HC2024.Meta.MadduryKansal.final.pdf ]]
  • RNGD - Tensor Contraction Processor for AI Computing, June Paik, Furiosa AI
    • [[ 83_HC2024.Furiosa.JunePaik.Final.pdf ]]
  • Blackhole The Standalone AI Computer and its Programming Model, Jasmina Vasiljevic, Tenstorrent
    • [[ 88_HC2024.Tenstorrent.Jasmina.Davor.v7.pdf ]]

Thermal

  • Predictable Scaling and Infrastructure, Trevor Cai, OpenAI
    • [[ HotChips - 2024-08-26.pdf ]]
  • AirJet: Solid-state active cooling helps maintain Moore’s Law, Frore Systems
    • [[ HC2024.T2.Frore.Sathyamurthy.final.pdf ]]
  • Next-Generation Cooling for NVIDIA Accelerated Computing, Ali Heydari, Nvidia
    • [[ HC2024.T2.Nvidia.Heydari.final.v1.pdf ]]
  • Datacenters: Explosive Growth meets Thermal Consequences, Edwards, Phononic
    • [[ HC2024.T2.Phononic.Edwards.final.v1.pdf ]]
  • On-device AI and its thermal implications, Nader Nikfar, Qualcomm
    • [[ HC2024.T2.Qualcomm.NaderNikfar.final-0824.pdf ]]
  • Thermal Techniques for Data Center Computer Density, Tom Garvens, Supermicro
    • [[ HC2024.T2.Supermicro.Garvens.final.pdf ]]

This line appears after every note.

Notes mentioning this note

你好
你好。

Here are all the notes in this garden, along with their links, visualized as a graph.