NVIDIA-Computex-2024-Keynote presentation

NVIDIA-Computex-2024-Keynote presentation

• 1. Except for the historical information contained herein, certain matters in this presentation are forward-looking statements. These forward-looking statements and any other forward-looking statements that go beyond historical facts that are made in this presentation are subject to risks and uncertainties that may cause actual results to differ materially. Important factors that could cause actual results to differ materially include: global economic conditions; NVIDIA’s reliance on third parties to manufacture, assemble, package and test NVIDIA’s products; the impact of technological development and competition; development of new products and technologies or enhancements to NVIDIA’s existing product and technologies; market acceptance of NVIDIA’s products or NVIDIA’s partners' products; design, manufacturing or software defects; changes in consumer preferences and demands; changes in industry standards and interfaces; unexpected loss of performance of NVIDIA’s products or technologies when integrated into systems and other factors. NVIDIA has based these forward-looking statements largely on its current expectations and projections about future events and trends that it believes may affect its financial condition, results of operations, business strategy, short-term and long-term business operations and objectives, and financial needs. These forward-looking statements are subject to a number of risks and uncertainties, and you should not rely upon the forward-looking statements as predictions of future events. The future events and trends discussed in this presentation may not occur and actual results could differ materially and adversely from those anticipated or implied in the forward-looking statements. Although NVIDIA believes that the expectations reflected in the forward-looking statements are reasonable, the company cannot guarantee that future results, levels of activity, performance, achievements or events and circumstances reflected in the forward-looking statements will occur. Except as required by law, NVIDIA disclaims any obligation to update these forward-looking statements to reflect future events or circumstances. For a complete discussion of factors that could materially affect NVIDIA’s financial results and operations, please refer to the reports NVIDIA files from time to time with the SEC, including NVIDIA’s most recent Annual Report on Form 10-K, Quarterly Reports on Form 10-Q, and Current Reports on Form 8-K. Copies of reports NVIDIA files with the SEC are posted on NVIDIA’s website and are available from NVIDIA without charge. Many of the products and features described herein remain in various stages and will be offered on a when-and-if-available basis. The statements within are not intended to be, and should not be interpreted as a commitment, promise, or legal obligation, and the development, release, and timing of any features or functionalities described for our products is subject to change and remains at the sole discretion of NVIDIA. NVIDIA will have no liability for failure to deliver or delay in the delivery of any of the products, features or functions set forth herein.

• 5. 于氳鷠畁侈♏塜㏇ꝧ㡐

• 6. ⱶ鵯夷⠕䟕榫䌋

• 7. 鞙飉㛡 ˟ 泹飉㛡

• 8. Data Processing cuDF AI Radio Aerial RAN Combinatorial Optimization cuOPT QC Simulation cuQUANTUM Deep Learning cuDNN Computational Lithography cuLITHO Gene Sequencing Parabricks AI Physics Modulus NVIDIA CUDA LIBRARIES OPEN NEW MARKETS NVIDIA CUDA ⭹䌋䈼ꝧ䦌于䄬㕙

• 9. NVIDIA 㲛⛜䫠⭴ GOOGLE COLAB ╈氳 PANDAS-CUDF NVIDIA ANNOUNCES PANDAS-CUDF IN GOOGLE COLAB

• 11. CUDA 㴨杯荂䓪䐢梫

• 16. LLM Large Language Model

• 17. 于榣哆ꪵ⽝

• 18. 榟䡗䌋☕䄄保䫠Ⳃ叏ꄆ㖇

• 21. AI.NVIDIA.COM Computer Vision Biology Vision Language RAG Speech Simulation Regional Language Digital Human Language

• 22. Agent LLM Speech Audio2Face Medical Specialist Agent Checklist Specialist Agent Privacy and Compliance Specialist Agent Embedding Model Vector Database Electronic Health Records Physician-Approved Reference Tables NeMo Retriever User GENERATIVE AI ENABLES DIGITAL NURSE, CUSTOMER SERVICE AGENTS, TUTORS, ETC 榟䡗䌋☕䄄保㴨杯丨⛤闀㚖㲙僜㵷䅨璢

• 24. ASUS TUF A14 / A16 ASUS Zephyrus G16 ASUS ProArt PX13 / P16 MSI Stealth A16 AI+ Now Over 200 RTX AI Laptops | Up to 700 AI TOPS | 7X Generative AI ANNOUNCING NEW RTX AI PCs 杯䄖飃鷪 200 堒 RTX AI 璜鋘㑔꧆胖 | 냖鷾 700 AI TOPS | 7X 榟䡗䌋☕䄄保 氪辑于堒 RTX AI ꧆胖

• 25. 鷠畁嘘㑔釨嘘䧘丨碎䡗ꝏ

• 26. DECOMPRESSION ENGINE 800 GB/sec TRANSFORMER ENGINE FP4/FP6 Tensor Core AI SUPERCHIP 208B Transistors 5th GENERATION NVLINK Scales to 576 GPUs SECURE AI Full Performance Encryption and TEE RAS ENGINE 100% In-System Self-Test NVIDIA BLACKWELL 䇖⺐ ⩚碎⹉丨釨嘘氳榟䡗䌋☕䄄保

• 27. 2016 2018 2020 2022 2024 TFLOPS Pascal 19 TFLOPS FP16 Volta 130 TFLOPS FP16 Ampere 620 TFLOPS FP16 Blackwell 20,000 TFLOPS FP4 Hopper 4,000 TFLOPS FP8 Moore’s Law 1,000X AI COMPUTE IN 8 YEARS 8 䇗⪐ 1,000X 氳☕䄄保鷠畁

• 28. 2016 2018 2020 2022 2024 TFLOPS Pascal 1,000+ GWh Volta 140 GWh Ampere 40 GWh Blackwell 3 GWh Hopper 13 GWh 350X ENERGY REDUCTION IN 8 YEARS TO TRAIN GPT4-1.8T 8 䇗⪐疒耈舘 1/350 鋍穓 GPT4-1.8T

• 29. 2016 2018 2020 2022 2024 TFLOPS Pascal 17,000 Joules/Token Volta 1,200 Joules/Token Ampere 150 Joules/Token Blackwell 0.4 Joules/Token Hopper 10 Joules/Token 45,000X ENERGY REDUCTION IN 8 YEARS TO GENERATE GPT4-1.8T TOKENS 8 䇗⪐疒耈舘 1/45,000 榟䡗 GPT4-1.8T 鍢⩕

• 30. DGX BLACKWELL DGX HOPPER NVLink Domain 72 8 9X NVLink BW (TB/s) 130 7 18X AI FLOPS (PF) 1,440 32 45X Power (kW) 100 10 10X

• 31. NVLink Switch Chip 50B Transistors in TSMC 4NP 72-Ports 400G SerDes 4 NVLinks at 1.8TB/sec 7.2TB/sec Full-Duplex Bandwidth SHARP In-Network Compute – 3.6 TFLOPS FP8

• 33. 1.6X Effective Bandwidth Supercharging Ethernet for Generative AI NVIDIA SPECTRUM-X 憡榟䡗䌋☕䄄保䫠鶡▁㜁私饟 Spectrum-X800 Ethernet Switch BlueField-3 400G SuperNIC

• 34. 2016 2018 2020 2022 2024 TFLOPS Spectrum-X800 51.2T – 256 Radix BF3 400G SuperNIC 10’s of Thousands of GPUs Spectrum-X800 Ultra 51.2T – 512 Radix CX8 800 SuperNIC 100’s of Thousands of GPUs Spectrum-X1600 102.4T – 512 Radix CX9 1600G SuperNIC Millions of GPUs 2024 2025 2026 ANNUAL SPECTRUM-X RHYTHM SCALING TO MILLIONS OF GPUS 䇗䈲 SPECTRUM-X 疒㜱 䴹㷤⮽丨氬蛓⠕ GPU

• 37. NVLink Switch 900 GB/sec CX7 SuperNIC Hopper GPU 6S HBM3 Hopper+ GPU 6S HBM3e Grace CPU BF3 SuperNIC Quantum-X400 InfiniBand Switch 鞴乣╈䑐釨嘘 ٬ ┉䇗疒㜱 ٬ 䤗轱꡿⯆ ٬ ┉⠕凡啶 DATACENTER SCALE • ONE-YEAR RHYTHM • TECHNOLOGY LIMITS • ONE ARCHITECTURE GPU CPU NVLINK NIC SWITCH Hopper Platform

• 38. GPU CPU NVLINK NIC SWITCH NVLink 5 Switch 1800 GB/sec Blackwell GPU 8S HBM3e Spectrum-X800 Ethernet Switch Quantum-X800 Switch Blackwell Platform CX8 SuperNIC 鞴乣╈䑐釨嘘 ٬ ┉䇗疒㜱 ٬ 䤗轱꡿⯆ ٬ ┉⠕凡啶 DATACENTER SCALE • ONE-YEAR RHYTHM • TECHNOLOGY LIMITS • ONE ARCHITECTURE

• 39. GPU CPU NVLINK NIC SWITCH NVLink 5 Switch 1800 GB/sec Blackwell GPU 8S HBM3e Blackwell Ultra GPU 8S HBM3e 12H Spectrum-X800 Ethernet Switch Quantum-X800 Switch Spectrum Ultra X800 Ethernet Switch 512-Radix Blackwell Platform CX8 SuperNIC 鞴乣╈䑐釨嘘 ٬ ┉䇗疒㜱 ٬ 䤗轱꡿⯆ ٬ ┉⠕凡啶 DATACENTER SCALE • ONE-YEAR RHYTHM • TECHNOLOGY LIMITS • ONE ARCHITECTURE

• 40. GPU CPU NVLINK NIC SWITCH Rubin Platform NVLink 6 Switch 3600 GB/sec CX9 SuperNIC 1600 Gb/sec Rubin Ultra GPU 12S HBM4 Vera CPU X1600 IB/Ethernet Switch Rubin GPU 8S HBM4 鞴乣╈䑐釨嘘 ٬ ┉䇗疒㜱 ٬ 䤗轱꡿⯆ ٬ ┉⠕凡啶 DATACENTER SCALE • ONE-YEAR RHYTHM • TECHNOLOGY LIMITS • ONE ARCHITECTURE

• 41. NVLink 5 Switch 1800 GB/sec CX8 SuperNIC Blackwell GPU 8S HBM3e Blackwell Ultra GPU 8S HBM3e 12H NVLink Switch 900 GB/sec CX7 SuperNIC Hopper GPU 6S HBM3 Hopper+ GPU 6S HBM3e BF3 SuperNIC Spectrum-X800 Ethernet Switch Quantum-X400 Infiniband Switch Quantum-X800 Switch Spectrum Ultra X800 Ethernet Switch 512-Radix 2022 2023 2024 2025 2026 2027 GPU CPU NVLINK NIC SWITCH Blackwell Platform Rubin Platform Hopper Platform Grace CPU NVLink 6 Switch 3600 GB/sec CX9 SuperNIC 1600 Gb/sec Rubin Ultra GPU 12S HBM4 Vera CPU X1600 IB/Ethernet Switch Rubin GPU 8S HBM4 鞴乣╈䑐釨嘘 ٬ ┉䇗疒㜱 ٬ 䤗轱꡿⯆ ٬ ┉⠕凡啶 DATACENTER SCALE • ONE-YEAR RHYTHM • TECHNOLOGY LIMITS • ONE ARCHITECTURE

• 42. GB200 Superchip Compute Node NVLink Switch Quantum-X800 Switch Spectrum-X800 Switch BlueField-3 SuperNIC ConnectX-8 SuperNIC HGX B200 NVIDIA BLACKWELL PLATFORM NVIDIA BLACKWELL 䇖⺐

• 53. NVIDIA Isaac Manipulator NVIDIA Omniverse NVIDIA AI Isaac ROS 3.0 Available Now on Github

• 54. NVIDIA Isaac Manipulator SIMATIC Pick AI NVIDIA Omniverse NVIDIA AI

• 56. NVIDIA DRIVE AV NVIDIA Omniverse NVIDIA AI

• 57. GR00T Stack NVIDIA Omniverse NVIDIA AI

• 59. 于榣哆ꪵ⽝