News
IndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value ChainIndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value Chain
EveryChip

AI accelerators

H100, B200, MI300X, the TPU, Trainium, Gaudi, Cerebras WSE and the NPUs of phones and laptops. 96 chips on EveryChip so far.

An AI accelerator is a chip designed to train or run neural networks, the layered models behind image recognition, speech and large language models. Most of that work is multiplying large tables of numbers, called matrices. Accelerators pack in thousands of multiply units, feed them from fast memory and use low-precision number formats that save power. Nvidia's data centre GPUs, Google's TPU and many start-up chips belong here.

What makes them fast

A neural network layer multiplies a matrix of inputs by a matrix of learned weights. Accelerators have dedicated matrix units, such as Nvidia's tensor cores or the systolic array of Google's TPU, in which numbers flow through a grid of multipliers. They use formats with fewer bits, such as 16-bit, 8-bit and even 4-bit numbers, so each operation costs less energy and more fit on the chip.

Memory and networks matter as much

A large model has billions of weights that must be read again and again. That is why AI accelerators sit beside stacks of High Bandwidth Memory, and why training clusters link thousands of chips with fast networks. Nvidia's H100 of 2022 has 80 billion transistors; its Blackwell B200 joins two dies with 208 billion. Demand for these chips since 2023 has strained supplies of HBM and advanced packaging.

Famous AI accelerator chips

Further reading

🇺🇸 United StatesAMD Instinct AMD's data centre GPU line for deep learning and HPCGPU · GPU architecture · 2017 Intel Xe 🇺🇸 United StatesIntel Xe Graphics architecture for integrated and discrete GPUsGPU · GPU architecture · 2020 Ampere 🇺🇸 United StatesAmpere Nvidia's 2020 GPU architecture behind GeForce RTX 30 and the A100 acceleratorGPU · GPU architecture · 2020 CDNA 🇺🇸 United StatesCDNA AMD microarchitecture for data centre GPU acceleratorsGPU · GPU architecture · 2020 Rubin 🇺🇸 United StatesRubin Nvidia GPU microarchitecture using HBM4 memory and 3 nm processGPU · GPU architecture · 2026 🇺🇸 United StatesHopper Nvidia's datacentre GPU architecture, first shipping in the H100 acceleratorGPU · GPU architecture · 2022 Volta 🇺🇸 United StatesVolta Nvidia's 2017 GPU architecture, first with Tensor Cores for deep learning.GPU · GPU architecture · 2017 🇺🇸 United StatesBlackwell Nvidia's GPU architecture for AI datacentres and gaming, launched in 2024GPU · GPU architecture · 2024 Nvidia L4 🇺🇸 United StatesNvidia L4 Low-profile data centre GPU for AI and videoGPU · GPU architecture Nvidia H100 🇺🇸 United StatesNvidia H100 AI and HPC accelerator based on the Hopper architectureGPU · GPU architecture Nvidia L40S 🇺🇸 United StatesNvidia L40S Data centre GPU for AI and graphics workloadsGPU · GPU architecture · 2023 Nvidia H200 🇺🇸 United StatesNvidia H200 AI GPU with 141 GB of HBM3e memoryGPU · GPU architecture · 2023 GB300 Grace Blackwell 🇺🇸 United StatesGB300 Grace Blackwell Ultra Superchip AI superchip combining Grace CPUs and Blackwell Ultra GPUsSoC · Arm Rubin CPX 🇺🇸 United StatesRubin CPX AI GPU for massive-context inference with GDDR7 memoryGPU · GPU architecture · 2026 Tesla V100 🇺🇸 United StatesTesla V100 Nvidia Volta GPU for AI and HPC data centresGPU · GPU architecture · 2017 Intel Data Center GPU 🇺🇸 United StatesIntel Data Center GPU Max Data centre GPU for HPC and AI workloadsGPU · GPU architecture AMD Instinct MI250X 🇺🇸 United StatesAMD Instinct MI250X Dual-GPU accelerator for supercomputersGPU · GPU architecture AMD Instinct MI100 🇺🇸 United States and 1 moreAMD Instinct MI100 CDNA architecture GPU for high-performance computing and AI workloads.GPU · GPU architecture · 2020 AMD Instinct MI300X 🇺🇸 United StatesAMD Instinct MI300X AI accelerator GPU with 192GB HBM3 memoryGPU · GPU architecture · 2023 AMD Instinct MI350X 🇺🇸 United StatesAMD Instinct MI350X Air-cooled AI accelerator using CDNA4 architecture and 3nm process.AI accelerator · GPU architecture · 2025 AMD Instinct MI300A 🇺🇸 United StatesAMD Instinct MI300A Modular APU combining CPU and GPU tiles for high-performance computing.SoC · x86 · 2023 Biren BR100 🇨🇳 ChinaBiren BR100 AI GPU for data centre compute workloadsGPU · GPU architecture Nvidia H20 🇺🇸 United States and 1 moreNvidia H20 AI accelerator chip for the Chinese marketGPU · GPU architecture B200 🇺🇸 United StatesB200 AI GPU with 208 billion transistors for trillion-parameter modelsGPU · GPU architecture A100 🇺🇸 United StatesA100 Data centre GPU for AI and high-performance computing.GPU · GPU architecture · 2020 Nvidia B300 🇺🇸 United StatesNvidia B300 AI accelerator with dual-die design and 288 GB memoryGPU · GPU architecture AMD Instinct MI325X 🇺🇸 United StatesAMD Instinct MI325X AI accelerator with 256GB HBM3E memoryAI accelerator · GPU architecture AMD Instinct MI355X 🇺🇸 United StatesAMD Instinct MI355X AI accelerator using CDNA 4 architecture on a 3nm process.AI accelerator · GPU architecture · 2025 🇺🇸 United StatesHopper Nvidia datacentre GPU microarchitecture for AI and high-performance computing.GPU · GPU architecture · 2022 🇺🇸 United StatesBlackwell Nvidia GPU microarchitecture for AI and gamingGPU · GPU architecture · 2024

Photo credits on this page

The small pictures above come from Wikimedia Commons under free licences. Some are cropped to fit.

The weekly digest

Every Monday: the chip of the day, new pages on EveryChip, and the conferences and anniversaries of the week ahead.