News
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

Ampere 🇺🇸 United StatesAmpere Nvidia's 2020 GPU architecture behind GeForce RTX 30 and the A100 acceleratorGPU · GPU architecture · 2020 🇺🇸 United StatesTesla Dojo Tesla's custom supercomputer and D1 chip for training self-driving vision modelsAI accelerator · RISC · 2023 Rubin 🇺🇸 United StatesRubin Nvidia GPU microarchitecture using HBM4 memory and 3 nm processGPU · GPU architecture · 2026 🇺🇸 United StatesBlackwell Nvidia's GPU architecture for AI datacentres and gaming, launched in 2024GPU · GPU architecture · 2024 GP5 🇺🇸 United StatesGP5 Analog co-processor for belief propagation and machine learning tasksAI accelerator · Other Volta 🇺🇸 United StatesVolta Nvidia's 2017 GPU architecture, first with Tensor Cores for deep learning.GPU · GPU architecture · 2017 Hexagon WorldHexagon A family of digital signal processors and neural processing units by Qualcomm.DSP · VLIW · 2006 🇺🇸 United StatesXeon Phi Intel's x86 manycore coprocessor family for supercomputers and HPCCPU · x86 · 2010 Intel Xe 🇺🇸 United StatesIntel Xe Graphics architecture for integrated and discrete GPUsGPU · GPU architecture · 2020 🇺🇸 United StatesPowerVR Graphics and AI accelerator IP for mobile and embedded systemsGPU · GPU architecture · 1985 Neural Engine 🇺🇸 United StatesNeural Engine Apple's on-device AI accelerator for machine learning tasksAI accelerator · Arm · 2017 Pixel Visual Core 🇺🇸 United StatesPixel Visual Core Google’s programmable image and vision processor for Pixel phonesSoC · Arm · 2017 🇺🇸 United StatesAMD Instinct AMD's data centre GPU line for deep learning and HPCGPU · GPU architecture · 2017 Am2045 🇺🇸 United StatesAm2045 Parallel processor array for embedded video and imaging tasksAI accelerator · RISC · 2003 🇺🇸 United StatesTensor Processing Unit Google custom chip for neural network machine learningAI accelerator · Other · 2015 🇺🇸 United StatesHopper Nvidia's datacentre GPU architecture, first shipping in the H100 acceleratorGPU · GPU architecture · 2022 CDNA 🇺🇸 United StatesCDNA AMD microarchitecture for data centre GPU acceleratorsGPU · GPU architecture · 2020 🇺🇸 United StatesNvidia Drive System on a chip family for autonomous vehiclesSoC · Arm · 2015 ATOM 🇰🇷 South KoreaATOM AI inference system on a chip by RebellionsAI accelerator · Other Nvidia H20 🇺🇸 United States and 1 moreNvidia H20 AI accelerator chip for the Chinese marketGPU · GPU architecture Nvidia L4 🇺🇸 United StatesNvidia L4 Low-profile data centre GPU for AI and videoGPU · GPU architecture B200 🇺🇸 United StatesB200 AI GPU with 208 billion transistors for trillion-parameter modelsGPU · GPU architecture Hailo-8 🇮🇱 IsraelHailo-8 Edge AI accelerator with on-chip memory and 26 TOPS performanceAI accelerator · Tensor design Nvidia H100 🇺🇸 United StatesNvidia H100 AI and HPC accelerator based on the Hopper architectureGPU · GPU architecture GB200 Grace Blackwell 🇺🇸 United StatesGB200 Grace Blackwell Superchip Nvidia AI superchip linking Grace CPUs and Blackwell GPUsSoC · Arm 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 MTIA v1 🇺🇸 United StatesMTIA v1 Meta’s first custom AI inference chip for recommendationsAI accelerator · RISC-V · 2020 Tesla V100 🇺🇸 United StatesTesla V100 Nvidia Volta GPU for AI and HPC data centresGPU · GPU architecture · 2017 Maia 200 🇺🇸 United StatesMaia 200 AI inference accelerator on TSMC 3nm processAI accelerator · Tensor design · 2026 Maia 100 🇺🇸 United StatesMaia 100 Microsoft's first in-house AI accelerator chip for Azure cloud.AI accelerator · Other · 2023 Corsair 🇺🇸 United StatesCorsair AI inference accelerator with in-memory computeAI accelerator · Tensor design · 2024 Intel Data Center GPU 🇺🇸 United StatesIntel Data Center GPU Max Data centre GPU for HPC and AI workloadsGPU · GPU architecture Intel Gaudi 3 🇺🇸 United StatesIntel Gaudi 3 AI accelerator chip using Ethernet for scalingAI accelerator · Other · 2024 Inferentia2 🇺🇸 United StatesInferentia2 Second-generation AI inference accelerator from AWSAI accelerator · Other Gaudi 2 🇺🇸 United States and 1 moreGaudi 2 AI training accelerator chip by IntelAI accelerator · Other · 2022 Intel Gaudi 🇺🇸 United StatesIntel Gaudi AI accelerator series from Intel for training and inference workloads.AI accelerator · Other · 2024 Trainium3 🇺🇸 United StatesTrainium3 Fourth-generation AI accelerator chip from AWSAI accelerator · Other · 2025 AMD Instinct MI250X 🇺🇸 United StatesAMD Instinct MI250X Dual-GPU accelerator for supercomputersGPU · GPU architecture 🇺🇸 United StatesCerebras WSE-3 Turbo Wafer-scale AI processor with 4 trillion transistorsAI accelerator · Other · 2026 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 DRIVE Thor 🇺🇸 United StatesDRIVE Thor System-on-chip for autonomous vehicles and robotaxisSoC · Arm Colossus MK2 GC200 🇬🇧 United KingdomColossus MK2 GC200 7nm AI processor chip by GraphcoreAI accelerator · Other · 2026 Blackhole 🇺🇸 United StatesBlackhole AI processor with RISC-V cores and Ethernet scalingAI accelerator · RISC-V · 2023 🇺🇸 United StatesCerebras WSE-2 AI accelerator built from an entire silicon waferAI accelerator · Other

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.