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

GP5 🇺🇸 United StatesGP5 Analog co-processor for belief propagation and machine learning tasksAI accelerator · Other 🇺🇸 United StatesTensor Processing Unit Google custom chip for neural network machine learningAI accelerator · Other · 2015 Trainium2 🇺🇸 United StatesTrainium2 AWS second-generation AI training accelerator chipAI accelerator · Other · 2024 SambaNova SN40L 🇺🇸 United StatesSambaNova SN40L AI inference chip with three-tier memory architectureAI accelerator · Other · 2023 AWS Inferentia 🇺🇸 United StatesAWS Inferentia AI inference chip designed by Amazon Web ServicesAI accelerator · Other TPU v4 🇺🇸 United StatesTPU v4 Google AI accelerator chip with 3D mesh networkingAI accelerator · Other AWS Trainium 🇺🇸 United StatesAWS Trainium Custom AI accelerator chip for machine learning trainingAI accelerator · Other · 2021 Loihi 2 🇺🇸 United StatesLoihi 2 Second-generation neuromorphic research processor from Intel LabsAI accelerator · Other Ascend 910 🇨🇳 ChinaAscend 910 AI training chip with DaVinci cores and HBM2 memoryAI accelerator · Other · 2019 Sohu 🇺🇸 United StatesSohu Transformer-specific AI accelerator chip by Etched.aiAI accelerator · Other IBM Spyre 🇺🇸 United StatesIBM Spyre AI accelerator chip for IBM Z mainframesAI accelerator · Other · 2024 ATOM 🇰🇷 South KoreaATOM AI inference system on a chip by RebellionsAI accelerator · Other Maia 100 🇺🇸 United StatesMaia 100 Microsoft's first in-house AI accelerator chip for Azure cloud.AI accelerator · Other · 2023 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 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 🇺🇸 United StatesCerebras WSE-3 Turbo Wafer-scale AI processor with 4 trillion transistorsAI accelerator · Other · 2026 Colossus MK2 GC200 🇬🇧 United KingdomColossus MK2 GC200 7nm AI processor chip by GraphcoreAI accelerator · Other · 2026 🇺🇸 United StatesCerebras WSE-2 AI accelerator built from an entire silicon waferAI accelerator · Other TPU v2 🇺🇸 United StatesTPU v2 Google AI accelerator chip for machine learning trainingAI accelerator · Other · 2019 TPU v3 🇺🇸 United StatesTPU v3 Google AI accelerator chip with water coolingAI accelerator · Other Hanguang 800 🇨🇳 ChinaHanguang 800 AI inference chip by Alibaba for cloud and edge computingAI accelerator · Other · 2019 Meta MTIA v2 🇺🇸 United StatesMeta MTIA v2 Custom AI inference accelerator for Meta ranking modelsAI accelerator · Other · 2024 RNGD 🇰🇷 South KoreaRNGD 150W AI inference accelerator chip by FuriosaAIAI accelerator · Other · 2024 Telum II 🇺🇸 United StatesTelum II Mainframe processor for IBM z17 with AI accelerationCPU · Other NorthPole 🇺🇸 United StatesNorthPole Brain-inspired AI inference chip by IBM ResearchAI accelerator · Other Ironwood 🇺🇸 United StatesIronwood Google's seventh-generation AI accelerator for inference workloadsAI accelerator · Other · 2025 Gaudi 2 🇺🇸 United States and 1 moreGaudi 2 AI training accelerator chip by IntelAI accelerator · Other · 2022 Ascend 910C 🇨🇳 ChinaAscend 910C AI accelerator chip by Huawei for data centresAI accelerator · Other NVDLA WorldNVDLA Open-source AI accelerator hardware by NvidiaAI accelerator · Other · 2017 🇺🇸 United StatesTrueNorth IBM neuromorphic chip mimicking brain structureAI accelerator · Other · 2014 Xetal 🇳🇱 NetherlandsXetal Massively parallel image processor from Philips ResearchAI accelerator · Other · 2001 CSX700 🇬🇧 United KingdomCSX700 192-core SIMD coprocessor for high-performance computingAI accelerator · Other · 2001 Geometric Arithmetic P WorldGeometric Arithmetic Parallel Processor A mesh-connected array of single-bit SIMD processing elements for parallel computing.AI accelerator · Other · 1981 WorldElectrochemical RAM Non-volatile memory for analog deep learning accelerationMemory · 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.