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

Graphics processors

GeForce, Radeon, Mali, Adreno and the graphics chips of consoles and arcades. 176 chips on EveryChip so far.

A graphics processing unit (GPU) is a chip built to draw images: it works out the colour of millions of pixels many times a second. Because each pixel can be worked on at the same time as the others, a GPU has thousands of small arithmetic units running in parallel. Nvidia marketed its GeForce 256 of 1999 as the first GPU, and since the late 2000s GPUs have also been used for science and AI.

How a GPU differs from a CPU

A CPU has a few powerful cores tuned to finish one task quickly. A GPU has many simpler cores grouped into blocks, which Nvidia calls streaming multiprocessors and AMD calls compute units. They run the same instruction on many pieces of data at once. GPUs also have very fast memory, such as GDDR or HBM, because they must feed all those units at the same time.

From games to general computing

Early graphics chips had fixed stages for transforming shapes and filling in pixels. From the early 2000s these became programmable shaders, small programs written by game developers. In 2006 Nvidia's Tesla architecture merged them into one unified design, and its CUDA platform let programmers use the GPU for any parallel work. That opened the way to GPU supercomputers and, after 2012, to deep learning.

Famous GPU chips

Further reading

🇺🇸 United StatesAMD Instinct AMD's data centre GPU line for deep learning and HPCGPU · GPU architecture · 2017 WorldGeForce 700 series Nvidia graphics card series from 2013 using Kepler and Maxwell chipsGPU · GPU architecture · 2013 🇺🇸 United StatesRadeon Pro Professional workstation graphics cards by AMDGPU · GPU architecture · 2016 🇺🇸 United StatesNvidia Tesla Former brand for Nvidia general-purpose GPU computing cardsGPU · GPU architecture · 2007 AMD FirePro 🇺🇸 United StatesAMD FirePro Professional graphics cards for workstations and servers by AMDGPU · GPU architecture CDNA 🇺🇸 United StatesCDNA AMD microarchitecture for data centre GPU acceleratorsGPU · GPU architecture · 2020 🇺🇸 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 GH200 Grace Hopper Sup 🇺🇸 United StatesGH200 Grace Hopper Superchip Combined Arm CPU and Hopper GPU for AI and HPC workloadsCPU · Arm Nvidia H200 🇺🇸 United StatesNvidia H200 AI GPU with 141 GB of HBM3e memoryGPU · GPU architecture · 2023 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 Nvidia H100 🇺🇸 United StatesNvidia H100 AI and HPC accelerator based on the Hopper architectureGPU · GPU architecture A100 🇺🇸 United StatesA100 Data centre GPU for AI and high-performance computing.GPU · GPU architecture · 2020 AMD FireStream 🇺🇸 United StatesAMD FireStream GPGPU co-processor cards for supercomputing and stream processing.GPU · GPU architecture · 2006 🇺🇸 United StatesHopper Nvidia datacentre GPU microarchitecture for AI and high-performance computing.GPU · GPU architecture · 2022

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.