The following is a list that contains general information about

GPUs A graphics processing unit (GPU) is a specialized electronic circuit designed for digital image processing and to accelerate computer graphics, being present either as a discrete video card or embedded on motherboards, mobile phones, personal ...

and video cards made by

AMD Advanced Micro Devices, Inc. (AMD) is an American multinational corporation and technology company headquartered in Santa Clara, California and maintains significant operations in Austin, Texas. AMD is a hardware and fabless company that de ...

, including those made by

ATI Technologies ATI Technologies Inc. was a Canadian semiconductor industry, semiconductor technology corporation based in Markham, Ontario, that specialized in the development of graphics processing units and chipsets. Founded in 1985, the company listed pub ...

before 2006, based on official specifications in table-form.

Field explanations

The headers in the table listed below describe the following: * Model – The marketing name for the GPU assigned by

/ ATI. Note that ATI trademarks have been replaced by AMD trademarks starting with the Radeon HD 6000 series for desktop and AMD FirePro series for professional graphics. * Codename – The internal engineering codename for the GPU. * Launch – Date of release for the GPU. * Architecture – The

microarchitecture In electronics, computer science and computer engineering, microarchitecture, also called computer organization and sometimes abbreviated as μarch or uarch, is the way a given instruction set architecture (ISA) is implemented in a particular ...

used by the GPU. * Fab – Fabrication process. Average feature size of components of the GPU. * Transistors –

Number A number is a mathematical object used to count, measure, and label. The most basic examples are the natural numbers 1, 2, 3, 4, and so forth. Numbers can be represented in language with number words. More universally, individual numbers can ...

transistors A transistor is a semiconductor device used to Electronic amplifier, amplify or electronic switch, switch electrical signals and electric power, power. It is one of the basic building blocks of modern electronics. It is composed of semicondu ...

on the die. * Die size – Physical surface area of the die. * Core config – The layout of the graphics pipeline, in terms of functional units. * Core clock – The reference base and boost (if available) core clock frequency. * Fillrate ** Pixel - The rate at which pixels can be rendered by the raster operators to a display. Measured in pixels/s. ** Texture - The rate at which textures can be mapped by the texture mapping units onto a polygon mesh. Measured in texels/s. * Performance ** Shader operations - How many operations the

pixel shader In computer graphics, a shader is a computer program that calculates the appropriate levels of light, darkness, and color during the rendering of a 3D scene—a process known as '' shading''. Shaders have evolved to perform a variety of s ...

s (or unified shaders in Direct3D 10 and newer GPUs) can perform. Measured in operations/s. ** Vertex operations - The amount of geometry operations that can be processed on the vertex shaders in one second (only applies to Direct3D 9.0c and older GPUs). Measured in vertices/s. * Memory ** Bus type – Type of memory bus utilized. ** Bus width – Maximum bit width of the memory bus utilized. ** Size – Size of the graphics memory. ** Clock – The reference memory

clock frequency Clock rate or clock speed in computing typically refers to the frequency at which the clock generator of a Microprocessor, processor can generate Clock signal, pulses used to Synchronization (computer science), synchronize the operations of it ...

. ** Bandwidth – Maximum theoretical

memory bandwidth Memory bandwidth is the rate at which data can be read from or stored into a semiconductor memory by a processor. Memory bandwidth is usually expressed in units of bytes/second, though this can vary for systems with natural data sizes that are ...

based on bus type and width. * TDP ( Thermal design power) – Maximum amount of heat generated by the GPU chip, measured in Watt. * TBP (Typical board power) – Typical power drawn by the total board, including power for the GPU chip and peripheral equipment, such as

Voltage regulator module A voltage regulator module (VRM), sometimes called processor power module (PPM), is a buck converter that provides the microprocessor and chipset the appropriate supply voltage, converting , or to lower voltages required by the devices, allowi ...

, memory, fans, etc., measured in Watt. * Bus interface – Bus by which the graphics processor is attached to the system (typically an expansion slot, such as PCI, AGP, or

PCIe PCI Express (Peripheral Component Interconnect Express), officially abbreviated as PCIe, is a high-speed standard used to connect hardware components inside computers. It is designed to replace older expansion bus standards such as Peripher ...

). * API support – Rendering and computing APIs supported by the GPU and driver. Due to conventions changing over time, some numerical definitions such as core config, core clock, performance and memory should not be compared one-to-one across generations. The following tables are for reference use only, and do not reflect actual performance.

Video codec acceleration

* R100 – Video Immersion * R200 – Video Immersion II * R300 – Video Immersion II + Video Shader * R410 – Video Shader HD * R420 – Video Shader HD + DXVA * R520 – Avivo Video * R600 – Avivo HD – UVD 1.0 * R700 – UVD 2, UVD 2.2 *

Evergreen In botany, an evergreen is a plant which has Leaf, foliage that remains green and functional throughout the year. This contrasts with deciduous plants, which lose their foliage completely during the winter or dry season. Consisting of many diffe ...

– UVD 2.2 * Northern Islands – UVD 3 (HD 67xx UVD 2.2) * Southern Islands – UVD 3.1, VCE 1.0 *

Sea Islands The Sea Islands are a chain of over a hundred tidal and barrier islands on the Atlantic Ocean coast of the Southeastern United States, between the mouths of the Santee and St. Johns rivers along South Carolina, Georgia and Florida. The la ...

– UVD 4.2, VCE 2.0 *

Volcanic Islands Geologically, a volcanic island is an island of volcano, volcanic origin. The term high island can be used to distinguish such islands from coral island, low islands, which are formed from sedimentation or the Tectonic uplift, uplifting of c ...

– UVD 5.0, 6.0, VCE 3.0 * Arctic Islands – UVD 6.3, VCE 3.4 *

Vega Vega is the brightest star in the northern constellation of Lyra. It has the Bayer designation α Lyrae, which is Latinised to Alpha Lyrae and abbreviated Alpha Lyr or α Lyr. This star is relatively close at only from the Sun, and ...

– UVD 7.0, VCE 4.0 and VCN 1.0 only at AMD Raven Ridge * Navi 1X – VCN 2.0 * Navi 2X – VCN 3.0 * Navi 3X – VCN 3.0

Features overview

API overview

Desktop GPUs

Wonder series

Mach series

Rage series

¹ Pixel pipelines :

Vertex shader In computer graphics, a shader is a computer program that calculates the appropriate levels of light, darkness, and color during the rendering of a 3D scene—a process known as '' shading''. Shaders have evolved to perform a variety of s ...

s : Texture mapping units : Render output units
² OpenGL 1.0 (Generic 2D) is provided through software implementations.

Radeon R100 series

* All models include Direct3D 7.0 and

OpenGL OpenGL (Open Graphics Library) is a Language-independent specification, cross-language, cross-platform application programming interface (API) for rendering 2D computer graphics, 2D and 3D computer graphics, 3D vector graphics. The API is typic ...

1.3 * The R100 cards were originally launched without any numbering as Radeon SDR, DDR, LE and VE; these products were later "rebranded" to their names within the numbered naming scheme, when the Radeon 8000 series was introduced. ¹ Pixel pipelines :

s : Texture mapping units : Render output units

^A First number indicates cards with 32 MB of memory. Second number indicates cards with 64 MB of memory.
^B First number indicates OEM cards. Second number indicates Retail cards.

IGP (3xx series)

* All models are manufactured with a 180 nm fabrication process * All models include Direct3D 7.0 and

1.3 * Based on the Radeon VE ¹ Pixel pipelines :

s : Texture mapping units : Render output units

Radeon R200 series

* All models are manufactured with a 150 nm fabrication process * All models include Direct3D 8.1 and

1.4 ¹

Pixel shader In computer graphics, a shader is a computer program that calculates the appropriate levels of light, darkness, and color during the rendering of a 3D scene—a process known as '' shading''. Shaders have evolved to perform a variety of s ...

s :

s : Texture mapping units : Render output units

IGP (9000 series)

* All models are manufactured with a 150 nm fabrication process * All models include Direct3D 8.1 and

1.4 * Based on the Radeon 9200 ¹

s :

s : Texture mapping units : Render output units

Radeon R300 series

AGP (9000 series, X1000 series)

* All models include Direct3D 9.0 and

2.0 * All models use an AGP 8x interface ¹

s :

Vertex Shader In computer graphics, a shader is a computer program that calculates the appropriate levels of light, darkness, and color during the rendering of a 3D scene—a process known as '' shading''. Shaders have evolved to perform a variety of s ...

s : Texture mapping units : Render output units
² The 256-bit version of the 9800 SE when unlocked to 8-pixel pipelines with third party driver modifications should function close to a full 9800 Pro.

PCIe (X3xx, X5xx, X6xx, X1000 series)

* All models include Direct3D 9.0 and

2.0 * All models use a PCIe ×16 interface ¹

s :

s : Texture mapping units : Render output units

IGP (X2xx, 11xx series)

* All models include Direct3D 9.0 and

2.0 * Based on the Radeon X300 ¹

s :

s : Texture mapping units : Render output units

Radeon R400 series

AGP (X7xx, X8xx)

* All models include AGP 8× * All models include Direct3D 9.0b and

2.0 ¹

s :

s : Texture mapping units : Render output units

PCIe (X5xx, X7xx, X8xx, X1000 series)

* All models include

×16 * All models include Direct3D 9.0b and

2.0 ¹

s :

s : Texture mapping units : Render output units

IGP (X12xx, 21xx)

* All models include Direct3D 9.0b and

2.0 * Based on Radeon X700

Radeon X1000 series

Note that ATI X1000 series cards (e.g. X1900) do not have Vertex Texture Fetch, hence they do not fully comply with the VS 3.0 model. Instead, they offer a feature called "Render to Vertex Buffer (R2VB)" that provides functionality that is an alternative Vertex Texture Fetch. ¹

s :

s : Texture mapping units : Render output units

Radeon HD 2000 series

Radeon HD 3000 series

IGP (HD 3000)

* All Radeon HD 3000 IGP models include Direct3D 10.0 and

3.3 ¹ Unified shaders : Texture mapping units : Render output units
² The clock frequencies may vary in different usage scenarios, as AMD PowerPlay technology is implemented. The clock frequencies listed here refer to the officially announced clock specifications.
³ The sideport is a dedicated memory bus. It is preferably used for a

frame buffer A framebuffer (frame buffer, or sometimes framestore) is a portion of random-access memory (RAM) containing a bitmap that drives a video display. It is a memory buffer containing data representing all the pixels in a complete video frame. Mode ...

All-in-Wonder series

s :

s : Texture mapping units : Render output units
² Unified shaders : Texture mapping units : Render output units

Radeon HD 4000 series

¹ Unified shaders : Texture mapping units : Render output units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.
³ The TDP is reference design TDP values from AMD. Different non-reference board designs from vendors may lead to slight variations in actual TDP.
⁴ All models feature UVD2 and PowerPlay.

IGP (HD 4000)

* All Radeon HD 4000 IGP models include Direct3D 10.1 and OpenGL 2.0 ¹ Unified shaders : Texture mapping units : Render output units
² The clock frequencies may vary in different usage scenarios, as

ATI PowerPlay AMD PowerPlay is the brand name for a set of technologies for the reduction of the energy consumption implemented in several of AMD's graphics processing units and APUs supported by their proprietary graphics device driver "Catalyst". AMD Power ...

technology is implemented. The clock frequencies listed here refer to the officially announced clock specifications.
³ The sideport is a dedicated memory bus. It preferably used for

Radeon HD 5000 series

* The HD5000 series is the last series of AMD GPUs which supports two analog

CRT CRT or Crt most commonly refers to: * Cathode-ray tube, a display * Critical race theory, an academic framework of analysis CRT may also refer to: Law * Charitable remainder trust, United States * Civil Resolution Tribunal, Canada * Columbia ...

-monitors with a single graphics card (i.e. with two RAM-DACs). *

AMD Eyefinity AMD Eyefinity is a brand name for AMD video card products that support multi-monitor setups by integrating multiple (up to six) display controllers on one GPU. AMD Eyefinity was introduced with the Radeon HD 5000 series "Evergreen" in September ...

introduced.

Radeon HD 6000 series

• The Radeon HD 6000 series has a new tesselation engine which is said to double the performance when working with tesselation compared to the previous HD 5000 series.

IGP (HD 6000)

* All models feature the UNB/MC Bus interface * All models lack double-precision FP * With driver Update OpenGL 4.4 available (Last Catalyst 15.12). OpenGL 4.5 available with Crimson Beta (driver version 15.30 or higher). * All models feature Angle independent anisotropic filtering, UVD3, and

capabilities, with up to three outputs. * All models feature 3D Blu-ray Disc acceleration. *Embedded GPUs as part of AMD's

Lynx A lynx ( ; : lynx or lynxes) is any of the four wikt:extant, extant species (the Canada lynx, Iberian lynx, Eurasian lynx and the bobcat) within the medium-sized wild Felidae, cat genus ''Lynx''. The name originated in Middle Engl ...

platform APUs.

Radeon HD 7000 series

IGP (HD 7000)

* All models feature the UNB/MC Bus interface * All models do not support double-precision FP * TeraScale 2 (VLIW5) based APUs feature angle independent anisotropic filtering, UVD3, and Eyefinity capabilities, with up to three outputs. * TeraScale 3 (VLIW4) based APUs feature angle independent anisotropic filtering, UVD3.2, and Eyefinity capabilities, with up to four outputs.

Radeon HD 8000 series

Radeon 200 series

Radeon 300 series

Radeon 400 series

Radeon 500 series

Radeon RX Vega series

Radeon VII series

Radeon RX 5000 series

Radeon RX 6000 series

Radeon RX 7000 series

Radeon RX 9000 series

Mobile GPUs

These GPUs are either integrated into the mainboard or occupy a Mobile PCI Express Module (MXM).

Rage Mobility series

s :

s : Texture mapping units : Render output units.

Mobility Radeon series

s :

s : Texture mapping units : Render output units.

Mobility Radeon X300, X600, X700, X800 series

s :

s : Texture mapping units : Render output units.

Mobility Radeon X1000 series

s :

s : Texture mapping units : Render output units.

Mobility Radeon HD 2000 series

OpenGL 3.3 is possible with latest drivers for all RV6xx. ¹

s :

s : Texture mapping units : Render output units.
² Unified Shaderss : Texture mapping units : Render output units

Mobility Radeon HD 3000 series

¹ Unified Shaders : Texture mapping units : Render output units

Mobility Radeon HD 4000 series

¹ Unified shaders : Texture mapping units : Render output units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.

Mobility Radeon HD 5000 series

¹ Unified shaders : Texture mapping units : Render output units
² The effective data transfer rate of

GDDR5 Graphics Double Data Rate 5 Synchronous Dynamic Random-Access Memory (GDDR5 SDRAM) is a type of synchronous graphics random-access memory (SGRAM) with a high bandwidth ("double data rate") interface designed for use in graphics cards, game con ...

is quadruple its nominal clock, instead of double as it is with other DDR memory.

Radeon HD 6000M series

IGP (HD 6000)

* All models feature the UNB/MC

Bus A bus (contracted from omnibus, with variants multibus, motorbus, autobus, etc.) is a motor vehicle that carries significantly more passengers than an average car or van, but fewer than the average rail transport. It is most commonly used ...

interface * All models lack double-precision FP * All models feature Angle independent anisotropic filtering, UVD3, and Eyefinity capabilities, with up to three outputs.

IGP (HD 6000G)

* All models include

Direct3D Direct3D is a graphics application programming interface (API) for Microsoft Windows. Part of DirectX, Direct3D is used to render three-dimensional graphics in applications where performance is important, such as games. Direct3D uses hardware ...

11,

4.4 and

OpenCL OpenCL (Open Computing Language) is a software framework, framework for writing programs that execute across heterogeneous computing, heterogeneous platforms consisting of central processing units (CPUs), graphics processing units (GPUs), di ...

1.2 * All models feature the UNB/MC

interface * All models lack double-precision FP * All models feature angle independent anisotropic filtering, UVD3 and Eyefinity capabilities, with up to three outputs. * All models feature VLIW5 ¹ Unified shaders : Texture mapping units : Render output units : Compute units
² TDP specified for AMD reference designs, includes CPU power consumption. Actual TDP of retail products may vary.

Radeon HD 7000M series

IGP (HD 7000G)

Radeon HD 8000M series

Radeon M200 series

Radeon M300 series

Radeon M400 series

Radeon M500 series

Radeon 600 series

Radeon RX 5000M series

Radeon RX 6000M series

Radeon RX 7000M series

Workstation GPUs

FireGL series

s :

s : Texture mapping units : Render output units
² Unified shaders : Texture mapping units : Render output units : Compute Units

FireMV (Multi-View) series

s :

s : Texture mapping unit : Render output units
² Unified shaders : Texture mapping unit : Render output units

FirePro (Multi-View) series

FirePro 3D series (V000)

¹ Unified shaders : Texture mapping units : Render output units : Compute Units
² The effective data transfer rate of

is quadruple its nominal clock, instead of double as it is with other DDR memory
³ Windows 7, 8.1, 10 Support for Fire Pro Cards with Terascale 2 and later by firepro driver 15.301.2601

FirePro series (Vx900)

¹ Unified shaders : Texture mapping units : Render output units : Compute Units
² The effective data transfer rate of

is quadruple its nominal clock, instead of double as it is with other DDR memory.
³ Support for Windows 7, 8.1 for OpenGL 4.4 and OpenCL 2.0, when Hardware is prepared with firepro driver 14.502.1045

FirePro Workstation series (Wx000)

* Vulkan 1.0 and OpenGL 4.5 possible for GCN with Driver Update FirePro equal to Radeon Crimson 16.3 or higher. * Vulkan 1.1 possible for GCN with Radeon Pro Software 18.Q1.1 or higher. It might not fully apply to GCN 1.0 or 1.1 GPUs. ¹ Unified shaders : Texture mapping units : Render output units : Compute Units
² The effective data transfer rate of

is quadruple its nominal clock, instead of double as it is with other DDR memory.
³ OpenGL 4.4: support with AMD FirePro driver release 14.301.000 or later, in footnotes of specs

FirePro D-Series

In 2014, AMD released the D-Series specifically for

Mac Pro Mac Pro is a series of workstations and servers for professionals made by Apple Inc. since 2006. The Mac Pro, by some performance benchmarks, is the most powerful computer that Apple offers. It is one of four desktop computers in the current ...

workstations. ¹ Unified shaders : Texture mapping units : Render output units : compute units

FirePro Workstation series (Wx100)

* Vulkan 1.0 and OpenGL 4.5 possible for GCN with Driver Update FirePro equal to Radeon Crimson 16.3 or higher. OpenCL 2.1 and 2.2 possible for all OpenCL 2.0-Cards with Driver Update in Future (Khronos). Linux Support for OpenCL is limited with AMDGPU Driver 16.60 actual to Version 1.2. * Vulkan 1.1 possible for GCN with Radeon Pro Software 18.Q1.1 or higher. It might not fully apply to GCN 1.0 or 1.1 GPUs. ¹ Unified shaders : Texture mapping units : Render output units : compute units
² The effective data transfer rate of

is quadruple its nominal clock, instead of double as it is with other DDR memory.
³ OpenGL 4.4: support with AMD FirePro driver release 14.301.000 or later, in footnotes of specs

FirePro Workstation series (Wx300)

* Vulkan 1.1 possible for GCN with Radeon Pro Software 18.Q1.1 or higher. It might not fully apply to GCN 1.0 or 1.1 GPUs.

Radeon PRO series

Radeon Pro WX x100 series

* Vulkan 1.1 possible for GCN with Radeon Pro software 18.Q1.1 or higher.

Radeon Pro WX x200 series

Radeon Pro Vega series

Radeon Pro 5000 series

Radeon Pro W5000 series

Radeon Pro W6000 series

Radeon Pro W7000 series

Mobile workstation GPUs

Mobility FireGL series

FirePro Mobile series

Radeon Pro WX x100 Mobile series

* Half precision power (FP16) is equal to single precision power (FP32) in 4th GCN generation (in 5th Gen: half precision (FP16) = 2× SP (FP32))

Radeon Pro 400 series

Radeon Pro 500 series

Radeon Pro WX x200 Mobile series

Radeon Pro Vega series

Radeon Pro 5000M series

Radeon Pro W5000M series

Radeon Pro W6000M series

Server GPUs

FireStream series

FirePro Remote series

¹ Unified shaders : Texture mapping units : Render output units : compute units
² The effective data transfer rate of

is quadruple its nominal clock, instead of double as it is with other DDR memory.

FirePro Server series (S000x/Sxx 000)

* Vulkan 1.0 and OpenGL 4.5 possible for GCN with Driver Update FirePro equal to Radeon Crimson 16.3 or higher. OpenGL 4.5 was only in Windows available. Actual Linux Driver support OpenGL 4.5 and Vulkan 1.0, but only OpenCL 1.2 by AMDGPU Driver 16.60. * Vulkan 1.1 possible for GCN with Radeon Pro Software 18.Q1.1 or higher. It might not fully apply to GCN 1.0 or 1.1 GPUs. ¹ Unified shaders : Texture mapping units : Render output units: Compute units
² The effective data transfer rate of

is quadruple its nominal clock, instead of double as it is with other DDR memory.
³ OpenGL 4.4: support with AMD FirePro driver release 14.301.000 or later, in footnotes of specs

Radeon Sky series

¹ Unified shaders : Texture mapping units : Render output units : compute units
² The effective data transfer rate of

is quadruple its nominal clock, instead of double as it is with other DDR memory.

Radeon Pro V series

Radeon Instinct series

Embedded GPUs

¹ Unified shaders : Texture mapping units : Render output units
² CU = Compute units
³ The effective data transfer rate of

is quadruple its nominal clock, instead of double as it is with other DDR memory.

Console GPUs

s :

s : Texture mapping units : Render output units
² Unified shaders : Texture mapping units : Render output units
³ Unified shaders : Texture mapping units : Render output units : RT Cores
⁴ The Latte looks similar to the RV730 used in the Radeon HD4650/4670.
⁵ In most cases, especially in games, half of this data can be considered.

References

External links

TechPowerUp! GPU Database
{{DEFAULTSORT:AMD graphics processing units ATI Technologies ATI graphics processing units Lists of microprocessors *ATI