Jump to content

List of AMD graphics processing units

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by 74.131.132.189 (talk) at 00:26, 15 November 2014 (Tonga has 64 ROPs, not 32). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

This page contains general information about the GPUs and video cards by Advanced Micro Devices (AMD), including those by ATI Technologies before 2006, based on official specifications in table form.

DirectX version note

DirectX version indicates which graphics acceleration operations the card implements.

  • DirectX 6.0 - Multitexturing
  • DirectX 7.0 - Hardware Transformation, Clipping and Lighting (TCL/T&L)
  • DirectX 8.0 - Pixel Shader 1.1 & Vertex Shader 1.1
  • DirectX 8.1 - Pixel Shader 1.4 & Vertex Shader 1.1
  • DirectX 9.0 - Shader Model 2.0
  • DirectX 9.0b - Pixel Shader 2.0b & Vertex Shader 2.0
  • DirectX 9.0c - Shader Model 3.0, GPGPU
  • DirectX 9.0L - Windows Vista only, DirectX 9.0c, Shader Model 3.0, Windows Graphics Foundation 1.0, DXVA 1.0, GPGPU
  • Direct3D 10.0 - Windows Vista/Windows 7, Shader Model 4.0, Windows Graphics Foundation 2.0, DXVA 2.0, GPGPU
  • Direct3D 10.1 - Windows Vista SP1/Windows 7, Shader Model 4.1, Windows Graphics Foundation 2.1, DXVA 2.1, GPGPU
  • Direct3D 11.0 - Windows Vista/Windows 7, Shader Model 5.0, Tessellation, Multithreaded rendering, Compute shaders, implemented by hardware and software running Direct3D 9/10/10.1, GPGPU
  • Direct3D 11.1 - Windows 8, Stereoscopic 3D Rendering, GPGPU
  • Direct3D 11.2 - Windows 8.1, Tiled resources, GPGPU
  • Direct3D 12.0 - Windows 8, Windows 8.1, low-level rendering API, GPGPU

OpenGL version note

OpenGL version indicates which graphics acceleration operations the card implements.

  • OpenGL 1.1 - Texture objects
  • OpenGL 1.2 - 3D textures, BGRA and packed pixel formats[1]
  • OpenGL 1.3 - Multitexturing, multisampling, texture compression
  • OpenGL 1.4 - Depth textures
  • OpenGL 1.5 - Vertex Buffer Object (VBO), Occlusion Queries[2]
  • OpenGL 2.0 - GLSL 1.1, MRT, Non Power of Two textures, Point Sprites, Two-sided stencil[2]
  • OpenGL 2.1 - GLSL 1.2, Pixel Buffer Object (PBO), sRGB Textures[2]
  • OpenGL 3.0 - GLSL 1.3, Texture Arrays, Conditional rendering, Frame Buffer Object (FBO)[3]
  • OpenGL 3.1 - GLSL 1.4, Instancing, Texture Buffer Object, Uniform Buffer Object, Primitive restart [4]
  • OpenGL 3.2 - GLSL 1.5, Geometry Shader, Multi-sampled textures [5]
  • OpenGL 3.3 - GLSL 3.30 Backports as much function as possible from the OpenGL 4.0 specification
  • OpenGL 4.0 - GLSL 4.00 Tessellation on GPU, shaders with 64-bit precision
  • OpenGL 4.1 - GLSL 4.10 Developer-friendly debug outputs, compatibility with OpenGL ES 2.0
  • OpenGL 4.2 - GLSL 4.20 Shaders with atomic counters, draw transform feedback instanced, shader packing, performance improvements
  • OpenGL 4.3 - GLSL 4.30 Compute shaders leveraging GPU parallelism, shader storage buffer objects, high-quality ETC2/EAC texture compression, increased memory security, a multi-application robustness extension
  • OpenGL 4.4 - GLSL 4.40 Buffer Placement Control, Efficient Asynchronous Queries, Shader Variable Layout, Efficient Multiple Object Binding, Streamlined Porting of Direct3D applications, Bindless Texture Extension, Sparse Texture Extension
  • OpenGL 4.5 - GLSL 4.50

Video codec acceleration

Field explanations

The fields in the table listed below describe the following:

  • Model – The marketing name for the processor assigned by ATi. Note that the ATi trademark has been replaced by AMD trademark starting with the Radeon HD 6000 series graphics processing units. Professional graphics processing units will switch to the AMD trademark as well.[8]
  • Launch – Date of release for the processor.
  • Model number – Mobility VPUs are based on technology from several technology families. ATi assigns codenames based on an "MXX" model string, which does not relate to the actual technological base of the processor (represented by the R-number). Additionally, ATi is the sole supplier for all Mobility Radeon parts. For this reason, except for the Mobility Radeon 2000 series, all Mobility processors are listed on the same table.
  • Code name – The internal engineering codename for the processor (typically designated by an RNXX name where N is the series number and XX is the market segment for which the product is designed. Additionally, a codename may follow the RVNXX format where "V" typically signifies a processor intended for a mainstream or value market segment).
  • Fab – Fabrication process. Average feature size of components of the processor.
  • Bus interface – Bus by which the graphics processor is attached to the system (typically an expansion slot, such as PCI, AGP, or PCIe).
  • Memory – The reference amount of memory used by the processor.
  • Core clock – The reference core clock frequency (used as some manufacturers adjust clocks lower and higher, this number will always be that listed by ATi).
  • Memory clock – The reference memory clock frequency (used as some manufacturers adjust clocks lower and higher, this number will always be that listed by ATi).
  • Config core – The layout of the graphics pipeline, in terms of functional units. Over time the number, type and variety of functional units in the GPU core has changed significantly; before each section in the list there is an explanation as to what functional units are present in each generation of processors.
  • Performance subsection
    • Shader operations - How many operations the pixel shaders (or unified shaders in DirectX 10 and newer GPUs) can perform. Measured in MOperations/s or GOperations/s.
    • Pixel fillrate - The number of pixels the raster operators can render to a display in one second. Measured in MPixels/s or GPixels/s.
    • Texture fillrate - The rate at which a texture can be mapped by the texture mapping units onto a polygon mesh in one second. Measured in MTextels/s or GTextels/s.
    • Vertex operations - The amount of geometry operations that can be processed on the vertex shaders in one second (only applies to DirectX 9.0c and older GPUs). Measured in MVertices/s.
  • Memory subsection
    • Bandwidth – Maximum theoretical bandwidth for the processor at factory clock with factory bus width. GB=109 bytes.
    • Bus type – Type of memory bus or buses utilized.
    • Bus width – Maximum bit width of the memory bus or buses utilized. This will always be a factory bus width.
  • API compliance section
    • DirectX – Highest version of DirectX with which the hardware is fully compliant.
    • OpenGL – Highest version of OpenGL with which the hardware is fully compliant.
  • Features – Additional features that are not standard as a part of the two graphics libraries.

Comparison table: Desktop GPUs

Wonder Series

Model Launch Fab (µm) Bus interface Memory (KB) Config core1 Memory API compliance
Bus type Bus width (bit)
Wonder MDA/CGA 1986 1 PC/XT 64 1:1 SRAM 8 2D
Wonder EGA 1987 1 PC/XT 256 1:1 SRAM 8 2D
Wonder VGA 1987 1, 0.8 PC/XT, ISA 256, 512
1024
1:1 DRAM 8, 16 2D

1 Pixel pipelines : Render output units

Mach Series

Model Launch Fab (µm) Bus interface Memory (KB) Config core1 Memory API compliance
Bus type Bus width (bit)
Mach 8 1991 0.8 ISA, MCA 512
1024
1:1 DRAM
VRAM
32 2D
Mach 32 1992 0.8 ISA, EISA, VLB
PCI, MCA
1024
2048
1:1 DRAM
VRAM
64 2D
Mach 64 1994 0.6 ISA, VLB, PCI 1024, 2048, 4096, 8192 1:1 DRAM, VRAM, SGRAM 64 2D

1 Pixel pipelines : Render output units

Rage Series

Model Launch Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API compliance
MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
3D Rage November 1995 500 PCI 2 40 40 1:0:1:1 40 40 40 0 0.32 EDO 64 5.0 None2
3D Rage II September 1996 500 PCI 2, 4, 8 60 83 1:0:1:1 60 60 60 0 0.664 SDR 64 5.0 None2
Rage Pro March 1997 350 AGP 2x 8, 16 75 75 1:0:1:1 75 75 75 0 0.6 SDR 64 6.0 1.1
Rage XL[9][10][11] August 1998 350 AGP 2x, PCI 8 125 83 1:0:1:1 Un­known 125 125 0 0.664 SDR 64 6.0 1.2
Rage 128 VR August 1998 250 AGP 2x, PCI 8,32 80 120 2:0:2:2 160 160 160 0 0.96 SDR 64 6.0 1.2
Rage 128 GL August 1998 250 AGP 2x, PCI 32 103 103 2:0:2:2 206 206 206 0 1.648 SDR 128 6.0 1.2
Rage 128 Pro August 1999 250 AGP 4x, PCI 16, 32 125 143 2:0:2:2 250 250 250 0 2.288 SDR 128 6.0 1.2
Rage 128 Ultra August 1999 250 AGP 4x, PCI 16, 32, 64 130 130 2:0:2:2 260 260 260 0 2.088 SDR 128 6.0 1.2
Rage Fury MAXX October 1999 250 AGP 4x, PCI 32 125 143 2:0:2:2 x2 500 500 500 0 4.576 SDR 128 x2 6.0 1.2

1 Pixel pipelines : Vertex shaders : Texture mapping units : Render output units
2 OpenGL 1.0 (Generic 2D) is provided through software implementations.

Radeon R100 (7xxx) Series

Model Launch Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
Radeon VE/7000 Feb 19, 2001 RV100 (piglet) 180 AGP 4x, PCI 32, 64 183 366 1:0:3:1 183 336 549 0 2.688 DDR 64
Radeon LE/7100 (OEM) May 1, 2001 Rage 6 / R100 180 AGP 4x 32 150 300 2:0:6:2 296 296 888 37 4.736 DDR 128
Radeon SDR/7200 June 2000 Rage 6 / R100 180 AGP 4x 32 166 166 2:0:6:2 333 333 996 41.5 2.656 SDR 128
Radeon DDR/7200 April 2000 Rage 6 / R100 180 AGP 4x 32, 64 166/183A 333/366A 2:0:6:2 333/366A 333/366A 966/1098A 41.5/45.75A 5.312/5.856A DDR 128
Radeon DDR/7500 VIVO 2001 Rage 6 / R100 180 AGP 4x, PCI 64 166/183B 333/366B 2:0:6:2 333/366B 333/366B 966/1098B 41.5/45.75B 5.312/5.856B DDR 128
Radeon DDR/7500 VIVO "SE" 2001 Rage 6 / R100 180 AGP 4x, PCI 64 200 400 2:0:6:2 400 400 1200 50.0 6.400 DDR 128
Radeon 7500 LE N/A RV200 (morpheus) 150 AGP 4x, PCI 32, 64 250 350 2:0:6:2 500 500 1500 62.5 5.600 DDR 128
Radeon 7500 Aug 14, 2001 RV200 (morpheus) 150 AGP 4x, PCI 32, 64 290 460 2:0:6:2 580 580 1740 72.5 7.360 DDR 128
Model Launch Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
Fillrate Memory

1 Pixel shaders : Vertex shaders : Texture mapping units : Render output units
A First number indicates cards with 32MB of memory. Second number indicates cards with 64MB 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 DirectX 7.0 and OpenGL 1.4
  • Based on the Radeon VE
Model Launch Code name Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
Radeon 320 May 2002 A3 FSB Un­known 160 200, 266 1:0:3:1 160 160 480 0 1.6, 2.128 DDR 64
Radeon 330 2002 RS200L (wilma) FSB Un­known 150 200, 266 1:0:3:1 150 150 450 0 1.6, 2.128 DDR 64
Radeon 340 2002 RS200 (wilma) FSB Un­known 183 200, 266 1:0:3:1 183 183 549 0 1.6, 2.128 DDR 64

1 Pixel shaders : Vertex shaders : Texture mapping units : Render output units

Radeon R200 (8xxx, 9xxx) Series

  • All models are manufactured with a 150 nm fabrication process
  • All models include DirectX 8.1 and OpenGL 1.4
Model Launch Code name Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
Radeon 8500 Aug 14, 2001 R200 (chaplin) AGP 4x 64, 128 275 550 4:2:8:4 1100 1100 2200 137.5 8.8 DDR 128
Radeon 8500 LE Feb 4, 2002 R200 (chaplin) AGP 4x 64, 128 250 500 4:2:8:4 1000 1000 2000 125 8 DDR 128
Radeon 9000 Aug 1, 2002 RV250 (iris) AGP 4x 64, 128 200 500 4:1:4:4 800 800 800 50 8 DDR 128
Radeon 9000 Pro Aug 1, 2002 RV250 (iris) AGP 4x 64, 128 275 550 4:1:4:4 1100 1100 1100 68.75 8.8 DDR 128
Radeon 9100 2003 R200 (chaplin) AGP 8x, PCI 64, 128 250 500 4:2:8:4 1000 1000 2000 125 8.0 DDR 128
Radeon 9200 Apr 1, 2003 RV280 (argus) AGP 8x, PCI 64, 128, 256 250 400 4:1:4:4 1000 1000 1000 62.5 6.4 DDR 128
Radeon 9200 SE July 2003 RV280 (argus) AGP 8x, PCI 64, 128, 256 200 333 4:1:4:4 800 800 800 50 2.67 DDR 64
Radeon 9250 July 2004 RV280 (argus) AGP 8x, PCI 64, 128, 256 240 400 4:1:4:4 960 960 960 60 6.4 DDR 128

1 Pixel shaders : Vertex shaders : Texture mapping units : Render output units

IGP (9xxx Series)

  • All models are manufactured with a 150 nm fabrication process
  • All models include DirectX 8.1 and OpenGL 1.4
  • Based on the Radeon 9200
Model Launch Code name Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
Radeon 9000 2003 RC350 FSB 16 - 128 300 400 4:1:2:2 600 600 600 0 3.2 DDR 64
Radeon 9100 2003 RS300 (superman) FSB 16 - 128 300 400 4:1:2:2 600 600 600 0 6.4 DDR 128
Radeon 9100 Pro May 3, 2004 RS350 FSB 16 - 128 300 400 4:1:2:2 600 600 600 0 6.4 DDR 128

1 Pixel shaders : Vertex shaders : Texture mapping units : Render output units

Radeon R300 Series

AGP (9xxx Series)

Model Launch Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
Radeon 9500 Oct. 24, 2002 R300 (khan) 150 AGP 8x 64, 128 275 540 4:4:4:8 1100 2200 1100 275 8.64 DDR 128
Radeon 9500 Pro Oct. 24, 2002 R300 (khan) 150 AGP 8x 128 275 540 8:4:8:8 2200 2200 2200 275 8.64 DDR 128
Radeon 9550 2004 RV350 (shivah) 130 AGP 8x 64, 128, 256 250 400 4:2:4:4 1000 1000 1000 125 6.4 DDR 128
Radeon 9550 SE 2004 RV350 (shivah) 130 AGP 8x 64, 128, 256 250 400 4:2:4:4 1000 1000 1000 125 3.2 DDR 64
Radeon 9600 2003 RV350 (shivah) 130 AGP 8x 128, 256 325 400 4:2:4:4 1300 1300 1300 162.5 6.4 DDR 128
Radeon 9600 Pro 2003 RV350 (shivah) 130 AGP 8x 128, 256 400 600 4:2:4:4 1600 1600 1600 200 9.6 DDR 128
Radeon 9600 SE 2003 RV350 (shivah) 130 AGP 8x 64, 128, 256 325 400 4:2:4:4 1300 1300 1300 162.5 3.2 DDR 64
Radeon 9600 XT Sept. 30, 2003 RV360 130 AGP 8x 128, 256 500 600 4:2:4:4 2000 2000 2000 250 9.6 DDR 128
Radeon 9700 Oct. 24, 2002 R300 (khan) 150 AGP 8x 128 275 540 8:4:8:8 2000 2000 2000 275 17.28 DDR 256
Radeon 9700 Pro July 18, 2002 R300 (khan) 150 AGP 8x 128 325 620 8:4:8:8 2600 2600 2600 325 19.84 DDR 256
Radeon 9800 2003 R350 150 AGP 8x 128 325 620 8:4:8:8 2600 2600 2600 325 19.84 DDR 256
Radeon 9800 XL 2003 R350 150 AGP 8x 128 350 620 8:4:8:8 2800 2800 2800 350 19.84 DDR 256
Radeon 9800 XXL[12] Oct. 1, 2003 R360 150 AGP 8x 128 390 676 8:4:8:8 2800 3120 3120 390 21.60 DDR 128
Radeon 9800 Pro 2003 R350, R360 150 AGP 8x 128, 256 380 680, 700 8:4:8:8 3040 3040 3040 380 21.76, 22.40 DDR, GDDR2 256
Radeon 9800 SE[13] N/A R350 150 AGP 8x 128, 256 325, 380[13] 540, 680[13] 4:4:4:8 1300, 1520[13] 2600, 3040[13] 1300, 1520[13] 325, 380[13] 8.64, 21.76[13] DDR 128, 2562[13]
Radeon 9800 XT Sept 9, 2003 R360 150 AGP 8x 256 412 730 8:4:8:8 3296 3296 3296 412 23.36 DDR 256
Model Launch Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
Fillrate Memory

1 Pixel shaders : Vertex Shaders : 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.[14]

PCI-E (X3xx, X5xx, X6xx, X1xxx Series)

  • All models include DirectX 9.0 and OpenGL 2.0
  • All models use a PCI-E x16 interface
Model Launch Code name Fab (nm) Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
Radeon X300 June 21, 2004 RV370 (hari) 110 64, 128 325 400 4:2:4:4 1300 1300 1300 162.5 6.4 DDR 128
Radeon X300 LE June 21, 2004 RV370 (hari) 110 64, 128 325 400 4:2:4:4 1300 1300 1300 162.5 6.4 DDR 128
Radeon X300 SE June 21, 2004 RV370 (hari) 110 64, 128 325 400 4:2:4:4 1300 1300 1300 162.5 3.2 DDR 64
Radeon X300 SE HyperMemory April 4, 2005 RV370 (hari) 110 32, 64, 128 onboard + up to 128 system 325 600 4:2:4:4 1300 1300 1300 162.5 3.2 DDR 64
Radeon X550 June 21, 2005 RV370 (hari) 110 128, 256 400 500 4:2:4:4 1600 1600 1600 200 8 DDR 128
Radeon X600 Pro June 21, 2004 RV380 (vishnu) 130 128, 256 400 600 4:2:4:4 1600 1600 1600 200 9.6 DDR 128
Radeon X600 XT June 21, 2004 RV380 (vishnu) 130 128, 256 500 740 4:2:4:4 2000 2000 2000 250 11.84 DDR 128
Radeon X1050 Dec. 7, 2006 RV370 (hari) 110 128, 256 400 666 4:2:4:4 1600 1600 1600 200 5.328 DDR2 64

1 Pixel shaders : Vertex Shaders : Texture mapping units : Render output units

IGP (X2xx, 11xx Series)

  • All models include DirectX 9.0 and OpenGL 2.0
  • Based on the Radeon X300
Model Launch Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
Radeon Xpress X200 Nov. 8, 2004 RS480 (metallo) 130 HT 16-128 system + 16 sideport 300 200-400 (DDR), 200 (sideport) 4:2:2:2 600 600 600 0 1.6-6.4 system + 0.8 sideport DDR 64, 128
Radeon Xpress 1100 (originally Xpress 200) 2005 RS482 (grayskull) 110 HT 16-128 system 300 200-400 (DDR), 400-800 (DDR2) 4:2:2:2 600 600 600 0 1.6-12.8 system DDR, DDR2 64, 128
Radeon Xpress 1150 (originally Xpress 200 for Intel) March 11, 2005 (Intel), May 23, 2006 (AMD) RC400, RC410, RS400, RS415, RS485 110 HT, FSB 16-128 system 400 200-400 (DDR), 400-800 (DDR2) 4:2:2:2 800 800 800 0 1.6-12.8 DDR, DDR2 64, 128

1Pixel shaders : Vertex Shaders : Texture mapping units : Render output units

Radeon R400 Series

AGP (X7xx, X8xx)

Model Launch Code name Fab (nm) Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
Radeon X700 Sept. 2005 RV410 (alto) 110 128, 256 400 700 8:6:8:8 3200 3200 3200 600 11.2 DDR 128
Radeon X700 Pro March 1, 2005 RV410 (alto) 110 128, 256 425 864 8:6:8:8 3400 3400 3400 637.5 13.824 GDDR3 128
Radeon X800 SE Oct. 2004 R420 (loki) 130 256 425 800 8:6:8:8 3400 6800 3400 637,5 25.6 GDDR3 256
Radeon X800 GT Dec. 6, 2005 R420 (loki) 130 256 475 980 8:6:8:16 3800 7600 3800 712.5 31.36 GDDR3 256
Radeon X800 Dec. 2004 R430 110 256 400 700 12:6:12:16 4800 6400 4800 600 22.4 GDDR3 256
Radeon X800 GTO Dec. 6, 2005 R420 (loki) 130 256 400 980 12:6:12:16 4800 6400 4800 600 31.36 GDDR3 256
Radeon X800 Pro May 5, 2004 R420 (loki) 130 256 475 900 12:6:12:16 5700 7600 5700 712.5 28.8 GDDR3 256
Radeon X800 XL Feb. 2, 2005 R430 110 256 400 980 16:6:16:16 6400 6400 6400 600 31.36 GDDR3 256
Radeon X800 XT May 4, 2004 R420 (loki) 130 256 500 1000 16:6:16:16 8000 8000 8000 750 32 GDDR3 256
Radeon X800 XT PE May 4, 2004 R420 (loki) 130 256 520 1120 16:6:16:16 8320 8320 8320 780 35.84 GDDR3 256
Radeon X850 Pro Feb. 28, 2005 R481 130 256 507 1040 12:6:12:16 6084 8112 6084 760.5 33.28 GDDR3 256
Radeon X850 XT Feb. 28, 2005 R481 130 256 520 1080 16:6:16:16 8320 8320 8320 780 34.56 GDDR3 256
Radeon X850 XT PE Feb. 28, 2005 R481 130 256 540 1180 16:6:16:16 8640 8640 8640 810 37.76 GDDR3 256

1 Pixel shaders : Vertex shaders : Texture mapping units : Render output units

PCI-E (X7xx, X8xx)

Model Launch Code name Fab (nm) Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
Radeon X700 SE Apr. 1, 2005 RV410 (alto) 110 128 400 400
500
4:6:4:8 1600 3200 1600 600 3.2 DDR 64
Radeon X700 LE Dec. 21, 2004 RV410 (alto) 110 128 400 500 8:6:8:8 3200 3200 3200 600 4 DDR 64
Radeon X700 Sept. 2005 RV410 (alto) 110 128, 256 400 500
700
8:6:8:8 3200 3200 3200 600 8
11.2
DDR 128
Radeon X700 Pro Dec. 21, 2004 RV410 (alto) 110 128, 256 425 864 8:6:8:8 3400 3400 3400 637.5 13.824 GDDR3 128
Radeon X700 XT Never Released RV410 (alto) 110 128, 256 475 1050 8:6:8:8 3800 3800 3800 712.5 16.8 GDDR3 128
Radeon X800 GT 128MB Aug. 1, 2005 R423
R480 (thor)
130 128 475 350 8:6:8:16 3800 7600 3800 712.5 22.4 DDR 256
Radeon X800 GT 256MB Aug. 1, 2005 R423
R480 (thor)
130 256 475 980 8:6:8:16 3800 7600 3800 712.5 31.36 GDDR3 256
Radeon X800 Dec. 1, 2004 R430 (thor) 110 128, 256 392 700 12:6:12:16 4704 6272 4704 588 22.4 GDDR3 256
Radeon X800 GTO 128MB Sept. 15, 2005 R423
R480
R430 (thor)
130
110
128 400 700 12:6:12:16 4800 6400 4800 600 22.4 GDDR3 256
Radeon X800 GTO 256MB Sept. 15, 2005 R423
R480
R430 (thor)
130
110
256 400 980 12:6:12:16 4800 6400 4800 600 31.36 GDDR3 256
Radeon X800 Pro May 5, 2004 R423 (thor) 130 256 475 900 12:6:12:16 5700 7600 5700 712.5 28.8 GDDR3 256
Radeon X800 XL Dec. 1, 2004 (256 MB)
May 4, 2005 (512 MB)
R430 (thor) 110 256, 512 MB 400 980 16:6:16:16 6400 6400 6400 600 31.36 GDDR3 256
Radeon X800 XT Dec. 1, 2004 R423 (thor) 130 256 500 1000 16:6:16:16 8000 8000 8000 750 32 GDDR3 256
Radeon X800 XT Platinum Edition May 5, 2004 R423 (thor) 130 256 520 1120 16:6:16:16 8320 8320 8320 780 35.84 GDDR3 256
Radeon X850 Pro Dec. 1, 2004 R480 (thor) 130 256 507 1040 12:6:12:16 6084 8112 6084 760.5 33.28 GDDR3 256
Radeon X850 XT Dec. 1, 2004 R480 (thor) 130 256 520 1080 16:6:16:16 8320 8320 8320 780 34.56 GDDR3 256
Radeon X850 XT CrossFire Master Sept. 29, 2004 R480 (thor) 130 256 520 1080 16:6:16:16 8320 8320 8320 780 34.56 GDDR3 256
Radeon X850 XT Platinum Edition Dec. 21, 2004 R480 (thor) 130 256 540 1180 16:6:16:16 8640 8640 8640 810 37.76 GDDR3 256
Model Launch Code name Fab (nm) Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GBit/s) Bus type Bus width (bit)
Fillrate Memory

1 Pixel shaders : Vertex Shaders : Texture mapping units : Render output units

IGP (X12xx, 21xx)

  • All models include DirectX 9.0b and OpenGL 2.0
  • Based on Radeon X700
Model Launch Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit)
Radeon Xpress X1200 Feb. 28 2007 RS690C (zeus) 80 HT 2.0 256 - 512 350 400 - 800 4:2:4:4 1400 1400 1400 175 6.4 - 12.8 DDR2 128
Radeon Xpress X1250 Aug. 29, 2006 (Intel), Feb. 28, 2007 (AMD) RS600, RS690 (zeus) 80 FSB, HT 2.0 256 - 512 400 400 - 800 4:2:4:4 1600 1600 1600 200 6.4 - 12.8 DDR2 128
Radeon Xpress 2100 March 4, 2008 RS740 (titan) 55 HT 2.0 256 - 512 500 400 - 800 4:2:4:4 2000 2000 2000 250 6.4 - 12.8 DDR2 128

Radeon R500 (X1xxx) Series

    • Note that ATI X1000 Series cards (e.g. X1900) don't 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.
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Clock rate Config core Fillrate Memory TDP (W) API support (version) Release Price (USD)
Core (MHz) Memory (MHz) Pixel (GP/s) Vertex (GV/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Max. DirectX OpenGL
Radeon X1300 Oct. 5, 2005 (PCI-E)
Dec. 1, 2005 (AGP)
RV515 90 107 100 AGP 8x
PCI
PCI-E x16
128
256
450 250 4:2:4:4 1.800 0.225 1.800 8.00 DDR2 128 9.0c 2.0 $
Radeon X1300
HyperMemory
Oct. 5, 2005 RV515 90 107 100 PCI-E x16 128
256
512
450 250 4:2:4:4 1.800 0.225 1.800 8.00 DDR2 64 9.0c 2.0 $
Radeon X1300 PRO Oct. 5, 2005 (PCI-E)
Nov. 1, 2006 (AGP)
RV515 90 107 100 AGP 8x
PCI-E x16
128
256
600 400 4:2:4:4 2.40 0.30 2.40 12.8 DDR2 128 31 9.0c 2.0 $
Radeon X1300 XT Aug. 12, 2006 RV530 90 157 150 AGP 8x
PCI-E x16
128
256
500 400 12:5:4:4 2.000 0.625 2.000 12.8 DDR2 128 22 9.0c 2.0 $
Radeon X1550 Jan. 8, 2007 RV516 80 107 100 AGP 8x
PCI
PCI-E x16
128
256
512
550 400 4:2:4:4 2.200 0.275 2.200 12.8 DDR2 128 27 9.0c 2.0 $
Radeon X1600 PRO Oct. 10, 2005 RV530 90 157 150 AGP 8x
PCI-E x16
128
256
512
500 390 12:5:4:4 2.000 0.625 2.000 12.48 DDR2 128 41 9.0c 2.0 $
Radeon X1600 XT Oct. 10, 2005 (PCI-E) RV530 90 157 150 AGP 8x
PCI-E x16
256
512
590 780 12:5:4:4 2.360 0.7375 2.360 22.08 GDDR3 128 42 9.0c 2.0 $
Radeon X1650 Feb. 1, 2007 RV530 90 157 150 AGP 8x
PCI-E x16
256
512
500 400 12:5:4:4 2.000 0.625 2.000 12.8 DDR2 128 9.0c 2.0 $
Radeon X1650 GT May 1, 2007 (PCI-E)
Oct. 1, 2007 (AGP)
RV560 80 330 230 AGP 8x
PCI-E x16
256
512
400 400 24:8:8:8 3.20 0.80 3.20 12.8 GDDR3 128 9.0c 2.0 $
Radeon X1650 PRO Aug. 23, 2006 (PCI-E)
Oct. 15, 2006 (AGP)
RV535 80 330 131 AGP 8x
PCI-E x16
256
512
600 700 12:5:4:4 2.40 0.75 2.40 22.4 GDDR3 128 44 9.0c 2.0 $
Radeon X1650 XT Oct. 30, 2006 RV560 80 330 230 AGP 8x
PCI-E x16
256
512
525 700 24:8:8:8 4.20 1.05 4.20 22.4 GDDR3 128 55 9.0c 2.0 $
Radeon X1800
CrossFire Edition
Dec. 20, 2005 R520 90 321 288 PCI-E x16 512 600 700 16:8:16:16 9.60 0.90 9.60 46.08 GDDR3 256 113 9.0c 2.0 $
Radeon X1800 GTO Mar. 9, 2006 R520 90 321 288 PCI-E x16 256
512
500 495 12:8:12:8 6.00 1.00 6.00 32.0 GDDR3 256 48 9.0c 2.0 $
Radeon X1800 XL Oct. 5, 2005 R520 90 321 288 PCI-E x16 256 500 500 16:8:16:16 8.00 1.00 8.00 32.0 GDDR3 256 70 9.0c 2.0 $
Radeon X1800 XT Oct. 5, 2005 R520 90 321 288 PCI-E x16 256
512
625 750 16:8:16:16 10.0 1.25 10.0 48.0 GDDR3 256 113 9.0c 2.0 $549
Radeon X1900
CrossFire Edition
Jan. 24, 2006 R580 90 384 352 PCI-E x16 512 625 725 48:8:16:16 10.0 1.25 10.0 46.4 GDDR3 256 100 9.0c 2.0 $
Radeon X1900 GT May 5, 2006 R580 90 384 352 PCI-E x16 256 575 600 36:8:12:12 6.90 1.15 6.90 38.4 GDDR3 256 75 9.0c 2.0 $
Radeon X1900 GT Rev. 2 Sept. 7, 2006 R580 90 384 352 PCI-E x16 256 512 660 36:8:12:12 6.144 1.024 6.144 42.64 GDDR3 256 9.0c 2.0 $
Radeon X1900 XT Jan. 24, 2006 R580 90 384 352 PCI-E x16 256
512
625 725 48:8:16:16 10.0 1.25 10.0 46.4 GDDR3 256 100 9.0c 2.0 $299
Radeon X1900 XTX Jan. 24, 2006 R580 90 384 352 PCI-E x16 512 650 775 48:8:16:16 10.4 1.30 10.4 49.6 GDDR3 256 135 9.0c 2.0 $399
Radeon X1950
CrossFire Edition
Aug. 23, 2006 R580+ 80 384 352 PCI-E x16 512 650 1000 48:8:16:16 10.4 1.30 10.4 46.4 GDDR4 256 9.0c 2.0 $
Radeon X1950 GT Jan. 29, 2007 (PCI-E)
Feb. 10, 2007 (AGP)
RV570 80 330 230 AGP 8x
PCI-E x16
256
512
500 600 36:8:12:12 6.00 1.00 6.00 38.4 GDDR3 256 57 9.0c 2.0 $140
Radeon X1950 PRO Oct. 17, 2006 (PCI-E)
Oct. 25, 2006 (AGP)
RV570 80 330 230 AGP 8x
PCI-E x16
256
512
575 690 36:8:12:12 6.90 1.15 6.90 44.16 GDDR3 256 66 9.0c 2.0 $
Radeon X1950 XT Oct. 17, 2006 (PCI-E)
Feb. 18, 2007 (AGP)
R580+ 80 384 352 AGP 8x
PCI-E 1.0 x16
256
512
625 700 (AGP)
900 (PCI-E)
48:8:16:16 10.0 1.25 10.0 44.8 (AGP)
57.6 (PCI-E)
GDDR3 256 96 9.0c 2.0 $
Radeon X1950 XTX Oct. 17, 2006 R580+ 80 384 352 PCI-E 1.0 x16 512 650 1000 48:8:16:16 10.4 1.30 10.4 64 GDDR4 256 125 9.0c 2.0 $449
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Core (MHz) Memory (MHz) Config core Pixel (GP/s) Vertex (GV/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Max. DirectX OpenGL Release Price (USD)
Clock rate Fillrate Memory TDP (W) API support (version)

1 Pixel shaders : Vertex shaders : Texture mapping units : Render output units

Radeon R600 (HD 2xxx, HD 3xxx) Series

Radeon HD 2xxx

Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Clock rate Config core Fillrate Memory Processing Power
GFLOPS
TDP (W) GFLOPS/W
Single Precision
API support (version) Release Price (USD)
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision Idle Max. DirectX OpenGL OpenCL
Radeon HD 2350 Jun 28, 2007 RV610 65 180 85 PCIe 1.0 ×16
AGP
256 525 400 40:4:4 2.10 2.10 6.40 DDR2 64 42.0 No 20 2.1 10.0 3.3 1.0 ?
Radeon HD 2400 PRO Jun 28, 2007 RV610 65 180 85 PCIe 1.0 ×16
AGP
PCI
128
256
512
525 400 40:4:4 2.10 2.10 6.40 DDR2 64 42.0 No 20 2.1 10.0 3.3 1.0 ?
Radeon HD 2400 XT Jun 28, 2007 RV610 65 180 85 PCIe 1.0 ×16 256 650 500 40:4:4 2.60 2.60 6.40 GDDR3 64 52.0 No 25 2.24 10.0 3.3 1.0 ?
Radeon HD 2600 PRO Jun 28, 2007 RV630 65 390 153 PCIe 1.0 ×16
AGP
256
512
600
600
500
700
120:8:4 2.40 4.80 16.0
21.9
DDR2
GDDR3
128 144.0 No 35 4.11 10.0 3.3 1.0 ?
Radeon HD 2600 XT Jun 28, 2007 RV630 65 390 153 PCIe 1.0 ×16
AGP
256
512
800
800
800
1100
120:8:4 3.20 6.40 22.4
35.2
GDDR3
GDDR4
128 192.0 No 45
50
4.27
3.84
10.0 3.3 1.0 ?
Radeon HD 2900 GT Nov 6, 2007 R600 GT 80 720 420 PCIe 1.0 ×16 256
512
601 800 240:12:12 7.21 7.21 51.2 GDDR3 256 288.5 150 1.92 10.0 3.3 1.0 ?
Radeon HD 2900 PRO Sep 25, 2007 R600 PRO 80 720 420 PCIe 1.0 ×16 512
1024
600
600
800
925
320:16:16 9.6 9.6 51.2
102.4
118.4
GDDR3
GDDR4
256
512
384.0 200 1.92 10.0 3.3 1.0 ?
Radeon HD 2900 XT May 14, 2007 R600 XT 80 720 420 PCIe 1.0 ×16 512
1024
743
743
828
1000
320:16:16 11.9 11.9 105.6
128.0
GDDR3
GDDR4
512 475.5 215 2.2 10.0 3.3 1.0 ?

Radeon HD 3xxx

Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Clock rate Config core Fillrate Memory Processing Power
GFLOPS
TDP (W) GFLOPS/W
Single Precision
API support (version) Release Price (USD)
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision Idle Max. DirectX OpenGL OpenCL
Radeon HD 3410 May 7, 2009 RV610 65 180 85 PCIe 1.0 x16 256 519 396 40:4:4 2.08 2.08 6.34 DDR2 64 41.52 No 20 10.0 3.3 1.0 ?
Radeon HD 3450 Jan 23, 2008 RV620 LE 55 181 67 PCIe 2.0 x16
AGP 8x
256
512
600 500 40:4:4 2.40 2.40 8.00 DDR2 64 48.0 No 25 1.92 10.1 3.3 1.0 ?
Radeon HD 3470 Jan 23, 2008 RV620 PRO 55 181 67 PCIe 2.0 x16 256
512
800 950 40:4:4 3.20 3.20 15.2 DDR2
GDDR3
64 64.0 No 30 2.13 10.1 3.3 1.0 ?
Radeon HD 3550 Aug 4, 2008 RV620 PRO 55 181 67 PCIe 2.0 x16 512 594 396 40:4:4 2.38 2.38 6.34 DDR2 64 47.52 No 30 10.1 3.3 1.0 ?
Radeon HD 3570 Jul 5, 2010 RV620 PRO 55 181 67 PCIe 2.0 x16 512 796 495 40:4:4 3.18 3.18 7.92 DDR2 64 63.68 No 30 10.1 3.3 1.0 ?
Radeon HD 3610 Sep 24, 2009 RV630 PRO 65 390 153 PCIe 1.0 x16 512
1024
594 396 120:8:4 2.38 4.75 12.7 DDR2 128 142.6 No 35 10.1 3.3 1.0 ?
Radeon HD 3650 Jan 23, 2008 RV635 PRO 55 378 132 PCIe 2.0 x16
AGP 8x
256
512
1024
725 800 120:8:4 2.90 5.80 13.0
25.6
DDR2
GDDR3
GDDR4
128 174.0 No 65 2.68 10.1 3.3 1.0 ?
Radeon HD 3730 Oct 5, 2008 RV635 PRO 55 378 135 PCIe 2.0 x16 512 722 405 120:8:4 2.89 5.78 13.0 DDR2 128 173.3 No 65 10.1 3.3 1.0 ?
Radeon HD 3750 Oct 5, 2008 RV635 PRO 55 378 135 PCIe 2.0 x16 512 796 693 120:8:4 3.18 6.37 22.2 GDDR3 128 191.0 No 65 10.1 3.3 1.0 ?
Radeon HD 3830 Apr 1, 2008 RV670 PRO 55 666 192 PCIe 2.0 x16 256 668 828 320:16:16 10.7 10.7 26.5 GDDR3 128 427.5 85.4 75 10.1 3.3 1.0 ?
Radeon HD 3850 Nov 19, 2007 RV670 PRO 55 666 192 PCIe 2.0 x16
AGP 8x
256
512
1024
668 830
900
320:16:16 10.7 10.7 53.1
57.6
GDDR3
GDDR4
256 427.5 85.4 75 10.1 3.3 1.0 179
Radeon HD 3870 Nov 19, 2007 RV670 XT 55 666 192 PCIe 2.0 x16
AGP 8x
512
1024
777
777
900
1126
320:16:16 12.4 12.4 57.6
72.1
GDDR3
GDDR4
256 497.3 99.2 106 4.68 10.1 3.3 1.0 269
Radeon HD 3850 X2 Apr 4, 2008 RV670 PRO 55 666×2 192×2 PCIe 2.0 x16 512×2 668 828 320:16:16×2 10.7×2 10.7×2 53.0×2 GDDR3 256×2 855.0 171 140 6.11 10.1 3.3 1.0 349
Radeon HD 3870 X2 Jan 28, 2008 R680 55 666×2 192×2 PCIe 2.0 x16 512×2 825
825
900
1125
320:16:16×2 13.2×2 13.2×2 57.6×2
72.0×2
GDDR3
GDDR4
256×2 1056 211.2 165 6.4 10.1 3.3 1.0 449

IGP (HD 3xxx)

  • All Radeon HD 3xxx IGP models include DirectX 10.0 and OpenGL 3.3
Model Launch Code name Graphics core Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory3 (MB) Core clock2 (MHz) Config core1 Fillrate Memory GFLOPS Features / Notes
Pixel (GP/s) Texture (GT/s) FP32 (GP/s) Bandwidth (GB/s) Bus type Effective clock (MHz) Bus width (bit)
Radeon 3000 Graphics (760G Chipset) 2009 RS780L[15] RV610 55 205 ~73 (~9 × 8.05) HT 3.0 Up to 512 system 350 40:4:4 1.4 1.4 0.7 20.8 (system) HT (system) N/A N/A 28 AVIVO
Radeon 3100 Graphics (780V Chipset) 2008
Jan 23 (China)
Mar 4 (Worldwide)
RS780C
Radeon HD 3200 Graphics (780G Chipset) RS780 Up to 512 system + optional 128 sideport 500 2 2 1 20.8 (system) + 2.6 (sideport) HT (system) + DDR2-1066 DDR3-1333 (sideport) 1333 (sideport) 16 (sideport) 40 UVD, 8x AA (wide-tent CFAA)
Radeon HD 3300 Graphics (790GX Chipset) Jul 2008 RS780D Up to 512 system + 128 sideport 700 2.8 2.8 1.4 HT (system) + DDR3-1333 (sideport) 56 UVD, PowerPlay

1 Unified shaders : Texture mapping units : Render output units
2 The clock frequencies may vary in different usage scenarios, as ATI 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 preferably used for frame buffer.

All-In-Wonder Series

Model Launch Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API (version)
MPixels/s MTextels/s MVertices/s Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
All-In-Wonder Radeon Jul 31, 2000 R100 180 AGP 4x 32 166 332 2:1:6:2 1 332 996 41.5 5.312 DDR 128 7.0 1.4
All-In-Wonder 7500 Jan 22, 2002 RV200 150 AGP 4x 64 260 360 2:0:6:2 1 520 1560 0 11.52 DDR 128 7.0 1.4
All-In-Wonder VE Dec 2, 2002 RV200 150 AGP 4x 64 250 500 2:0:6:2 1 500 1500 0 8 DDR 128 7.0 1.4
All-In-Wonder 8500 Apr 4, 2002 R200 150 AGP 4x 128 260 550 4:2:8:4 1 1100 2200 137.5 8.8 DDR 128 8.1 1.4
All-In-Wonder 8500 DV Aug 30, 2001 R200 150 AGP 4x 64 230 380 4:2:8:4 1 920 1840 115 6.08 DDR 128 8.1 1.4
All-In-Wonder 9000 Pro Mar 31, 2003 RV250 150 AGP 8x 64, 128 275 550 4:1:4:4 1 1110 1110 68.75 8.8 DDR 128 8.1 1.4
All-In-Wonder 9200 Jan 26, 2004 RV250 150 AGP 8x 128 250 400 4:1:4:4 1 1000 1000 62.5 6.4 DDR 128 8.1 1.4
All-In-Wonder 9200 SE N/A RV250 150 AGP 8x 128 250 332 4:1:4:4 1 1000 1000 62.5 2.656 DDR 64 8.1 1.4
All-In-Wonder 9600 Jan 26, 2004 RV350 130 AGP 8x 128 325 400 4:2:4:4 1 1300 1300 162.5 6.4 DDR 128 9.0 2.0
All-In-Wonder 9600 Pro Aug 05, 2003 RV350 130 AGP 8x 128 400 650 4:2:4:4 1 1600 1600 200 10.4 DDR 128 9.0 2.0
All-In-Wonder 9600 XT Jan 26, 2004 RV360 130 AGP 8x 128 525 650 4:2:4:4 1 2100 2100 262.5 10.4 DDR 128 9.0 2.0
All-In-Wonder 9700 Pro Dec 30, 2002 R300 150 AGP 8x 128 325 620 8:4:8:81 2600 2600 325 19.84 DDR 256 9.0 2.0
All-In-Wonder 9800 Pro Apr 7, 2003 R350 150 AGP 8x 128 380 680 8:4:8:81 3040 3040 380 21.76 DDR 256 9.0 2.0
All-In-Wonder 9800 SE Nov 1, 2003 R350 150 AGP 8x 128 380 680 4:4:4:81 3040 1520 380 10.88 DDR 128 9.0 2.0
All-In-Wonder X600 Pro Sept 21, 2004 RV370 110 AGP 8x 256 400 600 4:2:4:41 1600 1600 200 9.6 DDR 128 9.0 2.0
All-In-Wonder X800 GT Aug 8, 2005 R430 110 PCI-E x16 128 490 980 8:6:8:161 6400 3200 600 31.36 GDDR3 256 9.0b 2.0
All-In-Wonder X800 XL Jul 5, 2005 R430 110 PCI-E x16 256 400 980 16:6:16:161 6400 6400 600 31.36 GDDR3 256 9.0b 2.0
All-In-Wonder X800 XT Sept 9, 2004 R420 130 AGP 8x 256 500 1000 16:6:16:161 8000 8000 750 32 GDDR3 256 9.0b 2.0
All-In-Wonder 2006 Dec 22, 2005 RV515 90 PCI-E x16 256 450 800 4:2:4:41 1800 1800 225 12.8 DDR2 128 9.0c 2.0
All-In-Wonder X1800 XL Nov 21, 2005 R520 90 PCI-E x16 256 500 1000 16:8:16:161 8000 8000 1000 32 GDDR3 256 9.0c 2.0
All-In-Wonder X1900 Jan 24, 2006 R580 90 PCI-E x16 256 500 960 48:8:16:161 8000 8000 1000 30.72 GDDR3 256 9.0c 2.0
All-In-Wonder HD 3650 Jun 28, 2008 RV635 55 PCI-E x16 512 725 1200 120:8:42 2900 5800 N/A 19.2 DDR2 128 10.1 2.1

1 Pixel pipelines : Vertex shaders : Texture mapping units : Render output units
2 Unified shaders : Texture mapping units : Render output units

Radeon R700 (HD 4xxx) Series

Model4 Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory2 Processing Power
GFLOPS
TDP3 (W) GFLOPS/W
Single Precision
API support (version) Release Price (USD)
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision Idle Max. DirectX OpenGL OpenCL
Radeon HD 4350 Sep 30, 2008 RV710 55 242 73 PCIe 2.0 ×16
PCIe 2.0 ×1
AGP 8×
256
512
1024
600 400 80:8:4 2.40 4.80 6.40 DDR2 64 92.0 No 20 4.6 10.1 3.3 1.0 ?
Radeon HD 4550 Sep 30, 2008 RV710 55 242 73 PCIe 2.0 ×16 256
512
1024
600
600
655
800
80:8:4 2.40 4.80 10.5
12.8
DDR2
GDDR3
64 96.0 No 25 3.84 10.1 3.3 1.0 ?
Radeon HD 4570 Nov 25, 2008 RV710 55 242 73 PCIe 2.0 ×16 1024 650 500 80:8:4 2.60 5.20 8.00 DDR2 64 104.0 No 25 10.1 3.3 1.0 ?
Radeon HD 4580 Nov 20, 2011 RV635 PRO 55 378 135 PCIe 2.0 ×16 512 796 693 120:8:4 3.18 6.37 22.2 GDDR3 128 191.0 No 65 10.1 3.3 1.0 ?
Radeon HD 4650 Sep 10, 2008 RV730 PRO 55 514 146 PCIe 2.0 ×16
AGP 8×
256
512
1024
600
650
400 - 500
500
700
320:32:8 4.80
5.20
19.2
20.8
12.8 - 16.0
16.0
22.4
DDR2
GDDR3
GDDR4
64
128
384.0
416.0
No 48 8.0
8.7
10.1 3.3 1.0 ?
Radeon HD 4670 Sep 10, 2008 RV730 XT 55 514 146 PCIe 2.0 ×16
AGP 8×
512
1024
750
750
400 - 500
900
1000
320:32:8 6.00 24.0 12.8 - 16.0
28.8
32.0
DDR2
GDDR3
GDDR4
128 480.0 No 59 8.14 10.1 3.3 1.0 ?
Radeon HD 4730 Jun 8, 2009 RV770 CE 55 956 256 PCIe 2.0 ×16 512 700
750
900
900
640:32:8 5.60
6.00
22.4
24.0
57.6 GDDR5 128 896.0
960.0
179.2
192.0
110 8.15 10.1 3.3 1.0 ?
Radeon HD 4750 Sep 9, 2009 RV740 40 826 137 PCIe 2.0 ×16 512 730 800 640:32:16 11.7 23.4 51.2 GDDR5 128 934.4 80 12 10.1 3.3 1.0 ?
Radeon HD 4770 Apr 28, 2009 RV740 40 826 137 PCIe 2.0 ×16 512 750 800 640:32:16 12.0 24.0 51.2 GDDR5 128 960.0 192.0 80 12 10.1 3.3 1.0 ?
Radeon HD 4810 May 28, 2009 RV770 CE 55 956 256 PCIe 2.0 ×16 512 625
750
900
900
640:32:8 5.00
6.00
20.0
24.0
57.6 GDDR5 128 800.0
960.0
160.0
192.0
95 10.1 3.3 1.0 ?
Radeon HD 4830 Oct 21, 2008 RV770 LE 55 956 256 PCIe 2.0 ×16 512
1024
575 900 640:32:16 9.20 18.4 57.6 GDDR3
GDDR4
256 736.0 147.2 95 7.75 10.1 3.3 1.0 ?
Radeon HD 4850 Jun 25, 2008 RV770 PRO 55 956 256 PCIe 2.0 ×16 512
1024
2048
625 993 800:40:16 10.0 25.0 63.55 GDDR3
GDDR4
256 1000 200.0 110 9.09 10.1 3.3 1.0 ?
Radeon HD 4860 Sep 9, 2009 RV790 GT 55 959 282 PCIe 2.0 ×16 512
1024
700 750 640:32:16 11.2 22.4 96 GDDR5 256 896.0 179.2 130 6.89 10.1 3.3 1.0 ?
Radeon HD 4870 Jun 25, 2008 RV770 XT 55 956 256 PCIe 2.0 ×16 512
1024
2048
750 900 800:40:16 12.0 30.0 115.2 GDDR5 256 1200 240.0 150 8 10.1 3.3 1.0 ?
Radeon HD 4890 Apr 2, 2009 RV790 XT 55 959 282 PCIe 2.0 ×16 1024
2048
850 975 800:40:16 13.6 34.0 124.8 GDDR5 256 1360 272.0 190 7.16 10.1 3.3 1.0 ?
Radeon HD 4850 X2 Nov 7, 2008 R700 55 956×2 256×2 PCIe 2.0 ×16 512×2
1024×2
625 995 800:40:16×2 10.0×2 25.0×2 63.7×2 GDDR3 256x2 2000 400.0 250 8 10.1 3.3 1.0 339
Radeon HD 4870 X2 Aug 12, 2008 R700 55 956×2 256×2 PCIe 2.0 ×16 1024×2 700 900 800:40:16×2 11.2×2 28.0×2 115.2×2 GDDR5 256x2 2400 480.0 286 8.39 10.1 3.3 1.0 399

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 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 & PowerPlay.

IGP (HD 4xxx)

  • All Radeon HD 4xxx IGP models include DirectX 10.1 and OpenGL 3.3
Model Launch Code name Graphics core Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory3 (MB) Core clock2 (MHz) Config core1 Fillrate Memory GFLOPS Features / Notes
Pixel (GP/s) Texture (GT/s) FP32 (GP/s) Bandwidth (GB/s) Bus type Effective clock (MHz) Bus width (bit)
Radeon HD 4200 Graphics (785G Chipset) Aug 2009 RS880 RV620 55 >205 ~73 (~9 × 8.05) HT 3.0 Up to 512 system + optional 128 sideport 500 40:4:4 2 2 1 20.8 (system) + 2.6 (sideport) HT (system) + DDR2-1066 DDR3-1333 (sideport) 1333 (sideport) 16 (sideport) 40 UVD2
Radeon HD 4250 Graphics (880G Chipset) Mar 2010 RS880 560 2.24 2.24 1.12 HT (system) + DDR3-1333 (sideport) 44.8
Radeon HD 4290 Graphics (890GX Chipset) RS880D Up to 512 system + 128 sideport 700 2.8 2.8 1.4 56

1 Unified shaders : Texture mapping units : Render output units
2 The clock frequencies may vary in different usage scenarios, as ATI 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 preferably used for frame buffer.

Evergreen (HD 5xxx) Series

  • The HD5xxx series is the last series of AMD GPUs which supports two analogue CRT-monitors with a single graphics card (i.e. with two RAM-DACs) AMD Eyefinity introduced.
Model4 Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory2 Processing Power
GFLOPS
TDP3 (W) GFLOPS/W
Single Precision
API support (version) Release Price (USD)
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision Idle Max. DirectX OpenGL OpenCL
Radeon HD 5450 Feb 4, 2010 Cedar PRO 40 292 59 PCIe 2.1 x16
PCIe 2.1 x1
512
1024
2048
650
650
650
400
800
800
80:8:4 2.6 5.2 6.4
12.8
DDR2
DDR3
64 104 No 6.4 19.1 5.45 11.0 4.4 1.2 ~50
Radeon HD 5550 Feb 9, 2010 Redwood LE 40 627 104 PCIe 2.1 x16 512
1024
2048
550
550
550
400
800
800
320:16:8 4.4 8.8 12.8
25.6
51.2
DDR2
GDDR3
GDDR5
128 352 No 10 39 9.03 11.0 4.4 1.2 ~70
Radeon HD 5570 Feb 9, 2010 Redwood PRO 40 627 104 PCIe 2.1 x16 512
1024
2048
650
650
400
900
400:20:8 5.2 13.0 12.8
28.8
57.6
DDR2
GDDR3
GDDR5
128 520 No 10 39 13.3 11.0 4.4 1.2 80
Radeon HD 5670 Jan 14, 2010 Redwood XT 40 627 104 PCIe 2.1 x16 512
1024
2048
775
775
800
1000
400:20:8 6.2 15.5 25.6
64.0
GDDR3
GDDR5
128 620 No 15 64 9.69 11.0 4.4 1.2 99
Radeon HD 5750 Oct 13, 2009 Juniper PRO 40 1040 166 PCIe 2.1 x16 512
1024
700
700
1150
1150
720:36:16 11.2 25.2 73.6 GDDR5 128 1008 No 16 86 11.72 11.0 4.4 1.2 129
Radeon HD 5770 Oct 13, 2009 Juniper XT 40 1040 166 PCIe 2.1 x16 512
1024
850
850
1200
1200
800:40:16 13.6 34.0 76.8 GDDR5 128 1360 No 18 108 12.59 11.0 4.4 1.2 159
Radeon HD 5830 Feb 25, 2010 Cypress LE 40 2154 334 PCIe 2.1 x16 1024 800 1000 1120:56:16 12.8 44.8 128.0 GDDR5 256 1792 358.4 25 175 10.24 11.0 4.4 1.2 239
Radeon HD 5850 Sep 30, 2009 Cypress PRO 40 2154 334 PCIe 2.1 x16 1024
2048
725
725
1000
1000
1440:72:32 23.2 52.2 128.0 GDDR5 256 2088 417.6 27 151 13.83 11.0 4.4 1.2 259
Radeon HD 5870 Sep 23, 2009 Cypress XT 40 2154 334 PCIe 2.1 x16 1024
2048
850
850
1200
1200
1600:80:32 27.2 68.0 153.6 GDDR5 256 2720 544 27 188
228
14.47
11.93
11.0 4.4 1.2 379
Radeon HD 5870
Eyefinity Edition5
Mar 11, 2010 Cypress XT 40 2154 334 PCIe 2.1 x16 2048 850 1200 1600:80:32 27.2 68.0 153.6 GDDR5 256 2720 544 27 228 11.93 11.0 4.4 1.2 479
Radeon HD 5970 Nov 18, 2009 Hemlock XT 40 2154×2 334×2 PCIe 2.1 x16 1024×2
2048×2
725
725
1000
1000
1600:80:32×2 46.4 116.0 128×2 GDDR5 256×2 4640 928 51 294 15.78 11.0 4.4 1.2 599
Model4 Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Core (MHz) Memory (MHz) Config core1 Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision Idle Max. GFLOPS/W
Single Precision
DirectX OpenGL OpenCL Release Price (USD)
Clock rate Fillrate Memory2 Processing Power
GFLOPS
TDP3 (W) API support (version)

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 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 cards feature Angle independent anisotropic filtering and Eyefinity capabilities, with up to 3 outputs (Eyefinity edition may allow more simultaneous outputs).
5 The Radeon HD 5870 Eyefinity Edition card allows six mini DisplayPort outputs, all of which can be simultaneously active.[16]

Northern Islands (HD 6xxx) Series

All models up to and including HD 6870 are based on the TeraScale 2 (VLIW5), HD 69xx are based on the TeraScale 3 (VLIW4).

Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory2 Processing Power
GFLOPS
TDP3 (W) GFLOPS/W
Single Precision
API support (version) Release Price (USD)
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision Idle Max. DirectX OpenGL OpenCL
Radeon HD 6350 Apr 7, 2011 Cedar 40 292 59 PCIe 2.1 ×16 512 650 800 80:8:4 2.6 5.2 12.8 DDR3 64 104 No 6.4 19.1 5.45 11.0 4.4 1.2 $23
Radeon HD 6450 Feb 7, 2011 (OEM) Caicos 40 370 67 PCIe 2.1 ×16 512 625
750
533
800
160:8:4 2.5
3.0
5.0
6.0
8.5
12.8
DDR3 64 200
240
No 9 18
27
11.11
8.89
11.0 4.4 1.2 OEM
Radeon HD 6450 Apr 7, 2011 Caicos 40 370 67 PCIe 2.1 ×16 512
1024
2048
625
750
800
900
160:8:4 2.5
3.0
5.0
6.0
12.8
14.4
DDR3 64 200
240
No 9 18
27
11.11
8.89
11.0 4.4 1.2 $55
Radeon HD 6570 Feb 7, 2011 (OEM) Turks PRO 40 716 118 PCIe 2.1 ×16 1024 650 900 480:24:8 5.2 15.6 28.8 DDR3 128 624 No 10 44 14.18 11.0 4.4 1.2 OEM
Radeon HD 6570 Apr 19, 2011 Turks PRO 40 716 118 PCIe 2.1 ×16 2048
4096
650
650
667
1000
480:24:8 5.2 15.6 21.3
64.0
DDR3
GDDR5
128 624 No 11 60 10.4 11.0 4.4 1.2 $79
Radeon HD 6670 Apr 19, 2011 Turks XT 40 716 118 PCIe 2.1 ×16 512
1024
2048
800
800
800
1000
480:24:8 6.4 19.2 25.6
64.0
DDR3
GDDR5
128 768 No 12 66 11.64 11.0 4.4 1.2 $99
Radeon HD 6750 Jan 21, 2011 (OEM) Juniper PRO 40 1040 166 PCIe 2.1 ×16 512
1024
700
700
1150
1150
720:36:16 11.2 25.2 73.6 GDDR5 128 1008 No 16 86 11.72 11.0 4.4 1.2 OEM
Radeon HD 6770 Apr 19, 2011 Juniper XT 40 1040 166 PCIe 2.1 ×16 512
1024
850
850
1200
1050
800:40:16 13.6 34.0 76.8
67.2
GDDR5 128 1360 No 18 108 12.59 11.0 4.4 1.2 ?
Radeon HD 6790 Apr 4, 2011 Barts LE 40 1700 255 PCIe 2.1 ×16 1024 840 1050 800:40:16 13.4 33.6 134.4 GDDR5 256 1344 No 19 150 8.96 11.0 4.4 1.2 $149
Radeon HD 6850 Oct 22, 2010 Barts Pro 40 1700 255 PCIe 2.1 ×16 1024 775 1000 960:48:32 24.8 37.2 128.0 GDDR5 256 1488 No 19 127 11.72 11.0 4.4 1.2 $179
Radeon HD 6870 Barts XT 40 1700 255 PCIe 2.1 ×16 1024 900 1050 1120:56:32 28.8 50.4 134.4 GDDR5 256 2016 No 19 151 13.35 11.0 4.4 1.2 $239
Radeon HD 6930 Dec 2011 Cayman CE 40 2640 389 PCIe 2.1 ×16 1024
2048
750
750
1200
1200
1280:80:32 24.0 60.0 153.6 GDDR5 256 1920 480 18 186 10.32 11.0 4.4 1.2 $180
Radeon HD 6950 Dec 15, 2010 Cayman Pro 40 2640 389 PCIe 2.1 ×16 1024
2048
800
800
1250
1250
1408:88:32 25.6 70.4 160.0 GDDR5 256 2253 563 20 200 11.27 11.0 4.4 1.2 $259
$299
Radeon HD 6970 Cayman XT 40 2640 389 PCIe 2.1 ×16 2048 880 1375 1536:96:32 28.2 84.5 176.0 GDDR5 256 2703 675 20 250 10.81 11.0 4.4 1.2 $369
Radeon HD 6990 Mar 8, 2011 Antilles XT 40 2640×2 389×2 PCIe 2.1 ×16 2048×2 830 1250 1536:96:32×2 26.5×2 79.6×2 160.0×2 GDDR5 256×2 5099 1276.88 37 375 13.6 11.0 4.4 1.2 $699
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Core (MHz) Memory (MHz) Config core1 Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision Idle Max. GFLOPS/W
Single Precision
DirectX OpenGL OpenCL Release Price (USD)
Clock rate Fillrate Memory2 Processing Power
GFLOPS
TDP3 (W) API support (version)

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 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.

IGP (HD 6xxx)

  • All models include DirectX 11, OpenGL 4.4 and OpenCL 1.2
  • All models feature the UNB/MC Bus interface
  • All models do not feature double-precision FP
  • All models feature Angle independent anisotropic filtering, UVD3, and AMD Eyefinity capabilities, with up to three outputs.
  • All models feature 3D Blu-ray Disk acceleration.
  • All models are based on TeraScale 2 (VLIW5)
Model Released Code name Fab (nm) Core Clock (MHz) Config core1 Fillrate Shared Memory GFLOPS Max. Combined TDP2 (W) GFLOPS/W AMD APU
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon HD 6370D Q4 2011 WinterPark 32 443 160:8:4 1.77 3.54 25.6 DDR3-1600 128 142 65 2.18 E2-3200
Radeon HD 6410D Jun 20, 2011[17] WinterPark 600 160:8:4 2.4 4.8 29.9 DDR3-1866 192 65 2.95 A4-3300 A4-3400
Radeon HD 6530D Jun 20, 2011[17] BeaverCreek 443 320:16:8 3.54 7.08 284 65 - 100 2.84 - 4.37 A6-3500 A6-3600 A6-3620 A6-3650 A6-3670K
Radeon HD 6550D Jun 20, 2011 BeaverCreek 600 400:20:8 4.8 12 480 65 - 100 4.8 - 7.38 A8-3800 A8-3820 A8-3850 A8-3870K

1 Unified shaders : Texture mapping units : Render output units
2 TDP specified for AMD reference designs, includes CPU power consumption. Actual TDP of retail products may vary.

Southern Islands (HD 7xxx) Series

  • All models up to including HD 76xx based on TeraScale 2 (VLIW5), HD 77xx - 79xx are based on GCN 1.0 (Graphics Core Next) architecture except the HD 7790 which is based on GCN 1.1.
  • GPUs based on the GCN (Graphics Core Next) architecture, all support Direct X 11.2 with the latest drivers (Initially came with DirectX 11.1 support) and also support the Mantle API.
  • HD 7790 model is designed more like the 7800/7900 models rather than the 7700 featuring 2x primitive rate instead of 1x which is found in the other 7700 cards.[18]
  • Bonaire is in the Caribbean Sea, Malta is in the Mediterranean Sea. These parts are reverse rebranded out of the Sea Island Series to appear in the 7000 Series in 2013.[clarification needed]
  • Bonaire XT is the only card in the 7000 series to support True Audio.
  • The HD 7990 "Malta" was discontinued few months after its release.
  • According to AMD CodeXL, HD 7990's code name is New Zealand.
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory2 Processing Power
GFLOPS
TDP3 (W) GFLOPS/W
Single Precision
API support (version) Release Price (USD)
Core (MHz) Boost (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision Idle Max. DirectX OpenGL OpenCL
Radeon HD 7350 Jan 2012 (OEM) Cedar 40 292 59 PCIe 2.1 ×16 256
512
400
650
400
800
900
80:8:4 1.6
2.6
3.2
5.2
6.4
12.8
DDR2
DDR3
64 104 No 6.4 19.1 5.45 11.0 4.4 1.2 OEM
Radeon HD 7450 Jan 2012 (OEM) Caicos 40 370 67 PCIe 2.1 ×16 512
1024
625
750
533
800
160:8:4 2.5
3.0
5.0
6.0
8.5
12.8
GDDR3 64 200
240
No 9 18 11.11
13.33
11.0 4.4 1.2 OEM
Radeon HD 7470 Jan 2012 (OEM) Caicos 40 370 67 PCIe 2.1 ×16 512
1024
625
750
800
900
160:8:4 2.5
3.0
5.0
6.0
25.6
28.8
GDDR3
GDDR5
64 200
240
No 9 27 7.41
8.89
11.0 4.4 1.2 OEM
Radeon HD 7510 Feb 2013 (OEM) Turks LE 40 716 118 PCIe 2.1 ×16 1024 650 667 320:16:4 2.6 10.4 21.3 GDDR3 128 416 No 11.0 4.4 1.2 OEM
Radeon HD 7570 Jan 2012 (OEM) Turks PRO-L 40 716 118 PCIe 2.1 ×16 512
1024
650 900
1000
480:24:8 5.2 15.6 28.8
64
GDDR3
GDDR5
128 624 No 10
11
44
60
14.18
10.4
11.0 4.4 1.2 OEM
Radeon HD 7670 Jan 2012 (OEM) Turks XT 40 716 118 PCIe 2.1 ×16 512
1024
800 1000 480:24:8 6.4 19.2 64 GDDR5 128 768 No 12 66 11.64 11.0 4.4 1.2 OEM
Radeon HD 7730 April, 2013 Cape Verde LE 28 1500 123 PCIe 3.0 ×16 1024 800 1125 384:24:8 6.4 19.2 25.6
72
GDDR3
GDDR5
128 614.4 38.4 10 47 13.07 11.2 4.4 1.2 $60
Radeon HD 7750 Feb 15, 2012 Cape Verde PRO 28 1500 123 PCIe 3.0 ×16 1024
2048
4096
800
900
800
1125
512:32:16 12.8
14.4
25.6
28.8
25.6
72
GDDR3
GDDR5
128 819.2
921.6
51.2
57.6
10 55
75
14.89
12.29
11.2 4.4 1.2 $110
Radeon HD 7770
GHz Edition
Feb 15, 2012 Cape Verde XT 28 1500 123 PCIe 3.0 ×16 1024
2048
1000 1125 640:40:16 16 40 72 GDDR5 128 1280 80 10 80 16 11.2 4.4 1.2 $160
Radeon HD 7790 Mar 22, 2013 Bonaire XT 28 2080 160 PCIe 3.0 ×16 1024
2048
1000 1500 896:56:16 16.0 56.0 96 GDDR5 128 1792 128 10 85 21.08 11.2 4.4 2.0[19] $150
Radeon HD 7850 Mar 19, 2012 Pitcairn PRO 28 2800 212 PCIe 3.0 ×16 1024
2048
860 1200 1024:64:32 27.52 55.04 153.6 GDDR5 256 1761.28 110.08 10 130 13.548 11.2 4.4 1.2 $250
Radeon HD 7870
GHz Edition
Mar 19, 2012 Pitcairn XT 28 2800 212 PCIe 3.0 ×16 2048 1000 1200 1280:80:32 32 80 153.6 GDDR5 256 2560 160 10 175 14.629 11.2 4.4 1.2 $350
Radeon HD 7870 XT Nov 19, 2012 Tahiti LE 28 4313 352 PCIe 3.0 ×16 2048 925 975 1500 1536:96:32 29.6 88.8 192.0 GDDR5 256 2841.6
2995.2
710.4
748.8
15 185 16.19 11.2 4.4 1.2 $270
Radeon HD 7950 Jan 31, 2012 Tahiti PRO
Tahiti PRO-H
28 4313 352 PCIe 3.0 ×16 3072 800 1250 1792:112:32 25.6 89.6 240 GDDR5 384 2867.2 717 15 200 14.336 11.2 4.4 1.2 $450
Radeon HD 7950 Boost Aug 14, 2012 Tahiti PRO2
Tahiti PRO-H2
28 4313 352 PCIe 3.0 ×16 3072 850 925 1250 1792:112:32 29.6 103.6 240 GDDR5 384 3046.4
3315.2
761.6
828.8
15 225+ 14.734 11.2 4.4 1.2 $330
Radeon HD 7970 Jan 9, 2012 Tahiti XT 28 4313 352 PCIe 3.0 ×16 3072
6144
925 1375 2048:128:32 29.6 118.4 264 GDDR5 384 3788.8 947.2 15 250 15.155 11.2 4.4 1.2 $550
Radeon HD 7970
GHz Edition
Jun 22, 2012 Tahiti XT2 28 4313 352 PCIe 3.0 ×16 3072
6144
1000 1050 1500 2048:128:32 32 128.0 288 GDDR5 384 4096
4300
1024
1075
15 250+ 17.2 11.2 4.4 1.2 $500
Radeon HD 7990 Apr 24, 2013 New Zealand 28 4313 ×2 352 ×2 PCIe 3.0 ×16 3072 ×2 950 1000 1500 2048:128:32 ×2 32 ×2 128 ×2 288 ×2 GDDR5 384 ×2 8200 1894 15 375 21.86 11.2 4.4 1.2 $1000
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Core (MHz) Boost (MHz) Memory (MHz) Config core1 Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision Idle Max. GFLOPS/W
Single Precision
DirectX OpenGL OpenCL Release Price (USD)
Clock rate Fillrate Memory2 Processing Power
GFLOPS
TDP3 (W) API support (version)

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 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.

IGP (HD 7xxx)

  • All models include DirectX 11, OpenGL 4.4 and OpenCL 1.2
  • All models feature the UNB/MC Bus interface
  • All models do not feature double-precision FP
  • All models feature angle independent anisotropic filtering, UVD3.2, and Eyefinity capabilities, with up to four outputs.
  • All models are based on the TeraScale 3 (VLIW4) used in the Radeon HD 69xx Series (Cayman) GPUs.
Model Released Code name Fab (nm) Core Clock (MHz) Config core Fillrate Shared Memory GFLOPS Combined TDP1 (W) GFLOPS/W APU
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Idle Max.
Radeon HD 7480D June 1, 2012 Scrapper 32 723 128:8:4 2.87 5.76 25.6 DDR3-1600 128 185 Un­known 65 Un­known A4-4000 A4-5300
Radeon HD 7540D June 1, 2012 Devastator 32 760 192:12:4 3.02 9.12 29.9 DDR3-1866 128 292 Un­known 65 Un­known A6-5400K
Radeon HD 7560D June 1, 2012 Devastator 32 760 256:16:8 6.08 12.16 29.9 DDR3-1866 128 389 Un­known 65 - 100 Un­known A8-5500 A8-5600K
Radeon HD 7660D June 1, 2012 Devastator 32 760
800
384:24:8 6.08
6.4
18.24
19.2
29.9 DDR3-1866 128 584
614
Un­known 65 - 100 Un­known A10-5700 (760 MHz) A10-5800K (800 MHz)

1TDP specified for AMD reference designs, includes CPU power consumption. Actual TDP of retail products may vary.

Sea Islands (HD 8xxx) Series

  • All models up to including HD 84xx based on TeraScale 2 (VLIW5), HD 85xx and later are based on Graphics Core Next architecture.
  • HD 8570 & HD 8670 will now feature 256 KB L2 read/write cache[20]
  • all non-OEM versions are shifted into Q4' 13[21]
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Clock rate Config core Fillrate Memory Processing Power
GFLOPS
TDP (W) GFLOPS/W
Single Precision
API support (version) Release Price (USD)
Core (MHz) Boost (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision Idle Max. DirectX OpenGL OpenCL
Radeon HD 8350 (OEM) 2013 Cedar 40 292 59 PCIe 2.1 ×16 256
512
400 - 650 400
800
80:8:4 1.6
2.6
3.2
5.2
6.4
12.8
DDR2
DDR3
64 104 No 6.4 19.1 5.45 11.0 4.4 1.2 OEM
Radeon HD 8450 (OEM) 2013 Caicos 40 370 67 PCIe 2.1 ×16 512 625 533 160:8:4 2.5 5.0 8.53 DDR3 64 200 No 9 18 8 11.0 4.4 1.2 OEM
Radeon HD 8470 (OEM) 2013 Caicos 40 370 67 PCIe 2.1 ×16 1024 750 800 160:8:4 3.0 6.0 25.6 GDDR5 64 240 No 9 35 8 11.0 4.4 1.2 OEM
Radeon HD 8490 (OEM) 2013 Caicos 40 370 67 PCIe 2.1 ×16 1024 875 900 160:8:4 3.5 7.0 28.8 GDDR5 64 280 No 9 35 8 11.0 4.4 1.2 OEM
Radeon HD 8570 (OEM) 2013 Oland 28 1040 90 PCIe 3.0 ×8 2048 730 900
1150
384:24:8 6.4 19.2 28.8
72
DDR3
GDDR5
128 560 35 12 66 11.64 11.1 4.4 2.0[19] OEM
Radeon HD 8670 (OEM) 2013 Oland 28 1040 90 PCIe 3.0 ×8 2048 1000 1150 384:24:8 8 24 72 GDDR5 128 768 48 16 86 11.72 11.1 4.4 2.0[19] OEM
Radeon HD 8730 Sep 5th, 2013 Cape Verde LE 28 1500 123 PCIe 3.0 ×16 1024 800 1125 384:24:8 6.4 19.2 72 GDDR5 128 614.4 44.8 10 47 13.07 11.1 4.4 1.2
Radeon HD 8760 (OEM) 2013 Cape Verde XT 28 1500 123 PCIe 3.0 ×16 2048 1000 1125 640:40:16 16 40 72 GDDR5 128 1280 80 16 80 16 11.1 4.4 1.2 OEM
Radeon HD 8770 2013 Bonaire XT 28 2080 160 PCIe 3.0 ×16 2048 1000 1500 896:56:16 16.0 56.0 96 GDDR5 128 1792 128 10 85 21.08 11.1 4.4 1.2 ?
Radeon HD 8870 (OEM)[22] 2013 Pitcairn XT 28 2800 212 PCIe 3.0 x16 2048 1000 1200 1280:80:32 32 80 153.6 GDDR5 256 2560 160 15 150 17.06 11.1 4.4 1.2 OEM
Radeon HD 8950 (OEM) 2013 Tahiti Pro 28 4313 352 PCIe 3.0 x16 3072 850 925 1250 1792:112:32 27.2
29.6
95.2
103.6
240 GDDR5 384 3046.4
3315.2
761.6
828.8
15 225+ 14.734 11.1 4.4 2.0[19] OEM
Radeon HD 8970 (OEM) 2013 Tahiti XT2 28 4313 352 PCIe 3.0 x16 3072 1000 1050 1500 2048:128:32 32
33.6
128.0
134.4
288 GDDR5 384 4096
4301
1024
1075
15 250+ 17.2 11.1 4.4 1.2 OEM
Radeon HD 8990 (OEM) 2013 Malta 28 4313 x2 352 x2 PCIe 3.0 ×16 3072 x2 950 1000 1500 2048:128:32 x2 32 x2 128 x2 288 x2 GDDR5 384 x2 7782
8192
1946
2048
15 375 21.86 11.1 4.4 1.2 OEM
Model Launch Code name Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Core (MHz) Boost (MHz) Memory (MHz) Config core Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision Idle Max. GFLOPS/W
Single Precision
DirectX OpenGL OpenCL Release Price (USD)
Clock rate Fillrate Memory Processing Power
GFLOPS
TDP (W) API support (version)

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 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.

Sea Islands (Rx 2xx) Series

1 Unified Shaders : Texture Mapping Units : Render Output Units
2 Pixel fillrate is calculated as the number of ROPs multiplied by the base core clock speed.
3 Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
4 Single precision performance is calculated as two times the number of shaders multiplied by the base core clock speed.
5 Double precision performance of Hawaii is 1/8 of single precision performance,[23] Tahiti is 1/4 of single precision performance, others 28 nm chip is 1/16 of single precision performance.
6 Base clock of R9 290 and R9 290X will maintain at 947 MHz and 1000 MHz before reaching 95 °C, respectively.[24]
7 The R9 285 utilizes loss-less colour compression which can increase effective memory bandwidth (relative to GCN 1.0 and 1.1 cards) in certain situations.[25][26]
8 Support for OpenCL 2.0 has been extended to the 200 Series' R7 and R9 models[19].

Model Launch Codename Architecture Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory Processing Power
GFLOPS
TDP (W) GFLOPS/W Single Precision API support (version) TrueAudio Release Price (USD)
Core (MHz) Boost (MHz) Memory (MT/s) Pixel (GP/s)2 Texture (GT/s)3 Bus width (bit) Bus type Bandwidth (GB/s) Single Precision4 Double Precision5 Idle Max. DirectX OpenGL OpenCL Mantle
Radeon R5 210 Un­known Cedar Terascale 2 40 292 59 PCIe 2.0 ×16 256 400 Un­known 900 80:8:4 1.6 3.2 64 DDR3 7.2 64 No Un­known 19 3.4 11.0 4.4 1.2 No No Un­known
Radeon R5 220 Un­known Caicos PRO-L Terascale 2 40 370 67 PCIe 2.0 ×16 1024 625 650 1066 160:8:4 2.5 5 64 DDR3 8.53 200 No Un­known 18 11.1 11.0[27] 4.4 1.2 No No Un­known
Radeon R5 230 Apr 3, 2014[28] Caicos Terascale 2 40 370 67 PCIe 2.0 ×16 1024
2048
625[29] 1066 160:8:4 2.5 5 64 DDR3 8.53 200 No Un­known 19[30] 8 11.0[31] 4.4 1.2 No No Un­known
Radeon R5 235 Un­known Caicos XT Terascale 2 40 370 67 PCIe 2.0 ×16 1024 775 Un­known 1800 160:8:4 3.1 6.2 64 DDR3 14.4 248 No Un­known 35 7.1 11.0[27] 4.4 1.2 No No Un­known
Radeon R5 235X Un­known Caicos XT Terascale 2 40 370 67 PCIe 2.1 ×16 1024 875 Un­known 1800 160:8:4 3.5 7.0 64 DDR3 14.4 280 No Un­known 18 15.6 11.0[27] 4.4 1.2 No No Un­known
Radeon R5 240 Un­known Oland GCN 1.0 28 1040 90 PCIe 3.0 ×16 2048 730 780 1800 320:20:8 5.84 14.6 128 DDR3
GDDR5
22.8
57.6
467.2 Un­known Un­known 50 9.3 11.2[27] 4.4 1.2 Yes No Un­known
Radeon R7 240 Oct 8, 2013 Oland PRO GCN 1.0 28 1040 90 PCIe 3.0 ×16 2048 730 780 1800
4500
320:20:8 5.84 14.6 128 DDR3
GDDR5
28.8
72
467.2
499.2
29.2 Un­known 30 15.6 12.0[32] 4.4 2.0 Yes[33] No $69
Radeon R7 250 Oct 8, 2013 Oland XT GCN 1.0 28 1040 90 PCIe 3.0 ×16 1024
2048
1000 1050 1800
4600
384:24:8 8 24 128 DDR3
GDDR5
73.6 768
806.4
48 Un­known 75 11.8 12.0[32] 4.4 2.0 Yes No $89
Radeon R7 250X Feb 10, 2014 Cape Verde XT GCN 1.0 28 1500 123 PCIe 3.0 ×16 1024
2048
1000 4500 640:40:16 16 40 128 GDDR5 72 1280 80 Un­known 95 13.5 12.0[32] 4.4 2.0 Yes No $99
Radeon R7 260 Dec 17, 2013 Bonaire GCN 1.1 28 2080 160 PCIe 3.0 ×16 1024 1000 6000 768:48:16 16 48 128 GDDR5 96 1536 96 Un­known 95 16.2 12.0[32] 4.4 2.0 Yes Yes[34] $109
Radeon R7 260X Oct 8, 2013 Bonaire XTX GCN 1.1 28 2080 160 PCIe 3.0 ×16 1024
2048
1100 6500 896:56:16 17.6 61.6 128 GDDR5 104 1971.2 123.2 Un­known 115 17.1 12.0[32] 4.4 2.0 Yes Yes[35] $139
Radeon R7 265 Feb 13, 2014 Curaçao PRO GCN 1.0 28 2800 212 PCIe 3.0 ×16 2048 900 925 5600 1024:64:32 28.8 57.6 256 GDDR5 179.2 1843.2 115.2 Un­known 150 12.3 12.0[32] 4.4 2.0 Yes No $149
Radeon R9 270 Nov 13, 2013 Curaçao XT GCN 1.0 28 2800 212 PCIe 3.0 ×16 2048 900 925 5600 1280:80:32 28.8 72 256 GDDR5 179.2 2304
2368
144
148
Un­known 150 15.4 12.0[36] 4.4 2.0 Yes No $179
Radeon R9 270X Oct 8, 2013 Curaçao XT GCN 1.0 28 2800 212 PCIe 3.0 ×16 2048
4096
1000 1050 5600 1280:80:32 32 80 256 GDDR5 179.2 2560
2688
160
168
Un­known 180 14.2 12.0[36] 4.4 2.0 Yes No $199
Radeon R9 280 Mar 4, 2014 Tahiti PRO GCN 1.0 28 4313 352 PCIe 3.0 ×16 3072 827 933 5000 1792:112:32 26.5 92.6 384 GDDR5 240 2964
3343.9
741
836
Un­known 250 14.8 12.0[36] 4.4 2.0 Yes No $249
Radeon R9 280X Oct 8, 2013 Tahiti XT2
Tahiti XTL[37]
GCN 1.0 28 4313 352 PCIe 3.0 ×16 3072 850 1000 6000 2048:128:32 27.2 109 384 GDDR5 288 3481.6
4096
870.4
1024
Un­known 250 13.9 12.0[36] 4.4 2.0 Yes No $299
Radeon R9 285 Sep 2, 2014 Tonga PRO GCN 1.2 28 5000[26] 359[26] PCIe 3.0 ×16 2048 918 Un­known 5500 1792:112:64 29.4 102.8 256 GDDR5 176 3290 206.6[38] Un­known 190 17.3 12.0[36] 4.4 2.0 Yes Yes $249
Radeon R9 290 Nov 5, 2013 Hawaii PRO GCN 1.1 28 6200[39] 438 PCIe 3.0 ×16 4096 up to 9476 5000 2560:160:64 60.608 151.52 512 GDDR5 320 4848.6 606.1 Un­known 275 17.6 12.0[36] 4.4 2.0 Yes Yes $399
Radeon R9 290X Oct 24, 2013 Hawaii XT GCN 1.1 28 6200[39] 438 PCIe 3.0 ×16 4096
8192
up to 10006 5000 2816:176:64 64 176 512 GDDR5 320 5632 704 Un­known 290 19.4 12.0[36] 4.4 2.0 Yes Yes $549
Radeon R9 295X2 [40] Apr 8, 2014 Vesuvius GCN 1.1 28 2× 6200 2× 438 PCIe 3.0 ×16 2× 4096 1018 5000 2× 2816:176:64 2× 65.152 2× 179.168 2× 512 GDDR5 2× 320 11466.752 1433.344 Un­known 500 22.9 12.0[36] 4.4 2.0 Yes Yes $1499
Model Launch Codename Architecture Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory Processing Power
GFLOPS
TDP (W) GFLOPS/W Single Precision API support (version) True Audio Release Price (USD)
Core (MHz) Boost (MHz) Memory (MT/s) Pixel (GP/s)2 Texture (GT/s)3 Bus width (bit) Bus type Bandwidth (GB/s) Single Precision4 Double Precision5 Idle Max. DirectX OpenGL OpenCL Mantle

1 Unified Shaders : Texture Mapping Units : Render Output Units
2 Pixel fillrate is calculated as the number of ROPs multiplied by the base core clock speed.
3 Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
4 Single precision performance is calculated as two times the number of shaders multiplied by the base core clock speed.
5 Double precision performance of Hawaii is 1/8 of single precision performance,[23] Tahiti is 1/4 of single precision performance, others 28 nm chip is 1/16 of single precision performance.
6 Base clock of R9 290 and R9 290X will maintain at 947 MHz and 1000 MHz before reaching 95 °C, respectively.[24]
7 The R9 285 utilizes loss-less colour compression which can increase effective memory bandwidth (relative to GCN 1.0 and 1.1 cards) in certain situations.[25][26]

Pirate Islands (Rx 3xx) Series

1 Unified Shaders : Texture Mapping Units : Render Output Units
2 Pixel fillrate is calculated as the number of ROPs multiplied by the base core clock speed.
3 Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
4 Single precision performance is calculated as two times the number of shaders multiplied by the base core clock speed.

Model Launch Codename Architecture Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory Processing Power
GFLOPS
TDP (W) GFLOPS/W Single Precision API support (version) TrueAudio Release Price (USD)
Core (MHz) Boost (MHz) Memory (MT/s) Pixel (GP/s)2 Texture (GT/s)3 Bus width (bit) Bus type Bandwidth (GB/s) Single Precision4 Double Precision5 Idle Max. DirectX OpenGL OpenCL Mantle
Radeon R9 360 1H 2015 Iceland PRO GCN 1.2? 20? Un­known Un­known PCIe 3.0 ×16 Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known 12.0 Un­known Un­known Yes Un­known Un­known
Radeon R9 360X 1H 2015 Iceland PRO GCN 1.2? 20? Un­known Un­known PCIe 3.0 ×16 Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known 12.0 Un­known Un­known Yes Un­known Un­known
Radeon R9 370 1H 2015 Treasure PRO GCN 1.2? 20? Un­known Un­known PCIe 3.0 ×16 Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known 12.0 Un­known Un­known Yes Un­known Un­known
Radeon R9 370X 1H 2015 Treasure XT GCN 1.2? 20? Un­known Un­known PCIe 3.0 ×16 Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known 12.0 Un­known Un­known Yes Un­known Un­known
Radeon R9 380 1H 2015 Bermuda PRO GCN 1.2? 20? Un­known Un­known PCIe 3.0 ×16 Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known 12.0 Un­known Un­known Yes Un­known Un­known
Radeon R9 380X 1H 2015 Bermuda XT GCN 1.2? 20? Un­known Un­known PCIe 3.0 ×16 Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known Un­known 12.0 Un­known Un­known Yes Un­known Un­known
Radeon R9 390 1H 2015 Fiji PRO GCN 1.2? 20? Un­known Un­known PCIe 3.0 ×16 3072 1000 Un­known 1250 3520:220:? Un­known Un­known 3072 HBM 480 7040 Un­known Un­known Un­known Un­known 12.0 Un­known Un­known Yes Un­known Un­known
Radeon R9 390X 1H 2015 Fiji XT GCN 1.2? 20? Un­known Un­known PCIe 3.0 ×16 4096 1000 Un­known 1250 4096:256:? Un­known Un­known 4096 HBM 640 8192 Un­known Un­known Un­known Un­known 12.0 Un­known Un­known Yes Un­known Un­known
Model Launch Codename Architecture Fab (nm) Transistors (Million) Die Size (mm2) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory Processing Power
GFLOPS
TDP (W) GFLOPS/W Single Precision API support (version) True Audio Release Price (USD)
Core (MHz) Boost (MHz) Memory (MT/s) Pixel (GP/s)2 Texture (GT/s)3 Bus width (bit) Bus type Bandwidth (GB/s) Single Precision4 Double Precision5 Idle Max. DirectX OpenGL OpenCL Mantle

1 Unified Shaders : Texture Mapping Units : Render Output Units
2 Pixel fillrate is calculated as the number of ROPs multiplied by the base core clock speed.
3 Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
4 Single precision performance is calculated as two times the number of shaders multiplied by the base core clock speed.
5 Double precision performance of Hawaii is 1/8 of single precision performance,[23] Tahiti is 1/4 of single precision performance, others 28 nm chip is 1/16 of single precision performance.

Comparison table: Mobile GPUs

Rage Mobility Series

Model Launch Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Hardware T&L Config core1 Fillrate Memory API compliance (version) Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
Rage LT (Rage II) Nov 1996 500 PCI 4 60 66 No 0:1:1:1 0.06 0.06 0.53 EDO, SDR, SGR 64 5 N/A
Rage LT Pro (Rage Pro) Nov 1997 350 AGP, PCI 8 75 100 No 0:1:1:1 0.075 0.075 0.80 EDO, SDR, SGR 64 6 1.1 Motion Compensation
Rage Mobility M/P (Rage 128) Nov 1998 250 AGP, PCI 8 90 Un­known No 0:2:2:2 0.18 0.18 Un­known SDR, SGR 64 Un­known Un­known M had 4 MB of integrated SDRAM, P had none. IDCT, Motion Compensation.
Rage Mobility M1 (Rage 128) Feb 1999 250 AGP, PCI 8 90 90 No 0:2:2:2 0.18 0.18 0.72 SDR 64 6 1.2 M1 had 8 MB of integrated SDRAM, P had none. IDCT, Motion Compensation.
Rage 128 GL Aug 1998 250 AGP, PCI 32 103 103 No 0:2:2:2 0.206 0.206 1.65 SDR 128 6 1.2
Rage Mobility 128 (Rage 128 Pro) Oct 1999 250 AGP, PCI 16 105 105 No 0:2:2:2 0.21 0.21 2.28 SDR 128 6 1.2 IDCT, Motion Compensation
Rage Mobility M3 (AGP 4x) (Rage 128 Pro) Oct 1999 250 AGP, PCI 16 105 105 No 0:2:2:2 0.21 0.21 2.28 SDR 128 6 1.2 M3 had 8 MB of integrated SDRAM, IDCT, Motion Compensation.
Rage Mobility M4 (AGP 4x) (Rage 128 Pro) Oct 1999 250 AGP, PCI 32 105 105 No 0:2:2:2 0.21 0.21 2.28 SDR 128 6 1.2 M4 had 16 MB of integrated SDRAM, IDCT, Motion Compensation.

1 Vertex shaders : Pixel shaders : Texture mapping units : Render output units

Mobility Radeon Series

Model Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API compliance (version) Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
Mobility Radeon 7000 Feb 2001 M6 RV100 180 AGP 4x 8
16
32
144
167
144
183
0:1:3:1 0.167 0.5 1.464
2.928
SDR
DDR
32
64
6 1.3
Mobility Radeon 7500 Dec 2001 M7 RV200 150 AGP 4x 32
64
280 200 0:2:6:2 0.56 1.68 3.2
6.4
DDR 64
128
7 1.3 PowerPlay II, DX7 T&L
Mobility Radeon 9000 Aug 2002 M9 RV250 150 AGP 4x 32
64
250 200 1:4:4:4 1.0 1.0 3.2
6.4
DDR 64
128
8.1 1.4 PowerPlay 3.0, Fullstream
Mobility Radeon 9200 Mar 2003 M9+ RV280 150 AGP 8x 32
64
250
250
200
220
1:4:4:4 1.0 1.0 3.2/6.4
3.52/7.04
DDR 64
128
8.1 1.4 PowerPlay 3.0, Fullstream
Mobility Radeon 9500 2004? M11 RV360 130 AGP 8x 64 Un­known Un­known 2:4:4:4 Un­known Un­known Un­known DDR 64
128
9.0 2.0
Mobility Radeon 9550 2005 M12 RV360 130 AGP 8x 64 210 183 2:4:4:4 0.84 0.84 2.928
5.856
DDR 64
128
9.0 2.0
Mobility Radeon 9600 Mar 2003 M10, M11 RV350 130 AGP 8x 64
128
300 300 2:4:4:4 1.2 1.2 4.8
9.6
DDR 64
128
9.0 2.0
Mobility Radeon 9600 Pro 2004 M10 RV350 130 AGP 8x 128 350 350 2:4:4:4 1.4 1.4 11.2 DDR 128 9.0 2.0
Mobility Radeon 9700 Feb 2004 M11 RV360 130 AGP 8x 128 450 275 2:4:4:4 1.8 1.8 8.8 DDR 128 9.0 2.0
Mobility Radeon 9800 Sep 2004 M18 R420 130 AGP 8x 256 350 300 4:8:8:8 2.8 2.8 19.2 DDR 256 9.0 2.0

1 Vertex shaders : Pixel shaders : Texture mapping units : Render output units.

Mobility Radeon X300, X600, X700, X800 Series

Model Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API compliance (version) Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
Mobility Radeon X300 Nov 2005 M22 RV370 110 PCI-E x16 128 350 250 2:4:4:4 1.4 1.4 4 DDR 64 9.0b 2.0 Powerplay 5.0
Mobility Radeon X600 Jun 2004 M24 RV380 130 PCI-E x16 64, 128 400 250 2:4:4:4 1.6 1.6 8 DDR 128 9.0b 2.0
Mobility Radeon X700 Mar 2005 M26 RV410 110 PCI-E x16 Shared-128? 64, 128 350 350 6:8:8:4 1.4 2.8 11.2 DDR, GDDR3 128 9.0b 2.0 3DC, Dynamic Lane Count Switching,
Mobility Radeon X800 Nov 2004 M28 R423 130 PCI-E x16 256 400 400 6:12:12:12 4.8 4.8 25.6 GDDR3 256 9.0b 2.0 3DC, DLCS, Clock Gating
Mobility Radeon X800 XT Jun 2005 M28 PRO R423 130 PCI-E x16 256 480 550 6:16:16:16 7.68 7.68 35.2 GDDR3 256 9.0b 2.0 3DC, DLCS, Clock Gating

1 Vertex shaders : Pixel shaders : Texture mapping units : Render output units.

Mobility Radeon X1xxx Series

Model Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API compliance (version) Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
Mobility Radeon X1300 January 19, 2006 M52 RV515 90 PCIe x16 128 + shared 350 250 2:4:4:4 1.4 1.4 8 DDR DDR2 128 9.0c 2.0
Mobility Radeon X1350 September 18, 2006 M62 RV515 90 PCIe x16 128 + shared 470 350 2:4:4:4 1.88 1.88 11.2 DDR2 GDDR3 128 9.0c 2.0
Mobility Radeon X1400 January 19, 2006 M54 RV515 90 PCIe x16 128 + shared 445 250 2:4:4:4 1.78 1.78 8 DDR DDR2 128 9.0c 2.0
Mobility Radeon X1450 September 18, 2006 M64 RV515 90 PCIe x16 128 + Shared 550 450 2:4:4:4 2.2 2.2 14.4 DDR2 GDDR3 128 9.0c 2.0
Mobility Radeon X1600 February 1, 2006 M56 RV530 90 PCIe x16 256 450 470 5:12:4:4 1.8 1.8 15.04 GDDR3 128 9.0c 2.0
Mobility Radeon X1700 February 1, 2006 M66 RV535 80 PCIe x16 256 475 400
550
5:12:4:4 1.9 1.9 11.2
17.6
DDR2
GDDR3
128 9.0c 2.0 strained silicon
Mobility Radeon X1800 March 1, 2006 M58 R520 90 PCIe x16 256 450 500 8:12:12:12 5.4 5.4 32 GDDR3 256 9.0c 2.0
Mobility Radeon X1800 XT March 1, 2006 M58 R520 90 PCIe x16 256 550 650 8:16:16:16 8.8 8.8 41.6 GDDR3 256 9.0c 2.0
Mobility Radeon X1900 January 11, 2007 M59 RV570 80 PCIe x16 256 400 480 8:36:12:12 4.8 4.8 30.72 GDDR3 256 9.0c 2.0 PowerPlay 6.0

1 Vertex shaders : Pixel shaders : Texture mapping units : Render output units.

Mobility Radeon HD 2xxx Series

Model Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core Fillrate Memory API compliance (version) Processing Power
GFLOPs
Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
Mobility Radeon X2300 March 1, 2007 M64 RV515 90 PCIe x16 128 480 400 2:4:4:41 1.92 1.92 6.4
12.8
DDR
DDR2
GDDR3
64
128
9.0c 2.0 Un­known renamed product, HyperMemory, no UVD, PowerPlay 6.0
Mobility Radeon X2500 June 1, 2007 M66 RV530 90 PCIe x16 256 460 400 5:12:4:41 1.84 1.84 12.8 DDR
DDR2
GDDR3
128 9.0c 2.0 Un­known based on X1600/1700, HM up to 768Mb, no UVD, PowerPlay 6.0
Mobility Radeon HD 2300 March 1, 2007 M71 RV515 90 PCIe x16 128
256
512
480 400 2:4:4:41 1.92 1.92 6.4
12.8
DDR
DDR2
GDDR3
64
128
9.0c 2.0 Un­known same as X2300, but with UVD, PowerPlay 6.0
Mobility Radeon HD 2400 May 14, 2007 M72S RV610 65 PCIe x16 256+ Hyper Memory 450 400 40:4:42 1.8 1.8 6.4 DDR2 64 10 2.0 36 UVD, PowerPlay 7.0
Mobility Radeon HD 2400 XT May 14, 2007 M72M RV610 65 PCIe x16 256+ Hyper Memory 600
600
400
700
40:4:42 2.4 2.4 6.4
11.2
DDR2
GDDR3
64 10 2.0 48 UVD, PowerPlay 7.0
Mobility Radeon HD 2600 May 14, 2007 M76M RV630 65 PCIe x16 256+ Hyper Memory 500
500
400
600
120:8:42 2.0 4.0 12.8
19.2
DDR2
GDDR3
128 10 2.0 120 UVD, PowerPlay 7.0
Mobility Radeon HD 2600 XT May 14, 2007 M76XT RV630 65 PCIe x16 256+ Hyper Memory 680 750 120:8:42 2.72 5.44 24 GDDR3 128 10 2.0 168 UVD, PowerPlay 7.0
Mobility Radeon HD 2700 December 12, 2007 M76 RV630 65 PCIe x16 256+ Hyper Memory (total 768) 650 700 120:8:42 2.6 5.2 22.4 GDDR3 128 10 2.0 168 UVD, PowerPlay 7.0

1 Vertex shaders : Pixel shaders : Texture mapping units : Render output units.
2 Unified Shaderss : Texture mapping units : Render output units

Mobility Radeon HD 3xxx Series

Model[41] Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API compliance (version) Processing Power
GFLOPs
Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
Mobility Radeon HD 3100 August 1, 2008 RS780MC RV620 55 PCIe x16 1.1 up to 512 from system memory 300 800
(system memory)
40:4:4 1.2 1.2 6.4/12.8 DDR2 64/128 10 2.0 24 UVD, PowerPlay 7.0
Mobility Radeon HD 3200 June 4, 2008 RS780MC RV620 55 PCIe x16 1.1 up to 512 from system memory 500 800
(system memory)
40:4:4 2 2 6.4/12.8 DDR2 64/128 10 2.0 40 UVD, PowerPlay 7.0
Mobility Radeon HD 3410 July 25, 2008 M82-MPE RV620 55 PCIe x16 1.1 256, 512 400 400 40:4:4 1.6 1.6 6.4 DDR2 64 10.1 2.0 32 UVD, PowerPlay 7.0
Mobility Radeon HD 3430 July 25, 2008 M82-SE RV620 55 PCIe x16 2.0 256 450 400 40:4:4 1.8 1.8 6.4 DDR2 64 10.1 2.0 36 UVD, PowerPlay 7.0
Mobility Radeon HD 3450 January 7, 2008 M82 RV620 55 PCIe x16 2.0 256 500 400
700
40:4:4 2 2 6.4
11.2
DDR2
GDDR3
64 10.1 2.0 40 UVD, PowerPlay 7.0
Mobility Radeon HD 3470 January 7, 2008 M82-XT RV620 55 PCIe x16 2.0 256 680 400
800
40:4:4 2.72 2.72 6.4
12.8
DDR2
GDDR3
64 10.1 2.0 54.4 UVD, PowerPlay 7.0
Mobility Radeon HD 3650 January 7, 2008 M86 RV635 55 PCIe x16 2.0 512
1024
500 700 120:8:4 2 4 22.4 DDR2
GDDR3
GDDR4
128 10.1 3.3 120 UVD, PowerPlay 7.0
Mobility Radeon HD 3670 January 7, 2008 M86-XT RV635 55 PCIe x16 2.0 512
1024
680 800 120:8:4 2.72 5.44 25.6 DDR2
GDDR3
GDDR4
128 10.1 2.0 163.2 UVD, PowerPlay 7.0. TDP 30 watts
Mobility Radeon HD 3850 June 4, 2008 M88-L/M88-LP RV670 55 PCIe x16 2.0 512 580 750 320:16:16 9.28 9.28 48.0 GDDR3 256 10.1 2.0 371.2 UVD, PowerPlay 7.0
Mobility Radeon HD 3870 June 4, 2008 M88-LXT RV670 55 PCIe x16 2.0 512 660 850 320:16:16 10.56 10.56 54.4 GDDR3 256 10.1 2.0 422.4 UVD, PowerPlay 7.0. TDP 55 watts.
Mobility Radeon HD 3850 X2 June 5, 2008 2x M88-L/M88-LP R680 55 PCIe x16 2.0 2x 512 580 750 2x [320:16:16] 2x 9.28 2x 9.28 2x 48.0 GDDR3 2x 256 10.1 2.0 2x 371.2 UVD, PowerPlay 7.0
Mobility Radeon HD 3870 X2 September 1, 2008 2x M88-LXT R680 55 PCIe x16 2.0 2x 512 660 850 2x [320:16:16] 2x 10.56 2x 10.56 2x 54.4 GDDR3 2x 256 10.1 2.0 2x 422.4 UVD, PowerPlay 7.0. TDP 110 watts

1 Unified Shaders : Texture mapping units : Render output units

Mobility Radeon HD 4xxx Series

Model[41] Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API compliance (version) Processing Power
GFLOPs
Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
Mobility Radeon HD 4200 September 10, 2009 Un­known RV620 55 Internal PCIe x16 1.1 up to 512 from system memory 500 800
(system memory)
40:4:4 2 2 6.4/12.8 DDR2 DDR3 64/128 10.1 2.0 40 UVD2, PowerPlay 7.0
Mobility Radeon HD 4225 May 1, 2010 Un­known RV620 55 Internal PCIe x16 1.1 up to 512 from system memory 380 800
(system memory)
40:4:4 1.52 1.52 6.4/12.8 DDR2 DDR3 64/128 10.1 2.0 30.4 UVD2, PowerPlay 7.0
Mobility Radeon HD 4250 May 1, 2010 Un­known RV620 55 Internal PCIe x16 1.1 up to 512 from system memory 500 800
(system memory)
40:4:4 2 2 6.4/12.8 DDR2 DDR3 64/128 10.1 2.0 40 UVD2, PowerPlay 7.0
Mobility Radeon HD 4270 May 1, 2010 Un­known RV620 55 Internal PCIe x16 1.1 up to 512 from system memory 590 800
(system memory)
40:4:4 2.36 2.36 6.4/12.8 DDR2 DDR3 64/128 10.1 2.0 47.2 UVD2, PowerPlay 7.0
Mobility Radeon HD 4330 January 9, 2009 M92 RV710 55 PCIe x16 2.0 512 450 600 80:8:4 1.8 3.6 9.6 DDR2
DDR3
GDDR3
64 10.1 3.3 72 UVD2, PowerPlay 7.0
Mobility Radeon HD 4530 January 9, 2009 M92 RV710 55 PCIe x16 2.0 512 500 700 80:8:4 2 4 11.2 DDR2
DDR3
GDDR3
64 10.1 3.3 80 UVD2, PowerPlay 7.0
Mobility Radeon HD 4550 January 1, 2010 M92 RV710 55 PCIe x16 2.0 512 550 700 80:8:4 2.2 4.4 11.2 DDR2
DDR3
GDDR3
64 10.1 3.3 80 UVD2, PowerPlay 7.0
Mobility Radeon HD 4570 January 9, 2009 M92 RV710 55 PCIe x16 2.0 512 680 800 80:8:4 2.72 5.44 12.8 DDR2
DDR3
GDDR3
64 10.1 3.3 108.8 UVD2, PowerPlay 7.0
Mobility Radeon HD 4650 January 9, 2009 M96 RV730 55 PCIe x16 2.0 512
1024
500
550
600
800
320:32:8 4
4.4
16
17.6
19.2
25.6
DDR2
DDR3
GDDR3
128 10.1 3.3 320
352
UVD2, PowerPlay 7.0
Mobility Radeon HD 4670 January 9, 2009 M96-XT RV730 55 PCIe x16 2.0 512
1024
675 800 320:32:8 5.4 21.6 12.8
25.6
DDR2
DDR3
GDDR3
128 10.1 3.3 432 UVD2, PowerPlay 7.0
Mobility Radeon HD 4830 March 3, 2009[42] M97 RV740 40 PCIe x16 2.0 512
1024
400/600
400/600
800/900
800/900
640:32:16 6.4/9.6
6.4/9.6
12.8/19.2
12.8/19.2
25.6/28.8
25.6/28.8
GDDR3
DDR3
128 10.1 3.3 512/768
512/768
UVD2, PowerPlay 7.0
Mobility Radeon HD 4850[43] January 9, 2009 M98 RV770 55 PCIe x16 2.0 1024 500 850
700
800:40:16 8 20 54.4
89.6
GDDR3
GDDR52
256 10.1 3.3 800 UVD2, PowerPlay 7.0
Mobility Radeon HD 4860 March 3, 2009[42] M97 RV740 40 PCIe x16 2.0 1024 650 1000 640:32:16 10.4 20.8 64.0 GDDR52 128 10.1 3.3 832 UVD2, PowerPlay 7.0
Mobility Radeon HD 4870 January 9, 2009 M98-XT RV770 55 PCIe x16 2.0 512
1024
550 888
700
800:40:16 8.8 22 56.832
89.6
GDDR3
GDDR52
256 10.1 3.3 880 UVD2, PowerPlay 7.0
Mobility Radeon HD 4870 X2 January 9, 2009 M98-XT RV770 55 PCIe x16 2.0 2048 550 700 2x [800:40:16] 2x 8.8 2x 22 2x 89.6 GDDR52 2x 256 10.1 3.3 2x 880 UVD2, PowerPlay 7.0
Dual GPU solution

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 with other DDR memory.

Mobility Radeon HD 5xxx Series

Model: Mobility Radeon Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API compliance (version) Processing Power
GFLOPs
TDP (Watts)
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
Mobility Radeon HD 530v May 5, 2010 M92 RV710 55 PCIe x16 2.0 1024 500 600 80:8:4 2 4 9.6 DDR2
DDR3
GDDR3
64 10.1 3.3 80 Un­known
Mobility Radeon HD 545v May 5, 2010 M92 RV710 55 PCIe x16 2.0 1024 720 800 80:8:4 2.88 5.76 12.8 DDR2
DDR3
GDDR3
64 10.1 3.3 115.2 Un­known
Mobility Radeon HD 550v May 5, 2010 M96 RV730 55 PCIe x16 2.0 1024 450 600 320:32:8 3.6 14.4 19.2 DDR2
DDR3
GDDR3
128 10.1 3.3 288 Un­known
Mobility Radeon HD 560v May 5, 2010 M96 RV730 55 PCIe x16 2.0 1024 550 800 320:32:8 4.4 17.6 25.6 DDR2
DDR3
GDDR3
128 10.1 3.3 352 Un­known
Mobility Radeon HD 565v May 5, 2010 M96-XT RV730 55 PCIe x16 2.0 1024 675 800 320:32:8 5.4 21.6 25.6 DDR2
DDR3
GDDR3
128 10.1 3.3 432 Un­known
Mobility Radeon HD 5145 January 7, 2010 M92 RV710 55 PCIe x16 2.0 1024 720 900 80:8:4 2.88 5.76 14.4 DDR3
GDDR3
64 10.1 3.3 115.2 15
Mobility Radeon HD 5165 January 7, 2010 M96 RV730 55 PCIe x16 2.0 1024 600 900 320:32:8 4.8 19.2 28.8 DDR3
GDDR3
128 10.1 3.3 384 35
Mobility Radeon HD 5430 January 7, 2010 Park LP Cedar 40 PCIe x16 2.1 1024 500
550
800
800
80:8:4 2.0
2.2
4.0
4.4
12.8 DDR3
GDDR3
64 11 4.4 80
88
7
Mobility Radeon HD 5450 January 7, 2010 Park PRO Cedar 40 PCIe x16 2.1 1024 675 800 80:8:4 2.7 5.4 12.8 DDR3
GDDR3
64 11 4.4 108 11
Mobility Radeon HD 5470 January 7, 2010 Park XT Cedar 40 PCIe x16 2.1 1024
1024
512
750 800 80:8:4 3 6 12.8
12.8
25.6
DDR3
GDDR3
GDDR5
64 11 4.4 120 13
15
Mobility Radeon HD 5650 January 7, 2010 Madison PRO Redwood 40 PCIe x16 2.1 1024 450
650
800
800
400:20:8 3.6
5.2
9.0
13.0
25.6
25.6
DDR3
GDDR3
128 11 4.4 360
520
15
19
Mobility Radeon HD 5730 January 7, 2010 Madison LP Redwood 40 PCIe x16 2.1 1024 650 800 400:20:8 5.2 13 25.6 DDR3
GDDR3
128 11 4.4 520 26
Mobility Radeon HD 5750 January 7, 2010 Madison PRO Redwood 40 PCIe x16 2.1 1024 550 800 400:20:8 4.4 11 51.2 GDDR5 128 11 4.4 440 25
Mobility Radeon HD 5770 January 7, 2010 Madison XT Redwood 40 PCIe x16 2.0/2.1 1024 650 800 400:20:8 5.2 13 51.2 GDDR5 128 11 4.4 520 30
Mobility Radeon HD 5830 January 7, 2010 Broadway LP Juniper 40 PCIe x16 2.1 1024 500 800 800:40:16 8 20 25.6 DDR3
GDDR3
128 11 4.4 800 24
Mobility Radeon HD 5850 January 7, 2010 Broadway PRO Juniper 40 PCIe x16 2.1 2048
1024
1024
625
500
625
900
1000
1000
800:40:16 10
8
10
25
20
25
28.8
64
64
DDR3
GDDR5
GDDR5
128 11 4.4 1000
800
1000
31
30
39
Mobility Radeon HD 5870 January 7, 2010 Broadway XT Juniper 40 PCIe x16 2.1 1024 700 1000 800:40:16 11.2 28 64 GDDR5 128 11 4.4 1120 50
Model Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL Processing Power
GFLOPs
TDP (Watts)
Fillrate Memory API compliance (version)

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 with other DDR memory.

Radeon HD 6xxxM Series

Model Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate Memory API compliance (version) Processing Power
GFLOPs
TDP (Watts) GPU only Features
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
Radeon HD 6330M November 26, 2010 Robson LP Cedar 40 PCIe 2.1 x16 up to
1024
500 800 80:8:4 2.0 4.0 12.8 DDR3 64 11 4.4 80 7 UVD2.2, PowerPlay
Radeon HD 6350M November 26, 2010 Robson Pro Cedar 40 PCIe 2.1 x16 up to
1024
500
500
800
900
80:8:4 2.0 4.0 12.8
14.4
DDR3 64 11 4.4 80 7 UVD2.2, PowerPlay
Radeon HD 6370M November 26, 2010 Robson XT Cedar 40 PCIe 2.1 x16 1024 750 900 80:8:4 3.0 6.0 14.4 DDR3 64 11 4.4 120 11 UVD2.2, PowerPlay
Radeon HD 6430M January 4, 2011 Seymour LP Caicos 40 PCIe 2.1 x16 1024 480 800 160:8:4 1.92 3.84 12.8 DDR3 64 11 4.4 153.6 Un­known UVD3.0, PowerPlay
Radeon HD 6450M January 4, 2011 Seymour Pro Caicos 40 PCIe 2.1 x16 1024 600 800 160:8:4 2.4 4.8 12.8 DDR3 64 11 4.4 192 Un­known UVD3.0, PowerPlay
Radeon HD 6470M January 4, 2011 Seymour XT Caicos 40 PCIe 2.1 x16 1024 700
750
800
800
160:8:4 2.8
3.0
5.6
6.0
12.8 DDR3 64 11 4.4 224
240
Un­known UVD3.0, PowerPlay
Radeon HD 6490M January 4, 2011 Seymour XT Caicos 40 PCIe 2.1 x16 512 800 800 160:8:4 3.2 6.4 25.6 GDDR5 64 11 4.4 256 Un­known UVD3.0, PowerPlay
Radeon HD 6530M November 26, 2010 Capilano Pro Redwood 40 PCIe 2.1 x16 1024 500 900 400:20:8 4.0 10.0 28.8 DDR3 128 11 4.4 400 26 UVD2.2, PowerPlay
Radeon HD 6550M November 26, 2010 Capilano Pro Redwood 40 PCIe 2.1 x16 1024 600 900 400:20:8 4.8 12.0 28.8 DDR3 128 11 4.4 480 26 UVD2.2, PowerPlay
Radeon HD 6570M November 26, 2010 Capilano XT Redwood 40 PCIe 2.1 x16 1024 650 900 400:20:8 5.2 13.0 28.8
57.6
DDR3
GDDR5
128 11 4.4 520 30 UVD2.2, PowerPlay
Radeon HD 6630M January 4, 2011 Whistler LP Turks 40 PCIe 2.1 x16 256(mac)
1024
485 800 480:24:8 3.88 11.64 51.2 (mac)
25.6
GDDR5(mac)
DDR3
128 11 4.4 465.6 Un­known UVD3.0, PowerPlay
Radeon HD 6650M January 4, 2011 Whistler Pro Turks 40 PCIe 2.1 x16 1024 600 900 480:24:8 4.8 14.4 28.8 DDR3 128 11 4.4 576 Un­known UVD3.0, PowerPlay
Radeon HD 6730M January 4, 2011 Whistler XT Turks 40 PCIe 2.1 x16 1024 725 800 480:24:8 5.8 17.4 25.6 DDR3 128 11 4.4 696 Un­known UVD3.0, PowerPlay
Radeon HD 6750M January 4, 2011 Whistler Pro Turks 40 PCIe 2.1 x16 256
512
1024
600 800
900
480:24:8 4.8 14.4 51.2
57.6
GDDR5 128 11 4.4 576 Un­known UVD3.0, PowerPlay
Radeon HD 6770M January 4, 2011 Whistler XT Turks 40 PCIe 2.1 x16 1024 725 900 480:24:8 5.8 17.4 57.6 GDDR5 128 11 4.4 696 Un­known UVD3.0, PowerPlay
Radeon HD 6830M January 4, 2011 Granville Pro Juniper 40 PCIe x16 2.1 up to 2048 575 800 800:40:16 9.2 23.0 25.6 DDR3 128 11 4.4 920 39 UVD2.2, PowerPlay
Radeon HD 6850M January 4, 2011 Granville XT Juniper 40 PCIe x16 2.1 up to 2048 675 800 800:40:16 10.8 27.0 25.6 DDR3 128 11 4.4 1080 50 UVD2.2, PowerPlay
Radeon HD 6850M January 4, 2011 Granville Pro Juniper 40 PCIe x16 2.1 1024 575 800 800:40:16 9.2 23.0 57.6 GDDR5 128 11 4.4 920 39 UVD2.2, PowerPlay
Radeon HD 6870M January 4, 2011 Granville XT Juniper 40 PCIe x16 2.1 1024 675 1000 800:40:16 10.8 27 64 GDDR5 128 11 4.4 1080 50 UVD2.2, PowerPlay
Radeon HD 6950M January 4, 2011 Blackcomb Pro Barts 40 PCIe 2.1 x16 up to
2048
580 900 960:48:32 18.56 27.84 115.2 GDDR5 256 11 4.4 1113.6 50 UVD3.0, PowerPlay
Radeon HD 6970M January 4, 2011 Blackcomb XT Barts 40 PCIe 2.1 x16 up to
2048
680 900 960:48:32 21.76 32.64 115.2 GDDR5 256 11 4.4 1305.6 75 UVD3.0, PowerPlay
Radeon HD 6990M July 12, 2011 Blackcomb XTX Barts 40 PCIe 2.1 x16 2048 715 900 1120:56:32 22.88 40.04 115.2 GDDR5 256 11 4.4 1601.6 75 UVD3.0, PowerPlay
Model Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL Processing Power
GFLOPs
TDP (Watts) Features
Fillrate Memory API compliance (version)

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 with other DDR memory.

IGP (HD 6xxx)

  • All models include DirectX 11, OpenGL 4.4 and OpenCL 1.2
  • All models feature the UNB/MC Bus interface
  • All models do not feature double-precision FP
  • All models feature Angle independent anisotropic filtering, UVD3, and Eyefinity capabilities, with up to three outputs.
  • All models are based on the VLIW5 architecture.
Model Released Code name Fab (nm) Core Clock (MHz) Config core1 Fillrate Shared Memory GFLOPS Max. Combined TDP2 (W) GFLOPS/W APU
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon HD 6250[44] Nov 9, 2010[17] Wrestler[45] 40 280 - 400[44] 80:8:4 1.12 - ? 2.24 - ? 8.525 DDR3-1066 64 44.8 - ? 9 4.98 - ? Z-60
C-30
C-50
Radeon HD 6290 Jan 7, 2011 Ontario 276 - 400 C-60
Radeon HD 6310[44] Nov 9, 2010[17] Wrestler[45] 492 2.0 4.0 80 18 4.44 E-240
E-300
E-350
Radeon HD 6320 Aug 15, 2011 Wrestler 508 - 600 2.0 - ? 4.1 - ? 10.6 DDR3-1333 82 - 97 4.56 - 5.39 E-450

1 Unified shaders : Texture mapping units : Render output units
2 TDP specified for AMD reference designs, includes CPU power consumption. Actual TDP of retail products may vary.

IGP (HD 6xxxG)

  • All models include DirectX 11, OpenGL 4.4 and OpenCL 1.2
  • All models feature the UNB/MC Bus interface
  • All models do not feature double-precision FP
  • All models feature Angle independent anisotropic filtering, UVD3 and Eyefinity capabilities, with up to three outputs.
  • All models feature VLIW5
Model Released Code name Fab (nm) Core Clock (MHz) Config core1 Fillrate Shared Memory GFLOPS Max. Combined TDP2 (W) APU
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon HD 6380G June 14, 2011 WinterPark 32 400 160:8:4 1.6 3.2 17.06 DDR3-1333 128 128 35 E2-3000M
Radeon HD 6480G June 14, 2011 BeaverCreek 32 444 240:12:4 1.77 3.55 17.06 DDR3-1333 128 213.1 35 - 45 A4-3300M A4-3310MX
Radeon HD 6520G June 14, 2011 BeaverCreek 32 400 320:16:8 3.2 6.4 17.06 DDR3-1333 128 256 35 - 45 A6-3400M A6-3410MX
Radeon HD 6620G June 14, 2011 BeaverCreek 32 444 400:20:8 3.55 8.88 25.6 DDR3-1600 128 355.2 35 - 45 A8-3500M A8-3510MX A8-3530MX

1 Unified shaders : Texture mapping units : Render output units
2 TDP specified for AMD reference designs, includes CPU power consumption. Actual TDP of retail products may vary.

Radeon HD 7xxxM Series

  • Some models manufactured in a 28 nm fabrication process.
  • All models include OpenCL 1.2

[46]

Model Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory Processing Power GFLOPs API compliance (version) TDP (Watts)GPU only Features / Notes
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type2 Bus width (bit) DirectX OpenGL
Radeon HD 7430M January 7, 2012 Seymour Pro Caicos 40 PCIe 2.1 x16 1024 600 900 160:8:4 2.4 4.8 14.4 DDR3 64 192 11.0 4.4 7
Radeon HD 7450M January 7, 2012 Seymour Pro Caicos 40 PCIe 2.1 x16 1024 700
700
900
800
160:8:4 2.8 5.6 14.4
25.6
DDR3
GDDR5
64 224 11.0 4.4 7
Radeon HD 7470M January 7, 2012 Seymour XT Caicos 40 PCIe 2.1 x16 1024 750
800
900
800
160:8:4 3.0
3.2
6
6.4
14.4
25.6
DDR3
GDDR5
64 240
256
11.0 4.4 7~9
Radeon HD 7490M January 7, 2012 Seymour XTX Caicos 40 PCIe 2.1 x16 1024 800 950 160:8:4 3.2 6.4 30.4 GDDR5 64 256 11.0 4.4 9
Radeon HD 7510M January 7, 2012 Thames LE Turks 40 PCIe 2.1 x16 1024 450 800 400:20:8 3.6 9.0 12.8 DDR3 64 360 11.0 4.4 11
Radeon HD 7530M January 7, 2012 Thames LP Turks 40 PCIe 2.1 x16 1024 450 900 400:24:8 3.6 9.0 14.4 DDR3 64 360 11.0 4.4 11
Radeon HD 7550M January 7, 2012 Thames Pro Turks 40 PCIe 2.1 x16 1024 450
550
900
800
400:20:8 3.6
4.4
9.0
11.0
14.4
25.6
DDR3
GDDR5
64 360
440
11.0 4.4 13
Radeon HD 7570M January 7, 2012 Thames Pro Turks 40 PCIe 2.1 x16 1024 450
650
900
800
400:20:8 3.6
5.2
9.0
13.0
14.4
25.6
DDR3
GDDR5
64 360
520
11.0 4.4 13~15
Radeon HD 7590M January 7, 2012 Thames XT Turks 40 PCIe 2.1 x16 1024 600 800 480:24:8 4.8 14.4 25.6 GDDR5 64 576 11.0 4.4 18
Radeon HD 7610M January 7, 2012 Thames LE Turks 40 PCIe 2.1 x16 1024 450 800 400:20:8 3.6 9.0 25.6 DDR3 128 360 11.0 4.4 20
Radeon HD 7630M January 7, 2012 Thames LP Turks 40 PCIe 2.1 x16 1024 450 800 480:24:8 3.6 10.8 25.6 DDR3 128 432 11.0 4.4 20~25
Radeon HD 7650M January 7, 2012 Thames Pro Turks 40 PCIe 2.1 x16 1024 450
550
800
800
480:24:8 3.6
4.4
10.8
13.2
25.6 DDR3 128 432
528
11.0 4.4 20~25
Radeon HD 7670M January 7, 2012 Thames Pro Turks 40 PCIe 2.1 x16 1024 600 900 480:24:8 4.8 14.4 28.8
57.6
DDR3
GDDR5
128 576 11.0 4.4 20~25
Radeon HD 7690M January 7, 2012 Thames XT Turks 40 PCIe 2.1 x16 1024
2048
725
600
900
900
480:24:8 5.8
4.8
17.4
14.4
28.8
57.6
DDR3
GDDR5
128 696
576
11.0 4.4 20~25
Radeon HD 7690M XT January 7, 2012 Thames XTX Turks 40 PCIe 2.1 x16 1024
2048
725 900 480:24:8 5.8 17.4 57.6 GDDR5 128 696 11.0 4.4 25
Radeon HD 7730M April 24, 2012 Chelsea LP Cape Verde 28 PCIe 2.1 x16 2048 575
675
900
900
512:32:16 9.2
10.8
18.4
21.6
28.8 GDDR3 128 588.8
691.2
11.1 4.4 25~28
Radeon HD 7750M April 24, 2012 Chelsea Pro Cape Verde 28 PCIe 2.1 x16 1024
2048
575 1000 512:32:16 9.2 18.4 64 GDDR5 128 588.8 11.1 4.4 28
Radeon HD 7770M April 24, 2012 Chelsea XT Cape Verde 28 PCIe 2.1 x16 1024
2048
675 1000 512:32:16 10.8 21.6 64 GDDR5 128 691.2 11.1 4.4 32
Radeon HD 7850M April 24, 2012 Heathrow Pro Cape Verde 28 PCIe 3.0 x16 2048 675 1000 640:40:16 10.8 27 64 GDDR5 128 864 11.1 4.4 40
Radeon HD 7870M April 24, 2012 Heathrow XT Cape Verde 28 PCIe 3.0 x16 2048 800 1000 640:40:16 12.8 32 64 GDDR5 128 1024 11.1 4.4 40 - 45
Radeon HD 7970M April 24, 2012 Wimbledon XT Pitcairn 28 PCIe 3.0 x16 2048 - 4096 850 1200 1280:80:32 27.2 68 153.6 GDDR5 256 2176 11.1 4.4 75

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 with other DDR memory.

IGP (HD 7xxxG)

See Radeon HD 7000 Series.

Radeon HD 8xxxM Series

Model Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory Processing Power GFLOPs API compliance (version) TDP (Watts)GPU only
Core (MHz) Boost (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type2 Bus width (bit) DirectX OpenGL
Radeon HD 8550M/8630M January 8, 2013 Mars Oland 28 PCIe 3.0 x8 1024 650 700 900 384:24:8 5.2 - 5.6 15.6 - 16.8 14.4 DDR3 64 537.6 11.1 4.4 Un­known
Radeon HD 8570M/8650M January 8, 2013 Mars Oland 28 PCIe 3.0 x8 1024 650 700 1125 384:24:8 5.2 - 5.6 15.6 - 16.8 36 GDDR5 64 537.6 11.1 4.4 Un­known
Radeon HD 8670M January 8, 2013 Mars Oland 28 PCIe 3.0 x8 1024 775 825 900 384:24:8 6.2 - 6.6 18.6 - 19.8 14.4 DDR3 64 633.6 11.1 4.4 Un­known
Radeon HD 8690M January 8, 2013 Mars Oland 28 PCIe 3.0 x8 1024 775 825 1125 384:24:8 6.2 - 6.6 18.6 - 19.8 36 GDDR5 64 633.6 11.1 4.4 Un­known
Radeon HD 8730M January 8, 2013 Mars LP Oland 28 PCIe 3.0 x8 2048 650 700 1000 384:24:8 5.2 - 5.6 15.6 - 16.8 32 DDR3 128 537.6 11.1 4.4 Un­known
Radeon HD 8750M January 8, 2013 Mars Pro Oland 28 PCIe 3.0 x8 2048 620 - 775 670 - 825 1000
1000
384:24:8 4.96 - 6.6 14.88 - 19.8 32
64
DDR3
GDDR5
128 514.56 - 633.6 11.1 4.4 Un­known
Radeon HD 8770M January 8, 2013 Mars XT Oland 28 PCIe 3.0 x8 2048 775 825 1125 384:24:8 6.2 - 6.6 18.6 - 19.8 72 GDDR5 128 633.6 11.1 4.4 Un­known
Radeon HD 8790M January 8, 2013 Mars XTX Oland 28 PCIe 3.0 x8 2048 850 900 1125 384:24:8 6.8 - 7.2 20.4 - 21.6 72 GDDR5 128 691.2 11.1 4.4 Un­known
Radeon HD 8830M January 8, 2013 Venus LE Cape Verde 28 PCIe 3.0 x16 2048 575 625 1000 640:40:16 9.2 - 10 23 - 25 32 DDR3 128 800 11.1 4.4 Un­known
Radeon HD 8850M January 8, 2013 Venus PRO Cape Verde 28 PCIe 3.0 x16 2048 575 - 725 625 - 775 1000
1125
640:40:16 9.2 - 12.4 23 - 31 32
72
DDR3
GDDR5
128 800 - 992 11.1 4.4 Un­known
Radeon HD 8870M January 8, 2013 Venus XT Cape Verde 28 PCIe 3.0 x16 2048 725 775 1000
1125
640:40:16 11.6 - 12.4 29 - 31 32
72
DDR3
GDDR5
128 992 11.1 4.4 Un­known
Radeon HD 8970M May 15, 2013 Neptune XT Pitcairn 28 PCIe 3.0 x16 2048 - 4096 850 900 1200 1280:80:32 27.2 - 28.8 68 - 72 153.6 GDDR5 256 2304 11.1 4.4 100

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 with other DDR memory.

Radeon Rx M2xx Series

While the desktop versions are code-named "Volcanic Islands", the mobile GPUs of the AMD Radeon Rx 200 Series are code-named "Crystal Series": "Vesuvius", "Topaz" and "Amethyst".

Model Launch Model Number Code name Fab (nm) Bus interface Memory (MB) Clock rate Config core Fillrate Memory Processing Power GFLOPs API compliance (version) TDP (Watts)GPU only
Core (MHz) Boost (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
Radeon R5 M230 2014 Jet Pro Oland 28 PCIe 3.0 x8 2048
4096
780 855 1000 320:20:4 3.4 17.1 16 DDR3 64 547 11.2 4.3 Un­known
Radeon R5 M255 June 2014 Jet Pro Oland 28 PCIe 3.0 x8 2048
4096
Un­known 940 1000 320:20:8 7.5 18.8 16 DDR3 64 601 11.2 4.3 Un­known
Radeon R7 M260 June 2014 Opal Oland 28 PCIe 3.0 x8 2048
4096
Un­known 715
980
1000 384:24:8 5.7
7.8
17.2
23.5
32
16
DDR3 128
64
549.1
752.6
11.2 4.3 Un­known
Radeon R7 M260X June 2014 Opal Oland 28 PCIe 3.0 x8 2048
4096
Un­known 715 1000 384:24:8 5.7 17.2 64 GDDR5 128 549 11.2 4.3 Un­known
Radeon R7 M265 May 1, 2014 Opal XT Oland 28 PCIe 3.0 x8 2048
4096
725 825 1000 384:24:8 6.6 19.8 16
32
DDR3 64
128
633.6 11.2 4.3 Un­known
Radeon R9 M265X May 1, 2014 Venus Pro Cape Verde 28 PCIe 3.0 x16 2048
4096
575 625 1125 640:40:16 10 25 72 GDDR5 128 800 11.2 4.3 Un­known
Radeon R9 M270X May 1, 2014 Venus XT Cape Verde 28 PCIe 3.0 x16 2048
4096
725 775 1125 640:40:16 12.4 31 72 GDDR5 128 992 11.2 4.3 Un­known
Radeon R9 M275X May 1, 2014 Venus XTX Cape Verde 28 PCIe 3.0 x16 2048
4096
900 925 1125 640:40:16 14.8 37 72 GDDR5 128 1184 11.2 4.3 50
Radeon R9 M290X May 1, 2014 Neptune XT Pitcairn 28 PCIe 3.0 x16 4096 850 900 1200 1280:80:32 28.8 72 153.6 GDDR5 256 2176-2304 11.2 4.3 100
Radeon R9 M295X 2014 Tonga 28 PCIe 3.0 x16 4096 750 800 1375 2048:128:32 25.6 102.4 176 GDDR5 256 3276.8 11.2 4.3

Comparison table: Workstation GPUs

FireGL Series

Model Launch Core Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core Fillrate Memory Processing Power
GFLOPs
API compliance (version) Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single precision DirectX OpenGL
FireGL 8700 2001 Radeon 8500 150 AGP 64 250 270 2:4:8:41 1 2 8.64 DDR 64 × 2 Un­known 8.1 1.4
FireGL 8800 2001 Radeon 8500 150 AGP 128 300 290 2:4:8:41 1.2 2.4 9.28 DDR 64 × 2 Un­known 8.1 1.4
FireGL T2-128 2003 Radeon 9600 Pro 130 AGP 128 400 320 2:4:4:41 1.6 1.6 10.2 DDR 128 Un­known 9.0 2.0
FireGL Z1-128 2002 Radeon 9500 Pro 150 AGP 128 325 310 4:4:4:41 1.3 1.3 19.8 DDR 256 Un­known 9.0 2.0
FireGL X1-128 2002 Radeon 9700 150 AGP 128 325 310 4:8:8:81 2.6 2.6 19.84 DDR 256 Un­known 9.0 2.0
FireGL X1-256 2002 Radeon 9700 Pro 150 AGP-Pro 256 325 310 4:8:8:81 2.6 2.6 19.84 DDR 256 Un­known 9.0 2.0
FireGL X2-256 2003 Radeon 9800 Pro 150 AGP 256 380 350 4:8:8:81 3.04 3.04 22.4 DDR2 256 Un­known 9.0 2.0
FireGL X2-256T 2003 Radeon 9800 XT 150 AGP 256 412 344 4:8:8:81 3.3 3.3 22.0 DDR2 256 Un­known 9.0 2.0
FireGL X3-256 2004 Radeon X800 XT 130 AGP 256 450 450 6:12:12:121 5.4 5.4 28.8 GDDR3 256 Un­known 9.0b 2.0
FireGL V3100 2005 Radeon X300 XT 110 PCIe x16 128 400 200 2:4:4:41 1.6 1.6 6.4 DDR 128 Un­known 9.0 2.0
FireGL V3200 2005 Radeon X600 XT 130 PCIe x16 128 500 400 2:4:4:41 2 2 12.8 DDR2 128 Un­known 9.0b 2.0
FireGL V3300 2006 Radeon 1300 Pro 90 PCIe x16 128 600 400 2:4:4:41 2.4 2.4 6.4 GDDR2 64 Un­known 9.0c 2.0
FireGL V3350 2006 Radeon 1300 Pro 90 PCIe x16 256 600 400 2:4:4:41 2.4 2.4 6.4 GDDR2 64 Un­known 9.0c 2.0
FireGL V3400 2006 Radeon 1600 Rro/XT 90 PCIe x16 128 500 500 5:12:4:41 2 2 16 GDDR3 128 Un­known 9.0c 2.0
FireGL V3600 2007 Radeon HD 2600 Pro 65 PCIe x16 256 600 500 1202(24×5):8:4 2.4 4.8 16.0 GDDR3 128 144 10 2.1
FireGL V5000 2005 Radeon X700 Pro/XT 130 PCIe x16 128 425 430 6:8:8:81 3.4 3.4 13.6 GDDR3 128 Un­known 9.0b 2.0
FireGL V5100 2005 Radeon X800 Pro 130 PCIe x16 128 450 350 6:12:12:121 5.4 5.4 22.4 DDR 256 Un­known 9.0b 2.0
FireGL V5200 2005 Radeon X1600 XT 90 PCIe x16 256 600 700 5:12:4:41 2.4 2.4 22.4 GDDR3 128 Un­known 9.0c 2.0
FireGL V5600 2007 Radeon HD 2600 XT 65 PCIe 512 800 1100 1202(24×5):8:4 3.2 6.4 35.2 GDDR4 128 192 10 2.1
FireGL V7100 2005 Radeon X800 XT 130 PCIe 256 500 450 6:16:16:161 8 8 28.8 GDDR3 256 Un­known 9.0c 2.0
FireGL V7200 2006 Radeon X1800 XT 90 PCIe x16 256 600 650 8:16:16:161 9.6 9.6 41.6 GDDR3 256 Un­known 9.0c 2.0
FireGL V7300 2006 Radeon X1800 XT 90 PCIe 512 600 650 8:16:16:161 9.6 9.6 41.6 GDDR3 256 Un­known 9.0c 2.0
FireGL V7350 2006 Radeon X1800 XT 90 PCIe 1024 600 650 8:16:16:161 9.6 9.6 41.6 GDDR3 256 Un­known 9.0c 2.0
FireGL V7400 2006 (Canceled) Radeon X1950 Pro 80 PCIe 512? 550? 650? 8:36:16:161 19.8? 19.8? 41.6? GDDR3 256 Un­known 9.0c 2.0 never released, superseded by 2007 Series
FireGL V7600 2007 Radeon HD 2900 GT 80 PCIe 512 600 800 2402(48×5):12:12 9.6 9.6 51.2 GDDR3 256 288 10 2.1
FireGL V7700 2007 (2008) Radeon HD 3870 55 PCIe 2.0 512 775 1125 3202(64×5):16:16 12.4 12.4 72 GDDR4 256 496 10.1 (SM 4.0 only) 2.1 DisplayPort. Can do double precision computation via the AMD Stream SDK.
FireGL V8600 2007 Radeon HD 2900 XT 80 PCIe 1024 688 868 3202(64×5):16:16 11.008 11.008 111.1[47] GDDR4 512 440.32 10 2.1
FireGL V8650 2007 Radeon HD 2900 XT 80 PCIe 2048 688 868 3202(64×5):16:16 11.008 11.008 111.1 GDDR4 512 440.32 10 2.1

1 Vertex shaders : Pixel shaders : Texture mapping units : Render output units
2 Unified shaders : Texture mapping units : Render output units

FirePro 3D Series

Model Launch Code name Fab (nm) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory Processing Power
GFLOPs
API compliance (version) TDP watts Notes
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision DirectX OpenGL OpenCL
FirePro 3D V3700 August 8, 2008 RV620[48] 55 PCIe 2.0 x16 256 800 950 40(8×5):4:4 3.2 3.2 15.2 GDDR3 64 64 - 10.1 3.0 - 32 UVD+, PowerPlay
FirePro 3D V3750 September 11, 2008 RV730 55 PCIe 2.0 x16 256 550 750 320(64×5):32:8 4.4 17.6 24 GDDR3 128 352 - 10.1 3.3 - 48 UVD2, PowerPlay
FirePro 3D V3800[49] April 26, 2010 Redwood Pro(RV830) 40 PCIe 2.1 x16 512 650 900 400(80×5):20:8 5.2 13 14.4 GDDR3 64 520 - 11.0 4.0 1.0 43 UVD2, PowerPlay, Eyefinity
FirePro 3D V4800[50] April 26, 2010 Redwood XT(RV830) 40 PCIe 2.1 x16 1024 775 9002 400(80×5):20:8 6.2 15.5 57.6 GDDR52 128 620 - 11.0 4.0 1.0 69 UVD2, PowerPlay, Eyefinity
FirePro 3D V5700 August 8, 2008 RV730 55 PCIe 2.0 x16 512 700 900 320(64×5):32:8 5.6 22.4 28.8 GDDR3 128 448 - 10.1 3.3 - 58 UVD2, PowerPlay
FirePro 3D V5800[49] April 26, 2010 Juniper XT(RV840) 40 PCIe 2.1 x16 1024 700 10002 800(160×5):40:16 11.2 28 64 GDDR52 128 1120 - 11.0 4.0 1.0 74 UVD2, PowerPlay, Eyefinity
FirePro 3D V7750 March 27, 2009 RV730 55 PCIe 2.0 x16 1024 800 900 320(64×5):32:8 6.4 25.6 28.8 GDDR3 128 512 - 10.1 3.3 - 76 UVD2, PowerPlay
FirePro 3D V7800[50] April 26, 2010 Cypress Pro(RV870) 40 PCIe 2.1 x16 2048 700 10002 1440(288×5):72:32 22.4 50.4 128 GDDR52 256 2016 403.2 11.0 4.0 1.0 138 UVD2, PowerPlay, Eyefinity
FirePro 3D V8700 September 11, 2008 RV770 XT 55 PCIe 2.1 x16 1024 750 8502 800(160×5):40:16 12 30 108.8 GDDR52 256 1200 240 10.1 3.3 - 151 UVD2, PowerPlay
FirePro 3D V8750 July 28, 2009 RV770 XT 55 PCIe 2.1 x16 2048 750 9002 800(160×5):40:16 12 30 115.2 GDDR52 256 1200 240 10.1 3.3 - 154 UVD2, PowerPlay
FirePro 3D V8800 April 7, 2010 Cypress XT(RV870) 40 PCIe 2.1 x16 2048 825 11502 1600(320×5):80:32 26.4 66 147.2 GDDR52 256 2640 528 11.0 4.0 1.0 208 UVD2, PowerPlay, Eyefinity
FirePro 3D V9800 September 9, 2010 Cypress XT(RV870) 40 PCIe 2.1 x16 4096 850 11502 1600(320×5):80:32 27.2 68 147.2 GDDR52 256 2720 544 11.0 4.0 1.0 225 UVD2, PowerPlay, Eyefinity

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 with other DDR memory.

FirePro Series

Model Launch Code name Fab (nm) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory Processing Power
GFLOPs
API compliance (version) TDP watts Notes
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision DirectX OpenGL OpenCL
FirePro V3900 February 7, 2012 Turks 40 PCIe 2.1 x16 1024 650 900 480(96×5):24:8 5.2 15.6 28.8 GDDR3 128 624 - 11.0 4.0 1.0 50 HD3D, UVD3, DP 1.2, PowerPlay, Eyefinity
FirePro V4900 November 1, 2011 Turks 40 PCIe 2.1 x16 1024 800 1000 480(96×5):24:8 6.4 19.2 64 GDDR52 128 768 - 11.0 4.0 1.0 <75 Max HD3D, UVD3, DP 1.2, PowerPlay, Eyefinity
FirePro V5900 May 24, 2011 Cayman LE GL 40 PCIe 2.1 x16 2048 600 5002 512(128×4):32:32 19.2 19.2 64 GDDR52 256 610 154 11.0 4.0 1.0 <75 Max HD3D, UVD3, DP 1.2, PowerPlay, Eyefinity
FirePro V7900 May 24, 2011 Cayman Pro GL 40 PCIe 2.1 x16 2048 725 12502 1280(320×4):80:32 23.2 58 160 GDDR52 256 1860 464 11.0 4.0 1.0 <150 Max HD3D, UVD3, DP 1.2, PowerPlay, Eyefinity

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 with other DDR memory.

FireMV (Multi-View) Series

Model Launch Core Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate (GT/s) Memory API compliance (version) TDP (watts) Notes
Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
FireMV 2200 PCI RV280 PCI 64 Un­known Un­known 1:4:4:4 Un­known Un­known Un­known Un­known 8.1 1.4 Un­known DMS-59 for dual DVI-D output
FireMV 2200 PCIe Un­known RV370 PCIe x16 128 Un­known Un­known 2:4:4:4 Un­known Un­known Un­known Un­known 9.0 2.1 Un­known DMS-59 for dual DVI-D output
FireMV 2260 2008 RV620 PCIe x1/x16, PCI 256
512
Un­known Un­known 40(8×5):4:4 Un­known Un­known DDR2 Un­known 10.1[51] 2.1 15/8 Dual DisplayPort
FireMV 2400 PCI Un­known RV380 PCI 128 Un­known Un­known 2:4:4:4 Un­known Un­known Un­known Un­known 9.0 2.1 Un­known 2x VHDCI for quad DVI-D output, VGA
FireMV 2400 PCIe Un­known RV380 PCIe x1 256 Un­known Un­known 2:4:4:4 Un­known Un­known Un­known Un­known 9.0 2.1 Un­known 2x VHDCI for quad DVI-D output, VGA

1 Vertex shaders : Pixel shaders : Texture mapping unit : Render output units
2 Unified shaders : Texture mapping unit : Render output units

FirePro (Multi-View) Series

Model Launch Core Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core1 Fillrate (GT/s) Memory API compliance (version) TDP (watts) Notes
Bandwidth (GB/s) Bus type Bus width (bit) DirectX OpenGL
FirePro 2250 PCIe 2007 RV516 PCIe x1/x16 256 Un­known Un­known 2:4:4:4 Un­known Un­known Un­known Un­known 9.0 2.1 20/11 DMS-59 for dual DVI-D output
FirePro 2270 PCIe January 31, 2011 Cedar PCIe 2.1 x1/x16 512
1024
Un­known Un­known 80(16×5):8:4 Un­known Un­known DDR3 64 11.0 4.1 15/10 DMS-59 for dual DVI-D output and for DP
FirePro 2450 Multi-View 2009 2x RV620 PCIe x1/x16 512 Un­known Un­known 2x 40(8×5):4:4 Un­known Un­known GDDR3 Un­known 10.1 2.1 32 (17 in 2D) 2x VHDCI for quad DVI-D output, VGA
FirePro 2460 Multi-View[52] April 2010 Cedar (RV810) PCIe 2.0 x16 512 Un­known Un­known 80(16×5):8:4 Un­known Un­known GDDR3 64 11 4.1 20 UVD2, PowerPlay, Eyefinity (4 mini-displayports), DirectX 11(Hardware)

FireStream Series

Model Launch Code name Fab (nm) Bus interface RAM (MB) Clock rate Stream processors RAM Peak GFLOPS TDP Watts Notes
GPGPU (MHz) RAM (MHz) Bandwidth (GB/s) Type Bus width (bit) FP32 FP64
FireStream 9170 November 8, 2007 RV670 55 PCIe 2.0 x16 2048 800 800 320 51.2 GDDR3 256 512 102.4 105
FireStream 9250 June 16, 2008 RV770 55 PCIe 2.0 x16 1024 625 993 800 63.552 GDDR3 256 1000 200 150
FireStream 9270 November 13, 2008 RV770 55 PCIe 2.0 x16 2048 750 850 800 108.8 GDDR5 256 1200 240 160
FireStream 9350 June 23, 2010 RV870 40 PCIe 2.1 x16 2048 700 1000 1440 128 GDDR5 256 2016 403.2 150
FireStream 9370 June 23, 2010 RV870 40 PCIe 2.1 x16 4096 825 1150 1600 147.2 GDDR5 256 2640 528 225

FirePro Workstation Series

Model Launch Code name Fab (nm) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory Processing Power
GFLOPs
API compliance (version) TDP watts Notes
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision DirectX OpenGL OpenCL
FirePro W600 June 13, 2012 Cape Verde Pro 28 PCIe 3.0 x16 2048 750 1000 512:32:16 64 GDDR5 128 11.1 4.2 1.2 75 Six Mini DisplayPort
FirePro W2100[53] August 13, 2014 Oland XT 28 PCIe 3.0 x8 2048 630 900 320:20:8 5.04 12.6 28.8 DDR3 128 403.2 25.5 11.2 4.4 1.2 <26 Two Standard DisplayPort 1.2a outputs
FirePro W4100[54] August 13, 2014 Cape Verde 28 PCIe 3.0 x16 2048 630 1125 512:32:16 10.08 20.16 72 GDDR5 128 645.1 40.3 11.2 4.4 1.2 <50 Four Standard Mini-DisplayPort 1.2a outputs
FirePro W5000 June 13, 2012 Pitcairn LE 28 PCIe 3.0 x16 2048 825 800 768:48:32 26.4 39.6 102.4 GDDR5 256 1267.2 79.2 11.1 4.2 1.2 <75 Two DisplayPort, One DVI-I
FirePro W5100[55] August 13, 2014 Bonaire Pro 28 PCIe 3.0 x16 4096 930 1500 768:48:16 14.88 44.64 96 GDDR5 128 1430 89.2 11.1/12 4.4 2.0 <75 DirectGMA, GeometryBoost, Four Standard DisplayPort display outputs, DisplayPort 1.2a support, including Adaptive-Sync and HBR2 support
FirePro W7000 June 13, 2012 Pitcairn XT 28 PCIe 3.0 x16 4096 950 1200 1280:80:32 30.4 76 153.6 GDDR5 256 2432 152 11.1 4.2 1.2 <150 Four DisplayPort
FirePro W7100[56] August 13, 2014 Tonga 28 PCIe 3.0 x16 8192 TBA 1400 1792:112:32 TBA TBA 160 GDDR5 256 3300 206 11.2/12 4.4 2.0 <150 DirectGMA, GeometryBoost, Four Standard DisplayPort display outputs, DisplayPort 1.2a support, including Adaptive-Sync and HBR2 support
FirePro W8000 June 14, 2012 Tahiti PRO 28 PCIe 3.0 x16 4096 900 1375 1792:112:32 28.8 100.8 176 GDDR5 384 3225.6 806.4 11.1 4.2 1.2 189 ECC RAM, Four DisplayPort + SDI-Link
FirePro W8100[57] June 26, 2014 Hawaii Pro 28 PCIe 3.0 x16 8192 824 1250 2560:160:64 52.7 145 320 GDDR5 512 4218.9 2109.45 11.1 4.3 2.0 220 ECC RAM, Six Mini DisplayPort + SDI-Link
FirePro W9000 June 14, 2012 Tahiti XT 28 PCIe 3.0 x16 6144 975 1375 2048:128:32 31.2 124.8 264 GDDR5 384 3993.6 998.4 11.1 4.2 1.2 <274 ECC RAM, Six Mini DisplayPort + SDI-Link
FirePro W9100 March 26, 2014 Hawaii XT 28 PCIe 3.0 x16 16384 930 1250 2816:176:64 59.5 163.7 320 GDDR5 512 5237.8 2618.9 11.1 4.3 2.0[58] 275 ECC RAM, Six Mini DisplayPort + SDI-Link

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 with other DDR memory.

FirePro Server Series

Model Launch Code name Fab (nm) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory Processing Power
GFLOPs
API compliance (version) TDP watts Notes
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision DirectX OpenGL OpenCL
FirePro S7000 August 27, 2012 Pitcairn XT 28 PCIe 3.0 x16 4096 950 1200 1280:80:32 30.4 76 153.6 GDDR5 256 2432 152 11.1 4.2 1.2 <150 One DisplayPort
FirePro S9000 August 27, 2012 Tahiti PRO 28 PCIe 3.0 x16 6144 900 1375 1792:112:32 28.8 100.8 264 GDDR5 384 3225.6 806.4 11.1 4.2 1.2 <225 ECC RAM, One DisplayPort
FirePro S9050 [59] August 6, 2014 Tahiti PRO 28 PCIe 3.0 x16 12288 900 1375 1792:112:32 28.8 100.8 264 GDDR5 384 3225.6 806.4 11.1 4.2 1.2 <225 ECC RAM, One DisplayPort
FirePro S9150 [60] August 6, 2014 Hawaii XT 28 PCIe 3.0 x16 16384 900 1375 2816:176:64 57.6 158.4 320 GDDR5 512 5070 2530 11.1 4.2 1.2 <235 ECC RAM, None of DisplayPort
FirePro S10000 November 12, 2012 Tahiti PRO 28 PCIe 3.0 x16 2× 3072 825 1250 2× 1792:112:32 52.8 184.8 2× 240 GDDR5 384 5913.6 1478.4 11.1 4.2 1.2 <375 ECC RAM, Four Mini DisplayPort, One DVI-I

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 with other DDR memory.

FirePro Remote Series

Model Launch Code name Fab (nm) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory Processing Power
GFLOPs
API compliance (version) TDP watts Notes
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision DirectX OpenGL OpenCL
FirePro RG220 May 2010 RV711 55 PCIe 2.0 x16 512 500 800 80(16×5):8:4 2.0 4.0 12.8 GDDR3 for GPU,
RDRAM for PCoIP
64 80 No 10.1 3.3 None 35 Dual Ethernet ports plus DMS-59 for dual DVI-D output (no VGA host output)
FirePro R5000 February 25, 2013 Pitcairn LE 28 PCIe 3.0 x16 2048 825 800 768:48:32 26.4 39.6 102.4 GDDR5 256 1267.2 79.2 11.1 4.2 1.2 <150 Ethernet port plus Two Mini DisplayPort w/ Tera2 PCoIP

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 with other DDR memory.

Radeon Sky Series

Model Launch Code name Fab (nm) Bus interface Memory (MB) Clock rate Config core1 Fillrate Memory Processing Power
GFLOPs
API compliance (version) TDP watts Notes
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single Precision Double Precision DirectX OpenGL OpenCL
Radeon Sky 500 April, 2013 Pitcairn XT 28 PCIe 3.0 x16 4096 950 1200 1280:80:32 30.4 76 153.6 GDDR5 256 2432 152 11.1 4.2 1.2 150 One DisplayPort
Radeon Sky 700 April, 2013 Tahiti PRO 28 PCIe 3.0 x16 6144 900 1375 1792:112:32 28.8 100.8 264 GDDR5 384 3225.6 806.4 11.1 4.2 1.2 225 One DisplayPort
Radeon Sky 900 April, 2013 Tahiti PRO 28 PCIe 3.0 x16 2× 3072 825 1250 2× 1792:112:32 52.8 184.8 2× 240 GDDR5 384 5913.6 1478.4 11.1 4.2 1.2 300 Four Mini DisplayPort, One DVI-I

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 with other DDR memory.

Comparison table: Mobile Workstation GPUs

Mobility FireGL Series

Model Launch Model Number Based on Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core Fillrate Memory Processing Power
GFLOPs
API compliance (version) Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single precision DirectX OpenGL
Mobility FireGL 7800 2001 M7-GL Mobility Radeon 7500 180 AGP 64 280 200 0:2:2:21 0.56 0.56 6.4 DDR 128 Un­known 7 1.3
Mobility FireGL 9000 2002 M9 Mobility Radeon 9000 150 AGP 4X 64 250 200 1:4:4:41 1 1 6.4 DDR 128 Un­known 8.1 1.3
Mobility FireGL T2 2003 M10 Mobility Radeon 9600 130 AGP 4X 128 320 200 2:4:4:41 1.28 1.28 6.5 DDR 128 Un­known 9.0 2.0
Mobility FireGL T2e 2004 M11GL Mobility Radeon 9700 130 AGP 128 450 225 2:4:4:41 1.8 1.8 7.2 DDR 128 Un­known 9.0 2.0
Mobility FireGL V3100 2004 M22GL Mobility Radeon X300 110 PCIe x16 128 350 200 2:4:4:41 1.4 1.4 6.4 DDR 128 Un­known 9.0b 2.0
Mobility FireGL V3200 2004 M24GL Mobility Radeon X600 130 PCIe x16 128 400 250 2:4:4:41 1.6 1.6 12.8 DDR2 128 Un­known 9.0b 2.0
Mobility FireGL V5000 2005 M26GL Mobility Radeon X700 110 PCIe x16 128 350 425 6:8:8:81 2.8 2.8 13.6 GDDR3 128 Un­known 9.0b 2.0
Mobility FireGL V5200 2006 M56GL Mobility Radeon X1600 90 PCIe x16 256 425 475 5:12:12:121 5.1 5.1 15.2 GDDR3 128 Un­known 9.0c 2.0
Mobility FireGL V5250 2007 M66GL Mobility Radeon X1700 90 PCIe x16 256 450 350 5:12:12:121 5.4 5.4 11.2 GDDR3 128 Un­known 9.0c 2.0
Mobility FireGL V5600 2007 M76GL Mobility Radeon HD 2600 65 PCIe 2.0 x16 256 500 400 1202(24×5):8:4 2 4 12.8 GDDR3 128 120 10.1 2.1
Mobility FireGL V5700 2008 M86GL Mobility Radeon HD 3650 55 PCIe 2.0 x16 512 600 700 1202(24×5):8:4 2.4 4.8 22.4 GDDR3 128 144 10.1 2.1 Used in Lenovo ThinkPad W500
Mobility FireGL V5725 2008 M86GL Mobility Radeon HD 3650 55 PCIe 2.0 x16 256 680 800 1202(24×5):8:4 2.72 5.44 25.6 GDDR3 128 163.2 10.1 SM 4.1 2.1

1 Vertex shader : Pixel shaders : Texture mapping units : Render output units
2 Unified shaders : Texture mapping units : Render output units

FirePro (Mxxxx) Series

Model Launch Model Number Based on Fab (nm) Bus interface Memory (MB) Core clock (MHz) Memory clock (MHz) Config core Fillrate Memory Processing Power
GFLOPs
API compliance (version) Notes
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Single precision DirectX OpenGL
FirePro M5725 Un­known Un­known Mobility Radeon HD 4670 55 PCIe 2.0 x16 256 Un­known Un­known 3202(64×5):32:8 Un­known Un­known Un­known GDDR3 128 Un­known 10.1 SM 4.1 3.2
FirePro M5800 March 1, 2010 Redwood XT(RV830) Mobility Radeon HD 5730 40 PCIe 2.0 x16 1024 650 800 4002(80×5):20:8 5.2 13 25.6 GDDR5 128 520 11 SM 5 3.2 Used in HP EliteBook 8540w
FirePro M5950 2011 Whistler XT Radeon HD 6770M 40 PCIe 2.1 x16 1024 725 900 4802(96×5):24:8 5.8 17.4 57.6 GDDR5 128 696 11 4.1 Used in Dell Precision M4600
FirePro M7740 August 4, 2009 M97GL(RV740) Mobility Radeon HD 4860 40 PCIe 2.0 x16 1024 650 1000 6402(128×5):32:16 10.4 20.8 64 GDDR5 128 832 10.1 SM 4.1 3.2 used in Dell M6400 and M6500
FirePro M7820 May 1, 2010 Juniper XT(RV840) Mobility Radeon HD 5870 40 PCIe 2.0 x16 1024 700 1000 8002(160×5):40:16 11.2 28 64 GDDR5 128 1120 11 SM 5 3.2 used in Dell M6500, HP EliteBook 8740w
FirePro M8900 2011 Blackcomb XT Radeon HD 6970M 40 PCIe 2.1 x16 2048 680 900 9602(192×5):48:32 21.76 32.64 115.2 GDDR5 256 1305.6 11 4.1 UVD3, used in Dell M6600
FirePro M2000 2012 Turks Radeon HD 7590M 40 PCIe 2.1 x16 1024 500 800 4802:24:8 4 12 25.6 GDDR5 64 480 11.1 4.2 Dell Precision M6700
FirePro M4000 2012 Cape Verde Radeon HD 7770M 28 PCIe 2.1 x16 2048 600 1000 5122:32:16 9.6 19.2 51.2 GDDR5 128 614.4 11.1 4.2 HP EliteBook 8770w, Dell Precision M6700
FirePro M6000 2012 Cape Verde Radeon HD 7870M 28 PCIe 3.0 x16 2048 800 1000 6402:40:16 12 30 64 GDDR5 128 960 11.1 4.2 Dell Precision M6700
FirePro M4100 2013 Oland Radeon HD 8750M 28 PCIe 3.0 x16 2048 670 1000 3842:24:8 5.4 16.1 64 GDDR5 128 514.6 11.2 4.4 HP ZBook 14
FirePro M5100 2013 Cape Verde Radeon HD 8870M 28 PCIe 3.0 x16 2048 775 1125 6402:40:16 12.4 31 72 GDDR5 128 992 11.2 4.4
FirePro M6100 2013 Bonaire 28 PCIe 3.0 x16 2048 1075 1375 7682:48:16 17.2 51.6 88 GDDR5 128 1651.2 11.2 4.4 Dell Precision M6800

2 Unified Shaders : Texture mapping units : Render output units

Comparison table: Console GPUs

Console graphics processors

Model Launch Code name Fab (nm) Bus interface Core clock (MHz) Core config1 Fillrate Memory (MB) Memory clock (MHz) Memory API compliance (version) Processing Power
GFLOPs
Notes
MOperations/s MPixels/s MTextels/s Vertices/s Bandwidth (GB/s) RAM type Bus width (bit) DirectX OpenGL other
Flipper (GameCube)[61] September 14, 2001 180 Integrated 162 4:1:4:41 648 648 648 60.75 24 shared
16 shared
3 eDRAM
324
81
162
2.7
0.08
10.4/7.63
1T-SRAM
SDRAM
eDRAM
64
8
No Un­known Un­known 8 Fixed-function T&L, TEV "pixel shader"
Xenos (Xbox 360)[62] November 22, 2005 Xenon
Zephyr
Opus
Falcon
Jasper
Vejle
Corona
90/90
90/90
90/80
80/80
65/80
45/65
45/45
Integrated 500 48:16:82 240,000 4000 8000 6000 512 (shared)
10 eDRAM
700
500
22.4
32 (GPU to daughter die)
256 (Daughter die ROP to eDRAM)
GDDR3
eDRAM
128 9.0c+ No Un­known 240 Surface tessellation
Hollywood (Wii) November 19, 2006 90 Integrated 243 4:1:4:41 972 972 972 91.125 24 shared
64 shared
3 eDRAM
486
Unknown
243
4
4
15.6/11.4
1T-SRAM
GDDR3
eDRAM
64
Unknown
Unknown
No Un­known Un­known 11 Fixed-function T&L, TEV "pixel shader"
Latte (Wii U) November 18, 2012 45 Integrated 550 320:16:82 352,000 4400 8800 Unknown 2048 (shared)
32 eDRAM
800 (1600 effective)
550
12.8
70.4
DDR3
eDRAM
64
1024
No Un­known Un­known 352
Liverpool (PlayStation 4) November 15, 2013 Liverpool 28 Integrated 800 1152:72:32 1,843,200 25,600 57,600 Unknown 8192 (shared) 1375 (5500 effective) 176 GDDR5 256 No 4.2 GNM, GNMX, PlayStation Shader Language, Mantle technically possible 1843.2
Durango (Xbox One) November 22, 2013 Durango 28 Integrated 853 768:48:16 1,310,208 13,648 40,944 Unknown 8192 (shared)
32 eSRAM
1066 (2133 effective)
1706 (3412 effective)
68.2
204
DDR3
eSRAM
256 11.2 [63] No Mantle technically possible 1310.2 Tiled resources
Model Launch Code name Fab (nm) Bus interface Core clock (MHz) Core config1 MOperations/s MPixels/s MTextels/s Vertices/s Memory (MB) Memory clock (MHz) Bandwidth (GB/s) RAM type Bus width (bit) DirectX OpenGL Other Processing Power
GFLOPs
Notes
Fillrate Memory API compliance (version)

1 Pixel shaders : Vertex shaders : Texture mapping units : Render output units
2 Unified shaders : Texture mapping units : Render output units
3 10.4 GB/s texture bandwidth. 7.6 GB/s framebuffer bandwidth.

  • The latte looks rather similar to the RV730 used in the Radeon HD4650/4670.[64] Although It's an even closer possibly exact specification match to the HD5550 as it has exactly the same clock, number of Shaders, Texture mapping units & Render Outputs[65]

See also

References

  1. ^ Astle, Dave (2003-04-01). "Moving Beyond OpenGL 1.1 for Windows". gamedev.net. Retrieved 2007-11-15.
  2. ^ a b c OpenGL 2.1 specification
  3. ^ http://www.opengl.org/registry/doc/glspec30.20080811.pdf OpenGL 3.0 specification. Retrieved August 12, 2008.
  4. ^ OpenGL 3.1 specification. Retrieved October 1, 2009.
  5. ^ OpenGL 3.2 specification. Retrieved October 1, 2009.
  6. ^ http://www.tweakpc.de/hardware/tests/cpu/amd_a10-7850k_a10-7700k/s06.php
  7. ^ http://www.hitechreview.com/it-products/pc/amd%E2%80%99s-kaveri-chips-to-significantly-boost-performance/45507/
  8. ^ Wasson, Scott. "AMD jettisons ATI brand name, makes Radeon its own". The Tech Report. Retrieved 9 January 2011.
  9. ^ "XPERT 98 (RAGE XL)". https://web.archive.org/web/20011219195900/http://support.ati.com/. ATI. Retrieved 16 July 2014. {{cite web}}: External link in |website= (help)
  10. ^ "Rage XL". http://www.gpuzoo.com. gpuzoo. Retrieved 16 July 2014. {{cite web}}: External link in |website= (help)
  11. ^ "ATI Rage XL". http://www.techpowerup.com. techpowerup. Retrieved 16 July 2014. {{cite web}}: External link in |website= (help)
  12. ^ http://www.techpowerup.com/gpudb/443/radeon-9800-xxl.html
  13. ^ a b c d e f g h i "Powercolor Radeon 9800SE 256 bit Version".
  14. ^ Tech ARP - Radeon 9800 SE to Radeon 9800 Pro Mod Guide
  15. ^ AMD Vendor ID List. Retrieved February 12, 2009.
  16. ^ Angelini, Chris; Abi-Chahla, Fedy (September 23, 2009). "ATI Radeon HD 5870: DirectX 11, Eyefinity, And Serious Speed". Tom's Hardware. Bestofmedia Network. p. 8. Retrieved October 9, 2009.
  17. ^ a b c d AMD Begins to Ship Ontario and Zacate Application Processing Units for Revenue, Xbitlabs.com, 9 November 2010
  18. ^ "AMD launches Radeon 7790: Meet the Xbox 720's GPU". ExtremeTech. 2013-03-22. Retrieved 2013-11-10.
  19. ^ a b c d e "AMD OpenCL 2.0 Driver". support.amd.com/. AMD. Retrieved 2014-11-14.
  20. ^ "AMD Radeon HD 8670 GPU". Amd.com. 2012-10-26. Retrieved 2013-11-10.
  21. ^ "AMD bringt keine neuen Desktop-Grafikkarten vor dem vierten Quartal". 3DCenter.org. 2013-02-09. Retrieved 2013-11-10.
  22. ^ http://www.amd.com/us/Documents/AMD_Radeon_HD_8870_Feature_Summary.pdf
  23. ^ a b c Radeon R9 290X Review AMD's Back In Ultra-High-End Gaming - Hawaii A 6.2 Billion Transistor GPU For Gaming "We've also come to learn that AMD changed the double-precision rate from 1/4 to 1/8 on the R9 290X, yielding a maximum .7 TFLOPS. The FirePro version of this configuration will support full-speed (1/2 rate) DP compute, giving professional users an incentive to spring for Hawaii's professional implementation."
  24. ^ a b AMD Radeon R9 290 Review Fast And $400, But Is It Consistent - Digging Deeper Into Hawaii’s Behavior
  25. ^ a b http://www.extremetech.com/gaming/189034-amd-radeon-r9-285-review-the-gcn-1-2-torpedo-that-takes-out-nvidias-gtx-760
  26. ^ a b c d http://hexus.net/tech/reviews/graphics/74033-sapphire-radeon-r9-285-dual-x-oc-28nm-tonga/
  27. ^ a b c d http://www.amd.com/en-us/products/graphics/desktop/oem/r5
  28. ^ http://www.techpowerup.com/199511/amd-launches-radeon-r5-230-in-the-retail-channel-gigabyte-outs-its-offering.html
  29. ^ http://www.amd.com/en-us/products/graphics/desktop/r5#
  30. ^ http://www.cpu-world.com/news_2014/2014040401_AMD_Launches_Radeon_R5_230_For_Retail_Market.html
  31. ^ http://www.amd.com/en-us/products/graphics/desktop/r5
  32. ^ a b c d e f http://www.amd.com/en-us/products/graphics/desktop/r7
  33. ^ AnandTech Portal Understanding AMD’s Mantle A Low-Level Graphics API For GCN
  34. ^ AMD Radeon R7 260 1GB Video Card Review - Legit ReviewsAMD Cuts Bonaire GPU Features To Get The Price To $109
  35. ^ R7 260X TrueAudio’s First Outing On The Back Of Bonaire - AMD Radeon R9 280X, R9 270X, And R7 260X Old GPUs, New Names
  36. ^ a b c d e f g h http://www.amd.com/en-us/products/graphics/desktop/r9
  37. ^ AMD Preparing Tahiti XTL Revision of Radeon R9 280X Graphic Card For November Release
  38. ^ http://www.anandtech.com/show/8460/amd-radeon-r9-285-review/17
  39. ^ a b AnandTech Portal|The AMD Radeon R9 290X Review
  40. ^ http://www.kitguru.net/components/graphic-cards/anton-shilov/amd-radeon-r9-295-x2-final-specs-revealed-card-may-not-fit-all-pc-cases/
  41. ^ a b ATI Radeon Mobility Graphics Cards
  42. ^ a b AMD Launches World’s First 40 nm Graphics Processors
  43. ^ ATI Device ID page. Retrieved April 1, 2008.
  44. ^ a b c "Zacate CPU and Platform Details", AMD's Low Power Fusion APU: Zacate Unveiled, HotHardware, 9 November 2010, p. 2
  45. ^ a b Ontario/Zacate (Bobcat-Based APUs) And Beta Drivers
  46. ^ AMD Radeon HD 7000M Series Graphics
  47. ^ High-End Workstation Graphics Shootout - AMD FireGL V8650 Vs. NVIDIA QuadroFX 5600
  48. ^ AMD Vendor ID page. Retrieved September 6, 2008.
  49. ^ a b AMD FirePro V5800 and V3800 Review - Evergreen completes the sweep
  50. ^ a b AMD FirePro V4800 & FirePro V7800 Review. Retrieved September 6, 2008.
  51. ^ FireMV 2260 brochure: "Also with Microsoft DirectX 10.1 support the ATI FireMV 2260 exceeds all of the Windows Vista Aero minimum requirements". Retrieved July 12, 2008
  52. ^ ATI FirePro 2460 Multi-View Professional Graphics
  53. ^ http://www.amd.com/en-us/products/graphics/workstation/firepro-3d/2100#
  54. ^ http://www.amd.com/en-us/products/graphics/workstation/firepro-3d/4100#
  55. ^ http://www.amd.com/en-us/products/graphics/workstation/firepro-3d/5100#
  56. ^ http://www.amd.com/en-us/products/graphics/workstation/firepro-3d/7100#
  57. ^ http://www.anandtech.com/show/8196/amd-announces-firepro-w8100
  58. ^ "AMD FirePro™ W9100 Professional Graphics". AMD. Retrieved 16 June 2014.
  59. ^ http://www.amd.com/en-us/products/graphics/workstation/firepro-remote-graphics/s9050#
  60. ^ http://www.amd.com/en-us/products/graphics/workstation/firepro-remote-graphics/s9150#
  61. ^ GameCube vs. Xbox: Part Deux, ExtremeTech. Retrieved July 9, 2007.
  62. ^ Baumann, Dave. ATI Xenos: Xbox 360 Graphics Demystified, Beyond3D, June 13, 2005.
  63. ^ Hagedoorn, Hilbert (July 1, 2013). "MS now Confirms DirectX 11.2 is a Windows 8.1 Exclusive". The Guru of 3D. Retrieved July 1, 2013.
  64. ^ Leadbetter, Richard (2013-02-05). "Wii U graphics power finally revealed • Articles •". Eurogamer.net. Retrieved 2013-11-10.
  65. ^ "ATI Radeon HD 5550 Graphics". Amd.com. Retrieved 2013-11-10.