fbpx
Wikipedia

List of AMD graphics processing units

May 12, 2023

The following is a list that contains general information about GPUs and video cards by AMD, including those by ATI Technologies before 2006, based on official specifications in table-form.

Field explanations

The headers in the table listed below describe the following:

  • Model – The marketing name for the GPU assigned by AMD/ATI. Note that ATI trademarks have been replaced by AMD trademarks starting with the Radeon HD 6000 series for desktop and AMD FirePro series for professional graphics.
  • Codename – The internal engineering codename for the GPU.
  • Launch – Date of release for the GPU.
  • Architecture – The microarchitecture used by the GPU.
  • Fab – Fabrication process. Average feature size of components of the GPU.
  • Transistors – Number of transistors on the die.
  • Die size – Physical surface area of the die.
  • Core config – The layout of the graphics pipeline, in terms of functional units.
  • Core clock – The reference base and boost (if available) core clock frequency.
  • Fillrate
    • Pixel - The rate at which pixels can be rendered by the raster operators to a display. Measured in pixels/s.
    • Texture - The rate at which textures can be mapped by the texture mapping units onto a polygon mesh. Measured in texels/s.
  • Performance
    • Shader operations - How many operations the pixel shaders (or unified shaders in Direct3D 10 and newer GPUs) can perform. Measured in operations/s.
    • Vertex operations - The amount of geometry operations that can be processed on the vertex shaders in one second (only applies to Direct3D 9.0c and older GPUs). Measured in vertices/s.
  • Memory
    • Bus type – Type of memory bus utilized.
    • Bus width – Maximum bit width of the memory bus utilized.
    • Size – Size of the graphics memory.
    • Clock – The reference memory clock frequency.
    • Bandwidth – Maximum theoretical memory bandwidth based on bus type and width.
  • TDP (Thermal design power) – Maximum amount of heat generated by the GPU chip, measured in Watt.
  • TBP (Typical board power) – Typical power drawn by the total board, including power for the GPU chip and peripheral equipment, such as Voltage regulator module, memory, fans, etc., measured in Watt.
  • Bus interface – Bus by which the graphics processor is attached to the system (typically an expansion slot, such as PCI, AGP, or PCIe).
  • API support – Rendering and computing APIs supported by the GPU and driver.

Due to conventions changing over time, some numerical definitions such as core config, core clock, performance and memory should not be compared one-to-one across generations. The following tables are for reference use only, and do not reflect actual performance.

Video codec acceleration

Features overview

The following table shows features of AMD/ATI's GPUs.

[ VisualEditor ]
Name of GPU series Wonder Mach 3D Rage Rage Pro Rage 128 R100 R200 R300 R400 R500 R600 RV670 R700 Evergreen Northern
Islands 		Southern
Islands 		Sea
Islands 		Volcanic
Islands 		Arctic
Islands/Polaris 		Vega Navi 1x Navi 2x Navi 3x
Released 1986 1991 Apr
1996 		Mar
1997 		Aug
1998 		Apr
2000 		Aug
2001 		Sep
2002 		May
2004 		Oct
2005 		May
2007 		Nov
2007 		Jun
2008 		Sep
2009 		Oct
2010 		Jan
2012 		Sep
2013 		Jun
2015 		Jun 2016, Apr 2017, Aug 2019 Jun 2017, Feb 2019 Jul
2019 		Nov
2020 		Dec
2022
Marketing Name Wonder Mach 3D
Rage 		Rage
Pro 		Rage
128 		Radeon
7000 		Radeon
8000 		Radeon
9000 		Radeon
X700/X800 		Radeon
X1000 		Radeon
HD 2000 		Radeon
HD 3000 		Radeon
HD 4000 		Radeon
HD 5000 		Radeon
HD 6000 		Radeon
HD 7000 		Radeon
200 		Radeon
300 		Radeon
400/500/600 		Radeon
RX Vega, Radeon VII 		Radeon
RX 5000 		Radeon
RX 6000 		Radeon
RX 7000
AMD support    
Kind 2D 3D
Instruction set architecture Not publicly known TeraScale instruction set GCN instruction set RDNA instruction set
Microarchitecture TeraScale 1
(VLIW) 		TeraScale 2
(VLIW5) 		GCN 1st
gen 		GCN 2nd
gen 		GCN 3rd
gen 		GCN 4th
gen 		GCN 5th
gen 		RDNA RDNA 2 RDNA 3
Type Fixed pipeline[a] Programmable pixel & vertex pipelines Unified shader model
Direct3D — 5.0 6.0 7.0 8.1 9.0
11 (9_2) 		9.0b
11 (9_2) 		9.0c
11 (9_3) 		10.0
11 (10_0) 		10.1
11 (10_1) 		11 (11_0) 11 (11_1)
12 (11_1) 		11 (12_0)
12 (12_0) 		11 (12_1)
12 (12_1) 		11 (12_1)
12 (12_2)
Shader model — 1.4 2.0+ 2.0b 3.0 4.0 4.1 5.0 5.1 5.1
6.5 		6.7 6.7
OpenGL — 1.1 1.2 1.3 2.1[b][3] 3.3 4.5 (on Linux: 4.5 (Mesa 3D 21.0))[4][5][6][c] 4.6 (on Linux: 4.6 (Mesa 3D 20.0))
Vulkan — 1.0
(Win 7+ or Mesa 17+) 		1.2 (Adrenalin 20.1.2, Linux Mesa 3D 20.0)
1.3 (GCN 4 and above (with Adrenalin 22.1.2, Mesa 22.0)) 		1.3
OpenCL — Close to Metal 1.1 (no Mesa 3D support) 1.2 (on Linux: 1.1 (no Image support) with Mesa 3D) 2.0 (Adrenalin driver on Win7+)
(on Linux: 1.1 (no Image support) with Mesa 3D, 2.0 with AMD drivers or AMD ROCm) 		2.0 2.1 [7] ?
HSA / ROCm —   ?
Video decoding ASIC — Avivo/UVD UVD+ UVD 2 UVD 2.2 UVD 3 UVD 4 UVD 4.2 UVD 5.0 or 6.0 UVD 6.3 UVD 7 [8][d] VCN 2.0 [8][d] VCN 3.0 [9] ?
Video encoding ASIC — VCE 1.0 VCE 2.0 VCE 3.0 or 3.1 VCE 3.4 VCE 4.0 [8][d]
Fluid Motion ASIC[e]       ?
Power saving ? PowerPlay PowerTune PowerTune & ZeroCore Power ?
TrueAudio — Via dedicated DSP Via shaders
FreeSync — 1
2 		?
HDCP[f] ? 1.4 2.2 2.3 [10]
PlayReady[f] — 3.0   3.0 ?
Supported displays[g] 1–2 2 2–6 ?
Max. resolution ? 2–6 ×
2560×1600 		2–6 ×
4096×2160 @ 30 Hz 		2–6 ×
5120×2880 @ 60 Hz 		3 ×
7680×4320 @ 60 Hz [11]
7680×4320 @ 60 Hz PowerColor 		?
/drm/radeon[h]   — ?
/drm/amdgpu[h] — Experimental [12]   ?
  1. ^ The Radeon 100 Series has programmable pixel shaders, but do not fully comply with DirectX 8 or Pixel Shader 1.0. See article on R100's pixel shaders.
  2. ^ R300, R400 and R500 based cards do not fully comply with OpenGL 2+ as the hardware does not support all types of non-power of two (NPOT) textures.
  3. ^ OpenGL 4+ compliance requires supporting FP64 shaders and these are emulated on some TeraScale chips using 32-bit hardware.
  4. ^ a b c The UVD and VCE were replaced by the Video Core Next (VCN) ASIC in the Raven Ridge APU implementation of Vega.
  5. ^ Video processing ASIC for video frame rate interpolation technique. In Windows it works as a DirectShow filter in your player. In Linux, there is no support on the part of drivers and / or community.
  6. ^ a b To play protected video content, it also requires card, operating system, driver, and application support. A compatible HDCP display is also needed for this. HDCP is mandatory for the output of certain audio formats, placing additional constraints on the multimedia setup.
  7. ^ More displays may be supported with native DisplayPort connections, or splitting the maximum resolution between multiple monitors with active converters.
  8. ^ a b DRM (Direct Rendering Manager) is a component of the Linux kernel. AMDgpu is the Linux kernel module. Support in this table refers to the most current version.

API overview

The following table shows the graphics and compute APIs support across AMD GPU micro-architectures. Note that a branding series might include older generation chips.

[ VisualEditor ]
Chip series Micro­architecture Fab Supported APIs AMD support Year introduced Introduced with
Rendering Computing / ROCm
Vulkan[13] OpenGL[14] Direct3D HSA OpenCL
Wonder Fixed-pipeline[a] 1000 nm
800 nm 		— — — — — Ended 1986
Mach 800 nm
600 nm 		1991
3D Rage 500 nm 5.0 1996 3D Rage
Rage Pro 350 nm 1.1 6.0 1997 Rage Pro
Rage 128 250 nm 1.2 1998 Rage 128 GL/VR
R100 180 nm
150 nm 		1.3 7.0 2000 Radeon
R200 Programmable
pixel & vertex
pipelines 		150 nm 8.1 2001 Radeon 8500
R300 150 nm
130 nm
110 nm 		2.0[b] 9.0
11 (FL 9_2) 		2002 Radeon 9700
R420 130 nm
110 nm 		9.0b
11 (FL 9_2) 		2004 Radeon X800
R520 90 nm
80 nm 		9.0c
11 (FL 9_3) 		2005 Radeon X1800
R600 TeraScale 1 80 nm
65 nm 		3.3 10.0
11 (FL 10_0) 		ATI Stream 2007 Radeon HD 2900 XT
RV670 55 nm 10.1
11 (FL 10_1) 		ATI Stream APP[15] Radeon HD 3850/3870
RV770 55 nm
40 nm 		1.0 2008 Radeon HD 4850/4870
Evergreen TeraScale 2 40 nm 4.5
(Linux 4.2)
[16][17][18][c]		 11 (FL 11_0) 1.2 2009 Radeon HD 5850/5870
Northern Islands TeraScale 2
TeraScale 3 		2010 Radeon HD 6850/6870
Radeon HD 6950/6970
Southern Islands GCN 1st gen 28 nm 1.0 4.6 11 (FL 11_1)
12 (FL11_1) 		  1.2
2.0 possible 		2012 Radeon HD 7950/7970
Sea Islands GCN 2nd gen 1.2 11 (FL 12_0)
12 (FL 12_0) 		2.0
(1.2 in MacOS, Linux)
2.1 Beta in Linux ROCm
2.2 possible 		2013 Radeon HD 7790
Volcanic Islands GCN 3rd gen 2014 Radeon R9 285
Polaris GCN 4th gen 14 nm Current 2016 Radeon RX 480
Vega GCN 5th gen 14 nm
7 nm 		1.2
1.3 possible 		11 (FL 12_1)
12 (FL 12_1) 		2017 Radeon Vega Frontier Edition
Navi RDNA 7 nm 2019 Radeon RX 5700 (XT)
Navi 2X RDNA 2 7 nm
6 nm 		11 (FL 12_1)
12 (FL 12_2) 		2020 Radeon RX 6800 (XT)
Navi 3X RDNA 3 6 nm
5 nm 		1.3 ? ? 2022 Radeon RX 7900 XT(X)
  1. ^ Radeon 7000 Series has programmable pixel shaders, but do not fully comply with DirectX 8 or Pixel Shader 1.0. See article on R100's pixel shaders.
  2. ^ These series do not fully comply with OpenGL 2+ as the hardware does not support all types of non-power-of-two (NPOT) textures.
  3. ^ OpenGL 4+ compliance requires supporting FP64 shaders and these are emulated on some TeraScale chips using 32-bit hardware.

[19][20][21]

Desktop GPUs

Wonder series

Main article: ATI Wonder series
Model Launch Fab (nm) Bus interface Memory
Size (KiB) Bus type Bus width (bit)
Wonder MDA/CGA 1986 1000 PC/XT 64 DRAM 8
Wonder EGA 1987 PC/XT 256
Wonder VGA 1987 1000, 800 PC/XT, ISA 256, 512
1024 		8, 16

Mach series

Main article: ATI Mach
Model Launch Fab (nm) Bus interface Memory
Size (KiB) Bus type Bus width (bit)
Mach 8 1991 800 ISA, MCA 512, 1024 DRAM, VRAM 32
Mach 32 1992 ISA, EISA, VLB, PCI, MCA 1024, 2048 DRAM, VRAM 64
Mach 64 CX 1994 700 ISA, VLB, PCI 1024, 2048, 4096 DRAM, VRAM
Mach 64 GX
Mach 64 CT 1995 600 PCI DRAM, VRAM, EDO
Mach 64 VT (264VT)
Mach 64 VT2 (264VT2) 1996 EDO
Mach 64 VT4 (264VT4) 1998 2048, 4096 EDO, SGRAM

Rage series

Main article: ATI Rage
Model Launch GPU arch Fab (nm) Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory API compliance
MOperations/s MPixels/s MTexels/s MVertices/s Size (MiB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3D OpenGL
3D Rage April 1996[22] Mach64 500 PCI 40 40 1:0:1:1 40 40 40 0 2 0.32 EDO 64 5.0 None2
3D Rage II September 1996 Mach64 (Rage2 for Rage IIc) AGP 1× (Rage IIc only), PCI 60 83 (66 MHz with EDO) 60 60 60 2, 4, 8 0.664 EDO, SGRAM, SDR
Rage Pro March 1997 Rage 3 350 AGP 1x, AGP 2×, PCI 75 75 75 75 75 4, 8, 16 0.6 6.0 1.1
Rage XL[23][24][25][26] August 1998 250 AGP 2×, PCI 83 125 83 83 83 8 1.0 SDR
Rage 128 VR Rage 4 80 120 2:0:2:2 160 160 160 8, 32 0.96 1.2
Rage 128 GL 103 103 206 206 206 16, 32 1.648 SGRAM, SDR 128
Rage 128 Pro August 1999 AGP 4×, PCI 125 143 250 250 250 2.288
Rage 128 Ultra 130 130 260 260 260 16, 32, 64 2.088 SDR
Rage Fury MAXX October 1999 AGP 4× 125 143 2:0:2:2 ×2 500 500 500 32 ×2 4.576 128 ×2

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

Radeon 7000 series

Main article: Radeon R100 series
  • All models include Direct3D 7.0 and OpenGL 1.3
  • The R100 cards were originally launched without any numbering as Radeon SDR, DDR, LE and VE; these products were later "rebranded" to their names within the numbered naming scheme, when the Radeon 8000 series was introduced.
Model Launch Code name Fab (nm) Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MiB) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon VE / Radeon 7000 February 19, 2001 RV100 (piglet) 180 AGP 4x, PCI 150/166/183 150/166/183 1:0:3:1 183 (max) 336 (max) 549 (max) 0 32, 64 2.688 (max) DDR 64
Radeon LE / Radeon 7100 (OEM) April 6, 2001[27] Rage 6 / R100 AGP 4x 150 150 2:1:6:2 296 296 888 37.5 32 4.736 128
Radeon SDR / Radeon 7200 (SDR) June 1, 2000 AGP 4x, PCI 166 166 333 333 996 41.5 2.656 SDR
Radeon DDR / Radeon 7200 (DDR) April 1, 2000 AGP 4x 166/183A 166/183A 333/366A 333/366A 966/1098A 41.5/45.75A 32, 64 5.312/5.856A DDR
Radeon DDR / Radeon 7200 VIVO 2001 AGP 4x, PCI 166/183B 166/183B 333/366B 333/366B 966/1098B 41.5/45.75B 64 5.312/5.856B
Radeon DDR / Radeon 7500 VIVO "SE" 200 200 400 400 1200 50.0 6.400
Radeon 7500 LE RV200 (morpheus) 150 250 175 500 500 1500 62.5 32, 64 5.600 64
128
Radeon 7500 August 14, 2001 RV200 (morpheus) 290 230 580 580 1740 72.5 32, 64, 128[28] 7.360 128

1 Pixel pipelines : 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 Direct3D 7.0 and OpenGL 1.3
  • Based on the Radeon VE
Model Launch Code name Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MiB) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon 320 May 2002 A3 FSB 160 200, 266 1:0:3:1 160 160 480 0 ? 1.6, 2.128 DDR 64
Radeon 330 2002 RS200L (wilma) 150 150 150 450
Radeon 340 RS200 (wilma) 183 183 183 549

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

Radeon 8000 and 9000 series

Main article: Radeon R200 series
  • All models are manufactured with a 150 nm fabrication process
  • All models include Direct3D 8.1 and OpenGL 1.4
Model Launch Code name Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MiB) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon 8500 August 14, 2001 R200 (chaplin) AGP 4×, PCI 275 275 4:2:8:4 1100 1100 2200 137.5 64, 128 8.8 DDR 128
Radeon 8500 LE October 30, 2001 250 250 1000 1000 2000 125 8
Radeon 9000 August 1, 2002 RV250 (iris) 200 4:1:4:4 1000 50 6.4
Radeon 9000 Pro 275 275 1100 1100 1100 68.75 8.8
Radeon 9100 April 1, 2003 R200 (chaplin) 250 250 4:2:8:4 1000 1000 2000 125 8.0

4.0

128

64

Radeon 9200 RV280 (argus) AGP 8×, PCI 200 4:1:4:4 1000 62.5 64, 128, 256 6.4 128
Radeon 9200 SE March 1, 2003 200 166 800 800 800 50 2.67 64
Radeon 9250 March 1, 2004 240 200 960 960 960 60 3.2, 6.4 64, 128
Radeon 9250 SE 2004 AGP 8x 64

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

IGP (9000 series)

  • All models are manufactured with a 150 nm fabrication process
  • All models include Direct3D 8.1 and OpenGL 1.4
  • Based on the Radeon 9200
Model Launch Code name Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MiB) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon 9000 2003 RC350 FSB 300 400 4:1:2:2 600 600 600 75 16 - 128 3.2 DDR 64
Radeon 9100 RS300 (superman) 6.4 128
Radeon 9100 Pro May 3, 2004 RS350

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

Radeon R300 series

AGP (9000 series, X1000 series)

Main article: Radeon R300 series
  • All models include Direct3D 9.0 and OpenGL 2.0
  • All models use an AGP 8x interface
Model Launch Code name Fab (nm) Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MiB) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon 9500 October 24, 2002 R300 (Khan) 150 275 270 4:4:4:4 1100 1100 1100 275 64, 128 8.64

17.28

DDR 128

256

Radeon 9500 Pro 8:4:8:8 2200 2200 2200 128 8.64 128
Radeon 9550 2004 RV350 (Shivah) 130 250 200 4:2:4:4 1000 1000 1000 125 64, 128, 256 6.4
Radeon 9550 SE 3.2 64
Radeon 9600 2003 325 1300 1300 1300 162.5 128, 256 6.4 128
Radeon 9600 Pro March 6, 2003 400 300 1600 1600 1600 200 9.6
Radeon 9600 SE 2003 325 200 1300 1300 1300 162.5 64, 128, 256 3.2 64
Radeon 9600 XT September 30, 2003 RV360 500 300 2000 2000 2000 250 128, 256 9.6 128
Radeon 9600 TX 2003 (Medion OEM) R300 (Khan) 150 297 270 8:4:8:8 2376 2376 2376 287 128 8.6
Radeon 9700 TX 2002 (Dell OEM) 263 263 2104 2104 2104 275 16.83 256
Radeon 9700 October 24, 2002 275 270 2200 2200 2200 17.28
Radeon 9700 Pro July 18, 2002 325 310 2600 2600 2600 325 19.84
Radeon 9800 2003 R350
Radeon 9800 XL 350 2800 2800 2800 350
Radeon 9800 XXL[29] October 1, 2003 R360 390 338 3120 3120 3120 390 21.60 256[29]
Radeon 9800 Pro (R350) March 1, 2003[30] R350 380 340 (128 MB)

350 (256 MB)

3040 3040 3040 380 128

256

21.76

22.40

DDR

GDDR2

256
Radeon 9800 Pro (R360) 2003 R360 340 128 21.76 DDR
Radeon 9800 SE[31] March 1, 2003[32] R350 325

380[31]

 270

340[31]

 4:4:4:4[32] 1300

1520[31]

 1300

1520[31]

 1300

1520[31]

 325

380[31]

 128

256

8.64

21.76[31]

 DDR 128

2562[31]

Radeon 9800 XT September 9, 2003 R360 412 365 8:4:8:8 3296 3296 3296 412 256 23.36 256
Radeon X1050 AGP December 7, 2006 RV350 (Shivah) 130 250 200 4:2:4:4 1000 1000 1000 125 128, 256 6.4 128
Model Launch Code name Fab (nm) Core clock (MHz) Memory clock (MHz) Core config1 MOperations/s MPixels/s MTexels/s MVertices/s Size (MiB) 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.[33]

PCI-E (X3xx, X5xx, X6xx, X1000 series)

Main article: Radeon R300 series
  • All models include Direct3D 9.0 and OpenGL 2.0
  • All models use a PCI-E ×16 interface
Model Launch Code name Fab (nm) Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MiB) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon X300 September 1, 2004 RV370 (hari) 110 325 200 4:2:4:4 1300 1300 1300 162.5 64, 128 6.4 DDR 128
Radeon X300 LE
Radeon X300 SE 3.2 64
Radeon X300 SE HyperMemory April 4, 2005 300 32, 64, 128 onboard + up to 128 system
Radeon X550 June 21, 2005 400 250 1600 1600 1600 200 128, 256 8

4

128

64

Radeon X550 HyperMemory 128, 256 onboard + up to 512 system
Radeon X600 SE September 1, 2004 325 1300 1300 1300 162.5 128, 256 4 64
Radeon X600 400 1600 1600 1600 200 8 128
Radeon X600 Pro (RV370) 300 9.6
Radeon X600 Pro (RV380) RV380 (vishnu) 130
Radeon X600 XT 500 370 2000 2000 2000 250 11.84
Radeon X1050 (RV370) December 7, 2006 RV370 (hari) 110 400 250
333 		1600 1600 1600 200 5.328 DDR
DDR2 		64
128

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

IGP (X2xx, 11xx series)

Main article: Radeon R300 series
  • All models include Direct3D 9.0 and OpenGL 2.0
  • Based on the Radeon X300
Model Launch Code name Fab (nm) Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MiB) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon Xpress X200 November 8, 2004 RS480 (metallo) 130 HT 300 200-400 (DDR), 200 (sideport) 4:2:2:2 600 600 600 0 16-128 system + 16 sideport 1.6-6.4 system + 0.8 sideport DDR 64, 128
Radeon Xpress 1100 (originally Xpress 200) 2005 RS482 (grayskull) 110 HT 300 200-400 (DDR), 400-800 (DDR2) 16-128 system 1.6-

12.8 system

DDR, DDR2
Radeon Xpress 1150 (originally Xpress 200 for Intel) March 11, 2005 (Intel), May 23, 2006 (AMD) RC400, RC410, RS400, RS415, RS485 HT, FSB 400 800 800 800 1.6-12.8

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

Radeon X700 and X800 series

AGP (X7xx, X8xx)

Main article: Radeon R400 series
  • All models include AGP 8×
  • All models include Direct3D 9.0b and OpenGL 2.0
Model Launch Code name Fab (nm) Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon X700 Mar 2005 RV410 (alto) 110 400 350 8:6:8:8 3200 3200 3200 600 128, 256 11.2 DDR 128
Radeon X700 Pro Mar 1, 2005 425 432 3400 3400 3400 637.5 13.824 GDDR3
Radeon X800 SE Oct 2004 R420 (loki) 130 400 6800 256 25.6 256
Radeon X800 GT December 6, 2005 475 490 8:6:8:16 3800 7600 3800 712.5 31.36
Radeon X800 Dec. 2004 R430 110 400 350 12:6:12:16 4800 6400 4800 600 22.4
Radeon X800 GTO December 6, 2005 R420 (loki) 130 490 31.36
Radeon X800 Pro May 5, 2004 475 450 5700 7600 5700 712.5 28.8
Radeon X800 XL February 2, 2005 R430 110 400 490 16:6:16:16 6400 6400 6400 600 31.36
Radeon X800 XT May 4, 2004 R420 (loki) 130 500 500 8000 8000 8000 750 32
Radeon X800 XT PE 520 560 8320 8320 8320 780 35.84
Radeon X850 Pro February 28, 2005 R481 507 520 12:6:12:16 6084 8112 6084 760.5 33.28
Radeon X850 XT 520 540 16:6:16:16 8320 8320 8320 780 34.56
Radeon X850 XT PE 540 590 8640 8640 8640 810 37.76

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

PCI-E (X5xx, X7xx, X8xx, X1000 series)

Main article: Radeon R400 series
  • All models include PCI-E ×16
  • All models include Direct3D 9.0b and OpenGL 2.0
Model Launch Code name Fab (nm) Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon X550 XT January 24, 2007 RV410 (alto) 110 400 300 4:6:4:8 1600 3200 1600 600 128 4.8

9.6

DDR

GDDR3

64

128

Radeon X550 XTX 8:6:8:8 3200 3200
Radeon X700 SE April 1, 2005 200
250 		4:6:4:8 1600 1600 128 3.2 DDR 64
Radeon X700 LE December 21, 2004 250 8:6:8:8 3200 3200 128 4
Radeon X1050 (RV410) Jan, 25, 2008 200 128, 256 6.4 128
Radeon X700 Sept. 2005 250
350 		8
11.2
Radeon X700 Pro December 21, 2004 425 432 3400 3400 3400 637.5 128, 256 13.824 GDDR3
Radeon X700 XT Never Released 475 525 3800 3800 3800 712.5 128, 256 16.8
Radeon X740 XL March 7, 2005 (Medion OEM) 425 450 3400 3400 3400 637.5 128 14.4
Radeon X800 GT 128MB August 1, 2005 R423
R480 (thor) 		130 475 175 8:6:8:16 3800 7600 3800 712.5 128 22.4 DDR 256
Radeon X800 GT 256MB 490 256 31.36 GDDR3
Radeon X800 December 1, 2004 R430 (thor) 110 392 350 12:6:12:16 4704 6272 4704 588 128, 256 22.4
Radeon X800 GTO 128MB September 15, 2005 R423
R480
R430 (thor) 		130
110 		400 4800 6400 4800 600 128 22.4
Radeon X800 GTO 256MB 490 256 31.36
Radeon X800 Pro May 5, 2004 R423 (thor) 130 475 450 5700 7600 5700 712.5 28.8
Radeon X800 XL December 1, 2004 (256 MB)
May 4, 2005 (512 MB) 		R430 (thor) 110 400 490 16:6:16:16 6400 6400 6400 600 256, 512 31.36
Radeon X800 XT December 1, 2004 R423 (thor) 130 500 500 8000 8000 8000 750 256 32
Radeon X800 XT Platinum Edition May 5, 2004 520 560 8320 8320 8320 780 35.84
Radeon X850 Pro December 1, 2004 R480 (thor) 507 520 12:6:12:16 6084 8112 6084 760.5 33.28
Radeon X850 XT 520 540 16:6:16:16 8320 8320 8320 780 34.56
Radeon X850 XT CrossFire Master September 29, 2004 520 34.56
Radeon X850 XT Platinum Edition December 21, 2004 540 590 8640 8640 8640 810 37.76
Model Launch Code name Fab (nm) Core clock (MHz) Memory clock (MHz) Core config1 MOperations/s MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit)
Fillrate Memory

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

IGP (X12xx, 21xx)

Main article: Radeon R400 series
  • All models include Direct3D 9.0b and OpenGL 2.0
  • Based on Radeon X700
Model Launch Code name Fab (nm) Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon Xpress X1200 February 28, 2007 RS690C (zeus) 80 HT 2.0 350 400 – 800 4:2:4:4 1400 1400 1400 175 256 – 512 6.4 – 12.8 DDR2 128
Radeon Xpress X1250 August 29, 2006 (Intel), February 28, 2007 (AMD) RS600, RS690 (zeus) FSB, HT 2.0 400 1600 1600 1600 200
Radeon Xpress 2100 March 4, 2008 RS740 (titan) 55 HT 2.0 500 2000 2000 2000 250

Radeon X1000 series

Main article: Radeon X1000 series

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

Model Launch Code name Fab (nm) Transistors (million) Die size (mm2) Bus interface Clock rate Core config Fillrate Memory TDP (Watts) API support (version) Release Price (USD)
Core (MHz) Memory (MHz) MOperations/s MPixels/s MVertices/s MTexels/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Max. Direct3D OpenGL
Radeon X1300 October 5, 2005 (PCI-E)
December 1, 2005 (AGP) 		RV515 90 107 100 AGP 8×
PCI
PCI-E ×16 		450 250 4:2:4:4 1800 1800 225 1800 128
256 		8.0 DDR DDR2 128 9.0c 2.1 $99 (128MB)
$129 (256MB)
Radeon X1300
HyperMemory 		October 5, 2005 PCI-E ×16 128
256
512 		4.0 DDR2 64 $
Radeon X1300 PRO October 5, 2005 (PCI-E)
November 1, 2006 (AGP) 		AGP 8×
PCI-E ×16 		600 400 2400 2400 300 2400 128
256 		12.8 128 31 $149
Radeon X1300 XT August 12, 2006 RV530 157 150 500 12:5:4:4 6000 2000 625 2000 22 $89
Radeon X1550 January 8, 2007 RV516 107 100 AGP 8x
PCI
PCI-E x16 		4:2:4:4 2200 2200 275 2200 128
256
512 		27 $
Radeon X1600 PRO October 10, 2005 RV530 157 150 AGP 8×
PCI-E ×16 		390
390–690 		12:5:4:4 6000 2000 625 2000 12.48 DDR2
GDDR3 		41 $149 (128MB)
$199 (256MB)
Radeon X1600 XT October 10, 2005 (PCI-E) 590 690 7080 2360 737.5 2360 256
512 		22.08 GDDR3 42 $249
Radeon X1650 February 1, 2007 500 400 6000 2000 625 2000 12.8 DDR2 $
Radeon X1650 SE RV516 105 PCI-E ×16 635 4:2:4:4 256 DDR2 $
Radeon X1650 GT May 1, 2007 (PCI-E)
October 1, 2007 (AGP) 		RV560 80 330 230 AGP 8×
PCI-E x16 		400 24:8:8:8 9600 3200 800 3200 256
512 		GDDR3 $
Radeon X1650 PRO August 23, 2006 (PCI-E)
October 15, 2006 (AGP) 		RV535 131 600 700 12:5:4:4 7200 2400 750 2400 22.4 44 $99
Radeon X1650 XT October 30, 2006 RV560 230 525 24:8:8:8 12600 4200 1050 4200 55 $149
Radeon X1700 FSC November 5, 2007 (OEM) RV535 131 PCI-E ×16 587 695 12:5:4:4 7044 2348 733 2348 256 22.2 44 OEM
Radeon X1700 SE November 30, 2007 RV560 230 500 500 24:8:8:8 12000 4000 1000 4000 512 16.0 50 $
Radeon X1800
CrossFire Edition 		December 20, 2005 R520 90 321 288 600 700 16:8:16:16 9600 9600 900 9600 512 46.08 256 113 $
Radeon X1800 GTO March 9, 2006 500 495 12:8:12:8 6000 6000 1000 6000 256
512 		32.0 48 $249
Radeon X1800 XL October 5, 2005 500 16:8:16:16 8000 8000 1000 8000 256 70 $449
Radeon X1800 XT 625 750 10000 10000 1250 10000 256
512 		48.0 113 $499 (256MB)
$549 (512MB)
Radeon X1900
CrossFire Edition 		January 24, 2006 R580 384 352 625 725 48:8:16:16 30000 512 46.4 100 $599
Radeon X1900 GT May 5, 2006 575 600 36:8:12:12 20700 6900 1150 6900 256 38.4 75 $
Radeon X1900 GT Rev. 2 September 7, 2006 512 18432 6144 1024 6144 42.64
Radeon X1900 XT January 24, 2006 625 725 48:8:16:16 30000 10000 1250 10000 256
512 		46.4 100 $549
Radeon X1900 XTX R580 650 775 31200 10400 1300 10400 512 49.6 135 $649
Radeon X1950
CrossFire Edition 		August 23, 2006 R580+ 80 1000 31200 10400 1300 10400 64 GDDR4 $449
Radeon X1950 GT January 29, 2007 (PCI-E)
February 10, 2007 (AGP) 		RV570 330 230 AGP 8x
PCI-E x16 		500 600 36:8:12:12 18000 6000 1000 6000 256
512 		38.4 GDDR3 57 $140
Radeon X1950 PRO October 17, 2006 (PCI-E)
October 25, 2006 (AGP) 		575 690 20700 6900 1150 6900 44.16 66 $199
Radeon X1950 XT October 17, 2006 (PCI-E)
February 18, 2007 (AGP) 		R580+ 384 352 AGP 8x
PCI-E 1.0 x16 		625 700 (AGP)
900 (PCI-E) 		48:8:16:16 30000 10000 1250 10000 44.8 (AGP)
57.6 (PCI-E) 		96 $
Radeon X1950 XTX October 17, 2006 PCI-E 1.0 ×16 650 1000 31200 10400 1300 10400 512 64 GDDR4 125 $449
Model Launch Code name Fab (nm) Transistors (million) Die size (mm2) Bus interface Core (MHz) Memory (MHz) Core config MOperations/s MPixels/s MVertices/s MTexels/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Max. Direct3D OpenGL Release price (USD)
Clock rate Fillrate Memory TDP (Watts) API support (version)

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

Radeon HD 2000 series

Main articles: Radeon HD 2000 series and TeraScale 1
Model Launch Code name Fab (nm) Transistors (million) Die size (mm2) Bus interface Clock rate Core config Fillrate Memory Processing power
(GFLOPS) 		TDP (Watts) Crossfire support API support (version) Release price (USD)
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (Bit) Single precision Double precision Max. Direct3D OpenGL OpenCL
Radeon HD 2350 June 28, 2007 RV610 65 180 85 PCIe 1.0 ×16 525 400 40:4:4 2.10 2.10 64 onboard + up to 256 system 3.20 DDR2 32 42.0 — 20 No 10.0 3.3 APP Stream Only ?
Radeon HD 2400 PRO PCIe 1.0 ×16
AGP
PCI 		128
256
512 		6.40 64 $50–55
Radeon HD 2400 XT PCIe 1.0 ×16 650 500
700 		2.60 2.60 256 8.0
11.2 		DDR2
GDDR3 		52.0 25 $75–85
Radeon HD 2600 PRO RV630 390 153 PCIe 1.0 ×16
AGP 		600 120:8:4 2.40 4.80 256
512 		16.0
22.4 		128 144.0 35 $89–99
Radeon HD 2600 XT 800 800
1100 		3.20 6.40 25.6
35.2 		GDDR3
GDDR4 		192.0 45
50 		4-way CrossFire $119 (GDDR3) $149 (GDDR4)
Radeon HD 2900 GT November 6, 2007 R600 GT 80 720 420 PCIe 1.0 ×16 601 800 240:12:12 7.21 7.21 51.2 GDDR3 256 288.5 150 $200
Radeon HD 2900 PRO September 25, 2007 R600 PRO 600 800
925 		320:16:16 9.6 9.6 512
1024 		51.2
102.4
118.4 		GDDR3
GDDR4 		256
512 		384.0 200 $250 (GDDR3)
$300 (GDDR4)
Radeon HD 2900 XT May 14, 2007 R600 XT 743 828
1000 		11.9 11.9 105.6
128.0 		GDDR3
GDDR4 		512 475.5 215 $399

Radeon HD 3000 series

Main article: Radeon HD 3000 series
Model Launch Code name Fab (nm) Transistors (million) Die size (mm2) Bus interface Clock rate Core config Fillrate Memory Processing power
(GFLOPS) 		TDP (Watts) Crossfire Support API support (version) Release price (USD)
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (Bit) Single precision Double precision Max. Direct3D OpenGL OpenCL, ATI Stream
Radeon HD 3410 May 7, 2009 RV610 65 180 85 PCIe 1.0 ×16 519 396 40:4:4 2.08 2.08 256 6.34 DDR2 64 41.52 — 20 No 10.0 3.3 No, Yes ?
Radeon HD 3450 January 23, 2008 RV620 LE 55 181 67 PCIe 2.0 ×16
PCI
AGP 8× 		600 500 2.40 2.40 256
512 		8.00 48.0 25 10.1
Radeon HD 3470 RV620 PRO PCIe 2.0 ×16 800 950 3.20 3.20 15.2 DDR2
GDDR3 		64.0 30
Radeon HD 3550 August 4, 2008 594 396 2.38 2.38 512 6.34 DDR2 47.52
Radeon HD 3570 July 5, 2010 796 495 3.18 3.18 7.92 63.68
Radeon HD 3610 September 24, 2009 RV630 PRO 65 390 153 PCIe 1.0 ×16 594 396 120:8:4 2.38 4.75 512
1024 		12.7 128 142.6 35
Radeon HD 3650 January 23, 2008 RV635 PRO 55 378 PCIe 2.0 ×16
AGP 8× 		725 405
800 		2.90 5.80 256
512
1024 		13.0
25.6 		DDR2
GDDR3
GDDR4 		174.0 65 2-way CrossFire
Radeon HD 3730 October 5, 2008 135 PCIe 2.0 ×16 722 405 2.89 5.78 512
1024 		13.0 DDR2 173.3 No
Radeon HD 3750 796 693 3.18 6.37 512 22.2 GDDR3 191.0 2-way CrossFire
Radeon HD 3830 April 1, 2008 RV670 PRO 666 192 668 828 320:16:16 10.7 10.7 256 26.5 427.5 85.4 75 $129
Radeon HD 3850 November 19, 2007 PCIe 2.0 x16
AGP 8x 		830
900 		256
512
1024 		53.1
57.6 		GDDR3
GDDR4 		256 85.4 4-way CrossFire $179
Radeon HD 3870 RV670 XT 777 900
1126 		12.4 12.4 512
1024 		57.6
72.1 		497.3 99.2 106 $219
Radeon HD 3850 X2 April 4, 2008 RV670 PRO 666×2 192×2 PCIe 2.0 ×16 668 828 320:16:16×2 10.7×2 10.7×2 512×2 53.0×2 GDDR3 256×2 428.2×2 85.6×2 140 2-way CrossFire $349
Radeon HD 3870 X2 January 28, 2008 R680 825 901
1125 		13.2×2 13.2×2 57.6×2
72.1×2 		GDDR3
GDDR4 		528.0×2 105.6×2 165 $449

IGP (HD 3000)

Main article: AMD 700 chipset series
  • All Radeon HD 3000 IGP models include Direct3D 10.0 and OpenGL 3.3
Model Launch Code name Graphics core Fab (nm) Transistors (million) Die size (mm2) Bus interface Core clock2 (MHz) Core config1 Fillrate Memory3 Processing power
(GFLOPS) 		Features / Notes
Pixel (GP/s) Texture (GT/s) FP32 (GP/s) Size (MB) Bandwidth (GB/s) Bus type Effective clock (MHz) Bus width (Bit)
Radeon 3000 Graphics (760G Chipset) 2009 RS780L[34] RV610 55 205 ~73 (~9 × 8.05) HT 3.0 350 40:4:4 1.4 1.4 0.7 Up to 512 system 20.8 (system) HT (system) — — 28 AVIVO
Radeon 3100 Graphics (780V Chipset)
  • 2008
  • Jan 23 (China)
  • Mar 4 (worldwide)
 RS780C
Radeon HD 3200 Graphics (780G Chipset) RS780 500 2 2 1 Up to 512 system + optional 128 sideport 20.8 (system) + 2.6 (sideport) HT (system) + DDR2-1066 DDR3-1333 (sideport) 1333 (sideport) 16 (sideport) 40 UVD+, 8× AA (wide-tent CFAA)
Radeon HD 3300 Graphics (790GX Chipset) Jul 2008 RS780D 700 2.8 2.8 1.4 Up to 512 system + 128 sideport 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 AMD PowerPlay technology is implemented. The clock frequencies listed here refer to the officially announced clock specifications.
3 The sideport is a dedicated memory bus. It is preferably used for a frame buffer.

All-in-Wonder series

Main article: All-in-Wonder
Model Launch Code name Fab (nm) Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory API (version)
MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3D OpenGL
All-in-Wonder VE December 2, 2002 RV100 180 PCI 183 183 1:0:3:1 183 549 0 64 2.9 DDR 64 7.0 1.3
All-in-Wonder Radeon July 31, 2000 R100 AGP 4× 166 166 2:1:6:2 332 996 41.5 32 5.312 128
All-in-Wonder 7500 January 22, 2002 RV200 150 260 180 520 1560 65 64 5.760
All-in-Wonder 8500 April 4, 2002 R200 260 275 4:2:8:4 1100 2200 137.5 128 8.8 8.1 1.4
All-in-Wonder 8500 DV August 30, 2001 230 190 920 1840 115 64 6.08
All-in-Wonder 9000 Pro March 31, 2003 RV250 AGP 8x 275 225 4:1:4:4 1110 1110 68.75 64, 128 7.2
All-in-Wonder 9200 January 26, 2004 250 200 1000 1000 62.5 128 6.4
All-in-Wonder 9200 SE N/A 166 2.656 64
All-in-Wonder 9600 January 26, 2004 RV350 130 325 400 4:2:4:4 1300 1300 162.5 6.4 128 9.0 2.0
All-in-Wonder 9600 Pro August 5, 2003 400 650 1600 1600 200 10.4
All-in-Wonder 9600 XT January 26, 2004 525 2100 2100 262.5
All-in-Wonder 9700 Pro December 30, 2002 R300 150 325 620 8:4:8:8 2600 2600 325 19.84 256
All-in-Wonder 9800 Pro April 7, 2003 R350 380 680 3040 3040 380 21.76
All-in-Wonder 9800 SE November 1, 2003 4:4:4:8 1520 10.88 128
All-in-Wonder X600 Pro September 21, 2004 RV370 110 400 600 4:2:4:4 1600 1600 200 AGP 128,

PCI-E 256

9.6
All-in-Wonder X800 GT August 8, 2005 R430 PCI-E ×16 490 980 8:6:8:16 6400 3200 600 128 31.36 GDDR3 256 9.0b
All-in-Wonder X800 XL July 5, 2005 PCI-E ×16
AGP 8× 		400 16:6:16:16 6400 256
All-in-Wonder X800 XT September 9, 2004 R420 130 AGP 8× 500 1000 8000 8000 750 32
All-in-Wonder 2006 December 22, 2005 RV515 90 PCI-E ×16 450 800 4:2:4:4 1800 1800 225 12.8 DDR2 128 9.0c
All-in-Wonder X1800 XL November 21, 2005 R520 500 1000 16:8:16:16 8000 8000 1000 32 GDDR3 256
All-in-Wonder X1900 January 24, 2006 R580 960 48:8:16:16 30.72
All-in-Wonder HD 3650 June 28, 2008 RV635 55 725 1200 120:8:4 2900 5800 N/A 512 19.2 DDR2 128 10.1 3.3

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

Radeon HD 4000 series

Main articles: Radeon HD 4000 series and TeraScale 1
Model4 Launch Code name Fab (nm) Transistors (million) Die size (mm2) Bus interface Clock rate Core config1 Fillrate Memory2 Processing power
(GFLOPS) 		TDP3 (Watts) Crossfire support API support (version) Release price (USD)
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Single precision Double precision Idle Max. Direct3D OpenGL OpenCL
Radeon HD 4350 September 30, 2008 RV710 55 242 73 PCIe 2.0 ×16
PCIe 2.0 ×1
AGP 8× 		600 400
650 		80:8:4 2.40 4.80 256
512
1024 		6.40
10.4 		DDR2
DDR3 		64 92.0 No 20 No 10.1 3.3 1.0 ?
Radeon HD 4550 September 30, 2008 PCIe 2.0 ×16 600 655
800 		10.5
12.8 		96.0 No 25
Radeon HD 4570 November 25, 2008 242 650 500 2.60 5.20 1024 8.00 DDR2 104.0 No
Radeon HD 4580 November 20, 2011 RV635 PRO 378 135 796 693 120:8:4 3.18 6.37 512 22.2 GDDR3 128 191.0 No 65
Radeon HD 4650 September 10, 2008 RV730 PRO 514 146 PCIe 2.0 ×16
AGP 8× 		600
650 		400 – 500
500
700 		320:32:8 4.80
5.20 		19.2
20.8 		256
512
1024 		12.8 - 16.0
16.0
22.4 		DDR2
GDDR3
GDDR4 		64
128 		384.0
416.0 		No 48 2-way Crossfire
Radeon HD 4670 September 10, 2008 RV730 XT PCIe 2.0 ×16
AGP 8× 		750 400 – 500
900
1000 		320:32:8 6.00 24.0 512
1024 		12.8 – 16.0
28.8
32.0 		DDR2
GDDR3
GDDR4 		128 480.0 No 59 $79
Radeon HD 4730 June 8, 2009 RV770 CE 956 256 PCIe 2.0 ×16 700
750 		900 640:32:8 5.60
6.00 		22.4
24.0 		512 57.6 GDDR5 896.0
960.0 		179.2
192.0 		110 ?
Radeon HD 4750 September 9, 2009 RV740 40 826 137 730 800 640:32:16 11.7 23.4 51.2 934.4 80
Radeon HD 4770 April 28, 2009 750 800 12.0 24.0 51.2 960.0 192.0 $109
Radeon HD 4810 May 28, 2009 RV770 CE 55 956 256 625
750 		900 640:32:8 5.00
6.00 		20.0
24.0 		57.6 800.0
960.0 		160.0
192.0 		95 ?
Radeon HD 4830 October 21, 2008 RV770 LE 575 900 640:32:16 9.20 18.4 512
1024 		57.6 GDDR3
GDDR4 		256 736.0 147.2 $130
Radeon HD 4850 June 25, 2008 RV770 PRO 625 993 800:40:16 10.0 25.0 512
1024
2048 		63.55 GDDR3
GDDR4
GDDR5 		1000 200.0 110 4-way Crossfire $199
Radeon HD 4860 September 9, 2009 RV790 GT 959 282 700 750 640:32:16 11.2 22.4 512
1024 		96 GDDR5 896.0 179.2 130 ?
Radeon HD 4870 June 25, 2008 RV770 XT 956 256 750 900 800:40:16 12.0 30.0 512
1024
2048 		115.2 1200 240.0 150 $299
Radeon HD 4890 April 2, 2009 RV790 XT 959 282 850 975 13.6 34.0 1024
2048 		124.8 GDDR5 1360 272.0 190 $249
Radeon HD 4850 X2 November 7, 2008 R700 (2xRV770 PRO) 956×2 256×2 625 995 800:40:16×2 10.0×2 25.0×2 512×2
1024×2 		63.7×2 GDDR3 256×2 2000 400.0 250 2-way Crossfire $339
Radeon HD 4870 X2 August 12, 2008 R700 (2xRV770 XT) 750 900 12×2 30×2 1024×2 115.2×2 GDDR5 2400 480.0 286 $449
Model4 Launch Code name Fab (nm) Transistors (million) Die size (mm2) Bus interface Clock rate Core config1 Fillrate Memory2 Processing power
(GFLOPS) 		TDP3 (Watts) Crossfire support API support (version) Release price (USD)
Core (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Single precision Double precision Idle Max. Direct3D OpenGL OpenCL

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

IGP (HD 4000)

Main articles: AMD 700 chipset series and TeraScale 1
  • All Radeon HD 4000 IGP models include Direct3D 10.1 and OpenGL 2.0[35]
Model Launch Code name Graphics core Fab
(nm) 		Transistors
(million) 		Die size
(mm2) 		Bus interface Core Fillrate Memory3 Processing power
(GFLOPS) 		Features / Notes
Config1 Clock2 (MHz) Pixel (GP/s) Texture (GT/s) FP32 (GP/s) Size (MB) 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 40:4:4 500 2 2 1 Up to 512 system + optional 128 sideport 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 700 2.8 2.8 1.4 Up to 512 system + 128 sideport 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.

Radeon HD 5000 series

Main articles: Radeon HD 5000 series and TeraScale 2
  • The HD5000 series is the last series of AMD GPUs which supports two analog CRT-monitors with a single graphics card (i.e. with two RAM-DACs).
  • AMD Eyefinity introduced.


Model Launch Code
name 		Fab
(nm) 		Transistors
(million) 		Die size
(mm2) 		Bus
interface 		Clock rate Core
config[a]		 Fillrate Memory Processing power
(GFLOPS) 		TDP (Watts)[b] CrossFire
support 		API support (version) Release price (USD)
Core
(MHz) 		Memory
(MHz) 		Pixel
(GP/s) 		Texture
(GT/s) 		Size
(MB) 		Bandwidth
(GB/s) 		Bus type Bus width
(Bit) 		Single precision Double precision Idle Max. Direct3D OpenGL OpenCL
Radeon HD 5450 Feb 4, 2010 Cedar 40 292 59 PCIe 2.1 x16
PCI
PCIe 2.1 x1 		650
650
650 		400
800
800 		80:8:4 2.6 5.2 512
1024
2048 		6.4
12.8 		DDR2
DDR3 		64 104 — 6.4 19.1 No 11.3
(11 0) 		4.5 1.2 ~50
Radeon HD 5550 Feb 9, 2010 Redwood LE 627 104 PCIe 2.1 x16 550
550
550 		320:16:8 4.4 8.8 12.8
25.6
51.2 		DDR2
GDDR3
GDDR5 		128 352 10 39 ~70
Radeon HD 5570 Redwood PRO 650
650 		400
900 		400:20:8 5.2 13.0 12.8
28.8
57.6 		520 80
Radeon HD 5610 May 14, 2011 650 500 1024 16.0 GDDR3 ? ?
Radeon HD 5670 Jan 14, 2010 Redwood XT 775
775 		800
1000 		6.2 15.5 512
1024
2048 		25.6
64.0 		GDDR3
GDDR5 		620 15 64 4-way CrossFire 99
Radeon HD 5750 Oct 13, 2009 Juniper PRO 1040 170 700
700 		1150
1150 		720:36:16 11.2 25.2 512
1024 		73.6 GDDR5 1008 16 86 129
Radeon HD 5770 Juniper XT 850
850 		1200
1200 		800:40:16 13.6 34.0 76.8 1360 18 108 159
Radeon HD 5830 Feb 25, 2010 Cypress LE 2154 334 800 1000 1120:56:16 12.8 44.8 1024 128.0 256 1792 358.4 25 175 239
Radeon HD 5850 Sep 30, 2009 Cypress PRO 725
725 		1000
1000 		1440:72:32 23.2 52.2 1024
2048 		2088 417.6 27 151 259
Radeon HD 5870 Sep 23, 2009 Cypress XT 850
850 		1200
1200 		1600:80:32 27.2 68.0 153.6 2720 544 188
228 		379
Radeon HD 5870
Eyefinity Edition[c][36]		 Mar 11, 2010 850 1200 2048 228 479
Radeon HD 5970 Nov 18, 2009 Hemlock 2154×2 334×2 725
725 		1000
1000 		1600:80:32×2 46.4 116.0 1024×2
2048×2 		128×2 256×2 4640 928 51 294 2-way CrossFire 599
  1. ^ Unified shaders : Texture mapping units : Render output units
  2. ^ The TDP is reference design TDP values from AMD. Different non-reference board designs from vendors may lead to slight variations in actual TDP.
  3. ^ All chips feature AMD Eyefinity, but the Radeon HD 5870 Eyefinity Edition card also have six mini DisplayPort outputs, all of which can be simultaneously active.


Radeon HD 6000 series

Main articles: Radeon HD 6000 series and TeraScale 3 (VLIW4)

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

Model
(Codename) 		Release Date
& Price 		Architecture
& Fab 		Transistors
& Die Size 		Core Fillrate[a][b] Processing power[c]
(GFLOPS) 		Memory[d] TDP (Watts) Bus interface
Config[e] Clock (MHz) Texture
(GT/s) 		Pixel
(GP/s) 		Single Double Size (MB) Bus type
& width 		Clock
(MHz) 		Bandwidth (GB/s) Idle Max
Radeon HD 6350
(Cedar) 		April 7, 2011
$23 USD 		TeraScale 2
40 nm 		292×106
59 mm2		 80:8:4 650 5.2 2.6 104 — 512 DDR3
64-bit 		800 12.8 6.4 19.1 PCIe 2.1 ×16
Radeon HD 6450
(Caicos) 		February 7, 2011
OEM 		370×106
67 mm2		 160:8:4 625
750 		5.0
6.0 		2.5
3.0 		200
240 		— 512 DDR3
64-bit 		533
800 		8.5
12.8 		9 18
27
Radeon HD 6450
(Caicos) 		April 7, 2011
$55 USD 		160:8:4 625
750 		5.0
6.0 		2.5
3.0 		200
240 		— 512
1024
2048 		DDR3
64-bit 		800
900 		12.8
14.4 		9 18
27
Radeon HD 6570
(Turks Pro) 		February 7, 2011
OEM 		716×106
118 mm2		 480:24:8 650 15.6 5.2 624 — 1024 DDR3
128-bit 		900 28.8 10 44
Radeon HD 6570
(Turks Pro) 		April 19, 2011
$79 USD 		480:24:8 650 15.6 5.2 624 — 2048
4096 		DDR3
GDDR5
128-bit 		667
1000 		21.3
64 		11 60
Radeon HD 6670
(Turks XT) 		April 19, 2011
$99 USD 		480:24:8 800 19.2 6.4 768 — 512
1024
2048 		800
1000 		25.6
64 		12 66
Radeon HD 6750
(Juniper Pro) 		January 21, 2011
OEM 		1040×106
166 mm2		 720:36:16 700 25.2 11.2 1008 — 512
1024 		GDDR5
128-bit 		1150 73.6 16 86
Radeon HD 6770
(Juniper XT) 		April 19, 2011
? 		800:40:16 850 34.0 13.6 1360 — 512
1024 		1200
1050 		76.8
67.2 		18 108
Radeon HD 6790
(Barts LE) 		April 4, 2011
$149 USD 		1700×106
255 mm2		 800:40:16 840 33.6 13.4 1344 — 1024 GDDR5
256-bit 		1050 134.4 19 150
Radeon HD 6850
(Barts Pro) 		October 22, 2010
$179 USD 		960:48:32 775 37.2 24.8 1488 — 1024 1000 128 19 127
Radeon HD 6870
(Barts XT) 		October 22, 2010
$239 USD 		1120:56:32 900 50.4 28.8 2016 — 1024
2048 		1050 134.4 19 151
Radeon HD 6930
(Cayman CE) 		December 2011
$180 USD 		TeraScale 3
40 nm 		2640×106
389 mm2		 1280:80:32 750 60.0 24.0 1920 480 1024
2048 		GDDR5
256-bit 		1200 153.6 18 186
Radeon HD 6950
(Cayman Pro) 		December 15, 2010
$259 USD
$299 USD 		1408:88:32 800 70.4 25.6 2253 563 1024
2048 		1250
1250 		160 20 200
Radeon HD 6970
(Cayman XT) 		December 15, 2010
$369 USD 		1536:96:32 880 84.5 28.2 2703 675 2048 1375 176 20 250
Radeon HD 6990
(Antilles XT) 		March 8, 2011
$699 USD
2× 2640×106
389 mm2
 2× 1536:96:32 830 2×
79.6 		2×
26.5 		5099 1276.88 2×
2048 		GDDR5
256-bit 		1250 2×
160 		37 375
  1. ^ Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  2. ^ Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  3. ^ Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  4. ^ The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with DDR memory.
  5. ^ Unified Shaders : Texture Mapping Units : Render Output Units


IGP (HD 6000)

  • All models feature the UNB/MC Bus interface
  • All models do not feature double-precision FP
  • With driver Update OpenGL 4.4 available (Last Catalyst 15.12). OpenGL 4.5 available with Crimson Beta (driver version 15.30 or higher).
  • All models feature Angle independent anisotropic filtering, UVD3, and AMD Eyefinity capabilities, with up to three outputs.
  • All models feature 3D Blu-ray Disc acceleration.
  • Embedded GPU's as part of AMD's Lynx platform APU's.
Model Launch Codename Architecture Fab (nm) Core Clock rate (MHz) Config core[a] Fillrate Shared Memory Processing power
(GFLOPS) 		API compliance (version) Combined TDP[b] APU Series
Pixel (GP/s) Texture (GT/s) Bus width (bit) Bus type Bandwidth (GB/s) Direct3D OpenGL OpenCL Vulkan Idle (W) Max. (W)
Radeon HD 6370D November 1, 2011 WinterPark TeraScale 2 32 443 160:8:4 1.77 3.54 128 DDR3-1600 25.6 142 11.3
(11_0) 		4.5 1.2 — Un­known 65 E2
Radeon HD 6410D June 20, 2011 443[c]–600 1.77–2.4 3.54–4.8 142–192 A4
Radeon HD 6530D BeaverCreek 443 320:16:8 3.54 7.08 DDR3-1866 29.9 284 65–100 A6
Radeon HD 6550D 600 400:20:8 4.8 12 480 A8
  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.
  3. ^ A4-3300 series runs the Radeon HD 6410D at a speed of 443 MHz. Remaining A4 series run at 600 MHz.


Radeon HD 7000 series

Main articles: Radeon HD 7000 series, TeraScale 2 (VLIW5), and Graphics Core Next
Model
(Codename) 		Launch Architecture
Fab 		Transistors
Die Size 		Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory[e] TDP (Watts) Bus interface Release Price (USD)
Config[f] Clock[a] (MHz) Texture (GT/s) Pixel (GP/s) Single Double Size (MiB) Bus type
& width 		Clock (MHz) Bandwidth (GB/s) Idle Max.
Radeon HD 7350
(Cedar) 		January 2012 TeraScale 2[g]
40 nm 		292×106
59 mm2		 80:8:4 400
650 		3.2
5.2 		1.6
2.6 		104 — 256
512 		DDR2
DDR3
64-bit 		400
800
900 		6.4
12.8
14.4 		6.4 19.1 PCIe 2.1 ×16 OEM
Radeon HD 7450
(Caicos) 		January 2012 370×106
67 mm2		 160:8:4 625
750 		5.0
6.0 		2.5
3.0 		200
240 		— 512
1024 		DDR3
64-bit 		533
800 		8.5
12.8 		9 18 PCIe 2.1 ×16 OEM
Radeon HD 7470
(Caicos) 		January 2012 160:8:4 625
775 		5.0
6.2 		2.5
3.1 		200
248 		— 512
1024 		DDR3
GDDR5
64-bit 		800
900

 12.8
28.8

 9 27 PCIe 2.1 ×16 OEM
Radeon HD 7510
(Turks LE) 		February 2013 716×106
118 mm2		 320:16:4 650 10.4 2.6 416 — 1024 DDR3
128-bit 		667 21.3 Un­known Un­known PCIe 2.1 ×16 OEM
Radeon HD 7570
(Turks Pro-L) 		January 2012 480:24:8 650 15.6 5.2 624 — 512
1024 		DDR3
GDDR5
128-bit 		900
1000

 28.8
64

 10
11 		44
60 		PCIe 2.1 ×16 OEM
Radeon HD 7670
(Turks XT) 		January 2012 480:24:8 800 19.2 6.4 768 — 512
1024 		GDDR5
128-bit 		1000 64 12 66 PCIe 2.1 ×16 OEM
Radeon HD 7730
(Cape Verde LE) 		April 2013 GCN 1st gen
28 nm 		1500×106
123 mm2		 384:24:8 800 19.2 6.4 614.4 38.4 1024 DDR3
GDDR5
128-bit 		1125 25.6
72

 10 47 PCIe 3.0 ×16 $60
Radeon HD 7750
(Cape Verde Pro) 		February 2012 512:32:16 800
900 		25.6
28.8 		12.8
14.4 		819.2
921.6 		51.2
57.6 		1024
2048
4096 		DDR3
GDDR5
128-bit 		800
1125

 25.6
72

 10 55 PCIe 3.0 ×16 $110
Radeon HD 7770
GHz Edition
(Cape Verde XT) 		February 2012 640:40:16 1000 40 16 1280 80 1024
2048 		GDDR5
128-bit 		1125 72 10 80 PCIe 3.0 ×16 $160
Radeon HD 7790
(Bonaire XT) 		March 2013 GCN 2nd gen
28 nm 		2080×106
160 mm2		 896:56:16 1000 56.0 16.0 1792 128 1024
2048 		GDDR5
128-bit 		1500 96 10 85 PCIe 3.0 ×16 $150
Radeon HD 7850
(Pitcairn Pro) 		March 2012 GCN 1st gen
28 nm 		2800×106
212 mm2		 1024:64:32 860 55.04 27.52 1761.28 110.08 1024
2048 		GDDR5
256-bit 		1200 153.6 10 130 PCIe 3.0 ×16 $250
Radeon HD 7870
GHz Edition
(Pitcairn XT) 		March 2012 1280:80:32 1000 80 32 2560 160 2048 1200 153.6 10 175 PCIe 3.0 ×16 $350
Radeon HD 7870 XT
(Tahiti LE) 		November 2012 4313×106
352 mm2		 1536:96:32 925
975 		88.8 29.6 2841.6
2995.2 		710.4
748.8 		2048 GDDR5
256-bit 		1500 192.0 15 185 PCIe 3.0 ×16 $270
Radeon HD 7950
(Tahiti Pro) 		January 2012 1792:112:32 800 89.6 25.6 2867.2 717 3072 GDDR5
384-bit 		1250 240 15 200 PCIe 3.0 ×16 $450
Radeon HD 7950 Boost
(Tahiti Pro2) 		August 2012 1792:112:32 850
925 		103.6 29.6 3046.4
3315.2 		761.6
828.8 		3072 GDDR5
384-bit 		1250 240 15 225 PCIe 3.0 ×16 $330
Radeon HD 7970
(Tahiti XT) 		January 2012 2048:128:32 925 118.4 29.6 3788.8 947.2 3072
6144 		GDDR5
384-bit 		1375 264 15 250 PCIe 3.0 ×16 $550
Radeon HD 7970
GHz Edition
(Tahiti XT2) 		June 2012 2048:128:32 1000
1050 		128.0 32 4096
4300.8 		1024
1075 		3072
6144 		GDDR5
384-bit 		1500 288 15 250 PCIe 3.0 ×16 $500
Radeon HD 7990
(New Zealand) 		April 2013 2× 4313×106
352 mm2		 2× 2048:128:32 950
1000 		2× 128 2× 32 7782.4
8192 		1945.6
2048 		2× 3072 GDDR5
384-bit 		1500 2× 288 15 375 PCIe 3.0 ×16 $1000
Model
(Codename) 		Launch Architecture
Fab 		Transistors
Die Size 		Config[f] Clock[a] (MHz) Texture (GT/s) Pixel (GP/s) Single Double Size (MiB) Bus type
& width 		Clock
(MHz) 		Bandwidth (GB/s) Idle Max. Bus interface Release Price (USD)
Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory[e] TDP (Watts)
  1. ^ a b c d e f Boost values (if available) are stated below the base value in italic.
  2. ^ a b Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. ^ a b Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. ^ a b Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. ^ a b The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with DDR memory.
  6. ^ a b Unified Shaders : Texture Mapping Units : Render Output Units
  7. ^ Lacks hardware video encoder


IGP (HD 7000)

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


Model Launch Code name Architecture Fab (nm) Core Clock (MHz) Config core[a] Fillrate Shared Memory Processing power
(GFLOPS) 		API compliance (version) TDP (W)[b] APU
Base Turbo Texture (GT/s) Pixel (GP/s) Bus width (bit) Bus type Bandwidth (GB/s) Direct3D OpenGL[c] OpenCL
Radeon HD 7310[38] June 6, 2012 Ontario TeraScale 2[d] 40 500 — 80:8:4 4.00 2.00 64 DDR3-1066 8.53 80 11.3
(11_0) 		4.5 1.2 18 E2-1200
Radeon HD 7340[38] 523 680 5.44 2.72 DDR3-1333 10.66 83.6–108.8 E2-1800
Radeon HD 7480D June 1, 2012 Scrapper TeraScale 3[d] 32 723 — 128:8:4 11.6 2.9 128 DDR3-1600 25.6 185 65 A4-4000, A4-5300
Radeon HD 7540D 760 192:12:4 Un­known DDR3-1866 29.9 292 A6-5400K
Radeon HD 7560D Devastator 256:16:4 389 65–100 A8-5500, A8-5600K
Radeon HD 7660D 760 800 384:24:8 16.2 2.7 584–614 A10-5700 (760 MHz), A10-5800K (800 MHz)
  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.
  3. ^ OpenGL 4.5 possible for Terascale 3 with AMD Radeon Software Crimson Beta (driver 15.30 or higher).[37]
  4. ^ a b Lacks hardware video encoder


Radeon HD 8000 series

Main articles: Radeon HD 8000 series and Graphics Core Next § first
[ VisualEditor ]
Model
(Codename) 		Launch Architecture
(Fab) 		Transistors
Die Size 		Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory[e] TDP (W) Bus interface
Config[f] Clock[a] (MHz) Texture (GT/s) Pixel (GP/s) Single Double Size (MiB) Bus type &
width (bit) 		Clock (MHz) Band-
width (GB/s) 		Idle
Max
Radeon
HD 8350
(Cedar) 		January 8, 2013 TeraScale 2[g]
(40 nm) 		292×106
59 mm2		 80:8:4 400–650 3.2
5.2 		1.6
2.6 		104 — 256
512 		DDR2
DDR3
64-bit 		400
800

 6.4
12.8

 6.4
19.1 		PCIe 2.1 ×16
Radeon
HD 8450
(Caicos) 		January 8, 2013 370×106
67 mm2		 160:8:4 625 5.0 2.5 200 — 512 DDR3
64-bit 		533 8.53 9
18
Radeon
HD 8470
(Caicos) 		January 8, 2013 750 6.0 3.0 240 — 1024 GDDR5
64-bit 		800 25.6 9
35
Radeon
HD 8490
(Caicos) 		July 23, 2013 875 7.0 3.5 280 — 1024 DDR3L
GDDR5
64-bit 		800
900

 12.8
28.8

 9
35
Radeon
HD 8570
(Oland) 		January 8, 2013 GCN 1st gen
(28 nm) 		950×106
77 mm2		 384:24:8 730 19.2 6.4 560 35 2048 DDR3
GDDR5
128-bit 		900
1150

 28.8
72

 12
66 		PCIe 3.0 ×8
Radeon
HD 8670
(Oland) 		January 8, 2013 1000 24 8 768 48 2048 GDDR5
128-bit 		1150 72 16
86
Radeon
HD 8730
(Cape Verde LE) 		September 5, 2013 1500×106
123 mm2		 384:24:8 800 19.2 6.4 614.4 44.8 1024 GDDR5
128-bit 		1125 72 10
47 		PCIe 3.0 ×16
Radeon
HD 8760
(Cape Verde XT) 		January 8, 2013 640:40:16 1000 40 16 1280 80 2048 GDDR5
128-bit 		1125 72 16
80 		PCIe 3.0 ×16
Radeon
HD 8770
(Bonaire XT) 		September 2, 2013 GCN 2nd gen
(28 nm) 		2080×106
160 mm2		 896:56:16 1000 56.0 16.0 1792 128 2048 GDDR5
128-bit 		1500 96 10
85 		PCIe 3.0 ×16
Radeon
HD 8870
(Pitcairn XT)[39]		 January 8, 2013 GCN 1st gen
(28 nm) 		2800×106
212 mm2		 1280:80:32 1000 80 32 2560 160 2048 GDDR5
256-bit 		1200 153.6 15
150 		PCIe 3.0 ×16
Radeon
HD 8950
(Tahiti Pro) 		January 8, 2013 4313×106
352 mm2		 1792:112:32 850
925 		95.2
103.6 		27.2
29.6 		3046.4
3315.2 		761.6
828.8 		3072 GDDR5
384-bit 		1250 240 15
225 		PCIe 3.0 ×16
Radeon
HD 8970
(Tahiti XT2) 		January 8, 2013 2048:128:32 1000
1050 		128.0
134.4 		32
33.6 		4096
4301 		1024
1075 		3072 GDDR5
384-bit 		1500 288 15
250 		PCIe 3.0 ×16
Radeon
HD 8990
(Malta) 		April 24, 2013 2× 4313×106
2× 352 mm2		 2× 2048:128:32 950
1000 		2× 128 2× 32 7782
8192 		1946
2048 		2× 3072 GDDR5
384-bit 		1500 2× 288 15
375 		PCIe 3.0 ×16
Model
(Codename) 		Launch Architecture
(Fab) 		Transistors
Die Size 		Config[f] Clock[a] (MHz) Texture (GT/s) Pixel (GP/s) Single Double Size (MiB) Bus type &
width (bit) 		Clock (MHz) Band-
width (GB/s) 		Idle
Max 		Bus interface
Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory[e] TDP (W)
  1. ^ a b c d e f Boost values (if available) are stated below the base value in italic.
  2. ^ a b Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. ^ a b Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. ^ a b Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. ^ a b The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as with DDR memory.
  6. ^ a b Unified Shaders : Texture Mapping Units : Render Output Units
  7. ^ Lacks hardware video encoder


Radeon 200 series

Main articles: Radeon 200 series and Graphics Core Next § second
Model
(codename) 		Release Date
& Price 		Architecture
& Fab 		Transistors
& Die Size 		Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory TBP Bus interface
Config[e] Clock[a] (MHz) Texture (GT/s) Pixel (GP/s) Single Double Size (MiB) Bus type
& width 		Clock (MT/s) Band-
width (GB/s)
Radeon
R5 220[40]
(Caicos Pro) 		December 21, 2013
OEM 		Terascale 2[f]
40 nm 		370×106
67 mm2		 80:8:4 625
650 		5 2.5 200 — 1024 DDR3
64-bit 		1066 8.53 18 W PCIe 2.1 ×16
Radeon
R5 230[41]
(Caicos Pro) 		April 3, 2014[42]
? 		160:8:4 625 5 2.5 200 — 1024
2048 		DDR3
64-bit 		1066 8.53 19 W[43]
Radeon
R5 235[40]
(Caicos XT) 		December 21, 2013
OEM 		160:8:4 775 6.2 3.1 248 — 1024 DDR3
64-bit 		1800 14.4 35 W[44]
Radeon
R5 235X[40]
(Caicos XT) 		December 21, 2013
OEM 		160:8:4 875 7.0 3.5 280 — 1024 DDR3
64-bit 		1800 14.4 18 W
Radeon
R5 240[40]
(Oland) 		November 1, 2013[45]
OEM 		GCN 1st gen
28 nm 		1040×106
90 mm2		 384:24:8 730
780 		14.6 5.84 560.6
599 		29.2 1024
2048 		DDR3
GDDR3
64-bit 		1800
2000

 28.8
16.0

 30 W PCIe 3.0 ×8
Radeon
R7 240[46]
(Oland Pro) 		August 8, 2013
US $69 		320:20:8 730
780 		14.6 5.84 467.2
499.2 		29.2 2048
4096 		DDR3
GDDR5
128-bit 		1800
4500

 28.8
72

 30 W, <45 W (4 GB)[47]
Radeon
R7 250[46]
(Oland XT) 		August 8, 2013
US $89 		384:24:8 1000
(1050) 		24 8 768
806.4 		48 1024
2048 		DDR3
GDDR5
128-bit 		1800
4600

 28.8
73.6

 75 W
Radeon
R7 250E[48]
(Cape Verde Pro) 		December 21, 2013
US $109 		1500×106
123 mm2		 512:32:16 800 25.6 12.8 819.2 51.2 1024
2048 		GDDR5
128-bit 		4500 72 55 W PCIe 3.0 ×16
Radeon
R7 250X[46]
(Cape Verde XT) 		February 10, 2014
US $99 		640:40:16 1000 40 16 1280 80 1024
2048 		GDDR5
128-bit 		4500 72 95 W
Radeon
R7 260[46]
(Bonaire) 		December 17, 2013
US $109 		GCN 2nd gen
28 nm 		2080×106
160 mm2		 768:48:16 1000 48 16 1536 96 1024 GDDR5
128-bit 		6000 96 95 W
Radeon
R7 260X[46]
(Bonaire XTX) 		August 8, 2013
US $139 		896:56:16 1100 61.6 17.6 1971.2 123.2 1024
2048 		GDDR5
128-bit 		6500 104 115 W
Radeon
R7 265[46]
(Pitcairn Pro) 		February 13, 2014
US $149 		GCN 1st gen
28 nm 		2800×106
212 mm2		 1024:64:32 900
925 		57.6 28.8 1843.2 115.2 2048 GDDR5
256-bit 		5600 179.2 150 W
Radeon
R9 270[49]
(Pitcairn XT) 		November 13, 2013
US $179 		1280:80:32 900
925 		72 28.8 2304
2368 		144
148 		2048 GDDR5
256-bit 		5600 179.2 150 W
Radeon
R9 270X[49]
(Pitcairn XT) 		August 8, 2013
US $199 		1280:80:32 1000
1050 		80 32 2560
2688 		160
168 		2048
4096 		GDDR5
256-bit 		5600 179.2 180 W
Radeon
R9 280[49]
(Tahiti Pro) 		March 4, 2014
US $249 		4313×106
352 mm2		 1792:112:32 827
933 		92.6 26.5 2964
3343.9 		741
836 		3072 GDDR5
384-bit 		5000 240 250 W
Radeon
R9 280X[49]
(Tahiti XTL)[50]		 August 8, 2013
US $299 		2048:128:32 850
1000 		109–128 27.2–32 3481.6
4096 		870.4
1024 		3072 GDDR5
384-bit 		6000 288 250 W
Radeon
R9 285[49]
(Tonga Pro) 		September 2, 2014
US $249 		GCN 3rd gen
28 nm 		5000×106
359 mm2 [51]		 1792:112:32 918 102.8 29.4 3290 206.6[52] 2048 GDDR5
256-bit 		5500 176[g] 190 W
Radeon
R9 285X
(Tonga XT) 		Unreleased [54] 2048:128:32 1002 128.3 32.1 4104 256.5 3072 GDDR5
384-bit 		5500 264 200 W
Radeon
R9 290[49]
(Hawaii Pro) 		November 5, 2013
US $399 		GCN 2nd gen
28 nm 		6200×106
438 mm2 [55]		 2560:160:64 up to 947[h] 151.52 60.608 4848.6 606.1 4096 GDDR5
512-bit 		5000 320 250 W[57]
Radeon
R9 290X[49]
(Hawaii XT) 		October 24, 2013
November 6, 2014[58]
US $549 		2816:176:64 1000[h] 176 64 5632 704 4096
8192 		GDDR5
512-bit 		5000 320 250 W[57]
Radeon
R9 295X2[49][59]
(Vesuvius) 		April 8, 2014
US $1499 		2× 6200×106
2× 438 mm2		 2× 2816:176:64 1018 358.33 130.3 11466.75 1433.34 2× 4096 GDDR5
512-bit 		5000 2× 320 500 W
Model
(codename) 		Release Date
& Price 		Architecture
& Fab 		Transistors
& Die Size 		Config[e] Clock[a] (MHz) Texture (GT/s) Pixel (GP/s) Single Double Size (MiB) Bus type
& width 		Clock (MT/s) Band-
width (GB/s) 		TBP Bus interface
Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory
  1. ^ a b c d e f Boost values (if available) are stated below the base value in italic.
  2. ^ a b Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. ^ a b Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. ^ a b Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. ^ a b Unified Shaders : Texture Mapping Units : Render Output Units
  6. ^ Lacks hardware video encoder
  7. ^ The R9 285 utilizes loss-less colour compression which can increase effective memory performance (relative to GCN 1st gen and 2nd gen cards) in certain situations.[51][53]
  8. ^ a b Base clock of R9 290 and R9 290X will maintain at 947 MHz and 1000 MHz before reaching 95 °C, respectively.[56]


Radeon 300 series

Main articles: Radeon 300 series and Graphics Core Next § third
Model
(Codename) 		Release Date
& Price 		Architecture
(Fab) 		Transistors
Die Size 		Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory TBP (W) Bus interface
Config[e] Clock[a] (MHz) Texture (GT/s) Pixel (GP/s) Single Double Size (MiB) Bus type
& width 		Clock (MT/s) Band-
width (GB/s)
Radeon
R5 330
(Oland Pro) 		May 2015
OEM 		GCN 1st gen
(28 nm) 		1040×106
90 mm2		 320:20:8 Un­known
855
17.1
6.84
547.2
34.2 		1024
2048 		DDR3
128-bit 		1800 28.8 30 PCIe 3.0 ×16
Radeon
R5 340
(Oland XT) 		May 2015
OEM 		384:24:8 Un­known
825
19.8
6.6
633.6
39.6 		1024
2048 		DDR3
GDDR5
128-bit 		1800
4500

 28.8
72

 75
Radeon
R7 340
(Oland XT) 		May 2015
OEM 		384:24:8 730
780 		17.5
18.7 		5.8
6.2 		560.6
599 		32.7
35 		1024
2048
4096 		DDR3
GDDR5
128-bit 		1800
4500

 28.8
72

 75
Radeon
R5 340X[60]
(Oland XT) 		May 2015
OEM 		384:24:8 1050 25.2 8.4 806 50.4 2048 DDR3
64-bit 		2000 16 30
Radeon
R7 350
(Oland XT) 		May 2015
OEM 		384:24:8 1000
1050 		24
25.2 		8
8.4 		768
806.4 		48
50.4 		1024
2048 		DDR3
GDDR5
128-bit 		1800
4500

 28.8
72

 75
Radeon
R7 350 [61]
(Cape Verde XTL) 		February 2016
$89 USD 		1500×106
123 mm2		 512:32:16 925 29.6 14.8 947.2 59.2 2048 GDDR5
128-bit 		4500 72 75
Radeon
R7 350X[62]
(Oland XT) 		May 2015
OEM 		1040×106
90 mm2		 384:24:8 1050 25.2 8.4 806 50.4 4096 DDR3
128-bit 		2000 32 30
Radeon
R7 360[63][64]
(Bonaire Pro) 		June 2015
$109 USD 		GCN 2nd gen
(28 nm) 		2080×106
160 mm2		 768:48:16 1050 50.4 16.8 1612.8 100.8 2048 GDDR5
128-bit 		6500 104 100
Radeon
R9 360
(Bonaire Pro) 		May 2015
OEM 		768:48:16 1000
1050 		48
50.4 		16
16.8 		1536
1612.8 		96
100.8 		2048 GDDR5
128-bit 		6500 104 85
Radeon
R7 370[63]
(Pitcairn Pro) 		June 2015
$149 USD 		GCN 1st gen
(28 nm) 		2800×106
212 mm2		 1024:64:32 975 62.4 31.2 1996.8 124.8 2048
4096 		GDDR5
256-bit 		5600 179.2 110
Radeon
R9 370
(Pitcairn Pro) 		May 2015
OEM 		1024:64:32 950
975 		60.8
62.4 		30.4
31.2 		1945.6
1996.8 		121.6
124.8 		2048
4096 		GDDR5
256-bit 		5600 179.2 150
Radeon
R9 370X
(Pitcairn XT) 		August 2015
$179 USD 		1280:80:32 1000 80 32 2560 160 2048
4096 		GDDR5
256-bit 		5600 179.2 185
Radeon
R9 380
(Tonga Pro) 		May 2015
OEM 		GCN 3rd gen
(28 nm) 		5000×106
359 mm2		 1792:112:32 918 102.8 29.4 3290 206.6 4096 GDDR5
256-bit 		5500 176 190
Radeon
R9 380[65]
(Tonga Pro) 		June 2015
$199 USD 		1792:112:32 970 108.6 31.0 3476.5 217.3 2048
4096 		GDDR5
256-bit 		5700 182.4[f] 190
Radeon
R9 380X[65]
(Tonga XT) 		November 2015
$229 USD 		2048:128:32 970 124.2 31.0 3973.1 248.3 4096 GDDR5
256-bit 		5700 182.4 190
Radeon
R9 390[65]
(Grenada Pro) 		June 2015
$329 USD 		GCN 2nd gen
(28 nm) 		6200×106
438 mm2		 2560:160:64 1000 160 64 5120 640 8192 GDDR5
512-bit 		6000 384 275
Radeon
R9 390X[65]
(Grenada XT) 		June 2015
$429 USD 		2816:176:64 1050 184.8 67.2 5913.6 739.2 8192 GDDR5
512-bit 		6000 384 275
Radeon
R9 Fury[66]
(Fiji Pro) 		July 2015
$549 USD 		GCN 3rd gen
(28 nm) 		8900×106
596 mm2		 3584:224:64 1000 224 64 7168 448 4096 HBM
4096-bit 		1000 512 275
Radeon
R9 Nano[67]
(Fiji XT) 		August 2015
$649 USD 		4096:256:64 1000 256 64 8192 512 175
Radeon
R9 Fury X[65][68]
(Fiji XT) 		June 2015
$649 USD 		4096:256:64 1050 268.8 67.2 8601.6 537.6 275
Radeon
Pro Duo[69][70][71][72]
(Fiji XT) 		April 2016
$1499 USD 		2× 8900×106
2× 596 mm2		 2× 4096:256:64 1000 512 128 16384 1024 2× 4096 HBM
4096-bit 		1000 2× 512 350
Model
(Codename) 		Release Date
& Price 		Architecture
(Fab) 		Transistors
Die Size 		Config[e] Clock[a] (MHz) Texture (GT/s) Pixel (GP/s) Single Double Size (MiB) Bus type
& width 		Clock (MT/s) Band-
width (GB/s) 		TBP (W) Bus interface
Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory
  1. ^ a b c d e f Boost values (if available) are stated below the base value in italic.
  2. ^ a b Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. ^ a b Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. ^ a b Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation. Double precision performance of Hawaii cards is 1/8 of single precision performance, for the other it is 1/16 of single precision performance.
  5. ^ a b Unified Shaders : Texture Mapping Units : Render Output Units
  6. ^ The R9 380 utilizes loss-less color compression which can increase effective memory performance (relative to GCN 1st gen and 2nd gen cards) in certain situations.[citation needed]


Radeon 400 series

Main articles: Radeon 400 series and Graphics Core Next § fourth
Model
(Codename) 		Release Date
& Price 		Architecture
& Fab 		Transistors
& Die Size 		Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory TBP Bus interface
Config[e] Clock[a] (MHz) Texture (GT/s) Pixel (GP/s) Single Double Size (GiB) Bus type
& width 		Clock (MT/s) Band-
width (GB/s)
Radeon R5 430
(Oland Pro) [73][74]		 June 30, 2016
OEM 		GCN 1st gen
28 nm 		1040×106
90 mm2		 384:24:8
6 CU 		730
780 		17.52
18.72 		5.84
6.24 		560
599 		37.4
40 		1
2 		DDR3
GDDR5
128-bit 		1800
4500

 28.8
72

 50 W PCIe 3.0 ×8
Radeon R5 435
(Oland) [73][75]		 320:20:8
5 CU 		1030 20.6 8.24 659 41.2 2 DDR3
64-bit 		2000 16
Radeon R7 430
(Oland Pro) [76][77]		 384:24:8
6 CU 		730
780 		17.52
18.72 		5.84
6.24 		560
599 		37.4
40 		1
2
4 		DDR3
GDDR5
128-bit 		1800
4500

 28.8
72

Radeon R7 435
(Oland) [76][78]		 320:20:8
5 CU 		920 18.4 7.36 589 36.8 2 DDR3
64-bit 		2000 16
Radeon R7 450
(Cape Verde Pro) [76][79]		 1500×106
123 mm2		 512:32:16
8 CU 		1050 33.6 16.8 1075 65.2 GDDR5
128-bit 		4500 72 65 W PCIe 3.0 ×16
Radeon RX 455
(Bonaire Pro) [76][80]		 GCN 2nd gen
28 nm 		2080×106
160 mm2		 768:48:16
12 CU 		50.4 1613 100.8 6500 104 100 W
Radeon RX 460
(Baffin) [81][82][83][84][85]		 August 8, 2016
$109 USD(2 GB)
$139 USD(4 GB) 		GCN 4th gen
GloFo
14LPP[86][f]		 3000×106
123 mm2		 896:56:16
14 CU 		1090
1200 		61
67.2 		17.4
19.2 		1953
2150 		122
132 		2
4 		7000 112 <75 W PCIe 3.0 ×8
Radeon RX 470D
(Ellesmere) [88]		 October 21, 2016
CNY ¥1299
(China Only) 		5700×106
232 mm2		 1792:112:32
28 CU 		926
1206 		103.7
135.1 		29.6
38.6 		3319
4322 		207
270 		4 GDDR5
256-bit 		224 120 W PCIe 3.0 ×16
Radeon RX 470
(Ellesmere Pro) [81][83][84]		 August 4, 2016
$179 USD 		2048:128:32
32 CU 		118.5
154.4 		3793
4940 		237
309 		4
8 		6600 211
Radeon RX 480
(Ellesmere XT) [89][90][91][92]		 June 29, 2016
$199 USD (4 GB)
$239 USD (8 GB) 		2304:144:32
36 CU 		1120
1266 		161.3
182.3 		35.8
40.5 		5161
5834 		323
365 		7000
8000 		224
256 		150 W
  1. ^ a b c Boost values (if available) are stated below the base value in italic.
  2. ^ Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. ^ Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. ^ Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. ^ Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)
  6. ^ GlobalFoundries' 14 nm 14LPP FinFET process is second-sourced from Samsung Electronics.[87]


Radeon 500 series

Main articles: Radeon 500 series and Graphics Core Next § fourth
Model
(Code name) 		Release Date
& Price 		Architecture
& fab 		Transistors
& die size 		Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory TBP Bus
interface
Config[e] Clock[a]
(MHz) 		Texture
(GT/s) 		Pixel
(GP/s) 		Single Double Size Bus type
& width 		Clock
(MT/s) 		Bandwidth
(GB/s)
Radeon 520
(Banks)[f][93][94]		 Apr 18, 2017
OEM 		GCN 1
28 nm 		690×106
56mm2		 320:20:4
5 CU
1030
20.6
4.1
659.2
41.2 		1 GB
2 GB 		DDR3
GDDR5
64-bit 		2000
4500

 16
36

 ? PCIe 3.0
×8
Radeon 530
(Weston)[f][95]		 GCN 3
28 nm 		?
125 mm2		 320:20:8
5 CU
1024
20.480
8.2
655.36
40.96 		1 GB
2 GB
4 GB[96]		 DDR3
GDDR5
64-bit 		1800
4500

 14.4
36

 ?
384:24:8
6 CU
24.576
786.432
49.152
Radeon RX 540
(Polaris 12)[97][98]		 GCN 4
GloFo
14LPP[g][100]		 2.2×109
101 mm2		 512:32:16
8 CU 		1124
1219 		35.968
39.008 		17.984
19.504 		1150.976
1248.256 		71.936
78.016 		2 GB
4 GB 		GDDR5
128-bit 		6000 96 PCIe 3.0
×8
Radeon RX 550
(Polaris 12)[101][102][103]		 Apr 20, 2017
$79 USD 		1100
1183 		35.2
37.856 		17.6
18.928 		1126.4
1211.392 		70.4
75.712 		7000 112 50 W
Radeon RX 550 640SP
(Polaris 11)[104]		 Apr 20, 2017
$79 USD 		3.0×109
123 mm2		 640:40:16
10 CU 		1019
1071 		40.76
42.84 		16.304
17.136 		1304.32
1370.88 		81.52
85.68 		6000 96 60 W
Radeon RX 550X
(Polaris 12)[105]		 Apr 11, 2018
$79 USD 		2.2×109
101 mm2		 512:32:16
8 CU 		1100
1287 		35.2
41.184 		17.6
20.592 		1126.4
1317.888 		70.4
82.368 		7000 112 50 W
Radeon RX 550X 640SP
(Polaris 11)[106]		 Apr 11, 2018
OEM 		3.0×109
123 mm2		 640:40:16
10 CU 		1019
1071 		40.76
42.84 		16.304
17.136 		1304.32
1370.88 		81.52
85.68 		6000 96 60 W
Radeon RX 560D
(Polaris 21)[107][108][109]		 Jul 4, 2017
OEM and China Only 		3.0×109
123 mm2		 896:56:16
14 CU 		1090
1175 		61.0
65.8 		17,4
18.8 		1953
2106 		122,0
131.6 		65 W
Radeon RX 560[h]
(Polaris 21)[102][107][110]		 Jul 4, 2017
$99 USD 		1090
1175 		61.0
65.8 		17.4
18.8 		1953
2106 		122.0
131.6 		7000 112 60-80 W
Apr 18, 2017
$99 USD 		1024:64:16
16 CU 		1175
1275 		75.2
81.6 		18.8
20.4 		2406
2611 		150.4
163.2
Radeon RX 570
(Polaris 20)[111][102]		 Apr 18, 2017
$169 USD 		5.7×109
232 mm2		 2048:128:32
32 CU 		1168
1244 		149.5
159.2 		37.4
39.8 		4784
5095 		299.0
318.4 		4 GB
8 GB 		GDDR5
256-bit 		224 150 W PCIe 3.0
×16
Radeon RX 580
(Polaris 20)[112][102]		 Apr 18, 2017
$199 USD (4 GB)
$229 USD (8 GB) 		2304:144:32
36 CU 		1257
1340 		181.0
193.0 		40.2
42.9 		5792
6175 		362.0
385.9 		8000 256 185 W
Radeon RX 590 GME
(Polaris 20)[113][114][115]		 March 9, 2020
China Only 		1257
1380 		181.0
198.7 		40.2
44.2 		5792
6359 		362.0
397.4 		8 GB 175 W
Radeon RX 590
(Polaris 30)[116]		 Nov 15, 2018
$279 USD 		GCN 4
Samsung/GloFo
12LP (14LP+)[i]		 1469
1545 		211.5
222.5 		47.0
49.4 		6769
7120 		423.0
444.9 		225 W
  1. ^ a b c Boost values (if available) are stated below the base value in italic.
  2. ^ Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. ^ Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. ^ Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. ^ Unified shaders : Texture mapping units : Render output units and Compute units (CU)
  6. ^ a b Lacks hardware video encoder and decoder
  7. ^ GlobalFoundries' 14 nm 14LPP FinFET process is second-sourced from Samsung Electronics.[99]
  8. ^ In October 2017 AMD branded an additional Polaris chip as "RX 560", although it features fewer shader and texture mapping units than the first released RX 560.
  9. ^ GlobalFoundries' 12 nm 12LP process is based on Samsung's 14 nm 14LPP process.[99]

Radeon RX Vega series

Main articles: Radeon RX Vega series and Graphics Core Next § fifth
Model
(Code name) 		Release Date
& Price 		Architecture
& fab 		Transistors
& die size 		Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory TBP Bus
interface
Config[e] Clock[a]
(MHz) 		Texture
(GT/s) 		Pixel
(GP/s) 		Half Single Double Size
(GB) 		Bandwidth
(GB/s) 		Bus type
& width 		Clock
(MT/s)
Radeon RX Vega 56
(Vega 10)[117][118][119]		 Aug 28, 2017
$399 USD 		GCN 5
GloFo
14LPP[f][120][121]		 12.5×109
486 mm2		 3584:224:64
56 CU 		1156
1471 		258.9
329.5 		73.98
94.14 		16,572
21,088 		8,286
10,544 		517.9
659.0 		8 409.6 HBM2
2048-bit 		1600 210 W PCIe 3.0
×16
Radeon RX Vega 64
(Vega 10)[122][118][119]		 Aug 14, 2017
$499 USD 		4096:256:64
64 CU 		1247
1546 		319.2
395.8 		79.81
98.94 		20,431
25,330 		10,215
12,665 		638.5
791.6 		483.8 1890 295 W
Radeon RX Vega 64 Liquid
(Vega 10)[122][118][119]		 Aug 14, 2017
$699 USD 		1406
1677 		359.9
429.3 		89.98
107.3 		23,036
27,476 		11,518
13,738 		719.9
858.6 		345 W
  1. ^ a b c Boost values (if available) are stated below the base value in italic.
  2. ^ Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. ^ Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. ^ Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. ^ Unified shaders : Texture mapping units : Render output units and Compute units (CU)
  6. ^ GlobalFoundries' 14 nm 14LPP FinFET process is second-sourced from Samsung Electronics.

Radeon VII series

Main articles: Radeon RX Vega series § Radeon VII branded discrete graphics, and Graphics Core Next § fifth
Model
(Code name) 		Release Date
& Price 		Architecture
& fab 		Transistors
& die size 		Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory TBP Bus
interface
Config[e] Clock[a]
(MHz) 		Texture
(GT/s) 		Pixel
(GP/s) 		Half Single Double Size
(GB) 		Bandwidth
(GB/s) 		Bus type
& width 		Clock
(MT/s)
Radeon VII
(Vega 20)[123][124][125]		 Feb 7, 2019
$699 USD 		GCN 5
TSMC CLN7FF[126]		 13.23×109
331 mm2		 3840:240:64
60 CU 		1400
1750–1800 		336.0
420.0 		89.60
112.0 		21,504
27,648 		10,752
13,824 		2,688
3,459 		16 1024 HBM2
4096-bit 		2000 300 W PCIe 3.0
×16
  1. ^ a b c Boost values (if available) are stated below the base value in italic.
  2. ^ Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. ^ Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. ^ Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. ^ Unified shaders : Texture mapping units : Render output units and Compute units (CU)

Radeon RX 5000 series

Main articles: Radeon RX 5000 series and RDNA (microarchitecture)
Model
(Code name) 		Release Date
& Price 		Architecture
& fab 		Transistors
& die size 		Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory TBP Bus
interface
Config[e] Clock[a]
(MHz) 		Texture
(GT/s) 		Pixel
(GP/s) 		Half Single Double Size
(GB) 		Bandwidth
(GB/s) 		Bus type
& width 		Clock
(MT/s)
Radeon RX 5300
(Navi 14)[127][128]		 Aug 28, 2020
OEM 		RDNA
TSMC N7 		6.4×109
158 mm2		 1408:88:32
22 CU 		1327
1645 		116.8
144.8 		42.46
52.64 		7,474
9,265 		3,737
4,632 		233.5
289.5 		3 168 GDDR6
96-bit 		14000 100 W PCIe 4.0
×8
Radeon RX 5300 XT
(Navi 14)[129][130]		 Oct 7, 2019
OEM 		1670
1845 		146.7
162.4 		53.44
59.04 		9,405
10,390 		4,703
5,196 		293.9
324.7 		4 112 GDDR5
128-bit 		7000
Radeon RX 5500
(Navi 14)[131][132][133]		 224 GDDR6
128-bit 		14000 150 W
Radeon RX 5500 XT
(Navi 14)[134][135][136][137]		 Dec 7, 2019
$169 USD (4GB)
$199 USD (8GB) 		1717
1845 		151.1
162.4 		54.94
59.04 		9,670
10,390 		4,835
5,196 		302.2
324.7 		4
8 		130 W
Radeon RX 5600
(Navi 10)[138][139]		 Jan 21, 2020
OEM 		10.3×109
251 mm2		 2048:128:64
32 CU 		1375
1560 		176.0
199.7 		88.00
99.84 		11,264
12,780 		5,632
6,390 		352.0
399.4 		6 288 GDDR6
192-bit 		12000 150 W PCIe 4.0
×16
Radeon RX 5600 XT
(Navi 10)[140][141]		 Jan 21, 2020
$279 USD 		2304:144:64
36 CU 		198.0
224.6 		12,672
14,377 		6,336
7,188 		396.0
449.3 		288
336 		12000
14000 		160 W
Radeon RX 5700
(Navi 10)[142][143][144][145][146]		 Jul 7, 2019
$349 USD 		1465
1725 		210.9
248.4 		93.73
110.4 		13,501
15,900 		6,751
7,949 		421.9
496.8 		8 448 GDDR6
256-bit 		14000 180 W
Radeon RX 5700 XT
(Navi 10)[147][148][144][145][146]		 Jul 7, 2019
$399 USD 		2560:160:64
40 CU 		1605
1905 		256.8
304.8 		102.7
121.9 		16,435
19,510 		8,218
9,754 		513.6
609.6 		225 W
Radeon RX 5700 XT
50th Anniversary Edition
(Navi 10)[149][150][151][146]		 Jul 7, 2019
$449 USD 		1680
1980 		268.8
316.8 		107.5
126.7 		17,203
20,276 		8,602
10,138 		537.6
633.6 		235 W
  1. ^ a b c Boost values (if available) are stated below the base value in italic.
  2. ^ Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. ^ Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. ^ Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. ^ Unified shaders : Texture mapping units : Render output units and Compute units (CU)


Radeon RX 6000 series

Main articles: Radeon RX 6000 series and RDNA 2
Model
(Code name) 		Release Date
& Price 		Architecture
& fab 		Transistors
& die size 		Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Infinity Cache Memory TBP Bus
interface
Config[e] Clock[a]
(MHz) 		Texture
(GT/s) 		Pixel
(GP/s) 		Half Single Double Size Bandwidth
(GB/s) 		Size Bandwidth
(GB/s) 		Bus type
& width 		Clock
(MT/s)
Radeon RX 6400
(Navi 24)[152][153][f]		 Jan 19, 2022
$159 USD 		RDNA 2
TSMC N6 		5.4×109
107 mm2		 768:48:32:12
12 CU 		1923
2321 		92.3
111.4 		61.5
74.3 		5,907
7,130 		2,954
3,565 		184.6
222.8 		16 MB 208.0 4 GB 128 GDDR6
64-bit 		16000 53 W PCIe 4.0
×4
Radeon RX 6500 XT
(Navi 24)[154][155][156][f]		 Jan 19, 2022
$199 USD (4GB)
$219 USD (8GB) 		1024:64:32:16
16 CU 		2310
2815 		147.8
180.2 		73.9
90.1 		9,462
11,530 		4,731
5,765 		295.6
360.3 		232.0 4 GB
8 GB 		144 18000 107 W
113 W
Radeon RX 6600
(Navi 23)[157][158]		 Oct 13, 2021
$329 USD 		RDNA 2
TSMC N7 		11.06×109
237 mm2		 1792:112:64:28
28 CU 		1626
2491 		228.9
279.0 		104.1
159.4 		14,654
17,860 		7,325
8,928 		457.8
558.0 		32 MB 412.9 8 GB 224 GDDR6
128-bit 		14000 132 W PCIe 4.0
×8
Radeon RX 6600 XT
(Navi 23)[159][160][161][162]		 Aug 11, 2021
$379 USD 		2048:128:64:32
32 CU 		1968
2589 		251.9
331.4 		126.0
165.7 		16,122
21,209 		8,061
10,605 		503.8
662.8 		444.9 256 16000 160 W
Radeon RX 6650 XT
(Navi 23)[163][164]		 May 10, 2022
$399 USD 		2055
2635 		263.0
337.2 		131.5
168.6 		16,835
21,586 		8,417
10,793 		526.1
674.6 		468.9 280 17500 180 W
Radeon RX 6700
(Navi 22)[165][166][167]		 Jun 9, 2021
? 		17.2×109
335 mm2		 2304:144:64:36
36 CU 		1941
2450 		279.5
352.8 		124.2
156.8 		17,888
22,579 		8,944
11,290 		559.0
705.6 		80 MB 1065.0 10 GB 320 GDDR6
160-bit 		16000 175 W PCIe 4.0
×16
Radeon RX 6700 XT
(Navi 22)[168][169][170]		 Mar 18, 2021
$479 USD 		2560:160:64:40
40 CU 		2321
2581 		371.4
413.0 		148.5
165.2 		23,767
26,429 		11,884
13,215 		742.7
825.9 		96 MB 1278.0 12 GB 384 GDDR6
192-bit 		230 W
Radeon RX 6750 XT
(Navi 22)[171][172]		 May 10, 2022
$549 USD 		2150
2600 		344.0
416.0 		137.6
166.4 		22,016
26,624 		11,008
13,312 		688.0
832.0 		1326.0 432 18000 250 W
Radeon RX 6800
(Navi 21)[173][174][175][176]		 Nov 18, 2020
$579 USD 		26.8×109
520 mm2		 3840:240:96:60
60 CU 		1700
2105 		408.0
505.2 		163.2
202.1 		26,112
32,333 		13,056
16,166 		816
1,010 		128 MB 1432.6 16 GB 512 GDDR6
256-bit 		16000
Radeon RX 6800 XT
(Navi 21)[173][177][175][176]		 Nov 18, 2020
$649 USD 		4608:288:128:72
72 CU 		1825
2250 		525.6
648.0 		233.6
288.0 		33,638
41,472 		16,819
20,736 		1,051
1,296 		1664.2 300 W
Radeon RX 6900 XT
(Navi 21)[173][178][175][176]		 Dec 8, 2020
$999 USD 		5120:320:128:80
80 CU 		1825
2250 		584.0
720.0 		233.6
288.0 		37,376
46,080 		18,688
23,040 		1,168
1,440
Radeon RX 6950 XT
(Navi 21)[179][180]		 May 10, 2022
$1,099 USD 		1890
2310 		604.8
739.2 		241.9
295.7 		38,707
47,309 		19,354
23,654 		1,210
1,478 		1793.5 576 18000 335 W
  1. ^ a b c Boost values (if available) are stated below the base value in italic.
  2. ^ Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. ^ Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. ^ Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. ^ Unified shaders : Texture mapping units : Render output units : Ray accelerators and Compute units (CU)
  6. ^ a b Lacks hardware video encoder

Radeon RX 7000 series

Main articles: Radeon RX 7000 series and RDNA 3
Model
(Code name) 		Release date
& price 		Architecture
& fab 		Chiplets
(active) 		Transistors
& die size[a]		 Core Fillrate[b][c][d] Processing power[b][e]
(TFLOPS) 		Infinity Cache Memory TBP Bus
interface
Config[f][g] Clock[b]
(MHz) 		Texture
(GT/s) 		Pixel
(GP/s) 		Half Single Double Size
(MB) 		Bandwidth
(GB/s) 		Size
(GB) 		Bandwidth
(GB/s) 		Bus type
& width 		Clock
(MT/s)
Radeon RX 7900 XT
(Navi 31)[182]		 Dec 13, 2022
$899 USD 		RDNA 3
TSMC N5 (GCD)
TSMC N6 (MCD) 		1 × GCD
5 × MCD 		57.7×109
~531 mm2		 5376:336:192
84:168:84 CU 		1500
2400 		504.0
806.4 		288.0
460.8 		64.51
103.2 		32.26
51.61 		1.008
1.613 		80 2900 20 800 GDDR6
320-bit 		20000 315 W PCIe 4.0
×16
Radeon RX 7900 XTX
(Navi 31)[183]		 Dec 13, 2022
$999 USD 		1 × GCD
6 × MCD 		6144:384:192
96:192:96 CU 		1900
2500 		729.6
960.0 		364.8
480.0 		93.39
122.9 		46.69
61.44 		1.459
1.920 		96 3500 24 960 GDDR6
384-bit 		355 W
  1. ^ Approximate die size of entire MCM package that consists of single GCD (Graphics Compute Die) and six MCDs (Memory Cache Die).
    Radeon RX 7900 XT has only five active MCDs, inactive one is for structual support and heat dissipation. Die size of GCD is 306 mm2, size of each MCD is 37.5 mm2.[181]
  2. ^ a b c Boost values (if available) are stated below the base value in italic.
  3. ^ Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  4. ^ Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  5. ^ Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  6. ^ Unified shaders : Texture mapping units : Render output units : Ray accelerators : AI accelerators and Compute units (CU)
  7. ^ GPUs based on RDNA 3 have dual-issue stream processors so that up to two shader instructions can be executed per clock cycle under certain parallelism conditions.

Mobile GPUs

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

Rage Mobility series

Main article: ATI Rage
Model Launch Fab (nm) Bus interface Core clock (MHz) Memory clock (MHz) Hardware T&L Core config1 Fillrate Memory API compliance (version) Notes
Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3D OpenGL
Rage LT (Rage II) Nov 1996 500 PCI 60 66 No 0:1:1:1 0.06 0.06 4 0.53 EDO, SDR, SGR 64 5 N/A
Rage LT Pro (Rage Pro) Nov 1997 350 AGP, PCI 75 100 0.075 0.075 8 0.80 6 1.1 Motion compensation
Rage Mobility M/P (Rage Pro) Nov 1998 250 90 Un­known 0.18 0.18 Un­known SDR, SGR Un­known Un­known M had 4 MB of integrated SDRAM, P had none. IDCT, motion compensation.
Rage Mobility M1 (Rage Pro) Feb 1999 90 90 0.72 SDR 6 1.2 M1 had 8 MB of integrated SDRAM, P had none. IDCT, motion compensation.
Rage 128 GL Aug 1998 103 103 0:2:2:2 0.206 0.206 32 1.65 128
Rage Mobility 128 (Rage 128 Pro) Oct 1999 105 105 0.21 0.21 16 2.28 IDCT, Motion Compensation
Rage Mobility M3 (AGP 4×) (Rage 128 Pro) 2.28 M3 had 8 MB of integrated SDRAM, IDCT, Motion Compensation.
Rage Mobility M4 (AGP 4×) (Rage 128 Pro) 32 2.28 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 Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory API compliance (version) Notes
Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3D OpenGL
Mobility Radeon 7000 Feb 2001 M6 RV100 180 AGP 4× 144
167 		144
183 		0:1:3:1 0.167 0.5 8
16
32 		1.464
2.928 		SDR
DDR 		32
64 		7 1.3
Mobility Radeon 7500 Dec 2001 M7 RV200 150 280 200 1:2:6:2 0.56 1.68 32
64 		3.2
6.4 		DDR 64
128 		7 PowerPlay II, DX7 T&L
Mobility Radeon 9000 Aug 2002 M9 RV250 250 1:4:4:4 1.0 1.0 8.1 1.4 PowerPlay 3.0, Fullstream
Mobility Radeon 9200 Mar 2003 M9+ RV280 AGP 8× 250/250 200/220 3.2/3.52
6.4/7.04
Mobility Radeon 9500 2004? M11 RV360 130 Un­known Un­known 2:4:4:4 Un­known Un­known 64 Un­known 9.0 2.0
Mobility Radeon 9550 2005 M12 210 183 0.84 0.84 2.928
5.856
Mobility Radeon 9600 Mar 2003 M10, M11 RV350 300 300 1.2 1.2 64
128 		4.8
9.6
Mobility Radeon 9600 Pro 2004 M10 350 350 1.4 1.4 128 11.2 128
Mobility Radeon 9700 Feb 2004 M11 RV360 450 275 1.8 1.8 8.8
Mobility Radeon 9800 Sep 2004 M18 R420 350 300 4:8:8:8 2.8 2.8 256 19.2 256

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 Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory API compliance (version) Notes
Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3D OpenGL
Mobility Radeon X300 Nov 2005 M22 RV370 110 PCI-E ×16 350 250 2:4:4:4 1.4 1.4 128 4 DDR 64 9.0b 2.0 Powerplay 5.0
Mobility Radeon X600 Jun 2004 M24 RV380 130 400 1.6 1.6 64, 128 8 128
Mobility Radeon X700 Mar 2005 M26 RV410 110 400-100 (PowerPlay) 350-200 6:8:8:4 1.4 2.8 Shared-128? 64, 128 11.2 DDR, GDDR3 3DC, dynamic lane count switching
Mobility Radeon X800 Nov 2004 M28 R423 130 400 400 6:12:12:12 4.8 4.8 256 25.6 GDDR3 256 3DC, DLCS, Clock Gating
Mobility Radeon X800 XT Jun 2005 M28 PRO R423 130 480 550 6:16:16:16 7.68 7.68 35.2

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

Mobility Radeon X1000 series

Main article: Radeon X1000 series
Model Launch Model number Code name Fab (nm) Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory API compliance (version) Notes
Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3D OpenGL
Mobility Radeon X1300 January 19, 2006 M52 RV515 90 PCIe ×16 350 250 2:4:4:4 1.4 1.4 128 + shared 8 DDR DDR2 128 9.0c 2.0
Mobility Radeon X1350 September 18, 2006 M62 470 350 1.88 1.88 11.2 DDR2 GDDR3
Mobility Radeon X1400 January 19, 2006 M54 445 250 1.78 1.78 8 DDR DDR2
Mobility Radeon X1450 September 18, 2006 M64 550 450 2.2 2.2 14.4 DDR2 GDDR3
Mobility Radeon X1600 February 1, 2006 M56 RV530 425
450 		375
470 		5:12:4:4 1.7
1.8 		1.7
1.8 		256 12.0
15.04 		DDR2
GDDR3
Mobility Radeon X1700 M66 RV535 475 400
550 		1.9 1.9 11.2
17.6 		strained silicon
Mobility Radeon X1800 March 1, 2006 M58 R520 450 500 8:12:12:12 5.4 5.4 32 GDDR3 256
Mobility Radeon X1800 XT M58 550 650 8:16:16:16 8.8 8.8 41.6
Mobility Radeon X1900 January 11, 2007 M68 RV570 80 400 470 8:36:12:12 4.8 4.8 30.08 PowerPlay 6.0

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

Mobility Radeon HD 2000 series

Main article: Radeon HD 2000 series

OpenGL 3.3 is possible with latest drivers for all RV6xx.

Model Launch Model number Code name Fab (nm) Bus interface Core clock (MHz) Memory clock (MHz) Core config Fillrate Memory API compliance (version) Processing power
(GFLOPS) 		Notes
Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3D OpenGL
Mobility Radeon X2300 March 1, 2007 M64 RV515 90 PCIe ×16 480 400 2:4:4:41 1.92 1.92 128 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 460 5:12:4:41 1.84 1.84 256 12.8 128 Un­known based on X1600/1700, HM up to 768Mb, no UVD, PowerPlay 6.0
Mobility Radeon HD 2300 March 1, 2007 M71 RV515 480 2:4:4:41 1.92 1.92 128
256
512 		6.4
12.8 		64
128 		Un­known same as X2300, but with UVD, PowerPlay 6.0
Mobility Radeon HD 2400 May 14, 2007 M72S RV610 65 450 40:4:42 1.8 1.8 256+ Hyper Memory 6.4 DDR2 64 10.0 2.0 (3.3) 36 UVD, PowerPlay 7.0
Mobility Radeon HD 2400 XT M72M 600
600 		400
700 		2.4 2.4 6.4
11.2 		DDR2
GDDR3 		48
Mobility Radeon HD 2600 M76M RV630 500
500 		400
600 		120:8:42 2.0 4.0 12.8
19.2 		128 120
Mobility Radeon HD 2600 XT M76XT 680 750 2.72 5.44 24 GDDR3 168
Mobility Radeon HD 2700 December 12, 2007 M76 650 700 2.6 5.2 256+ Hyper Memory (total 768) 22.4

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

Mobility Radeon HD 3000 series

Main article: Radeon HD 3000 series
Model[184] Launch Model number Code name Fab (nm) Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory API compliance (version) Processing power
(GFLOPS) 		TDP

(Watts)

Notes
Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3D OpenGL
Mobility Radeon HD 3100 August 1, 2008 RS780MC RV620 55 PCIe ×16 1.1 300 800
(system memory) 		40:4:4 1.2 1.2 up to 512 from system memory 6.4/12.8 DDR2 64/128 10.1 2.0 (3.3) 24 UVD, PowerPlay 7.0
Mobility Radeon HD 3200 June 4, 2008 RS780MC 500 800
(system memory) 		2 2 6.4/12.8 40
Mobility Radeon HD 3410 July 25, 2008 M82-MPE 400 400 1.6 1.6 256, 512 6.4 64 32
Mobility Radeon HD 3430 M82-SE PCIe ×16 2.0 450 400 1.8 1.8 256 6.4 36
Mobility Radeon HD 3450 January 7, 2008 M82 500 400
700 		2 2 6.4
11.2 		DDR2
GDDR3 		40
Mobility Radeon HD 3470 M82-XT 680 400
800 		2.72 2.72 6.4
12.8 		54.4
Mobility Radeon HD 3650 M86 RV635 500 500
700 		120:8:4 2 4 512
1024 		16.0
22.4 		DDR2
GDDR3
GDDR4 		128 3.3 120
Mobility Radeon HD 3670 M86-XT 680 800 2.72 5.44 25.6 2.0 (3.3) 163.2 30 UVD, PowerPlay 7.0
Mobility Radeon HD 3850 June 4, 2008 M88-L/M88-LP RV670 580 750 320:16:16 9.28 9.28 512 48.0 GDDR3 256 371.2
Mobility Radeon HD 3870 M88-LXT 660 850 10.56 10.56 54.4 422.4 55
Mobility Radeon HD 3850 X2 June 5, 2008 2× M88-L/M88-LP R680 580 750 2x [320:16:16] 2× 9.28 2× 9.28 2× 512 2× 48.0 2× 256 2× 371.2
Mobility Radeon HD 3870 X2 September 1, 2008 2× M88-LXT 660 850 2× 10.56 2× 10.56 2× 54.4 2× 422.4 110

1 Unified Shaders : Texture mapping units : Render output units

Mobility Radeon HD 4000 series

Main article: Radeon HD 4000 series
Model Launch Model Number Code name Fab (nm) Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory API compliance (version) Processing power
(GFLOPS) 		Notes
Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3D OpenGL
Mobility Radeon HD 4200 September 10, 2009 Un­known RV620 55 Internal PCIe x16 1.1 500 800
(system memory) 		40:4:4 2 2 up to 512 from system memory 6.4/12.8 DDR2 DDR3 64/128 10.1 3.3 40 UVD2, PowerPlay 7.0
Mobility Radeon HD 4225 May 1, 2010 Un­known 380 1.52 1.52 30.4
Mobility Radeon HD 4250 Un­known 500 2 2 40
Mobility Radeon HD 4270 Un­known 590 2.36 2.36 47.2
Mobility Radeon HD 4330 January 9, 2009 M92 RV710 PCIe ×16 2.0 450 600 80:8:4 1.8 3.6 512 9.6 DDR2
DDR3
GDDR3 		64 72
Mobility Radeon HD 4530 500 700 2 4 11.2 80
Mobility Radeon HD 4550 January 1, 2010 550 2.2 4.4 80
Mobility Radeon HD 4570 January 9, 2009 680 800 2.72 5.44 12.8 108.8
Mobility Radeon HD 4650 M96 RV730 500
550 		600
800 		320:32:8 4
4.4 		16
17.6 		512
1024 		19.2
25.6 		DDR2
DDR3
GDDR3 		128 320
352
Mobility Radeon HD 4670 M96-XT 675 800 5.4 21.6 12.8
25.6 		432
Mobility Radeon HD 4830 March 3, 2009[185] M97 RV740 40 400/600
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 		512/768
512/768
Mobility Radeon HD 4850[186] January 9, 2009 M98 RV770 55 500 850
700 		800:40:16 8 20 1024 54.4
89.6 		GDDR3
GDDR52		 256 800
Mobility Radeon HD 4860 March 3, 2009[185] M97 RV740 40 650 1000 640:32:16 10.4 20.8 64.0 GDDR52 128 832
Mobility Radeon HD 4870 January 9, 2009 M98-XT RV770 55 550 888
700 		800:40:16 8.8 22 512
1024 		56.832
89.6 		GDDR3
GDDR52		 256 880
Mobility Radeon HD 4870 X2 550 700 2× [800:40:16] 2× 8.8 2× 22 2048 2× 89.6 GDDR52 2× 256 2× 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 it is with other DDR memory.

Mobility Radeon HD 5000 series

Main article: Radeon HD 5000 series
Model: Mobility Radeon Launch Model Number Code name Fab (nm) Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Fillrate Memory API compliance (version) Processing power
(GFLOPS) 		TDP (Watts)
Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3D OpenGL
Mobility Radeon HD 530v[187] May 5, 2010 M92 RV710 55 PCIe ×16 2.0 500 600 80:8:4 2 4 1024 9.6 DDR2
DDR3
GDDR3 		64 10.1 3.3 80 10
Mobility Radeon HD 545v[188] 720 400

800

2.88 5.76 512

1024

6.4

12.8

115.2 15
Mobility Radeon HD 550v[189] M96 RV730 450 600 320:32:8 3.6 14.4 1024 19.2 128 288 10
Mobility Radeon HD 560v[190] 550 800 4.4 17.6 25.6 352 15
Mobility Radeon HD 565v[191] M96-XT 675 5.4 21.6 25.6 432 20
Mobility Radeon HD 5145 January 7, 2010 M92 RV710 720 900 80:8:4 2.88 5.76 14.4 DDR3
GDDR3 		64 115.2 15
Mobility Radeon HD 5165 M96 RV730 600 320:32:8 4.8 19.2 28.8 128 384 35
Mobility Radeon HD 5430 Park LP Cedar (RV 810) 40 PCIe ×16 2.1 500
550 		800 80:8:4 2.0
2.2 		4.0
4.4 		12.8 64 11 4.4 80
88 		7
Mobility Radeon HD 5450 Park PRO 675 2.7 5.4 108 11
Mobility Radeon HD 5470 Park XT 750 3 6 1024
512 		12.8
25.6 		DDR3
GDDR3
GDDR5 		120 13
15
Mobility Radeon HD 5650 Madison PRO Redwood (RV 830) 450
650 		400:20:8 3.6
5.2 		9.0
13.0 		1024 25.6 DDR3
GDDR3 		128 360
520 		15
19
Mobility Radeon HD 5730 Madison LP 650 5.2 13 520 26
Mobility Radeon HD 5750 Madison PRO 550 4.4 11 51.2 GDDR5 440 25
Mobility Radeon HD 5770 Madison XT PCIe ×16 2.0/2.1 650 5.2 13 520 30
Mobility Radeon HD 5830 Broadway LP Juniper (RV 840) PCIe ×16 2.1 500 800:40:16 8 20 25.6 DDR3
GDDR3 		800 24
Mobility Radeon HD 5850 Broadway PRO 625
500
625 		900
1000 		800:40:16 10
8
10 		25
20
25 		2048
1024 		28.8
64
64 		1000
800
1000az 		31
30
39
Mobility Radeon HD 5870 Broadway XT 700 1000 11.2 28 1024 64 GDDR5 1120 50
Model Launch Model Number Code name Fab (nm) Bus interface Core clock (MHz) Memory clock (MHz) Core config1 Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3D 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 it is with other DDR memory.

Radeon HD 6000M series

Main article: Radeon HD 6000 series
Model[192] Launch Architecture
Fab 		Core Fillrate[a][b] Processing power[c]
(GFLOPS) 		Memory TDP (Watts) Bus interface
Config[d] Clock (MHz) Pixel (GP/s) Texture (GT/s) Size (MiB) Bus type &
width 		Clock (MHz) Bandwidth (GB/s)
Radeon HD 6330M
(Robson LP)[193]		 November 2010 TeraScale 2
40 nm 		80:8:4 500 2.0 4.0 80 1024 DDR3
64-bit 		800 12.8 7 PCIe 2.1 x16
Radeon HD 6350M
(Robson Pro)[193]		 November 2010 500 2.0 4.0 80 1024 DDR3
64-bit 		800
900 		12.8
14.4 		7
Radeon HD 6370M
(Robson XT)[193]		 November 2010 750 3.0 6.0 120 1024 DDR3
64-bit 		900 14.4 11
Radeon HD 6430M
(Seymour LP)[194]		 January 2011 TeraScale 2
40 nm 		160:8:4 480 1.92 3.84 153.6 1024 DDR3
64-bit 		800 12.8 Un­known PCIe 2.1 x16
Radeon HD 6450M
(Seymour Pro)[194]		 January 2011 600 2.4 4.8 192 1024 DDR3
64-bit 		800 12.8 Un­known
Radeon HD 6470M
(Seymour XT)[194]		 January 2011 700
750 		2.8
3.0 		5.6
6.0 		224
240 		1024 DDR3
64-bit 		800
800 		12.8 Un­known
Radeon HD 6490M
(Seymour XT)[194]		 January 2011 800 3.2 6.4 256 512 GDDR5
64-bit 		800 25.6 Un­known
Radeon HD 6530M
(Capilano Pro)[195]		 November 2010 TeraScale 2
40 nm 		400:20:8 500 4.0 10.0 400 1024 DDR3
128-bit 		900 28.8 26 PCIe 2.1 x16
Radeon HD 6550M
(Capilano Pro)[195]		 November 2010 600 4.8 12.0 480 1024 DDR3
128-bit 		900 28.8 26
Radeon HD 6570M
(Capilano XT)[195]		 November 2010 650 5.2 13.0 520 1024 DDR3
64-bit
GDDR5
128-bit 		900 28.8

57.6

 30
Radeon HD 6630M
(Whistler LP)[196]		 January 2011 TeraScale 2
40 nm 		480:24:8 485 3.88 11.64 465.6 256 (Mac)

1024

 GDDR5
128-bit (Mac)
DDR3
128-bit 		800 51.2 (Mac)

25.6

 Un­known PCIe 2.1 x16
Radeon HD 6650M
(Whistler Pro)[196]		 January 2011 600 4.8 14.4 576 1024 DDR3
128-bit 		900 28.8 Un­known
Radeon HD 6730M
(Whistler XT)[196]		 January 2011 725 5.8 17.4 696 1024 DDR3
128-bit 		800 25.6 Un­known
Radeon HD 6750M
(Whistler Pro)[196]		 January 2011 600 4.8 14.4 576 256
512
1024 		GDDR5
128-bit 		800
900 		51.2
57.6 		Un­known
Radeon HD 6770M
(Whistler XT)[196]		 January 2011 725 5.8 17.4 696 1024 GDDR5
128-bit 		900 57.6 Un­known
Radeon HD 6830M
(Granville Pro)[197]		 January 2011 TeraScale 2
40 nm 		800:40:16 575 9.2 23.0 920 2048 DDR3
128-bit 		800 25.6 39 PCIe 2.1 x16
Radeon HD 6850M
(Granville XT)[197]		 January 2011 675 10.8 27.0 1080 2048 DDR3
128-bit 		800 25.6 50
Radeon HD 6850M
(Granville Pro)[197]		 January 2011 575 9.2 23.0 920 1024 GDDR5
128-bit 		800 57.6 39
Radeon HD 6870M
(Granville XT)[197]		 January 2011 675 10.8 27 1080 1024 GDDR5
128-bit 		1000 64 50
Radeon HD 6950M
(Blackcomb Pro)[198]		 January 2011 TeraScale 2
40 nm 		960:48:32 580 18.56 27.84 1113.6 2048 GDDR5
256-bit 		900 115.2 50 PCIe 2.1 x16
Radeon HD 6970M
(Blackcomb XT)[198]		 January 2011 680 21.76 32.64 1305.6 2048 GDDR5
256-bit 		900 115.2 75
Radeon HD 6990M
(Blackcomb XTX)[199]		 July 2011 TeraScale 2
40 nm 		1120:56:32 715 22.88 40.04 1601.6 2048 GDDR5
256-bit 		900 115.2 75 PCIe 2.1 x16
  1. ^ Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the core clock speed.
  2. ^ Pixel fillrate is calculated as the number of Render Output Units multiplied by the core clock speed.
  3. ^ Single Precision performance is calculated from the core clock speed based on a FMA operation.
  4. ^ Unified Shaders : Texture Mapping Units : Render Output Units

IGP (HD 6000)

  • All models feature the UNB/MC Bus interface
  • All models do mnot feature double-precision FP
  • All models feature Angle independent anisotropic filtering, UVD3, and Eyefinity capabilities, with up to three outputs.
Model Released Code name Architecture Fab (nm) Core clock rate (MHz) Config core[a] Fillrate Shared memory Processing power
(GFLOPS) 		API compliance (version) Combined TDP[b] APU
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit) Direct3D OpenGL OpenCL Vulkan Idle (W) Max. (W)
Radeon HD 6250[200] November 9, 2010[201] Wrestler[202] TeraScale 2 40 280–400 80:8:4:2 1.12–1.6 2.24–3.2 8.525 DDR3-1066 64 44.8–64 11.3
(11_0) 		4.5 1.2 — Un­known 9 C-30, C-50, Z-60
Radeon HD 6290 January 7, 2011 Ontario 276–400 C-60
Radeon HD 6310[200] November 9, 2010[201] Wrestler[202] 492 2.0 4.0 80 18 E-240, E-300, E-350
Radeon HD 6320 August 15, 2011 508–600 2.032–2.4 4.064–4.8 10.6 DDR3-1333 82–97 E-450
  1. ^ Unified Shaders : Texture Mapping Units : Render Output Units : Compute units
  2. ^ TDP specified for AMD reference designs, includes CPU power consumption. Actual TDP of retail products may vary.

IGP (HD 6000G)

  • All models include Direct3D 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) Core config1 Fillrate Shared Memory Processing power
(GFLOPS) 		Max. combined TDP2 (Watts) APU
Pixel (GP/s) Texture (GT/s) Bandwidth (GB/s) Bus type Bus width (bit)
Radeon HD 6380G June 14, 2011 WinterPark 32 400 160:8:4:2 1.6 3.2 17.06 DDR3-1333 128 128 35 E2-3000M
Radeon HD 6480G BeaverCreek 444 240:12:4:3 1.77 3.55 213.1 35 - 45 A4-3300M A4-3310MX
Radeon HD 6520G 400 320:16:8:4 3.2 6.4 256 A6-3400M A6-3410MX A6-3420M
Radeon HD 6620G 444 400:20:8:5 3.55 8.88 25.6 DDR3-1600 355.2 A8-3500M A8-3510MX A8-3530MX

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

Radeon HD 7000M series

Main article: Radeon HD 7000 series
 
A Radeon HD 7970M GPU on a Mobile PCI Express Module
Model
(Codename) 		Launch Architecture
(Fab) 		Core Fillrate Processing power
(GFLOPS) 		Memory Bus interface TDP (W)
Config[a] Clock (MHz) Texture (GT/s) Pixel (GP/s) Size (GiB) Bus type &
width (bit)[b]		 Memory (MHz) Bandwidth (GB/s)
Radeon HD 7430M
(Seymour Pro) 		January 2012 TeraScale 2[c]
(40 nm) 		160:8:4:2 600 4.8 2.4 192 1 DDR3
64-bit 		900 14.4 PCIe 2.1 ×16 7
Radeon HD 7450M
(Seymour Pro) 		700
700 		5.6 2.8 224 1 DDR3
GDDR5
64-bit 		900
800

 14.4
25.6

 7
Radeon HD 7470M
(Seymour XT) 		750
800 		6
6.4 		3.0
3.2 		240
256 		1 DDR3
GDDR5
64-bit 		900
800

 14.4
25.6

 7~9
Radeon HD 7490M
(Seymour XTX) 		800 6.4 3.2 256 1 GDDR5
64-bit 		950 30.4 9
Radeon HD 7510M
(Thames LE) 		January 2012 TeraScale 2[c]
(40 nm) 		400:20:8:5 450 9.0 3.6 360 1 DDR3
64-bit 		800 12.8 11
Radeon HD 7530M
(Thames LP) 		January 2012 TeraScale 2[c]
(40 nm) 		400:24:8:5 450 9.0 3.6 360 1 DDR3
64-bit 		900 14.4 11
Radeon HD 7550M
(Thames Pro) 		January 2012 TeraScale 2[c]
(40 nm) 		400:20:8:5 450
550 		9.0
11.0 		3.6
4.4 		360
440 		1 DDR3
GDDR5
64-bit 		900
800

 14.4
25.6

 13
Radeon HD 7570M
(Thames Pro) 		January 2012 TeraScale 2[c]
(40 nm) 		400:20:8:5 450
650 		9.0
13.0 		3.6
5.2 		360
520 		1 DDR3
GDDR5
64-bit 		900
800

 14.4
25.6

 13~15
Radeon HD 7590M
(Thames XT) 		January 2012 TeraScale 2[c]
(40 nm) 		480:24:8:6 600 14.4 4.8 576 1 GDDR5
64-bit 		800 25.6 18
Radeon HD 7610M
(Thames LE) 		January 2012 TeraScale 2[c]
(40 nm) 		400:20:8:5 450 9.0 3.6 360 1 DDR3
128-bit 		800 25.6 20
Radeon HD 7630M
(Thames LP) 		January 2012 TeraScale 2[c]
(40 nm) 		480:24:8:6 450 10.8 3.6 432 1 DDR3
128-bit 		800 25.6 20~25
Radeon HD 7650M
(Thames Pro) 		450
550 		10.8
13.2 		3.6
4.4 		432
528 		1 DDR3
128-bit 		800
800 		25.6 20~25
Radeon HD 7670M
(Thames Pro) 		600 14.4 4.8 576 1 DDR3
GDDR5
128-bit 		900 28.8
57.6

 20~25
Radeon HD 7690M
(Thames XT) 		725
600 		17.4
14.4 		5.8
4.8 		696
576 		1
2 		DDR3
GDDR5
128-bit 		900
900

 28.8
57.6

 20~25
Radeon HD 7690M XT
(Thames XTX) 		725 17.4 5.8 696 1
2 		GDDR5
128-bit 		900 57.6 25
Radeon HD 7730M
(Chelsea LP) 		April 2012 GCN 1st gen
(28 nm) 		512:32:16:8 575
675 		18.4
21.6 		9.2
10.8 		588.8
691.2 		2 GDDR3
128-bit 		900
900 		28.8 PCIe 2.1 ×16 25~28
Radeon HD 7750M
(Chelsea Pro) 		575 18.4 9.2 588.8 1
2 		GDDR5
128-bit 		1000 64 28
Radeon HD 7770M
(Chelsea XT) 		675 21.6 10.8 691.2 1
2 		GDDR5
128-bit 		1000 64 32
Radeon HD 7850M
(Heathrow Pro) 		April 2012 GCN 1st gen
(28 nm) 		640:40:16:10 675 27 10.8 864 2 GDDR5
128-bit 		1000 64 PCIe 3.0 ×16 40
Radeon HD 7870M
(Heathrow XT) 		800 32 12.8 1024 2 GDDR5
128-bit 		1000 64 40–45
Radeon HD 7970M
(Wimbledon XT) 		April 2012 GCN 1st gen
(28 nm) 		1280:80:32:20 850 68 27.2 2176 2
4 		GDDR5
256-bit 		1200 153.6 PCIe 3.0 ×16 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 it is with other DDR memory.
  3. ^ a b c d e f g h Lacks hardware video encoder

IGP (HD 7000G)

Main article: Radeon HD 7000 series
Model
(Codename) 		Launch Architecture
(Fab) 		Core config[a] Clock rate (MHz) Fillrate Processing power
(GFLOPS) 		Shared memory
Core (MHz) Boost (MHz) Pixel (GP/s) Texture (GT/s) Bus type
& width (bit) 		Clock Bandwidth (GB/s)
Radeon HD 7400G
(Scrapper) 		September 2012 TeraScale 3[b]
(32 nm) 		192:12:4 327 424 1.31 3.92 125.57 DDR3
128-bit 		1333 to 2133 21.33–34.13
Radeon HD 7420G
(Scrapper) 		June 2012 128:8:4 480 655 1.92 3.84 122.88
Radeon HD 7500G
(Scrapper) 		May 2012 256:16:8 327 424 2.62 5.23 167.42
Radeon HD 7520G
(Scrapper) 		June 2012 192:12:4 496 685 1.98 5.95 190.46
Radeon HD 7600G
(Devastator) 		September 2012 384:24:8 320 424 2.56 7.68 245.76
Radeon HD 7620G
(Devastator) 		May 2012 360 497 2.88 8.64 276.48
Radeon HD 7640G
(Devastator) 		256:16:8 496 685 3.97 7.94 253.95
Radeon HD 7660G
(Devastator) 		384:24:8 11.9 380.93
  1. ^ Unified Shaders : Texture Mapping Units : Render Output Units
  2. ^ Lacks hardware video encoder

Radeon HD 8000M series

Main article: Radeon HD 8000 series
Model
(Codename) 		Launch Architecture
(Fab) 		Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory[e] TDP (W)
Config[f] Clock[a] (MHz) Texture (GT/s) Pixel (GP/s) Size (GiB) Bus type &
width (bit) 		Clock (MHz) Band-
width (GB/s)
Radeon
HD 8550M / 8630M
(Sun LE) 		8 January 2013 GCN 1st gen
(28 nm) 		384:24:8 650
700 		5.2
5.6 		15.6
16.8 		537.6 1 DDR3
64 		900 14.4 Un­known
Radeon
HD 8570M / 8650M
(Sun Pro) 		8 January 2013 384:24:8 650
700 		5.2
5.6 		15.6
16.8 		537.6 1 GDDR5
64 		1125 36 Un­known
Radeon
HD 8670M
(Mars XT) 		8 January 2013 384:24:8 775
825 		6.2
6.6 		18.6
19.8 		633.6 1 DDR3
64 		900 14.4 Un­known
Radeon
HD 8690M
(Sun XT) 		8 January 2013 384:24:8 775
825 		6.2
6.6 		18.6
19.8 		633.6 1 GDDR5
64 		1125 36 Un­known
Radeon
HD 8730M
(Mars LE) 		8 January 2013 384:24:8 650
700 		5.2
5.6 		15.6
16.8 		537.6 2 DDR3
128 		1000 32 Un­known
Radeon
HD 8750M
(Mars Pro) 		8 January 2013 384:24:8 620–775
670–825 		4.96
6.6 		14.88
19.8 		514.56
633.6 		2 DDR3
GDDR5
128 		1000 32
64

 Un­known
Radeon
HD 8770M
(Mars XT) 		8 January 2013 384:24:8 775
825 		6.2
6.6 		18.6
19.8 		633.6 2 GDDR5
128 		1125 72 Un­known
Radeon
HD 8790M
(Mars XTX) 		8 January 2013 384:24:8 850
900 		6.8
7.2 		20.4
21.6 		691.2 2 GDDR5
128 		1125 72 Un­known
Radeon
HD 8830M
(Venus LE) 		8 January 2013 640:40:16 575
625 		9.2
10 		23
25 		800 2 DDR3
128 		1000 32 Un­known
Radeon
HD 8850M
(Venus Pro) 		8 January 2013 640:40:16 575–725
625–775 		9.2
12.4 		23
31 		800
992 		2 DDR3
GDDR5
128 		1000
1125

 32
72

 Un­known
Radeon
HD 8870M
(Venus XT) 		8 January 2013 640:40:16 725
775 		11.6
12.4 		29
31 		992 2 DDR3
GDDR5
128 		1000
1125

 32
72

 Un­known
Radeon
HD 8970M
(Neptune XT) 		8 January 2013 1280:80:32 850
900 		27.2
28.8 		68
72 		2304 2
4 		GDDR5
256 		1200 153.6 100
  1. ^ a b c Boost values (if available) are stated below the base value in italic.
  2. ^ Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. ^ Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. ^ Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. ^ The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.
  6. ^ Unified Shaders : Texture Mapping Units : Render Output Units

Radeon M200 series

Main article: Radeon 200 series § Mobile
May 12, 2023
list, graphics, processing, units, following, list, that, contains, general, information, about, gpus, video, cards, including, those, technologies, before, 2006, based, official, specifications, table, form, contents, field, explanations, video, codec, accele. The following is a list that contains general information about GPUs and video cards by AMD including those by ATI Technologies before 2006 based on official specifications in table form Contents 1 Field explanations 2 Video codec acceleration 3 Features overview 4 API overview 5 Desktop GPUs 5 1 Wonder series 5 2 Mach series 5 3 Rage series 5 4 Radeon 7000 series 5 4 1 IGP 3xx series 5 5 Radeon 8000 and 9000 series 5 5 1 IGP 9000 series 5 6 Radeon R300 series 5 6 1 AGP 9000 series X1000 series 5 6 2 PCI E X3xx X5xx X6xx X1000 series 5 6 3 IGP X2xx 11xx series 5 7 Radeon X700 and X800 series 5 7 1 AGP X7xx X8xx 5 7 2 PCI E X5xx X7xx X8xx X1000 series 5 7 3 IGP X12xx 21xx 5 8 Radeon X1000 series 5 9 Radeon HD 2000 series 5 10 Radeon HD 3000 series 5 10 1 IGP HD 3000 5 11 All in Wonder series 5 12 Radeon HD 4000 series 5 12 1 IGP HD 4000 5 13 Radeon HD 5000 series 5 14 Radeon HD 6000 series 5 14 1 IGP HD 6000 5 15 Radeon HD 7000 series 5 15 1 IGP HD 7000 5 16 Radeon HD 8000 series 5 17 Radeon 200 series 5 18 Radeon 300 series 5 19 Radeon 400 series 5 20 Radeon 500 series 5 21 Radeon RX Vega series 5 22 Radeon VII series 5 23 Radeon RX 5000 series 5 24 Radeon RX 6000 series 5 25 Radeon RX 7000 series 6 Mobile GPUs 6 1 Rage Mobility series 6 2 Mobility Radeon series 6 3 Mobility Radeon X300 X600 X700 X800 series 6 4 Mobility Radeon X1000 series 6 5 Mobility Radeon HD 2000 series 6 6 Mobility Radeon HD 3000 series 6 7 Mobility Radeon HD 4000 series 6 8 Mobility Radeon HD 5000 series 6 9 Radeon HD 6000M series 6 9 1 IGP HD 6000 6 9 2 IGP HD 6000G 6 10 Radeon HD 7000M series 6 10 1 IGP HD 7000G 6 11 Radeon HD 8000M series 6 12 Radeon M200 series 6 13 Radeon M300 series 6 14 Radeon M400 series 6 15 Radeon 500 series 6 16 Radeon 600 series 6 17 Radeon RX 5000M series 6 18 Radeon RX 6000M series 6 19 Radeon RX 7000M series 7 Workstation GPUs 7 1 FireGL series 7 2 FireMV Multi View series 7 3 FirePro Multi View series 7 4 FirePro 3D series V000 7 5 FirePro series Vx900 7 6 FirePro Workstation series Wx000 7 7 FirePro D Series 7 8 FirePro Workstation series Wx100 7 9 FirePro Workstation series Wx300 7 10 Radeon PRO series 7 11 Radeon Pro WX x100 series 7 12 Radeon Pro WX x200 series 7 13 Radeon Pro Vega series 7 14 Radeon Pro 5000 series 7 15 Radeon Pro W5000 series 7 16 Radeon Pro W6000 series 7 17 Radeon Pro W7000 series 8 Mobile workstation GPUs 8 1 Mobility FireGL series 8 2 FirePro Mobile series 8 3 Radeon Pro WX x100 Mobile series 8 4 Radeon Pro 400 series 8 5 Radeon Pro 500 series 8 6 Radeon Pro WX x200 Mobile series 8 7 Radeon Pro Vega series 8 8 Radeon Pro 5000M series 8 9 Radeon Pro W5000M series 8 10 Radeon Pro W6000M series 9 Server GPUs 9 1 FireStream series 9 2 FirePro Remote series 9 3 FirePro Server series S000x Sxx 000 9 4 Radeon Sky series 9 5 Radeon Pro V series 9 6 Radeon Instinct series 10 Embedded GPUs 11 Console GPUs 12 See also 13 References 14 External linksField explanations EditThe headers in the table listed below describe the following Model The marketing name for the GPU assigned by AMD ATI Note that ATI trademarks have been replaced by AMD trademarks starting with the Radeon HD 6000 series for desktop and AMD FirePro series for professional graphics Codename The internal engineering codename for the GPU Launch Date of release for the GPU Architecture The microarchitecture used by the GPU Fab Fabrication process Average feature size of components of the GPU Transistors Number of transistors on the die Die size Physical surface area of the die Core config The layout of the graphics pipeline in terms of functional units Core clock The reference base and boost if available core clock frequency Fillrate Pixel The rate at which pixels can be rendered by the raster operators to a display Measured in pixels s Texture The rate at which textures can be mapped by the texture mapping units onto a polygon mesh Measured in texels s Performance Shader operations How many operations the pixel shaders or unified shaders in Direct3D 10 and newer GPUs can perform Measured in operations s Vertex operations The amount of geometry operations that can be processed on the vertex shaders in one second only applies to Direct3D 9 0c and older GPUs Measured in vertices s Memory Bus type Type of memory bus utilized Bus width Maximum bit width of the memory bus utilized Size Size of the graphics memory Clock The reference memory clock frequency Bandwidth Maximum theoretical memory bandwidth based on bus type and width TDP Thermal design power Maximum amount of heat generated by the GPU chip measured in Watt TBP Typical board power Typical power drawn by the total board including power for the GPU chip and peripheral equipment such as Voltage regulator module memory fans etc measured in Watt Bus interface Bus by which the graphics processor is attached to the system typically an expansion slot such as PCI AGP or PCIe API support Rendering and computing APIs supported by the GPU and driver Due to conventions changing over time some numerical definitions such as core config core clock performance and memory should not be compared one to one across generations The following tables are for reference use only and do not reflect actual performance Video codec acceleration EditR100 Video Immersion R200 Video Immersion II R300 Video Immersion II Video Shader R410 Video Shader HD R420 Video Shader HD DXVA R520 Avivo Video R600 Avivo HD UVD 1 0 R700 UVD 2 UVD 2 2 Evergreen UVD 2 2 Northern Islands UVD 3 HD 67xx UVD 2 2 Southern Islands UVD 3 1 VCE 1 0 Sea Islands UVD 4 2 VCE 2 0 Volcanic Islands UVD 5 0 6 0 VCE 3 0 Arctic Islands UVD 6 3 VCE 3 4 Vega UVD 7 0 VCE 4 0 and VCN 1 0 only at AMD Raven Ridge Navi 1X VCN 2 0 Navi 2X VCN 3 0Features overview EditThe following table shows features of AMD ATI s GPUs VisualEditor viewtalkedit Name of GPU series Wonder Mach 3D Rage Rage Pro Rage 128 R100 R200 R300 R400 R500 R600 RV670 R700 Evergreen NorthernIslands SouthernIslands SeaIslands VolcanicIslands ArcticIslands Polaris Vega Navi 1x Navi 2x Navi 3xReleased 1986 1991 Apr1996 Mar1997 Aug1998 Apr2000 Aug2001 Sep2002 May2004 Oct2005 May2007 Nov2007 Jun2008 Sep2009 Oct2010 Jan2012 Sep2013 Jun2015 Jun 2016 Apr 2017 Aug 2019 Jun 2017 Feb 2019 Jul2019 Nov2020 Dec2022Marketing Name Wonder Mach 3DRage RagePro Rage128 Radeon7000 Radeon8000 Radeon9000 RadeonX700 X800 RadeonX1000 RadeonHD 2000 RadeonHD 3000 RadeonHD 4000 RadeonHD 5000 RadeonHD 6000 RadeonHD 7000 Radeon200 Radeon300 Radeon400 500 600 RadeonRX Vega Radeon VII RadeonRX 5000 RadeonRX 6000 RadeonRX 7000AMD support Kind 2D 3DInstruction set architecture Not publicly known TeraScale instruction set GCN instruction set RDNA instruction setMicroarchitecture TeraScale 1 VLIW TeraScale 2 VLIW5 TeraScale 2 VLIW5 up to 68xx TeraScale 3 VLIW4 in 69xx 1 2 GCN 1stgen GCN 2ndgen GCN 3rdgen GCN 4thgen GCN 5thgen RDNA RDNA 2 RDNA 3Type Fixed pipeline a Programmable pixel amp vertex pipelines Unified shader modelDirect3D 5 0 6 0 7 0 8 1 9 011 9 2 9 0b11 9 2 9 0c11 9 3 10 011 10 0 10 111 10 1 11 11 0 11 11 1 12 11 1 11 12 0 12 12 0 11 12 1 12 12 1 11 12 1 12 12 2 Shader model 1 4 2 0 2 0b 3 0 4 0 4 1 5 0 5 1 5 16 5 6 7 6 7OpenGL 1 1 1 2 1 3 2 1 b 3 3 3 4 5 on Linux 4 5 Mesa 3D 21 0 4 5 6 c 4 6 on Linux 4 6 Mesa 3D 20 0 Vulkan 1 0 Win 7 or Mesa 17 1 2 Adrenalin 20 1 2 Linux Mesa 3D 20 0 1 3 GCN 4 and above with Adrenalin 22 1 2 Mesa 22 0 1 3OpenCL Close to Metal 1 1 no Mesa 3D support 1 2 on Linux 1 1 no Image support with Mesa 3D 2 0 Adrenalin driver on Win7 on Linux 1 1 no Image support with Mesa 3D 2 0 with AMD drivers or AMD ROCm 2 0 2 1 7 HSA ROCm Video decoding ASIC Avivo UVD UVD UVD 2 UVD 2 2 UVD 3 UVD 4 UVD 4 2 UVD 5 0 or 6 0 UVD 6 3 UVD 7 8 d VCN 2 0 8 d VCN 3 0 9 Video encoding ASIC VCE 1 0 VCE 2 0 VCE 3 0 or 3 1 VCE 3 4 VCE 4 0 8 d Fluid Motion ASIC e Power saving PowerPlay PowerTune PowerTune amp ZeroCore Power TrueAudio Via dedicated DSP Via shadersFreeSync 12 HDCP f 1 4 2 2 2 3 10 PlayReady f 3 0 3 0 Supported displays g 1 2 2 2 6 Max resolution 2 6 2560 1600 2 6 4096 2160 30 Hz 2 6 5120 2880 60 Hz 3 7680 4320 60 Hz 11 7680 4320 60 Hz PowerColor drm radeon h drm amdgpu h Experimental 12 The Radeon 100 Series has programmable pixel shaders but do not fully comply with DirectX 8 or Pixel Shader 1 0 See article on R100 s pixel shaders R300 R400 and R500 based cards do not fully comply with OpenGL 2 as the hardware does not support all types of non power of two NPOT textures OpenGL 4 compliance requires supporting FP64 shaders and these are emulated on some TeraScale chips using 32 bit hardware a b c The UVD and VCE were replaced by the Video Core Next VCN ASIC in the Raven Ridge APU implementation of Vega Video processing ASIC for video frame rate interpolation technique In Windows it works as a DirectShow filter in your player In Linux there is no support on the part of drivers and or community a b To play protected video content it also requires card operating system driver and application support A compatible HDCP display is also needed for this HDCP is mandatory for the output of certain audio formats placing additional constraints on the multimedia setup More displays may be supported with native DisplayPort connections or splitting the maximum resolution between multiple monitors with active converters a b DRM Direct Rendering Manager is a component of the Linux kernel AMDgpu is the Linux kernel module Support in this table refers to the most current version API overview EditThe following table shows the graphics and compute APIs support across AMD GPU micro architectures Note that a branding series might include older generation chips VisualEditor viewtalkedit Chip series Micro architecture Fab Supported APIs AMD support Year introduced Introduced withRendering Computing ROCmVulkan 13 OpenGL 14 Direct3D HSA OpenCLWonder Fixed pipeline a 1000 nm800 nm Ended 1986Mach 800 nm600 nm 19913D Rage 500 nm 5 0 1996 3D RageRage Pro 350 nm 1 1 6 0 1997 Rage ProRage 128 250 nm 1 2 1998 Rage 128 GL VRR100 180 nm150 nm 1 3 7 0 2000 RadeonR200 Programmablepixel amp vertexpipelines 150 nm 8 1 2001 Radeon 8500R300 150 nm130 nm110 nm 2 0 b 9 011 FL 9 2 2002 Radeon 9700R420 130 nm110 nm 9 0b11 FL 9 2 2004 Radeon X800R520 90 nm80 nm 9 0c11 FL 9 3 2005 Radeon X1800R600 TeraScale 1 80 nm65 nm 3 3 10 011 FL 10 0 ATI Stream 2007 Radeon HD 2900 XTRV670 55 nm 10 111 FL 10 1 ATI Stream APP 15 Radeon HD 3850 3870RV770 55 nm40 nm 1 0 2008 Radeon HD 4850 4870Evergreen TeraScale 2 40 nm 4 5 Linux 4 2 16 17 18 c 11 FL 11 0 1 2 2009 Radeon HD 5850 5870Northern Islands TeraScale 2TeraScale 3 2010 Radeon HD 6850 6870Radeon HD 6950 6970Southern Islands GCN 1st gen 28 nm 1 0 4 6 11 FL 11 1 12 FL11 1 1 22 0 possible 2012 Radeon HD 7950 7970Sea Islands GCN 2nd gen 1 2 11 FL 12 0 12 FL 12 0 2 0 1 2 in MacOS Linux 2 1 Beta in Linux ROCm2 2 possible 2013 Radeon HD 7790Volcanic Islands GCN 3rd gen 2014 Radeon R9 285Polaris GCN 4th gen 14 nm Current 2016 Radeon RX 480Vega GCN 5th gen 14 nm7 nm 1 21 3 possible 11 FL 12 1 12 FL 12 1 2017 Radeon Vega Frontier EditionNavi RDNA 7 nm 2019 Radeon RX 5700 XT Navi 2X RDNA 2 7 nm6 nm 11 FL 12 1 12 FL 12 2 2020 Radeon RX 6800 XT Navi 3X RDNA 3 6 nm5 nm 1 3 2022 Radeon RX 7900 XT X Radeon 7000 Series has programmable pixel shaders but do not fully comply with DirectX 8 or Pixel Shader 1 0 See article on R100 s pixel shaders These series do not fully comply with OpenGL 2 as the hardware does not support all types of non power of two NPOT textures OpenGL 4 compliance requires supporting FP64 shaders and these are emulated on some TeraScale chips using 32 bit hardware 19 20 21 Desktop GPUs EditWonder series Edit Main article ATI Wonder series Model Launch Fab nm Bus interface MemorySize KiB Bus type Bus width bit Wonder MDA CGA 1986 1000 PC XT 64 DRAM 8Wonder EGA 1987 PC XT 256Wonder VGA 1987 1000 800 PC XT ISA 256 5121024 8 16Mach series Edit Main article ATI Mach Model Launch Fab nm Bus interface MemorySize KiB Bus type Bus width bit Mach 8 1991 800 ISA MCA 512 1024 DRAM VRAM 32Mach 32 1992 ISA EISA VLB PCI MCA 1024 2048 DRAM VRAM 64Mach 64 CX 1994 700 ISA VLB PCI 1024 2048 4096 DRAM VRAMMach 64 GXMach 64 CT 1995 600 PCI DRAM VRAM EDOMach 64 VT 264VT Mach 64 VT2 264VT2 1996 EDOMach 64 VT4 264VT4 1998 2048 4096 EDO SGRAMRage series Edit Main article ATI Rage Model Launch GPU arch Fab nm Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate Memory API complianceMOperations s MPixels s MTexels s MVertices s Size MiB Bandwidth GB s Bus type Bus width bit Direct3D OpenGL3D Rage April 1996 22 Mach64 500 PCI 40 40 1 0 1 1 40 40 40 0 2 0 32 EDO 64 5 0 None23D Rage II September 1996 Mach64 Rage2 for Rage IIc AGP 1 Rage IIc only PCI 60 83 66 MHz with EDO 60 60 60 2 4 8 0 664 EDO SGRAM SDRRage Pro March 1997 Rage 3 350 AGP 1x AGP 2 PCI 75 75 75 75 75 4 8 16 0 6 6 0 1 1Rage XL 23 24 25 26 August 1998 250 AGP 2 PCI 83 125 83 83 83 8 1 0 SDRRage 128 VR Rage 4 80 120 2 0 2 2 160 160 160 8 32 0 96 1 2Rage 128 GL 103 103 206 206 206 16 32 1 648 SGRAM SDR 128Rage 128 Pro August 1999 AGP 4 PCI 125 143 250 250 250 2 288Rage 128 Ultra 130 130 260 260 260 16 32 64 2 088 SDRRage Fury MAXX October 1999 AGP 4 125 143 2 0 2 2 2 500 500 500 32 2 4 576 128 21 Pixel pipelines Vertex shaders Texture mapping units Render output units2 OpenGL 1 0 Generic 2D is provided through software implementations Radeon 7000 series Edit Main article Radeon R100 series All models include Direct3D 7 0 and OpenGL 1 3 The R100 cards were originally launched without any numbering as Radeon SDR DDR LE and VE these products were later rebranded to their names within the numbered naming scheme when the Radeon 8000 series was introduced Model Launch Code name Fab nm Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate MemoryMOperations s MPixels s MTexels s MVertices s Size MiB Bandwidth GB s Bus type Bus width bit Radeon VE Radeon 7000 February 19 2001 RV100 piglet 180 AGP 4x PCI 150 166 183 150 166 183 1 0 3 1 183 max 336 max 549 max 0 32 64 2 688 max DDR 64Radeon LE Radeon 7100 OEM April 6 2001 27 Rage 6 R100 AGP 4x 150 150 2 1 6 2 296 296 888 37 5 32 4 736 128Radeon SDR Radeon 7200 SDR June 1 2000 AGP 4x PCI 166 166 333 333 996 41 5 2 656 SDRRadeon DDR Radeon 7200 DDR April 1 2000 AGP 4x 166 183A 166 183A 333 366A 333 366A 966 1098A 41 5 45 75A 32 64 5 312 5 856A DDRRadeon DDR Radeon 7200 VIVO 2001 AGP 4x PCI 166 183B 166 183B 333 366B 333 366B 966 1098B 41 5 45 75B 64 5 312 5 856BRadeon DDR Radeon 7500 VIVO SE 200 200 400 400 1200 50 0 6 400Radeon 7500 LE RV200 morpheus 150 250 175 500 500 1500 62 5 32 64 5 600 64128Radeon 7500 August 14 2001 RV200 morpheus 290 230 580 580 1740 72 5 32 64 128 28 7 360 1281 Pixel pipelines Vertex shaders Texture mapping units Render output unitsA 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 Edit All models are manufactured with a 180 nm fabrication process All models include Direct3D 7 0 and OpenGL 1 3 Based on the Radeon VEModel Launch Code name Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate MemoryMOperations s MPixels s MTexels s MVertices s Size MiB Bandwidth GB s Bus type Bus width bit Radeon 320 May 2002 A3 FSB 160 200 266 1 0 3 1 160 160 480 0 1 6 2 128 DDR 64Radeon 330 2002 RS200L wilma 150 150 150 450Radeon 340 RS200 wilma 183 183 183 5491 Pixel pipelines Vertex shaders Texture mapping units Render output units Radeon 8000 and 9000 series Edit Main article Radeon R200 series All models are manufactured with a 150 nm fabrication process All models include Direct3D 8 1 and OpenGL 1 4Model Launch Code name Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate MemoryMOperations s MPixels s MTexels s MVertices s Size MiB Bandwidth GB s Bus type Bus width bit Radeon 8500 August 14 2001 R200 chaplin AGP 4 PCI 275 275 4 2 8 4 1100 1100 2200 137 5 64 128 8 8 DDR 128Radeon 8500 LE October 30 2001 250 250 1000 1000 2000 125 8Radeon 9000 August 1 2002 RV250 iris 200 4 1 4 4 1000 50 6 4Radeon 9000 Pro 275 275 1100 1100 1100 68 75 8 8Radeon 9100 April 1 2003 R200 chaplin 250 250 4 2 8 4 1000 1000 2000 125 8 0 4 0128 64Radeon 9200 RV280 argus AGP 8 PCI 200 4 1 4 4 1000 62 5 64 128 256 6 4 128Radeon 9200 SE March 1 2003 200 166 800 800 800 50 2 67 64Radeon 9250 March 1 2004 240 200 960 960 960 60 3 2 6 4 64 128Radeon 9250 SE 2004 AGP 8x 641 Pixel shaders Vertex shaders Texture mapping units Render output units IGP 9000 series Edit All models are manufactured with a 150 nm fabrication process All models include Direct3D 8 1 and OpenGL 1 4 Based on the Radeon 9200Model Launch Code name Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate MemoryMOperations s MPixels s MTexels s MVertices s Size MiB Bandwidth GB s Bus type Bus width bit Radeon 9000 2003 RC350 FSB 300 400 4 1 2 2 600 600 600 75 16 128 3 2 DDR 64Radeon 9100 RS300 superman 6 4 128Radeon 9100 Pro May 3 2004 RS3501 Pixel shaders Vertex shaders Texture mapping units Render output units Radeon R300 series Edit AGP 9000 series X1000 series Edit Main article Radeon R300 series All models include Direct3D 9 0 and OpenGL 2 0 All models use an AGP 8x interfaceModel Launch Code name Fab nm Core clock MHz Memory clock MHz Core config1 Fillrate MemoryMOperations s MPixels s MTexels s MVertices s Size MiB Bandwidth GB s Bus type Bus width bit Radeon 9500 October 24 2002 R300 Khan 150 275 270 4 4 4 4 1100 1100 1100 275 64 128 8 64 17 28 DDR 128 256Radeon 9500 Pro 8 4 8 8 2200 2200 2200 128 8 64 128Radeon 9550 2004 RV350 Shivah 130 250 200 4 2 4 4 1000 1000 1000 125 64 128 256 6 4Radeon 9550 SE 3 2 64Radeon 9600 2003 325 1300 1300 1300 162 5 128 256 6 4 128Radeon 9600 Pro March 6 2003 400 300 1600 1600 1600 200 9 6Radeon 9600 SE 2003 325 200 1300 1300 1300 162 5 64 128 256 3 2 64Radeon 9600 XT September 30 2003 RV360 500 300 2000 2000 2000 250 128 256 9 6 128Radeon 9600 TX 2003 Medion OEM R300 Khan 150 297 270 8 4 8 8 2376 2376 2376 287 128 8 6Radeon 9700 TX 2002 Dell OEM 263 263 2104 2104 2104 275 16 83 256Radeon 9700 October 24 2002 275 270 2200 2200 2200 17 28Radeon 9700 Pro July 18 2002 325 310 2600 2600 2600 325 19 84Radeon 9800 2003 R350Radeon 9800 XL 350 2800 2800 2800 350Radeon 9800 XXL 29 October 1 2003 R360 390 338 3120 3120 3120 390 21 60 256 29 Radeon 9800 Pro R350 March 1 2003 30 R350 380 340 128 MB 350 256 MB 3040 3040 3040 380 128 256 21 76 22 40 DDR GDDR2 256Radeon 9800 Pro R360 2003 R360 340 128 21 76 DDRRadeon 9800 SE 31 March 1 2003 32 R350 325 380 31 270 340 31 4 4 4 4 32 1300 1520 31 1300 1520 31 1300 1520 31 325 380 31 128 256 8 64 21 76 31 DDR 128 2562 31 Radeon 9800 XT September 9 2003 R360 412 365 8 4 8 8 3296 3296 3296 412 256 23 36 256Radeon X1050 AGP December 7 2006 RV350 Shivah 130 250 200 4 2 4 4 1000 1000 1000 125 128 256 6 4 128Model Launch Code name Fab nm Core clock MHz Memory clock MHz Core config1 MOperations s MPixels s MTexels s MVertices s Size MiB Bandwidth GB s Bus type Bus width bit Fillrate Memory1 Pixel shaders Vertex Shaders Texture mapping units Render output units2 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 33 PCI E X3xx X5xx X6xx X1000 series Edit Main article Radeon R300 series All models include Direct3D 9 0 and OpenGL 2 0 All models use a PCI E 16 interfaceModel Launch Code name Fab nm Core clock MHz Memory clock MHz Core config1 Fillrate MemoryMOperations s MPixels s MTexels s MVertices s Size MiB Bandwidth GB s Bus type Bus width bit Radeon X300 September 1 2004 RV370 hari 110 325 200 4 2 4 4 1300 1300 1300 162 5 64 128 6 4 DDR 128Radeon X300 LERadeon X300 SE 3 2 64Radeon X300 SE HyperMemory April 4 2005 300 32 64 128 onboard up to 128 systemRadeon X550 June 21 2005 400 250 1600 1600 1600 200 128 256 8 4 128 64Radeon X550 HyperMemory 128 256 onboard up to 512 systemRadeon X600 SE September 1 2004 325 1300 1300 1300 162 5 128 256 4 64Radeon X600 400 1600 1600 1600 200 8 128Radeon X600 Pro RV370 300 9 6Radeon X600 Pro RV380 RV380 vishnu 130Radeon X600 XT 500 370 2000 2000 2000 250 11 84Radeon X1050 RV370 December 7 2006 RV370 hari 110 400 250 333 1600 1600 1600 200 5 328 DDRDDR2 641281 Pixel shaders Vertex Shaders Texture mapping units Render output units IGP X2xx 11xx series Edit Main article Radeon R300 series All models include Direct3D 9 0 and OpenGL 2 0 Based on the Radeon X300Model Launch Code name Fab nm Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate MemoryMOperations s MPixels s MTexels s MVertices s Size MiB Bandwidth GB s Bus type Bus width bit Radeon Xpress X200 November 8 2004 RS480 metallo 130 HT 300 200 400 DDR 200 sideport 4 2 2 2 600 600 600 0 16 128 system 16 sideport 1 6 6 4 system 0 8 sideport DDR 64 128Radeon Xpress 1100 originally Xpress 200 2005 RS482 grayskull 110 HT 300 200 400 DDR 400 800 DDR2 16 128 system 1 6 12 8 system DDR DDR2Radeon Xpress 1150 originally Xpress 200 for Intel March 11 2005 Intel May 23 2006 AMD RC400 RC410 RS400 RS415 RS485 HT FSB 400 800 800 800 1 6 12 81Pixel shaders Vertex Shaders Texture mapping units Render output units Radeon X700 and X800 series Edit AGP X7xx X8xx Edit Main article Radeon R400 series All models include AGP 8 All models include Direct3D 9 0b and OpenGL 2 0Model Launch Code name Fab nm Core clock MHz Memory clock MHz Core config1 Fillrate MemoryMOperations s MPixels s MTexels s MVertices s Size MB Bandwidth GB s Bus type Bus width bit Radeon X700 Mar 2005 RV410 alto 110 400 350 8 6 8 8 3200 3200 3200 600 128 256 11 2 DDR 128Radeon X700 Pro Mar 1 2005 425 432 3400 3400 3400 637 5 13 824 GDDR3Radeon X800 SE Oct 2004 R420 loki 130 400 6800 256 25 6 256Radeon X800 GT December 6 2005 475 490 8 6 8 16 3800 7600 3800 712 5 31 36Radeon X800 Dec 2004 R430 110 400 350 12 6 12 16 4800 6400 4800 600 22 4Radeon X800 GTO December 6 2005 R420 loki 130 490 31 36Radeon X800 Pro May 5 2004 475 450 5700 7600 5700 712 5 28 8Radeon X800 XL February 2 2005 R430 110 400 490 16 6 16 16 6400 6400 6400 600 31 36Radeon X800 XT May 4 2004 R420 loki 130 500 500 8000 8000 8000 750 32Radeon X800 XT PE 520 560 8320 8320 8320 780 35 84Radeon X850 Pro February 28 2005 R481 507 520 12 6 12 16 6084 8112 6084 760 5 33 28Radeon X850 XT 520 540 16 6 16 16 8320 8320 8320 780 34 56Radeon X850 XT PE 540 590 8640 8640 8640 810 37 761 Pixel shaders Vertex shaders Texture mapping units Render output units PCI E X5xx X7xx X8xx X1000 series Edit Main article Radeon R400 series All models include PCI E 16 All models include Direct3D 9 0b and OpenGL 2 0Model Launch Code name Fab nm Core clock MHz Memory clock MHz Core config1 Fillrate MemoryMOperations s MPixels s MTexels s MVertices s Size MB Bandwidth GB s Bus type Bus width bit Radeon X550 XT January 24 2007 RV410 alto 110 400 300 4 6 4 8 1600 3200 1600 600 128 4 8 9 6 DDR GDDR3 64 128Radeon X550 XTX 8 6 8 8 3200 3200Radeon X700 SE April 1 2005 200250 4 6 4 8 1600 1600 128 3 2 DDR 64Radeon X700 LE December 21 2004 250 8 6 8 8 3200 3200 128 4Radeon X1050 RV410 Jan 25 2008 200 128 256 6 4 128Radeon X700 Sept 2005 250350 811 2Radeon X700 Pro December 21 2004 425 432 3400 3400 3400 637 5 128 256 13 824 GDDR3Radeon X700 XT Never Released 475 525 3800 3800 3800 712 5 128 256 16 8Radeon X740 XL March 7 2005 Medion OEM 425 450 3400 3400 3400 637 5 128 14 4Radeon X800 GT 128MB August 1 2005 R423R480 thor 130 475 175 8 6 8 16 3800 7600 3800 712 5 128 22 4 DDR 256Radeon X800 GT 256MB 490 256 31 36 GDDR3Radeon X800 December 1 2004 R430 thor 110 392 350 12 6 12 16 4704 6272 4704 588 128 256 22 4Radeon X800 GTO 128MB September 15 2005 R423R480R430 thor 130110 400 4800 6400 4800 600 128 22 4Radeon X800 GTO 256MB 490 256 31 36Radeon X800 Pro May 5 2004 R423 thor 130 475 450 5700 7600 5700 712 5 28 8Radeon X800 XL December 1 2004 256 MB May 4 2005 512 MB R430 thor 110 400 490 16 6 16 16 6400 6400 6400 600 256 512 31 36Radeon X800 XT December 1 2004 R423 thor 130 500 500 8000 8000 8000 750 256 32Radeon X800 XT Platinum Edition May 5 2004 520 560 8320 8320 8320 780 35 84Radeon X850 Pro December 1 2004 R480 thor 507 520 12 6 12 16 6084 8112 6084 760 5 33 28Radeon X850 XT 520 540 16 6 16 16 8320 8320 8320 780 34 56Radeon X850 XT CrossFire Master September 29 2004 520 34 56Radeon X850 XT Platinum Edition December 21 2004 540 590 8640 8640 8640 810 37 76Model Launch Code name Fab nm Core clock MHz Memory clock MHz Core config1 MOperations s MPixels s MTexels s MVertices s Size MB Bandwidth GB s Bus type Bus width bit Fillrate Memory1 Pixel shaders Vertex Shaders Texture mapping units Render output units IGP X12xx 21xx Edit Main article Radeon R400 series All models include Direct3D 9 0b and OpenGL 2 0 Based on Radeon X700Model Launch Code name Fab nm Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate MemoryMOperations s MPixels s MTexels s MVertices s Size MB Bandwidth GB s Bus type Bus width bit Radeon Xpress X1200 February 28 2007 RS690C zeus 80 HT 2 0 350 400 800 4 2 4 4 1400 1400 1400 175 256 512 6 4 12 8 DDR2 128Radeon Xpress X1250 August 29 2006 Intel February 28 2007 AMD RS600 RS690 zeus FSB HT 2 0 400 1600 1600 1600 200Radeon Xpress 2100 March 4 2008 RS740 titan 55 HT 2 0 500 2000 2000 2000 250Radeon X1000 series Edit Main article Radeon X1000 series Note that ATI X1000 series cards e g X1900 do not have Vertex Texture Fetch hence they do not fully comply with the VS 3 0 model Instead they offer a feature called Render to Vertex Buffer R2VB that provides functionality that is an alternative Vertex Texture Fetch Model Launch Code name Fab nm Transistors million Die size mm2 Bus interface Clock rate Core config Fillrate Memory TDP Watts API support version Release Price USD Core MHz Memory MHz MOperations s MPixels s MVertices s MTexels s Size MB Bandwidth GB s Bus type Bus width bit Max Direct3D OpenGLRadeon X1300 October 5 2005 PCI E December 1 2005 AGP RV515 90 107 100 AGP 8 PCIPCI E 16 450 250 4 2 4 4 1800 1800 225 1800 128256 8 0 DDR DDR2 128 9 0c 2 1 99 128MB 129 256MB Radeon X1300HyperMemory October 5 2005 PCI E 16 128256512 4 0 DDR2 64 Radeon X1300 PRO October 5 2005 PCI E November 1 2006 AGP AGP 8 PCI E 16 600 400 2400 2400 300 2400 128256 12 8 128 31 149Radeon X1300 XT August 12 2006 RV530 157 150 500 12 5 4 4 6000 2000 625 2000 22 89Radeon X1550 January 8 2007 RV516 107 100 AGP 8xPCIPCI E x16 4 2 4 4 2200 2200 275 2200 128256512 27 Radeon X1600 PRO October 10 2005 RV530 157 150 AGP 8 PCI E 16 390 390 690 12 5 4 4 6000 2000 625 2000 12 48 DDR2 GDDR3 41 149 128MB 199 256MB Radeon X1600 XT October 10 2005 PCI E 590 690 7080 2360 737 5 2360 256512 22 08 GDDR3 42 249Radeon X1650 February 1 2007 500 400 6000 2000 625 2000 12 8 DDR2 Radeon X1650 SE RV516 105 PCI E 16 635 4 2 4 4 256 DDR2 Radeon X1650 GT May 1 2007 PCI E October 1 2007 AGP RV560 80 330 230 AGP 8 PCI E x16 400 24 8 8 8 9600 3200 800 3200 256512 GDDR3 Radeon X1650 PRO August 23 2006 PCI E October 15 2006 AGP RV535 131 600 700 12 5 4 4 7200 2400 750 2400 22 4 44 99Radeon X1650 XT October 30 2006 RV560 230 525 24 8 8 8 12600 4200 1050 4200 55 149Radeon X1700 FSC November 5 2007 OEM RV535 131 PCI E 16 587 695 12 5 4 4 7044 2348 733 2348 256 22 2 44 OEMRadeon X1700 SE November 30 2007 RV560 230 500 500 24 8 8 8 12000 4000 1000 4000 512 16 0 50 Radeon X1800CrossFire Edition December 20 2005 R520 90 321 288 600 700 16 8 16 16 9600 9600 900 9600 512 46 08 256 113 Radeon X1800 GTO March 9 2006 500 495 12 8 12 8 6000 6000 1000 6000 256512 32 0 48 249Radeon X1800 XL October 5 2005 500 16 8 16 16 8000 8000 1000 8000 256 70 449Radeon X1800 XT 625 750 10000 10000 1250 10000 256512 48 0 113 499 256MB 549 512MB Radeon X1900CrossFire Edition January 24 2006 R580 384 352 625 725 48 8 16 16 30000 512 46 4 100 599Radeon X1900 GT May 5 2006 575 600 36 8 12 12 20700 6900 1150 6900 256 38 4 75 Radeon X1900 GT Rev 2 September 7 2006 512 18432 6144 1024 6144 42 64Radeon X1900 XT January 24 2006 625 725 48 8 16 16 30000 10000 1250 10000 256512 46 4 100 549Radeon X1900 XTX R580 650 775 31200 10400 1300 10400 512 49 6 135 649Radeon X1950CrossFire Edition August 23 2006 R580 80 1000 31200 10400 1300 10400 64 GDDR4 449Radeon X1950 GT January 29 2007 PCI E February 10 2007 AGP RV570 330 230 AGP 8xPCI E x16 500 600 36 8 12 12 18000 6000 1000 6000 256512 38 4 GDDR3 57 140Radeon X1950 PRO October 17 2006 PCI E October 25 2006 AGP 575 690 20700 6900 1150 6900 44 16 66 199Radeon X1950 XT October 17 2006 PCI E February 18 2007 AGP R580 384 352 AGP 8xPCI E 1 0 x16 625 700 AGP 900 PCI E 48 8 16 16 30000 10000 1250 10000 44 8 AGP 57 6 PCI E 96 Radeon X1950 XTX October 17 2006 PCI E 1 0 16 650 1000 31200 10400 1300 10400 512 64 GDDR4 125 449Model Launch Code name Fab nm Transistors million Die size mm2 Bus interface Core MHz Memory MHz Core config MOperations s MPixels s MVertices s MTexels s Size MB Bandwidth GB s Bus type Bus width bit Max Direct3D OpenGL Release price USD Clock rate Fillrate Memory TDP Watts API support version 1 Pixel shaders Vertex shaders Texture mapping units Render output units Radeon HD 2000 series Edit Main articles Radeon HD 2000 series and TeraScale 1 Model Launch Code name Fab nm Transistors million Die size mm2 Bus interface Clock rate Core config Fillrate Memory Processing power GFLOPS TDP Watts Crossfire support API support version Release price USD Core MHz Memory MHz Pixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width Bit Single precision Double precision Max Direct3D OpenGL OpenCLRadeon HD 2350 June 28 2007 RV610 65 180 85 PCIe 1 0 16 525 400 40 4 4 2 10 2 10 64 onboard up to 256 system 3 20 DDR2 32 42 0 20 No 10 0 3 3 APP Stream Only Radeon HD 2400 PRO PCIe 1 0 16AGPPCI 128256512 6 40 64 50 55Radeon HD 2400 XT PCIe 1 0 16 650 500700 2 60 2 60 256 8 011 2 DDR2GDDR3 52 0 25 75 85Radeon HD 2600 PRO RV630 390 153 PCIe 1 0 16AGP 600 120 8 4 2 40 4 80 256512 16 022 4 128 144 0 35 89 99Radeon HD 2600 XT 800 8001100 3 20 6 40 25 635 2 GDDR3GDDR4 192 0 4550 4 way CrossFire 119 GDDR3 149 GDDR4 Radeon HD 2900 GT November 6 2007 R600 GT 80 720 420 PCIe 1 0 16 601 800 240 12 12 7 21 7 21 51 2 GDDR3 256 288 5 150 200Radeon HD 2900 PRO September 25 2007 R600 PRO 600 800925 320 16 16 9 6 9 6 5121024 51 2102 4118 4 GDDR3GDDR4 256512 384 0 200 250 GDDR3 300 GDDR4 Radeon HD 2900 XT May 14 2007 R600 XT 743 8281000 11 9 11 9 105 6128 0 GDDR3GDDR4 512 475 5 215 399Radeon HD 3000 series Edit Main article Radeon HD 3000 series Model Launch Code name Fab nm Transistors million Die size mm2 Bus interface Clock rate Core config Fillrate Memory Processing power GFLOPS TDP Watts Crossfire Support API support version Release price USD Core MHz Memory MHz Pixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width Bit Single precision Double precision Max Direct3D OpenGL OpenCL ATI StreamRadeon HD 3410 May 7 2009 RV610 65 180 85 PCIe 1 0 16 519 396 40 4 4 2 08 2 08 256 6 34 DDR2 64 41 52 20 No 10 0 3 3 No Yes Radeon HD 3450 January 23 2008 RV620 LE 55 181 67 PCIe 2 0 16PCIAGP 8 600 500 2 40 2 40 256512 8 00 48 0 25 10 1Radeon HD 3470 RV620 PRO PCIe 2 0 16 800 950 3 20 3 20 15 2 DDR2GDDR3 64 0 30Radeon HD 3550 August 4 2008 594 396 2 38 2 38 512 6 34 DDR2 47 52Radeon HD 3570 July 5 2010 796 495 3 18 3 18 7 92 63 68Radeon HD 3610 September 24 2009 RV630 PRO 65 390 153 PCIe 1 0 16 594 396 120 8 4 2 38 4 75 5121024 12 7 128 142 6 35Radeon HD 3650 January 23 2008 RV635 PRO 55 378 PCIe 2 0 16AGP 8 725 405800 2 90 5 80 2565121024 13 025 6 DDR2GDDR3GDDR4 174 0 65 2 way CrossFireRadeon HD 3730 October 5 2008 135 PCIe 2 0 16 722 405 2 89 5 78 5121024 13 0 DDR2 173 3 NoRadeon HD 3750 796 693 3 18 6 37 512 22 2 GDDR3 191 0 2 way CrossFireRadeon HD 3830 April 1 2008 RV670 PRO 666 192 668 828 320 16 16 10 7 10 7 256 26 5 427 5 85 4 75 129Radeon HD 3850 November 19 2007 PCIe 2 0 x16AGP 8x 830900 2565121024 53 157 6 GDDR3GDDR4 256 85 4 4 way CrossFire 179Radeon HD 3870 RV670 XT 777 9001126 12 4 12 4 5121024 57 672 1 497 3 99 2 106 219Radeon HD 3850 X2 April 4 2008 RV670 PRO 666 2 192 2 PCIe 2 0 16 668 828 320 16 16 2 10 7 2 10 7 2 512 2 53 0 2 GDDR3 256 2 428 2 2 85 6 2 140 2 way CrossFire 349Radeon HD 3870 X2 January 28 2008 R680 825 9011125 13 2 2 13 2 2 57 6 272 1 2 GDDR3GDDR4 528 0 2 105 6 2 165 449IGP HD 3000 Edit Main article AMD 700 chipset series All Radeon HD 3000 IGP models include Direct3D 10 0 and OpenGL 3 3Model Launch Code name Graphics core Fab nm Transistors million Die size mm2 Bus interface Core clock2 MHz Core config1 Fillrate Memory3 Processing power GFLOPS Features NotesPixel GP s Texture GT s FP32 GP s Size MB Bandwidth GB s Bus type Effective clock MHz Bus width Bit Radeon 3000 Graphics 760G Chipset 2009 RS780L 34 RV610 55 205 73 9 8 05 HT 3 0 350 40 4 4 1 4 1 4 0 7 Up to 512 system 20 8 system HT system 28 AVIVORadeon 3100 Graphics 780V Chipset 2008Jan 23 China Mar 4 worldwide RS780CRadeon HD 3200 Graphics 780G Chipset RS780 500 2 2 1 Up to 512 system optional 128 sideport 20 8 system 2 6 sideport HT system DDR2 1066 DDR3 1333 sideport 1333 sideport 16 sideport 40 UVD 8 AA wide tent CFAA Radeon HD 3300 Graphics 790GX Chipset Jul 2008 RS780D 700 2 8 2 8 1 4 Up to 512 system 128 sideport HT system DDR3 1333 sideport 56 UVD PowerPlay1 Unified shaders Texture mapping units Render output units 2 The clock frequencies may vary in different usage scenarios as AMD PowerPlay technology is implemented The clock frequencies listed here refer to the officially announced clock specifications 3 The sideport is a dedicated memory bus It is preferably used for a frame buffer All in Wonder series Edit Main article All in Wonder Model Launch Code name Fab nm Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate Memory API version MPixels s MTexels s MVertices s Size MB Bandwidth GB s Bus type Bus width bit Direct3D OpenGLAll in Wonder VE December 2 2002 RV100 180 PCI 183 183 1 0 3 1 183 549 0 64 2 9 DDR 64 7 0 1 3All in Wonder Radeon July 31 2000 R100 AGP 4 166 166 2 1 6 2 332 996 41 5 32 5 312 128All in Wonder 7500 January 22 2002 RV200 150 260 180 520 1560 65 64 5 760All in Wonder 8500 April 4 2002 R200 260 275 4 2 8 4 1100 2200 137 5 128 8 8 8 1 1 4All in Wonder 8500 DV August 30 2001 230 190 920 1840 115 64 6 08All in Wonder 9000 Pro March 31 2003 RV250 AGP 8x 275 225 4 1 4 4 1110 1110 68 75 64 128 7 2All in Wonder 9200 January 26 2004 250 200 1000 1000 62 5 128 6 4All in Wonder 9200 SE N A 166 2 656 64All in Wonder 9600 January 26 2004 RV350 130 325 400 4 2 4 4 1300 1300 162 5 6 4 128 9 0 2 0All in Wonder 9600 Pro August 5 2003 400 650 1600 1600 200 10 4All in Wonder 9600 XT January 26 2004 525 2100 2100 262 5All in Wonder 9700 Pro December 30 2002 R300 150 325 620 8 4 8 8 2600 2600 325 19 84 256All in Wonder 9800 Pro April 7 2003 R350 380 680 3040 3040 380 21 76All in Wonder 9800 SE November 1 2003 4 4 4 8 1520 10 88 128All in Wonder X600 Pro September 21 2004 RV370 110 400 600 4 2 4 4 1600 1600 200 AGP 128 PCI E 256 9 6All in Wonder X800 GT August 8 2005 R430 PCI E 16 490 980 8 6 8 16 6400 3200 600 128 31 36 GDDR3 256 9 0bAll in Wonder X800 XL July 5 2005 PCI E 16 AGP 8 400 16 6 16 16 6400 256All in Wonder X800 XT September 9 2004 R420 130 AGP 8 500 1000 8000 8000 750 32All in Wonder 2006 December 22 2005 RV515 90 PCI E 16 450 800 4 2 4 4 1800 1800 225 12 8 DDR2 128 9 0cAll in Wonder X1800 XL November 21 2005 R520 500 1000 16 8 16 16 8000 8000 1000 32 GDDR3 256All in Wonder X1900 January 24 2006 R580 960 48 8 16 16 30 72All in Wonder HD 3650 June 28 2008 RV635 55 725 1200 120 8 4 2900 5800 N A 512 19 2 DDR2 128 10 1 3 31 Pixel shaders Vertex shaders Texture mapping units Render output units 2 Unified shaders Texture mapping units Render output units Radeon HD 4000 series Edit Main articles Radeon HD 4000 series and TeraScale 1 Model4 Launch Code name Fab nm Transistors million Die size mm2 Bus interface Clock rate Core config1 Fillrate Memory2 Processing power GFLOPS TDP3 Watts Crossfire support API support version Release price USD Core MHz Memory MHz Pixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width bit Single precision Double precision Idle Max Direct3D OpenGL OpenCLRadeon HD 4350 September 30 2008 RV710 55 242 73 PCIe 2 0 16PCIe 2 0 1AGP 8 600 400650 80 8 4 2 40 4 80 2565121024 6 4010 4 DDR2DDR3 64 92 0 No 20 No 10 1 3 3 1 0 Radeon HD 4550 September 30 2008 PCIe 2 0 16 600 655800 10 512 8 96 0 No 25Radeon HD 4570 November 25 2008 242 650 500 2 60 5 20 1024 8 00 DDR2 104 0 NoRadeon HD 4580 November 20 2011 RV635 PRO 378 135 796 693 120 8 4 3 18 6 37 512 22 2 GDDR3 128 191 0 No 65Radeon HD 4650 September 10 2008 RV730 PRO 514 146 PCIe 2 0 16AGP 8 600650 400 500500700 320 32 8 4 805 20 19 220 8 2565121024 12 8 16 016 022 4 DDR2GDDR3GDDR4 64128 384 0416 0 No 48 2 way CrossfireRadeon HD 4670 September 10 2008 RV730 XT PCIe 2 0 16AGP 8 750 400 5009001000 320 32 8 6 00 24 0 5121024 12 8 16 028 832 0 DDR2GDDR3GDDR4 128 480 0 No 59 79Radeon HD 4730 June 8 2009 RV770 CE 956 256 PCIe 2 0 16 700750 900 640 32 8 5 606 00 22 424 0 512 57 6 GDDR5 896 0960 0 179 2192 0 110 Radeon HD 4750 September 9 2009 RV740 40 826 137 730 800 640 32 16 11 7 23 4 51 2 934 4 80Radeon HD 4770 April 28 2009 750 800 12 0 24 0 51 2 960 0 192 0 109Radeon HD 4810 May 28 2009 RV770 CE 55 956 256 625750 900 640 32 8 5 006 00 20 024 0 57 6 800 0960 0 160 0192 0 95 Radeon HD 4830 October 21 2008 RV770 LE 575 900 640 32 16 9 20 18 4 5121024 57 6 GDDR3GDDR4 256 736 0 147 2 130Radeon HD 4850 June 25 2008 RV770 PRO 625 993 800 40 16 10 0 25 0 51210242048 63 55 GDDR3GDDR4GDDR5 1000 200 0 110 4 way Crossfire 199Radeon HD 4860 September 9 2009 RV790 GT 959 282 700 750 640 32 16 11 2 22 4 5121024 96 GDDR5 896 0 179 2 130 Radeon HD 4870 June 25 2008 RV770 XT 956 256 750 900 800 40 16 12 0 30 0 51210242048 115 2 1200 240 0 150 299Radeon HD 4890 April 2 2009 RV790 XT 959 282 850 975 13 6 34 0 10242048 124 8 GDDR5 1360 272 0 190 249Radeon HD 4850 X2 November 7 2008 R700 2xRV770 PRO 956 2 256 2 625 995 800 40 16 2 10 0 2 25 0 2 512 21024 2 63 7 2 GDDR3 256 2 2000 400 0 250 2 way Crossfire 339Radeon HD 4870 X2 August 12 2008 R700 2xRV770 XT 750 900 12 2 30 2 1024 2 115 2 2 GDDR5 2400 480 0 286 449Model4 Launch Code name Fab nm Transistors million Die size mm2 Bus interface Clock rate Core config1 Fillrate Memory2 Processing power GFLOPS TDP3 Watts Crossfire support API support version Release price USD Core MHz Memory MHz Pixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width bit Single precision Double precision Idle Max Direct3D OpenGL OpenCL1 Unified shaders Texture mapping units Render output units 2 The effective data transfer rate of GDDR5 is quadruple its nominal clock instead of double as it is with other DDR memory 3 The TDP is reference design TDP values from AMD Different non reference board designs from vendors may lead to slight variations in actual TDP 4 All models feature UVD2 and PowerPlay IGP HD 4000 Edit Main articles AMD 700 chipset series and TeraScale 1 All Radeon HD 4000 IGP models include Direct3D 10 1 and OpenGL 2 0 35 Model Launch Code name Graphics core Fab nm Transistors million Die size mm2 Bus interface Core Fillrate Memory3 Processing power GFLOPS Features NotesConfig1 Clock2 MHz Pixel GP s Texture GT s FP32 GP s Size MB Bandwidth GB s Bus type Effective clock MHz Bus width Bit Radeon HD 4200 Graphics 785G Chipset Aug 2009 RS880 RV620 55 gt 205 73 9 8 05 HT 3 0 40 4 4 500 2 2 1 Up to 512 system optional 128 sideport 20 8 system 2 6 sideport HT system DDR2 1066 DDR3 1333 sideport 1333 sideport 16 sideport 40 UVD2Radeon HD 4250 Graphics 880G Chipset Mar 2010 RS880 560 2 24 2 24 1 12 HT system DDR3 1333 sideport 44 8Radeon HD 4290 Graphics 890GX Chipset RS880D 700 2 8 2 8 1 4 Up to 512 system 128 sideport 561 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 Radeon HD 5000 series Edit Main articles Radeon HD 5000 series and TeraScale 2 The HD5000 series is the last series of AMD GPUs which supports two analog CRT monitors with a single graphics card i e with two RAM DACs AMD Eyefinity introduced Model Launch Codename Fab nm Transistors million Die size mm2 Businterface Clock rate Coreconfig a Fillrate Memory Processing power GFLOPS TDP Watts b CrossFiresupport API support version Release price USD Core MHz Memory MHz Pixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width Bit Single precision Double precision Idle Max Direct3D OpenGL OpenCLRadeon HD 5450 Feb 4 2010 Cedar 40 292 59 PCIe 2 1 x16PCIPCIe 2 1 x1 650650650 400800800 80 8 4 2 6 5 2 51210242048 6 412 8 DDR2DDR3 64 104 6 4 19 1 No 11 3 11 0 4 5 1 2 50Radeon HD 5550 Feb 9 2010 Redwood LE 627 104 PCIe 2 1 x16 550550550 320 16 8 4 4 8 8 12 825 651 2 DDR2GDDR3GDDR5 128 352 10 39 70Radeon HD 5570 Redwood PRO 650650 400900 400 20 8 5 2 13 0 12 828 857 6 520 80Radeon HD 5610 May 14 2011 650 500 1024 16 0 GDDR3 Radeon HD 5670 Jan 14 2010 Redwood XT 775775 8001000 6 2 15 5 51210242048 25 664 0 GDDR3GDDR5 620 15 64 4 way CrossFire 99Radeon HD 5750 Oct 13 2009 Juniper PRO 1040 170 700700 11501150 720 36 16 11 2 25 2 5121024 73 6 GDDR5 1008 16 86 129Radeon HD 5770 Juniper XT 850850 12001200 800 40 16 13 6 34 0 76 8 1360 18 108 159Radeon HD 5830 Feb 25 2010 Cypress LE 2154 334 800 1000 1120 56 16 12 8 44 8 1024 128 0 256 1792 358 4 25 175 239Radeon HD 5850 Sep 30 2009 Cypress PRO 725725 10001000 1440 72 32 23 2 52 2 10242048 2088 417 6 27 151 259Radeon HD 5870 Sep 23 2009 Cypress XT 850850 12001200 1600 80 32 27 2 68 0 153 6 2720 544 188228 379Radeon HD 5870Eyefinity Edition c 36 Mar 11 2010 850 1200 2048 228 479Radeon HD 5970 Nov 18 2009 Hemlock 2154 2 334 2 725725 10001000 1600 80 32 2 46 4 116 0 1024 22048 2 128 2 256 2 4640 928 51 294 2 way CrossFire 599viewtalkedit Unified shaders Texture mapping units Render output units The TDP is reference design TDP values from AMD Different non reference board designs from vendors may lead to slight variations in actual TDP All chips feature AMD Eyefinity but the Radeon HD 5870 Eyefinity Edition card also have six mini DisplayPort outputs all of which can be simultaneously active Radeon HD 6000 series Edit Main articles Radeon HD 6000 series and TeraScale 3 VLIW4 The Radeon HD 6000 series has a new tesselation engine which is said to double the performance when working with tesselation compared to the previous HD 5000 series Model Codename Release Date amp Price Architecture amp Fab Transistors amp Die Size Core Fillrate a b Processing power c GFLOPS Memory d TDP Watts Bus interfaceConfig e Clock MHz Texture GT s Pixel GP s Single Double Size MB Bus type amp width Clock MHz Bandwidth GB s Idle MaxRadeon HD 6350 Cedar April 7 2011 23 USD TeraScale 240 nm 292 106 59 mm2 80 8 4 650 5 2 2 6 104 512 DDR364 bit 800 12 8 6 4 19 1 PCIe 2 1 16Radeon HD 6450 Caicos February 7 2011 OEM 370 106 67 mm2 160 8 4 625750 5 06 0 2 53 0 200240 512 DDR364 bit 533800 8 512 8 9 1827Radeon HD 6450 Caicos April 7 2011 55 USD 160 8 4 625750 5 06 0 2 53 0 200240 51210242048 DDR364 bit 800900 12 814 4 9 1827Radeon HD 6570 Turks Pro February 7 2011 OEM 716 106 118 mm2 480 24 8 650 15 6 5 2 624 1024 DDR3128 bit 900 28 8 10 44Radeon HD 6570 Turks Pro April 19 2011 79 USD 480 24 8 650 15 6 5 2 624 20484096 DDR3GDDR5128 bit 6671000 21 364 11 60Radeon HD 6670 Turks XT April 19 2011 99 USD 480 24 8 800 19 2 6 4 768 51210242048 8001000 25 664 12 66Radeon HD 6750 Juniper Pro January 21 2011 OEM 1040 106 166 mm2 720 36 16 700 25 2 11 2 1008 5121024 GDDR5128 bit 1150 73 6 16 86Radeon HD 6770 Juniper XT April 19 2011 800 40 16 850 34 0 13 6 1360 5121024 12001050 76 867 2 18 108Radeon HD 6790 Barts LE April 4 2011 149 USD 1700 106 255 mm2 800 40 16 840 33 6 13 4 1344 1024 GDDR5256 bit 1050 134 4 19 150Radeon HD 6850 Barts Pro October 22 2010 179 USD 960 48 32 775 37 2 24 8 1488 1024 1000 128 19 127Radeon HD 6870 Barts XT October 22 2010 239 USD 1120 56 32 900 50 4 28 8 2016 10242048 1050 134 4 19 151Radeon HD 6930 Cayman CE December 2011 180 USD TeraScale 340 nm 2640 106 389 mm2 1280 80 32 750 60 0 24 0 1920 480 10242048 GDDR5256 bit 1200 153 6 18 186Radeon HD 6950 Cayman Pro December 15 2010 259 USD 299 USD 1408 88 32 800 70 4 25 6 2253 563 10242048 12501250 160 20 200Radeon HD 6970 Cayman XT December 15 2010 369 USD 1536 96 32 880 84 5 28 2 2703 675 2048 1375 176 20 250Radeon HD 6990 Antilles XT March 8 2011 699 USD 2 2640 106 389 mm2 2 1536 96 32 830 2 79 6 2 26 5 5099 1276 88 2 2048 GDDR5256 bit 1250 2 160 37 375viewtalkedit Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed Precision performance is calculated from the base or boost core clock speed based on a FMA operation The effective data transfer rate of GDDR5 is quadruple its nominal clock instead of double as it is with DDR memory Unified Shaders Texture Mapping Units Render Output Units IGP HD 6000 Edit All models feature the UNB MC Bus interface All models do not feature double precision FP With driver Update OpenGL 4 4 available Last Catalyst 15 12 OpenGL 4 5 available with Crimson Beta driver version 15 30 or higher All models feature Angle independent anisotropic filtering UVD3 and AMD Eyefinity capabilities with up to three outputs All models feature 3D Blu ray Disc acceleration Embedded GPU s as part of AMD s Lynx platform APU s Model Launch Codename Architecture Fab nm Core Clock rate MHz Config core a Fillrate Shared Memory Processing power GFLOPS API compliance version Combined TDP b APU SeriesPixel GP s Texture GT s Bus width bit Bus type Bandwidth GB s Direct3D OpenGL OpenCL Vulkan Idle W Max W Radeon HD 6370D November 1 2011 WinterPark TeraScale 2 32 443 160 8 4 1 77 3 54 128 DDR3 1600 25 6 142 11 3 11 0 4 5 1 2 Un known 65 E2Radeon HD 6410D June 20 2011 443 c 600 1 77 2 4 3 54 4 8 142 192 A4Radeon HD 6530D BeaverCreek 443 320 16 8 3 54 7 08 DDR3 1866 29 9 284 65 100 A6Radeon HD 6550D 600 400 20 8 4 8 12 480 A8viewtalkedit Unified Shaders Texture Mapping Units Render Output Units TDP specified for AMD reference designs includes CPU power consumption Actual TDP of retail products may vary A4 3300 series runs the Radeon HD 6410D at a speed of 443 MHz Remaining A4 series run at 600 MHz Radeon HD 7000 series Edit Main articles Radeon HD 7000 series TeraScale 2 VLIW5 and Graphics Core Next Model Codename Launch ArchitectureFab TransistorsDie Size Core Fillrate a b c Processing power a d GFLOPS Memory e TDP Watts Bus interface Release Price USD Config f Clock a MHz Texture GT s Pixel GP s Single Double Size MiB Bus type amp width Clock MHz Bandwidth GB s Idle Max Radeon HD 7350 Cedar January 2012 TeraScale 2 g 40 nm 292 106 59 mm2 80 8 4 400650 3 25 2 1 62 6 104 256512 DDR2DDR364 bit 400800900 6 412 814 4 6 4 19 1 PCIe 2 1 16 OEMRadeon HD 7450 Caicos January 2012 370 106 67 mm2 160 8 4 625750 5 06 0 2 53 0 200240 5121024 DDR364 bit 533800 8 512 8 9 18 PCIe 2 1 16 OEMRadeon HD 7470 Caicos January 2012 160 8 4 625775 5 06 2 2 53 1 200248 5121024 DDR3GDDR564 bit 800900 12 828 8 9 27 PCIe 2 1 16 OEMRadeon HD 7510 Turks LE February 2013 716 106 118 mm2 320 16 4 650 10 4 2 6 416 1024 DDR3128 bit 667 21 3 Un known Un known PCIe 2 1 16 OEMRadeon HD 7570 Turks Pro L January 2012 480 24 8 650 15 6 5 2 624 5121024 DDR3GDDR5128 bit 9001000 28 864 1011 4460 PCIe 2 1 16 OEMRadeon HD 7670 Turks XT January 2012 480 24 8 800 19 2 6 4 768 5121024 GDDR5128 bit 1000 64 12 66 PCIe 2 1 16 OEMRadeon HD 7730 Cape Verde LE April 2013 GCN 1st gen28 nm 1500 106 123 mm2 384 24 8 800 19 2 6 4 614 4 38 4 1024 DDR3GDDR5128 bit 1125 25 672 10 47 PCIe 3 0 16 60Radeon HD 7750 Cape Verde Pro February 2012 512 32 16 800900 25 628 8 12 814 4 819 2921 6 51 257 6 102420484096 DDR3GDDR5128 bit 8001125 25 672 10 55 PCIe 3 0 16 110Radeon HD 7770GHz Edition Cape Verde XT February 2012 640 40 16 1000 40 16 1280 80 10242048 GDDR5128 bit 1125 72 10 80 PCIe 3 0 16 160Radeon HD 7790 Bonaire XT March 2013 GCN 2nd gen28 nm 2080 106 160 mm2 896 56 16 1000 56 0 16 0 1792 128 10242048 GDDR5128 bit 1500 96 10 85 PCIe 3 0 16 150Radeon HD 7850 Pitcairn Pro March 2012 GCN 1st gen28 nm 2800 106 212 mm2 1024 64 32 860 55 04 27 52 1761 28 110 08 10242048 GDDR5256 bit 1200 153 6 10 130 PCIe 3 0 16 250Radeon HD 7870GHz Edition Pitcairn XT March 2012 1280 80 32 1000 80 32 2560 160 2048 1200 153 6 10 175 PCIe 3 0 16 350Radeon HD 7870 XT Tahiti LE November 2012 4313 106 352 mm2 1536 96 32 925975 88 8 29 6 2841 62995 2 710 4748 8 2048 GDDR5256 bit 1500 192 0 15 185 PCIe 3 0 16 270Radeon HD 7950 Tahiti Pro January 2012 1792 112 32 800 89 6 25 6 2867 2 717 3072 GDDR5384 bit 1250 240 15 200 PCIe 3 0 16 450Radeon HD 7950 Boost Tahiti Pro2 August 2012 1792 112 32 850925 103 6 29 6 3046 43315 2 761 6828 8 3072 GDDR5384 bit 1250 240 15 225 PCIe 3 0 16 330Radeon HD 7970 Tahiti XT January 2012 2048 128 32 925 118 4 29 6 3788 8 947 2 30726144 GDDR5384 bit 1375 264 15 250 PCIe 3 0 16 550Radeon HD 7970GHz Edition Tahiti XT2 June 2012 2048 128 32 10001050 128 0 32 40964300 8 10241075 30726144 GDDR5384 bit 1500 288 15 250 PCIe 3 0 16 500Radeon HD 7990 New Zealand April 2013 2 4313 106 352 mm2 2 2048 128 32 9501000 2 128 2 32 7782 48192 1945 62048 2 3072 GDDR5384 bit 1500 2 288 15 375 PCIe 3 0 16 1000Model Codename Launch ArchitectureFab TransistorsDie Size Config f Clock a MHz Texture GT s Pixel GP s Single Double Size MiB Bus type amp width Clock MHz Bandwidth GB s Idle Max Bus interface Release Price USD Core Fillrate a b c Processing power a d GFLOPS Memory e TDP Watts viewtalkedit a b c d e f Boost values if available are stated below the base value in italic a b Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed a b Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed a b Precision performance is calculated from the base or boost core clock speed based on a FMA operation a b The effective data transfer rate of GDDR5 is quadruple its nominal clock instead of double as it is with DDR memory a b Unified Shaders Texture Mapping Units Render Output Units Lacks hardware video encoder IGP HD 7000 Edit All models feature the UNB MC Bus interface All models do not support double precision FP TeraScale 2 VLIW5 based APUs feature angle independent anisotropic filtering UVD3 and Eyefinity capabilities with up to three outputs TeraScale 3 VLIW4 based APUs feature angle independent anisotropic filtering UVD3 2 and Eyefinity capabilities with up to four outputs Model Launch Code name Architecture Fab nm Core Clock MHz Config core a Fillrate Shared Memory Processing power GFLOPS API compliance version TDP W b APUBase Turbo Texture GT s Pixel GP s Bus width bit Bus type Bandwidth GB s Direct3D OpenGL c OpenCLRadeon HD 7310 38 June 6 2012 Ontario TeraScale 2 d 40 500 80 8 4 4 00 2 00 64 DDR3 1066 8 53 80 11 3 11 0 4 5 1 2 18 E2 1200Radeon HD 7340 38 523 680 5 44 2 72 DDR3 1333 10 66 83 6 108 8 E2 1800Radeon HD 7480D June 1 2012 Scrapper TeraScale 3 d 32 723 128 8 4 11 6 2 9 128 DDR3 1600 25 6 185 65 A4 4000 A4 5300Radeon HD 7540D 760 192 12 4 Un known DDR3 1866 29 9 292 A6 5400KRadeon HD 7560D Devastator 256 16 4 389 65 100 A8 5500 A8 5600KRadeon HD 7660D 760 800 384 24 8 16 2 2 7 584 614 A10 5700 760 MHz A10 5800K 800 MHz viewtalkedit Unified Shaders Texture Mapping Units Render Output Units TDP specified for AMD reference designs includes CPU power consumption Actual TDP of retail products may vary OpenGL 4 5 possible for Terascale 3 with AMD Radeon Software Crimson Beta driver 15 30 or higher 37 a b Lacks hardware video encoder Radeon HD 8000 series Edit Main articles Radeon HD 8000 series and Graphics Core Next first VisualEditor viewtalkedit Model Codename Launch Architecture Fab TransistorsDie Size Core Fillrate a b c Processing power a d GFLOPS Memory e TDP W Bus interfaceConfig f Clock a MHz Texture GT s Pixel GP s Single Double Size MiB Bus type amp width bit Clock MHz Band width GB s IdleMaxRadeonHD 8350 Cedar January 8 2013 TeraScale 2 g 40 nm 292 106 59 mm2 80 8 4 400 650 3 25 2 1 62 6 104 256512 DDR2DDR364 bit 400800 6 412 8 6 419 1 PCIe 2 1 16RadeonHD 8450 Caicos January 8 2013 370 106 67 mm2 160 8 4 625 5 0 2 5 200 512 DDR364 bit 533 8 53 918RadeonHD 8470 Caicos January 8 2013 750 6 0 3 0 240 1024 GDDR564 bit 800 25 6 935RadeonHD 8490 Caicos July 23 2013 875 7 0 3 5 280 1024 DDR3LGDDR564 bit 800900 12 828 8 935RadeonHD 8570 Oland January 8 2013 GCN 1st gen 28 nm 950 106 77 mm2 384 24 8 730 19 2 6 4 560 35 2048 DDR3GDDR5128 bit 9001150 28 872 1266 PCIe 3 0 8RadeonHD 8670 Oland January 8 2013 1000 24 8 768 48 2048 GDDR5128 bit 1150 72 1686RadeonHD 8730 Cape Verde LE September 5 2013 1500 106 123 mm2 384 24 8 800 19 2 6 4 614 4 44 8 1024 GDDR5128 bit 1125 72 1047 PCIe 3 0 16RadeonHD 8760 Cape Verde XT January 8 2013 640 40 16 1000 40 16 1280 80 2048 GDDR5128 bit 1125 72 1680 PCIe 3 0 16RadeonHD 8770 Bonaire XT September 2 2013 GCN 2nd gen 28 nm 2080 106 160 mm2 896 56 16 1000 56 0 16 0 1792 128 2048 GDDR5128 bit 1500 96 1085 PCIe 3 0 16RadeonHD 8870 Pitcairn XT 39 January 8 2013 GCN 1st gen 28 nm 2800 106 212 mm2 1280 80 32 1000 80 32 2560 160 2048 GDDR5256 bit 1200 153 6 15150 PCIe 3 0 16RadeonHD 8950 Tahiti Pro January 8 2013 4313 106 352 mm2 1792 112 32 850925 95 2103 6 27 229 6 3046 43315 2 761 6828 8 3072 GDDR5384 bit 1250 240 15225 PCIe 3 0 16RadeonHD 8970 Tahiti XT2 January 8 2013 2048 128 32 10001050 128 0134 4 3233 6 40964301 10241075 3072 GDDR5384 bit 1500 288 15250 PCIe 3 0 16RadeonHD 8990 Malta April 24 2013 2 4313 106 2 352 mm2 2 2048 128 32 9501000 2 128 2 32 77828192 19462048 2 3072 GDDR5384 bit 1500 2 288 15375 PCIe 3 0 16Model Codename Launch Architecture Fab TransistorsDie Size Config f Clock a MHz Texture GT s Pixel GP s Single Double Size MiB Bus type amp width bit Clock MHz Band width GB s IdleMax Bus interfaceCore Fillrate a b c Processing power a d GFLOPS Memory e TDP W a b c d e f Boost values if available are stated below the base value in italic a b Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed a b Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed a b Precision performance is calculated from the base or boost core clock speed based on a FMA operation a b The effective data transfer rate of GDDR5 is quadruple its nominal clock instead of double as with DDR memory a b Unified Shaders Texture Mapping Units Render Output Units Lacks hardware video encoder Radeon 200 series Edit Main articles Radeon 200 series and Graphics Core Next second Model codename Release Date amp Price Architecture amp Fab Transistors amp Die Size Core Fillrate a b c Processing power a d GFLOPS Memory TBP Bus interfaceConfig e Clock a MHz Texture GT s Pixel GP s Single Double Size MiB Bus type amp width Clock MT s Band width GB s RadeonR5 220 40 Caicos Pro December 21 2013 OEM Terascale 2 f 40 nm 370 106 67 mm2 80 8 4 625650 5 2 5 200 1024 DDR364 bit 1066 8 53 18 W PCIe 2 1 16RadeonR5 230 41 Caicos Pro April 3 2014 42 160 8 4 625 5 2 5 200 10242048 DDR364 bit 1066 8 53 19 W 43 RadeonR5 235 40 Caicos XT December 21 2013 OEM 160 8 4 775 6 2 3 1 248 1024 DDR364 bit 1800 14 4 35 W 44 RadeonR5 235X 40 Caicos XT December 21 2013 OEM 160 8 4 875 7 0 3 5 280 1024 DDR364 bit 1800 14 4 18 WRadeonR5 240 40 Oland November 1 2013 45 OEM GCN 1st gen28 nm 1040 106 90 mm2 384 24 8 730780 14 6 5 84 560 6599 29 2 10242048 DDR3GDDR364 bit 18002000 28 816 0 30 W PCIe 3 0 8RadeonR7 240 46 Oland Pro August 8 2013 US 69 320 20 8 730780 14 6 5 84 467 2499 2 29 2 20484096 DDR3GDDR5128 bit 18004500 28 872 30 W lt 45 W 4 GB 47 RadeonR7 250 46 Oland XT August 8 2013 US 89 384 24 8 1000 1050 24 8 768806 4 48 10242048 DDR3GDDR5128 bit 18004600 28 873 6 75 WRadeonR7 250E 48 Cape Verde Pro December 21 2013 US 109 1500 106 123 mm2 512 32 16 800 25 6 12 8 819 2 51 2 10242048 GDDR5128 bit 4500 72 55 W PCIe 3 0 16RadeonR7 250X 46 Cape Verde XT February 10 2014 US 99 640 40 16 1000 40 16 1280 80 10242048 GDDR5128 bit 4500 72 95 WRadeonR7 260 46 Bonaire December 17 2013 US 109 GCN 2nd gen28 nm 2080 106 160 mm2 768 48 16 1000 48 16 1536 96 1024 GDDR5128 bit 6000 96 95 WRadeonR7 260X 46 Bonaire XTX August 8 2013 US 139 896 56 16 1100 61 6 17 6 1971 2 123 2 10242048 GDDR5128 bit 6500 104 115 WRadeonR7 265 46 Pitcairn Pro February 13 2014 US 149 GCN 1st gen28 nm 2800 106 212 mm2 1024 64 32 900925 57 6 28 8 1843 2 115 2 2048 GDDR5256 bit 5600 179 2 150 WRadeonR9 270 49 Pitcairn XT November 13 2013 US 179 1280 80 32 900925 72 28 8 23042368 144148 2048 GDDR5256 bit 5600 179 2 150 WRadeonR9 270X 49 Pitcairn XT August 8 2013 US 199 1280 80 32 10001050 80 32 25602688 160168 20484096 GDDR5256 bit 5600 179 2 180 WRadeonR9 280 49 Tahiti Pro March 4 2014 US 249 4313 106 352 mm2 1792 112 32 827933 92 6 26 5 29643343 9 741836 3072 GDDR5384 bit 5000 240 250 WRadeonR9 280X 49 Tahiti XTL 50 August 8 2013 US 299 2048 128 32 8501000 109 128 27 2 32 3481 64096 870 41024 3072 GDDR5384 bit 6000 288 250 WRadeonR9 285 49 Tonga Pro September 2 2014 US 249 GCN 3rd gen28 nm 5000 106 359 mm2 51 1792 112 32 918 102 8 29 4 3290 206 6 52 2048 GDDR5256 bit 5500 176 g 190 WRadeonR9 285X Tonga XT Unreleased 54 2048 128 32 1002 128 3 32 1 4104 256 5 3072 GDDR5384 bit 5500 264 200 WRadeonR9 290 49 Hawaii Pro November 5 2013 US 399 GCN 2nd gen28 nm 6200 106 438 mm2 55 2560 160 64 up to 947 h 151 52 60 608 4848 6 606 1 4096 GDDR5512 bit 5000 320 250 W 57 RadeonR9 290X 49 Hawaii XT October 24 2013 November 6 2014 58 US 549 2816 176 64 1000 h 176 64 5632 704 40968192 GDDR5512 bit 5000 320 250 W 57 RadeonR9 295X2 49 59 Vesuvius April 8 2014 US 1499 2 6200 106 2 438 mm2 2 2816 176 64 1018 358 33 130 3 11466 75 1433 34 2 4096 GDDR5512 bit 5000 2 320 500 WModel codename Release Date amp Price Architecture amp Fab Transistors amp Die Size Config e Clock a MHz Texture GT s Pixel GP s Single Double Size MiB Bus type amp width Clock MT s Band width GB s TBP Bus interfaceCore Fillrate a b c Processing power a d GFLOPS Memoryvte a b c d e f Boost values if available are stated below the base value in italic a b Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed a b Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed a b Precision performance is calculated from the base or boost core clock speed based on a FMA operation a b Unified Shaders Texture Mapping Units Render Output Units Lacks hardware video encoder The R9 285 utilizes loss less colour compression which can increase effective memory performance relative to GCN 1st gen and 2nd gen cards in certain situations 51 53 a b Base clock of R9 290 and R9 290X will maintain at 947 MHz and 1000 MHz before reaching 95 C respectively 56 Radeon 300 series Edit Main articles Radeon 300 series and Graphics Core Next third Model Codename Release Date amp Price Architecture Fab TransistorsDie Size Core Fillrate a b c Processing power a d GFLOPS Memory TBP W Bus interfaceConfig e Clock a MHz Texture GT s Pixel GP s Single Double Size MiB Bus type amp width Clock MT s Band width GB s RadeonR5 330 Oland Pro May 2015 OEM GCN 1st gen 28 nm 1040 106 90 mm2 320 20 8 Un known855 17 1 6 84 547 2 34 2 10242048 DDR3128 bit 1800 28 8 30 PCIe 3 0 16RadeonR5 340 Oland XT May 2015 OEM 384 24 8 Un known825 19 8 6 6 633 6 39 6 10242048 DDR3GDDR5128 bit 18004500 28 872 75RadeonR7 340 Oland XT May 2015 OEM 384 24 8 730780 17 518 7 5 86 2 560 6599 32 735 102420484096 DDR3GDDR5128 bit 18004500 28 872 75RadeonR5 340X 60 Oland XT May 2015 OEM 384 24 8 1050 25 2 8 4 806 50 4 2048 DDR364 bit 2000 16 30RadeonR7 350 Oland XT May 2015 OEM 384 24 8 10001050 2425 2 88 4 768806 4 4850 4 10242048 DDR3GDDR5128 bit 18004500 28 872 75RadeonR7 350 61 Cape Verde XTL February 2016 89 USD 1500 106 123 mm2 512 32 16 925 29 6 14 8 947 2 59 2 2048 GDDR5128 bit 4500 72 75RadeonR7 350X 62 Oland XT May 2015 OEM 1040 106 90 mm2 384 24 8 1050 25 2 8 4 806 50 4 4096 DDR3128 bit 2000 32 30RadeonR7 360 63 64 Bonaire Pro June 2015 109 USD GCN 2nd gen 28 nm 2080 106 160 mm2 768 48 16 1050 50 4 16 8 1612 8 100 8 2048 GDDR5128 bit 6500 104 100RadeonR9 360 Bonaire Pro May 2015 OEM 768 48 16 10001050 4850 4 1616 8 15361612 8 96100 8 2048 GDDR5128 bit 6500 104 85RadeonR7 370 63 Pitcairn Pro June 2015 149 USD GCN 1st gen 28 nm 2800 106 212 mm2 1024 64 32 975 62 4 31 2 1996 8 124 8 20484096 GDDR5256 bit 5600 179 2 110RadeonR9 370 Pitcairn Pro May 2015 OEM 1024 64 32 950975 60 862 4 30 431 2 1945 61996 8 121 6124 8 20484096 GDDR5256 bit 5600 179 2 150RadeonR9 370X Pitcairn XT August 2015 179 USD 1280 80 32 1000 80 32 2560 160 20484096 GDDR5256 bit 5600 179 2 185RadeonR9 380 Tonga Pro May 2015 OEM GCN 3rd gen 28 nm 5000 106 359 mm2 1792 112 32 918 102 8 29 4 3290 206 6 4096 GDDR5256 bit 5500 176 190RadeonR9 380 65 Tonga Pro June 2015 199 USD 1792 112 32 970 108 6 31 0 3476 5 217 3 20484096 GDDR5256 bit 5700 182 4 f 190RadeonR9 380X 65 Tonga XT November 2015 229 USD 2048 128 32 970 124 2 31 0 3973 1 248 3 4096 GDDR5256 bit 5700 182 4 190RadeonR9 390 65 Grenada Pro June 2015 329 USD GCN 2nd gen 28 nm 6200 106 438 mm2 2560 160 64 1000 160 64 5120 640 8192 GDDR5512 bit 6000 384 275RadeonR9 390X 65 Grenada XT June 2015 429 USD 2816 176 64 1050 184 8 67 2 5913 6 739 2 8192 GDDR5512 bit 6000 384 275RadeonR9 Fury 66 Fiji Pro July 2015 549 USD GCN 3rd gen 28 nm 8900 106 596 mm2 3584 224 64 1000 224 64 7168 448 4096 HBM4096 bit 1000 512 275RadeonR9 Nano 67 Fiji XT August 2015 649 USD 4096 256 64 1000 256 64 8192 512 175RadeonR9 Fury X 65 68 Fiji XT June 2015 649 USD 4096 256 64 1050 268 8 67 2 8601 6 537 6 275RadeonPro Duo 69 70 71 72 Fiji XT April 2016 1499 USD 2 8900 106 2 596 mm2 2 4096 256 64 1000 512 128 16384 1024 2 4096 HBM4096 bit 1000 2 512 350Model Codename Release Date amp Price Architecture Fab TransistorsDie Size Config e Clock a MHz Texture GT s Pixel GP s Single Double Size MiB Bus type amp width Clock MT s Band width GB s TBP W Bus interfaceCore Fillrate a b c Processing power a d GFLOPS Memoryvte a b c d e f Boost values if available are stated below the base value in italic a b Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed a b Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed a b Precision performance is calculated from the base or boost core clock speed based on a FMA operation Double precision performance of Hawaii cards is 1 8 of single precision performance for the other it is 1 16 of single precision performance a b Unified Shaders Texture Mapping Units Render Output Units The R9 380 utilizes loss less color compression which can increase effective memory performance relative to GCN 1st gen and 2nd gen cards in certain situations citation needed Radeon 400 series Edit Main articles Radeon 400 series and Graphics Core Next fourth Model Codename Release Date amp Price Architecture amp Fab Transistors amp Die Size Core Fillrate a b c Processing power a d GFLOPS Memory TBP Bus interfaceConfig e Clock a MHz Texture GT s Pixel GP s Single Double Size GiB Bus type amp width Clock MT s Band width GB s Radeon R5 430 Oland Pro 73 74 June 30 2016 OEM GCN 1st gen28 nm 1040 106 90 mm2 384 24 86 CU 730780 17 5218 72 5 846 24 560599 37 440 12 DDR3GDDR5128 bit 18004500 28 872 50 W PCIe 3 0 8Radeon R5 435 Oland 73 75 320 20 85 CU 1030 20 6 8 24 659 41 2 2 DDR364 bit 2000 16Radeon R7 430 Oland Pro 76 77 384 24 86 CU 730780 17 5218 72 5 846 24 560599 37 440 124 DDR3GDDR5128 bit 18004500 28 872Radeon R7 435 Oland 76 78 320 20 85 CU 920 18 4 7 36 589 36 8 2 DDR364 bit 2000 16Radeon R7 450 Cape Verde Pro 76 79 1500 106 123 mm2 512 32 168 CU 1050 33 6 16 8 1075 65 2 GDDR5128 bit 4500 72 65 W PCIe 3 0 16Radeon RX 455 Bonaire Pro 76 80 GCN 2nd gen28 nm 2080 106 160 mm2 768 48 1612 CU 50 4 1613 100 8 6500 104 100 WRadeon RX 460 Baffin 81 82 83 84 85 August 8 2016 109 USD 2 GB 139 USD 4 GB GCN 4th genGloFo14LPP 86 f 3000 106 123 mm2 896 56 1614 CU 10901200 6167 2 17 419 2 19532150 122132 24 7000 112 lt 75 W PCIe 3 0 8Radeon RX 470D Ellesmere 88 October 21 2016 CNY 1299 China Only 5700 106 232 mm2 1792 112 3228 CU 9261206 103 7135 1 29 638 6 33194322 207270 4 GDDR5256 bit 224 120 W PCIe 3 0 16Radeon RX 470 Ellesmere Pro 81 83 84 August 4 2016 179 USD 2048 128 3232 CU 118 5154 4 37934940 237309 48 6600 211Radeon RX 480 Ellesmere XT 89 90 91 92 June 29 2016 199 USD 4 GB 239 USD 8 GB 2304 144 3236 CU 11201266 161 3182 3 35 840 5 51615834 323365 70008000 224256 150 Wvte a b c Boost values if available are stated below the base value in italic Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed Precision performance is calculated from the base or boost core clock speed based on a FMA operation Unified Shaders Texture Mapping Units Render Output Units and Compute Units CU GlobalFoundries 14 nm 14LPP FinFET process is second sourced from Samsung Electronics 87 Radeon 500 series Edit Main articles Radeon 500 series and Graphics Core Next fourth Model Code name Release Date amp Price Architecture amp fab Transistors amp die size Core Fillrate a b c Processing power a d GFLOPS Memory TBP BusinterfaceConfig e Clock a MHz Texture GT s Pixel GP s Single Double Size Bus type amp width Clock MT s Bandwidth GB s Radeon 520 Banks f 93 94 Apr 18 2017 OEM GCN 128 nm 690 106 56mm2 320 20 45 CU 1030 20 6 4 1 659 2 41 2 1 GB2 GB DDR3GDDR564 bit 20004500 1636 PCIe 3 0 8Radeon 530 Weston f 95 GCN 328 nm 125 mm2 320 20 85 CU 1024 20 480 8 2 655 36 40 96 1 GB2 GB4 GB 96 DDR3GDDR564 bit 18004500 14 436 384 24 86 CU 24 576 786 432 49 152Radeon RX 540 Polaris 12 97 98 GCN 4GloFo14LPP g 100 2 2 109 101 mm2 512 32 168 CU 11241219 35 96839 008 17 98419 504 1150 9761248 256 71 93678 016 2 GB4 GB GDDR5128 bit 6000 96 PCIe 3 0 8Radeon RX 550 Polaris 12 101 102 103 Apr 20 2017 79 USD 11001183 35 237 856 17 618 928 1126 41211 392 70 475 712 7000 112 50 WRadeon RX 550 640SP Polaris 11 104 Apr 20 2017 79 USD 3 0 109 123 mm2 640 40 1610 CU 10191071 40 7642 84 16 30417 136 1304 321370 88 81 5285 68 6000 96 60 WRadeon RX 550X Polaris 12 105 Apr 11 2018 79 USD 2 2 109 101 mm2 512 32 168 CU 11001287 35 241 184 17 620 592 1126 41317 888 70 482 368 7000 112 50 WRadeon RX 550X 640SP Polaris 11 106 Apr 11 2018 OEM 3 0 109 123 mm2 640 40 1610 CU 10191071 40 7642 84 16 30417 136 1304 321370 88 81 5285 68 6000 96 60 WRadeon RX 560D Polaris 21 107 108 109 Jul 4 2017 OEM and China Only 3 0 109 123 mm2 896 56 1614 CU 10901175 61 065 8 17 418 8 19532106 122 0131 6 65 WRadeon RX 560 h Polaris 21 102 107 110 Jul 4 2017 99 USD 10901175 61 065 8 17 418 8 19532106 122 0131 6 7000 112 60 80 WApr 18 2017 99 USD 1024 64 1616 CU 11751275 75 281 6 18 820 4 24062611 150 4163 2Radeon RX 570 Polaris 20 111 102 Apr 18 2017 169 USD 5 7 109 232 mm2 2048 128 3232 CU 11681244 149 5159 2 37 439 8 47845095 299 0318 4 4 GB8 GB GDDR5256 bit 224 150 W PCIe 3 0 16Radeon RX 580 Polaris 20 112 102 Apr 18 2017 199 USD 4 GB 229 USD 8 GB 2304 144 3236 CU 12571340 181 0193 0 40 242 9 57926175 362 0385 9 8000 256 185 WRadeon RX 590 GME Polaris 20 113 114 115 March 9 2020China Only 12571380 181 0198 7 40 244 2 57926359 362 0397 4 8 GB 175 WRadeon RX 590 Polaris 30 116 Nov 15 2018 279 USD GCN 4Samsung GloFo12LP 14LP i 14691545 211 5222 5 47 049 4 67697120 423 0444 9 225 Wvte a b c Boost values if available are stated below the base value in italic Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed Precision performance is calculated from the base or boost core clock speed based on a FMA operation Unified shaders Texture mapping units Render output units and Compute units CU a b Lacks hardware video encoder and decoder GlobalFoundries 14 nm 14LPP FinFET process is second sourced from Samsung Electronics 99 In October 2017 AMD branded an additional Polaris chip as RX 560 although it features fewer shader and texture mapping units than the first released RX 560 GlobalFoundries 12 nm 12LP process is based on Samsung s 14 nm 14LPP process 99 Radeon RX Vega series Edit Main articles Radeon RX Vega series and Graphics Core Next fifth Model Code name Release Date amp Price Architecture amp fab Transistors amp die size Core Fillrate a b c Processing power a d GFLOPS Memory TBP BusinterfaceConfig e Clock a MHz Texture GT s Pixel GP s Half Single Double Size GB Bandwidth GB s Bus type amp width Clock MT s Radeon RX Vega 56 Vega 10 117 118 119 Aug 28 2017 399 USD GCN 5GloFo14LPP f 120 121 12 5 109 486 mm2 3584 224 6456 CU 11561471 258 9329 5 73 9894 14 16 57221 088 8 28610 544 517 9659 0 8 409 6 HBM22048 bit 1600 210 W PCIe 3 0 16Radeon RX Vega 64 Vega 10 122 118 119 Aug 14 2017 499 USD 4096 256 6464 CU 12471546 319 2395 8 79 8198 94 20 43125 330 10 21512 665 638 5791 6 483 8 1890 295 WRadeon RX Vega 64 Liquid Vega 10 122 118 119 Aug 14 2017 699 USD 14061677 359 9429 3 89 98107 3 23 03627 476 11 51813 738 719 9858 6 345 Wvte a b c Boost values if available are stated below the base value in italic Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed Precision performance is calculated from the base or boost core clock speed based on a FMA operation Unified shaders Texture mapping units Render output units and Compute units CU GlobalFoundries 14 nm 14LPP FinFET process is second sourced from Samsung Electronics Radeon VII series Edit Main articles Radeon RX Vega series Radeon VII branded discrete graphics and Graphics Core Next fifth Model Code name Release Date amp Price Architecture amp fab Transistors amp die size Core Fillrate a b c Processing power a d GFLOPS Memory TBP BusinterfaceConfig e Clock a MHz Texture GT s Pixel GP s Half Single Double Size GB Bandwidth GB s Bus type amp width Clock MT s Radeon VII Vega 20 123 124 125 Feb 7 2019 699 USD GCN 5TSMC CLN7FF 126 13 23 109 331 mm2 3840 240 6460 CU 14001750 1800 336 0420 0 89 60112 0 21 50427 648 10 75213 824 2 6883 459 16 1024 HBM24096 bit 2000 300 W PCIe 3 0 16vte a b c Boost values if available are stated below the base value in italic Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed Precision performance is calculated from the base or boost core clock speed based on a FMA operation Unified shaders Texture mapping units Render output units and Compute units CU Radeon RX 5000 series Edit Main articles Radeon RX 5000 series and RDNA microarchitecture Model Code name Release Date amp Price Architecture amp fab Transistors amp die size Core Fillrate a b c Processing power a d GFLOPS Memory TBP BusinterfaceConfig e Clock a MHz Texture GT s Pixel GP s Half Single Double Size GB Bandwidth GB s Bus type amp width Clock MT s Radeon RX 5300 Navi 14 127 128 Aug 28 2020 OEM RDNATSMC N7 6 4 109 158 mm2 1408 88 3222 CU 13271645 116 8144 8 42 4652 64 7 4749 265 3 7374 632 233 5289 5 3 168 GDDR696 bit 14000 100 W PCIe 4 0 8Radeon RX 5300 XT Navi 14 129 130 Oct 7 2019 OEM 16701845 146 7162 4 53 4459 04 9 40510 390 4 7035 196 293 9324 7 4 112 GDDR5128 bit 7000Radeon RX 5500 Navi 14 131 132 133 224 GDDR6128 bit 14000 150 WRadeon RX 5500 XT Navi 14 134 135 136 137 Dec 7 2019 169 USD 4GB 199 USD 8GB 17171845 151 1162 4 54 9459 04 9 67010 390 4 8355 196 302 2324 7 48 130 WRadeon RX 5600 Navi 10 138 139 Jan 21 2020 OEM 10 3 109 251 mm2 2048 128 6432 CU 13751560 176 0199 7 88 0099 84 11 26412 780 5 6326 390 352 0399 4 6 288 GDDR6192 bit 12000 150 W PCIe 4 0 16Radeon RX 5600 XT Navi 10 140 141 Jan 21 2020 279 USD 2304 144 6436 CU 198 0224 6 12 67214 377 6 3367 188 396 0449 3 288336 1200014000 160 WRadeon RX 5700 Navi 10 142 143 144 145 146 Jul 7 2019 349 USD 14651725 210 9248 4 93 73110 4 13 50115 900 6 7517 949 421 9496 8 8 448 GDDR6256 bit 14000 180 WRadeon RX 5700 XT Navi 10 147 148 144 145 146 Jul 7 2019 399 USD 2560 160 6440 CU 16051905 256 8304 8 102 7121 9 16 43519 510 8 2189 754 513 6609 6 225 WRadeon RX 5700 XT 50th Anniversary Edition Navi 10 149 150 151 146 Jul 7 2019 449 USD 16801980 268 8316 8 107 5126 7 17 20320 276 8 60210 138 537 6633 6 235 Wvte a b c Boost values if available are stated below the base value in italic Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed Precision performance is calculated from the base or boost core clock speed based on a FMA operation Unified shaders Texture mapping units Render output units and Compute units CU Radeon RX 6000 series Edit Main articles Radeon RX 6000 series and RDNA 2 Model Code name Release Date amp Price Architecture amp fab Transistors amp die size Core Fillrate a b c Processing power a d GFLOPS Infinity Cache Memory TBP BusinterfaceConfig e Clock a MHz Texture GT s Pixel GP s Half Single Double Size Bandwidth GB s Size Bandwidth GB s Bus type amp width Clock MT s Radeon RX 6400 Navi 24 152 153 f Jan 19 2022 159 USD RDNA 2TSMC N6 5 4 109 107 mm2 768 48 32 1212 CU 19232321 92 3111 4 61 574 3 5 9077 130 2 9543 565 184 6222 8 16 MB 208 0 4 GB 128 GDDR664 bit 16000 53 W PCIe 4 0 4Radeon RX 6500 XT Navi 24 154 155 156 f Jan 19 2022 199 USD 4GB 219 USD 8GB 1024 64 32 1616 CU 23102815 147 8180 2 73 990 1 9 46211 530 4 7315 765 295 6360 3 232 0 4 GB8 GB 144 18000 107 W113 WRadeon RX 6600 Navi 23 157 158 Oct 13 2021 329 USD RDNA 2TSMC N7 11 06 109 237 mm2 1792 112 64 2828 CU 16262491 228 9279 0 104 1159 4 14 65417 860 7 3258 928 457 8558 0 32 MB 412 9 8 GB 224 GDDR6128 bit 14000 132 W PCIe 4 0 8Radeon RX 6600 XT Navi 23 159 160 161 162 Aug 11 2021 379 USD 2048 128 64 3232 CU 19682589 251 9331 4 126 0165 7 16 12221 209 8 06110 605 503 8662 8 444 9 256 16000 160 WRadeon RX 6650 XT Navi 23 163 164 May 10 2022 399 USD 20552635 263 0337 2 131 5168 6 16 83521 586 8 41710 793 526 1674 6 468 9 280 17500 180 WRadeon RX 6700 Navi 22 165 166 167 Jun 9 2021 17 2 109 335 mm2 2304 144 64 3636 CU 19412450 279 5352 8 124 2156 8 17 88822 579 8 94411 290 559 0705 6 80 MB 1065 0 10 GB 320 GDDR6160 bit 16000 175 W PCIe 4 0 16Radeon RX 6700 XT Navi 22 168 169 170 Mar 18 2021 479 USD 2560 160 64 4040 CU 23212581 371 4413 0 148 5165 2 23 76726 429 11 88413 215 742 7825 9 96 MB 1278 0 12 GB 384 GDDR6192 bit 230 WRadeon RX 6750 XT Navi 22 171 172 May 10 2022 549 USD 21502600 344 0416 0 137 6166 4 22 01626 624 11 00813 312 688 0832 0 1326 0 432 18000 250 WRadeon RX 6800 Navi 21 173 174 175 176 Nov 18 2020 579 USD 26 8 109 520 mm2 3840 240 96 6060 CU 17002105 408 0505 2 163 2202 1 26 11232 333 13 05616 166 8161 010 128 MB 1432 6 16 GB 512 GDDR6256 bit 16000Radeon RX 6800 XT Navi 21 173 177 175 176 Nov 18 2020 649 USD 4608 288 128 7272 CU 18252250 525 6648 0 233 6288 0 33 63841 472 16 81920 736 1 0511 296 1664 2 300 WRadeon RX 6900 XT Navi 21 173 178 175 176 Dec 8 2020 999 USD 5120 320 128 8080 CU 18252250 584 0720 0 233 6288 0 37 37646 080 18 68823 040 1 1681 440Radeon RX 6950 XT Navi 21 179 180 May 10 2022 1 099 USD 18902310 604 8739 2 241 9295 7 38 70747 309 19 35423 654 1 2101 478 1793 5 576 18000 335 Wvte a b c Boost values if available are stated below the base value in italic Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed Precision performance is calculated from the base or boost core clock speed based on a FMA operation Unified shaders Texture mapping units Render output units Ray accelerators and Compute units CU a b Lacks hardware video encoder Radeon RX 7000 series Edit Main articles Radeon RX 7000 series and RDNA 3 Model Code name Release date amp price Architecture amp fab Chiplets active Transistors amp die size a Core Fillrate b c d Processing power b e TFLOPS Infinity Cache Memory TBP BusinterfaceConfig f g Clock b MHz Texture GT s Pixel GP s Half Single Double Size MB Bandwidth GB s Size GB Bandwidth GB s Bus type amp width Clock MT s Radeon RX 7900 XT Navi 31 182 Dec 13 2022 899 USD RDNA 3TSMC N5 GCD TSMC N6 MCD 1 GCD5 MCD 57 7 109 531 mm2 5376 336 19284 168 84 CU 15002400 504 0806 4 288 0460 8 64 51103 2 32 2651 61 1 0081 613 80 2900 20 800 GDDR6320 bit 20000 315 W PCIe 4 0 16Radeon RX 7900 XTX Navi 31 183 Dec 13 2022 999 USD 1 GCD6 MCD 6144 384 19296 192 96 CU 19002500 729 6960 0 364 8480 0 93 39122 9 46 6961 44 1 4591 920 96 3500 24 960 GDDR6384 bit 355 Wvte Approximate die size of entire MCM package that consists of single GCD Graphics Compute Die and six MCDs Memory Cache Die Radeon RX 7900 XT has only five active MCDs inactive one is for structual support and heat dissipation Die size of GCD is 306 mm2 size of each MCD is 37 5 mm2 181 a b c Boost values if available are stated below the base value in italic Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed Precision performance is calculated from the base or boost core clock speed based on a FMA operation Unified shaders Texture mapping units Render output units Ray accelerators AI accelerators and Compute units CU GPUs based on RDNA 3 have dual issue stream processors so that up to two shader instructions can be executed per clock cycle under certain parallelism conditions Mobile GPUs EditThese GPUs are either integrated into the mainboard or occupy a Mobile PCI Express Module MXM Rage Mobility series Edit Main article ATI Rage Model Launch Fab nm Bus interface Core clock MHz Memory clock MHz Hardware T amp L Core config1 Fillrate Memory API compliance version NotesPixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width bit Direct3D OpenGLRage LT Rage II Nov 1996 500 PCI 60 66 No 0 1 1 1 0 06 0 06 4 0 53 EDO SDR SGR 64 5 N ARage LT Pro Rage Pro Nov 1997 350 AGP PCI 75 100 0 075 0 075 8 0 80 6 1 1 Motion compensationRage Mobility M P Rage Pro Nov 1998 250 90 Un known 0 18 0 18 Un known SDR SGR Un known Un known M had 4 MB of integrated SDRAM P had none IDCT motion compensation Rage Mobility M1 Rage Pro Feb 1999 90 90 0 72 SDR 6 1 2 M1 had 8 MB of integrated SDRAM P had none IDCT motion compensation Rage 128 GL Aug 1998 103 103 0 2 2 2 0 206 0 206 32 1 65 128Rage Mobility 128 Rage 128 Pro Oct 1999 105 105 0 21 0 21 16 2 28 IDCT Motion CompensationRage Mobility M3 AGP 4 Rage 128 Pro 2 28 M3 had 8 MB of integrated SDRAM IDCT Motion Compensation Rage Mobility M4 AGP 4 Rage 128 Pro 32 2 28 M4 had 16 MB of integrated SDRAM IDCT Motion Compensation 1 Vertex shaders Pixel shaders Texture mapping units Render output units Mobility Radeon series Edit Model Launch Model number Code name Fab nm Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate Memory API compliance version NotesPixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width bit Direct3D OpenGLMobility Radeon 7000 Feb 2001 M6 RV100 180 AGP 4 144167 144183 0 1 3 1 0 167 0 5 81632 1 4642 928 SDRDDR 3264 7 1 3Mobility Radeon 7500 Dec 2001 M7 RV200 150 280 200 1 2 6 2 0 56 1 68 3264 3 26 4 DDR 64128 7 PowerPlay II DX7 T amp LMobility Radeon 9000 Aug 2002 M9 RV250 250 1 4 4 4 1 0 1 0 8 1 1 4 PowerPlay 3 0 FullstreamMobility Radeon 9200 Mar 2003 M9 RV280 AGP 8 250 250 200 220 3 2 3 526 4 7 04Mobility Radeon 9500 2004 M11 RV360 130 Un known Un known 2 4 4 4 Un known Un known 64 Un known 9 0 2 0Mobility Radeon 9550 2005 M12 210 183 0 84 0 84 2 9285 856Mobility Radeon 9600 Mar 2003 M10 M11 RV350 300 300 1 2 1 2 64128 4 89 6Mobility Radeon 9600 Pro 2004 M10 350 350 1 4 1 4 128 11 2 128Mobility Radeon 9700 Feb 2004 M11 RV360 450 275 1 8 1 8 8 8Mobility Radeon 9800 Sep 2004 M18 R420 350 300 4 8 8 8 2 8 2 8 256 19 2 2561 Vertex shaders Pixel shaders Texture mapping units Render output units Mobility Radeon X300 X600 X700 X800 series Edit Model Launch Model number Code name Fab nm Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate Memory API compliance version NotesPixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width bit Direct3D OpenGLMobility Radeon X300 Nov 2005 M22 RV370 110 PCI E 16 350 250 2 4 4 4 1 4 1 4 128 4 DDR 64 9 0b 2 0 Powerplay 5 0Mobility Radeon X600 Jun 2004 M24 RV380 130 400 1 6 1 6 64 128 8 128Mobility Radeon X700 Mar 2005 M26 RV410 110 400 100 PowerPlay 350 200 6 8 8 4 1 4 2 8 Shared 128 64 128 11 2 DDR GDDR3 3DC dynamic lane count switchingMobility Radeon X800 Nov 2004 M28 R423 130 400 400 6 12 12 12 4 8 4 8 256 25 6 GDDR3 256 3DC DLCS Clock GatingMobility Radeon X800 XT Jun 2005 M28 PRO R423 130 480 550 6 16 16 16 7 68 7 68 35 21 Vertex shaders Pixel shaders Texture mapping units Render output units Mobility Radeon X1000 series Edit Main article Radeon X1000 series Model Launch Model number Code name Fab nm Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate Memory API compliance version NotesPixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width bit Direct3D OpenGLMobility Radeon X1300 January 19 2006 M52 RV515 90 PCIe 16 350 250 2 4 4 4 1 4 1 4 128 shared 8 DDR DDR2 128 9 0c 2 0Mobility Radeon X1350 September 18 2006 M62 470 350 1 88 1 88 11 2 DDR2 GDDR3Mobility Radeon X1400 January 19 2006 M54 445 250 1 78 1 78 8 DDR DDR2Mobility Radeon X1450 September 18 2006 M64 550 450 2 2 2 2 14 4 DDR2 GDDR3Mobility Radeon X1600 February 1 2006 M56 RV530 425450 375470 5 12 4 4 1 71 8 1 71 8 256 12 015 04 DDR2GDDR3Mobility Radeon X1700 M66 RV535 475 400550 1 9 1 9 11 217 6 strained siliconMobility Radeon X1800 March 1 2006 M58 R520 450 500 8 12 12 12 5 4 5 4 32 GDDR3 256Mobility Radeon X1800 XT M58 550 650 8 16 16 16 8 8 8 8 41 6Mobility Radeon X1900 January 11 2007 M68 RV570 80 400 470 8 36 12 12 4 8 4 8 30 08 PowerPlay 6 01 Vertex shaders Pixel shaders Texture mapping units Render output units Mobility Radeon HD 2000 series Edit Main article Radeon HD 2000 series OpenGL 3 3 is possible with latest drivers for all RV6xx Model Launch Model number Code name Fab nm Bus interface Core clock MHz Memory clock MHz Core config Fillrate Memory API compliance version Processing power GFLOPS NotesPixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width bit Direct3D OpenGLMobility Radeon X2300 March 1 2007 M64 RV515 90 PCIe 16 480 400 2 4 4 41 1 92 1 92 128 6 412 8 DDRDDR2GDDR3 64128 9 0c 2 0 Un known renamed product HyperMemory no UVD PowerPlay 6 0Mobility Radeon X2500 June 1 2007 M66 RV530 460 5 12 4 41 1 84 1 84 256 12 8 128 Un known based on X1600 1700 HM up to 768Mb no UVD PowerPlay 6 0Mobility Radeon HD 2300 March 1 2007 M71 RV515 480 2 4 4 41 1 92 1 92 128256512 6 412 8 64128 Un known same as X2300 but with UVD PowerPlay 6 0Mobility Radeon HD 2400 May 14 2007 M72S RV610 65 450 40 4 42 1 8 1 8 256 Hyper Memory 6 4 DDR2 64 10 0 2 0 3 3 36 UVD PowerPlay 7 0Mobility Radeon HD 2400 XT M72M 600600 400700 2 4 2 4 6 411 2 DDR2GDDR3 48Mobility Radeon HD 2600 M76M RV630 500500 400600 120 8 42 2 0 4 0 12 819 2 128 120Mobility Radeon HD 2600 XT M76XT 680 750 2 72 5 44 24 GDDR3 168Mobility Radeon HD 2700 December 12 2007 M76 650 700 2 6 5 2 256 Hyper Memory total 768 22 41 Vertex shaders Pixel shaders Texture mapping units Render output units 2 Unified Shaderss Texture mapping units Render output units Mobility Radeon HD 3000 series Edit Main article Radeon HD 3000 series Model 184 Launch Model number Code name Fab nm Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate Memory API compliance version Processing power GFLOPS TDP Watts NotesPixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width bit Direct3D OpenGLMobility Radeon HD 3100 August 1 2008 RS780MC RV620 55 PCIe 16 1 1 300 800 system memory 40 4 4 1 2 1 2 up to 512 from system memory 6 4 12 8 DDR2 64 128 10 1 2 0 3 3 24 UVD PowerPlay 7 0Mobility Radeon HD 3200 June 4 2008 RS780MC 500 800 system memory 2 2 6 4 12 8 40Mobility Radeon HD 3410 July 25 2008 M82 MPE 400 400 1 6 1 6 256 512 6 4 64 32Mobility Radeon HD 3430 M82 SE PCIe 16 2 0 450 400 1 8 1 8 256 6 4 36Mobility Radeon HD 3450 January 7 2008 M82 500 400700 2 2 6 411 2 DDR2GDDR3 40Mobility Radeon HD 3470 M82 XT 680 400800 2 72 2 72 6 412 8 54 4Mobility Radeon HD 3650 M86 RV635 500 500700 120 8 4 2 4 5121024 16 022 4 DDR2GDDR3GDDR4 128 3 3 120Mobility Radeon HD 3670 M86 XT 680 800 2 72 5 44 25 6 2 0 3 3 163 2 30 UVD PowerPlay 7 0Mobility Radeon HD 3850 June 4 2008 M88 L M88 LP RV670 580 750 320 16 16 9 28 9 28 512 48 0 GDDR3 256 371 2Mobility Radeon HD 3870 M88 LXT 660 850 10 56 10 56 54 4 422 4 55Mobility Radeon HD 3850 X2 June 5 2008 2 M88 L M88 LP R680 580 750 2x 320 16 16 2 9 28 2 9 28 2 512 2 48 0 2 256 2 371 2Mobility Radeon HD 3870 X2 September 1 2008 2 M88 LXT 660 850 2 10 56 2 10 56 2 54 4 2 422 4 1101 Unified Shaders Texture mapping units Render output units Mobility Radeon HD 4000 series Edit Main article Radeon HD 4000 series Model Launch Model Number Code name Fab nm Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate Memory API compliance version Processing power GFLOPS NotesPixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width bit Direct3D OpenGLMobility Radeon HD 4200 September 10 2009 Un known RV620 55 Internal PCIe x16 1 1 500 800 system memory 40 4 4 2 2 up to 512 from system memory 6 4 12 8 DDR2 DDR3 64 128 10 1 3 3 40 UVD2 PowerPlay 7 0Mobility Radeon HD 4225 May 1 2010 Un known 380 1 52 1 52 30 4Mobility Radeon HD 4250 Un known 500 2 2 40Mobility Radeon HD 4270 Un known 590 2 36 2 36 47 2Mobility Radeon HD 4330 January 9 2009 M92 RV710 PCIe 16 2 0 450 600 80 8 4 1 8 3 6 512 9 6 DDR2DDR3GDDR3 64 72Mobility Radeon HD 4530 500 700 2 4 11 2 80Mobility Radeon HD 4550 January 1 2010 550 2 2 4 4 80Mobility Radeon HD 4570 January 9 2009 680 800 2 72 5 44 12 8 108 8Mobility Radeon HD 4650 M96 RV730 500550 600800 320 32 8 44 4 1617 6 5121024 19 225 6 DDR2DDR3GDDR3 128 320352Mobility Radeon HD 4670 M96 XT 675 800 5 4 21 6 12 825 6 432Mobility Radeon HD 4830 March 3 2009 185 M97 RV740 40 400 600400 600 800 900800 900 640 32 16 6 4 9 66 4 9 6 12 8 19 212 8 19 2 25 6 28 825 6 28 8 GDDR3DDR3 512 768512 768Mobility Radeon HD 4850 186 January 9 2009 M98 RV770 55 500 850700 800 40 16 8 20 1024 54 489 6 GDDR3GDDR52 256 800Mobility Radeon HD 4860 March 3 2009 185 M97 RV740 40 650 1000 640 32 16 10 4 20 8 64 0 GDDR52 128 832Mobility Radeon HD 4870 January 9 2009 M98 XT RV770 55 550 888700 800 40 16 8 8 22 5121024 56 83289 6 GDDR3GDDR52 256 880Mobility Radeon HD 4870 X2 550 700 2 800 40 16 2 8 8 2 22 2048 2 89 6 GDDR52 2 256 2 880 UVD2 PowerPlay 7 0Dual GPU solution1 Unified shaders Texture mapping units Render output units 2 The effective data transfer rate of GDDR5 is quadruple its nominal clock instead of double as it is with other DDR memory Mobility Radeon HD 5000 series Edit Main article Radeon HD 5000 series Model Mobility Radeon Launch Model Number Code name Fab nm Bus interface Core clock MHz Memory clock MHz Core config1 Fillrate Memory API compliance version Processing power GFLOPS TDP Watts Pixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width bit Direct3D OpenGLMobility Radeon HD 530v 187 May 5 2010 M92 RV710 55 PCIe 16 2 0 500 600 80 8 4 2 4 1024 9 6 DDR2DDR3GDDR3 64 10 1 3 3 80 10Mobility Radeon HD 545v 188 720 400 800 2 88 5 76 512 1024 6 4 12 8 115 2 15Mobility Radeon HD 550v 189 M96 RV730 450 600 320 32 8 3 6 14 4 1024 19 2 128 288 10Mobility Radeon HD 560v 190 550 800 4 4 17 6 25 6 352 15Mobility Radeon HD 565v 191 M96 XT 675 5 4 21 6 25 6 432 20Mobility Radeon HD 5145 January 7 2010 M92 RV710 720 900 80 8 4 2 88 5 76 14 4 DDR3GDDR3 64 115 2 15Mobility Radeon HD 5165 M96 RV730 600 320 32 8 4 8 19 2 28 8 128 384 35Mobility Radeon HD 5430 Park LP Cedar RV 810 40 PCIe 16 2 1 500550 800 80 8 4 2 02 2 4 04 4 12 8 64 11 4 4 8088 7Mobility Radeon HD 5450 Park PRO 675 2 7 5 4 108 11Mobility Radeon HD 5470 Park XT 750 3 6 1024512 12 825 6 DDR3GDDR3GDDR5 120 1315Mobility Radeon HD 5650 Madison PRO Redwood RV 830 450650 400 20 8 3 65 2 9 013 0 1024 25 6 DDR3GDDR3 128 360520 1519Mobility Radeon HD 5730 Madison LP 650 5 2 13 520 26Mobility Radeon HD 5750 Madison PRO 550 4 4 11 51 2 GDDR5 440 25Mobility Radeon HD 5770 Madison XT PCIe 16 2 0 2 1 650 5 2 13 520 30Mobility Radeon HD 5830 Broadway LP Juniper RV 840 PCIe 16 2 1 500 800 40 16 8 20 25 6 DDR3GDDR3 800 24Mobility Radeon HD 5850 Broadway PRO 625500625 9001000 800 40 16 10810 252025 20481024 28 86464 10008001000az 313039Mobility Radeon HD 5870 Broadway XT 700 1000 11 2 28 1024 64 GDDR5 1120 50Model Launch Model Number Code name Fab nm Bus interface Core clock MHz Memory clock MHz Core config1 Pixel GP s Texture GT s Size MB Bandwidth GB s Bus type Bus width bit Direct3D 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 it is with other DDR memory Radeon HD 6000M series Edit Main article Radeon HD 6000 series Model 192 Launch ArchitectureFab Core Fillrate a b Processing power c GFLOPS Memory TDP Watts Bus interfaceConfig d Clock MHz Pixel GP s Texture GT s Size MiB Bus type amp width Clock MHz Bandwidth GB s Radeon HD 6330M Robson LP 193 November 2010 TeraScale 240 nm 80 8 4 500 2 0 4 0 80 1024 DDR364 bit 800 12 8 7 PCIe 2 1 x16Radeon HD 6350M Robson Pro 193 November 2010 500 2 0 4 0 80 1024 DDR364 bit 800900 12 814 4 7Radeon HD 6370M Robson XT 193 November 2010 750 3 0 6 0 120 1024 DDR364 bit 900 14 4 11Radeon HD 6430M Seymour LP 194 January 2011 TeraScale 240 nm 160 8 4 480 1 92 3 84 153 6 1024 DDR364 bit 800 12 8 Un known PCIe 2 1 x16Radeon HD 6450M Seymour Pro 194 January 2011 600 2 4 4 8 192 1024 DDR364 bit 800 12 8 Un knownRadeon HD 6470M Seymour XT 194 January 2011 700750 2 83 0 5 66 0 224240 1024 DDR364 bit 800800 12 8 Un knownRadeon HD 6490M Seymour XT 194 January 2011 800 3 2 6 4 256 512 GDDR564 bit 800 25 6 Un knownRadeon HD 6530M Capilano Pro 195 November 2010 TeraScale 240 nm 400 20 8 500 4 0 10 0 400 1024 DDR3128 bit 900 28 8 26 PCIe 2 1 x16Radeon HD 6550M Capilano Pro 195 November 2010 600 4 8 12 0 480 1024 DDR3128 bit 900 28 8 26Radeon HD 6570M Capilano XT 195 November 2010 650 5 2 13 0 520 1024 DDR364 bitGDDR5128 bit 900 28 857 6 30Radeon HD 6630M Whistler LP 196 January 2011 TeraScale 240 nm 480 24 8 485 3 88 11 64 465 6 256 Mac 1024 GDDR5128 bit Mac DDR3128 bit 800 51 2 Mac 25 6 Un known PCIe 2 1 x16Radeon HD 6650M Whistler Pro 196 January 2011 600 4 8 14 4 576 1024 DDR3128 bit 900 28 8 Un knownRadeon HD 6730M Whistler XT 196 January 2011 725 5 8 17 4 696 1024 DDR3128 bit 800 25 6 Un knownRadeon HD 6750M Whistler Pro 196 January 2011 600 4 8 14 4 576 256 5121024 GDDR5128 bit 800 900 51 2 57 6 Un knownRadeon HD 6770M Whistler XT 196 January 2011 725 5 8 17 4 696 1024 GDDR5128 bit 900 57 6 Un knownRadeon HD 6830M Granville Pro 197 January 2011 TeraScale 240 nm 800 40 16 575 9 2 23 0 920 2048 DDR3128 bit 800 25 6 39 PCIe 2 1 x16Radeon HD 6850M Granville XT 197 January 2011 675 10 8 27 0 1080 2048 DDR3128 bit 800 25 6 50Radeon HD 6850M Granville Pro 197 January 2011 575 9 2 23 0 920 1024 GDDR5128 bit 800 57 6 39Radeon HD 6870M Granville XT 197 January 2011 675 10 8 27 1080 1024 GDDR5128 bit 1000 64 50Radeon HD 6950M Blackcomb Pro 198 January 2011 TeraScale 240 nm 960 48 32 580 18 56 27 84 1113 6 2048 GDDR5256 bit 900 115 2 50 PCIe 2 1 x16Radeon HD 6970M Blackcomb XT 198 January 2011 680 21 76 32 64 1305 6 2048 GDDR5256 bit 900 115 2 75Radeon HD 6990M Blackcomb XTX 199 July 2011 TeraScale 240 nm 1120 56 32 715 22 88 40 04 1601 6 2048 GDDR5256 bit 900 115 2 75 PCIe 2 1 x16vte Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the core clock speed Pixel fillrate is calculated as the number of Render Output Units multiplied by the core clock speed Single Precision performance is calculated from the core clock speed based on a FMA operation Unified Shaders Texture Mapping Units Render Output Units IGP HD 6000 Edit All models feature the UNB MC Bus interface All models do mnot feature double precision FP All models feature Angle independent anisotropic filtering UVD3 and Eyefinity capabilities with up to three outputs Model Released Code name Architecture Fab nm Core clock rate MHz Config core a Fillrate Shared memory Processing power GFLOPS API compliance version Combined TDP b APUPixel GP s Texture GT s Bandwidth GB s Bus type Bus width bit Direct3D OpenGL OpenCL Vulkan Idle W Max W Radeon HD 6250 200 November 9 2010 201 Wrestler 202 TeraScale 2 40 280 400 80 8 4 2 1 12 1 6 2 24 3 2 8 525 DDR3 1066 64 44 8 64 11 3 11 0 4 5 1 2 Un known 9 C 30 C 50 Z 60Radeon HD 6290 January 7 2011 Ontario 276 400 C 60Radeon HD 6310 200 November 9 2010 201 Wrestler 202 492 2 0 4 0 80 18 E 240 E 300 E 350Radeon HD 6320 August 15 2011 508 600 2 032 2 4 4 064 4 8 10 6 DDR3 1333 82 97 E 450vte Unified Shaders Texture Mapping Units Render Output Units Compute units TDP specified for AMD reference designs includes CPU power consumption Actual TDP of retail products may vary IGP HD 6000G Edit All models include Direct3D 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 VLIW5Model Released Code name Fab nm Core clock MHz Core config1 Fillrate Shared Memory Processing power GFLOPS Max combined TDP2 Watts APUPixel 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 2 1 6 3 2 17 06 DDR3 1333 128 128 35 E2 3000MRadeon HD 6480G BeaverCreek 444 240 12 4 3 1 77 3 55 213 1 35 45 A4 3300M A4 3310MXRadeon HD 6520G 400 320 16 8 4 3 2 6 4 256 A6 3400M A6 3410MX A6 3420MRadeon HD 6620G 444 400 20 8 5 3 55 8 88 25 6 DDR3 1600 355 2 A8 3500M A8 3510MX A8 3530MX1 Unified shaders Texture mapping units Render output units Compute units 2 TDP specified for AMD reference designs includes CPU power consumption Actual TDP of retail products may vary Radeon HD 7000M series Edit Main article Radeon HD 7000 series A Radeon HD 7970M GPU on a Mobile PCI Express Module Model Codename Launch Architecture Fab Core Fillrate Processing power GFLOPS Memory Bus interface TDP W Config a Clock MHz Texture GT s Pixel GP s Size GiB Bus type amp width bit b Memory MHz Bandwidth GB s Radeon HD 7430M Seymour Pro January 2012 TeraScale 2 c 40 nm 160 8 4 2 600 4 8 2 4 192 1 DDR364 bit 900 14 4 PCIe 2 1 16 7Radeon HD 7450M Seymour Pro 700700 5 6 2 8 224 1 DDR3GDDR564 bit 900800 14 425 6 7Radeon HD 7470M Seymour XT 750800 66 4 3 03 2 240256 1 DDR3GDDR564 bit 900800 14 425 6 7 9Radeon HD 7490M Seymour XTX 800 6 4 3 2 256 1 GDDR564 bit 950 30 4 9Radeon HD 7510M Thames LE January 2012 TeraScale 2 c 40 nm 400 20 8 5 450 9 0 3 6 360 1 DDR364 bit 800 12 8 11Radeon HD 7530M Thames LP January 2012 TeraScale 2 c 40 nm 400 24 8 5 450 9 0 3 6 360 1 DDR364 bit 900 14 4 11Radeon HD 7550M Thames Pro January 2012 TeraScale 2 c 40 nm 400 20 8 5 450550 9 011 0 3 64 4 360440 1 DDR3GDDR564 bit 900800 14 425 6 13Radeon HD 7570M Thames Pro January 2012 TeraScale 2 c 40 nm 400 20 8 5 450650 9 013 0 3 65 2 360520 1 DDR3GDDR564 bit 900800 14 425 6 13 15Radeon HD 7590M Thames XT January 2012 TeraScale 2 c 40 nm 480 24 8 6 600 14 4 4 8 576 1 GDDR564 bit 800 25 6 18Radeon HD 7610M Thames LE January 2012 TeraScale 2 c 40 nm 400 20 8 5 450 9 0 3 6 360 1 DDR3128 bit 800 25 6 20Radeon HD 7630M Thames LP January 2012 TeraScale 2 c 40 nm 480 24 8 6 450 10 8 3 6 432 1 DDR3128 bit 800 25 6 20 25Radeon HD 7650M Thames Pro 450550 10 813 2 3 64 4 432528 1 DDR3128 bit 800800 25 6 20 25Radeon HD 7670M Thames Pro 600 14 4 4 8 576 1 DDR3GDDR5128 bit 900 28 857 6 20 25Radeon HD 7690M Thames XT 725600 17 414 4 5 84 8 696576 12 DDR3GDDR5128 bit 900900 28 857 6 20 25Radeon HD 7690M XT Thames XTX 725 17 4 5 8 696 12 GDDR5128 bit 900 57 6 25Radeon HD 7730M Chelsea LP April 2012 GCN 1st gen 28 nm 512 32 16 8 575675 18 421 6 9 210 8 588 8691 2 2 GDDR3128 bit 900900 28 8 PCIe 2 1 16 25 28Radeon HD 7750M Chelsea Pro 575 18 4 9 2 588 8 12 GDDR5128 bit 1000 64 28Radeon HD 7770M Chelsea XT 675 21 6 10 8 691 2 12 GDDR5128 bit 1000 64 32Radeon HD 7850M Heathrow Pro April 2012 GCN 1st gen 28 nm 640 40 16 10 675 27 10 8 864 2 GDDR5128 bit 1000 64 PCIe 3 0 16 40Radeon HD 7870M Heathrow XT 800 32 12 8 1024 2 GDDR5128 bit 1000 64 40 45Radeon HD 7970M Wimbledon XT April 2012 GCN 1st gen 28 nm 1280 80 32 20 850 68 27 2 2176 24 GDDR5256 bit 1200 153 6 PCIe 3 0 16 75vte Unified Shaders Texture Mapping Units Render Output Units The effective data transfer rate of GDDR5 is quadruple its nominal clock instead of double as it is with other DDR memory a b c d e f g h Lacks hardware video encoder IGP HD 7000G Edit Main article Radeon HD 7000 series Model Codename Launch Architecture Fab Core config a Clock rate MHz Fillrate Processing power GFLOPS Shared memoryCore MHz Boost MHz Pixel GP s Texture GT s Bus type amp width bit Clock Bandwidth GB s Radeon HD 7400G Scrapper September 2012 TeraScale 3 b 32 nm 192 12 4 327 424 1 31 3 92 125 57 DDR3128 bit 1333 to 2133 21 33 34 13Radeon HD 7420G Scrapper June 2012 128 8 4 480 655 1 92 3 84 122 88Radeon HD 7500G Scrapper May 2012 256 16 8 327 424 2 62 5 23 167 42Radeon HD 7520G Scrapper June 2012 192 12 4 496 685 1 98 5 95 190 46Radeon HD 7600G Devastator September 2012 384 24 8 320 424 2 56 7 68 245 76Radeon HD 7620G Devastator May 2012 360 497 2 88 8 64 276 48Radeon HD 7640G Devastator 256 16 8 496 685 3 97 7 94 253 95Radeon HD 7660G Devastator 384 24 8 11 9 380 93vte Unified Shaders Texture Mapping Units Render Output Units Lacks hardware video encoder Radeon HD 8000M series Edit Main article Radeon HD 8000 series Model Codename Launch Architecture Fab Core Fillrate a b c Processing power a d GFLOPS Memory e TDP W Config f Clock a MHz Texture GT s Pixel GP s Size GiB Bus type amp width bit Clock MHz Band width GB s RadeonHD 8550M 8630M Sun LE 8 January 2013 GCN 1st gen 28 nm 384 24 8 650700 5 25 6 15 616 8 537 6 1 DDR364 900 14 4 Un knownRadeonHD 8570M 8650M Sun Pro 8 January 2013 384 24 8 650700 5 25 6 15 616 8 537 6 1 GDDR564 1125 36 Un knownRadeonHD 8670M Mars XT 8 January 2013 384 24 8 775825 6 26 6 18 619 8 633 6 1 DDR364 900 14 4 Un knownRadeonHD 8690M Sun XT 8 January 2013 384 24 8 775825 6 26 6 18 619 8 633 6 1 GDDR564 1125 36 Un knownRadeonHD 8730M Mars LE 8 January 2013 384 24 8 650700 5 25 6 15 616 8 537 6 2 DDR3128 1000 32 Un knownRadeonHD 8750M Mars Pro 8 January 2013 384 24 8 620 775670 825 4 966 6 14 8819 8 514 56633 6 2 DDR3GDDR5128 1000 3264 Un knownRadeonHD 8770M Mars XT 8 January 2013 384 24 8 775825 6 26 6 18 619 8 633 6 2 GDDR5128 1125 72 Un knownRadeonHD 8790M Mars XTX 8 January 2013 384 24 8 850900 6 87 2 20 421 6 691 2 2 GDDR5128 1125 72 Un knownRadeonHD 8830M Venus LE 8 January 2013 640 40 16 575625 9 210 2325 800 2 DDR3128 1000 32 Un knownRadeonHD 8850M Venus Pro 8 January 2013 640 40 16 575 725625 775 9 212 4 2331 800992 2 DDR3GDDR5128 10001125 3272 Un knownRadeonHD 8870M Venus XT 8 January 2013 640 40 16 725775 11 612 4 2931 992 2 DDR3GDDR5128 10001125 3272 Un knownRadeonHD 8970M Neptune XT 8 January 2013 1280 80 32 850900 27 228 8 6872 2304 24 GDDR5256 1200 153 6 100vte a b c Boost values if available are stated below the base value in italic Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base or boost core clock speed Pixel fillrate is calculated as the number of Render Output Units multiplied by the base or boost core clock speed Precision performance is calculated from the base or boost core clock speed based on a FMA operation The effective data transfer rate of GDDR5 is quadruple its nominal clock instead of double as it is with other DDR memory Unified Shaders Texture Mapping Units Render Output Units Radeon M200 series Edit Main article Radeon 200 series Mobile Model Codename Launch Architecture Fab Core Fillrate a b c Processing power a d GFLOPS Memory TDPConfig e Clock a MHz Texture GT s Pixel GP s Size GiB Bus type amp width Clock MT s Band width GB s RadeonR5 M230 Jet Pro January 2014 GCN 1st gen 28 nm 320 20 8 5 780855 3 4 17 1 547 24 DDR364 bit 2000 16 Un knownRadeonR5 M255 Jet Pro June 2014 320 20 8 5 925940 7 5 18 8 601 24 DDR364 bit 2000 16 Un knownRadeonR7 M260 Topaz June 2014 384 24 8 6 620980 5 77 8 17 223 5 549 1752 6 24 DDR364 bit 18002000 14 416 Un knownRadeonR7 M260X Opal June 2014 384 24 8 6 620715 5 7 17 2 549 24 GDDR5128 bit 4000 64 Un knownRadeonR7 M265 Opal XT May 2014 384 24 8 6 725825 6 6 19 8 633 6 24 DDR364 bit 18002000 14 416 Un knownRadeonR9 M265X Venus Pro May 2014 640 40 16 10 575625 10 25 800 24 GDDR5128 bit 4500 72 td, wikipedia, wiki, book, books, library,

article

, read, download, free, free download, mp3, video, mp4, 3gp, jpg, jpeg, gif, png, picture, music, song, movie, book, game, games.
Model
(Codename) 		Launch Architecture
(Fab) 		Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS) 		Memory TDP
Config[e] Clock[a] (MHz) Texture (GT/s) Pixel (GP/s) Size (GiB) Bus type
& width 		Clock (MT/s) Band-
width (GB/s)
Radeon
R5 M230
(Jet Pro) 		January 2014 GCN 1st gen
(28 nm) 		320:20:8:5 780
855 		3.4 17.1 547 2
4 		DDR3
64-bit 		2000 16 Un­known
Radeon
R5 M255
(Jet Pro) 		June 2014 320:20:8:5 925
940 		7.5 18.8 601 2
4 		DDR3
64-bit 		2000 16 Un­known
Radeon
R7 M260
(Topaz) 		June 2014 384:24:8:6 620
980 		5.7
7.8 		17.2
23.5 		549.1
752.6 		2
4 		DDR3
64-bit 		1800
2000 		14.4
16 		Un­known
Radeon
R7 M260X
(Opal) 		June 2014 384:24:8:6 620
715 		5.7 17.2 549 2
4 		GDDR5
128-bit 		4000 64 Un­known
Radeon
R7 M265
(Opal XT) 		May 2014 384:24:8:6 725
825 		6.6 19.8 633.6 2
4 		DDR3
64-bit 		1800
2000 		14.4
16 		Un­known
Radeon
R9 M265X
(Venus Pro) 		May 2014 640:40:16:10 575
625 		10 25 800 2
4 		GDDR5
128-bit 		4500 72