List of AMD graphics processing units

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

Direct3D version note

Direct3D version indicates which graphics acceleration operations the card implements.

• Direct3D 6.0 - Multitexturing
• Direct3D 7.0 - Hardware Transformation, Clipping and Lighting (TCL/T&L)
• Direct3D 8.0 - Pixel Shader 1.1 & Vertex Shader 1.1
• Direct3D 8.1 - Pixel Shader 1.4 & Vertex Shader 1.1
• Direct3D 9.0 - Shader Model 2.0
• Direct3D 9.0b - Pixel Shader 2.0b & Vertex Shader 2.0
• Direct3D 9.0c - Shader Model 3.0, GPGPU
• Direct3D 9.0L - Windows Vista only, Direct3D 9.0c, Shader Model 3.0, Windows Graphics Foundation 1.0, DXVA 1.0, GPGPU
• Direct3D 10.0 - Windows Vista/Windows 7, Shader Model 4.0, Windows Graphics Foundation 2.0, DXVA 2.0, GPGPU
• Direct3D 10.1 - Windows Vista SP1/Windows 7, Shader Model 4.1, Windows Graphics Foundation 2.1, DXVA 2.1, GPGPU
• Direct3D 11.0 - Windows Vista SP2/Windows 7, Shader Model 5.0, Tessellation, Multithreaded rendering, Compute shaders, implemented by hardware and software running Direct3D 9/10/10.1, GPGPU
• Direct3D 11.1 - Windows 7 SP1/Windows 8, Stereoscopic 3D Rendering, GPGPU
• Direct3D 11.2 - Windows 8.1, Tiled resources, GPGPU
• Direct3D 11.3 - Windows 8.1, GPGPU
• Direct3D 12.0 - Windows 10, low-level rendering API, GPGPU

OpenGL version note

OpenGL version indicates which graphics acceleration operations the card implements.

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

Video codec acceleration

• R100 - Video Immersion
• R200 - Video Immersion II
• R300 - Video Immersion II + Video Shader
• R410 - Video Shader HD
• R420 - Video Shader HD + DXVA
• R520 - Avivo Video
• R600 - Avivo HD Video - UVD
• R700 - UVD 2, UVD 2.2
• Evergreen - UVD 2.2
• Northern Islands - UVD 3 (HD 67xx UVD 2.2)
• Southern Islands - UVD 3, Video Coding Engine
• Volcanic Islands - UVD 4.x, Video Coding Engine 2.0^[6][7]

Field explanations

The fields in the table listed below describe the following:

• Model – The marketing name for the processor assigned by ATi. Note that the ATi trademark has been replaced by AMD trademark starting with the Radeon HD 6000 series graphics processing units. Professional graphics processing units will switch to the AMD trademark as well.^[8]
• Launch – Date of release for the processor.
• Model number – Mobility VPUs are based on technology from several technology families. ATi assigns codenames based on an "MXX" model string, which does not relate to the actual technological base of the processor (represented by the R-number). Additionally, ATi is the sole supplier for all Mobility Radeon parts. For this reason, except for the Mobility Radeon 2000 series, all Mobility processors are listed on the same table.
• Code name – The internal engineering codename for the processor (typically designated by an RNXX name where N is the series number and XX is the market segment for which the product is designed. Additionally, a codename may follow the RVNXX format where "V" typically signifies a processor intended for a mainstream or value market segment).
• Fab – Fabrication process. Average feature size of components of the processor.
• Bus interface – Bus by which the graphics processor is attached to the system (typically an expansion slot, such as PCI, AGP, or PCIe).
• Memory – The reference amount of memory used by the processor.
• Core clock – The reference core clock frequency (used as some manufacturers adjust clocks lower and higher, this number will always be that listed by ATi).
• Memory clock – The reference memory clock frequency (used as some manufacturers adjust clocks lower and higher, this number will always be that listed by ATi).
• Core config – The layout of the graphics pipeline, in terms of functional units. Over time the number, type and variety of functional units in the GPU core has changed significantly; before each section in the list there is an explanation as to what functional units are present in each generation of processors.
• Performance subsection
  • Shader operations - How many operations the pixel shaders (or unified shaders in Direct3D 10 and newer GPUs) can perform. Measured in MOperations/s or GOperations/s.
  • Pixel fillrate - The number of pixels the raster operators can render to a display in one second. Measured in MPixels/s or GPixels/s.
  • Texture fillrate - The rate at which a texture can be mapped by the texture mapping units onto a polygon mesh in one second. Measured in MTextels/s or GTextels/s.
  • Vertex operations - The amount of geometry operations that can be processed on the vertex shaders in one second (only applies to Direct3D 9.0c and older GPUs). Measured in MVertices/s.
• Memory subsection
  • Bandwidth – Maximum theoretical bandwidth for the processor at factory clock with factory bus width. GB=10⁹ bytes.
  • Bus type – Type of memory bus or buses utilized.
  • Bus width – Maximum bit width of the memory bus or buses utilized. This will always be a factory bus width.
• API compliance section
  • Direct3D – Highest version of Direct3D with which the hardware is fully compliant.
  • OpenGL – Highest version of OpenGL with which the hardware is fully compliant.
• Features – Additional features that are not standard as a part of the two graphics libraries.

Comparison table: Desktop GPUs

Wonder Series

Model	Launch	Fab (µm)	Bus interface	Core config1	Memory			API compliance
					Size (KiB)	Bus type	Bus width (bit)
Wonder MDA/CGA	1986	1	PC/XT	1:1	64	SRAM	8	2D
Wonder EGA	1987	1	PC/XT	1:1	256	SRAM	8	2D
Wonder VGA	1987	1, 0.8	PC/XT, ISA	1:1	256, 512 1024	DRAM	8, 16	2D

¹ Pixel pipelines : Render output units

Mach Series

Model	Launch	Fab (µm)	Bus interface	Core config1	Memory			API compliance
					Size (KiB)	Bus type	Bus width (bit)
Mach 8	1991	0.8	ISA, MCA	1:1	512 1024	DRAM VRAM	32	2D
Mach 32	1992	0.8	ISA, EISA, VLB PCI, MCA	1:1	1024 2048	DRAM VRAM	64	2D
Mach 64	1994	0.6	ISA, VLB, PCI	1:1	1024, 2048, 4096, 8192	DRAM, VRAM, SGRAM	64	2D

¹ Pixel pipelines : Render output units

Rage Series

Model	Launch	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	November 1995	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	500	PCI	60	83	1:0:1:1	60	60	60	0	2, 4, 8	0.664	SDR	64	5.0	None2
Rage Pro	March 1997	350	AGP 2x	75	75	1:0:1:1	75	75	75	0	8, 16	0.6	SDR	64	6.0	1.1
Rage XL[9][10][11]	August 1998	350	AGP 2x, PCI	125	83	1:0:1:1	Unknown	125	125	0	8	0.664	SDR	64	6.0	1.2
Rage 128 VR	August 1998	250	AGP 2x, PCI	80	120	2:0:2:2	160	160	160	0	8, 32	0.96	SDR	64	6.0	1.2
Rage 128 GL	August 1998	250	AGP 2x, PCI	103	103	2:0:2:2	206	206	206	0	32	1.648	SDR	128	6.0	1.2
Rage 128 Pro	August 1999	250	AGP 4x, PCI	125	143	2:0:2:2	250	250	250	0	16, 32	2.288	SDR	128	6.0	1.2
Rage 128 Ultra	August 1999	250	AGP 4x, PCI	130	130	2:0:2:2	260	260	260	0	16, 32, 64	2.088	SDR	128	6.0	1.2
Rage Fury MAXX	October 1999	250	AGP 4x, PCI	125	143	2:0:2:2 x2	500	500	500	0	32	4.576	SDR	128 x2	6.0	1.2

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

Radeon R100 (7xxx) Series

• All models include Direct3D 7.0 and OpenGL 1.3

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/7000	Feb 19, 2001	RV100 (piglet)	180	AGP 4x, PCI	183	366	1:0:3:1	183	336	549	0	32, 64	2.688	DDR	64
Radeon LE/7100 (OEM)	May 1, 2001	Rage 6 / R100	180	AGP 4x	150	300	2:0:6:2	296	296	888	37	32	4.736	DDR	128
Radeon SDR/7200	June 2000	Rage 6 / R100	180	AGP 4x	166	166	2:0:6:2	333	333	996	41.5	32	2.656	SDR	128
Radeon DDR/7200	April 2000	Rage 6 / R100	180	AGP 4x	166/183A	333/366A	2:0:6:2	333/366A	333/366A	966/1098A	41.5/45.75A	32, 64	5.312/5.856A	DDR	128
Radeon DDR/7500 VIVO	2001	Rage 6 / R100	180	AGP 4x, PCI	166/183B	333/366B	2:0:6:2	333/366B	333/366B	966/1098B	41.5/45.75B	64	5.312/5.856B	DDR	128
Radeon DDR/7500 VIVO "SE"	2001	Rage 6 / R100	180	AGP 4x, PCI	200	400	2:0:6:2	400	400	1200	50.0	64	6.400	DDR	128
Radeon 7500 LE	N/A	RV200 (morpheus)	150	AGP 4x, PCI	250	350	2:0:6:2	500	500	1500	62.5	32, 64	5.600	DDR	128
Radeon 7500	Aug 14, 2001	RV200 (morpheus)	150	AGP 4x, PCI	290	460	2:0:6:2	580	580	1740	72.5	32, 64	7.360	DDR	128
Model	Launch	Code name	Fab (nm)	Bus interface	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
^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 1.4
• 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	Unknown	1.6, 2.128	DDR	64
Radeon 330	2002	RS200L (wilma)	FSB	150	200, 266	1:0:3:1	150	150	450	0	Unknown	1.6, 2.128	DDR	64
Radeon 340	2002	RS200 (wilma)	FSB	183	200, 266	1:0:3:1	183	183	549	0	Unknown	1.6, 2.128	DDR	64

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

Radeon R200 (8xxx, 9xxx) Series

• All models are manufactured with a 150 nm fabrication process
• All models include 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	Aug 14, 2001	R200 (chaplin)	AGP 4x	275	550	4:2:8:4	1100	1100	2200	137.5	64, 128	8.8	DDR	128
Radeon 8500 LE	Feb 4, 2002	R200 (chaplin)	AGP 4x	250	500	4:2:8:4	1000	1000	2000	125	64, 128	8	DDR	128
Radeon 9000	Aug 1, 2002	RV250 (iris)	AGP 4x	200	500	4:1:4:4	800	800	800	50	64, 128	8	DDR	128
Radeon 9000 Pro	Aug 1, 2002	RV250 (iris)	AGP 4x	275	550	4:1:4:4	1100	1100	1100	68.75	64, 128	8.8	DDR	128
Radeon 9100	2003	R200 (chaplin)	AGP 8x, PCI	250	500	4:2:8:4	1000	1000	2000	125	64, 128	8.0	DDR	128
Radeon 9200	Apr 1, 2003	RV280 (argus)	AGP 8x, PCI	250	400	4:1:4:4	1000	1000	1000	62.5	64, 128, 256	6.4	DDR	128
Radeon 9200 SE	July 2003	RV280 (argus)	AGP 8x, PCI	200	333	4:1:4:4	800	800	800	50	64, 128, 256	2.67	DDR	64
Radeon 9250	July 2004	RV280 (argus)	AGP 8x, PCI	240	400	4:1:4:4	960	960	960	60	64, 128, 256	6.4	DDR	128

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

IGP (9xxx Series)

• All models are manufactured with a 150 nm fabrication process
• All models include 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	0	16 - 128	3.2	DDR	64
Radeon 9100	2003	RS300 (superman)	FSB	300	400	4:1:2:2	600	600	600	0	16 - 128	6.4	DDR	128
Radeon 9100 Pro	May 3, 2004	RS350	FSB	300	400	4:1:2:2	600	600	600	0	16 - 128	6.4	DDR	128

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

Radeon R300 Series

AGP (9xxx Series)

• All models include Direct3D 9.0 and OpenGL 2.0

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 9500	Oct. 24, 2002	R300 (khan)	150	AGP 8x	275	540	4:4:4:8	1100	2200	1100	275	64, 128	8.64	DDR	128
Radeon 9500 Pro	Oct. 24, 2002	R300 (khan)	150	AGP 8x	275	540	8:4:8:8	2200	2200	2200	275	128	8.64	DDR	128
Radeon 9550	2004	RV350 (shivah)	130	AGP 8x	250	400	4:2:4:4	1000	1000	1000	125	64, 128, 256	6.4	DDR	128
Radeon 9550 SE	2004	RV350 (shivah)	130	AGP 8x	250	400	4:2:4:4	1000	1000	1000	125	64, 128, 256	3.2	DDR	64
Radeon 9600	2003	RV350 (shivah)	130	AGP 8x	325	400	4:2:4:4	1300	1300	1300	162.5	128, 256	6.4	DDR	128
Radeon 9600 Pro	2003	RV350 (shivah)	130	AGP 8x	400	600	4:2:4:4	1600	1600	1600	200	128, 256	9.6	DDR	128
Radeon 9600 SE	2003	RV350 (shivah)	130	AGP 8x	325	400	4:2:4:4	1300	1300	1300	162.5	64, 128, 256	3.2	DDR	64
Radeon 9600 XT	Sept. 30, 2003	RV360	130	AGP 8x	500	600	4:2:4:4	2000	2000	2000	250	128, 256	9.6	DDR	128
Radeon 9700	Oct. 24, 2002	R300 (khan)	150	AGP 8x	275	540	8:4:8:8	2000	2000	2000	275	128	17.28	DDR	256
Radeon 9700 Pro	July 18, 2002	R300 (khan)	150	AGP 8x	325	620	8:4:8:8	2600	2600	2600	325	128	19.84	DDR	256
Radeon 9800	2003	R350	150	AGP 8x	325	620	8:4:8:8	2600	2600	2600	325	128	19.84	DDR	256
Radeon 9800 XL	2003	R350	150	AGP 8x	350	620	8:4:8:8	2800	2800	2800	350	128	19.84	DDR	256
Radeon 9800 XXL[12]	Oct. 1, 2003	R360	150	AGP 8x	390	676	8:4:8:8	3120	3120	3120	390	128	21.60	DDR	256[12]
Radeon 9800 Pro	Mar. 1, 2003[13]	R350, R360	150	AGP 8x	380	680, 700	8:4:8:8	3040	3040	3040	380	128, 256	21.76, 22.40	DDR, GDDR2	256
Radeon 9800 SE[14]	Mar. 1, 2003[15]	R350	150	AGP 8x	325, 380[14]	540, 680[14]	4:4:4:4[15]	1300, 1520[14]	1300, 1520[14]	1300, 1520[14]	325, 380[14]	128, 256	8.64, 21.76[14]	DDR	128, 2562[14]
Radeon 9800 XT	Sept. 9, 2003	R360	150	AGP 8x	412	730	8:4:8:8	3296	3296	3296	412	256	23.36	DDR	256
Model	Launch	Code name	Fab (nm)	Bus interface	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.^[16]

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

• All models include Direct3D 9.0 and OpenGL 2.0
• All models use a PCI-E x16 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	June 21, 2004	RV370 (hari)	110	325	400	4:2:4:4	1300	1300	1300	162.5	64, 128	6.4	DDR	128
Radeon X300 LE	June 21, 2004	RV370 (hari)	110	325	400	4:2:4:4	1300	1300	1300	162.5	64, 128	6.4	DDR	128
Radeon X300 SE	June 21, 2004	RV370 (hari)	110	325	400	4:2:4:4	1300	1300	1300	162.5	64, 128	3.2	DDR	64
Radeon X300 SE HyperMemory	April 4, 2005	RV370 (hari)	110	325	600	4:2:4:4	1300	1300	1300	162.5	32, 64, 128 onboard + up to 128 system	3.2	DDR	64
Radeon X550	June 21, 2005	RV370 (hari)	110	400	500	4:2:4:4	1600	1600	1600	200	128, 256	8	DDR	128
Radeon X600 Pro	June 21, 2004	RV380 (vishnu)	130	400	600	4:2:4:4	1600	1600	1600	200	128, 256	9.6	DDR	128
Radeon X600 XT	June 21, 2004	RV380 (vishnu)	130	500	740	4:2:4:4	2000	2000	2000	250	128, 256	11.84	DDR	128
Radeon X1050	Dec. 7, 2006	RV370 (hari)	110	400	666	4:2:4:4	1600	1600	1600	200	128, 256	5.328	DDR2	64

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

IGP (X2xx, 11xx 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	Nov. 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)	4:2:2:2	600	600	600	0	16-128 system	1.6-12.8 system	DDR, DDR2	64, 128
Radeon Xpress 1150 (originally Xpress 200 for Intel)	March 11, 2005 (Intel), May 23, 2006 (AMD)	RC400, RC410, RS400, RS415, RS485	110	HT, FSB	400	200-400 (DDR), 400-800 (DDR2)	4:2:2:2	800	800	800	0	16-128 system	1.6-12.8	DDR, DDR2	64, 128

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

Radeon R400 Series

AGP (X7xx, X8xx)

• All models include AGP 8x
• 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	March 2005	RV410 (alto)	110	400	700	8:6:8:8	3200	3200	3200	600	128, 256	11.2	DDR	128
Radeon X700 Pro	March 1, 2005	RV410 (alto)	110	425	864	8:6:8:8	3400	3400	3400	637.5	128, 256	13.824	GDDR3	128
Radeon X800 SE	Oct. 2004	R420 (loki)	130	425	800	8:6:8:8	3400	6800	3400	637,5	256	25.6	GDDR3	256
Radeon X800 GT	Dec. 6, 2005	R420 (loki)	130	475	980	8:6:8:16	3800	7600	3800	712.5	256	31.36	GDDR3	256
Radeon X800	Dec. 2004	R430	110	400	700	12:6:12:16	4800	6400	4800	600	256	22.4	GDDR3	256
Radeon X800 GTO	Dec. 6, 2005	R420 (loki)	130	400	980	12:6:12:16	4800	6400	4800	600	256	31.36	GDDR3	256
Radeon X800 Pro	May 5, 2004	R420 (loki)	130	475	900	12:6:12:16	5700	7600	5700	712.5	256	28.8	GDDR3	256
Radeon X800 XL	Feb. 2, 2005	R430	110	400	980	16:6:16:16	6400	6400	6400	600	256	31.36	GDDR3	256
Radeon X800 XT	May 4, 2004	R420 (loki)	130	500	1000	16:6:16:16	8000	8000	8000	750	256	32	GDDR3	256
Radeon X800 XT PE	May 4, 2004	R420 (loki)	130	520	1120	16:6:16:16	8320	8320	8320	780	256	35.84	GDDR3	256
Radeon X850 Pro	Feb. 28, 2005	R481	130	507	1040	12:6:12:16	6084	8112	6084	760.5	256	33.28	GDDR3	256
Radeon X850 XT	Feb. 28, 2005	R481	130	520	1080	16:6:16:16	8320	8320	8320	780	256	34.56	GDDR3	256
Radeon X850 XT PE	Feb. 28, 2005	R481	130	540	1180	16:6:16:16	8640	8640	8640	810	256	37.76	GDDR3	256

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

PCI-E (X7xx, X8xx)

• All models include PCI-E x16
• 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 SE	Apr. 1, 2005	RV410 (alto)	110	400	400 500	4:6:4:8	1600	3200	1600	600	128	3.2	DDR	64
Radeon X700 LE	Dec. 21, 2004	RV410 (alto)	110	400	500	8:6:8:8	3200	3200	3200	600	128	4	DDR	64
Radeon X700	Sept. 2005	RV410 (alto)	110	400	500 700	8:6:8:8	3200	3200	3200	600	128, 256	8 11.2	DDR	128
Radeon X700 Pro	Dec. 21, 2004	RV410 (alto)	110	425	864	8:6:8:8	3400	3400	3400	637.5	128, 256	13.824	GDDR3	128
Radeon X700 XT	Never Released	RV410 (alto)	110	475	1050	8:6:8:8	3800	3800	3800	712.5	128, 256	16.8	GDDR3	128
Radeon X800 GT 128MB	Aug. 1, 2005	R423 R480 (thor)	130	475	350	8:6:8:16	3800	7600	3800	712.5	128	22.4	DDR	256
Radeon X800 GT 256MB	Aug. 1, 2005	R423 R480 (thor)	130	475	980	8:6:8:16	3800	7600	3800	712.5	256	31.36	GDDR3	256
Radeon X800	Dec. 1, 2004	R430 (thor)	110	392	700	12:6:12:16	4704	6272	4704	588	128, 256	22.4	GDDR3	256
Radeon X800 GTO 128MB	Sept. 15, 2005	R423 R480 R430 (thor)	130 110	400	700	12:6:12:16	4800	6400	4800	600	128	22.4	GDDR3	256
Radeon X800 GTO 256MB	Sept. 15, 2005	R423 R480 R430 (thor)	130 110	400	980	12:6:12:16	4800	6400	4800	600	256	31.36	GDDR3	256
Radeon X800 Pro	May 5, 2004	R423 (thor)	130	475	900	12:6:12:16	5700	7600	5700	712.5	256	28.8	GDDR3	256
Radeon X800 XL	Dec. 1, 2004 (256 MB) May 4, 2005 (512 MB)	R430 (thor)	110	400	980	16:6:16:16	6400	6400	6400	600	256, 512	31.36	GDDR3	256
Radeon X800 XT	Dec. 1, 2004	R423 (thor)	130	500	1000	16:6:16:16	8000	8000	8000	750	256	32	GDDR3	256
Radeon X800 XT Platinum Edition	May 5, 2004	R423 (thor)	130	520	1120	16:6:16:16	8320	8320	8320	780	256	35.84	GDDR3	256
Radeon X850 Pro	Dec. 1, 2004	R480 (thor)	130	507	1040	12:6:12:16	6084	8112	6084	760.5	256	33.28	GDDR3	256
Radeon X850 XT	Dec. 1, 2004	R480 (thor)	130	520	1080	16:6:16:16	8320	8320	8320	780	256	34.56	GDDR3	256
Radeon X850 XT CrossFire Master	Sept. 29, 2004	R480 (thor)	130	520	1080	16:6:16:16	8320	8320	8320	780	256	34.56	GDDR3	256
Radeon X850 XT Platinum Edition	Dec. 21, 2004	R480 (thor)	130	540	1180	16:6:16:16	8640	8640	8640	810	256	37.76	GDDR3	256
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 (GBit/s)	Bus type	Bus width (bit)
							Fillrate				Memory

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

IGP (X12xx, 21xx)

• All models include 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	Feb. 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	Aug. 29, 2006 (Intel), Feb. 28, 2007 (AMD)	RS600, RS690 (zeus)	80	FSB, HT 2.0	400	400 - 800	4:2:4:4	1600	1600	1600	200	256 - 512	6.4 - 12.8	DDR2	128
Radeon Xpress 2100	March 4, 2008	RS740 (titan)	55	HT 2.0	500	400 - 800	4:2:4:4	2000	2000	2000	250	256 - 512	6.4 - 12.8	DDR2	128

Radeon R500 (X1xxx) Series

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

Model	Launch	Code name	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Clock rate		Core config	Fillrate			Memory				TDP (W)	API support (version)		Release Price (USD)
							Core (MHz)	Memory (MHz)		Pixel (GP/s)	Vertex (GV/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Max.	Direct3D	OpenGL
Radeon X1300	Oct. 5, 2005 (PCI-E) Dec. 1, 2005 (AGP)	RV515	90	107	100	AGP 8x PCI PCI-E x16	450	250	4:2:4:4	1.800	0.225	1.800	128 256	8.00	DDR2	128		9.0c	2.0	$
Radeon X1300 HyperMemory	Oct. 5, 2005	RV515	90	107	100	PCI-E x16	450	250	4:2:4:4	1.800	0.225	1.800	128 256 512	8.00	DDR2	64		9.0c	2.0	$
Radeon X1300 PRO	Oct. 5, 2005 (PCI-E) Nov. 1, 2006 (AGP)	RV515	90	107	100	AGP 8x PCI-E x16	600	400	4:2:4:4	2.40	0.30	2.40	128 256	12.8	DDR2	128	31	9.0c	2.0	$
Radeon X1300 XT	Aug. 12, 2006	RV530	90	157	150	AGP 8x PCI-E x16	500	400	12:5:4:4	2.000	0.625	2.000	128 256	12.8	DDR2	128	22	9.0c	2.0	$
Radeon X1550	Jan. 8, 2007	RV516	90	107	100	AGP 8x PCI PCI-E x16	550	400	4:2:4:4	2.200	0.275	2.200	128 256 512	12.8	DDR2	128	27	9.0c	2.0	$
Radeon X1600 PRO	Oct. 10, 2005	RV530	90	157	150	AGP 8x PCI-E x16	500	390	12:5:4:4	2.000	0.625	2.000	128 256 512	12.48	DDR2	128	41	9.0c	2.0	$
Radeon X1600 XT	Oct. 10, 2005 (PCI-E)	RV530	90	157	150	AGP 8x PCI-E x16	590	780	12:5:4:4	2.360	0.7375	2.360	256 512	22.08	GDDR3	128	42	9.0c	2.0	$
Radeon X1650	Feb. 1, 2007	RV530	90	157	150	AGP 8x PCI-E x16	500	400	12:5:4:4	2.000	0.625	2.000	256 512	12.8	DDR2	128		9.0c	2.0	$
Radeon X1650 GT	May 1, 2007 (PCI-E) Oct. 1, 2007 (AGP)	RV560	80	330	230	AGP 8x PCI-E x16	400	400	24:8:8:8	3.20	0.80	3.20	256 512	12.8	GDDR3	128		9.0c	2.0	$
Radeon X1650 PRO	Aug. 23, 2006 (PCI-E) Oct. 15, 2006 (AGP)	RV535	80	330	131	AGP 8x PCI-E x16	600	700	12:5:4:4	2.40	0.75	2.40	256 512	22.4	GDDR3	128	44	9.0c	2.0	$
Radeon X1650 XT	Oct. 30, 2006	RV560	80	330	230	AGP 8x PCI-E x16	525	700	24:8:8:8	4.20	1.05	4.20	256 512	22.4	GDDR3	128	55	9.0c	2.0	$
Radeon X1800 CrossFire Edition	Dec. 20, 2005	R520	90	321	288	PCI-E x16	600	700	16:8:16:16	9.60	0.90	9.60	512	46.08	GDDR3	256	113	9.0c	2.0	$
Radeon X1800 GTO	Mar. 9, 2006	R520	90	321	288	PCI-E x16	500	495	12:8:12:8	6.00	1.00	6.00	256 512	32.0	GDDR3	256	48	9.0c	2.0	$
Radeon X1800 XL	Oct. 5, 2005	R520	90	321	288	PCI-E x16	500	500	16:8:16:16	8.00	1.00	8.00	256	32.0	GDDR3	256	70	9.0c	2.0	$
Radeon X1800 XT	Oct. 5, 2005	R520	90	321	288	PCI-E x16	625	750	16:8:16:16	10.0	1.25	10.0	256 512	48.0	GDDR3	256	113	9.0c	2.0	$549
Radeon X1900 CrossFire Edition	Jan. 24, 2006	R580	90	384	352	PCI-E x16	625	725	48:8:16:16	10.0	1.25	10.0	512	46.4	GDDR3	256	100	9.0c	2.0	$
Radeon X1900 GT	May 5, 2006	R580	90	384	352	PCI-E x16	575	600	36:8:12:12	6.90	1.15	6.90	256	38.4	GDDR3	256	75	9.0c	2.0	$
Radeon X1900 GT Rev. 2	Sept. 7, 2006	R580	90	384	352	PCI-E x16	512	660	36:8:12:12	6.144	1.024	6.144	256	42.64	GDDR3	256		9.0c	2.0	$
Radeon X1900 XT	Jan. 24, 2006	R580	90	384	352	PCI-E x16	625	725	48:8:16:16	10.0	1.25	10.0	256 512	46.4	GDDR3	256	100	9.0c	2.0	$299
Radeon X1900 XTX	Jan. 24, 2006	R580	90	384	352	PCI-E x16	650	775	48:8:16:16	10.4	1.30	10.4	512	49.6	GDDR3	256	135	9.0c	2.0	$399
Radeon X1950 CrossFire Edition	Aug. 23, 2006	R580+	80	384	352	PCI-E x16	650	1000	48:8:16:16	10.4	1.30	10.4	512	46.4	GDDR4	256		9.0c	2.0	$
Radeon X1950 GT	Jan. 29, 2007 (PCI-E) Feb. 10, 2007 (AGP)	RV570	80	330	230	AGP 8x PCI-E x16	500	600	36:8:12:12	6.00	1.00	6.00	256 512	38.4	GDDR3	256	57	9.0c	2.0	$140
Radeon X1950 PRO	Oct. 17, 2006 (PCI-E) Oct. 25, 2006 (AGP)	RV570	80	330	230	AGP 8x PCI-E x16	575	690	36:8:12:12	6.90	1.15	6.90	256 512	44.16	GDDR3	256	66	9.0c	2.0	$
Radeon X1950 XT	Oct. 17, 2006 (PCI-E) Feb. 18, 2007 (AGP)	R580+	80	384	352	AGP 8x PCI-E 1.0 x16	625	700 (AGP) 900 (PCI-E)	48:8:16:16	10.0	1.25	10.0	256 512	44.8 (AGP) 57.6 (PCI-E)	GDDR3	256	96	9.0c	2.0	$
Radeon X1950 XTX	Oct. 17, 2006	R580+	80	384	352	PCI-E 1.0 x16	650	1000	48:8:16:16	10.4	1.30	10.4	512	64	GDDR4	256	125	9.0c	2.0	$449
Model	Launch	Code name	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Core (MHz)	Memory (MHz)	Core config	Pixel (GP/s)	Vertex (GV/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Max.	Direct3D	OpenGL	Release Price (USD)
							Clock rate			Fillrate			Memory				TDP (W)	API support (version)

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

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

• It includes a data-parallel process (DPP) array, a command processor, a memory controller and other logic.^[17]

Radeon HD 2xxx

Model	Launch	Code name	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Clock rate		Core config	Fillrate		Memory				Processing Power (GFLOPS)		TDP (W)		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 2350	Jun 28, 2007	RV610	65	180	85	PCIe 1.0 ×16 AGP	525	400	40:4:4	2.10	2.10	256	6.40	DDR2	32	42.0	No		20	10.0	3.3	No	?
Radeon HD 2400 PRO	Jun 28, 2007	RV610	65	180	85	PCIe 1.0 ×16 AGP PCI	525	400	40:4:4	2.10	2.10	128 256 512	6.40	DDR2	64	42.0	No		20	10.0	3.3	No	?
Radeon HD 2400 XT	Jun 28, 2007	RV610	65	180	85	PCIe 1.0 ×16	650	500 700	40:4:4	2.60	2.60	256	8.0 11.2	DDR2 GDDR3	64	52.0	No		25	10.0	3.3	No	?
Radeon HD 2600 PRO	Jun 28, 2007	RV630	65	390	153	PCIe 1.0 ×16 AGP	600 600	500 700	120:8:4	2.40	4.80	256 512	16.0 21.9	DDR2 GDDR3	128	144.0	No		35	10.0	3.3	No	?
Radeon HD 2600 XT	Jun 28, 2007	RV630	65	390	153	PCIe 1.0 ×16 AGP	800 800	800 1100	120:8:4	3.20	6.40	256 512	22.4 35.2	GDDR3 GDDR4	128	192.0	No		45 50	10.0	3.3	No	?
Radeon HD 2900 GT	Nov 6, 2007	R600 GT	80	720	420	PCIe 1.0 ×16	601	800	240:12:12	7.21	7.21	256 512	51.2	GDDR3	256	288.5	No		150	10.0	3.3	No	?
Radeon HD 2900 PRO	Sep 25, 2007	R600 PRO	80	720	420	PCIe 1.0 ×16	600 600	800 925	320:16:16	9.6	9.6	512 1024	51.2 102.4 118.4	GDDR3 GDDR4	256 512	384.0	No		200	10.0	3.3	No	?
Radeon HD 2900 XT	May 14, 2007	R600 XT	80	720	420	PCIe 1.0 ×16	743 743	828 1000	320:16:16	11.9	11.9	512 1024	105.6 128.0	GDDR3 GDDR4	512	475.5	No		215	10.0	3.3	No	?

Radeon HD 3xxx

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

IGP (HD 3xxx)

• All Radeon HD 3xxx 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[18]	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)	N/A	N/A	28	AVIVO
Radeon 3100 Graphics (780V Chipset)	2008 Jan 23 (China) Mar 4 (Worldwide)	RS780C
Radeon HD 3200 Graphics (780G Chipset)		RS780						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, 8x 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	UVD2, PowerPlay

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

All-in-Wonder Series

Model	Launch	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate			Memory				API (version)
								MPixels/s	MTextels/s	MVertices/s	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
All-in-Wonder Radeon	Jul 31, 2000	R100	180	AGP 4x	166	332	2:1:6:2	332	996	41.5	32	5.312	DDR	128	7.0	1.4
All-in-Wonder 7500	Jan 22, 2002	RV200	150	AGP 4x	260	360	2:0:6:2	520	1560	0	64	11.52	DDR	128	7.0	1.4
All-in-Wonder VE	Dec 2, 2002	RV200	150	AGP 4x	250	500	2:0:6:2	500	1500	0	64	8	DDR	128	7.0	1.4
All-in-Wonder 8500	Apr 4, 2002	R200	150	AGP 4x	260	550	4:2:8:4	1100	2200	137.5	128	8.8	DDR	128	8.1	1.4
All-in-Wonder 8500 DV	Aug 30, 2001	R200	150	AGP 4x	230	380	4:2:8:4	920	1840	115	64	6.08	DDR	128	8.1	1.4
All-in-Wonder 9000 Pro	Mar 31, 2003	RV250	150	AGP 8x	275	550	4:1:4:4	1110	1110	68.75	64, 128	8.8	DDR	128	8.1	1.4
All-in-Wonder 9200	Jan 26, 2004	RV250	150	AGP 8x	250	400	4:1:4:4	1000	1000	62.5	128	6.4	DDR	128	8.1	1.4
All-in-Wonder 9200 SE	N/A	RV250	150	AGP 8x	250	332	4:1:4:4	1000	1000	62.5	128	2.656	DDR	64	8.1	1.4
All-in-Wonder 9600	Jan 26, 2004	RV350	130	AGP 8x	325	400	4:2:4:4	1300	1300	162.5	128	6.4	DDR	128	9.0	2.0
All-in-Wonder 9600 Pro	Aug 05, 2003	RV350	130	AGP 8x	400	650	4:2:4:4	1600	1600	200	128	10.4	DDR	128	9.0	2.0
All-in-Wonder 9600 XT	Jan 26, 2004	RV360	130	AGP 8x	525	650	4:2:4:4	2100	2100	262.5	128	10.4	DDR	128	9.0	2.0
All-in-Wonder 9700 Pro	Dec 30, 2002	R300	150	AGP 8x	325	620	8:4:8:8	2600	2600	325	128	19.84	DDR	256	9.0	2.0
All-in-Wonder 9800 Pro	Apr 7, 2003	R350	150	AGP 8x	380	680	8:4:8:8	3040	3040	380	128	21.76	DDR	256	9.0	2.0
All-in-Wonder 9800 SE	Nov 1, 2003	R350	150	AGP 8x	380	680	4:4:4:8	3040	1520	380	128	10.88	DDR	128	9.0	2.0
All-in-Wonder X600 Pro	Sept 21, 2004	RV370	110	AGP 8x	400	600	4:2:4:4	1600	1600	200	256	9.6	DDR	128	9.0	2.0
All-in-Wonder X800 GT	Aug 8, 2005	R430	110	PCI-E x16	490	980	8:6:8:16	6400	3200	600	128	31.36	GDDR3	256	9.0b	2.0
All-in-Wonder X800 XL	Jul 5, 2005	R430	110	PCI-E x16	400	980	16:6:16:16	6400	6400	600	256	31.36	GDDR3	256	9.0b	2.0
All-in-Wonder X800 XT	Sept 9, 2004	R420	130	AGP 8x	500	1000	16:6:16:16	8000	8000	750	256	32	GDDR3	256	9.0b	2.0
All-in-Wonder 2006	Dec 22, 2005	RV515	90	PCI-E x16	450	800	4:2:4:4	1800	1800	225	256	12.8	DDR2	128	9.0c	2.0
All-in-Wonder X1800 XL	Nov 21, 2005	R520	90	PCI-E x16	500	1000	16:8:16:16	8000	8000	1000	256	32	GDDR3	256	9.0c	2.0
All-in-Wonder X1900	Jan 24, 2006	R580	90	PCI-E x16	500	960	48:8:16:16	8000	8000	1000	256	30.72	GDDR3	256	9.0c	2.0
All-in-Wonder HD 3650	Jun 28, 2008	RV635	55	PCI-E x16	725	1200	120:8:4	2900	5800	N/A	512	19.2	DDR2	128	10.1	3.3

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

Radeon R700 (HD 4xxx) Series

Model4	Launch	Code name	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Clock rate		Core config1	Fillrate		Memory2				Processing Power (GFLOPS)		TDP3 (W)		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	Sep 30, 2008	RV710	55	242	73	PCIe 2.0 ×16 PCIe 2.0 ×1 AGP 8×	600	400	80:8:4	2.40	4.80	256 512 1024	6.40	DDR2	64	92.0	No		20	10.1	3.3	1.0	?
Radeon HD 4550	Sep 30, 2008	RV710	55	242	73	PCIe 2.0 ×16	600 600	655 800	80:8:4	2.40	4.80	256 512 1024	10.5 12.8	DDR2 GDDR3	64	96.0	No		25	10.1	3.3	1.0	?
Radeon HD 4570	Nov 25, 2008	RV710	55	242	73	PCIe 2.0 ×16	650	500	80:8:4	2.60	5.20	1024	8.00	DDR2	64	104.0	No		25	10.1	3.3	1.0	?
Radeon HD 4580	Nov 20, 2011	RV635 PRO	55	378	135	PCIe 2.0 ×16	796	693	120:8:4	3.18	6.37	512	22.2	GDDR3	128	191.0	No		65	10.1	3.3	1.0	?
Radeon HD 4650	Sep 10, 2008	RV730 PRO	55	514	146	PCIe 2.0 ×16 AGP 8×	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	10.1	3.3	1.0	?
Radeon HD 4670	Sep 10, 2008	RV730 XT	55	514	146	PCIe 2.0 ×16 AGP 8×	750 750	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	10.1	3.3	1.0	?
Radeon HD 4730	Jun 8, 2009	RV770 CE	55	956	256	PCIe 2.0 ×16	700 750	900 900	640:32:8	5.60 6.00	22.4 24.0	512	57.6	GDDR5	128	896.0 960.0	179.2 192.0		110	10.1	3.3	1.0	?
Radeon HD 4750	Sep 9, 2009	RV740	40	826	137	PCIe 2.0 ×16	730	800	640:32:16	11.7	23.4	512	51.2	GDDR5	128	934.4			80	10.1	3.3	1.0	?
Radeon HD 4770	Apr 28, 2009	RV740	40	826	137	PCIe 2.0 ×16	750	800	640:32:16	12.0	24.0	512	51.2	GDDR5	128	960.0	192.0		80	10.1	3.3	1.0	?
Radeon HD 4810	May 28, 2009	RV770 CE	55	956	256	PCIe 2.0 ×16	625 750	900 900	640:32:8	5.00 6.00	20.0 24.0	512	57.6	GDDR5	128	800.0 960.0	160.0 192.0		95	10.1	3.3	1.0	?
Radeon HD 4830	Oct 21, 2008	RV770 LE	55	956	256	PCIe 2.0 ×16	575	900	640:32:16	9.20	18.4	512 1024	57.6	GDDR3 GDDR4	256	736.0	147.2		95	10.1	3.3	1.0	?
Radeon HD 4850	Jun 25, 2008	RV770 PRO	55	956	256	PCIe 2.0 ×16	625	993	800:40:16	10.0	25.0	512 1024 2048	63.55	GDDR3 GDDR4	256	1000	200.0		110	10.1	3.3	1.0	199
Radeon HD 4860	Sep 9, 2009	RV790 GT	55	959	282	PCIe 2.0 ×16	700	750	640:32:16	11.2	22.4	512 1024	96	GDDR5	256	896.0	179.2		130	10.1	3.3	1.0	?
Radeon HD 4870	Jun 25, 2008	RV770 XT	55	956	256	PCIe 2.0 ×16	750	900	800:40:16	12.0	30.0	512 1024 2048	115.2	GDDR5	256	1200	240.0		150	10.1	3.3	1.0	299
Radeon HD 4890	Apr 2, 2009	RV790 XT	55	959	282	PCIe 2.0 ×16	850	975	800:40:16	13.6	34.0	1024 2048	124.8	GDDR5	256	1360	272.0		190	10.1	3.3	1.0	?
Radeon HD 4850 X2	Nov 7, 2008	R700	55	956×2	256×2	PCIe 2.0 ×16	625	995	800:40:16×2	10.0×2	25.0×2	512×2 1024×2	63.7×2	GDDR3	256x2	2000	400.0		250	10.1	3.3	1.0	339
Radeon HD 4870 X2	Aug 12, 2008	R700	55	956×2	256×2	PCIe 2.0 ×16	750	900	800:40:16×2	12×2	30×2	1024×2	115.2×2	GDDR5	256x2	2400	480.0		286	10.1	3.3	1.0	399
Model4	Launch	Code name	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Clock rate		Core config1	Fillrate		Memory2				Processing Power (GFLOPS)		TDP3 (W)		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 & PowerPlay.

IGP (HD 4xxx)

• All Radeon HD 4xxx IGP models include Direct3D 10.1 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 HD 4200 Graphics (785G Chipset)	Aug 2009	RS880	RV620	55	>205	~73 (~9 × 8.05)	HT 3.0	500	40:4:4	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.

Evergreen (HD 5xxx) Series

• The HD5xxx series is the last series of AMD GPUs which supports two analogue CRT-monitors with a single graphics card (i.e. with two RAM-DACs) AMD Eyefinity introduced.

Model4	Launch	Code name	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Clock rate		Core config1	Fillrate		Memory2				Processing Power (GFLOPS)		TDP3 (W)		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 PRO	40	292	59	PCIe 2.1 x16 PCI-classic 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	No	6.4	19.1	11.0	4.4	1.2	~50
Radeon HD 5550	Feb 9, 2010	Redwood LE	40	627	104	PCIe 2.1 x16	550 550 550	400 800 800	320:16:8	4.4	8.8	512 1024 2048	12.8 25.6 51.2	DDR2 GDDR3 GDDR5	128	352	No	10	39	11.0	4.4	1.2	~70
Radeon HD 5570	Feb 9, 2010	Redwood PRO	40	627	104	PCIe 2.1 x16	650 650	400 900	400:20:8	5.2	13.0	512 1024 2048	12.8 28.8 57.6	DDR2 GDDR3 GDDR5	128	520	No	10	39	11.0	4.4	1.2	80
Radeon HD 5610	May 14, 2011	Redwood PRO	40	627	104	PCIe 2.1 x16	650	500	400:20:8	5.2	13.0	1024	16.0	GDDR3	128	520			39	11.0	4.4	1.2
Radeon HD 5670	Jan 14, 2010	Redwood XT	40	627	104	PCIe 2.1 x16	775 775	800 1000	400:20:8	6.2	15.5	512 1024 2048	25.6 64.0	GDDR3 GDDR5	128	620	No	15	64	11.0	4.4	1.2	99
Radeon HD 5750	Oct 13, 2009	Juniper PRO	40	1040	170	PCIe 2.1 x16	700 700	1150 1150	720:36:16	11.2	25.2	512 1024	73.6	GDDR5	128	1008	No	16	86	11.0	4.4	1.2	129
Radeon HD 5770	Oct 13, 2009	Juniper XT	40	1040	170	PCIe 2.1 x16	850 850	1200 1200	800:40:16	13.6	34.0	512 1024	76.8	GDDR5	128	1360	No	18	108	11.0	4.4	1.2	159
Radeon HD 5830	Feb 25, 2010	Cypress LE	40	2154	334	PCIe 2.1 x16	800	1000	1120:56:16	12.8	44.8	1024	128.0	GDDR5	256	1792	358.4	25	175	11.0	4.4	1.2	239
Radeon HD 5850	Sep 30, 2009	Cypress PRO	40	2154	334	PCIe 2.1 x16	725 725	1000 1000	1440:72:32	23.2	52.2	1024 2048	128.0	GDDR5	256	2088	417.6	27	151	11.0	4.4	1.2	259
Radeon HD 5870	Sep 23, 2009	Cypress XT	40	2154	334	PCIe 2.1 x16	850 850	1200 1200	1600:80:32	27.2	68.0	1024 2048	153.6	GDDR5	256	2720	544	27	188 228	11.0	4.4	1.2	379
Radeon HD 5870 Eyefinity Edition5	Mar 11, 2010	Cypress XT	40	2154	334	PCIe 2.1 x16	850	1200	1600:80:32	27.2	68.0	2048	153.6	GDDR5	256	2720	544	27	228	11.0	4.4	1.2	479
Radeon HD 5970	Nov 18, 2009	Hemlock XT	40	2154×2	334×2	PCIe 2.1 x16	725 725	1000 1000	1600:80:32×2	46.4	116.0	1024×2 2048×2	128×2	GDDR5	256×2	4640	928	51	294	11.0	4.4	1.2	599
Model4	Launch	Code name	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Core (MHz)	Memory (MHz)	Core config1	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	Release Price (USD)
							Clock rate			Fillrate		Memory2				Processing Power (GFLOPS)		TDP3 (W)		API support (version)

¹ Unified shaders : Texture mapping units : Render output units
² The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as 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 cards feature Angle independent anisotropic filtering and Eyefinity capabilities. Each have up to 3 outputs (Eyefinity Edition allows more than 3 simultaneous outputs)^5
5 The Radeon HD 5870 Eyefinity Edition card allows six mini DisplayPort outputs, all of which can be simultaneously active.^[19]

Radeon HD 6xxx Series

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

Model	Launch	Code name	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Clock rate		Core config1	Fillrate		Memory2				Processing Power (GFLOPS)		TDP3 (W)		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 6350	Apr 7, 2011	Cedar	40	292	59	PCIe 2.1 ×16	650	800	80:8:4	2.6	5.2	512	12.8	DDR3	64	104	No	6.4	19.1	11.0	4.4	1.2	$23
Radeon HD 6450	Feb 7, 2011 (OEM)	Caicos	40	370	67	PCIe 2.1 ×16	625 750	533 800	160:8:4	2.5 3.0	5.0 6.0	512	8.5 12.8	DDR3	64	200 240	No	9	18 27	11.0	4.4	1.2	OEM
Radeon HD 6450	Apr 7, 2011	Caicos	40	370	67	PCIe 2.1 ×16	625 750	800 900	160:8:4	2.5 3.0	5.0 6.0	512 1024 2048	12.8 14.4	DDR3	64	200 240	No	9	18 27	11.0	4.4	1.2	$55
Radeon HD 6570	Feb 7, 2011 (OEM)	Turks PRO	40	716	118	PCIe 2.1 ×16	650	900	480:24:8	5.2	15.6	1024	28.8	DDR3	128	624	No	10	44	11.0	4.4	1.2	OEM
Radeon HD 6570	Apr 19, 2011	Turks PRO	40	716	118	PCIe 2.1 ×16	650 650	667 1000	480:24:8	5.2	15.6	2048 4096	21.3 64.0	DDR3 GDDR5	128	624	No	11	60	11.0	4.4	1.2	$79
Radeon HD 6670	Apr 19, 2011	Turks XT	40	716	118	PCIe 2.1 ×16	800 800	800 1000	480:24:8	6.4	19.2	512 1024 2048	25.6 64.0	DDR3 GDDR5	128	768	No	12	66	11.0	4.4	1.2	$99
Radeon HD 6750	Jan 21, 2011 (OEM)	Juniper PRO	40	1040	166	PCIe 2.1 ×16	700 700	1150 1150	720:36:16	11.2	25.2	512 1024	73.6	GDDR5	128	1008	No	16	86	11.0	4.4	1.2	OEM
Radeon HD 6770	Apr 19, 2011	Juniper XT	40	1040	166	PCIe 2.1 ×16	850 850	1200 1050	800:40:16	13.6	34.0	512 1024	76.8 67.2	GDDR5	128	1360	No	18	108	11.0	4.4	1.2	?
Radeon HD 6790	Apr 4, 2011	Barts LE	40	1700	255	PCIe 2.1 ×16	840	1050	800:40:16	13.4	33.6	1024	134.4	GDDR5	256	1344	No	19	150	11.0	4.4	1.2	$149
Radeon HD 6850	Oct 22, 2010	Barts Pro	40	1700	255	PCIe 2.1 ×16	775	1000	960:48:32	24.8	37.2	1024	128.0	GDDR5	256	1488	No	19	127	11.0	4.4	1.2	$179
Radeon HD 6870		Barts XT	40	1700	255	PCIe 2.1 ×16	900	1050	1120:56:32	28.8	50.4	1024 2048	134.4	GDDR5	256	2016	No	19	151	11.0	4.4	1.2	$239
Radeon HD 6930	Dec 2011	Cayman CE	40	2640	389	PCIe 2.1 ×16	750 750	1200 1200	1280:80:32	24.0	60.0	1024 2048	153.6	GDDR5	256	1920	480	18	186	11.0	4.4	1.2	$180
Radeon HD 6950	Dec 15, 2010	Cayman Pro	40	2640	389	PCIe 2.1 ×16	800 800	1250 1250	1408:88:32	25.6	70.4	1024 2048	160.0	GDDR5	256	2253	563	20	200	11.0	4.4	1.2	$259 $299
Radeon HD 6970		Cayman XT	40	2640	389	PCIe 2.1 ×16	880	1375	1536:96:32	28.2	84.5	2048	176.0	GDDR5	256	2703	675	20	250	11.0	4.4	1.2	$369
Radeon HD 6990	Mar 8, 2011	Antilles XT	40	2640×2	389×2	PCIe 2.1 ×16	830	1250	1536:96:32×2	26.5×2	79.6×2	2048×2	160.0×2	GDDR5	256×2	5099	1276.88	37	375	11.0	4.4	1.2	$699
Model	Launch	Code name	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Core (MHz)	Memory (MHz)	Core config1	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	Release Price (USD)
							Clock rate			Fillrate		Memory2				Processing Power (GFLOPS)		TDP3 (W)		API support (version)

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

IGP (HD 6xxx)

• All models include Direct3D 11, OpenGL 4.1 and OpenCL 1.2
• All models feature the UNB/MC Bus interface
• All models do not feature double-precision FP
• All models feature Angle independent anisotropic filtering, UVD3, and AMD Eyefinity capabilities, with up to three outputs.
• All models feature 3D Blu-ray Disc acceleration.
• All models are based on TeraScale 2 (VLIW5)

Model	Released	Code name	Fab (nm)	Core Clock (MHz)	Core config1	Fillrate		Shared Memory			Processing Power (GFLOPS)	Max. Combined TDP2 (W)	AMD APU
						Pixel (GP/s)	Texture (GT/s)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon HD 6370D	Q4 2011	WinterPark	32	443	160:8:4	1.77	3.54	25.6	DDR3-1600	128	142	65	E2-3200
Radeon HD 6410D	Jun 20, 2011[20]	WinterPark		600	160:8:4	2.4	4.8	29.9	DDR3-1866		192	65	A4-3300 A4-3400
Radeon HD 6530D	Jun 20, 2011[20]	BeaverCreek		443	320:16:8	3.54	7.08				284	65 - 100	A6-3500 A6-3600 A6-3620 A6-3650 A6-3670K
Radeon HD 6550D	Jun 20, 2011	BeaverCreek		600	400:20:8	4.8	12				480	65 - 100	A8-3800 A8-3820 A8-3850 A8-3870K

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

Radeon HD 7xxx Series

• All models up to including HD 76xx based on TeraScale 2 (VLIW5), HD 77xx - 79xx are based on GCN 1.0 (Graphics Core Next) architecture except the HD 7790 which is based on GCN 1.1.
• Only the Bonaire (GCN 1.1) based HD 7xx0-series supports OpenCL 2.0. GCN 1.0 devices do not support the complete OpenCL 2.0 profile at this time.^[21][22]
• GPUs based on the GCN (Graphics Core Next) architecture, all support Direct X 11.2 with the latest drivers (Initially came with Direct3D 11.1 support) and also support the Mantle API.
• HD 7790 model is designed more like the 7800/7900 models rather than the 7700 featuring 2x primitive rate instead of 1x which is found in the other 7700 cards.^[23]
• Bonaire is in the Caribbean Sea, Malta is in the Mediterranean Sea. These parts are reverse rebranded out of the Sea Island Series to appear in the 7000 Series in 2013.
• Bonaire XT is the only card in the 7000 series to support True Audio.
• The HD 7990 "Malta" was discontinued few months after its release.
• According to AMD CodeXL, HD 7990's code name is New Zealand.

Model	Launch	Code name	Architecture	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Clock rate			Core config1	Fillrate		Memory2				Processing Power (GFLOPS)		TDP3 (W)		API support (version)			Release Price (USD)
								Core (MHz)	Boost (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 7350	Jan 2012 (OEM)	Cedar	TeraScale 2	40	292	59	PCIe 2.1 ×16	400 650		400 800 900	80:8:4	1.6 2.6	3.2 5.2	256 512	6.4 12.8	DDR2 DDR3	64	104	No	6.4	19.1	11.0	4.4	1.2	OEM
Radeon HD 7450	Jan 2012 (OEM)	Caicos	TeraScale 2	40	370	67	PCIe 2.1 ×16	625 750		533 800	160:8:4	2.5 3.0	5.0 6.0	512 1024	8.5 12.8	GDDR3	64	200 240	No	9	18	11.0	4.4	1.2	OEM
Radeon HD 7470	Jan 2012 (OEM)	Caicos	TeraScale 2	40	370	67	PCIe 2.1 ×16	625 775		800 900	160:8:4	2.5 3.1	5.0 6.2	512 1024	12.8 14.4	GDDR3 GDDR3	64	200 248	No	9	27	11.0	4.4	1.2	OEM
Radeon HD 7510	Feb 2013 (OEM)	Turks LE	TeraScale 2	40	716	118	PCIe 2.1 ×16	650		667	320:16:4	2.6	10.4	1024	21.3	GDDR3	128	416	No			11.0	4.4	1.2	OEM
Radeon HD 7570	Jan 2012 (OEM)	Turks PRO-L	TeraScale 2	40	716	118	PCIe 2.1 ×16	650		900 1000	480:24:8	5.2	15.6	512 1024	28.8 64	GDDR3 GDDR5	128	624	No	10 11	44 60	11.0	4.4	1.2	OEM
Radeon HD 7670	Jan 2012 (OEM)	Turks XT	TeraScale 2	40	716	118	PCIe 2.1 ×16	800		1000	480:24:8	6.4	19.2	512 1024	64	GDDR5	128	768	No	12	66	11.0	4.4	1.2	OEM
Radeon HD 7730	April, 2013	Cape Verde LE	GCN 1.0	28	1500	123	PCIe 3.0 ×16	800		1125	384:24:8	6.4	19.2	1024	25.6 72	GDDR3 GDDR5	128	614.4	38.4	10	47	11.2	4.4	1.2[21][22]	$60
Radeon HD 7750	Feb 15, 2012	Cape Verde PRO	GCN 1.0	28	1500	123	PCIe 3.0 ×16	800 900		800 1125	512:32:16	12.8 14.4	25.6 28.8	1024 2048 4096	25.6 72	GDDR3 GDDR5	128	819.2 921.6	51.2 57.6	10	55	11.2	4.4	1.2	$110
Radeon HD 7770 GHz Edition	Feb 15, 2012	Cape Verde XT	GCN 1.0	28	1500	123	PCIe 3.0 ×16	1000		1125	640:40:16	16	40	1024 2048	72	GDDR5	128	1280	80	10	80	11.2	4.4	1.2	$160
Radeon HD 7790	Mar 22, 2013	Bonaire XT	GCN 1.1	28	2080	160	PCIe 3.0 ×16	1000		1500	896:56:16	16.0	56.0	1024 2048	96	GDDR5	128	1792	128	10	85	11.2	4.4	2.0[21][22]	$150
Radeon HD 7850	Mar 19, 2012	Pitcairn PRO	GCN 1.0	28	2800	212	PCIe 3.0 ×16	860		1200	1024:64:32	27.52	55.04	1024 2048	153.6	GDDR5	256	1761.28	110.08	10	130	11.2	4.4	1.2	$250
Radeon HD 7870 GHz Edition	Mar 19, 2012	Pitcairn XT	GCN 1.0	28	2800	212	PCIe 3.0 ×16	1000		1200	1280:80:32	32	80	2048	153.6	GDDR5	256	2560	160	10	175	11.2	4.4	1.2	$350
Radeon HD 7870 XT	Nov 19, 2012	Tahiti LE	GCN 1.0	28	4313	352	PCIe 3.0 ×16	925	975	1500	1536:96:32	29.6	88.8	2048	192.0	GDDR5	256	2841.6 2995.2	710.4 748.8	15	185	11.2	4.4	1.2	$270
Radeon HD 7950	Jan 31, 2012	Tahiti PRO Tahiti PRO-H	GCN 1.0	28	4313	352	PCIe 3.0 ×16	800		1250	1792:112:32	25.6	89.6	3072	240	GDDR5	384	2867.2	717	15	200	11.2	4.4	1.2	$450
Radeon HD 7950 Boost	Aug 14, 2012	Tahiti PRO2 Tahiti PRO-H2	GCN 1.0	28	4313	352	PCIe 3.0 ×16	850	925	1250	1792:112:32	29.6	103.6	3072	240	GDDR5	384	3046.4 3315.2	761.6 828.8	15	225	11.2	4.4	1.2	$330
Radeon HD 7970	Jan 9, 2012	Tahiti XT	GCN 1.0	28	4313	352	PCIe 3.0 ×16	925		1375	2048:128:32	29.6	118.4	3072 6144	264	GDDR5	384	3788.8	947.2	15	250	11.2	4.4	1.2	$550
Radeon HD 7970 GHz Edition	Jun 22, 2012	Tahiti XT2	GCN 1.0	28	4313	352	PCIe 3.0 ×16	1000	1050	1500	2048:128:32	32	128.0	3072 6144	288	GDDR5	384	4096 4300	1024 1075	15	250	11.2	4.4	1.2	$500
Radeon HD 7990	Apr 24, 2013	New Zealand	GCN 1.0	28	4313 ×2	352 ×2	PCIe 3.0 ×16	950	1000	1500	2048:128:32 ×2	32 ×2	128 ×2	3072 ×2	288 ×2	GDDR5	384 ×2	8200	1894	15	375	11.2	4.4	1.2	$1000
Model	Launch	Code name	Architecture	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Core (MHz)	Boost (MHz)	Memory (MHz)	Core config1	Pixel (GP/s)	Texture (GT/s)	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Double Precision	Idle	Max.	Direct3D	OpenGL	OpenCL	Release Price (USD)
								Clock rate				Fillrate		Memory2				Processing Power (GFLOPS)		TDP3 (W)		API support (version)

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

IGP (HD 7xxx)

• All models include Direct3D 11, OpenGL 4.4 and OpenCL 1.2
• All models feature the UNB/MC Bus interface
• All models do not support double-precision FP
• All models feature angle independent anisotropic filtering, UVD3.2, and Eyefinity capabilities, with up to four outputs.
• All models are based on the TeraScale 3 (VLIW4) used in the Radeon HD 69xx Series (Cayman) GPUs.

Model	Released	Code name	Fab (nm)	Core Clock (MHz)	Core config	Fillrate		Shared Memory			Processing Power (GFLOPS)	Combined TDP1 (W)		APU
						Pixel (GP/s)	Texture (GT/s)	Bandwidth (GB/s)	Bus type	Bus width (bit)		Idle	Max.
Radeon HD 7480D	June 1, 2012	Scrapper	32	723	128:8:4	2.87	5.76	25.6	DDR3-1600	128	185	Unknown	65	A4-4000 A4-5300
Radeon HD 7540D	June 1, 2012	Devastator	32	760	192:12:4	3.02	9.12	29.9	DDR3-1866	128	292	Unknown	65	A6-5400K
Radeon HD 7560D	June 1, 2012	Devastator	32	760	256:16:8	6.08	12.16	29.9	DDR3-1866	128	389	Unknown	65 - 100	A8-5500 A8-5600K
Radeon HD 7660D	June 1, 2012	Devastator	32	760 800	384:24:8	6.08 6.4	18.24 19.2	29.9	DDR3-1866	128	584 614	Unknown	65 - 100	A10-5700 (760 MHz) A10-5800K (800 MHz)

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

Radeon HD 8xxx Series

• All models up to including HD 84xx based on TeraScale 2 (VLIW5), HD 85xx and later are based on Graphics Core Next architecture.
• HD 8570 & HD 8670 will now feature 256 KB L2 read/write cache^[24]
• all non-OEM versions are shifted into Q4 2013^[25]

Model	Launch	Code name	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Clock rate			Core config	Fillrate		Memory				Processing Power (GFLOPS)		TDP (W)		API support (version)			Release Price (USD)
							Core (MHz)	Boost (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Double Precision	Idle	Max.	Direct3D	OpenGL	OpenCL
Radeon HD 8350 (OEM)	2013	Cedar	40	292	59	PCIe 2.1 ×16	400 - 650		400 800	80:8:4	1.6 2.6	3.2 5.2	256 512	6.4 12.8	DDR2 DDR3	64	104	No	6.4	19.1	11.0	4.4	1.2	OEM
Radeon HD 8450 (OEM)	2013	Caicos	40	370	67	PCIe 2.1 ×16	625		533	160:8:4	2.5	5.0	512	8.53	DDR3	64	200	No	9	18	11.0	4.4	1.2	OEM
Radeon HD 8470 (OEM)	2013	Caicos	40	370	67	PCIe 2.1 ×16	750		800	160:8:4	3.0	6.0	1024	25.6	GDDR5	64	240	No	9	35	11.0	4.4	1.2	OEM
Radeon HD 8490 (OEM)	2013	Caicos	40	370	67	PCIe 2.1 ×16	875		900	160:8:4	3.5	7.0	1024	28.8	GDDR5	64	280	No	9	35	11.0	4.4	1.2	OEM
Radeon HD 8570 (OEM)	2013	Oland	28	1040	90	PCIe 3.0 ×8	730		900 1150	384:24:8	6.4	19.2	2048	28.8 72	DDR3 GDDR5	128	560	35	12	66	11.1	4.4	2.0[21]	OEM
Radeon HD 8670 (OEM)	2013	Oland	28	1040	90	PCIe 3.0 ×8	1000		1150	384:24:8	8	24	2048	72	GDDR5	128	768	48	16	86	11.1	4.4	2.0[21]	OEM
Radeon HD 8730	Sep 5th, 2013	Cape Verde LE	28	1500	123	PCIe 3.0 ×16	800		1125	384:24:8	6.4	19.2	1024	72	GDDR5	128	614.4	44.8	10	47	11.1	4.4	1.2
Radeon HD 8760 (OEM)	2013	Cape Verde XT	28	1500	123	PCIe 3.0 ×16	1000		1125	640:40:16	16	40	2048	72	GDDR5	128	1280	80	16	80	11.1	4.4	1.2	OEM
Radeon HD 8770	2013	Bonaire XT	28	2080	160	PCIe 3.0 ×16	1000		1500	896:56:16	16.0	56.0	2048	96	GDDR5	128	1792	128	10	85	11.1	4.4	1.2	?
Radeon HD 8870 (OEM)[26]	2013	Pitcairn XT	28	2800	212	PCIe 3.0 ×16	1000		1200	1280:80:32	32	80	2048	153.6	GDDR5	256	2560	160	15	150	11.1	4.4	1.2	OEM
Radeon HD 8950 (OEM)	2013	Tahiti Pro	28	4313	352	PCIe 3.0 ×16	850	925	1250	1792:112:32	27.2 29.6	95.2 103.6	3072	240	GDDR5	384	3046.4 3315.2	761.6 828.8	15	225	11.1	4.4	2.0[21]	OEM
Radeon HD 8970 (OEM)	2013	Tahiti XT2	28	4313	352	PCIe 3.0 ×16	1000	1050	1500	2048:128:32	32 33.6	128.0 134.4	3072	288	GDDR5	384	4096 4301	1024 1075	15	250	11.1	4.4	1.2	OEM
Radeon HD 8990 (OEM)	2013	Malta	28	4313 x2	352 x2	PCIe 3.0 ×16	950	1000	1500	2048:128:32 x2	32 x2	128 x2	3072 x2	288 x2	GDDR5	384 x2	7782 8192	1946 2048	15	375	11.1	4.4	1.2	OEM
Model	Launch	Code name	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Core (MHz)	Boost (MHz)	Memory (MHz)	Core config	Pixel (GP/s)	Texture (GT/s)	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Double Precision	Idle	Max.	Direct3D	OpenGL	OpenCL	Release Price (USD)
							Clock rate				Fillrate		Memory				Processing Power (GFLOPS)		TDP (W)		API support (version)

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

Radeon Rx 200 Series

• All GCN GPUs support Mantle.
• All GCN 1.1 and above GPUs support TrueAudio and Direct3D 12 (level 12_0).^[27][28][29]

Model	Launch	Codename	Architecture	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Clock rate			Core config1	Fillrate		Memory				Processing Power (GFLOPS)		TDP (W)	API support (version)			Release Price (USD)
								Core (MHz)	Boost (MHz)	Memory (MT/s)		Pixel (GP/s)2	Texture (GT/s)3	Size (MiB)	Bus width (bit)	Bus type	Bandwidth (GB/s)	Single Precision4	Double Precision5		Direct3D	OpenGL	OpenCL8
Radeon R5 210	Unknown	Cedar	Terascale 2	40	292	59	PCIe 2.0 ×16	400	Unknown	900	80:8:4	1.6	3.2	256	64	DDR3	7.2	64	No	19	11.0	4.4	1.2	Unknown
Radeon R5 220	Unknown	Caicos PRO-L	Terascale 2	40	370	67	PCIe 2.0 ×16	625	650	1066	80:8:4[30]	2.5	5	1024	64	DDR3	8.53	200	No	18	11.0[30]	4.4	1.2	Unknown
Radeon R5 230	Apr 3, 2014[31]	Caicos Pro	Terascale 2	40	370	67	PCIe 2.0 ×16	625[32]	N/A	1066	160:8:4	2.5	5	1024 2048	64	DDR3	8.53	200	No	19[33]	11.0[34]	4.4	1.2	Unknown
Radeon R5 235	Unknown	Caicos XT	Terascale 2	40	370	67	PCIe 2.0 ×16	775	Unknown	1800	160:8:4	3.1	6.2	1024	64	DDR3	14.4	248	No	35[35]	11.0[30]	4.4	1.2	Unknown
Radeon R5 235X	Unknown	Caicos XT	Terascale 2	40	370	67	PCIe 2.1 ×16	875	Unknown	1800	160:8:4	3.5	7.0	1024	64	DDR3	14.4	280	No	18	11.0[30]	4.4	1.2	Unknown
Radeon R5 240	Nov 1st, 2013[36]	Oland	GCN 1.0	28	1040	90	PCIe 3.0 ×8	730	780	1800 ?	320:20:8	5.84	14.6	1024 2048	128	DDR3 GDDR5	28.8 ?	467.2 499.2	Unknown	50	11.2[30]	4.4	1.2[21][22]	Unknown
Radeon R7 240	Oct 8, 2013	Oland PRO	GCN 1.0	28	1040	90	PCIe 3.0 ×8	730	780	1800 4500	320:20:8	5.84	14.6	2048	128	DDR3 GDDR5	28.8 72	467.2 499.2	29.2	30	12.0[37]	4.4	1.2	$69
Radeon R7 250	Oct 8, 2013	Oland XT	GCN 1.0	28	1040	90	PCIe 3.0 ×8	1000	1050	1800 4600	384:24:8	8	24	1024 2048	128	DDR3 GDDR5	73.6	768 806.4	48	75	12.0[37]	4.4	1.2	$89
Radeon R7 250E[38]	Dec 21, 2013	Cape Verde PRO	GCN 1.0	28	1500	123	PCIe 3.0 ×16	800	N/A	4500	512:32:16	12.8	25.6	1024 2048	128	GDDR5	72	819.2	51.2	55	12.0	4.4	1.2	Unknown
Radeon R7 250X	Feb 10, 2014	Cape Verde XT	GCN 1.0	28	1500	123	PCIe 3.0 ×16	1000	N/A	4500	640:40:16	16	40	1024 2048	128	GDDR5	72	1280	80	95	12.0[37]	4.4	1.2	$99
Radeon R7 260	Dec 17, 2013	Bonaire	GCN 1.1	28	2080	160	PCIe 3.0 ×16	1000	N/A	6000	768:48:16	16	48	1024	128	GDDR5	96	1536	96	95	12.0[37]	4.4	2.0[21][22]	$109
Radeon R7 260X	Oct 8, 2013	Bonaire XTX	GCN 1.1	28	2080	160	PCIe 3.0 ×16	1100	N/A	6500	896:56:16	17.6	61.6	1024 2048	128	GDDR5	104	1971.2	123.2	115	12.0[37]	4.4	2.0	$139
Radeon R7 265	Feb 13, 2014	Curaçao PRO (Pitcairn PRO)	GCN 1.0	28	2800	212	PCIe 3.0 ×16	900	925	5600	1024:64:32	28.8	57.6	2048	256	GDDR5	179.2	1843.2	115.2	150	12.0[37]	4.4	1.2	$149
Radeon R9 270	Nov 13, 2013	Curaçao PRO (Pitcairn XT)	GCN 1.0	28	2800	212	PCIe 3.0 ×16	900	925	5600	1280:80:32	28.8	72	2048	256	GDDR5	179.2	2304 2368	144 148	150	12.0[39]	4.4	1.2	$179
Radeon R9 270X	Oct 8, 2013	Curaçao XT (Pitcairn XT)	GCN 1.0	28	2800	212	PCIe 3.0 ×16	1000	1050	5600	1280:80:32	32	80	2048 4096	256	GDDR5	179.2	2560 2688	160 168	180	12.0[39]	4.4	1.2	$199
Radeon R9 280	Mar 4, 2014	Tahiti PRO	GCN 1.0	28	4313	352	PCIe 3.0 ×16	827	933	5000	1792:112:32	26.5	92.6	3072	384	GDDR5	240	2964 3343.9	741 836	250	12.0[39]	4.4	1.2	$249
Radeon R9 280X	Oct 8, 2013	Tahiti XT2 Tahiti XTL[40]	GCN 1.0	28	4313	352	PCIe 3.0 ×16	850	1000	6000	2048:128:32	27.2 - 32	109 - 128	3072	384	GDDR5	288	3481.6 4096	870.4 1024	250	12.0[39]	4.4	1.2	$299
Radeon R9 285	Sep 2, 2014	Tonga PRO	GCN 1.2	28	5000[41]	359[41]	PCIe 3.0 ×16	918	N/A	5500	1792:112:32	29.4	102.8	2048	256	GDDR5	176	3290	206.6[42]	190	12.0[39]	4.4	2.0[21][22]	$249
Radeon R9 290	Nov 5, 2013	Hawaii PRO	GCN 1.1	28	6200[43]	438	PCIe 3.0 ×16	up to 9476	N/A	5000	2560:160:64	60.608	151.52	4096	512	GDDR5	320	4848.6	606.1	250[44]	12.0[39]	4.4	2.0	$399
Radeon R9 290X	Oct 24, 2013	Hawaii XT	GCN 1.1	28	6200[43]	438	PCIe 3.0 ×16	up to 10006	N/A	5000	2816:176:64	64	176	4096 8192	512	GDDR5	320	5632	704	250[44]	12.0[39]	4.4	2.0	$549
Radeon R9 295X2 [45]	Apr 8, 2014	Vesuvius	GCN 1.1	28	6200 ×2	438 ×2	PCIe 3.0 ×16	1018	N/A	5000	2816:176:64 ×2	65.152 ×2	179.168 ×2	4096 ×2	512 ×2	GDDR5	320 ×2	5733.376 ×2	2× 716.672	500	12.0[39]	4.4	2.0	$1499
Model	Launch	Codename	Architecture	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Core (MHz)	Boost (MHz)	Memory (MT/s)	Core config1	Pixel (GP/s)2	Texture (GT/s)3	Size (MiB)	Bus width (bit)	Bus type	Bandwidth (GB/s)	Single Precision4	Double Precision5	TDP (W)	Direct3D	OpenGL	OpenCL8	Release Price (USD)
								Clock rate				Fillrate		Memory				Processing Power (GFLOPS)			API support (version)

¹ Unified Shaders : Texture Mapping Units : Render Output Units
² Pixel fillrate is calculated as the number of ROPs multiplied by the base core clock speed.
³ Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
⁴ Single precision performance is calculated as two times the number of shaders multiplied by the base core clock speed.
⁵ Double precision performance is 1/16 of the single precision performance on GCN 1.2,^[46][47] 1/2 on GCN 1.1 (capped to 1/8 on high-end consumer Radeon cards, and 1/16 on mid- and entry-level cards),^[48][49] and 1/4 on GCN 1.0 (capped to 1/16 on mid- and entry-level cards).^[50]
6 Base clock of R9 290 and R9 290X will maintain at 947 MHz and 1000 MHz before reaching 95 °C, respectively.^[51]
7 The R9 285 utilizes loss-less colour compression which can increase effective memory performance (relative to GCN 1.0 and 1.1 cards) in certain situations.^[52][41]
8 Support for OpenCL 2.0 has been extended to the 200 Series' R7 and R9 models.^[21]

Radeon Rx 300 Series

• All GPUs, except for the Fiji chips, are refined or enhanced versions of Rx 200 chips.^{[53][54][55][56][57][58][59]}

• Non-OEM GPUs have received additional features, including: Power saving frame limiter (user configurable), LiquidVR support, Virtual Super Resolution (VSR) support & reduced power consumption. These features were previously limited to the R9 285 with partial support for VSR on the 290/290X.

• All GPUs support Mantle and Vulkan.
• All GCN 1.0 GPUs support Direct3D 12 feature_level 11_2 and OpenCL 1.2
• All GCN 1.1 and above GPUs contain TrueAudio and support Direct3D 12 feature_level 12_0 and OpenCL 2.1

Model	Launch	Codename	Architecture	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Clock rate			Core config1	Fillrate		Memory6				Processing Power (GFLOPS)		TDP (W)	API support (version)			Release Price (USD)
								Core (MHz)	Boost (MHz)	Memory (MT/s)		Pixel (GP/s)2	Texture (GT/s)3	Size (MiB)	Bus width (bit)	Bus type	Bandwidth (GB/s)	Single Precision4	Double Precision5		Direct3D	OpenGL	OpenCL
Radeon R5 330 (OEM)	May 6, 2015	Oland Pro	GCN 1.0	28	1040	90	PCIe 3.0 ×16	Unknown	855	1800	320:20:8	6.84	17.1	1024 2048	128	DDR3	28.8	547.2	34.2	30	12.0 (11_1)	4.5	1.2	OEM
Radeon R5 340 (OEM)	May 6, 2015	Oland XT						Unknown	825	1800 4500	384:24:8	6.6	19.8	1024 2048	128	DDR3 GDDR5	72	633.6	39.6	75				OEM
Radeon R7 340 (OEM)	May 6, 2015							730	780	1800 4500	384:24:8	5.8	17.5	1024 2048 4096	128	DDR3 GDDR5	72	560.6 599	35	75				OEM
Radeon R7 350 (OEM)	May 6, 2015							1000	1050	1800 4500	384:24:8	8	24	1024 2048	128	DDR3 GDDR5	72	768 806.4	48	75				OEM
Radeon R7 360[60][61]	June 18, 2015	Tobago (Bonaire Pro)	GCN 1.1		2080	160		1050	N/A	6500	768:48:16	16.8	50.4	2048	128	GDDR5	104	1612.8	100.8	100	12.0 (12_0)		2.0	$109
Radeon R9 360 (OEM)	May 6, 2015	Bonaire Pro						1000	1050	6500	768:48:16	16	48	2048	128	GDDR5	104	1536	96	85				OEM
Radeon R7 370[60]	June 18, 2015	Trinidad Pro (Pitcairn Pro)	GCN 1.0		2800	212		975	N/A	5600	1024:64:32	31.2	62.4	2048 4096	256	GDDR5	179.2	1996.8	124.8	110	12.0 (11_1)		1.2	$149 $149+
Radeon R9 370 (OEM)	May 6, 2015	Curaçao Pro						950	975	5600	1024:64:32	30.4	60.8	2048 4096	256	GDDR5	179.2	1945.6	121.6	150				OEM
Radeon R9 370X	August 27, 2015	Trinidad XT (Pitcairn XT)						1000	N/A	5600	1280:80:32	32	80	2048 4096	256	GDDR5	179.2	2560	160	TBA				$179 $179+
Radeon R9 380 (OEM)	May 6, 2015	Tonga Pro	GCN 1.2		5000	359		918	N/A	5500	1792:112:32	29.4	102.8	4096	256	GDDR5	176	3290	206.6	190	12.0 (12_0)		2.0	OEM
Radeon R9 380[62]	June 18, 2015	Antigua Pro (Tonga Pro)						970	N/A	5700	1792:112:32	31.0	108.6	2048 4096	256	GDDR5	182.4	3476.5	217.3	190				$199 $199+
Radeon R9 380X[62]	November 19, 2015	Antigua XT (Tonga XT)						970	N/A	5700	2048:128:32	31.0	124.2	4096	256	GDDR5	182.4	3973.1	248.3	190				$229
Radeon R9 390[62]	June 18, 2015	Grenada Pro (Hawaii Pro)	GCN 1.1		6200	438		1000	N/A	6000	2560:160:64	64	160	8192	512	GDDR5	384	5120	640	275				$329
Radeon R9 390X[62]	June 18, 2015	Grenada XT (Hawaii XT)						1050	N/A	6000	2816:176:64	67.2	184.8	8192	512	GDDR5	384	5913.6	739.2	275				$429
Radeon R9 Fury[63]	July 14, 2015	Fiji Pro	GCN 1.2		8900	596		1000	N/A	1000	3584:224:64	64	224	4096	4096	HBM	512	7168	448	275				$549
Radeon R9 Nano[64]	August 27, 2015	Fiji XT						1000	N/A	1000	4096:256:64	64	256	4096				8192	512	175				$649
Radeon R9 Fury X[62][65]	June 24, 2015							1050	N/A	1000	4096:256:64	67.2	268.8	4096				8601.6	537.6	275				$649
Radeon R9 Fury X2[66]	2015 Q4	2× Fiji XT			2× 8900	2× 596		TBA	N/A	1000	2× 4096:256:64	TBA	TBA	2× 4096	2× 4096			TBA	TBA	TBA				TBA
Model	Launch	Codename	Architecture	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Core (MHz)	Boost (MHz)	Memory (MT/s)	Core config1	Pixel (GP/s)2	Texture (GT/s)3	Size (MiB)	Bus width (bit)	Bus type	Bandwidth (GB/s)	Single Precision4	Double Precision5	TDP (W)	Direct3D	OpenGL	OpenCL	Release Price (USD)
								Clock rate				Fillrate		Memory6				Processing Power (GFLOPS)			API support (version)

¹ Unified Shaders : Texture Mapping Units : Render Output Units
² Pixel fillrate is calculated as the number of ROPs multiplied by the base core clock speed.
³ Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
⁴ Single precision performance is calculated as two times the number of shaders multiplied by the base core clock speed.
⁵ Double precision performance is 1/16 of the single precision performance on GCN 1.2,^[67][68] 1/2 on GCN 1.1 (capped to 1/8 on high-end consumer Radeon cards, and 1/16 on mid- and entry-level cards),^[48][69] and 1/4 on GCN 1.0 (capped to 1/16 on mid- and entry-level cards).^[70]
6 The GCN 1.2 GPUs utilize loss-less colour compression which can increase effective memory performance (relative to GCN 1.0 and 1.1 cards) in certain situations.^[52][41]

Comparison table: Mobile GPUs

Rage Mobility Series

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	No	0:1:1:1	0.075	0.075	8	0.80	EDO, SDR, SGR	64	6	1.1	Motion Compensation
Rage Mobility M/P (Rage 128)	Nov 1998	250	AGP, PCI	90	Unknown	No	0:2:2:2	0.18	0.18	8	Unknown	SDR, SGR	64	Unknown	Unknown	M had 4 MB of integrated SDRAM, P had none. IDCT, Motion Compensation.
Rage Mobility M1 (Rage 128)	Feb 1999	250	AGP, PCI	90	90	No	0:2:2:2	0.18	0.18	8	0.72	SDR	64	6	1.2	M1 had 8 MB of integrated SDRAM, P had none. IDCT, Motion Compensation.
Rage 128 GL	Aug 1998	250	AGP, PCI	103	103	No	0:2:2:2	0.206	0.206	32	1.65	SDR	128	6	1.2
Rage Mobility 128 (Rage 128 Pro)	Oct 1999	250	AGP, PCI	105	105	No	0:2:2:2	0.21	0.21	16	2.28	SDR	128	6	1.2	IDCT, Motion Compensation
Rage Mobility M3 (AGP 4x) (Rage 128 Pro)	Oct 1999	250	AGP, PCI	105	105	No	0:2:2:2	0.21	0.21	16	2.28	SDR	128	6	1.2	M3 had 8 MB of integrated SDRAM, IDCT, Motion Compensation.
Rage Mobility M4 (AGP 4x) (Rage 128 Pro)	Oct 1999	250	AGP, PCI	105	105	No	0:2:2:2	0.21	0.21	32	2.28	SDR	128	6	1.2	M4 had 16 MB of integrated SDRAM, IDCT, Motion Compensation.

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

Mobility Radeon Series

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

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

Mobility Radeon X300, X600, X700, X800 Series

Model	Launch	Model Number	Code name	Fab (nm)	Bus interface	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 x16	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	PCI-E x16	400	250	2:4:4:4	1.6	1.6	64, 128	8	DDR	128	9.0b	2.0
Mobility Radeon X700	Mar 2005	M26	RV410	110	PCI-E x16	400-100 (PowerPlay)	350-200	6:8:8:4	1.4	2.8	Shared-128? 64, 128	11.2	DDR, GDDR3	128	9.0b	2.0	3DC, Dynamic Lane Count Switching,
Mobility Radeon X800	Nov 2004	M28	R423	130	PCI-E x16	400	400	6:12:12:12	4.8	4.8	256	25.6	GDDR3	256	9.0b	2.0	3DC, DLCS, Clock Gating
Mobility Radeon X800 XT	Jun 2005	M28 PRO	R423	130	PCI-E x16	480	550	6:16:16:16	7.68	7.68	256	35.2	GDDR3	256	9.0b	2.0	3DC, DLCS, Clock Gating

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

Mobility Radeon X1xxx Series

Model	Launch	Model Number	Code name	Fab (nm)	Bus interface	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 x16	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	RV515	90	PCIe x16	470	350	2:4:4:4	1.88	1.88	128 + shared	11.2	DDR2 GDDR3	128	9.0c	2.0
Mobility Radeon X1400	January 19, 2006	M54	RV515	90	PCIe x16	445	250	2:4:4:4	1.78	1.78	128 + shared	8	DDR DDR2	128	9.0c	2.0
Mobility Radeon X1450	September 18, 2006	M64	RV515	90	PCIe x16	550	450	2:4:4:4	2.2	2.2	128 + Shared	14.4	DDR2 GDDR3	128	9.0c	2.0
Mobility Radeon X1600	February 1, 2006	M56	RV530	90	PCIe x16	425 450	375 470	5:12:4:4	1.7 1.8	1.7 1.8	256	12.0 15.04	DDR2 GDDR3	128	9.0c	2.0
Mobility Radeon X1700	February 1, 2006	M66	RV535	80	PCIe x16	475	400 550	5:12:4:4	1.9	1.9	256	11.2 17.6	DDR2 GDDR3	128	9.0c	2.0	strained silicon
Mobility Radeon X1800	March 1, 2006	M58	R520	90	PCIe x16	450	500	8:12:12:12	5.4	5.4	256	32	GDDR3	256	9.0c	2.0
Mobility Radeon X1800 XT	March 1, 2006	M58	R520	90	PCIe x16	550	650	8:16:16:16	8.8	8.8	256	41.6	GDDR3	256	9.0c	2.0
Mobility Radeon X1900	January 11, 2007	M59	RV570	80	PCIe x16	400	480	8:36:12:12	4.8	4.8	256	30.72	GDDR3	256	9.0c	2.0	PowerPlay 6.0

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

Mobility Radeon HD 2xxx Series

Model	Launch	Model Number	Code name	Fab (nm)	Bus interface	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 x16	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	90	PCIe x16	460	400	5:12:4:41	1.84	1.84	256	12.8	DDR DDR2 GDDR3	128	9.0c	2.0	Unknown	based on X1600/1700, HM up to 768Mb, no UVD, PowerPlay 6.0
Mobility Radeon HD 2300	March 1, 2007	M71	RV515	90	PCIe x16	480	400	2:4:4:41	1.92	1.92	128 256 512	6.4 12.8	DDR DDR2 GDDR3	64 128	9.0c	2.0	Unknown	same as X2300, but with UVD, PowerPlay 6.0
Mobility Radeon HD 2400	May 14, 2007	M72S	RV610	65	PCIe x16	450	400	40:4:42	1.8	1.8	256+ Hyper Memory	6.4	DDR2	64	10	2.0	36	UVD, PowerPlay 7.0
Mobility Radeon HD 2400 XT	May 14, 2007	M72M	RV610	65	PCIe x16	600 600	400 700	40:4:42	2.4	2.4	256+ Hyper Memory	6.4 11.2	DDR2 GDDR3	64	10	2.0	48	UVD, PowerPlay 7.0
Mobility Radeon HD 2600	May 14, 2007	M76M	RV630	65	PCIe x16	500 500	400 600	120:8:42	2.0	4.0	256+ Hyper Memory	12.8 19.2	DDR2 GDDR3	128	10	2.0	120	UVD, PowerPlay 7.0
Mobility Radeon HD 2600 XT	May 14, 2007	M76XT	RV630	65	PCIe x16	680	750	120:8:42	2.72	5.44	256+ Hyper Memory	24	GDDR3	128	10	2.0	168	UVD, PowerPlay 7.0
Mobility Radeon HD 2700	December 12, 2007	M76	RV630	65	PCIe x16	650	700	120:8:42	2.6	5.2	256+ Hyper Memory (total 768)	22.4	GDDR3	128	10	2.0	168	UVD, PowerPlay 7.0

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

Mobility Radeon HD 3xxx Series

Model[71]	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 3100	August 1, 2008	RS780MC	RV620	55	PCIe x16 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	2.0	24	UVD, PowerPlay 7.0
Mobility Radeon HD 3200	June 4, 2008	RS780MC	RV620	55	PCIe x16 1.1	500	800 (system memory)	40:4:4	2	2	up to 512 from system memory	6.4/12.8	DDR2	64/128	10	2.0	40	UVD, PowerPlay 7.0
Mobility Radeon HD 3410	July 25, 2008	M82-MPE	RV620	55	PCIe x16 1.1	400	400	40:4:4	1.6	1.6	256, 512	6.4	DDR2	64	10.1	2.0	32	UVD, PowerPlay 7.0
Mobility Radeon HD 3430	July 25, 2008	M82-SE	RV620	55	PCIe x16 2.0	450	400	40:4:4	1.8	1.8	256	6.4	DDR2	64	10.1	2.0	36	UVD, PowerPlay 7.0
Mobility Radeon HD 3450	January 7, 2008	M82	RV620	55	PCIe x16 2.0	500	400 700	40:4:4	2	2	256	6.4 11.2	DDR2 GDDR3	64	10.1	2.0	40	UVD, PowerPlay 7.0
Mobility Radeon HD 3470	January 7, 2008	M82-XT	RV620	55	PCIe x16 2.0	680	400 800	40:4:4	2.72	2.72	256	6.4 12.8	DDR2 GDDR3	64	10.1	2.0	54.4	UVD, PowerPlay 7.0
Mobility Radeon HD 3650	January 7, 2008	M86	RV635	55	PCIe x16 2.0	500	500 700	120:8:4	2	4	512 1024	16.0 22.4	DDR2 GDDR3 GDDR4	128	10.1	3.3	120	UVD, PowerPlay 7.0
Mobility Radeon HD 3670	January 7, 2008	M86-XT	RV635	55	PCIe x16 2.0	680	800	120:8:4	2.72	5.44	512 1024	25.6	DDR2 GDDR3 GDDR4	128	10.1	2.0	163.2	UVD, PowerPlay 7.0. TDP 30 watts
Mobility Radeon HD 3850	June 4, 2008	M88-L/M88-LP	RV670	55	PCIe x16 2.0	580	750	320:16:16	9.28	9.28	512	48.0	GDDR3	256	10.1	2.0	371.2	UVD, PowerPlay 7.0
Mobility Radeon HD 3870	June 4, 2008	M88-LXT	RV670	55	PCIe x16 2.0	660	850	320:16:16	10.56	10.56	512	54.4	GDDR3	256	10.1	2.0	422.4	UVD, PowerPlay 7.0. TDP 55 watts.
Mobility Radeon HD 3850 X2	June 5, 2008	2x M88-L/M88-LP	R680	55	PCIe x16 2.0	580	750	2x [320:16:16]	2x 9.28	2x 9.28	2x 512	2x 48.0	GDDR3	2x 256	10.1	2.0	2x 371.2	UVD, PowerPlay 7.0
Mobility Radeon HD 3870 X2	September 1, 2008	2x M88-LXT	R680	55	PCIe x16 2.0	660	850	2x [320:16:16]	2x 10.56	2x 10.56	2x 512	2x 54.4	GDDR3	2x 256	10.1	2.0	2x 422.4	UVD, PowerPlay 7.0. TDP 110 watts

¹ Unified Shaders : Texture mapping units : Render output units

Mobility Radeon HD 4xxx Series

Model[71]	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	2.0	40	UVD2, PowerPlay 7.0
Mobility Radeon HD 4225	May 1, 2010	Unknown	RV620	55	Internal PCIe x16 1.1	380	800 (system memory)	40:4:4	1.52	1.52	up to 512 from system memory	6.4/12.8	DDR2 DDR3	64/128	10.1	2.0	30.4	UVD2, PowerPlay 7.0
Mobility Radeon HD 4250	May 1, 2010	Unknown	RV620	55	Internal PCIe x16 1.1	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	2.0	40	UVD2, PowerPlay 7.0
Mobility Radeon HD 4270	May 1, 2010	Unknown	RV620	55	Internal PCIe x16 1.1	590	800 (system memory)	40:4:4	2.36	2.36	up to 512 from system memory	6.4/12.8	DDR2 DDR3	64/128	10.1	2.0	47.2	UVD2, PowerPlay 7.0
Mobility Radeon HD 4330	January 9, 2009	M92	RV710	55	PCIe x16 2.0	450	600	80:8:4	1.8	3.6	512	9.6	DDR2 DDR3 GDDR3	64	10.1	3.3	72	UVD2, PowerPlay 7.0
Mobility Radeon HD 4530	January 9, 2009	M92	RV710	55	PCIe x16 2.0	500	700	80:8:4	2	4	512	11.2	DDR2 DDR3 GDDR3	64	10.1	3.3	80	UVD2, PowerPlay 7.0
Mobility Radeon HD 4550	January 1, 2010	M92	RV710	55	PCIe x16 2.0	550	700	80:8:4	2.2	4.4	512	11.2	DDR2 DDR3 GDDR3	64	10.1	3.3	80	UVD2, PowerPlay 7.0
Mobility Radeon HD 4570	January 9, 2009	M92	RV710	55	PCIe x16 2.0	680	800	80:8:4	2.72	5.44	512	12.8	DDR2 DDR3 GDDR3	64	10.1	3.3	108.8	UVD2, PowerPlay 7.0
Mobility Radeon HD 4650	January 9, 2009	M96	RV730	55	PCIe x16 2.0	500 550	600 800	320:32:8	4 4.4	16 17.6	512 1024	19.2 25.6	DDR2 DDR3 GDDR3	128	10.1	3.3	320 352	UVD2, PowerPlay 7.0
Mobility Radeon HD 4670	January 9, 2009	M96-XT	RV730	55	PCIe x16 2.0	675	800	320:32:8	5.4	21.6	512 1024	12.8 25.6	DDR2 DDR3 GDDR3	128	10.1	3.3	432	UVD2, PowerPlay 7.0
Mobility Radeon HD 4830	March 3, 2009[72]	M97	RV740	40	PCIe x16 2.0	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	512 1024	25.6/28.8 25.6/28.8	GDDR3 DDR3	128	10.1	3.3	512/768 512/768	UVD2, PowerPlay 7.0
Mobility Radeon HD 4850[73]	January 9, 2009	M98	RV770	55	PCIe x16 2.0	500	850 700	800:40:16	8	20	1024	54.4 89.6	GDDR3 GDDR52	256	10.1	3.3	800	UVD2, PowerPlay 7.0
Mobility Radeon HD 4860	March 3, 2009[72]	M97	RV740	40	PCIe x16 2.0	650	1000	640:32:16	10.4	20.8	1024	64.0	GDDR52	128	10.1	3.3	832	UVD2, PowerPlay 7.0
Mobility Radeon HD 4870	January 9, 2009	M98-XT	RV770	55	PCIe x16 2.0	550	888 700	800:40:16	8.8	22	512 1024	56.832 89.6	GDDR3 GDDR52	256	10.1	3.3	880	UVD2, PowerPlay 7.0
Mobility Radeon HD 4870 X2	January 9, 2009	M98-XT	RV770	55	PCIe x16 2.0	550	700	2x [800:40:16]	2x 8.8	2x 22	2048	2x 89.6	GDDR52	2x 256	10.1	3.3	2x 880	UVD2, PowerPlay 7.0 Dual GPU solution

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

Mobility Radeon HD 5xxx 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	May 5, 2010	M92	RV710	55	PCIe x16 2.0	500	600	80:8:4	2	4	1024	9.6	DDR2 DDR3 GDDR3	64	10.1	3.3	80	Unknown
Mobility Radeon HD 545v	May 5, 2010	M92	RV710	55	PCIe x16 2.0	720	800	80:8:4	2.88	5.76	1024	12.8	DDR2 DDR3 GDDR3	64	10.1	3.3	115.2	Unknown
Mobility Radeon HD 550v	May 5, 2010	M96	RV730	55	PCIe x16 2.0	450	600	320:32:8	3.6	14.4	1024	19.2	DDR2 DDR3 GDDR3	128	10.1	3.3	288	Unknown
Mobility Radeon HD 560v	May 5, 2010	M96	RV730	55	PCIe x16 2.0	550	800	320:32:8	4.4	17.6	1024	25.6	DDR2 DDR3 GDDR3	128	10.1	3.3	352	Unknown
Mobility Radeon HD 565v	May 5, 2010	M96-XT	RV730	55	PCIe x16 2.0	675	800	320:32:8	5.4	21.6	1024	25.6	DDR2 DDR3 GDDR3	128	10.1	3.3	432	Unknown
Mobility Radeon HD 5145	January 7, 2010	M92	RV710	55	PCIe x16 2.0	720	900	80:8:4	2.88	5.76	1024	14.4	DDR3 GDDR3	64	10.1	3.3	115.2	15
Mobility Radeon HD 5165	January 7, 2010	M96	RV730	55	PCIe x16 2.0	600	900	320:32:8	4.8	19.2	1024	28.8	DDR3 GDDR3	128	10.1	3.3	384	35
Mobility Radeon HD 5430	January 7, 2010	Park LP	Cedar	40	PCIe x16 2.1	500 550	800 800	80:8:4	2.0 2.2	4.0 4.4	1024	12.8	DDR3 GDDR3	64	11	4.4	80 88	7
Mobility Radeon HD 5450	January 7, 2010	Park PRO	Cedar	40	PCIe x16 2.1	675	800	80:8:4	2.7	5.4	1024	12.8	DDR3 GDDR3	64	11	4.4	108	11
Mobility Radeon HD 5470	January 7, 2010	Park XT	Cedar	40	PCIe x16 2.1	750	800	80:8:4	3	6	1024 1024 512	12.8 12.8 25.6	DDR3 GDDR3 GDDR5	64	11	4.4	120	13 15
Mobility Radeon HD 5650	January 7, 2010	Madison PRO	Redwood	40	PCIe x16 2.1	450 650	800 800	400:20:8	3.6 5.2	9.0 13.0	1024	25.6 25.6	DDR3 GDDR3	128	11	4.4	360 520	15 19
Mobility Radeon HD 5730	January 7, 2010	Madison LP	Redwood	40	PCIe x16 2.1	650	800	400:20:8	5.2	13	1024	25.6	DDR3 GDDR3	128	11	4.4	520	26
Mobility Radeon HD 5750	January 7, 2010	Madison PRO	Redwood	40	PCIe x16 2.1	550	800	400:20:8	4.4	11	1024	51.2	GDDR5	128	11	4.4	440	25
Mobility Radeon HD 5770	January 7, 2010	Madison XT	Redwood	40	PCIe x16 2.0/2.1	650	800	400:20:8	5.2	13	1024	51.2	GDDR5	128	11	4.4	520	30
Mobility Radeon HD 5830	January 7, 2010	Broadway LP	Juniper	40	PCIe x16 2.1	500	800	800:40:16	8	20	1024	25.6	DDR3 GDDR3	128	11	4.4	800	24
Mobility Radeon HD 5850	January 7, 2010	Broadway PRO	Juniper	40	PCIe x16 2.1	625 500 625	900 1000 1000	800:40:16	10 8 10	25 20 25	2048 1024 1024	28.8 64 64	DDR3 GDDR5 GDDR5	128	11	4.4	1000 800 1000	31 30 39
Mobility Radeon HD 5870	January 7, 2010	Broadway XT	Juniper	40	PCIe x16 2.1	700	1000	800:40:16	11.2	28	1024	64	GDDR5	128	11	4.4	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 6xxxM 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)	TDP (Watts) GPU only	Features
									Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
Radeon HD 6330M	November 26, 2010	Robson LP	Cedar	40	PCIe 2.1 x16	500	800	80:8:4	2.0	4.0	up to 1024	12.8	DDR3	64	11	4.4	80	7	UVD2.2, PowerPlay
Radeon HD 6350M	November 26, 2010	Robson Pro	Cedar	40	PCIe 2.1 x16	500 500	800 900	80:8:4	2.0	4.0	up to 1024	12.8 14.4	DDR3	64	11	4.4	80	7	UVD2.2, PowerPlay
Radeon HD 6370M	November 26, 2010	Robson XT	Cedar	40	PCIe 2.1 x16	750	900	80:8:4	3.0	6.0	1024	14.4	DDR3	64	11	4.4	120	11	UVD2.2, PowerPlay
Radeon HD 6430M	January 4, 2011	Seymour LP	Caicos	40	PCIe 2.1 x16	480	800	160:8:4	1.92	3.84	1024	12.8	DDR3	64	11	4.4	153.6	Unknown	UVD3.0, PowerPlay
Radeon HD 6450M	January 4, 2011	Seymour Pro	Caicos	40	PCIe 2.1 x16	600	800	160:8:4	2.4	4.8	1024	12.8	DDR3	64	11	4.4	192	Unknown	UVD3.0, PowerPlay
Radeon HD 6470M	January 4, 2011	Seymour XT	Caicos	40	PCIe 2.1 x16	700 750	800 800	160:8:4	2.8 3.0	5.6 6.0	1024	12.8	DDR3	64	11	4.4	224 240	Unknown	UVD3.0, PowerPlay
Radeon HD 6490M	January 4, 2011	Seymour XT	Caicos	40	PCIe 2.1 x16	800	800	160:8:4	3.2	6.4	512	25.6	GDDR5	64	11	4.4	256	Unknown	UVD3.0, PowerPlay
Radeon HD 6530M	November 26, 2010	Capilano Pro	Redwood	40	PCIe 2.1 x16	500	900	400:20:8	4.0	10.0	1024	28.8	DDR3	128	11	4.4	400	26	UVD2.2, PowerPlay
Radeon HD 6550M	November 26, 2010	Capilano Pro	Redwood	40	PCIe 2.1 x16	600	900	400:20:8	4.8	12.0	1024	28.8	DDR3	128	11	4.4	480	26	UVD2.2, PowerPlay
Radeon HD 6570M	November 26, 2010	Capilano XT	Redwood	40	PCIe 2.1 x16	650	900	400:20:8	5.2	13.0	1024	28.8 57.6	DDR3 GDDR5	128	11	4.4	520	30	UVD2.2, PowerPlay
Radeon HD 6630M	January 4, 2011	Whistler LP	Turks	40	PCIe 2.1 x16	485	800	480:24:8	3.88	11.64	256(mac) 1024	51.2 (mac) 25.6	GDDR5(mac) DDR3	128	11	4.4	465.6	Unknown	UVD3.0, PowerPlay
Radeon HD 6650M	January 4, 2011	Whistler Pro	Turks	40	PCIe 2.1 x16	600	900	480:24:8	4.8	14.4	1024	28.8	DDR3	128	11	4.4	576	Unknown	UVD3.0, PowerPlay
Radeon HD 6730M	January 4, 2011	Whistler XT	Turks	40	PCIe 2.1 x16	725	800	480:24:8	5.8	17.4	1024	25.6	DDR3	128	11	4.4	696	Unknown	UVD3.0, PowerPlay
Radeon HD 6750M	January 4, 2011	Whistler Pro	Turks	40	PCIe 2.1 x16	600	800 900	480:24:8	4.8	14.4	256 512 1024	51.2 57.6	GDDR5	128	11	4.4	576	Unknown	UVD3.0, PowerPlay
Radeon HD 6770M	January 4, 2011	Whistler XT	Turks	40	PCIe 2.1 x16	725	900	480:24:8	5.8	17.4	1024	57.6	GDDR5	128	11	4.4	696	Unknown	UVD3.0, PowerPlay
Radeon HD 6830M	January 4, 2011	Granville Pro	Juniper	40	PCIe x16 2.1	575	800	800:40:16	9.2	23.0	up to 2048	25.6	DDR3	128	11	4.4	920	39	UVD2.2, PowerPlay
Radeon HD 6850M	January 4, 2011	Granville XT	Juniper	40	PCIe x16 2.1	675	800	800:40:16	10.8	27.0	up to 2048	25.6	DDR3	128	11	4.4	1080	50	UVD2.2, PowerPlay
Radeon HD 6850M	January 4, 2011	Granville Pro	Juniper	40	PCIe x16 2.1	575	800	800:40:16	9.2	23.0	1024	57.6	GDDR5	128	11	4.4	920	39	UVD2.2, PowerPlay
Radeon HD 6870M	January 4, 2011	Granville XT	Juniper	40	PCIe x16 2.1	675	1000	800:40:16	10.8	27	1024	64	GDDR5	128	11	4.4	1080	50	UVD2.2, PowerPlay
Radeon HD 6950M	January 4, 2011	Blackcomb Pro	Barts	40	PCIe 2.1 x16	580	900	960:48:32	18.56	27.84	up to 2048	115.2	GDDR5	256	11	4.4	1113.6	50	UVD3.0, PowerPlay
Radeon HD 6970M	January 4, 2011	Blackcomb XT	Barts	40	PCIe 2.1 x16	680	900	960:48:32	21.76	32.64	up to 2048	115.2	GDDR5	256	11	4.4	1305.6	75	UVD3.0, PowerPlay
Radeon HD 6990M	July 12, 2011	Blackcomb XTX	Barts	40	PCIe 2.1 x16	715	900	1120:56:32	22.88	40.04	2048	115.2	GDDR5	256	11	4.4	1601.6	75	UVD3.0, PowerPlay
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)	Features
									Fillrate		Memory				API compliance (version)

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

IGP (HD 6xxx)

• 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 are based on the VLIW5 architecture.

Model	Released	Code name	Fab (nm)	Core Clock (MHz)	Core config1	Fillrate		Shared Memory			Processing Power (GFLOPS)	Max. Combined TDP2 (W)	APU
						Pixel (GP/s)	Texture (GT/s)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon HD 6250[74]	Nov 9, 2010[20]	Wrestler[75]	40	280 - 400[74]	80:8:4	1.12 - 1.6	2.24 - 3.2	8.525	DDR3-1066	64	44.8 - 64	9	Z-60 C-30 C-50
Radeon HD 6290	Jan 7, 2011	Ontario		276 - 400									C-60
Radeon HD 6310[74]	Nov 9, 2010[20]	Wrestler[75]		492		2.0	4.0				80	18	E-240 E-300 E-350
Radeon HD 6320	Aug 15, 2011	Wrestler		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
² TDP specified for AMD reference designs, includes CPU power consumption. Actual TDP of retail products may vary.

IGP (HD 6xxxG)

• 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 (W)	APU
						Pixel (GP/s)	Texture (GT/s)	Bandwidth (GB/s)	Bus type	Bus width (bit)
Radeon HD 6380G	June 14, 2011	WinterPark	32	400	160:8:4	1.6	3.2	17.06	DDR3-1333	128	128	35	E2-3000M
Radeon HD 6480G	June 14, 2011	BeaverCreek	32	444	240:12:4	1.77	3.55	17.06	DDR3-1333	128	213.1	35 - 45	A4-3300M A4-3310MX
Radeon HD 6520G	June 14, 2011	BeaverCreek	32	400	320:16:8	3.2	6.4	17.06	DDR3-1333	128	256	35 - 45	A6-3400M A6-3410MX A6-3420M
Radeon HD 6620G	June 14, 2011	BeaverCreek	32	444	400:20:8	3.55	8.88	25.6	DDR3-1600	128	355.2	35 - 45	A8-3500M A8-3510MX A8-3530MX

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

Radeon HD 7xxxM Series

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

^[76]

Model	Launch	Model Number	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing Power (GFLOPS)	API compliance (version)		TDP (Watts) GPU only	Features / Notes
						Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type2	Bus width (bit)		Direct3D	OpenGL
Radeon HD 7430M	January 7, 2012	Seymour Pro	Caicos	40	PCIe 2.1 x16	600	900	160:8:4	2.4	4.8	1024	14.4	DDR3	64	192	11.0	4.4	7
Radeon HD 7450M	January 7, 2012	Seymour Pro	Caicos	40	PCIe 2.1 x16	700 700	900 800	160:8:4	2.8	5.6	1024	14.4 25.6	DDR3 GDDR5	64	224	11.0	4.4	7
Radeon HD 7470M	January 7, 2012	Seymour XT	Caicos	40	PCIe 2.1 x16	750 800	900 800	160:8:4	3.0 3.2	6 6.4	1024	14.4 25.6	DDR3 GDDR5	64	240 256	11.0	4.4	7~9
Radeon HD 7490M	January 7, 2012	Seymour XTX	Caicos	40	PCIe 2.1 x16	800	950	160:8:4	3.2	6.4	1024	30.4	GDDR5	64	256	11.0	4.4	9
Radeon HD 7510M	January 7, 2012	Thames LE	Turks	40	PCIe 2.1 x16	450	800	400:20:8	3.6	9.0	1024	12.8	DDR3	64	360	11.0	4.4	11
Radeon HD 7530M	January 7, 2012	Thames LP	Turks	40	PCIe 2.1 x16	450	900	400:24:8	3.6	9.0	1024	14.4	DDR3	64	360	11.0	4.4	11
Radeon HD 7550M	January 7, 2012	Thames Pro	Turks	40	PCIe 2.1 x16	450 550	900 800	400:20:8	3.6 4.4	9.0 11.0	1024	14.4 25.6	DDR3 GDDR5	64	360 440	11.0	4.4	13
Radeon HD 7570M	January 7, 2012	Thames Pro	Turks	40	PCIe 2.1 x16	450 650	900 800	400:20:8	3.6 5.2	9.0 13.0	1024	14.4 25.6	DDR3 GDDR5	64	360 520	11.0	4.4	13~15
Radeon HD 7590M	January 7, 2012	Thames XT	Turks	40	PCIe 2.1 x16	600	800	480:24:8	4.8	14.4	1024	25.6	GDDR5	64	576	11.0	4.4	18
Radeon HD 7610M	January 7, 2012	Thames LE	Turks	40	PCIe 2.1 x16	450	800	400:20:8	3.6	9.0	1024	25.6	DDR3	128	360	11.0	4.4	20
Radeon HD 7630M	January 7, 2012	Thames LP	Turks	40	PCIe 2.1 x16	450	800	480:24:8	3.6	10.8	1024	25.6	DDR3	128	432	11.0	4.4	20~25
Radeon HD 7650M	January 7, 2012	Thames Pro	Turks	40	PCIe 2.1 x16	450 550	800 800	480:24:8	3.6 4.4	10.8 13.2	1024	25.6	DDR3	128	432 528	11.0	4.4	20~25
Radeon HD 7670M	January 7, 2012	Thames Pro	Turks	40	PCIe 2.1 x16	600	900	480:24:8	4.8	14.4	1024	28.8 57.6	DDR3 GDDR5	128	576	11.0	4.4	20~25
Radeon HD 7690M	January 7, 2012	Thames XT	Turks	40	PCIe 2.1 x16	725 600	900 900	480:24:8	5.8 4.8	17.4 14.4	1024 2048	28.8 57.6	DDR3 GDDR5	128	696 576	11.0	4.4	20~25
Radeon HD 7690M XT	January 7, 2012	Thames XTX	Turks	40	PCIe 2.1 x16	725	900	480:24:8	5.8	17.4	1024 2048	57.6	GDDR5	128	696	11.0	4.4	25
Radeon HD 7730M	April 24, 2012	Chelsea LP	Cape Verde	28	PCIe 2.1 x16	575 675	900 900	512:32:16	9.2 10.8	18.4 21.6	2048	28.8	GDDR3	128	588.8 691.2	11.1	4.4	25~28
Radeon HD 7750M	April 24, 2012	Chelsea Pro	Cape Verde	28	PCIe 2.1 x16	575	1000	512:32:16	9.2	18.4	1024 2048	64	GDDR5	128	588.8	11.1	4.4	28
Radeon HD 7770M	April 24, 2012	Chelsea XT	Cape Verde	28	PCIe 2.1 x16	675	1000	512:32:16	10.8	21.6	1024 2048	64	GDDR5	128	691.2	11.1	4.4	32
Radeon HD 7850M	April 24, 2012	Heathrow Pro	Cape Verde	28	PCIe 3.0 x16	675	1000	640:40:16	10.8	27	2048	64	GDDR5	128	864	11.1	4.4	40
Radeon HD 7870M	April 24, 2012	Heathrow XT	Cape Verde	28	PCIe 3.0 x16	800	1000	640:40:16	12.8	32	2048	64	GDDR5	128	1024	11.1	4.4	40 - 45
Radeon HD 7970M	April 24, 2012	Wimbledon XT	Pitcairn	28	PCIe 3.0 x16	850	1200	1280:80:32	27.2	68	2048 4096	153.6	GDDR5	256	2176	11.1	4.4	75

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

IGP (HD 7xxxG)

See Radeon HD 7000 Series.

Radeon HD 8xxxM Series

• All models include OpenCL 1.2

Model	Launch	Model Number	Code name	Fab (nm)	Bus interface	Clock rate			Core config1	Fillrate		Memory				Processing Power (GFLOPS)	API compliance (version)		TDP (Watts) GPU only
						Core (MHz)	Boost (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type2	Bus width (bit)		Direct3D	OpenGL
Radeon HD 8550M/8630M	January 8, 2013	Mars	Oland	28	PCIe 3.0 x8	650	700	900	384:24:8	5.2 - 5.6	15.6 - 16.8	1024	14.4	DDR3	64	537.6	11.1	4.4	Unknown
Radeon HD 8570M/8650M	January 8, 2013	Mars	Oland	28	PCIe 3.0 x8	650	700	1125	384:24:8	5.2 - 5.6	15.6 - 16.8	1024	36	GDDR5	64	537.6	11.1	4.4	Unknown
Radeon HD 8670M	January 8, 2013	Mars	Oland	28	PCIe 3.0 x8	775	825	900	384:24:8	6.2 - 6.6	18.6 - 19.8	1024	14.4	DDR3	64	633.6	11.1	4.4	Unknown
Radeon HD 8690M	January 8, 2013	Mars	Oland	28	PCIe 3.0 x8	775	825	1125	384:24:8	6.2 - 6.6	18.6 - 19.8	1024	36	GDDR5	64	633.6	11.1	4.4	Unknown
Radeon HD 8730M	January 8, 2013	Mars LP	Oland	28	PCIe 3.0 x8	650	700	1000	384:24:8	5.2 - 5.6	15.6 - 16.8	2048	32	DDR3	128	537.6	11.1	4.4	Unknown
Radeon HD 8750M	January 8, 2013	Mars Pro	Oland	28	PCIe 3.0 x8	620 - 775	670 - 825	1000 1000	384:24:8	4.96 - 6.6	14.88 - 19.8	2048	32 64	DDR3 GDDR5	128	514.56 - 633.6	11.1	4.4	Unknown
Radeon HD 8770M	January 8, 2013	Mars XT	Oland	28	PCIe 3.0 x8	775	825	1125	384:24:8	6.2 - 6.6	18.6 - 19.8	2048	72	GDDR5	128	633.6	11.1	4.4	Unknown
Radeon HD 8790M	January 8, 2013	Mars XTX	Oland	28	PCIe 3.0 x8	850	900	1125	384:24:8	6.8 - 7.2	20.4 - 21.6	2048	72	GDDR5	128	691.2	11.1	4.4	Unknown
Radeon HD 8830M	January 8, 2013	Venus LE	Cape Verde	28	PCIe 3.0 x16	575	625	1000	640:40:16	9.2 - 10	23 - 25	2048	32	DDR3	128	800	11.1	4.4	Unknown
Radeon HD 8850M	January 8, 2013	Venus PRO	Cape Verde	28	PCIe 3.0 x16	575 - 725	625 - 775	1000 1125	640:40:16	9.2 - 12.4	23 - 31	2048	32 72	DDR3 GDDR5	128	800 - 992	11.1	4.4	Unknown
Radeon HD 8870M	January 8, 2013	Venus XT	Cape Verde	28	PCIe 3.0 x16	725	775	1000 1125	640:40:16	11.6 - 12.4	29 - 31	2048	32 72	DDR3 GDDR5	128	992	11.1	4.4	Unknown
Radeon HD 8970M	May 15, 2013	Neptune XT	Pitcairn	28	PCIe 3.0 x16	850	900	1200	1280:80:32	27.2 - 28.8	68 - 72	2048 4096	153.6	GDDR5	256	2304	11.1	4.4	100

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

Radeon Rx M2xx Series

Model	Launch	Model Number	Code name	Fab (nm)	Bus interface	Clock rate			Core config	Fillrate		Memory				Processing Power (GFLOPS)	API compliance (version)		TDP (Watts) GPU only
						Core (MHz)	Boost (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)		Direct3D	OpenGL
Radeon R5 M230	2014	Jet Pro	Oland	28	PCIe 3.0 x8	780	855	1000	320:20:4	3.4	17.1	2048 4096	16	DDR3	64	547	11.2	4.3	Unknown
Radeon R5 M255	June 2014	Jet Pro	Oland/Iceland	28	PCIe 3.0 x8	Unknown	940	1000	320:20:8	7.5	18.8	2048 4096	16	DDR3	64	601	11.2	4.3	Unknown
Radeon R7 M260	June 2014	Opal/Topaz	Oland/Iceland	28	PCIe 3.0 x8	Unknown	715 980	1000	384:24:8	5.7 7.8	17.2 23.5	2048 4096	32 16	DDR3	128 64	549.1 752.6	11.2	4.3	Unknown
Radeon R7 M260X	June 2014	Opal	Oland	28	PCIe 3.0 x8	Unknown	715	1000	384:24:8	5.7	17.2	2048 4096	64	GDDR5	128	549	11.2	4.3	Unknown
Radeon R7 M265	May 1, 2014	Opal XT	Oland	28	PCIe 3.0 x8	725	825	1000	384:24:8	6.6	19.8	2048 4096	16 32	DDR3	64 128	633.6	11.2	4.3	Unknown
Radeon R9 M265X	May 1, 2014	Venus Pro	Cape Verde	28	PCIe 3.0 x16	575	625	1125	640:40:16	10	25	2048 4096	72	GDDR5	128	800	11.2	4.3	Unknown
Radeon R9 M270X	May 1, 2014	Venus XT	Cape Verde	28	PCIe 3.0 x16	725	775	1125	640:40:16	12.4	31	2048 4096	72	GDDR5	128	992	11.2	4.3	Unknown
Radeon R9 M275X	May 1, 2014	Venus XTX	Cape Verde	28	PCIe 3.0 x16	900	925	1125	640:40:16	14.8	37	2048 4096	72	GDDR5	128	1184	11.2	4.3	50
Radeon R9 M280X	Feb 9, 2015	Saturn XT	Bonaire	28	PCIe 3.0 x16	1000	1100	1500	896:56:16	17.6	61.6	2048 4096	96	GDDR5	128	1792	11.2	4.3	~75
Radeon R9 M290X	May 1, 2014	Neptune XT	Pitcairn	28	PCIe 3.0 x16	850	900	1200	1280:80:32	28.8	72	4096	153.6	GDDR5	256	2176-2304	11.2	4.3	100
Radeon R9 M295X	2014		Tonga	28	PCIe 3.0 x16	750	800	1375	2048:128:32	25.6	102.4	4096	176	GDDR5	256	3276.8	11.2	4.3	125

Radeon Rx M3xx Series

Model	Launch	Model Number	Code name	Fab (nm)	Bus interface	Clock rate			Core config	Fillrate		Memory				Processing Power (GFLOPS)	API compliance (version)		TDP (Watts) GPU only
						Core (MHz)	Boost (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)		Direct3D	OpenGL
Radeon R5 M330[77]	2015	Exo Pro[78]	Oland	28	PCIe 3.0 x16	Unknown	1030	900[78] 1000	320:20:8	Unknown	Unknown	2048 4096	14.4 16	DDR3	64	658.5	12	4.3 Vulkan	18[78]
Radeon R7 M360[79]	2015	Meso XT [80]	Oland	28	PCIe 3.0 x16	Unknown	1125	1000	384:24:8	9	27	2048 4096	16	DDR3	64	864	12	4.3 Vulkan	Unknown
Radeon R9 M365X	2015	Strato Pro	Cape Verde	28	PCIe 3.0 x16	Unknown	925	1125	640:40:16	14.8	37	4096	72	GDDR5	128	1184	12	4.3 Vulkan	50
Radeon R9 M370X[81]	May, 2015	Unknown	Cape Verde	28	PCIe 3.0 x16	800	N/D	1125	640:40:16	12.8	32	2048	72	GDDR5	128	1024	12	4.3 Vulkan	40-45
Radeon R9 M375	2015	Strato Pro	Cape Verde	28	PCIe 3.0 x16	Unknown	1015	1100	640:40:16	16.2	40.6	4096	35.2	DDR3	128	1280	12	4.3 Vulkan	Unknown
Radeon R9 M375X	2015	Strato Pro	Cape Verde	28	PCIe 3.0 x16	Unknown	1015	1125	640:40:16	16.2	40.6	4096	72	GDDR5	128	1280	12	4.3 Vulkan	Unknown
Radeon R9 M380	2015	Strato Pro	Cape Verde	28	PCIe 3.0 x16	Unknown	1000	1500	640:40:16	16	40	4096	96	GDDR5	128	1280	12	4.3 Vulkan	Unknown
Radeon R9 M385X	2015	Unknown	Bonaire	28	PCIe 3.0 x16	Unknown	1100	1500	896:56:16	17.6	61.6	4096	96	GDDR5	128	1971.2	12	4.3 Vulkan	~75
Radeon R9 M390	June, 2015	Unknown	Pitcairn	28	PCIe 3.0 x16	Unknown	958	1365	1024:64:32	30.7	61.3	2048	174.7	GDDR5	256	1962	12	4.3 Vulkan	~100
Radeon R9 M390X	2015	Amethyst XT	Tonga	28	PCIe 3.0 x16	Unknown	723	1250	2048:128:32	23.1	92.5	4096	160	GDDR5	256	2961.4	12	4.3 Vulkan	125
Radeon R9 M395X	2015	Amethyst XT	Tonga	28	PCIe 3.0 x16	Unknown	909	1365	2048:128:32	29.1	116.3	4096	174.7	GDDR5	256	3723.2	12	4.3 Vulkan	125

Comparison table: Workstation GPUs

FireGL Series

Model	Launch	Core	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config	Fillrate		Memory				Processing Power (GFLOPS)	API compliance (version)		Notes
								Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Direct3D	OpenGL
FireGL 8700	2001	Radeon 8500	150	AGP	250	270	2:4:8:41	1	2	64	8.64	DDR	64 × 2	Unknown	8.1	1.4
FireGL 8800	2001	Radeon 8500	150	AGP	300	290	2:4:8:41	1.2	2.4	128	9.28	DDR	64 × 2	Unknown	8.1	1.4
FireGL T2-64	2003	Radeon 9600 Pro	130	AGP	325	200	2:4:4:41	1.3	1.3	64	6.4	DDR	128	Unknown	9.0	2.0
FireGL T2-128	2003	Radeon 9600 Pro	130	AGP	400	320	2:4:4:41	1.6	1.6	128	10.2	DDR	128	Unknown	9.0	2.0
FireGL Z1-128	2002	Radeon 9500 Pro	150	AGP	325	310	4:4:4:41	1.3	1.3	128	19.8	DDR	256	Unknown	9.0	2.0
FireGL X1-128	2002	Radeon 9700	150	AGP	325	310	4:8:8:81	2.6	2.6	128	19.84	DDR	256	Unknown	9.0	2.0
FireGL X1-256	2002	Radeon 9700 Pro	150	AGP Pro	325	310	4:8:8:81	2.6	2.6	256	19.84	DDR	256	Unknown	9.0	2.0
FireGL X2-256	2003	Radeon 9800 Pro	150	AGP	380	350	4:8:8:81	3.04	3.04	256	22.4	DDR2	256	Unknown	9.0	2.0
FireGL X2-256T	2003	Radeon 9800 XT	150	AGP	412	344	4:8:8:81	3.3	3.3	256	22.0	DDR2	256	Unknown	9.0	2.0
FireGL X3-256	2004	Radeon X800 XT	130	AGP	450	450	6:12:12:121	5.4	5.4	256	28.8	GDDR3	256	Unknown	9.0b	2.0
FireGL V3100	2005	Radeon X300 XT	110	PCIe x16	400	200	2:4:4:41	1.6	1.6	128	6.4	DDR	128	Unknown	9.0	2.0
FireGL V3200	2005	Radeon X600 XT	130	PCIe x16	500	400	2:4:4:41	2	2	128	12.8	DDR2	128	Unknown	9.0b	2.0
FireGL V3300	2006	Radeon 1300 Pro	90	PCIe x16	600	400	2:4:4:41	2.4	2.4	128	6.4	GDDR2	64	Unknown	9.0c	2.0
FireGL V3350	2006	Radeon 1300 Pro	90	PCIe x16	600	400	2:4:4:41	2.4	2.4	256	6.4	GDDR2	64	Unknown	9.0c	2.0
FireGL V3400	2006	Radeon 1600 Pro/XT	90	PCIe x16	500	500	5:12:4:41	2	2	128	16	GDDR3	128	Unknown	9.0c	2.0
FireGL V3600	2007	Radeon HD 2600 Pro	65	PCIe x16	600	500	1202(24×5):8:4	2.4	4.8	256	16.0	GDDR3	128	144	10	2.1
FireGL V5000	2005	Radeon X700 Pro/XT	130	PCIe x16	425	430	6:8:8:81	3.4	3.4	128	13.6	GDDR3	128	Unknown	9.0b	2.0
FireGL V5100	2005	Radeon X800 Pro	130	PCIe x16	450	350	6:12:12:121	5.4	5.4	128	22.4	DDR	256	Unknown	9.0b	2.0
FireGL V5200	2005	Radeon X1600 XT	90	PCIe x16	600	700	5:12:4:41	2.4	2.4	256	22.4	GDDR3	128	Unknown	9.0c	2.0
FireGL V5600	2007	Radeon HD 2600 XT	65	PCIe	800	1100	1202(24×5):8:4	3.2	6.4	512	35.2	GDDR4	128	192	10	2.1
FireGL V7100	2005	Radeon X800 XT	130	PCIe	500	450	6:16:16:161	8	8	256	28.8	GDDR3	256	Unknown	9.0c	2.0
FireGL V7200	2006	Radeon X1800 XT	90	PCIe x16	600	650	8:16:16:161	9.6	9.6	256	41.6	GDDR3	256	Unknown	9.0c	2.0
FireGL V7300	2006	Radeon X1800 XT	90	PCIe	600	650	8:16:16:161	9.6	9.6	512	41.6	GDDR3	256	Unknown	9.0c	2.0
FireGL V7350	2006	Radeon X1800 XT	90	PCIe	600	650	8:16:16:161	9.6	9.6	1024	41.6	GDDR3	256	Unknown	9.0c	2.0
FireGL V7400	2006 (Canceled)	Radeon X1950 Pro	80	PCIe	550?	650?	8:36:16:161	19.8?	19.8?	512?	41.6?	GDDR3	256	Unknown	9.0c	2.0	never released, superseded by 2007 Series
FireGL V7600	2007	Radeon HD 2900 GT	80	PCIe	600	800	2402(48×5):12:12	9.6	9.6	512	51.2	GDDR3	256	288	10	2.1
FireGL V7700	2007 (2008)	Radeon HD 3870	55	PCIe 2.0	775	1125	3202(64×5):16:16	12.4	12.4	512	72	GDDR4	256	496	10.1 (SM 4.0 only)	2.1	DisplayPort. Can do double precision computation via the AMD Stream SDK.
FireGL V8600	2007	Radeon HD 2900 XT	80	PCIe	688	868	3202(64×5):16:16	11.008	11.008	1024	111.1[82]	GDDR4	512	440.32	10	2.1
FireGL V8650	2007	Radeon HD 2900 XT	80	PCIe	688	868	3202(64×5):16:16	11.008	11.008	2048	111.1	GDDR4	512	440.32	10	2.1

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

FirePro 3D Series (Vxxx)

Model	Launch	Code name	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing Power (GFLOPS)		API compliance (version)			TDP watts	Notes
							Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Double Precision	Direct3D	OpenGL	OpenCL
FirePro 3D V3700	August 8, 2008	RV620[83]	55	Unknown	Unknown	PCIe 2.0 x16	800	950	40(8×5):4:4	3.2	3.2	256	15.2	GDDR3	64	64	-	10.1	3.0	-	32	UVD+, PowerPlay
FirePro 3D V3750	September 11, 2008	RV730	55	Unknown	Unknown	PCIe 2.0 x16	550	750	320(64×5):32:8	4.4	17.6	256	24	GDDR3	128	352	-	10.1	3.3	-	48	UVD2, PowerPlay
FirePro 3D V3800[84]	April 26, 2010	Redwood Pro(RV830)	40	Unknown	Unknown	PCIe 2.1 x16	650	900	400(80×5):20:8	5.2	13	512	14.4	GDDR3	64	520	-	11.0	4.1	1.1	43	UVD2, PowerPlay, Eyefinity
FirePro 3D V4800[85]	April 26, 2010	Redwood XT(RV830)	40	672	104	PCIe 2.1 x16	775	9002	400(80×5):20:8	6.2	15.5	1024	57.6	GDDR52	128	620	-	11.0	4.1 SL 5	1.1	69	UVD2, PowerPlay, Eyefinity
FirePro 3D V5700	August 8, 2008	RV730	55	Unknown	Unknown	PCIe 2.0 x16	700	900	320(64×5):32:8	5.6	22.4	512	28.8	GDDR3	128	448	-	10.1	3.3	-	58	UVD2, PowerPlay
FirePro 3D V5800[84]	April 26, 2010	Juniper XT(RV840)	40	Unknown	Unknown	PCIe 2.1 x16	700	10002	800(160×5):40:16	11.2	28	1024	64	GDDR52	128	1120	-	11.0	4.1	1.1	74	UVD2, PowerPlay, Eyefinity
FirePro 3D V7750	March 27, 2009	RV730	55	Unknown	Unknown	PCIe 2.0 x16	800	900	320(64×5):32:8	6.4	25.6	1024	28.8	GDDR3	128	512	-	10.1	3.3	-	76	UVD2, PowerPlay
FirePro 3D V7800[85]	April 26, 2010	Cypress Pro(RV870)	40	Unknown	Unknown	PCIe 2.1 x16	700	10002	1440(288×5):72:32	22.4	50.4	2048	128	GDDR52	256	2016	403.2	11.0	4.1	1.1	138	UVD2, PowerPlay, Eyefinity
FirePro 3D V8700	September 11, 2008	RV770 XT	55	Unknown	Unknown	PCIe 2.1 x16	750	8502	800(160×5):40:16	12	30	1024	108.8	GDDR52	256	1200	240	10.1	3.3	-	151	UVD2, PowerPlay
FirePro 3D V8750	July 28, 2009	RV770 XT	55	Unknown	Unknown	PCIe 2.1 x16	750	9002	800(160×5):40:16	12	30	2048	115.2	GDDR52	256	1200	240	10.1	3.3	-	154	UVD2, PowerPlay
FirePro 3D V8800	April 7, 2010	Cypress XT(RV870)	40	Unknown	Unknown	PCIe 2.1 x16	825	11502	1600(320×5):80:32	26.4	66	2048	147.2	GDDR52	256	2640	528	11.0	4.1	1.1	208	UVD2, PowerPlay, Eyefinity
FirePro 3D V9800	September 9, 2010	Cypress XT(RV870)	40	Unknown	Unknown	PCIe 2.1 x16	850	11502	1600(320×5):80:32	27.2	68	4096	147.2	GDDR52	256	2720	544	11.0	4.1	1.1	225	UVD2, PowerPlay, Eyefinity

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

FirePro Series (Vxxx)

Model	Launch	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing Power (GFLOPS)		API compliance (version)			TDP watts	Notes
					Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Double Precision	Direct3D	OpenGL	OpenCL
FirePro V3900	February 7, 2012	Turks	40	PCIe 2.1 x16	650	900	480(96×5):24:8	5.2	15.6	1024	28.8	GDDR3	128	624	-	11.0	4.2	1.1	50	HD3D, UVD3, DP 1.2, PowerPlay, Eyefinity
FirePro V4900	November 1, 2011	Turks	40	PCIe 2.1 x16	800	1000	480(96×5):24:8	6.4	19.2	1024	64	GDDR52	128	768	-	11.0	4.2	1.1	<75 Max	HD3D, UVD3, DP 1.2, PowerPlay, Eyefinity
FirePro V5900	May 24, 2011	Cayman LE GL	40	PCIe 2.1 x16	600	5002	512(128×4):32:32	19.2	19.2	2048	64	GDDR52	256	610	154	11.0	4.2	1.1	<75 Max	HD3D, UVD3, DP 1.2, PowerPlay, Eyefinity
FirePro V7900	May 24, 2011	Cayman Pro GL	40	PCIe 2.1 x16	725	12502	1280(320×4):80:32	23.2	58	2048	160	GDDR52	256	1860	464	11.0	4.2	1.1	<150 Max	HD3D, UVD3, DP 1.2, PowerPlay, Eyefinity

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

FirePro Workstation Series (Wx000)

Model	Launch	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing Power (GFLOPS)		API compliance (version)			TDP watts	Notes
					Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Double Precision	Direct3D	OpenGL	OpenCL
FirePro W600	June 13, 2012	Cape Verde Pro	28	PCIe 3.0 x16	750	1000	512:32:16			2048	64	GDDR5	128			11.1	4.2	1.2	75	Six Mini DisplayPort
FirePro W5000	June 13, 2012	Pitcairn LE	28	PCIe 3.0 x16	825	800	768:48:32	26.4	39.6	2048	102.4	GDDR5	256	1267.2	79.2	11.1	4.2	1.2	<75	Two DisplayPort, One DVI-I
FirePro W7000	June 13, 2012	Pitcairn XT	28	PCIe 3.0 x16	950	1200	1280:80:32	30.4	76	4096	153.6	GDDR5	256	2432	152	11.1	4.2	1.2	<150	ECC RAM, Four DisplayPort
FirePro W8000	June 14, 2012	Tahiti PRO	28	PCIe 3.0 x16	900	1375	1792:112:32	28.8	100.8	4096	176	GDDR5	384	3225.6	806.4	11.1	4.2	1.2	189	ECC RAM, Four DisplayPort + SDI-Link
FirePro W9000	June 14, 2012	Tahiti XT	28	PCIe 3.0 x16	975	1375	2048:128:32	31.2	124.8	6144	264	GDDR5	384	3993.6	998.4	11.1	4.2	1.2	<274	ECC RAM, Six Mini DisplayPort + SDI-Link

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

FirePro Workstation Series (Wx100)

Model	Launch	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing Power (GFLOPS)		API compliance (version)			TDP watts	Notes
					Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Double Precision	Direct3D	OpenGL	OpenCL
FirePro W2100[86]	August 13, 2014	Oland XT	28	PCIe 3.0 x8	630	900	320:20:8	5.04	12.6	2048	28.8	DDR3	128	403.2	25.5	11.2	4.4	1.2	<26	Two Standard DisplayPort 1.2a outputs
FirePro W4100[87]	August 13, 2014	Cape Verde	28	PCIe 3.0 x16	630	1125	512:32:16	10.08	20.16	2048	72	GDDR5	128	645.1	40.3	11.2	4.4	1.2	<50	Four Standard Mini-DisplayPort 1.2a outputs
FirePro W5100[88]	August 13, 2014	Bonaire Pro	28	PCIe 3.0 x16	930	1500	768:48:16	14.88	44.64	4096	96	GDDR5	128	1430	89.2	11.1/12	4.4	2.0	<75	DirectGMA, GeometryBoost, Four Standard DisplayPort display outputs, DisplayPort 1.2a support, including Adaptive-Sync and HBR2 support
FirePro W7100[89]	August 13, 2014	Tonga Pro GL	28	PCIe 3.0 x16	920	1400	1792:112:32	29.4	103	8192	160	GDDR5	256	3297	206	11.2/12	4.4	2.0	<150	DirectGMA, GeometryBoost, Four Standard DisplayPort display outputs, DisplayPort 1.2a support, including Adaptive-Sync and HBR2 support
FirePro W8100[90]	June 26, 2014	Hawaii Pro GL	28	PCIe 3.0 x16	824	1250	2560:160:64	52.7	145	8192	320	GDDR5	512	4218.9	2109.45	11.1	4.3	2.0	220	ECC RAM, Four DisplayPort + SDI-Link
FirePro W9100	March 26, 2014	Hawaii XT	28	PCIe 3.0 x16	930	1250	2816:176:64	59.5	163.7	16384	320	GDDR5	512	5237.8	2618.9	11.1	4.3	2.0[91]	275	ECC RAM, Six Mini DisplayPort + SDI-Link

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

FirePro Workstation Series (Wx300)

Model	Launch	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing Power (GFLOPS)		API compliance (version)			TDP watts	Notes
					Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Double Precision	Direct3D	OpenGL	OpenCL
FirePro W4300[92]	December 1, 2015	Bonaire PRO	28	PCIe 3.0 x16	930	1500	768:48:16[93]	14.88	44.64	4096	96	GDDR5	128	1428.48	89.28	12 SM5	4.4	2.0	<50	Four Mini DisplayPort 1.2a outputs, low profile

FirePro Server Series (Sxxxx/Sxx xxx)

Model	Launch	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing Power (GFLOPS)		API compliance (version)			TDP watts	Notes
					Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Double Precision	Direct3D	OpenGL	OpenCL
FirePro S7000	August 27, 2012	Pitcairn XT	28	PCIe 3.0 x16	950	1200	1280:80:32	30.4	76	4096	153.6	GDDR5	256	2432	152	11.1	4.2	1.2	<150	One DisplayPort
FirePro S9000	August 27, 2012	Tahiti PRO	28	PCIe 3.0 x16	900	1375	1792:112:32	28.8	100.8	6144	264	GDDR5	384	3225.6	806.4	11.1	4.2	1.2	<225	ECC RAM, One DisplayPort
FirePro S9050 [94]	August 6, 2014	Tahiti PRO	28	PCIe 3.0 x16	900	1375	1792:112:32	28.8	100.8	12288	264	GDDR5	384	3225.6	806.4	11.1	4.2	1.2	<225	ECC RAM, One DisplayPort
FirePro S9150 [95]	August 6, 2014	Hawaii XT	28	PCIe 3.0 x16	900	1375	2816:176:64	57.6	158.4	16384	320	GDDR5	512	5070	2530	11.1	4.2	1.2	<235	ECC RAM, None of physical display outputs
FirePro S9170 [96]	July 8, 2015	Grenada XT	28	PCIe 3.0 x16	930	1375	2816:176:64	59.52	163.68	32768	320	GDDR5	512	5240	2620	12	4.4	2.0	<275	ECC RAM, optimized for Full Throughput double precision, None of physical display outputs
FirePro S10000	November 12, 2012	2× Tahiti PRO	28	PCIe 3.0 x16	825	1250	2× 1792:112:32	52.8	184.8	2× 3072	2× 240	GDDR5	384	5913.6	1478.4	11.1	4.2	1.2	<375	ECC RAM, Four Mini DisplayPort, One DVI-I

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

Radeon Sky Series

Model	Launch	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing Power (GFLOPS)		API compliance (version)			TDP watts	Notes
					Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Double Precision	Direct3D	OpenGL	OpenCL
Radeon Sky 500	April, 2013	Pitcairn XT	28	PCIe 3.0 x16	950	1200	1280:80:32	30.4	76	4096	153.6	GDDR5	256	2432	152	11.1	4.2	1.2	150	One DisplayPort
Radeon Sky 700	April, 2013	Tahiti PRO	28	PCIe 3.0 x16	900	1375	1792:112:32	28.8	100.8	6144	264	GDDR5	384	3225.6	806.4	11.1	4.2	1.2	225	One DisplayPort
Radeon Sky 900	April, 2013	2× Tahiti PRO	28	PCIe 3.0 x16	825	1250	2× 1792:112:32	52.8	184.8	2× 3072	2× 240	GDDR5	384	5913.6	1478.4	11.1	4.2	1.2	300	Four Mini DisplayPort, One DVI-I

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

FireMV (Multi-View) Series

Model	Launch	Core	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate (GT/s)	Memory				API compliance (version)		TDP / idle (watts)	Notes
								Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
FireMV 2200 PCI		RV280	PCI	Unknown	Unknown	1:4:4:4	Unknown	64	Unknown	Unknown	Unknown	8.1	1.4	Unknown	DMS-59 for dual DVI-D output
FireMV 2200 PCIe	Unknown	RV370	PCIe x16	Unknown	Unknown	2:4:4:4	Unknown	128	Unknown	Unknown	Unknown	9.0	2.1	Unknown	DMS-59 for dual DVI-D output
FireMV 2260	2008	RV620	PCIe 2.0 x1/x16, PCI	Unknown	Unknown	40(8×5):4:4	Unknown	256	8	DDR2	Unknown	10.1[97]	3.2	15/8	Dual DisplayPort (with adapters: DVI-D)
FireMV 2400 PCI	Unknown	RV380	PCI	Unknown	Unknown	2:4:4:4	Unknown	128	Unknown	Unknown	Unknown	9.0	2.1	Unknown	2x VHDCI for quad DVI-D output, VGA
FireMV 2400 PCIe	Unknown	RV380	PCIe x1	Unknown	Unknown	2:4:4:4	Unknown	256	Unknown	Unknown	Unknown	9.0	2.1	Unknown	2x VHDCI for quad DVI-D output, VGA

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

FirePro (Multi-View) Series

Model	Launch	Core	Fab (nm)	Transistors (Million)	Die Size (mm2)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate		Memory				API compliance (version)		TDP / idle (watts)	Notes
										Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Direct3D	OpenGL
FirePro 2250	2007	RV516	Unknown	Unknown	Unknown	PCIe x1/x16	Unknown	Unknown	2:4:4:4	Unknown	Unknown	256	Unknown	Unknown	Unknown	9.0	2.1	20/11	DMS-59 for dual DVI-D output
FirePro 2270	January 31, 2011	Cedar	40	292	59	PCIe 2.1 x1/x16	600	600	80(16×5):8:4	2.4	4.8	512 1024	9.6	GDDR3	64	11.0	4.1	15/8 17/8	DMS-59 for dual output: DP or DVI-I or D-sub
FirePro 2450 Multi-View	2009	2x RV620	Unknown	Unknown	Unknown	PCIe 2.0 x1/x16	Unknown	Unknown	2x 40(8×5):4:4	Unknown	Unknown	512	Unknown	GDDR3	Unknown	10.1	3.3	36/18	2x VHDCI for quad output: DVI-I or D-sub
FirePro 2460 Multi-View[98]	April 2010	Cedar (RV810)	Unknown	Unknown	Unknown	PCIe 2.1 x16	Unknown	Unknown	80(16×5):8:4	Unknown	Unknown	512	16	GDDR5	64	11	4.1	17/13	4x Mini DP for quad output: DP or DVI-D, UVD2, PowerPlay, Eyefinity

FireStream Series

• FireStream 9170-92xx include Direct3D 10.1 and OpenGL 3.0
• FireStream 93xx include Direct3D 11, OpenGL 4.0 and OpenCL 1.0

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

FirePro Remote Series

Model	Launch	Code name	Fab (nm)	Bus interface	Clock rate		Core config1	Fillrate		Memory				Processing Power (GFLOPS)		API compliance (version)			TDP watts	Notes
					Core (MHz)	Memory (MHz)		Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Double Precision	Direct3D	OpenGL	OpenCL
FirePro RG220	May 2010	RV711	55	PCIe 2.0 x16	500	800	80(16×5):8:4	2.0	4.0	512	12.8	GDDR3 for GPU, RDRAM for PCoIP	64	80	No	10.1	3.3	None	35	Dual Ethernet ports plus DMS-59 for dual DVI-D output (no VGA host output)
FirePro R5000	February 25, 2013	Pitcairn LE	28	PCIe 3.0 x16	825	800	768:48:32	26.4	39.6	2048	102.4	GDDR5	256	1267.2	79.2	11.1	4.2	1.2	<150	Ethernet port plus Two Mini DisplayPort w/ Tera2 PCoIP

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

Comparison table: Mobile Workstation GPUs

Mobility FireGL Series

Model	Launch	Model Number	Based on	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config	Fillrate		Memory				Processing Power (GFLOPS)	API compliance (version)		Notes
									Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Direct3D	OpenGL
Mobility FireGL 7800	2001	M7-GL	Mobility Radeon 7500	180	AGP	280	200	0:2:2:21	0.56	0.56	64	6.4	DDR	128	Unknown	7	1.3
Mobility FireGL 9000	2002	M9	Mobility Radeon 9000	150	AGP 4x	250	200	1:4:4:41	1	1	64	6.4	DDR	128	Unknown	8.1	1.3
Mobility FireGL T2	2003	M10	Mobility Radeon 9600	130	AGP 4x	320	200	2:4:4:41	1.28	1.28	128	6.5	DDR	128	Unknown	9.0	2.0
Mobility FireGL T2e	2004	M11GL	Mobility Radeon 9700	130	AGP	450	225	2:4:4:41	1.8	1.8	128	7.2	DDR	128	Unknown	9.0	2.0
Mobility FireGL V3100	2004	M22GL	Mobility Radeon X300	110	PCIe x16	350	200	2:4:4:41	1.4	1.4	128	6.4	DDR	128	Unknown	9.0b	2.0
Mobility FireGL V3200	2004	M24GL	Mobility Radeon X600	130	PCIe x16	400	250	2:4:4:41	1.6	1.6	128	12.8	DDR2	128	Unknown	9.0b	2.0
Mobility FireGL V5000	2005	M26GL	Mobility Radeon X700	110	PCIe x16	350	425	6:8:8:81	2.8	2.8	128	13.6	GDDR3	128	Unknown	9.0b	2.0
Mobility FireGL V5200	2006	M56GL	Mobility Radeon X1600	90	PCIe x16	425	475	5:12:12:121	5.1	5.1	256	15.2	GDDR3	128	Unknown	9.0c	2.0
Mobility FireGL V5250	2007	M66GL	Mobility Radeon X1700	90	PCIe x16	450	350	5:12:12:121	5.4	5.4	256	11.2	GDDR3	128	Unknown	9.0c	2.0
Mobility FireGL V5600	2007	M76GL	Mobility Radeon HD 2600	65	PCIe 2.0 x16	500	400	1202(24×5):8:4	2	4	256	12.8	GDDR3	128	120	10.1	2.1
Mobility FireGL V5700	2008	M86GL	Mobility Radeon HD 3650	55	PCIe 2.0 x16	600	700	1202(24×5):8:4	2.4	4.8	512	22.4	GDDR3	128	144	10.1	2.1	Used in Lenovo ThinkPad W500
Mobility FireGL V5725	2008	M86GL	Mobility Radeon HD 3650	55	PCIe 2.0 x16	680	800	1202(24×5):8:4	2.72	5.44	256	25.6	GDDR3	128	163.2	10.1 SM 4.1	2.1

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

FirePro Mobile Series

Model	Launch	Model Number	Based on	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config	Fillrate		Memory				Processing Power (GFLOPS)		API compliance (version)			Notes
									Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single Precision	Double Precision	Direct3D	OpenGL	OpenCL
FirePro M5725	Unknown	Unknown	Radeon HD 4670	55	PCIe 2.0 x16	Unknown	Unknown	3202(64×5):32:8	Unknown	Unknown	256	Unknown	GDDR3	128	Unknown		10.1 SM 4.1	3.2
FirePro M5800	March 1, 2010	Redwood XT (RV830)	Radeon HD 5730	40	PCIe 2.0 x16	650	800	4002(80×5):20:8	5.2	13	1024	25.6	GDDR5	128	520		11 SM 5	3.2		HP EliteBook 8540w
FirePro M3900		Seymour XT		40	PCIe 2.1 x16	700	900	160			1024	14.4	DDR3	64	224		11	4.3	1.2	HP Elitebook 8460w
FirePro M5950	2011	Whistler XT	Radeon HD 6770M	40	PCIe 2.1 x16	725	900	4802(96×5):24:8	5.8	17.4	1024	57.6	GDDR5	128	696		11	4.3	1.2	Dell Precision M4600
FirePro M7740	August 4, 2009	M97GL (RV740)	Radeon HD 4860	40	PCIe 2.0 x16	650	1000	6402(128×5):32:16	10.4	20.8	1024	64	GDDR5	128	832		10.1 SM 4.1	3.2		Dell M6400 and M6500
FirePro M7820	May 1, 2010	Juniper XT (RV840)	Radeon HD 5870	40	PCIe 2.0 x16	700	1000	8002(160×5):40:16	11.2	28	1024	64	GDDR5	128	1120		11	4.1	1.1	Dell M6500, HP EliteBook 8740w
FirePro M8900	2011	Blackcomb XT	Radeon HD 6970M	40	PCIe 2.1 x16	680	900	9602(192×5):48:32	21.76	32.64	2048	115.2	GDDR5	256	1310		11	4.3	1.2	UVD3, Dell M6600
FirePro M2000	2012	Turks	Radeon HD 7590M	40	PCIe 2.1 x16	500	800	4802:24:8	4	12	1024	25.6	GDDR5	64	480		11	4.3	1.2	HP EliteBook 8470w
FirePro M4000	2012	Cape Verde	Radeon HD 7770M	28	PCIe 2.1 x16	600	1000	5122:32:16	9.6	19.2	2048	51.2	GDDR5	128	614		11	4.3	1.2	HP EliteBook 8570w, HP EliteBook 8770w, Dell Precision M4700
FirePro M6000	2012	Cape Verde	Radeon HD 7870M	28	PCIe 3.0 x16	800	1000	6402:40:16	12	30	2048	64	GDDR5	128	960		11	4.3	1.2	Dell Precision M6700
FirePro M4100	2013	Oland	Radeon HD 8750M	28	PCIe 3.0 x16	670	1000	3842:24:8	5.4	16.1	2048	64	GDDR5	128	514	32	11	4.3	1.2	HP ZBook 14
FirePro W4170M	2014	Mars		28	PCIe 3.0 x16	825	1125	3842:24:8	6.6	19.8	2048	72	GDDR5	128	691.2	43.2	12 SM 5	4.4	1.2	Dell Precision M2800, HP ZBook 15u G2
FirePro W4190M	2015				PCIe 3.0 x16						2048		GDDR5	128			12 SM 5	4.4	1.2	HP ZBook 15u G3
FirePro M5100	2013	Cape Verde	Radeon HD 8870M	28	PCIe 3.0 x16	775	1125	6402:40:16	12.4	31	2048	72	GDDR5	128	992	62	12 SM 5	4.4	1.2	Dell Precision M4800, Panasonic Toughbook 54, HP Zbook 15
FirePro W5130M	2015	Tropo LE	GCN 1.0	28	PCIe 3.0 x16	up to 925	1000	512:32:16	14.4	28.8	up to 2048	64	GDDR5	128	up to 950	up to 59.4	12 SM 5	4.4	1.2	Dell Precision 3510
FirePro W5170M	2015	Tropo XT	GCN 1.0	28	PCIe 3.0 x16	up to 925	1125	640:40:16	14.4	36.0	up to 2048	72	GDDR5	128	up to 1180	up to 73.8	12 SM 5	4.4	1.2	Dell Precision 7510, Dell Precision 7710, HP ZBook 15 G3
FirePro M6100	2013	Bonaire	Radeon R9 M280X	28	PCIe 3.0 x16	up to 1100	1500	8962:56:16	17.6	61.6	2048	96	GDDR5	128	1971.2	103	12 SM 5	4.4	1.2	Dell Precision M6800, HP Zbook 17 G2
FirePro W6150M	2015				PCIe 3.0 x16						4096		GDDR5	128			12 SM 5	4.4	1.2	HP Zbook 17 G3
FirePro W7170M	2015	Amethyst XT	GCN 1.2	28	PCIe 3.0 x16	723	1250	2048:128:32	23.1	92.5	4096	160	GDDR5	256	2960	185	12 SM 5	4.5	2.0	Dell Precision 7710

² Unified Shaders : Texture mapping units : Render output units

Comparison table: Console GPUs

Console graphics processors

Model	Launch	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Core config1	Fillrate				Memory					API compliance (version)			Processing Power (GFLOPS)	Notes
							MOperations/s	MPixels/s	MTextels/s	Vertices/s	Size (MiB)	Clock (MHz)	Bandwidth (GB/s)	RAM type	Bus width (bit)	Direct3D	OpenGL	other
Flipper (GameCube) [99][100][101]	September 14, 2001		180	Integrated	162	4:1:4:41	648	648	648	90	24 shared 16 shared 3 eDRAM	324 81 162	3.2 0.08 12.8/7.63	1T-SRAM SDRAM eDRAM	64 8	No	Unknown	Unknown	9.4	Fixed-function T&L, TEV pixel shader
Xenos (Xbox 360) [102]	November 22, 2005	Xenon Zephyr Opus Falcon Jasper Vejle Corona	90/90 90/90 90/80 80/80 65/80 45/65 45/45	Integrated	500	48:16:82	240,000	4000	8000	6000	512 (shared) 10 eDRAM	700 500	22.4 32 (GPU to daughter die) 256 (Daughter die ROP to eDRAM)	GDDR3 eDRAM	128	9.0c+	No	Unknown	240	Surface tessellation
Hollywood (Wii)	November 19, 2006		90	Integrated	243	4:1:4:41	972	972	972	135	24 shared 64 shared 3 eDRAM	486 Unknown 243	4.8 4 19.2/11.4	1T-SRAM GDDR3 eDRAM	64 Unknown Unknown	No	Unknown	Unknown	14.1	Fixed-function T&L, TEV pixel shader
Latte (Wii U)	November 18, 2012		45	Integrated	550	320:16:82	352,000	4400	8800	Unknown	2048 (shared) 32 eDRAM	800 (1600 effective) 550	12.8 70.4	DDR3 eDRAM	64 1024	No	Unknown	Unknown	352
Liverpool (PlayStation 4)	November 15, 2013	Liverpool	28	Integrated	800	1152:72:32	1,843,200	25,600	57,600	Unknown	8192 (shared)	1375 (5500 effective)	176	GDDR5	256	No	4.2	GNM, GNMX, PlayStation Shader Language, Mantle technically possible	1843.2
Durango (Xbox One)	November 22, 2013	Durango	28	Integrated	853	768:48:16	1,310,208	13,648	40,944	Unknown	8192 (shared) 32 eSRAM	1066.5 (2133 effective) 1706 (3412 effective)	68.2 204	DDR3 eSRAM	256	11.2 [103]	No	Mantle technically possible	1310.2	Tiled resources
Model	Launch	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Core config1	MOperations/s	MPixels/s	MTextels/s	Vertices/s	Size (MB)	Clock (MHz)	Bandwidth (GB/s)	RAM type	Bus width (bit)	Direct3D	OpenGL	Other	Processing Power (GFLOPS)	Notes
							Fillrate				Memory					API compliance (version)

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

• The Latte looks similar to the RV730 used in the Radeon HD4650/4670.^[104] Although It's an even closer possibly exact specification match to the HD5550 as it has exactly the same clock, number of Shaders, Texture mapping units & Render Outputs^[105]

See also

• ATI video card suffixes
• List of AMD chipsets
• List of AMD Accelerated Processing Unit microprocessors
• Comparison of AMD processors
• List of Nvidia graphics processing units
• List of Intel graphics processing units

References

External links

• Old ATi legacy portal on the AMD domain
• AMD Radeon 6970 Performance Comparison
• Public AMD GPU specifications on X.org website
• Video Card Comparison on GPUReview.com
• TechPowerUp! GPU Database

AMD graphics   Radeon-brand (List of GPUs, Template:AMD GPU features and List of APUs, Template:AMD APU features) Fixed pipeline Wonder Mach Rage R100 R200 R300 R400 R500 All-in-Wonder Unified shaders TeraScale HD 2000 HD 3000 HD 4000 HD 5000 HD 6000 Unified shaders & memory GCN HD 7000 HD 8000 Rx 200 Rx 300 Rx 400   Current technologies and software Audio/Video acceleration Unified Video Decoder (UVD) Video Coding Engine (VCE) TrueAudio GPU technologies Eyefinity (multi-monitor) FreeSync (variable refresh rate) PowerTune (power-saving) CrossFireX (multi-GPU) Hybrid Graphics HyperMemory HyperZ Mantle HSA Software current Radeon Software Mantle HD3D AMD CodeXL GPU PerfStudio AMD APP SDK GPUOpen TressFX HLSL2GLSL unsuccessful Catalyst Close to Metal   Other brands and products Workstations & Supercomputers FireGL/FirePro (certified OpenGL) FireMV (multi-monitor) FireStream (stream processing & GPGPU) Consoles Flipper (GameCube) Xenos (Xbox 360) Hollywood (Wii) Latte (Wii U) AMD Liverpool (PlayStation 4) AMD Durango (Xbox One)