Radeon HD 8000 series

The Radeon HD 8000 series is a family of computer GPUs developed by AMD. AMD was initially rumored to release the family in the second quarter of 2013,^[9][10][11] with the cards manufactured on a 28 nm process and making use of the improved Graphics Core Next architecture.^[12] However the 8000 series turned out to be an OEM rebadge of the 7000 series (although Bonaire is a GCN 2.0 based chip, thus being of newer development).

AMD Radeon HD 8000 series (OEM)

Release date	Q2 2013
Codename	Southern Islands Sea Islands Solar System Richland Kabini
Architecture	TeraScale 2 TeraScale 3 GCN 1st gen GCN 2nd gen
Transistors	292M (Cedar) 40 nm 370M (Caicos) 40 nm 950M (Oland) 28 nm 1.500M (Cape Verde) 28 nm 2.080M (Bonaire) 28 nm 2.800M (Pitcairn) 28 nm 4.313M (Tahiti) 28 nm 2 x 4.313M (Malta) 28 nm
Cards
Entry-level	8350 8450 8470 8490 8570 8670 8730
Mid-range	8760 8770
High-end	8870 8950 8970
Enthusiast	8990
API support
Direct3D	Direct3D 12.0 (feature level 11_1) (GCN version) [1] Shader Model 6.5 (GCN) or Shader Model 5.0
OpenCL	OpenCL 2.1 (GCN version)
OpenGL	OpenGL 4.5[2][3][4][5][6] OpenGL 4.6 (GCN only, Windows 7+ and Adrenalin 18.4.1+, Linux) [7]
Vulkan	Vulkan 1.2 (GCN, Windows),[8] Vulkan 1.3 (GCN, Linux), or none (TeraScale) SPIR-V
History
Predecessor	Radeon HD 7000 series
Successor	Radeon R5/R7/R9 200 series
Support status
Unsupported

Architecture

The Radeon HD 7000 series was launched in 2011 and it marked AMD's shift from VLIW (TeraScale) to RISC/SIMD architecture (Graphics Core Next). The highend-mainstream cards were equipped with GCN-based chips while some of the mid-low end ones were just rebranded TeraScale-based cards. All of the GCN-based chips were made using the 28 nm process, becoming the first chips ever to be based on that technology. The GCN-based chips for desktop cards were codenamed as Southern Islands, while the mobile ones (again, only the GCN-based and not the rebranded ones) were codenamed as Solar System.

Multi-monitor support

Main article: AMD Eyefinity

The AMD Eyefinity-branded on-die display controllers were introduced in September 2009 alongside the Radeon HD 5000 series and have been present on all chips since then.^[13]

Video acceleration

Both Unified Video Decoder (UVD) and Video Coding Engine (VCE) are present on all GCN-based chips (starting with the GCN 1.0 HD 7000 series). Both are fully supported by AMD Catalyst and by the free and open-source graphics device driver#ATI/AMD.

OpenCL (API)

OpenCL accelerates many scientific Software Packages against CPU up to factor 10 or 100 and more. OpenCL 1.0 to 1.2 are supported for all Chips with TeraScale and GCN Architecture. OpenCL 2.0 is supported with GCN 2nd Gen. or 1.2 and higher) ^[14] For OpenCL 2.1 and 2.2 only Driver Updates are necessary with OpenCL 2.0 conformant Cards.

Vulkan (API)

API Vulkan 1.0 is supported for all with GCN Architecture. Vulkan 1.1 (GCN 2nd Gen. or 1.2 and higher) will be supported with actual drivers in 2018 (here only HD 8770).^{[14][needs update]} On newer drivers Vulkan 1.1 on Windows and Linux is supported on all GCN-architecture based GPUs. Vulkan 1.2 is available with Adrenalin 20.1 and Linux Mesa 20.0 for GCN 2nd Gen. or higher.

Chipset table

Main articles: List of AMD graphics processing units and List of AMD Accelerated Processing Unit microprocessors

Desktop models

• Graphics Core Next (GCN) supports the Mantle API and Vulkan API
• OpenGL 4.5 support for TeraScale 2 with AMD Crimson Beta (driver version 15.30 or higher)
• OpenGL 4.5 and Vulkan 1.0 support for GCN 1.0 and higher with AMD Crimson 16.3 or higher.^[15][16]
• Vulkan 1.1 support for GCN 1.0 and higher with AMD Adrenalin 18.3.3 or higher.^[17]

[ VisualEditor ]

• view
• talk
• edit

Model (Codename)	Launch	Architecture (Fab)	Transistors Die Size	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory[e]				TDP (W)	Bus interface
				Config[f]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (MiB)	Bus type & width (bit)	Clock (MHz)	Band- width (GB/s)	Idle Max
Radeon HD 8350 (Cedar)	January 8, 2013	TeraScale 2[g] (40 nm)	292×106 59 mm2	80:8:4	400–650	3.2 5.2	1.6 2.6	104	—	256 512	DDR2 DDR3 64-bit	400 800	6.4 12.8	6.4 19.1	PCIe 2.1 ×16
Radeon HD 8450 (Caicos)	January 8, 2013		370×106 67 mm2	160:8:4	625	5.0	2.5	200	—	512	DDR3 64-bit	533	8.53	9 18
Radeon HD 8470 (Caicos)	January 8, 2013				750	6.0	3.0	240	—	1024	GDDR5 64-bit	800	25.6	9 35
Radeon HD 8490 (Caicos)	July 23, 2013				875	7.0	3.5	280	—	1024	DDR3L GDDR5 64-bit	800 900	12.8 28.8	9 35
Radeon HD 8570 (Oland)	January 8, 2013	GCN 1st gen (28 nm)	950×106 77 mm2	384:24:8	730	19.2	6.4	560	35	2048	DDR3 GDDR5 128-bit	900 1150	28.8 72	12 66	PCIe 3.0 ×8
Radeon HD 8670 (Oland)	January 8, 2013				1000	24	8	768	48	2048	GDDR5 128-bit	1150	72	16 86
Radeon HD 8730 (Cape Verde LE)	September 5, 2013		1500×106 123 mm2	384:24:8	800	19.2	6.4	614.4	44.8	1024	GDDR5 128-bit	1125	72	10 47	PCIe 3.0 ×16
Radeon HD 8760 (Cape Verde XT)	January 8, 2013			640:40:16	1000	40	16	1280	80	2048	GDDR5 128-bit	1125	72	16 80	PCIe 3.0 ×16
Radeon HD 8770 (Bonaire XT)	September 2, 2013	GCN 2nd gen (28 nm)	2080×106 160 mm2	896:56:16	1000	56.0	16.0	1792	128	2048	GDDR5 128-bit	1500	96	10 85	PCIe 3.0 ×16
Radeon HD 8870 (Pitcairn XT)[18]	January 8, 2013	GCN 1st gen (28 nm)	2800×106 212 mm2	1280:80:32	1000	80	32	2560	160	2048	GDDR5 256-bit	1200	153.6	15 150	PCIe 3.0 ×16
Radeon HD 8950 (Tahiti Pro)	January 8, 2013		4313×106 352 mm2	1792:112:32	850 925	95.2 103.6	27.2 29.6	3046.4 3315.2	761.6 828.8	3072	GDDR5 384-bit	1250	240	15 225	PCIe 3.0 ×16
Radeon HD 8970 (Tahiti XT2)	January 8, 2013			2048:128:32	1000 1050	128.0 134.4	32 33.6	4096 4301	1024 1075	3072	GDDR5 384-bit	1500	288	15 250	PCIe 3.0 ×16
Radeon HD 8990 (Malta)	April 24, 2013		2× 4313×106 2× 352 mm2	2× 2048:128:32	950 1000	2× 128	2× 32	7782 8192	1946 2048	2× 3072	GDDR5 384-bit	1500	2× 288	15 375	PCIe 3.0 ×16
Model (Codename)	Launch	Architecture (Fab)	Transistors Die Size	Config[f]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)	Single	Double	Size (MiB)	Bus type & width (bit)	Clock (MHz)	Band- width (GB/s)	Idle Max	Bus interface
				Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)		Memory[e]				TDP (W)

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as with DDR memory.
6. Unified Shaders : Texture Mapping Units : Render Output Units
7. Lacks hardware video encoder

Mobile Models

Model (Codename)	Launch	Architecture (Fab)	Core		Fillrate[a][b][c]		Processing power[a][d] (GFLOPS)	Memory[e]				TDP (W)
			Config[f]	Clock[a] (MHz)	Texture (GT/s)	Pixel (GP/s)		Size (GiB)	Bus type & width (bit)	Clock (MHz)	Band- width (GB/s)
Radeon HD 8550M / 8630M (Sun LE)	8 January 2013	GCN 1st gen (28 nm)	384:24:8	650 700	15.6 16.8	5.2 5.6	537.6	1	DDR3 64	900	14.4	Un­known
Radeon HD 8570M / 8650M (Sun Pro)	8 January 2013		384:24:8	650 700	15.6 16.8	5.2 5.6	537.6	1	GDDR5 64	1125	36	Un­known
Radeon HD 8670M (Mars XT)	8 January 2013		384:24:8	775 825	18.6 19.8	6.2 6.6	633.6	1	DDR3 64	900	14.4	Un­known
Radeon HD 8690M (Sun XT)	8 January 2013		384:24:8	775 825	18.6 19.8	6.2 6.6	633.6	1	GDDR5 64	1125	36	Un­known
Radeon HD 8730M (Mars LE)	8 January 2013		384:24:8	650 700	15.6 16.8	5.2 5.6	537.6	2	DDR3 128	1000	32	Un­known
Radeon HD 8750M (Mars Pro)	8 January 2013		384:24:8	620–775 670–825	14.88 19.8	4.96 6.6	514.56 633.6	2	DDR3 GDDR5 128	1000	32 64	Un­known
Radeon HD 8770M (Mars XT)	8 January 2013		384:24:8	775 825	18.6 19.8	6.2 6.6	633.6	2	GDDR5 128	1125	72	Un­known
Radeon HD 8790M (Mars XTX)	8 January 2013		384:24:8	850 900	20.4 21.6	6.8 7.2	691.2	2	GDDR5 128	1125	72	Un­known
Radeon HD 8830M (Venus LE)	8 January 2013		640:40:16	575 625	23 25	9.2 10	800	2	DDR3 128	1000	32	Un­known
Radeon HD 8850M (Venus Pro)	8 January 2013		640:40:16	575–725 625–775	23 31	9.2 12.4	800 992	2	DDR3 GDDR5 128	1000 1125	32 72	Un­known
Radeon HD 8870M (Venus XT)	8 January 2013		640:40:16	725 775	29 31	11.6 12.4	992	2	DDR3 GDDR5 128	1000 1125	32 72	Un­known
Radeon HD 8970M (Neptune XT)	8 January 2013		1280:80:32	850 900	68 72	27.2 28.8	2304	2 4	GDDR5 256	1200	153.6	100

• v
• t
• e

1. Boost values (if available) are stated below the base value in italic.
2. Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
3. Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
4. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. The effective data transfer rate of GDDR5 is quadruple its nominal clock, instead of double as it is with other DDR memory.
6. Unified Shaders : Texture Mapping Units : Render Output Units

Integrated Models

Model (Codename)	Launch	Architecture (Fab)	APU	Core config[a]	Clock rate		Fillrate[b][c]		Memory		Processing Power[d] (GFLOPS)		TDP
					Core (MHz)	Memory (MHz)	Pixel (GP/s)	Texture (GT/s)	Bus type	Bus width (bit)	Single (boost)	Double (boost)
Radeon HD 8370D (Scrapper)	19 March 2013	TeraScale 3[e] 32 nm	A4-6300	128:8:4	760	System	3.04	6.08	DDR3	128	194.6	33	Un­known
Radeon HD 8470D (Scrapper)	19 March 2013		A6-6400	192:12:4	800	System	3.20	9.60	DDR3	128	307.2	Yes	Un­known
Radeon HD 8570D (Devastator)	19 March 2013		A8-6500 A8-6600K	256:16:8	800 844	System	6.40	12.8	DDR3	128	432.1	Yes	Un­known
Radeon HD 8670D (Devastator)	19 March 2013		A10-6700 A10-6800K	384:24:8	844	System	6.75	20.3	DDR3	128	648.2	Yes	Un­known
Radeon HD 8310G		TeraScale 3[e] 32 nm	A4-5145M	128:8:4	424 (554)	System			DDR3L	128		Un­known	Un­known
Radeon HD 8350G	19 March 2013		A4-5150M	128:8:4	514 (720)	System	2.06	4.11	DDR3L	128	131.6 (184.3)	32.9	Un­known
Radeon HD 8410G (Scrapper)	May 2013		A6-5345M	192:24:4	450 (600)	System	1.80	10.80	DDR3L	128	172.8 (230.4)	Un­known	Un­known
Radeon HD 8450G (Scrapper)	23 May 2013		A6-535xM	192:12:4	533 (720)	1600	2.17	17.33	DDR3L	128	204.7 (276.5)	Un­known	35W
Radeon HD 8510G (Scrapper)	May 2013		A8-5545M	384:48:8	450 (554)	System	3.60	21.60	DDR3L	128	351.9 (425.5)	Un­known	19W
Radeon HD 8550G Devastator	19 March 2013		A8-555xM	256:16:8	515 (720)	System	4.12	8.24	DDR3L	128	263.7 (368.6)	Un­known	Un­known
Radeon HD 8610G Devastator	May 2013		A10-5745M	384:24:8	533 (626)	System			DDR3L	128	409.3 (489.8)	Un­known	Un­known
Radeon HD 8650G Devastator	19 March 2013		A10-575xM	384:24:8	533 (720)	System	4.26	12.8	DDR3L	128	409.3 (553.0)	Un­known	Un­known

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. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
5. Lacks hardware video encoder

Radeon Feature Matrix

The following table shows features of AMD/ATI's GPUs (see also: List of AMD graphics processing units).

[ VisualEditor ]

• view
• talk
• edit

Name of GPU series	Wonder	Mach	3D Rage	Rage Pro	Rage 128	R100	R200	R300	R400	R500	R600	RV670	R700	Evergreen	Northern Islands		Southern Islands	Sea Islands	Volcanic Islands	Arctic Islands/Polaris	Vega	Navi 1x	Navi 2x	Navi 3x	Navi 4x
Released	1986	1991	Apr 1996	Mar 1997	Aug 1998	Apr 2000	Aug 2001	Sep 2002	May 2004	Oct 2005	May 2007	Nov 2007	Jun 2008	Sep 2009	Oct 2010	Dec 2010	Jan 2012	Sep 2013	Jun 2015	Jun 2016, Apr 2017, Aug 2019	Jun 2017, Feb 2019	Jul 2019	Nov 2020	Dec 2022	Feb 2025
Marketing Name	Wonder	Mach	3D Rage	Rage Pro	Rage 128	Radeon 7000	Radeon 8000	Radeon 9000	Radeon X700/X800	Radeon X1000	Radeon HD 2000	Radeon HD 3000	Radeon HD 4000	Radeon HD 5000	Radeon HD 6000		Radeon HD 7000	Radeon 200	Radeon 300	Radeon 400/500/600	Radeon RX Vega, Radeon VII	Radeon RX 5000	Radeon RX 6000	Radeon RX 7000	Radeon RX 9000
AMD support
Kind	2D		3D
Instruction set architecture	Not publicly known										TeraScale instruction set						GCN instruction set					RDNA instruction set
Microarchitecture	Not publicly known					GFX1		GFX2			TeraScale 1 (VLIW5) (GFX3)			TeraScale 2 (VLIW5) (GFX4)	TeraScale 2 (VLIW5) up to 68xx (GFX4)	TeraScale 3 (VLIW4) in 69xx [19][20] (GFX5)	GCN 1st gen (GFX6)	GCN 2nd gen (GFX7)	GCN 3rd gen (GFX8)	GCN 4th gen (GFX8)	GCN 5th gen (GFX9)	RDNA (GFX10.1)	RDNA 2 (GFX10.3)	RDNA 3 (GFX11)	RDNA 4 (GFX12)
Type	Fixed pipeline[a]						Programmable pixel & vertex pipelines				Unified shader model
Direct3D	—		5.0	6.0		7.0	8.1	9.0 11 (9_2)	9.0b 11 (9_2)	9.0c 11 (9_3)	10.0 11 (10_0)	10.1 11 (10_1)		11 (11_0)			11 (11_1) 12 (11_1)	11 (12_0) 12 (12_0)			11 (12_1) 12 (12_1)		11 (12_1) 12 (12_2)
Shader model	—						1.4	2.0+	2.0b	3.0	4.0	4.1		5.0			5.1	5.1 6.5			6.7				6.8
OpenGL	—			1.1	1.2	1.3		1.5[b][21]			3.3			4.6[22][c]
Vulkan	—															1.1[c][d]	1.3[23]		1.4[24]
OpenCL	—										Close to Metal		1.1 (not supported by Mesa)	1.2+ (on Linux: 1.1+ (no Image support on Clover, with by Rusticl) with Mesa, 1.2+ on GCN 1.Gen)				2.0+ (Adrenalin driver on Win7+) (on Linux ROCm, Mesa 1.2+ (no Image support in Clover, but in Rusticl with Mesa, 2.0+ and 3.0 with AMD drivers or AMD ROCm), 5th gen: 2.2 win 10+ and Linux RocM 5.0+				2.2+ and 3.0 Windows 8.1+ and Linux ROCm 5.0+ (Mesa Rusticl 1.2+ and 3.0 (2.1+ and 2.2+ wip))[25][26][27]
HSA / ROCm	—																					?
Video decoding ASIC	—										Avivo/UVD	UVD+	UVD 2	UVD 2.2	UVD 3		UVD 4	UVD 4.2	UVD 5.0 or 6.0	UVD 6.3	UVD 7 [28][e]	VCN 2.0 [28][e]	VCN 3.0 [29]	VCN 4.0	VCN 5.0
Video encoding ASIC	—																VCE 1.0	VCE 2.0	VCE 3.0 or 3.1	VCE 3.4	VCE 4.0 [28][e]
Fluid Motion [f]																								?
Power saving	?										PowerPlay				PowerTune	PowerTune & ZeroCore Power					?
TrueAudio	—																	Via dedicated DSP		Via shaders
FreeSync	—																	1 2
HDCP[g]	—										?							1.4		2.2		2.3 [30]
PlayReady[g]	—																			3.0		3.0
Supported displays[h]						1–2	2							2–6								?			4
Max. resolution	?													2–6 × 2560×1600			2–6 × 4096×2160 @ 30 Hz			2–6 × 5120×2880 @ 60 Hz	3 × 7680×4320 @ 60 Hz [31]	7680×4320 @ 60 Hz PowerColor		7680x4320 @165 Hz	7680x4320
/drm/radeon[i]																			—
/drm/amdgpu[i]	—																	Optional [32]

1. The Radeon 100 Series has programmable pixel shaders, but do not fully comply with DirectX 8 or Pixel Shader 1.0. See article on R100's pixel shaders.
2. R300, R400 and R500 based cards do not fully comply with OpenGL 2+ as the hardware does not support all types of non-power of two (NPOT) textures.
3. OpenGL 4+ compliance requires supporting FP64 shaders and these are emulated on some TeraScale chips using 32-bit hardware.
4. Vulkan support is theoretically possible but has not been implemented in a stable driver.
5. The UVD and VCE were replaced by the Video Core Next (VCN) ASIC in the Raven Ridge APU implementation of Vega.
6. Video processing for video frame rate interpolation technique. In Windows it works as a DirectShow filter in your player. In Linux, there is no support on the part of drivers and / or community.
7. To play protected video content, it also requires card, operating system, driver, and application support. A compatible HDCP display is also needed for this. HDCP is mandatory for the output of certain audio formats, placing additional constraints on the multimedia setup.
8. More displays may be supported with native DisplayPort connections, or splitting the maximum resolution between multiple monitors with active converters.
9. DRM (Direct Rendering Manager) is a component of the Linux kernel. AMDgpu is the Linux kernel module. Support in this table refers to the most current version.

See also

• Radeon HD 2000 series
• Radeon HD 3000 series
• Radeon HD 4000 series
• Radeon HD 5000 series
• Radeon HD 6000 series
• Radeon HD 7000 series
• Radeon Rx 200 series
• Nvidia GeForce 700 series
• List of AMD graphics processing units
• Free and open-source device drivers: graphics#ATI/AMD