List of AMD accelerated processing units

This is a list of microprocessors designed by Advanced Micro Devices, under the AMD Accelerated Processing Unit product series.

Features overview

The following table shows features of AMD's APUs

Codename	Server	Basic						Toronto
		Micro														Kyoto
	Desktop	Performance										Renoir
		Mainstream	Llano	Trinity	Richland	Kaveri	Kaveri Refresh (Godavari)	Carrizo	Bristol Ridge	Raven Ridge	Picasso
		Entry
		Basic														Kabini
	Mobile	Performance										Renoir	Cezanne
		Mainstream	Llano	Trinity	Richland	Kaveri		Carrizo	Bristol Ridge	Raven Ridge	Picasso
		Entry																		Dalí
		Basic													Desna, Ontario, Zacate	Kabini, Temash	Beema, Mullins	Carrizo-L	Stoney Ridge
	Embedded			Trinity		Bald Eagle		Merlin Falcon, Brown Falcon		Great Horned Owl		Grey Hawk			Ontario, Zacate	Kabini	Steppe Eagle, Crowned Eagle, LX-Family		Prairie Falcon	Banded Kestrel
Platform			High, standard and low power												Low and ultra-low power
Released			Aug 2011	Oct 2012	Jun 2013	Jan 2014	2015	Jun 2015	Jun 2016	Oct 2017	Jan 2019	Mar 2020	Jan 2021		Jan 2011	May 2013	Apr 2014	May 2015	Feb 2016	Apr 2019
CPU microarchitecture			K10	Piledriver		Steamroller		Excavator	"Excavator+"[1]	Zen	Zen+	Zen 2	Zen 3		Bobcat	Jaguar	Puma	Puma+[2]	"Excavator+"	Zen
ISA			x86-64												x86-64
Socket	Desktop	High-end	N/A
		Mainstream	N/A				FM2+[lower-alpha 1]		AM4
		Entry	FM1	FM2		FM2+[lower-alpha 2]										AM1
		Basic	N/A												N/A
	Other		FS1	FS1+, FP2		FP3		FP4		FP5		FP6			FT1	FT3	FT3b		FP4	FP5
PCI Express version			2.0			3.0						4.0			2.0				3.0
Fab. (nm)			GF 32SHP (HKMG SOI)			GF 28SHP (HKMG bulk)				GF 14LPP (FinFET bulk)	GF 12LP (FinFET bulk)	TSMC N7 (FinFET bulk)			TSMC N40 (bulk)	TSMC N28 (HKMG bulk)	GF 28SHP (HKMG bulk)			GF 14LPP (FinFET bulk)
Die area (mm^2)			228	246		245		245	250	210[3]		156	?		75 (+ 28 FCH)	107		?	125	149
Min TDP (W)			35	17				12				10			4.5	4	3.95	10	6
Max APU TDP (W)			100			95		65							18	25
Max stock APU base clock (GHz)			3	3.8	4.1	4.1		3.7	3.8	3.6	3.7	3.8	?		1.75	2.2	2	2.2	3.2	3.3
Max APUs per node[lower-alpha 3]			1												1
Max CPU[lower-alpha 4] cores per APU			4									8			2	4			2
Max threads per CPU core			1							2					1					2
Integer structure			3+3	2+2						4+2		4+2+1	?		1+1+1+1				2+2	4+2
i386, i486, i586, CMOV, NOPL, i686, PAE, NX bit, CMPXCHG16B, AMD-V, RVI, ABM, and 64-bit LAHF/SAHF
IOMMU[lower-alpha 5]			N/A
BMI1, AES-NI, CLMUL, and F16C														N/A
MOVBE			N/A
AVIC, BMI2 and RDRAND															N/A
ADX, SHA, RDSEED, SMAP, SMEP, XSAVEC, XSAVES, XRSTORS, CLFLUSHOPT, and CLZERO			N/A										N/A
WBNOINVD, CLWB, RDPID, RDPRU, and MCOMMIT			N/A															N/A
FPUs per core			1	0.5						1				1				0.5	1
Pipes per FPU			2											2
FPU pipe width			128-bit									256-bit		80-bit	128-bit
CPU instruction set SIMD level			SSE4a[lower-alpha 6]	AVX				AVX2						SSSE3	AVX			AVX2
3DNow!			3DNow!+	N/A										N/A
PREFETCH/PREFETCHW
FMA4, LWP, TBM, and XOP			N/A						N/A				N/A					N/A
FMA3
L1 data cache per core (KiB)			64	16				32						32
L1 data cache associativity (ways)			2	4				8						8
L1 instruction caches per core			1	0.5						1				1				0.5	1
Max APU total L1 instruction cache (KiB)			256	128		192				256		512		64	128			96	128
L1 instruction cache associativity (ways)			2			3				4		8		2				3	4
L2 caches per core			1	0.5						1				1				0.5	1
Max APU total L2 cache (MiB)			4					2				4		1	2			1
L2 cache associativity (ways)			16							8				16					8
APU total L3 cache (MiB)			N/A						4		8		N/A					4
APU L3 cache associativity (ways)									16									16
L3 cache scheme			Victim			N/A			Victim									Victim
Max stock DRAM support			DDR3-1866		DDR3-2133			DDR3-2133, DDR4-2400	DDR4-2400	DDR4-2933		DDR4-3200, LPDDR4-4266	LPDDR4-4266	DDR3L-1333	DDR3L-1600	DDR3L-1866		DDR3-1866, DDR4-2400	DDR4-2400
Max DRAM channels per APU			2											1					2
Max stock DRAM bandwidth (GB/s) per APU			29.866		34.132			38.400		46.932		68.256	?	10.666	12.800	14.933		19.200	38.400
GPU microarchitecture			TeraScale 2 (VLIW5)	TeraScale 3 (VLIW4)		GCN 2nd gen		GCN 3rd gen		GCN 5th gen[4]				TeraScale 2 (VLIW5)	GCN 2nd gen			GCN 3rd gen[4]	GCN 5th gen
GPU instruction set			TeraScale instruction set			GCN instruction set								TeraScale instruction set	GCN instruction set
Max stock GPU base clock (MHz)			600	800	844	866		1108		1250	1400	2100	?	538	600	?	847	900	1200
Max stock GPU base GFLOPS[lower-alpha 7]			480	614.4	648.1	886.7		1134.5		1760	1971.2	2150.4	?	86	?	?	?	345.6	460.8
3D engine[lower-alpha 8]			Up to 400:20:8	Up to 384:24:6		Up to 512:32:8				Up to 704:44:16[5]		Up to 512:32:8	?	80:8:4	128:8:4			Up to 192:?:?	Up to 192:?:?
			IOMMUv1			IOMMUv2								IOMMUv1			?		IOMMUv2
Video decoder			UVD 3.0			UVD 4.2		UVD 6.0		VCN 1.0[6]		VCN 2.0[7]		UVD 3.0	UVD 4.0	UVD 4.2	UVD 6.0	UVD 6.3	VCN 1.0
Video encoder			N/A	VCE 1.0		VCE 2.0		VCE 3.1						N/A	VCE 2.0		VCE 3.1
AMD Fluid Motion
GPU power saving			PowerPlay	PowerTune										PowerPlay	PowerTune[8]
TrueAudio			N/A			[9]							N/A
FreeSync						1 2									1 2
HDCP[lower-alpha 9]			?			1.4				1.4 2.2				?	1.4				1.4 2.2
PlayReady[lower-alpha 9]			N/A						3.0 not yet				N/A					3.0 not yet
Supported displays[lower-alpha 10]			2–3	2–4				3		3 (desktop) 4 (mobile, embedded)		4		2				3	4
/drm/radeon[lower-alpha 11][11][12]								N/A									N/A
/drm/amdgpu[lower-alpha 11][13]			N/A			[14]								N/A	[14]

1. For FM2+ Excavator models: A8-7680, A6-7480 & Athlon X4 845.
2. For FM2+ Excavator models: A8-7680, A6-7480 & Athlon X4 845.
3. A PC would be one node.
4. An APU combines a CPU and a GPU. Both have cores.
5. Requires firmware support.
6. No SSE4. No SSSE3.
7. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
8. Unified shaders : texture mapping units : render output units
9. 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.
10. To feed more than two displays, the additional panels must have native DisplayPort support.[10] Alternatively active DisplayPort-to-DVI/HDMI/VGA adapters can be employed.
11. DRM (Direct Rendering Manager) is a component of the Linux kernel. Support in this table refers to the most current version.

Graphics API overview

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

Chip series	Micro-architecture	Fab	Supported APIs					AMD support	Year introduced	Introduced with
			Rendering			Computing
			Vulkan[15]	OpenGL[16]	Direct3D	HSA	OpenCL
Wonder	Fixed-pipeline[lower-alpha 1]	1000nm 800nm	N/A	N/A	N/A	N/A	N/A	Ended	1986
Mach		800nm 600nm							1991
3D Rage		500nm			5.0				1996	3D Rage
Rage Pro		350nm		1.1	6.0				1997	Rage Pro
Rage 128		250nm		1.2					1998	Rage 128 GL/VR
R100		180 nm 150 nm		1.3	7.0				2000	Radeon
R200	Programmable pixel & vertex pipelines	150 nm			8.1				2001	Radeon 8500
R300		150 nm 130 nm 110 nm		2.0[lower-alpha 2]	9.0 11 (FL 9_2)				2002	Radeon 9700
R420		130 nm 110 nm			9.0b 11 (FL 9_2)				2004	Radeon X800
R520		90 nm 80 nm			9.0c 11 (FL 9_3)				2005	Radeon X1800
R600	TeraScale 1	80 nm 65 nm		3.3	10.0 11 (FL 10_0)		ATI Stream		2007	Radeon HD 2900 XT
RV670		55 nm			10.1 11 (FL 10_1)		ATI Stream APP[17]			Radeon HD 3850/3870
RV770		55 nm 40 nm					1.0		2008	Radeon HD 4850/4870
Evergreen	TeraScale 2	40 nm		4.5 (Linux 4.2) [18][19][20][lower-alpha 3]	11 (FL 11_0)		1.2		2009	Radeon HD 5850/5870
Northern Islands	TeraScale 2 TeraScale 3								2010	Radeon HD 6850/6870 Radeon HD 6950/6970
Southern Islands	GCN 1^st gen	28 nm	1.0	4.6	11 (FL 11_1) 12 (FL11_1)		1.2 2.0 possible	Current	2012	Radeon HD 7950/7970
Sea Islands	GCN 2^nd gen		1.2		11 (FL 12_0) 12 (FL 12_0)		2.0 (1.2 in MacOS, Linux) 2.1 Beta in Linux ROCm 2.2 possible		2013	Radeon HD 7790
Volcanic Islands	GCN 3^rd gen								2014	Radeon R9 285
Arctic Islands	GCN 4^th gen	14 nm							2016	Radeon RX 480
Vega	GCN 5^th gen	14 nm 7 nm			11 (FL 12_1) 12 (FL 12_1)				2017	Radeon Vega Frontier Edition
Navi	RDNA 1^st gen	7 nm							2019	Radeon RX 5700 (XT)
Navi 2X	RDNA 2^nd gen								2020	Radeon RX 6800 (XT)

1. Radeon 7000 Series has programmable pixel shaders, but do not fully comply with DirectX 8 or Pixel Shader 1.0. See article on R100's pixel shaders.
2. These series do not fully comply with OpenGL 2+ as the hardware does not support all types of non-power-of-two (NPOT) textures.
3. OpenGL 4+ compliance requires supporting FP64 shaders and these are emulated on some TeraScale chips using 32-bit hardware.

[21][22][23]

Desktop APUs

Lynx: "Llano" (2011)

• Socket FM1
• CPU: K10 (or Husky or K10.5) with no L3 cache cores with an upgraded architecture known as Stars
  • L1 Cache: 64 KB Data per core and 64 KB Instructions per core
• MMX, Enhanced 3DNow!, SSE, SSE2, SSE3, SSE4a, ABM, NX bit, AMD64, Cool'n'Quiet, AMD-V
• GPU: TeraScale 2 (Evergreen); all A and E series models feature Redwood-class integrated graphics on die (BeaverCreek for the dual-core variants and WinterPark for the quad-core variants). Sempron and Athlon models exclude integrated graphics.[24]
• List of embedded GPU's
• Support for up to four DIMMs of up to DDR3-1866 memory
• Fabrication 32 nm on GlobalFoundries SOI process; Die size: 228 mm², with 1.178 billion transistors[25][26]
• 5 GT/s UMI
• Integrated PCIe 2.0 controller
• Select models support Turbo Core technology for faster CPU operation when the thermal specification permits
• Select models support Hybrid Graphics technology to assist a discrete Radeon HD 6450, 6570, or 6670 discrete graphics card. This is similar to the current Hybrid CrossFireX technology available in the AMD 700 and 800 chipset series

Model	Released	Fab	Stepping	CPU						GPU				Memory support	TDP	Box Number	Part number
				Cores (threads)	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
Sempron X2 198	Q1 2012	32nm	B0	2 (2)	2.5GHz	N/A	64KB inst. 64KB data per core	2× 512KB	N/A	N/A				DDR3-1600	65W	SD198XOJGXBOX	SD198XOJZ22GX
Athlon II X2 221					2.8 GHz											AD221XOJGXBOX	AD221XOJZ22GX
Athlon II X4 631 (65 W)	2012			4 (4)	2.6GHz			4× 1MB						DDR3-1866		AD631XOJGXBOX	AD631XOJZ43GX
Athlon II X4 631 (100 W)	August 15, 2011														0100W	AD631XOJGXBOX	AD631XWNZ43GX
Athlon II X4 638	February 8, 2012				2.7 GHz										65 W	AD638XOJGXBOX	AD638XOJZ43GX
Athlon II X4 641					2.8 GHz										100W	AD641XWNGXBOX	AD641XWNZ43GX
Athlon II X4 651	November 14, 2011				3.0GHz											AD651XWNGXBOX	AD651XWNZ43GX
Athlon II X4 651K	Q1 2012															AD651KWNGXBOX	AD651KWNZ43GX
E2-3200	Q4 2011			2 (2)	2.4GHz			2× 512KB		HD 6370D	160:8:4	443MHz	141.7	DDR3-1600	65W	ED3200OJGXBOX	ED3200OJZ22GX ED3200OJZ22HX
A4-3300	September 7, 2011				2.5GHz					HD 6410D						AD3300OJGXBOX AD3300OJHXBOX	AD33000OJZ22GX AD33000OJZ22HX
A4-3400					2.7GHz							600MHz	192			AD3400OJGXBOX AD3400OJHXBOX	AD3400OJZ22GX AD3400OJZ22HX
A4-3420	December 20, 2011				2.8GHz											N/A	AD3420OJZ22HX
A6-3500	August 17, 2011			3 (3)	2.1GHz	2.4GHz		3× 1MB		HD 6530D	320:16:8	443MHz	283.5	DDR3-1866		AD3500OJGXBOX	AD3500OJZ33GX
A6-3600				4 (4)				4× 1MB								AD3600OJGXBOX	AD3600OJZ43GX
A6-3620	December 20, 2011				2.2GHz	2.5GHz										AD3620OJGXBOX	AD3620OJZ43GX
A6-3650	June 30, 2011				2.6GHz	N/A									100W	AD3650WNZ43GX
A6-3670K^4	December 20, 2011				2.7GHz											AD3670WNGXBOX	AD3670WNZ43GX
A8-3800	August 17, 2011				2.4GHz	2.7GHz				HD 6550D	400:20:8	600MHz	480		65W	AD3800OJZ43GX
A8-3820	December 20, 2011				2.5GHz	2.8GHz										AD3820OJGXBOX	AD3820OJZ43GX
A8-3850	June 30, 2011				2.9GHz	N/A									100W	AD3850WNGXBOX	AD3850WNZ43GX
A8-3870K^4	December 20, 2011				3.0GHz											AD3870WNGXBOX	AD3870WNZ43GX

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

Virgo: "Trinity" (2012)

• Fabrication 32 nm on GlobalFoundries SOI process
• Socket FM2
• CPU: Piledriver
  • L1 Cache: 16 KB Data per core and 64 KB Instructions per module
• GPU TeraScale 3 (VLIW4)
• Die Size: 246 mm², 1.303 Billion transistors[28]
• Support for up to four DIMMs of up to DDR3-1866 memory
• 5 GT/s UMI
• GPU (based on VLIW4 architecture) instruction support: DirectX 11, Opengl 4.2, DirectCompute, Pixel Shader 5.0, Blu-ray 3D, OpenCL 1.2, AMD Stream, UVD3
• Integrated PCIe 2.0 controller, and Turbo Core technology for faster CPU/GPU operation when the thermal specification permits
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AMD64, AMD-V, AES, CLMUL, AVX, XOP, FMA3, FMA4, F16C,[29] ABM, BMI1, TBM
• Sempron and Athlon models exclude integrated graphics
• Select models support Hybrid Graphics technology to assist a Radeon HD 7350, 7450, 7470, 7550, 7570, 7670 discrete graphics card.[30][31] However, it has been found that this does not always improve 3D accelerated graphics performance.[32][33]

Model number	Released	Fab	Stepping	CPU						GPU				Memory support	TDP	Box Number	Part number[34]
				Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
Sempron X2 240[35]		32nm	TN-A1	2 (2) [1]	2.9GHz	3.3GHz	64KB inst. per module 16KB data per core	1MB	N/A	N/A				DDR3-1600	65W		SD240XOKA23HJ
Athlon X2 340[36]	Oct 2012				3.2GHz	3.6GHz											AD340XOKA23HJ
Athlon X4 730	Oct 1, 2012			4 (4) [2]	2.8GHz	3.2GHz		2× 2MB						DDR3-1866	65W		AD730XOKA44HJ
Athlon X4 740	Oct 2012				3.2GHz	3.7GHz										AD740XOKHJBOX	AD740XOKA44HJ
Athlon X4 750K					3.4GHz	4.0GHz									100W	AD750KWOHJBOX	AD750KWOA44HJ
FirePro A300	Aug 7, 2012				3.4GHz	4.0GHz				FirePro	384:24:8 6 CU	760MHz	583.6		65W		AWA300OKA44HJ
FirePro A320					3.8GHz	4.2GHz						800MHz	614.4		100W		AWA320WOA44HJ
A4-5300	Oct 1, 2012			2 (2) [1]	3.4GHz	3.6GHz		1MB		HD 7480D	128:8:4 2 CU	723MHz	185	DDR3-1600	65W	AD5300OKHJBOX	AD5300OKA23HJ
A4-5300B	Oct 2012																AD530BOKA23HJ
A6-5400K	Oct 1, 2012				3.6GHz	3.8GHz				HD 7540D	192:12:4 3 CU	760MHz	291.8	DDR3-1866		AD540KOKHJBOX	AD540KOKA23HJ
A6-5400B	Oct 2012																AD540BOKA23HJ
A8-5500	Oct 1, 2012			4 (4) [2]	3.2GHz	3.7GHz		2× 2MB		HD 7560D	256:16:8 4 CU	760MHz	389.1	DDR3-1866	065W	AD5500OKHJBOX	AD5500OKA44HJ
A8-5500B	Oct 2012																AD550BOKA44HJ
A8-5600K	Oct 1, 2012				3.6GHz	3.9GHz									100W	AD560KWOHJBOX	AD560KWOA44HJ
A10-5700	Oct 1, 2012				3.4GHz	4.0GHz				HD 7660D	384:24:8 6 CU	760MHz	583.6		065W	AD5700OKHJBOX	AD5700OKA44HJ
A10-5800K					3.8GHz	4.2GHz						800MHz	614.4		100W	AD580KWOHJBOX	AD580KWOA44HJ
A10-5800B	Oct 2012																AD580BWOA44HJ

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Richland" (2013)

• Fabrication 32 nm on GlobalFoundries SOI process
• Socket FM2
• Two or four CPU cores based on the Piledriver microarchitecture
  • Die Size: 246 mm², 1.303 Billion transistors[37]
  • L1 Cache: 16 KB Data per core and 64 KB Instructions per module
  • MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AMD64, AMD-V, AES, AVX, AVX1.1, XOP, FMA3, FMA4, F16C, ABM, BMI1, TBM, Turbo Core 3.0, NX bit, PowerNow!
• GPU
  • TeraScale 3 architecture
  • HD Media Accelerator, AMD Hybrid Graphics

Model	Released	Fab	Stepping	CPU						GPU				Memory support	TDP	Box Number	Part number
				Cores (threads) [FPUs]	Base	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
Sempron X2 250[35]		32nm	RL-A1	2 (2) [1]	3.2 GHz	3.6 GHz	64KB inst. per module 16KB data per core	1MB	N/A	N/A					065W		SD250XOKA23HL
Athlon X2 350[38]					3.5 GHz	3.9 GHz								DDR3-1866	65W		AD350XOKA23HL
Athlon X2 370K	Jun 2013				4.0 GHz	4.2 GHz										AD370KOKHLBOX	AD370KOKA23HL
Athlon X4 750	Oct 2013			4 (4) [2]	3.4 GHz	4.0 GHz		2× 2MB							065W		AD750XOKA44HL
Athlon X4 760K	Jun 2013				3.8 GHz	4.1 GHz									100W	AD760KWOHLBOX	AD760KWOA44HL
FX-670K[39]	March 2014 (OEM)				3.7 GHz	4.3 GHz									65W		FD670KOKA44HL
A4-4000	May 2013			2 (2) [1]	3.0 GHz	3.2 GHz		1 MB		7480D	128:8:4 2 CU	720 MHz	184.3	DDR3-1333	65W	AD4000OKHLBOX	AD4000OKA23HL
A4-4020	Jan 2014				3.2 GHz	3.4 GHz										AD4020OKHLBOX	AD4000OKA23HL
A4-6300	July 2013				3.7 GHz	3.9 GHz				8370D		760 MHz	194.5	DDR3-1600		AD6300OKHLBOX	AD6300OKA23HL
A4-6300B																	AD630BOKA23HL
A4-6320	Dec 2013				3.8 GHz	4.0 GHz										AD6320OKHLBOX	AD6320OKA23HL
A4-6320B	March 2014																AD632BOKA23HL
A4-7300	Aug 2014									8470D	192:12:4 3 CU	800MHz	307.2				AD7300OKA23HL
A4 PRO-7300B																	AD730BOKA23HL
A6-6400B	Jun 4, 2013				3.9 GHz	4.1 GHz								DDR3-1866			AD640BOKA23HL
A6-6400K																AD640KOKHLBOX	AD640KOKA23HL
A6-6420B	Jan 2014				4.0 GHz	4.2 GHz											AD642BOKA23HL
A6-6420K																AD642KOKHLBOX	AD642KOKA23HL
A8-6500T	Sep 18, 2013			4 (4) [2]	2.1 GHz	3.1 GHz		2× 2 MB		8550D	256:16:8 4 CU	720 MHz	368.6	DDR3-1866	45 W	AD650TYHHLBOX	AD650TYHA44HL
A8-6500	Jun 4, 2013				3.5 GHz	4.1 GHz				8570D		800 MHz	409.6		65 W	AD6500OKHLBOX	AD6500OKA44HL
A8-6500B																	AD650BOKA44HL
A8-6600K					3.9 GHz	4.2 GHz						844 MHz	432.1		100 W	AD660KWOHLBOX	AD660KWOA44HL
A10-6700T	Sep 18, 2013				2.5 GHz	3.5 GHz				8650D	384:24:8 4 CU	720 MHz	552.9	DDR3-1866	45 W	AD670TYHHLBOX	AD670TYHA44HL
A10-6700	Jun 4, 2013				3.7 GHz	4.3 GHz				8670D		844 MHz	648.1		65 W	AD6700OKHLBOX	AD6700OKA44HL
A10-6790B	Oct 29, 2013				4.0 GHz										100 W	AD679KWOHLBOX	AD679KWOA44HL
A10-6790K	Oct 28, 2013																AD679BWOA44HL
A10-6800K	Jun 4, 2013				4.1 GHz	4.4 GHz								DDR3-2133		AD680KWOHLBOX	AD680KWOA44HL
A10-6800B																	AD680BWOA44HL

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Kabini" (2013, SoC)

• Fabrication 28 nm by GlobalFoundries
• Socket AM1, aka Socket FS1b (AM1 platform)
• 2 to 4 CPU Cores (Jaguar (microarchitecture))
• L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AMD64, AVX, F16C, CLMUL, AES, MOVBE (Move Big-Endian instruction), XSAVE/XSAVEOPT, ABM, BMI1, AMD-V support
• SoC with integrated memory, PCIe, 2× USB 3.0, 6× USB 2.0, Gigabit Ethernet, and 2× SATA III (6 Gb/s) controllers
• GPU based on Graphics Core Next (GCN)

Model	Released	Fab	Stepping	CPU					GPU				Memory support	TDP	Box Number	Part number
				Cores (threads)	Clock	Cache[lower-alpha 1]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 2]
						L1	L2	L3
Sempron 2650	April 9, 2014	28nm	A1	2 (2)	1.45 GHz	32 KB inst. 32 KB data per core	1 MB	N/A	R3 (HD 8240)	128:8:4 2 CU	400 MHz	102.4	DDR3-1333 (Single channel only)	25 W	SD2650JAHMBOX	SD2650JAH23HM
Sempron 3850				4 (4)	1.30 GHz		2 MB		R3 (HD 8280)		450 MHz	115.2	DDR3-1600 (Single channel only)		SD3850JAHMBOX	SD3850JAH44HM
Athlon 5150					1.60 GHz				R3 (HD 8400)		600 MHz	153.6			AD5150JAHMBOX	AD5150JAH44HM
Athlon 5350					2.05 GHz										AD5350JAHMBOX	AD5350JAH44HM
Athlon 5370	February, 2016				2.20 GHz											AD5370JAH44HM

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Kaveri" (2014) & "Godavari" (2015)

• Fabrication 28 nm by GlobalFoundries.
• Socket FM2+,[40] support for PCIe 3.0.
• Two or four CPU cores based on the Steamroller microarchitecture.
  • Kaveri refresh models have codename Godavari.[41]
• Die Size: 245 mm², 2.41 Billion transistors.[42]
• L1 Cache: 16 KB Data per core and 96 KB Instructions per module.
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, XOP, FMA3, FMA4, F16C, ABM, BMI1, TBM, Turbo Core
• Three to eight Compute Units (CUs) based on GCN 2nd gen microarchitecture;[43] 1 Compute Unit (CU) consists of 64 Unified Shader Processors : 4 Texture Mapping Units (TMUs) : 1 Render Output Unit (ROPs).
• Heterogeneous System Architecture-enabled zero-copy through pointer passing.
• SIP blocks: Unified Video Decoder, Video Coding Engine, TrueAudio.[44]
• Dual-channel (2× 64 Bit) DDR3 memory controller.
• Integrated custom ARM Cortex-A5 co-processor[45] with TrustZone Security Extensions[46] in select APU models, except the Performance APU models.[47]
• Select models support Hybrid Graphics technology by using a Radeon R7 240 or R7 250 discrete graphics card.[48]
• Display controller: AMD Eyefinity 2, 4K Ultra HD support, DisplayPort 1.2 Support.[49]

Model	Release date	Fab	Stepping	CPU						GPU				Memory support	TDP	Box Number	Part number
				Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
Athlon X2 450[38]	Jul 31, 2014	28nm	KV-A1	2 (2) [1]	3.5 GHz	3.9 GHz	96 KB inst. per module 16 KB data per core	1 MB	N/A	N/A				DDR3-1866	65 W		AD450XYBI23JA
Athlon X4 840[38]	Aug 2014			4 (4) [2]	3.1 GHz	3.8 GHz		2× 2 MB						DDR3-1866		AD840XYBJABOX	AD840XYBI44JA
Athlon X4 860K					3.7 GHz	4.0 GHz									95 W	AD860KXBJABOX AD860KWOHLBOX AD860KXBJASBX	AD860KXBI44JA
Athlon X4 870K	Dec 2015		GV-A1		3.9 GHz	4.1 GHz										AD870KXBJCSBX	AD870KXBI44JC
Athlon X4 880K	Mar 1, 2016				4.0 GHz	4.2 GHz								DDR3-2133		AD880KXBJCSBX
FX-770K[50]	Dec 2014		KV-A1	3.5 GHz	3.9 GHz	DDR3-2133	65 W							FD770KYBI44JA
A4 PRO-7350B	Jul 31, 2014			2 (2) [1]	3.4 GHz	3.8 GHz	1 MB	R5	192:12:8 3 CU	514 MHz	197.3	DDR3-1866	65 W		AD735BYBI23JA
PRO A4-8350B	Sep 29, 2015				3.5 GHz	3.9 GHz			256:16:8 4 CU	757 MHz	387.5				AD835BYBI23JC
A6-7400K	Jul 31, 2014				3.5 GHz	3.9 GHz				756 MHz	387			AD740KYBJABOX	AD740KYBI23JA
A6 PRO-7400B															AD740BYBI23JA
A6-7470K	Feb 2, 2016		GV-A1		3.7 GHz	4.0 GHz				800 MHz	409.6	DDR3-2133		AD747KYBJCBOX	AD747KYBI23JC
PRO A6-8550B	Sep 29, 2015														AD855BYBI23JC
A8-7500[51][52]	2014 ?		KV-A1	4 (4) [2]	3.0 GHz	3.7 GHz	2× 2 MB	R7	384:24:8 6 CU	720 MHz	552.9	DDR3-2133	65 W		AD7500YBI44JA
A8-7600	Jul 31, 2014				3.1 GHz	3.8 GHz								AD7600YBJABOX	AD7600YBI44JA
A8 PRO-7600B															AD760BYBI44JA
A8-7650K	Jan 7, 2015				3.3 GHz								95 W	AD765KXBJABOX AD765KXBJASBX	AD765KXBI44JA
A8-7670K	Jul 20, 2015		GV-A1		3.6 GHz	3.9 GHz				757 MHz	581.3			AD767KXBJCSBX AD767KXBJCBOX	AD767KXBI44JC
PRO A8-8650B	Sep 29, 2015				3.2 GHz	3.9 GHz							65 W		AD865BYBI44JC
A10-7700K	Jan 14, 2014		KV-A1		3.4 GHz	3.8 GHz				720 MHz	552.9		95 W	AD770KXBJABOX	AD770KXBI44JA
A10-7800	Jul 31, 2014				3.5 GHz	3.9 GHz			512:32:8 8 CU	720 MHz	737.2		65 W	AD7800YBJABOX	AD7800YBI44JA
A10 PRO-7800B															AD780BYBI44JA
A10-7850K	Jan 14, 2014				3.7 GHz	4.0 GHz							95 W	AD785KXBJABOX	AD785KXBI44JA
A10 PRO-7850B	Jul 31, 2014														AD785BXBI44JA
A10-7860K	Feb 2, 2016		GV-A1		3.6 GHz					757 MHz	775.1		65 W	AD786KYBJABOX AD786KYBJCSBX	AD786KYBI44JC
A10-7870K	May 28, 2015				3.9 GHz	4.1 GHz				866 MHz	886.7		95 W	AD787KXDJCBOX AD787KXDJCSBX	AD787KXDI44JC
A10-7890K	Mar 1, 2016				4.1 GHz	4.3 GHz								AD789KXDJCHBX
PRO A10-8750B	Sep 29, 2015				3.6 GHz	4.0 GHz				757 MHz	775.1		65 W		AD875BYBI44JC
PRO A10-8850B					3.9 GHz	4.1 GHz				800 MHz	819.2		95 W		AD885BXBI44JC

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Carrizo" (2016)

• Fabrication 28 nm by GlobalFoundries
• Socket FM2+, AM4, support for PCIe 3.0
• Two or four CPU cores based on the Excavator microarchitecture
• Die Size: 250.04 mm², 3.1 Billion transistors[53]
• L1 Cache: 32 KB Data per core and 96 KB Instructions per module
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, XOP, FMA3, FMA4, F16C, ABM, BMI1, BMI2, TBM, RDRAND, Turbo Core
• Dual-channel DDR3 or DDR4 memory controller
• Third Generation GCN based GPU
• Integrated custom ARM Cortex-A5 co-processor[45] with TrustZone Security Extensions[46][47]

Model	Released	Fab	Stepping	Socket	CPU						GPU				Memory support	TDP	Box Number[lower-alpha 1]	Part number
					Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 2]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 3]
								L1	L2	L3
Athlon X4 845	Feb 2, 2016	28nm	CZ-A1	FM2+	4 (4) [2]	3.5 GHz	3.8 GHz	96 KB inst. per module 32 KB data per core	2× 1 MB	N/A	N/A				DDR3-2133	65 W	AD845XYBJCSBX AD845XACKASBX	AD845XACI43KA
A6-7480[54]	Oct 2018				2 (2) [1]	3.5 GHz	3.8 GHz		1 MB		R5	384:24:8 6 CU	900 MHz	691.2			AD7480ACABBOX	AD7480ACI23AB
A8-7680[55]					4 (4) [2]	3.5 GHz	3.8 GHz		2× 1 MB		R7						AD7680ACABBOX	AD7680ACI43AB
PRO A6-8570E	Oct 2016			AM4	2 (2) [1]	3.0 GHz	3.4 GHz		1 MB		R5	256:16:4 4 CU	800 MHz	409.6	DDR4-2400	35 W		AD857BAHM23AB
PRO A6-8570						3.5 GHz	3.8 GHz					384:24:6 6 CU	1029 MHz	790.2		65 W		AD857BAGM23AB
PRO A10-8770E					4 (4) [2]	2.8 GHz	3.5 GHz		2× 1 MB		R7		847 MHz	650.4		35 W		AD877BAHM44AB
PRO A10-8770						3.5 GHz	3.8 GHz						1029 MHz	790.2		65 W		AD877BAGM44AB
PRO A12-8870E						2.9 GHz	3.8 GHz					512:32:8 8 CU	900 MHz	921.6		35 W		AD887BAHM44AB
PRO A12-8870						3.7 GHz	4.2 GHz						1108 MHz	1134.5		65 W		AD887BAUM44AB

1. With cooler if available.
2. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
3. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Bristol Ridge" (2016)

• Fabrication 28 nm by GlobalFoundries
• Socket AM4, support for PCIe 3.0
• Two or four "Excavator+" CPU cores
• L1 Cache: 32 KB Data per core and 96 KB Instructions per module
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, XOP, FMA3, FMA4, F16C, ABM, BMI1, BMI2, TBM, RDRAND, Turbo Core
• Dual-channel DDR4 memory controller
• PCI Express 3.0 x8 (No Bifurcation support, requires a PCI-e switch for any configuration other than x8)
• PCI Express 3.0 x4 as link to optional external chipset
• 4x USB 3.1 Gen 1
• Storage: 2x SATA and 2x NVMe or 2x PCI Express
• Third Generation GCN based GPU[56] with hybrid VP9 decoding

Model	Released	Fab	Stepping	CPU						GPU				Memory support	TDP	Stock Cooler (box)[lower-alpha 1]	Box Number[lower-alpha 2]	Part number
				Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 3]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 4]
							L1	L2	L3
Athlon X4 940	July 27, 2017	28nm	BR-A1	4 (4) [2]	3.2 GHz	3.6 GHz	96 KB inst. per module 32 KB data per core	2× 1 MB	N/A	N/A				DDR4-2400	65 W	Near-Silent 65 W	AD940XAGABBOX	AD940XAGM44AB
Athlon X4 950					3.5 GHz	3.8 GHz											AD950XAGABBOX	AD950XAGM44AB
Athlon X4 970					3.8 GHz	4.0 GHz											AD970XAUABBOX	AD970XAUM44AB
A6-9500E	September 5, 2016			2 (2) [1]	3.0 GHz	3.4 GHz		1× 1 MB		R5	256:16:4 4 CU	800 MHz	409.6		35 W	Near-Silent 65 W	AD9500AHABBOX	AD9500AHM23AB
PRO A6-9500E	October 3, 2016															?	?	?
A6-9400	March 16, 2019				3.4 GHz	3.7 GHz					192:12:4 3 CU	720 MHz	276.4		65 W	Z7LH01R201	AD9400AGABBOX
A6-9500	September 5, 2016				3.5 GHz	3.8 GHz					384:24:6 6 CU	1029 MHz	790.2			Near-Silent 65 W	AD9500AGABBOX	AD9500AGM23AB
PRO A6-9500	October 3, 2016															?	?	?
A6-9550	July 27, 2017				3.8 GHz	4.0 GHz					256:16:4 4 CU	800 MHz	409.6			Near-Silent 65 W	AD9550AGABBOX	D9550AGM23AB
A8-9600	September 5, 2016			4 (4) [2]	3.1 GHz	3.4 GHz		2× 1 MB		R7	384:24:6 6 CU	900 MHz	691.2		65 W	Near-Silent 65 W	AD9600AGABBOX	AD9600AGM44AB
PRO A8-9600	October 3, 2016															?	?	?
A10-9700E	September 5, 2016				3.0 GHz	3.5 GHz						847 MHz	650.4		35 W	Near-Silent 65 W	AD9700AHABBOX	AD9700AHM44AB
PRO A10-9700E	October 3, 2016															?	?	?
A10-9700	September 5, 2016				3.5 GHz	3.8 GHz						1029 MHz	790.2		65 W	Near-Silent 65 W	AD9700AGABBOX	D9700AGM44AB
PRO A10-9700	October 3, 2016															?	?	?
A12-9800E	September 5, 2016				3.1 GHz	3.8 GHz					512:32:8[57] 8 CU	900 MHz	921.6		35 W	Near-Silent 65 W	AD9800AHABBOX	AD9800AUM44AB
PRO A12-9800E	October 3, 2016															?	?	?
A12-9800	September 5, 2016				3.8 GHz	4.2 GHz						1108 MHz	1134.5		65 W	Near-Silent 65 W	AD9800AUM44AB
PRO A12-9800	October 3, 2016															?	?	?

1. A box without cooler might also be available (WOF).
2. With cooler if available.
3. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
4. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Raven Ridge" (2018)

• Fabrication 14 nm by GlobalFoundries
• Transistors: 4.94 billion
• Die size: 210 mm²
• Socket AM4
• Zen CPU cores
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, FMA3, F16C, ABM, BMI1, BMI2, RDRAND, Turbo Core
• Dual-channel DDR4 memory controller
• Fifth generation GCN based GPU
• Video Core Next (VCN) 1.0

Model	Release Date & Price	Process	CPU						GPU				Socket	PCIe lanes	Memory support	TDP	Stock cooler (box)[lower-alpha 1]	Box Number	Part Number
			Cores (threads)	Clock rate (GHz)		Cache[lower-roman 1]			Model	Config[lower-roman 2]	Clock	Processing power (GFLOPS)[lower-roman 3]
				Base	Boost	L1	L2	L3
Athlon 200GE[59]	September 6, 2018 US $55	GloFo 14LP	2 (4)	3.2	N/A	64 KB inst. 32 KB data per core	512 KB per core	4 MB	Vega 3	192:12:4 3 CU	1000 MHz	384	AM4	16 (8+4+4)	DDR4-2666 dual-channel	35 W	Basic Stock Cooler	YD200GC6FBBOX	YD200GC6M2OFB YD20GGC6M2OFB
Athlon Pro 200GE[60]	September 6, 2018 OEM																N/A	N/A	YD200BC6M2OFB
Athlon 220GE[61]	December 21, 2018 US $65			3.4													Basic Stock Cooler	YD220GC6FBBOX	YD220GC6M2OFB
Athlon 240GE[62]	December 21, 2018 US $75			3.5														YD240GC6FBBOX	YD240GC6M2OFB
Athlon 3000G[63]	November 19, 2019 US $49										1100 MHz	424.4						YD3000C6FHBOX	YD3000C6M2OFH
Athlon 300GE[64]	July 7, 2019 OEM			3.4													N/A	N/A	YD30GEC6M2OFH
Athlon Silver 3050GE[65]	July 21, 2020 OEM																		YD305GC6M2OFH
Ryzen 3 2200GE[66]	April 19, 2018 OEM		4 (4)	3.2	3.6				Vega 8	512:32:16 8 CU		1126			DDR4-2933 dual-channel				YD2200C6M4MFB
Ryzen 3 Pro 2200GE[67]	May 10, 2018 OEM																		YD220BC6M4MFB
Ryzen 3 2200G	February 12, 2018 US $99			3.5	3.7											45–65 W	Wraith Stealth	YD2200C5FBBOX	YD2200C5M4MFB
Ryzen 3 Pro 2200G[68]	May 10, 2018 OEM																N/A	N/A	YD220BC5M4MFB
Ryzen 5 2400GE[69]	April 19, 2018 OEM		4 (8)	3.2	3.8				RX Vega 11	704:44:16	1250 MHz	1760				35 W			YD2400C6M4MFB
Ryzen 5 Pro 2400GE[70]	May 10, 2018 OEM																		YD240BC6M4MFB
Ryzen 5 2400G[71]	February 12, 2018[72][73] US $169			3.6	3.9											45–65 W	Wraith Stealth	YD2400C5FBBOX	YD2400C5M4MFB
Ryzen 5 Pro 2400G[74]	May 10, 2018 OEM																N/A	N/A	YD240BC5M4MFB

1. AMD defines 1 kilobyte (KB) as 1024 bytes, and 1 megabyte (MB) as 1024 kilobytes.[58]
2. Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)
3. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Picasso" (2019)

• Fabrication 12 nm by GlobalFoundries
• Transistors: 4.94 billion
• Die size: 210 mm²
• Socket AM4
• Zen+ CPU cores
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, FMA3, F16C, ABM, BMI1, BMI2, RDRAND, Turbo Core
• Dual-channel DDR4 memory controller
• Fifth generation GCN based GPU
• Video Core Next (VCN) 1.0

Model	Release Date & Price	Fab	CPU						GPU				Socket	PCIe lanes	Memory support	TDP	Part Number
			Cores (threads)	Clock rate (GHz)		Cache			Model	Config[lower-roman 1]	Clock	Processing power (GFLOPS)[lower-roman 2]
				Base	Boost	L1	L2	L3
Athlon Pro 300GE[75]	September 30, 2019 OEM	12 nm	2 (4)	3.4	N/A	64 KiB inst. 32 KB data per core	512 KiB per core	4 MiB	Vega 3	192:12:4 3 CU	1100 MHz	424.4	AM4	16 (8+4+4)	DDR4-2667 dual-channel	35 W	YD300BC6M2OFH
Athlon Silver Pro 3125GE[76]	July 21, 2020 OEM																YD3125C6M2OFH
Athlon Gold 3150GE[77]			4 (4)	3.3	3.8										DDR4-2933 dual-channel		YD3150C6M4MFH
Athlon Gold Pro 3150GE[78]																	YD315BC6M4MFH
Athlon Gold 3150G[79]				3.5	3.9											45-65 W	YD3150C5M4MFH
Athlon Gold Pro 3150G[80]																	YD315BC5M4MFH
Ryzen 3 3200GE[81]	July 7, 2019 OEM			3.3	3.8				Vega 8	512:32:16 8 CU	1200 MHz	1228.8				35 W	YD3200C6M4MFH
Ryzen 3 Pro 3200GE[82]	September 30, 2019 OEM																YD320BC6M4MFH
Ryzen 3 3200G[83]	July 7, 2019 US $99			3.6	4.0						1250 MHz	1280				45-65 W	YD3200C5M4MFH
Ryzen 3 Pro 3200G[84]	September 30, 2019 OEM																YD320BC5M4MFH
Ryzen 5 3350GE	July 21, 2020 OEM		4 (8)	3.3	3.9				RX Vega 11	704:44:16 11 CU	1200 MHz					35 W	YD3350C6M4MFH
Ryzen 5 Pro 3350GE[85]																	YD335BC6M4MFH
Ryzen 5 3350G				3.6	4.0						1300 MHz	1830.4				45-65 W	YD3350C5M4MFH
Ryzen 5 Pro 3350G[86]																	YD335BC5M4MFH
Ryzen 5 3400GE[87]	July 7, 2019 OEM			3.3	4.0											35 W	YD3400C6M4MFH
Ryzen 5 Pro 3400GE[88]	September 30, 2019 OEM																YD340BC6M4MFH
Ryzen 5 3400G[89]	July 7, 2019 US $149			3.7	4.2						1400 MHz	1971.2				45-65 W	YD3400C5M4MFH
Ryzen 5 Pro 3400G[90]	September 30, 2019 OEM																YD340BC5M4MFH

1. Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Renoir" (2020)

• Fabrication 7 nm by TSMC
• Socket AM4
• Up to eight Zen 2 CPU cores
• Dual-channel DDR4 memory controller

Model	Release date and price	Fab.	CPU							GPU				Socket	PCIe lanes	Memory support	TDP
			Cores (threads)	Core Config[lower-roman 1]	Clock rate (GHz)		Cache			Model	Config.[lower-roman 2]	Clock	Processing power (GFLOPS)[lower-roman 3]
					Base	Boost	L1	L2	L3
Ryzen 3 4300GE [91]	2H 2020 [92]	TSMC 7FF	4 (8)	1 × 4	3.5	4.0	32 KiB inst. 32 KiB data per core	512 KiB per core	4 MiB	Vega 6	384:24:8 6 CU	1700 MHz	1305.6	AM4	24 (16+4+4)	DDR4-3200 dual-channel	35 W
Ryzen 3 Pro 4350GE[91]
Ryzen 3 4300G[91]					3.8	4.0											65 W
Ryzen 3 Pro 4350G[91]
Ryzen 5 4600GE[91]			6 (12)	2 × 3	3.3	4.2			8 MiB 4 MiB per CCX	Vega 7	448:28:8 7 CU	1900 MHz	1702.4				35 W
Ryzen 5 Pro 4650GE[91]
Ryzen 5 4600G[91]					3.7	4.2											65 W
Ryzen 5 Pro 4650G[91]
Ryzen 7 4700GE[91]			8 (16)	2 × 4	3.1	4.3				Vega 8	512:32:8 8 CU	2000 MHz	2048				35 W
Ryzen 7 Pro 4750GE[91]
Ryzen 7 4700G[91]					3.6	4.4						2100 MHz	2150.4				65 W
Ryzen 7 Pro 4750G[91]

1. Active core complexes (CCXs) × active cores per CCX.
2. Unified shaders : texture mapping units : render output units and compute units (CU)
3. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

Server APUs

Opteron X2100-series "Kyoto" (2013)

• Fabrication 28 nm
• Socket FT3 (BGA)
• 4 CPU Cores (Jaguar (microarchitecture))
• L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AVX, F16C, CLMUL, AES, MOVBE (Move Big-Endian instruction), XSAVE/XSAVEOPT, ABM, BMI1, AMD-V support
• Turbo Dock Technology, C6 and CC6 low power states
• GPU based on GCN (Graphics Core Next) architecture

Model	Released	Fab	Stepping	CPU					GPU				Memory support	TDP	Part number	Release price (USD)
				Cores (threads)	Clock	Cache[lower-alpha 2]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 3]
						L1	L2	L3
X1150	May 2013	28nm	KB-A1	4 (4)	2.0 GHz	32 KB inst. 32 KB data per core	2 MB	N/A	N/A				DDR3	9 W		$64
X2150					1.9 GHz				HD 8400	128:8:4	266 MHz	28.9		22 W	OX2150IAJ44HM	$99
X2170	September 2016				2.4 GHz						600MHz	153.6	DDR3	25 W	OX2170IXJ44JB

1. A box without cooler might also be available (WOF).
2. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
3. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

Opteron X3000-series "Toronto" (2017)

• Fabrication 28 nm
• Socket FP4
• Two or Four CPU cores based on the Excavator microarchitecture[93][94]
• L1 Cache: 32 KB Data per core and 96 KB Instructions per module
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, XOP, FMA3, FMA4, F16C, ABM, BMI1, BMI2, TBM, RDRAND
• DDR4 SDRAM
• GPU based on 3rd Generation GCN (Graphics Core Next) architecture

Model	Released	Fab	Stepping	CPU						GPU				Memory support	TDP	Part number	Release price (USD)
				Cores (threads)	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
X3216	Q2 2017	28nm	01h	2 (2)	1.6 GHz	3.0 GHz	96 KB inst. per module 32 KB data per core	1 MB	N/A	R5	256:16:4 4 CU	800 MHz	409.6	DDR4-1600	12-15 W	Un­known	OEM for HP
X3418				4 (4)	1.8 GHz	3.2 GHz		2 MB		R7	384:24:6 6 CU		614.4	DDR4-2400	12-35 W
X3421					2.1 GHz	3.4 GHz					512:32:8 8 CU		819.2

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

Mobile APUs

Sabine: "Llano" (2011)

• Fabrication 32 nm on GlobalFoundries SOI process
• Socket FS1
• Upgraded Stars (AMD 10h architecture) codenamed Husky CPU cores (K10.5) with no L3 cache, and with Redwood-class integrated graphics on die
• L1 Cache: 64 KB Data per core and 64 KB Instructions per core(BeaverCreek for the dual-core variants and WinterPark for the quad-core variants)
• Integrated PCIe 2.0 controller
• GPU: TeraScale 2
• Select models support Turbo Core technology for faster CPU operation when the thermal specification permits
• Support for 1.35 V DDR3L-1333 memory, in addition to regular 1.5 V DDR3 memory specified
• 2.5 GT/s UMI
• MMX, Enhanced 3DNow!, SSE, SSE2, SSE3, SSE4a, ABM, NX bit, AMD64, AMD-V
• PowerNow!

Model	Released	Fab	Stepping	CPU						GPU				Memory support	TDP	Part number
				Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
E2-3000M	Jun 14, 2011	32nm	B0	2 (2) [1]	1.8 GHz	2.4 GHz	64 KB inst. 64 KB data per core	2 × 512 KB	N/A	HD 6380G	160:8:4	400 MHz	128	DDR3-1333	35 W	EM3000DDX22GX
A4-3300M	Jun 14, 2011				1.9 GHz	2.5 GHz		2 × 1 MB		HD 6480G	240:12:4	444 MHz	213.1		35 W	AM3300DDX23GX
A4-3305M	Dec 7, 2011							2 × 512 KB			160:8:4	593 MHz	189.7			AM3305DDX22GX
A4-3310MX	Jun 14, 2011				2.1 GHz			2 × 1 MB			240:12:4	444MHz	213.1		45 W	AM3310HLX23GX
A4-3320M	Dec 7, 2011				2.0 GHz	2.6 GHz									35 W	AM3320DDX23GX
A4-3330MX					2.2 GHz										45 W	AM3330HLX23GX
A4-3330MX					2.3 GHz			2 × 512 KB			160:8:4	593 MHz	189.7			AM3330HLX23HX
A6-3400M	Jun 14, 2011			4 (4) [2]	1.4 GHz	2.3 GHz		4 × 1 MB		HD 6520G	320:16:8	400 MHz	256		35 W	AM3400DDX43GX
A6-3410MX					1.6 GHz									DDR3-1600	45 W	AM3410HLX43GX
A6-3420M	Dec 7, 2011				1.5 GHz	2.4 GHz								DDR3-1333	35 W	AM3420DDX43GX
A6-3430MX					1.7 GHz									DDR3-1600	45 W	AM3430HLX43GX
A8-3500M	Jun 14, 2011				1.5 GHz	2.4 GHz				HD 6620G	400:20:8	444 MHz	355.2	DDR3-1333	35 W	AM3500DDX43GX
A8-3510MX					1.8 GHz	2.5 GHz								DDR3-1600	45 W	AM3510HLX43GX
A8-3520M	Dec 7, 2011				1.6 GHz									DDR3-1333	35 W	AM3520DDX43GX
A8-3530MX	Jun 14, 2011				1.9 GHz	2.6 GHz								DDR3-1600	45 W	AM3530HLX43GX
A8-3550MX	Dec 7, 2011				2.0 GHz	2.7 GHz										AM3550HLX43GX

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

Comal: "Trinity" (2012)

An AMD A10-4600M APU

• Fabrication 32 nm on GlobalFoundries SOI process
• Socket FS1r2, FP2
• Based on the Piledriver architecture
• L1 Cache: 16 KB Data per core and 64 KB Instructions per module
• GPU: TeraScale 3 (VLIW4)
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, XOP, FMA3, FMA4, F16C, ABM, BMI1, TBM, Turbo Core
• Memory support: 1.35 V DDR3L-1600 memory, in addition to regular 1.5 V DDR3 memory specified (Dual-channel)
• 2.5 GT/s UMI
• Transistors: 1.303 billion
• Die size: 246 mm²

Model number	Released	Fab	Stepping	Socket	CPU						GPU					Memory support	TDP	Part number
					Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config^2	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
								L1	L2	L3
A4-4355M	Sep 27, 2012	32nm	TN-A1	FP2	2 (2) [1]	1.9 GHz	2.4 GHz	64 KB inst. per module 16 KB data per core	1 MB	N/A	HD 7400G	192:12:4 3 CU	327 MHz	424 MHz	125.5	DDR3-1333	17 W	AM4355SHE23HJ
A6-4455M	May 15, 2012					2.1 GHz	2.6 GHz		2 MB		HD 7500G	256:16:8 4 CU			167.4			AM4455SHE24HJ
A8-4555M	Sep 27, 2012				4 (4) [2]	1.6 GHz	2.4 GHz		2× 2 MB		HD 7600G	384:24:8 6 CU	320 MHz		245.7		19 W	AM4555SHE44HJ
A8-4557M[95]	March 2013					1.9 GHz	2.8 GHz				HD 7000	256:16:8 4 CU	497 MHz	655 MHz	254.4	DDR3L-1600	35 W	AM4557DFE44HJ
A10-4655M	May 15, 2012					2.0 GHz	2.8 GHz				HD 7620G	384:24:8 6 CU	360 MHz	496 MHz	276.4	DDR3-1333	25 W	AM4655SIE44HJ
A10-4657M[95]	March 2013					2.3 GHz	3.2 GHz				HD 7000		497 MHz	686 MHz	381.6	DDR3L-1600	35 W	AM4657DFE44HJ
A4-4300M	May 15, 2012			FS1	2 (2) [1]	2.5 GHz	3.0 GHz		1 MB		HD 7420G	128:8:4 2 CU	480 MHz	655 MHz	122.8	DDR3-1600		AM4300DEC23HJ
A6-4400M						2.7 GHz	3.2 GHz				HD 7520G	192:12:4 3 CU	496 MHz	685 MHz	190.4			AM4400DEC23HJ
A8-4500M					4 (4) [2]	1.9 GHz	2.8 GHz		2× 2 MB		HD 7640G	256:16:8 4 CU			253.9			AM4500DEC44HJ
A10-4600M						2.3 GHz	3.2 GHz				HD 7660G	384:24:8 6 CU			380.9			AM4600DEC44HJ

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Richland" (2013)

• Fabrication 32 nm on GlobalFoundries SOI process
• Socket FS1r2, FP2
• Elite Performance APU.[96][97]
• CPU: Piledriver architecture
  • L1 Cache: 16 KB Data per core and 64 KB Instructions per module
• GPU: TeraScale 3 (VLIW4)
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, XOP, FMA3, FMA4, F16C, ABM, BMI1, TBM, Turbo Core

Model number	Released	Fab	Stepping	Socket	CPU						GPU					Memory support	TDP	Part number
					Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config^2	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
								L1	L2	L3
A4-5145M	May 2013	32nm	RL-A1	FP2	2 (2) [1]	2.0 GHz	2.6 GHz	64 KB inst. per module 16 KB data per core	1 MB	N/A	HD 8310G	128:8:4 2 CU	424 MHz	554 MHz	108.5	DDR3L-1333	17 W	AM5145SIE44HL
A6-5345M						2.2 GHz	2.8 GHz				HD 8410G	192:12:4 3 CU	450 MHz	600 MHz	172.8			AM5345SIE44HL
A8-5545M					4 (4) [2]	1.7 GHz	2.7 GHz		4 MB		HD 8510G	384:28:8 6 CU		554 MHz	345.6		19 W	AM5545SIE44HL
A10-5745M						2.1 GHz	2.9 GHz				HD 8610G		533 MHz	626 MHz	409.3		25 W	AM5745SIE44HL
A4-5150M	Q1 2013			FS1	2 (2) [1]	2.7 GHz	3.3 GHz		1 MB		HD 8350G	128:8:4 2 CU	533 MHz	720 MHz	136.4	DDR3-1600	35 W	AM5150DEC23HL
A6-5350M						2.9 GHz	3.5 GHz				HD 8450G	192:12:4 3 CU			204.6			AM5350DEC23HL
A6-5357M	May 2013															DDR3L-1600		AM5357DFE23HL
A8-5550M	Q1 2013				4 (4) [2]	2.1 MHz	3.1 GHz		4 MB		HD 8550G	256:16:8 4 CU	515 MHz		263.6	DDR3-1600		AM5550DEC44HL
A8-5557M	May 2013												554 MHz		283.6	DDR3L-1600		AM5557DFE44HL
A10-5750M	Q1 2013					2.5 GHz	3.5 GHz				HD 8650G	384:24:8 6 CU	533 MHz		409.3	DDR3-1866		AM5750DEC44HL
A10-5757M	May 2013												600 MHz		460.8	DDR3L-1600		AM5757DFE44HL

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Kaveri" (2014)

• Fabrication 28 nm
• Socket FP3
• Up to 4 Steamroller x86 CPU cores with 4 MB of L2 cache.[98]
• L1 Cache: 16 KB Data per core and 96 KB Instructions per module
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, XOP, FMA3, FMA4, F16C, ABM, BMI1, TBM, Turbo Core
• Three to eight Compute Units (CUs) based on Graphics Core Next (GCN)[43] microarchitecture; 1 Compute Unit (CU) consists of 64 Unified Shader Processors : 4 Texture Mapping Units (TMUs) : 1 Render Output Unit (ROPs)
• AMD Heterogeneous System Architecture (HSA) 2.0
• SIP blocks: Unified Video Decoder, Video Coding Engine, TrueAudio[44]
• Dual-channel (2x64-bit) DDR3 memory controller
• Integrated custom ARM Cortex-A5 co-processor[45] with TrustZone Security Extensions[46]

Model number	Released	Fab	CPU						GPU					Memory support	TDP	Part number
			Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
						L1	L2	L3
A6-7000	June 2014	28nm	2 (2) [1]	2.2 GHz	3.0 GHz	96 KB inst. per module 16 KB data per core	1 MB	N/A	R4	192:12:3 3 CU	494 MHz	533 MHz	189.6	DDR3-1333	17W	AM7000ECH23JA
A6 Pro-7050B											533 MHz	N/A	204.6	DDR3-1600		AM705BECH23JA
A8-7100			4 (4) [2]	1.8 GHz	3.0 GHz		2× 2 MB		R5	256:16:4 4 CU	450 MHz	514 MHz	230.4	DDR3-1600	20W	AM7100ECH44JA
A8 Pro-7150B				1.9 GHz	3.2 GHz						553 MHz	N/A	283.1			AM715BECH44JA
A10-7300				1.9 GHz	3.2 GHz				R6	384:24:8 6 CU	464 MHz	533 MHz	356.3			AM7300ECH44JA
A10 Pro-7350B				2.1 GHz	3.3 GHz						553 MHz	N/A	424.7			AM735BECH44JA
FX-7500				2.1 GHz	3.3 GHz				R7		498 MHz	553 MHz	382.4			FM7500ECH44JA
A8-7200P				2.4 GHz	3.3 GHz				R5	256:16:4 4 CU	553 MHz	626 MHz	283.1	DDR3-1866	35W	AM740PDGH44JA
A10-7400P				2.5 GHz	3.4 GHz				R6	384:24:8 6 CU	576 MHz	654 MHz	442.3			AM740PDGH44JA
FX-7600P				2.7 GHz	3.6 GHz				R7	512:32:8 8 CU	600 MHz	686 MHz	614.4	DDR3-2133		FM760PDGH44JA

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Carrizo" (2015)

• Fabrication 28 nm
• Socket FP4
• Up to 4 Excavator x86 CPU cores
• L1 Cache: 32 KB Data per core and 96 KB Instructions per module
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, XOP, FMA3, FMA4, F16C, ABM, BMI1, BMI2, TBM, RDRAND, Turbo Core
• GPU based on Graphics Core Next 1.2

Model number	Released	Fab	CPU						GPU					Memory support	TDP	Part number
			Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
						L1	L2	L3
A6-8500P	June 2015	28nm	2 (2) [1]	1.6 GHz	3.0 GHz	96 KB inst. per module 32 KB data per core	1 MB	N/A	R5	256:16:4 4 CU	800 MHz	N/A	409.6	DDR3-1600	12-35W	AM850PAAY23KA
Pro A6-8500B																AM850BAAY23KA
Pro A6-8530B	Q3 2016			2.3 GHz	3.2 GHz									DDR4-1866		AM853BADY23AB
A8-8600P	June 2015		4 (4) [2]	1.6 GHz	3.0 GHz		2× 1 MB		R6	384:24:8 6 CU	720 MHz		552.9	DDR3-2133		AM860PAAY43KA
Pro A8-8600B																AM860BAAY43KA
A10-8700P				1.8 GHz	3.2 GHz						800 MHz		614.4			AM870PAAY43KA
Pro A10-8700B																AM870BAAY43KA
Pro A10-8730B	Q3 2016			2.4 GHz	3.3 GHz				R5		720 MHz		552.9	DDR4-1866		AM873BADY44AB
A10-8780P	December 2015			2.0 GHz	3.3 GHz				R8	512:32:8 8 CU				DDR3		AM878PAIY43KA
FX-8800P	June 2015			2.1 GHz	3.4 GHz				R7		800 MHz		819.2	DDR4-2133		FM880PAAY43KA
Pro A12-8800B																FM880BAAY43KA
Pro A12-8830B	Q3 2016			2.5 GHz	3.4 GHz					384:24:8 6 CU	758 MHz		582.1	DDR4-1866		AM883BADY44AB

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Bristol Ridge" (2016)

• Fabrication 28 nm
• Socket FP4[99]
• Two or four "Excavator+" x86 CPU cores
• L1 Cache: 32 KB Data per core and 96 KB Instructions per module
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, XOP, FMA3, FMA4, F16C, ABM, BMI1, BMI2, TBM, RDRAND, Turbo Core
• GPU based on Graphics Core Next 1.2 with VP9 decoding

Model number	Released	Fab	CPU						GPU					Memory support	TDP	Part number
			Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
						L1	L2	L3
Pro A6-9500B	October 24, 2016	28nm	2 (2) [1]	2.3 GHz	3.2GHz	96 KB inst. per module 32 KB data per core	1 MB	N/A	R5	256:16:4 4 CU	800 MHz	N/A	409.6	DDR4-1866	12–15W
Pro A8-9600B	October 24, 2016		4 (4) [2]	2.4 GHz	3.3 GHz		2× 1 MB		R5	384:24:6 6 CU	720 MHz		552.9	DDR4-1866	12–15W
A10-9600P	June 2016															AM960PADY44AB
A10-9620P[100]	2017 (OEM)			2.5 GHz	3.4 GHz						758 MHz		582.1
Pro A10-9700B	October 24, 2016								R7
A12-9700P	June 2016															AM970PADY44AB
Pro A8-9630B	October 24, 2016			2.6 GHz	3.3GHz				R5		800 MHz		614.4	DDR4-2400	25–45W
A10-9630P	June 2016															AM963PAEY44AB
Pro A10-9730B	October 24, 2016			2.8 GHz	3.5 GHz				R7		900 MHz		691.2
A12-9730P	June 2016															AM973PAEY44AB
Pro A12-9800B	October 24, 2016			2.7 GHz	3.6 GHz				R7	512:32:8 8 CU	758 MHz		776.1	DDR4-1866	12–15W
FX-9800P A12-9720P[101][102]	June 2016 2017 (OEM)															FM980PADY44AB ?
Pro A12-9830B	October 24, 2016			3.0 GHz	3.7 GHz						900 MHz		921.6	DDR4-2400	25–45W
FX-9830P	June 2016															FM983PAEY44AB

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Raven Ridge" (2017)

• Fabrication 14 nm by GlobalFoundries
• Transistors: 4.94 billion
• Socket FP5
• Die size: 210 mm²
• Zen CPU cores
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, FMA3, F16C, ABM, BMI1, BMI2, RDRAND, Turbo Core
• Fifth generation GCN based GPU

Model	Release date	Process	CPU						GPU				Socket	PCIe lanes	Memory support	TDP	Part number
			Cores (threads)	Clock rate (GHz)		Cache[lower-roman 1]			Model	Config[lower-roman 2]	Clock	Processing power (GFLOPS)[lower-roman 3]
				Base	Boost	L1	L2	L3
Athlon Pro 200U [104]	2019	GloFo 14LP	2 (4)	2.3	3.2	64 KB inst. 32 KB data per core	512 KB per core	4 MB	Vega 3	192:12:4 3 CU	1000 MHz	384	FP5	12 (8+4)	DDR4-2400 dual-channel	12–25W	YM200UC4T2OFB
Athlon 300U [105]	January 6, 2019			2.4	3.3												YM300UC4T2OFG
Ryzen 3 2200U [106]	January 8, 2018			2.5	3.4						1100 MHz	422.4					YM2200C4T2OFB
Ryzen 3 3200U [107]	January 6, 2019			2.6	3.5						1200 MHz	460.8					YM3200C4T2OFG
Ryzen 3 2300U [108]	January 8, 2018		4 (4)	2.0	3.4				Vega 6	384:24:8 6 CU	1100 MHz	844.8					YM2300C4T4MFB
Ryzen 3 Pro 2300U [109]	May 15, 2018																YM230BC4T4MFB
Ryzen 5 2500U [110]	October 26, 2017		4 (8)		3.6				Vega 8	512:32:16 8 CU		1126.4					YM2500C4T4MFB
Ryzen 5 Pro 2500U [111]	May 15, 2018																YM250BC4T4MFB
Ryzen 5 2600H [112]	September 10, 2018			3.2											DDR4-3200 dual-channel	35–54W	YM2600C3T4MFB
Ryzen 7 2700U [113]	October 26, 2017			2.2	3.8				Vega 10	640:40:16 10 CU	1300 MHz	1664			DDR4-2400 dual-channel	12–25W	YM2700C4T4MFB
Ryzen 7 Pro 2700U [114]	May 15, 2018																YM270BC4T4MFB
Ryzen 7 2800H [115]	September 10, 2018			3.3					Vega 11	704:44:16 11 CU		1830.4			DDR4-3200 dual-channel	35–54W	YM2800C3T4MFB

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[103]
2. Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)
3. Single precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Picasso" (2019)

• Fabrication 12 nm by GlobalFoundries
• Socket FP5
• Die size: 210 mm²
• Up to four Zen+ CPU cores
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, FMA3, F16C, ABM, BMI1, BMI2, RDRAND, Turbo Core
• Dual-channel DDR4 memory controller
• Fifth generation GCN based GPU

Model	Release date	Process	CPU						GPU				Memory support	TDP	Part number
			Cores (threads)	Clock rate (GHz)		Cache[lower-roman 1]			Model	Config[lower-roman 2]	Clock	Processing power (GFLOPS)[lower-roman 3]
				Base	Boost	L1	L2	L3
Ryzen 3 3300U[116]	January 6, 2019	GloFo 12LP (14LP+)	4 (4)	2.1	3.5	64 KB inst. 32 KB data per core	512 KB per core	4 MB	Vega 6	384:24:8 6 CU[117]	1200 MHz	921.6	DDR4-2400 dual-channel	15 W	YM3300C4T4MFG
Ryzen 3 PRO 3300U[118]	April 8, 2019														YM330BC4T4MFG
Ryzen 5 3450U[119]	June 2020		4 (8)						Vega 8	512:32:16 8 CU[120]		1228.8			YM3450C4T4MFG
Ryzen 5 3500U[121]	January 6, 2019				3.7										YM3500C4T4MFG
Ryzen 5 PRO 3500U[122]	April 8, 2019														YM350BC4T4MFG
Ryzen 5 3500C[123]	September 22, 2020														YM350CC4T4MFG
Ryzen 5 3550H[124]	January 6, 2019													35 W	YM3500C4T4MFG
Ryzen 5 3580U[125]	October 2019								Vega 9	576:36:16 9 CU	1300 MHz	1497.6		15 W
Ryzen 7 3700U[126]	January 6, 2019			2.3	4.0				Vega 10	640:40:16 10 CU[127]	1400 MHz	1792.0			YM3700C4T4MFG
Ryzen 7 PRO 3700U[128]	April 8, 2019														YM370BC4T4MFG
Ryzen 7 3700C[129]	September 22, 2020														YM370CC4T4MFG
Ryzen 7 3750H[130]	January 6, 2019													35 W	YM3700C4T4MFG
Ryzen 7 3780U[131]	October 2019								Vega 11	704:44:16 11 CU		1971.2		15 W

1. AMD defines 1 kilobyte (KB) as 1024 bytes, and 1 megabyte (MB) as 1024 kilobytes.[27]
2. Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)
3. Single precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Renoir" (2020)

• Fabrication 7 nm by TSMC[132][133][134]
• Socket FP6
• Die size: 156 mm²
• 9.8 billion transistors on one single 7nm monolithic die[135]
• Up to eight Zen 2 CPU cores
• Fifth generation GCN based GPU (7nm Vega)

Model	Release date	Fab	CPU							GPU			Socket	PCIe lanes	Memory support	TDP
			Cores (threads)	Core config[lower-roman 1]	Clock rate (GHz)		Cache			Model, config[lower-roman 2]	Clock	Processing power (GFLOPS)[lower-roman 3]
					Base	Boost	L1	L2	L3
Ryzen 3 4300U[136]	March 16, 2020	TSMC 7FF	4 (4)	1 × 4	2.7	3.7	32 KiB inst. 32 KiB data per core	512 KiB per core	4 MiB	AMD Radeon Graphics, 320:20:8 5 CU	1400 MHz	896	FP6	16 (8+4+4)	DDR4-3200 LPDDR4-4266 dual-channel	10–25 W
Ryzen 3 PRO 4450U[137]	May 7, 2020		4 (8)		2.5
Ryzen 5 4500U[138]	March 16, 2020		6 (6)	2 × 3	2.3	4.0			8 MiB 4 MiB per CCX	AMD Radeon Graphics, 384:24:8 6 CU	1500 MHz	1152
Ryzen 5 4600U[139]			6 (12)		2.1
Ryzen 5 PRO 4650U[140]	May 7, 2020
Ryzen 5 4600HS[141]	March 16, 2020				3.0											35 W
Ryzen 5 4600H[142]																35–54 W
Ryzen 7 4700U[143]			8 (8)	2 × 4	2.0	4.1				AMD Radeon Graphics, 448:28:8 7 CU	1600 MHz	1433.6				10–25 W
Ryzen 7 PRO 4750U[144]	May 7, 2020		8 (16)		1.7
Ryzen 7 4800U[145]	March 16, 2020				1.8	4.2				AMD Radeon Graphics, 512:32:8 8 CU	1750 MHz	1792
Ryzen 7 4800HS[146]					2.9					AMD Radeon Graphics, 448:28:8 7 CU	1600 MHz	1433.6				35 W
Ryzen 7 4800H[147]																35–54 W
Ryzen 9 4900HS[148]					3	4.3				AMD Radeon Graphics, 512:32:8 8 CU	1750 MHz	1792				35 W
Ryzen 9 4900H[149]					3.3	4.4										35–54 W

1. Active Core Complexes (CCX) × active cores per CCX.
2. Unified shaders : texture mapping units : render output units and compute units (CU)
3. Single precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Lucienne" (2021)

• Fabrication 7 nm by TSMC
• Socket FP6
• Die size: 156 mm²
• 9.8 billion transistors on one single 7nm monolithic die[135]
• Up to eight Zen 2 CPU cores
• Fifth generation GCN based GPU (7nm Vega)

Model	Release date	Fab	CPU							GPU			Socket	PCIe lanes	Memory support	TDP
			Cores (threads)	Core config[lower-roman 1]	Clock rate (GHz)		Cache			Model, config[lower-roman 2]	Clock	Processing power (GFLOPS)[lower-roman 3]
					Base	Boost	L1	L2	L3
Ryzen 3 5300U[150]	January 12, 2021	TSMC 7FF	4 (8)	1 × 4	2.6	3.8	32 KiB inst. 32 KiB data per core	512 KiB per core	4 MiB	AMD Radeon Graphics 6 CU	1500 MHz	-	FP6	16 (8+4+4)	DDR4-3200 LPDDR4-4266 dual-channel	10–25 W
Ryzen 5 5500U[151]			6 (12)	2 × 3	2.1	4.0			8 MiB 4 MiB per CCX	AMD Radeon Graphics 7 CU	1800 MHz
Ryzen 7 5700U[152]			8 (16)	2 × 4	1.8	4.3			8 MiB 4 MiB per CCX	AMD Radeon Graphics 8 CU	1900 MHz

1. Active Core Complexes (CCX) × active cores per CCX.
2. Unified shaders : texture mapping units : render output units and compute units (CU)
3. Single precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Cezanne" (2021)

• Fabrication 7 nm by TSMC
• Socket FP6
• Die size: 180 mm²
• Up to eight Zen 3 CPU cores
• Fifth generation GCN based GPU (7nm Vega)

Model	Release date	Fab	CPU							GPU			Socket	PCIe lanes	Memory support	TDP
			Cores (threads)	Core config[lower-roman 1]	Clock rate (GHz)		Cache			Model, config[lower-roman 2]	Clock	Processing power (GFLOPS)[lower-roman 3]
					Base	Boost	L1	L2	L3
Ryzen 3 5400U[153]	January 12, 2021	TSMC 7FF	4 (8)	1 x 4	2.6	4.0	32 KiB inst. 32 KiB data per core	512 KiB per core	8 MiB	AMD Radeon Graphics 6 CU	1600 MHz	-	FP6	16 (8+4+4)	DDR4-3200 LPDDR4-4266 dual-channel	10–25 W
Ryzen 5 5600U[154]			6 (12)	2 × 3	2.3	4.2			16 MiB	AMD Radeon Graphics 7 CU	1800 MHz
Ryzen 5 5600H[155]					3.3											35–54 W
Ryzen 5 5600HS[156]					3.0
Ryzen 7 5800U[157]			8 (16)	2 × 4	1.9	4.4				AMD Radeon Graphics 8 CU	2000 MHz					10–25 W
Ryzen 7 5800H[158]					3.2											35–54 W
Ryzen 7 5800HS[159]					2.8
Ryzen 9 5900HS[160]					3.0	4.6					2100 MHz
Ryzen 9 5900HX[161]					3.3
Ryzen 9 5980HS[162]					3.0	4.8
Ryzen 9 5980HX[163]					3.3

1. Active Core Complexes (CCX) × active cores per CCX.
2. Unified shaders : texture mapping units : render output units and compute units (CU)
3. Single precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

Ultra-mobile APUs

Brazos: "Desna", "Ontario", "Zacate" (2011)

• Fabrication 40 nm by TSMC
• Socket FT1 (BGA-413)
• Based on the Bobcat microarchitecture[164]
• L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, ABM, NX bit, AMD64, AMD-V
• PowerNow!
• DirectX 11 integrated graphics with UVD 3.0
• Z-series denote Desna; C-series denote Ontario; and the E-series denotes Zacate
• 2.50 GT/s UMI (PCIe 1.0 ×4)

Model	Released	Fab	Stepping	CPU						GPU					Memory support	TDP	Part number
				Cores (threads) FPUs	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
Z-01	Jun 1, 2011	40nm	B0	2 (2) [1]	1.0 GHz	N/A	32 KB inst. 32 KB data per core	2 × 512 KB	N/A	HD 6250	80:8:4	276 MHz	N/A	44.1	DDR3-1066	5.9 W	XMZ01AFVB22GV
C-30	Jan 4, 2011			1 (1) [1]	1.2 GHz			512 KB								9 W	CMC30AFPB12GT
C-50				2 (2) [1]	1.0 GHz			2 × 512 KB									CMC50AFPB22GT
C-60	Aug 22, 2011		C0			1.33 GHz				HD 6290			400 MHz				CMC60AFPB22GV
E-240	Jan 4, 2011		B0	1 (1) [1]	1.5 GHz	N/A		512 KB		HD 6310		500 MHz	N/A	80	DDR3-1066	18W	EME240GBB12GT
E-300	Aug 22, 2011			2 (2) [1]	1.3 GHz			2 × 512 KB				488 MHz		78			EME300GBB22GV
E-350	Jan 4, 2011				1.6 GHz							492 MHz		78.7			EME350GBB22GT
E-450	Aug 22, 2011		B0 C0		1.65 GHz					HD 6320		508 MHz	600 MHz	81.2	DDR3-1333		EME450GBB22GV

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

Brazos 2.0: "Ontario", "Zacate" (2012)

• Fabrication 40 nm by TSMC
• Socket FT1 (BGA-413)
• Based on the Bobcat microarchitecture[164]
• L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, ABM, NX bit, AMD64, AMD-V
• PowerNow!
• DirectX 11 integrated graphics
• C-series denote Ontario; and the E-series denotes Zacate
• 2.50 GT/s UMI (PCIe 1.0 ×4)

Model	Released	Fab	Stepping	CPU						GPU					Memory support	TDP	Part number
				Cores (threads) FPUs	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
C-70	Sep 15, 2012	40nm	C0	2 (2) [1]	1.0 GHz	1.33 GHz	32 KB inst. 32 KB data per core	2 × 512 KB	N/A	HD 7290	80:8:4	276 MHz	400 MHz	44.1	DDR3-1066	9 W	CMC70AFPB22GV
E1-1200	Jun 6, 2012		C0		1.4 GHz	N/A				HD 7310		500 MHz	N/A	80	DDR3-1066	18 W	EM1200GBB22GV
E1-1500	Jan 7, 2013				1.48 GHz							529 MHz		84.6
E2-1800	Jun 6, 2012				1.7 GHz					HD 7340		523 MHz	680 MHz	83.6	DDR3-1333		EM1800GBB22GV
E2-2000	Jan 7, 2013				1.75 GHz							538 MHz	700 MHz	86

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

Brazos-T: "Hondo" (2012)

• Fabrication 40 nm by TSMC
• Socket FT1 (BGA-413)
• Based on the Bobcat microarchitecture[164]
• L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• Found in tablet computers
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, ABM, NX bit, AMD64, AMD-V
• PowerNow!
• DirectX 11 integrated graphics
• 2.50 GT/s UMI (PCIe 1.0 ×4)

Model	Released	Fab	Stepping	CPU				GPU				Memory support	TDP	Part number
				Cores (threads) FPUs	Clock	Cache[lower-alpha 1]		Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 2]
						L1	L2
Z-60	Oct 9, 2012	40nm	C0	2 (2) [1]	1.0 GHz	32 KB inst. 32 KB data per core	2× 512 KB	HD 6250	80:8:4	276 MHz	44.1	DDR3-1066	4.5 W	XMZ60AFVB22GV

1. AMD in its technical documentation uses KB, which it defines as "kilobyte" and as equal to 1024 B (i.e., 1 KiB), and MB, which it defines as "megabyte" and as equal to 1024 KB (1 MiB).[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Kabini", "Temash" (2013)

• Fabrication 28 nm by TSMC
• Socket FT3 (BGA)
• 2 to 4 CPU Cores (Jaguar (microarchitecture))
• L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AVX, F16C, CLMUL, AES, MOVBE (Move Big-Endian instruction), XSAVE/XSAVEOPT, ABM, BMI1, AMD-V support
• Turbo Dock Technology, C6 and CC6 low power states
• GPU based on Graphics Core Next (GCN)
• AMD Eyefinity multi-monitor for up to two displays

Temash, Elite Mobility APU

Model	Released	Fab	Stepping	CPU						GPU				Memory support	TDP	Part number
				Cores (threads) FPUs	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Turbo
							L1	L2	L3
A4-1200	May 23, 2013	28nm	KB-A1	2 (2) [1]	1.0 GHz	N/A	32 KB inst. 32 KB data per core	1 MB	N/A	HD 8180	128:8:4 2 CU	225 MHz	N/A	DDR3L-1066	4 W	AT1200IFJ23HM
A4-1250										HD 8210		300 MHz		DDR3L-1333	8W	AT1250IDJ23HM
A4-1350				4 (4) [2]				2 MB						DDR3L-1066		AT1350IDJ44HM
A6-1450						1.4 GHz				HD 8250			400 MHz			AT1450IDJ44HM

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]

Kabini, Mainstream APU

Model	Released	Fab	Stepping	CPU					GPU			Memory support	TDP	Part number
				Cores (threads) [FPUs]	Clock	Cache[lower-alpha 1]			Model	Config	Clock
						L1	L2	L3
E1-2100	May 2013	28nm	KB-A1	2 (2) [1]	1.0 GHz	32 KB inst. 32 KB data per core	1 MB	N/A	HD 8210	128:8:4 2 CU	300 MHz	DDR3L-1333	9 W	EM2100ICJ23HM
E1-2200	Feb 2014				1.05 GHz									EM2200ICJ23HM
E1-2500	May 2013				1.4 GHz				HD 8240		400 MHz		15 W	EM2500IBJ23HM
E2-3000					1.65 GHz				HD 8280		450 MHz	DDR3L-1600		EM3000IBJ23HM
E2-3800	Feb 2014			4	1.3 GHz		2 MB							EM3800IBJ44HM
A4-5000	May 2013				1.5 GHz				HD 8330		497 MHz			AM5000IBJ44HM
A4-5100	Feb 2014				1.55 GHz									AM5100IBJ44HM
A6-5200	May 2013				2.0 GHz				HD 8400		600 MHz		25 W	AM5200IAJ44HM
A4 Pro-3340B	Nov 2014				2.2 GHz				HD 8240		400 MHz			AM334BIAJ44HM

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]

"Beema", "Mullins" (2014)

• Fabrication 28 nm by GlobalFoundries
• Socket FT3b (BGA)
• CPU: 2 to 4 (Puma cores)
  • L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• GPU based on Graphics Core Next (GCN)
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AVX, F16C, CLMUL, AES, MOVBE (Move Big-Endian instruction), XSAVE/XSAVEOPT, ABM, BMI1, AMD-V support
• Intelligent Turbo Boost
• Platform Security Processor, with an integrated ARM Cortex-A5 for TrustZone execution

Mullins, Tablet/2-in-1 APU

Model	Released	Fab	Stepping	CPU						GPU				Memory support	TDP	Part number
				Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Turbo
							L1	L2	L3
E1 Micro-6200T	Q2 2014	28nm	ML-A1	2 (2) [1]	1.0 GHz	1.4 GHz	32 KB inst. 32 KB data per core	1 MB	N/A	R2	128:8:4 2 CU	300 MHz	600 MHz	DDR3L-1066	3.95 W	EM620TIWJ23JB
A4 Micro-6400T				4 (4) [2]		1.6 GHz		2 MB		R3		350 MHz	686 MHz	DDR3L-1333	4.5 W	AM640TIVJ44JB
A10 Micro-6700T					1.2 GHz	2.2 GHz				R6		500 MHz	N/A			AM670TIVJ44JB

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]

Beema, Notebook APU

Model	Released	Fab	Stepping	CPU						GPU				Memory support	TDP	Part number
				Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Turbo
							L1	L2	L3
E1-6010	Q2 2014	28nm	ML-A1	2 (2) [1]	1.35 GHz	N/A	32 KB inst. 32 KB data per core	1 MB	N/A	R2	128:8:4 2 CU	300 MHz	600 MHz	DDR3L-1333	10 W	EM6010IUJ23JB
E1-6015[165]	Q2 2015				1.4 GHz
E2-6110	Q2 2014			4 (4) [2]	1.5 GHz			2 MB						DDR3L-1600	15 W	EM6110ITJ44JB
A4-6210					1.8 GHz					R3		350 MHz	686 MHz			AM6210ITJ44JB
A4-6250J[166]					2.0 GHz										25 W
A6-6310					1.8 GHz	2.4 GHz				R4		300 MHz	800 MHz	DDR3L-1866	15 W	AM6310ITJ44JB
A8-6410					2.0 GHz					R5						AM6410ITJ44JB
A4 Pro-3350B	May 2016									R4				DDR3-1600		AM335BITJ44JB

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]

"Carrizo-L" (2015)

• Fabrication 28 nm by GlobalFoundries
• Socket FT3b (BGA), FP4 (µBGA)[167]
• CPU: 2 to 4 (Puma+ cores)
  • L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• GPU based on Graphics Core Next (GCN)
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AVX, F16C, CLMUL, AES, MOVBE (Move Big-Endian instruction), XSAVE/XSAVEOPT, ABM, BMI1, AMD-V support
• Intelligent Turbo Boost
• Platform Security Processor, with an integrated ARM Cortex-A5 for TrustZone execution
• All models except A8-7410 available in both laptop and all-in-one desktop versions

Model	Released	Fab	Stepping	CPU						GPU				Memory support	TDP	Part number
				Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Turbo
							L1	L2	L3
E1-7010	May 2015	28nm	ML-A1	2	1.5 GHz	N/A	32 KB inst. 32 KB data per core	1 MB	N/A	R2	128:8:4 2 CU		400 MHz	DDR3L-1333	10 W	EM7010IUJ23JB EM7010JCY23JB EM7010JCY23JBD
E2-7110				4	1.8 GHz			2 MB		R2			600 MHz	DDR3L-1600	12–25 W	EM7110ITJ44JB EM7110JBY44JB EM7110JBY44JBD
A4-7210						2.2 GHz				R3			686 MHz			AM7210ITJ44JB AM7210JBY44JBD
A6-7310					2.0 GHz	2.4 GHz				R4			800 MHz	DDR3L-1866		AM7310ITJ44JB AM7310JBY44JB AM7310JBY44JBD
A8-7410					2.2 GHz	2.5 GHz				R5			847 MHz			AM7410JBY44JB

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]

"Stoney Ridge" (2016)

• Fabrication 28 nm by GlobalFoundries
• Socket FP4[99] / FT4
• 2 "Excavator+" x86 CPU cores
• L1 Cache: 32 KB Data per core and 96 KB Instructions per module
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, XOP, FMA3, FMA4, F16C, ABM, BMI1, BMI2, TBM, RDRAND, Turbo Core
• GPU based on Graphics Core Next 3rd Generation with VP9 decoding

Model number	Released	Fab	CPU						GPU				Memory support	TDP	Part number
			Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 2]
						L1	L2	L3
E2-9000e	November 2016	28nm	2 (2) [1]	1.5 GHz	2.0 GHz	96 KB inst. per module 32 KB data per core	1 MB	N/A	R2	128:8:4 2 CU	600 MHz	153.6	DDR4-1866	6 W	EM900EANN23AC
E2-9000	June 2016			1.8 GHz	2.2 GHz									10 W	EM9000AKN23AC
E2-9010				2.0 GHz	2.2 GHz									10–15 W	EM9010AVY23AC
A4-9120	Q2 2017			2.2 GHz	2.5 GHz				R3		655 MHz	167.6	DDR4-2133	10–15 W	AM9120AYN23AC
A4-9125	Q2 2018			2.3 GHz	2.6 GHz						686 MHz	175.6			AM9125AYN23AC
A4-9120C	January 6, 2019			1.6 GHz	2.4 GHz				R4	192:12:8 3 CU	600 MHz	230.4	DDR4-1866	6 W	AM912CANN23AC
A6-9200e	November 2016			1.8 GHz	2.7GHz								DDR4-2133		AM920EANN23AC
A6-9200				2.0 GHz	2.8 GHz									10 W	AM9200AKN23AC
A6-9210	June 2016			2.4 GHz	2.8 GHz									10–15 W	AM9210AVY23AC
A6-9220	Q2 2017			2.5 GHz	2.9 GHz						655 MHz	251.5		10–15 W	AM9220AYN23AC
A6-9225	Q2 2018			2.6 GHz	3.0 GHz						686 MHz	263.4			AM9225AYN23AC
A6-9220C	January 6, 2019			1.8 GHz	2.7 GHz				R5		720 MHz	276.4	DDR4-1866	6 W	AM922CANN23AC
A9-9400	November 2016			2.4 GHz	3.2 GHz						800 MHz	307.2	DDR4-2133	10 W	AM9400AKN23AC
A9-9410	June 2016			2.9 GHz	3.5 GHz									10–25 W	AM9410AFY23AC
A9-9420	Q2 2017			3.0 GHz	3.6 GHz						847 MHz	325.2			AM9420AYN23AC
A9-9425	Q2 2018			3.1 GHz	3.7 GHz						900 MHz	345.6			AM9425AYN23AC
A9-9430[168]	Q2 2017			3.2 GHz	3.5 GHz						847 MHz	325.2	DDR4-2400	25 W	AD9430AJN23AC
Pro A4-4350B	Q1 2018			2.5 GHz	2.9 GHz						655 MHz	251.5	DDR4-2133	15 W
Pro A4-5350B	Q1 2020			3.0 GHz	3.6 GHz						847 MHz	325.2
Pro A6-7350B	Q1 2018
Pro A6-8350B	Q1 2020			3.1 GHz	3.7 GHz						900 MHz	345.6

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Dalí", "Pollock" (2020)

• Fabrication 14 nm by GlobalFoundries
• Socket FP5 / FT5
• Two Zen CPU cores
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, FMA3, F16C, ABM, BMI1, BMI2, RDRAND, Turbo Core

Model	Release date	Fab	CPU						GPU				Socket	PCIe lanes	Memory support	TDP	Part number
			Cores (threads)	Clock rate (GHz)		Cache			Model	Config[lower-alpha 1]	Clock	Processing power (GFLOPS)[lower-alpha 2]
				Base	Boost	L1	L2	L3
AMD 3015e[169]	July 6, 2020	14 nm	2 (4)	1.2	2.3	64 KiB inst. 32 KiB data per core	512 KiB per core	4 MiB	AMD Radeon^(TM) Graphics (Vega)	3 CU	600 MHz		FT5	12 (8+4)	DDR4-1600 single-channel	6 W	AM3015BRP2OFJ
AMD 3020e[170]	January 6, 2020		2 (2)	1.2	2.6					192:12:4 3 CU	1000 MHz	384	FP5		DDR4-2400 dual-channel		YM3020C7T2OFG
Athlon Silver 3050e[171]			2 (4)	1.4	2.8												YM3050C7T2OFG
Athlon Silver 3050U[172]			2 (2)	2.3	3.2					128:8:4 2 CU	1100 MHz	281.6				12-25 W	YM3050C4T2OFG
Athlon Silver 3050C[173]	September 22, 2020																YM305CC4T2OFG
Athlon Gold 3150U[174]	January 6, 2020		2 (4)	2.6	3.3					192:12:4 3 CU	1000 MHz	384					YM3150C4T2OFG
Athlon Gold 3150C[175]	September 22, 2020																YM315CC4T2OFG
Ryzen 3 3250U[176]	January 6, 2020			2.6	3.5						1200 MHz	460.8					YM3250C4T2OFG
Ryzen 3 3250C[177]	September 22, 2020																YM325CC4T2OFG

1. Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)
2. Single precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

Embedded APUs

Brazos: "Ontario" and "Zacate" (2011)

• Fabrication 40 nm
• Socket FT1 (BGA-413)
• CPU microarchitecture: Bobcat[178]
• L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, ABM, NX bit, AMD64, AMD-V
• GPU microarchitecture: TeraScale 2 (VLIW5) "Evergreen"
• Memory support: single-channel, support up to two DIMMs of DDR3-1333 or DDR3L-1066
• 5 GT/s UMI

Model	Released	Fab	Stepping	CPU					GPU				Memory support	TDP	Part number
				Cores (threads)/[FPUs]	Clock	Cache[lower-alpha 1]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 2]
						L1	L2	L3
G-Series T24L	Mar 1, 2011 May 23, 2011	40nm	B0	1 (1) [1]	800 MHz 1.0 GHz	32 KB inst. 32 KB data per core	512 KB	N/A	N/A				DDR3-1066	5 W	GET24LFPB12GTE GET24LFQB12GVE
G-Series T30L	Mar 1, 2011 May 23, 2011				1.4 GHz									18 W	GET30LGBB12GTE GET30LGBB12GVE
G-Series T48L	Mar 1, 2011 May 23, 2011			2 (2) [1]			2 × 512 KB								GET48LGBB22GTE GET48LGBB22GVE
G-Series T16R	Jun 25, 2012		B0	1 (1) [1]	615 MHz		512 KB		HD 6250	80:8:4	276 MHz	44.1	DDR3L-1066	4.5 W	GET16RFWB12GVE
G-Series T40R	May 23, 2011				1.0 GHz						280 MHz	44.8	DDR3-1066	5.5 W	GET40RFQB12GVE
G-Series T40E				2 (2) [1]			2 × 512 KB							6.4 W	GET40EFQB22GVE
G-Series T40N	Jan 19, 2011 May 23, 2011								HD 6250 HD 6290					9 W	GET40NFPB22GTE GET40NFPB22GVE
G-Series T40R	May 23, 2011			1 (1) [1]			512 KB		HD 6250					5.5 W	GET40RFSB12GVE
G-Series T44R	Jan 19, 2011 May 23, 2011				1.2 GHz									9 W	GET44RFPB12GTE GET44RFPB12GVE
G-Series T48E	Jun 25, 2012			2 (2) [1]	1.4GHz		2 × 512 KB							18 W	GET48EGBB22GVE
G-Series T48N	Jan 19, 2011 May 23, 2011								HD 6310		500 MHz 520 MHz	80 83.2			GET48NGBB22GTE GET48NGBB22GVE
G-Series T52R	Jan 19, 2011 May 23, 2011			1 (1) [1]	1.5 GHz		512 KB				500 MHz	80	DDR3-1066 DDR3-1333		GET52RGBB12GTE GET52RGBB12GVE
G-Series T56E	Jun 25, 2012			2 (2) [1]	1.65 GHz		2 × 512 KB		HD 6250		275 MHz	44	DDR3-1333		GET56EGBB22GVE
G-Series T56N	Jan 19, 2011 May 23, 2011				1.6 GHz 1.65 GHz				HD 6310 HD 6320		500 MHz	80	DDR3-1066 DDR3-1333		GET56NGBB22GTE GET56NGBB22GVE

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Kabini" (2013, SoC)

• Fabrication 28 nm
• Socket FT3 (769-BGA)[179]
• CPU microarchitecture: Jaguar
• L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AVX, F16C, CLMUL, AES, MOVBE (Move Big-Endian instruction), XSAVE/XSAVEOPT, ABM, BMI1, AMD-V support. No support for FMA (Fused Multiply-Accumulate). Trusted Platform Module (TPM) 1.2 support
• GPU microarchitecture: Graphics Core Next (GCN) with Unified Video Decoder 3 (H.264, VC-1, MPEG2, etc.)
• Single channel DDR3-1600, 1.25 and 1.35 V voltage level support, support for ECC memory
• Integrates Controller Hub functional block, HD audio, 2 SATA channels, USB 2.0 and USB 3.0 (except GX-210JA)

Model	Released	Fab	Stepping	CPU					GPU				Memory support	TDP	Junction temperature (°C)	Part number
				Cores (threads) [FPUs]	Clock	Cache[lower-alpha 1]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 2]
						L1	L2	L3
GX-210UA	Un­known	28nm	B0	2 (2) [1]	1.0 GHz	32 KB inst. 32 KB data per core	1MB	N/A	N/A				DDR3-1333	8.5 W	0-90	GE210UIGJ23HM
GX-210JA	Jul 30, 2013								HD 8180E	128:8:4 2 CU	225 MHz	57.6	DDR3-1066	6 W		GE210JIHJ23HM
GX-209HA	Un­known								HD 8400E		600 MHz	153.6		9 W	-40-105	GE209HISJ23HM
GX-210HA	Jun 1, 2013								HD 8210E		300 MHz	76.8	DDR3-1333		0-90	GE210HICJ23HM
GX-217GA					1.65 GHz				HD 8280E		450 MHz	115.2	DDR3-1600	15 W		GE217GIBJ23HM
GX-411GA	Un­known			4 (4) [2]	1.1 GHz		2 MB		HD 8210E		300 MHz	76.8	DDR3-1066		-40-105	GE411GIRJ44HM
GX-415GA	Jun 1, 2013				1.5 GHz				HD 8330E		500 MHz	128	DDR3-1600		0-90	GE415GIBJ44HM
GX-416RA					1.6 GHz				N/A							GE416RIBJ44HM
GX-420CA					2.0 GHz				HD 8400E	128:8:4 2 CU	600 MHz	153.6		25 W		GE420CIAJ44HM

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Steppe Eagle" (2014, SoC)

• Fabrication 28 nm
• Socket FT3b (769-BGA)
• CPU microarchitecture: Puma
• L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AVX, F16C, CLMUL, AES, MOVBE (Move Big-Endian instruction), XSAVE/XSAVEOPT, ABM, BMI1, AMD-V support

Model	Released	Fab	Stepping	CPU						GPU					Memory support	TDP	Junction temperature (°C)	Part number
				Cores (threads) [FPUs]	Clock	Turbo	Cache[lower-alpha 1]			Model	Config	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
GX-210JC	June 4, 2014	28nm	ML-A1	2 (2) [1]	1.0 GHz	N/A	32 KB inst. 32 KB data per core	1 MB	N/A	R1E	128:8:4 2 CU	267 MHz	N/A	68.3	DDR3-1600	6 W	-40-105	GE210JIZJ23JB
GX-212JC					1.2 GHz					R2E		300 MHz		76.8	DDR3-1333		0-90	GE212JIYJ23JB
GX-216HC					1.6 GHz					R4E					DDR3-1066	10 W	-40-105	GE216HHBJ23JB
GX-222GC					2.2 GHz					R5E		655 MHz		167.6	DDR3-1600	15 W	0-90	GE222GITJ23JB
GX-412HC				4 (4) [2]	1.2 GHz			2 MB		R3E		300 MHz		76.8	DDR3-1333	7 W		GE412HIYJ44JB
GX-424CC					2.4 GHz					R5E		497 MHz		127.2	DDR3-1866	25 W		GE424CIXJ44JB

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Crowned Eagle" (2014, SoC)

• Fabrication 28 nm
• Socket FT3b (769-BGA)
• CPU microarchitecture: Puma
• L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AVX, F16C, CLMUL, AES, MOVBE (Move Big-Endian instruction), XSAVE/XSAVEOPT, ABM, BMI1, AMD-V support
• no GPU

Model	Released	Fab	Stepping	CPU					GPU	Memory support	TDP	Junction temperature (°C)	Part number
				Cores (threads) [FPUs]	Clock	Cache[lower-alpha 1]
						L1	L2	L3
GX-224PC	June 4, 2014	28nm		2 (2) [1]	2.4 GHz	32 KB inst. 32 KB data per core	1 MB	N/A	N/A	DDR3-1866	25 W	0-90	GE224PIXJ23JB
GX-410VC				4 (4) [2]	1.0 GHz		2 MB			DDR3-1066	7 W	-40-105	GE410VIZJ44JB
GX-412TC					1.2 GHz					DDR3-1600	6W	0-90	GE412TIYJ44JB
GX-420MC					2.0GHz						17.5 W		GE420MIXJ44JB

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]

LX-Family (2016, SoC)

• Fabrication 28 nm
• Socket FT3b (769-BGA)
• 2 Puma x86 cores with 1MB shared L2 cache
• L1 Cache: 32 KB Data per core and 32 KB Instructions per core
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AVX, F16C, CLMUL, AES, MOVBE (Move Big-Endian instruction), XSAVE/XSAVEOPT, ABM, BMI1, AMD-V support
• GPU microarchitecture: Graphics Core Next (GCN) (1CU) with support for DirectX 11.2
• Single channel 64-bit DDR3 memory with ECC
• Integrated Controller Hub supports: PCIe® 2.0 4×1, 2 USB3 + 4 USB2 ports, 2 SATA 2.0/3.0 ports

Model	Released	Fab	Stepping	CPU					GPU				Memory support	TDP	Part number
				Cores (threads) [FPUs]	Clock	Cache[lower-alpha 1]			Model	Config	Clock	Processing power (GFLOPS)[lower-alpha 2]
						L1	L2	L3
GX-208JL	Feb 23, 2016	28nm	ML-A1	2	800 MHz	32 KB inst. 32 KB data per core	1 MB	N/A	R1E	64:4:1 1 CU	267 MHz	34.1	DDR3-1333	6 W	GE208JIVJ23JB
GX-210HL	2017				1.0 GHz								DDR3-1066	7 W	GE208HIZJ23JB
GX-210JL	Feb 23, 2016												DDR3-1333	6 W	GE210JIVJ23JB
GX-210KL	2017													4.5 W	GE210KIVJ23JB
GX-215GL	Feb 23, 2016				1.5 GHz						497 MHz	63.6	DDR3-1600	15 W	GE215GITJ23JB
GX-218GL					1.8 GHz										GE218GITJ23JB

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

I-Family: "Brown Falcon" (2016, SoC)

• Fabrication 28 nm
• Socket FP4[180]
• 2 or 4 Excavator x86 cores with 1MB shared L2 cache
• L1 Cache: 32 KB Data per core and 96 KB Instructions per module
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, XOP, FMA3, FMA4, F16C, ABM, BMI1, BMI2, TBM, RDRAND
• GPU microarchitecture: Graphics Core Next (GCN) (up to 4 CUs) with support for DirectX 12
• Dual channel 64-bit DDR4 or DDR3 memory with ECC
• 4K × 2K H.265 decode capability and multi format encode and decode
• Integrated Controller Hub supports: PCIe 3.0 1×4, PCIe 2/3 4×1, 2 USB3 + 2 USB2 ports, 2 SATA 2.0/3.0 ports

Model	Released	Fab	Stepping	CPU						GPU					Memory support	TDP	Part number
				[Modules/FPUs] Cores/threads	Clock	Turbo	Cache[lower-alpha 1]			Model	Config^2	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
GX-217GI	Feb 23, 2016	28nm		[1] 2	1.7 GHz	2.0 GHz	96 KB inst. per module 32 KB data per core	1 MB	N/A	R6E	256:16:4 4 CU	758 MHz	N/A	388	DDR3/DDR4-1600	015 W	GE217GAAY23KA
GX-420GI[181][182]	2016			[2] 4	2.0 GHz	2.2 GHz		2 MB		R6E R7E	256:16:4 4 CU 384:24:4 6 CU	758 MHz 626 MHz	N/A	388 480.7	DDR4-1866	016.1 W	GE420GAAY43KA

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

J-Family: "Prairie Falcon" (2016, SoC)

• Fabrication 28 nm
• Socket FP4[183]
• 2 "Excavator+" x86 cores with 1MB shared L2 cache
• L1 Cache: 32 KB Data per core and 96 KB Instructions per module
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, XOP, FMA3, FMA4, F16C, ABM, BMI1, BMI2, TBM, RDRAND
• GPU microarchitecture: Radeon R5E Graphics Core Next (GCN) (up to 3 CUs) with support for DirectX 12
• Single channel 64-bit DDR4 or DDR3 memory
• 4K × 2K H.265 decode capability with 10-bit compatibility and multi format encode and decode
• Integrated Controller Hub supports: PCIe 3.0 1×4, PCIe 2/3 4×1, 2 USB3 + 2 USB2 ports, 2 SATA 2.0/3.0 ports

Model	Released	Fab	Stepping	CPU						GPU					Memory support	TDP	Junction temperature (°C)	Part number
				[Modules/FPUs] Cores/threads	Clock	Turbo	Cache[lower-alpha 1]			Model	Config^2	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
GX-212JJ	2018	28nm		[1] 2	1.2 GHz	1.6 GHz	96 KB inst. per module 32 KB data per core	1 MB	N/A	R1E	64:4:1 1 CU	600 MHz	N/A	76.8	DDR3-1333 DDR4-1600	6–10 W	0-90	GE212JAWY23AC
GX-215JJ	2017				1.5 GHz	2.0 GHz				R2E	128:8:2 2 CU			153.6	DDR3-1600 DDR4-1866			GE215JAWY23AC
GX-220IJ	2018				2.0 GHz	2.2 GHz										10–15 W		GE220IAVY23AC
GX-224IJ	2017				2.4 GHz	2.8 GHz				R4E	192:12:3 3 CU			230.4	DDR3-1866 DDR4-2133			GE224IAVY23AC

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

Comal: "Trinity" (2012)

• Fabrication 32 nm
• Socket FP2 (BGA-827), FS1r2
• CPU microarchitecture: Piledriver
• L1 Cache: 16 KB Data per core and 64 KB Instructions per module
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AMD64, AMD-V, AES, CLMUL, AVX 1.1, XOP, FMA3, FMA4, F16C,[29] ABM, BMI1, TBM
• GPU microarchitecture: TeraScale 3 (VLIW4) "Northern Islands"
• Memory support: dual-channel 1.35 V DDR3L-1600 memory, in addition to regular 1.5 V DDR3
• 2.5 GT/s UMI
• Die size: 246 mm²; Transistors: 1.303 billion
• OpenCL 1.1 and OpenGL 4.2 support

Model	Released	Fab	Stepping	CPU						GPU					Memory support	TDP	Part number
				[Modules/FPUs] Cores/threads	Clock	Turbo	Cache[lower-alpha 1]			Model	Config^2	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
R-252F	May 21, 2012	32nm	B0	[1] 2	1.9 GHz	2.4 GHz	64 KB inst. per module 16 KB data per core	1 MB	N/A	HD 7400G	192:12:4 3 CU	333 MHz	417 MHz	127.8	DDR3-1333	17 W	RE252FSHE23HJE
R-260H					2.1 GHz	2.6 GHz		2? MB		HD 7500G	256:16:8 4 CU	327 MHz	424 MHz	167.4			RE260HSHE24HJE
R-268D					2.5 GHz	3.0 GHz		1 MB		HD 7420G	192:12:4 3 CU	470 MHz	640 MHz	180.4	DDR3-1600	35 W	RE268DDEC23HJE
R-272F					2.7 GHz	3.2 GHz				HD 7520G		497 MHz	686 MHz	190.8			RE272FDEC23HJE
R-452L				[2] 4	1.6 GHz	2.4 GHz		2 × 2 MB		HD 7600G	256:16:8 4 CU	327 MHz	424 MHz	167.4		19 W	RE452LSHE44HJE
R-460H					1.9 GHz	2.8 GHz				HD 7640G		497 MHz	655 MHz	254.4		35 W	RE460HDEC44HJE
R-460L					2.0 GHz					HD 7620G	384:24:8 6 CU	360 MHz	497 MHz	276.4	DDR3-1333	25 W	RE460LSIE44HJE
R-464L					2.3 GHz	3.2 GHz				HD 7660G		497 MHz	686 MHz	381.6	DDR3-1600	35 W	RE464LDEC44HJE

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Bald Eagle" (2014)

• Fabrication 28 nm
• Socket FP3
• Up to 4 Steamroller x86 cores[184]
• L1 Cache: 16 KB Data per core and 96 KB Instructions per module
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AMD64, AMD-V, AES, CLMUL, AVX 1.1, XOP, FMA3, FMA4, F16C,[29] ABM, BMI1, TBM
• GPU microarchitecture: Graphics Core Next (GCN) (up to 8 CUs) with support for DirectX 11.1 and OpenGL 4.2
• Dual channel DDR3 memory with ECC
• Unified Video Decode (UVD) 4.2 and Video Coding Engine (VCE) 2.0

Model	Released	Fab	Stepping	CPU						GPU					Memory support	TDP	Junction temperature (°C)	Part number
				[Modules/FPUs] Cores/threads	Clock	Turbo	Cache[lower-alpha 1]			Model	Config^2	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
RX-219NB	May 20, 2014	28nm		[1] 2	2.2 GHz	3.0 GHz	96 KB inst. per module 16 KB data per core	1 MB	N/A	N/A					DDR3-1600	15-17 W	0-100	RE219NECH23JA
RX-225FB										R4	192:12:4 3 CU	464 MHz	533 MHz	178.1				RE225FECH23JA
RX-425BB				[2] 4	2.5 GHz	3.4 GHz		4 MB		R6	384:24:8 6 CU	576 MHz	654 MHz	442.3	DDR3-1866	30-35 W		RE425BDGH44JA
RX-427BB					2.7 GHz	3.6 GHz				R7	512:32:8 8 CU	600 MHz	686 MHz	614.4	DDR3-2133	30-35 W		RE427BDGH44JA
RX-427NB										N/A								RE427NDGH44JA

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

"Merlin Falcon" (2015, SoC)

• Fabrication 28 nm
• Socket FP4
• Up to 4 Excavator x86 cores[185]
• L1 Cache: 32 KB Data per core and 96 KB Instructions per module
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, XOP, FMA3, FMA4, F16C, ABM, BMI1, BMI2, TBM, RDRAND
• GPU microarchitecture: Graphics Core Next (GCN) (up to 8 CUs) with support for DirectX 12
• Dual channel 64-bit DDR4 or DDR3 memory with ECC
• Unified Video Decode (UVD) 6 (4K H.265 and H.264 decode) and Video Coding Engine (VCE) 3.1 (4K H.264 encode)
• Dedicated AMD Secure Processor supports secure boot with AMD Hardware Validated Boot (HVB)
• Integrated FCH featuring PCIe 3.0 USB3.0, SATA3, SD, GPIO, SPI, I2S, I2C, UART

Model	Released	Fab	Stepping	CPU						GPU					Memory support	TDP	Junction temperature (°C)	Part number
				[Modules/FPUs] Cores/threads	Clock	Turbo	Cache[lower-alpha 1]			Model	Config^2	Clock	Turbo	Processing power (GFLOPS)[lower-alpha 2]
							L1	L2	L3
RX-216TD	October 21, 2015	28nm		[1] 2	1.6 GHz	3.0 GHz	96 KB inst. per module 32 KB data per core	1 MB	N/A	N/A					DDR3/DDR4-1600	12-15 W	0-90	RE216TAAY23KA
RX-216GD										R5	256:?:? 4 CU	800 MHz	N/A	409.6				RE216GAAY23KA
RX-416GD				[2] 4	1.6 GHz	2.4 GHz		2 MB		R6	384:?:? 6 CU	720 MHz		552.9		15 W	-40-105	RE416GATY43KA
RX-418GD	October 21, 2015				1.8 GHz	3.2 GHz					384:?:? 6 CU	800 MHz		614.4	DDR3-2133 DDR4-2400	12-35 W	0-90	RE418GAAY43KA
RX-421BD					2.1 GHz	3.4 GHz				R7	512:?:? 8 CU			819.2				RE421BAAY43KA
RX-421ND										N/A								RE421NAAY43KA

1. AMD in its technical documentation uses KB, which it defines as Kilobyte and as equal to 1024 bytes, and MB, which it defines as Megabyte and as equal to 1024 KB.[27]
2. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

V1000-Family: "Great Horned Owl" (2018, SoC)

• Fabrication 14 nm by GlobalFoundries
• Up to 4 Zen cores
• Socket FP5
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, FMA3, F16C, ABM, BMI1, BMI2, RDRAND, Turbo Core
• Dual channel DDR4 memory with ECC
• Fifth generation GCN based GPU

Model	Release date	Process	CPU						GPU				Memory support	Ethernet	TDP (W)	Junction temperature (°C)
			Cores (threads)	Clock rate (GHz)		Cache[lower-roman 1]			Model	Config[lower-roman 2]	Clock	Processing power (GFLOPS)[lower-roman 3]
				Base	Boost	L1	L2	L3
V1500B[186]	December 2018	GloFo 14LP	4 (8)	2.2	N/A	64 KB inst. 32 KB data per core	512 KB per core	4 MB	N/A				DDR4-2400 dual-channel	2× 10GbE	12–25	0–105
V1780B[186]				3.35	3.6								DDR4-3200 dual-channel		35–54
V1202B[186]	February 2018		2 (4)	2.3	3.2				RX Vega 3	192:12:16 3 CU	1000 MHz	384	DDR4-2400 dual-channel		12–25
V1404I[186]	December 2018		4 (8)	2.0	3.6				RX Vega 8	512:32:16 8 CU	1100 MHz	1126.4				−40 – 105
V1605B[186]	February 2018															0–105
V1756B[186]				3.25							1300 MHz	1331.2	DDR4-3200 dual-channel		35–54
V1807B[186]				3.35	3.8				RX Vega 11	704:44:16 11 CU		1830.4

1. AMD defines 1 kilobyte (KB) as 1024 bytes, and 1 megabyte (MB) as 1024 kilobytes.
2. Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)
3. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

R1000-Family: "Banded Kestrel" (2019, SoC)

• Fabrication 14 nm by GlobalFoundries
• Up to 2 Zen cores
• Socket FP5
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, SSE4a, AMD64, AMD-V, AES, CLMUL, AVX, AVX 1.1, AVX2, FMA3, F16C, ABM, BMI1, BMI2, RDRAND, Turbo Core
• Dual channel DDR4 memory with ECC
• Fifth generation GCN based GPU

Model	Release date	Process	CPU							GPU				Memory support	TDP
			Cores (threads)	Clock rate (GHz)			Cache[lower-roman 1]			Model	Config[lower-roman 2]	Clock	Processing power (GFLOPS)[lower-roman 3]
				Base	Boost	XFR	L1	L2	L3
R1102G [188]	February 25, 2020	GloFo 14LP	2 (2)	1.2	2.6	Un­known	64KB inst. 32 KB data per core	512KB per core	4MB	RX Vega 3	192:12:4 3 CU	1000 MHz	384	DDR4-2400 single-channel	6 W
R1305G[188]			2 (4)	1.5	2.8	Un­known								DDR4-2400 dual-channel	8-10 W
R1505G[188]	April 16, 2019			2.4	3.3	Un­known									12–25 W
R1606G[188]				2.6	3.5	Un­known						1200 MHz	460.8

1. AMD defines 1 kilobyte (KB) as 1024 bytes, and 1 megabyte (MB) as 1024 kilobytes.[187]
2. Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)
3. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

V2000-Family: "Grey Hawk" (2020, SoC)

• Fabrication 7 nm by TSMC
• Up to 8 Zen 2 cores
• Fifth generation GCN based GPU

Model	Release date	Process	CPU						GPU				Memory support	TDP (W)	Junction temperature (°C)
			Cores (threads)	Clock rate (GHz)		Cache[lower-roman 1]			Model	Config[lower-roman 2]	Clock	Processing power (GFLOPS)[lower-roman 3]
				Base	Boost	L1	L2	L3
V2516[189]	November 10, 2020	TSMC 7FF	6 (12)	2.1	3.95	64 KB inst. 32 KB data per core	3 MB shared	8 MB	?	6 CU	1500 MHz	?	DDR4-3200 dual-channel	10–25	0–105
V2546[189]				3.0	3.95									35–54
V2718[189]			8 (16)	1.7	4.15		4 MB shared			7 CU	1600 MHz			10–25
V2748[189]				2.9	4.25									35–54

1. AMD defines 1 kilobyte (KB) as 1024 bytes, and 1 megabyte (MB) as 1024 kilobytes.
2. Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)
3. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

Custom APUs

As of May 1, 2013, AMD opened the doors of their "semi-custom" business unit.[190] Since these chips are custom-made for specific customer needs, they vary widely from both consumer-grade APUs and even the other custom-built ones. Some notable examples of semi-custom chips that have come from this sector include the chips from the PlayStation 4 and Xbox One.[191] So far the size of the integrated GPU in these semi-custom APUs exceed by far the GPU size in the consumer-grade APUs.

Chip (device)	Release date	Fab	Die area (mm2)	CPU				GPU							Memory			Storage	API support	Special features
				Archi- tecture	Cores	Clock (GHz)	L2 cache	Archi- tecture	Core config[lower-alpha 1]	Clock (MHz)	GFLOPS [lower-alpha 2]	Pixel fillrate (GP/s) [lower-alpha 3]	Texture fillrate (GT/s) [lower-alpha 4]	Other	Size	Bus type & width	Band- width (GB/s)			Audio	Other
Liverpool (PS4)	Nov 2013	28 nm	348	Jaguar	8 cores	1.6	2× 2 MiB	GCN 2	1152:72:32 18 CU	800	1843	25.6	57.6	8 ACEs	8 GiB	GDDR5 256-bit	176	3DBD/DVD 1× 2.5" SATA hard drive Easily replaceable hard drive USB 3.0	OpenGL 4.2, GNM, GNMX and PSSL	Dolby Atmos (BD) S/PDIF	PS VR PS4 additional modules HDR10 (except discs)[lower-alpha 5] CEC Optional IR sensor
Durango (Xbox One)	Nov 2013		363			1.75			768:48:16 12 CU	853	1310	13.6	40.9	2 ACEs	32 MiB	ESRAM[lower-alpha 6]	204	3DBD/DVD/CD 1× 2.5" SATA hard drive USB 3.0	Direct3D 11.2 and 12	Fully Dolby Atmos, DTS:X, and Windows Sonic S/PDIF	Xbox One additional modules FreeSync (1) HDMI 1.4 through IR sensor and IR out port Kensington lock
															8 GiB	DDR3 256-bit	68
Edmonton (Xbox One S) [192]	Jun 2016	16 nm	240							914	1404	14.6	43.9	2 ACEs	32 MiB	ESRAM	219	4KBD/3DBD/DVD/CD[lower-alpha 7] 1× 2.5" SATA hard drive USB 3.0		Fully Dolby Atmos, DTS:X, and Windows Sonic S/PDIF	Xbox One S additional modules Fully HDR10 Dolby Vision (streaming) FreeSync (1&2) HDMI 1.4 through IR sensor and IR out port Kensington lock
															8 GiB	DDR3 256-bit	68
(PS4 Slim)	Sep 2016		208			1.6			1152:72:32 18 CU	800	1843	25.6	57.6	8 ACEs	8 GiB	GDDR5 256-bit	176	3DBD/DVD 1× 2.5" SATA hard drive Easily replaceable hard drive USB 3.0	OpenGL 4.2, GNM, GNMX and PSSL	Dolby Atmos (BD)	PS VR PS4 Slim additional modules HDR10 (except discs) CEC Optional IR sensor
Neo (PS4 Pro) [193][194][195]	Nov 2016		325			2.13		GCN 4 Polaris [196]	2304:144:32 36 CU	911	4198	58.3	131.2	4 ACEs and 2 HWS Double-rate FP16[lower-alpha 8] checkerboard rendering	8 GiB [197]	GDDR5 256-bit	218	3DBD/DVD 1× 2.5" SATA hard drive Easily replaceable hard drive USB 3.0	OpenGL 4.2 (4.5), GNM, GNMX and PSSL	Dolby Atmos (BD) S/PDIF	PS VR PS4 Pro additional modules HDR10 (except discs) Up to 4K@60 Hz CEC Optional IR sensor
															1 GiB	DDR3[lower-alpha 9]	?
Scorpio (Xbox One X) [198][199][200]	Nov 2017		359	Customized Jaguar		2.3			2560:160:32 40 CU	1172	6001	37.5	187.5	4 ACEs and 2 HWS	12 GiB	GDDR5 384-bit	326	4KBD/3DBD/DVD/CD 1× 2.5" SATA hard drive USB 3.0	Direct3D 11.2 and 12	Fully Dolby Atmos, DTS:X, and Windows Sonic S/PDIF	Xbox One X additional modules Fully HDR10 Dolby Vision (streaming) FreeSync (1&2) Up to 4K@60 Hz HDMI 1.4b through IR sensor and IR out port
Fenghuang (Subor Z+) [201][202][203]	cancelled [204]	14 nm [205]	397	Zen	4 cores 8 threads	3.0		GCN 5 Vega	1536:96:32 24 CU	1300	3994	41.6	124.8	Double-rate FP16	8 GiB	GDDR5 256-bit	154	1× 2.5" SATA SSD 1× 2.5" SATA hard drive Easily replaceable drives USB 3.0	Vulkan 1.1, Direct3D 12.1	S/PDIF	Subor Z Plus additional modules Windows 10 Enterprise LTSC
Oberon (PS5) [206]	Nov 2020	7 nm	308	Zen 2	8 cores 16 threads	3.5 (variable)		RDNA 2	2304:144:64 36 CU	2233 (variable)	10290 (variable)	142.9	321.6	Double-rate FP16 Real-time ray tracing Primitive shaders Custom 3D audio blocks	16 GiB	GDDR6 256-bit	448	4KBD Custom 5.5 GB/s PCIe 4.0 x4 NVMe SSD PCIe 4.0 M.2 slot Easily replaceable M.2 SSD USB (except PS5 games)	Vulkan 1.2	PS5 TEMPEST 3D AudioTech	PS VR Dedicated DMA controller and I/O coprocessors Custom coherency engines and cache scrubbers Custom decompression block HDR Up to 4K@120 Hz Up to 8K@30 Hz
Anaconda (Xbox Series X)	Nov 2020		360			3.6 (3.8 w/o SMT)			3328:208:64 52 CU	1825	12147	116.8	379.6	Double-rate FP16 Real-time ray tracing Mesh shaders Variable rate shading ANN acceleration	10 GiB	GDDR6 320-bit	560	4KBD Custom 2.4 GB/s NVMe SSD Custom expansion card USB 3.1 (except XSX games)	DirectX 12 Ultimate	Custom spatial audio block MS Project Acoustics Fully Dolby Atmos, DTS:X, and Windows Sonic	Custom decompression block HDR VRR Up to 4K@120 Hz Up to 8K@30 Hz CEC
															6 GiB	GDDR6 192-bit[lower-alpha 10]	336
Lockhart (Xbox Series S)			197			3.4 (3.6 w/o SMT)			1280:80:32 20 CU	1565	4006	50.1	125.2		8 GiB	GDDR6 128-bit	224
															2 GiB	GDDR6 32-bit	56

1. Unified Shaders : Texture Mapping Units : Render Output Units
2. Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
3. Pixel fillrate is calculated as the number of ROPs multiplied by the base (or boost) core clock speed.
4. Texture fillrate is calculated as the number of TMUs multiplied by the base (or boost) core clock speed.
5. UHD BD is the only video disc format supporting HDR.
6. Cache
7. "Digital" version does not have an optical drive.
8. Feature preview of Rapid Packed Math, introduced in GCN 5 Vega.
9. Swap
10. A plain 320-bit 20GiB version could be made by just replacing four 1 GiB GDDR6 chips by 2 GiB ones.

See also

• AMD Accelerated Processing Unit
• List of AMD chipsets
• List of AMD FX microprocessors
• List of AMD graphics processing units
• Ryzen

Notes

Note 1: The clock multiplier applies to the 200 MHz base clock. (AMD default clock base is 200 MHz)
Note 2: Unified shader processors (USPs): Texture mapping units (TMUs): Render output units (ROPs). 1 CU (Compute Unit) = 64 USPs: 4 TMUs : 1 ROPs
Note 3: Models enabled by Turbo Core technology, up to 10% clock speed increase is planned. With CPU boost, only one core of a dual-core model has boost enabled.
Note 4: K models feature an unlocked multiplier and overclockable GPU.
Note 5: One AMD module consists of two integer cores and two FPUs, which can be combined into one wide FPU for executing certain instructions, such as FMA. The two cores share certain resources, but are two separate units.

References

1. "AMD Announces the 7th Generation APU: Excavator mk2 in Bristol Ridge and Stoney Ridge for Notebooks". 31 May 2016. Retrieved 3 January 2020.
2. "AMD Mobile "Carrizo" Family of APUs Designed to Deliver Significant Leap in Performance, Energy Efficiency in 2015" (Press release). 20 November 2014. Retrieved 16 February 2015.
3. "The Mobile CPU Comparison Guide Rev. 13.0 Page 5 : AMD Mobile CPU Full List". TechARP.com. Retrieved 13 December 2017.
4. "AMD VEGA10 and VEGA11 GPUs spotted in OpenCL driver". VideoCardz.com. Retrieved 6 June 2017.
5. Cutress, Ian (1 February 2018). "Zen Cores and Vega: Ryzen APUs for AM4 – AMD Tech Day at CES: 2018 Roadmap Revealed, with Ryzen APUs, Zen+ on 12nm, Vega on 7nm". Anandtech. Retrieved 7 February 2018.
6. Larabel, Michael (17 November 2017). "Radeon VCN Encode Support Lands in Mesa 17.4 Git". Phoronix. Retrieved 20 November 2017.
7. Liu, Leo (2020-09-04). "Add Renoir VCN decode support". Retrieved 2020-09-11. It has same VCN2.x block as Navi1x
8. Tony Chen; Jason Greaves, "AMD's Graphics Core Next (GCN) Architecture" (PDF), AMD, retrieved 13 August 2016
9. "A technical look at AMD's Kaveri architecture". Semi Accurate. Retrieved 6 July 2014.
10. "How do I connect three or More Monitors to an AMD Radeon™ HD 5000, HD 6000, and HD 7000 Series Graphics Card?". AMD. Retrieved 8 December 2014.
11. Airlie, David (26 November 2009). "DisplayPort supported by KMS driver mainlined into Linux kernel 2.6.33". Retrieved 16 January 2016.
12. "Radeon feature matrix". freedesktop.org. Retrieved 10 January 2016.
13. Deucher, Alexander (16 September 2015). "XDC2015: AMDGPU" (PDF). Retrieved 16 January 2016.
14. Michel Dänzer (17 November 2016). "[ANNOUNCE] xf86-video-amdgpu 1.2.0". lists.x.org.
15. "Conformant Products - The Khronos Group Inc". The Khronos Group. Retrieved 2019-06-06.
16. "Conformant Products - The Khronos Group Inc". The Khronos Group. Retrieved 2019-06-06.
17. "GPU-Tech.org - Catalyst 11.10 WHQL - First official Battlefield 3 driver for Radeon cards". www.gpu-tech.org.
18. "AMD Radeon Software Crimson Edition Beta". AMD. Retrieved 2018-04-20.
19. "Mesamatrix". mesamatrix.net. Retrieved 2018-04-22.
20. "RadeonFeature". X.Org Foundation. Retrieved 2018-04-20.
21. "Graphics Core Next: The Southern Islands Architecture". Tom's Hardware. 2011-12-21. Retrieved 2013-06-26.
22. "AMD Clarifies 2013 Radeon Plans". Tom's Hardware. 2013-02-20. Retrieved 2013-06-26.
23. "Radeon VEGA Frontier Edition". AMD. 2017-05-30. Retrieved 2017-06-30.
24. "AMD launches A-Series and the first 32nm Athlon II X4 CPUs". Retrieved 2013-11-10.
25. Theo Valich (28 May 2012). "AMD Comes Clean on Transistor Numbers With FX, Fusion Processors". Retrieved 23 August 2013.
26. Anand Lal Shimpi (27 September 2012). "AMD A10-5800K & A8-5600K Review: Trinity on the Desktop, Part 1". Retrieved 23 August 2013.
27. "Processor Programming Reference (PPR) for AMD Family 17h Model 01h, Revision B1 Processors" (PDF). AMD Technical Documentation. AMD Developer Central: Advanced Micro Devices, Inc. 2017-04-15. p. 25. Retrieved 2019-11-01.
28. "Trinity Improvements Include Updated Piledriver Cores and VLIW4 GPUs". Retrieved 2013-11-10.
29. "AMD detonates Trinity: Behold Bulldozer's second coming - ExtremeTech". Retrieved 2017-10-07.
30. "AMD Trinity On The Desktop: A10, A8, And A6 Get Benchmarked!—Trinity: Coming Soon To A Desktop Near You". Retrieved 2013-11-10.
31. "AMD Trinity for Desktops. Part 1: Graphics Core". X-bit labs. 2012-09-27. Archived from the original on October 11, 2012.
32. "Review: AMD A10-5800K Dual Graphics evaluation—CPU". Retrieved 2013-11-10.
33. "The AMD A8-3850 Review: Llano on the Desktop". Retrieved 2013-11-10.
34. "Product Search Results—Bottom Line Telecommunications". Bottom Line Telecommunications Corporation. Retrieved 2013-11-10.
35. "AMD Sempron CPU". Retrieved 2015-03-02.
36. Альберт Шаповалов (10 September 2014). "Обзор и тестирование процессора AMD Athlon X2 340". Ru.gecid.com/ (in Russian). Retrieved 2016-09-12.
37. Hassan Mujtaba. "AMD A10-6800K and A10-6700 "Richland" APU Review". Wccftech. Retrieved 20 March 2020.
38. "AMD Athlon Processors". Retrieved 2015-03-02.
39. btarunr (23 March 2014). "AMD FX-670K CPU Shows Up in the Wild". TechPowerUp.
40. Anton Shilov (2013-05-30). "AMD's Next-Gen "Kaveri" APUs Will Require New Mainboards". Retrieved 2014-12-17.
41. "AMD Godavari core". www.cpu-world.com. Retrieved 2018-09-16.
42. Joel Hruska. "AMD Kaveri A10-7850K and A8-7600 review: Was it worth the wait for the first true heterogeneous chip?". ExtremeTech. Retrieved 20 March 2020.
43. Hassan Mujtaba. "AMD Kaveri APU Architecture Detailed". Retrieved 2015-03-15.
44. "A technical look at AMD's Kaveri architecture". SemiAccurate. 2014-01-15.
45. "AMD to add ARM processors to boost chip security". June 14, 2012. Retrieved September 3, 2013.
46. "AMD and ARM Fusion redefine beyond x86". Archived from the original on 2013-11-05. Retrieved 2013-11-10.
47. "Carrizo presentation, page 12 - Carrizo is the 1st ARM Trustzone capable performance APU" (PDF). Retrieved January 13, 2020.
48. "AMD A10-7850K Graphics Performance". Retrieved April 2, 2014.
49. "AMD A8-7600 Kaveri APU review - The Embedded GPU - HSA & hUMA". 2014-01-14.
50. Gennadiy Shvets (18 October 2014). "HP offers desktop PCs with AMD FX-770K Kaveri processor". OFweek. Archived from the original on 13 May 2018. Retrieved 23 March 2016.
51. "ASRock - FM2+ CPU Support List". asrock.com. Retrieved 18 October 2020.
52. 电脑维修技术网. "AMD APU A8-7500 CPU怎么样？". pc811.com. Retrieved 18 October 2020.
53. Hassan Mujtaba (26 August 2015). "AMD Details Carrizo APUs Energy Efficient Design at Hot Chips 2015 – 28nm Bulk High Density Design With 3.1 Billion Transistors, 250mm2 Die". Wccftech. Retrieved 20 March 2020.
54. "AMD quietly launches new Carrizo APU: A8-7680 processor". 26 October 2018. Retrieved 29 June 2019.
55. Cutress, Ian (28 October 2018). "Day of the Dead: AMD Releases new Carrizo FM2+ APU, the A8-7680". Retrieved 29 June 2019.
56. Cutress, Ian (23 September 2016). "AMD 7th Gen Bristol Ridge and AM4 Analysis". Anandtech.com. Retrieved 23 September 2016.
57. Sang-ho, Lee (19 September 2016). "AMD Final Heavy Equipment X Carrier ZEN Bristol Ridge A12-9800 platform change". BodNara Korea. Retrieved 12 November 2016.
58. "Processor Programming Reference (PPR) for AMD Family 17h Model 01h, Revision B1 Processors" (PDF). AMD Technical Documentation. AMD Developer Central: Advanced Micro Devices, Inc. 2017-04-15. p. 25. Retrieved 2019-11-01.
59. "AMD Athlon™ 200GE Processor with Radeon™ Vega 3 Graphics". AMD.
60. "AMD Athlon™ PRO 200GE APU". AMD.
61. "AMD Athlon™ 220GE Processor with Radeon™ Vega 3 Graphics".
62. "AMD Athlon™ 240GE Processor with Radeon™ Vega 3 Graphics". AMD.
63. "AMD Athlon™ 3000G Processor with Radeon™ Graphics". AMD.
64. "AMD Athlon™ 300GE".
65. "AMD Athlon™ Silver 3050GE".
66. "AMD Ryzen™ 3 2200GE with Radeon™ Vega 8 Graphics". AMD.
67. "AMD Ryzen™ 3 PRO 2200GE Processor with Radeon™ Vega 8 Graphics".
68. "AMD Ryzen™ 3 PRO 2200G Processor with Radeon™ Vega 8 Graphics". www.amd.com.
69. "Specs". www.amd.com. Retrieved 2019-06-10.
70. "Specs". www.amd.com. Retrieved 2019-06-10.
71. "AMD Ryzen™ 5 2400G". Retrieved 2018-01-19.
72. "AMD's 2nd-gen Ryzen is coming in April, desktop Ryzen APUs arrive February 12". TechSpot. Retrieved 2019-06-10.
73. Peter Bright - Jan 8, 2018 9:50 pm UTC (2018-01-08). "AMD's 2018 roadmap: Desktop APUs in February, second-generation Ryzen in April". Ars Technica. Retrieved 2019-06-10.
74. "Specs". www.amd.com. Retrieved 2019-06-10.
75. "AMD Athlon™ PRO 300GE".
76. "AMD Athlon™ Silver PRO 3125GE".
77. "AMD Athlon™ Gold 3150GE".
78. "AMD Athlon™ Gold PRO 3150GE".
79. "AMD Athlon™ Gold 3150G".
80. "AMD Athlon™ Gold PRO 3150G".
81. "AMD Ryzen™ 3 3200GE".
82. "AMD Ryzen™ 3 PRO 3200GE".
83. "AMD Ryzen™ 3 3200G with Radeon™ Vega 8 Graphics".
84. "AMD Ryzen™ 3 PRO 3200G".
85. "AMD Ryzen™ 5 PRO 3350GE".
86. "AMD Ryzen™ 5 PRO 3350G".
87. "AMD Ryzen™ 5 3400GE".
88. "AMD Ryzen™ 5 PRO 3400GE".
89. "AMD Ryzen™ 5 3400G".
90. "AMD Ryzen™ 5 3400G".
91. Cutress, Ian. "AMD Launches 12 Desktop Renoir Ryzen 4000G Series APUs: But You Can't Buy Them". Anandtech.
92. Balraj, Tarun. "AMD Announces Renoir for Desktop: Ryzen 4000G, PRO 4000G, and Athlon PRO 3000G". TechPowerUp.
93. Kennedy, Patrick (5 June 2017). "New HPE ProLiant MicroServer Gen10 Powered by AMD Opteron X3000 APUs". Retrieved 5 June 2017.
94. "Opteron". AMD Opteron. AMD. Retrieved 5 June 2017.
95. "AMD lists A8-4557M and A10-4657M mobile APUs". www.cpu-world.com. Retrieved 2018-09-17.
96. "AMD intros 35W Richland mobile APUs". Retrieved 2013-11-10.
97. Poeter, Damon. (2013-03-12) AMD Bakes New Interface Capabilities Into Richland APUs | News & Opinion
98. "Archived copy". Archived from the original on 2013-12-03. Retrieved 2013-11-26.CS1 maint: archived copy as title (link)
99. Cutress, Ian (1 June 2016). "AMD Announces 7th Generation APU". Anandtech.com. Retrieved 1 June 2016.
100. "AMD A10-9620P SoC - Benchmarks and Specs". Notebookcheck.net. Retrieved 20 July 2018.
101. "AMD A12-9720P SoC - Benchmarks and Specs". Notebookcheck.net. Retrieved 20 July 2018.
102. "HP Pavilion 17 - HP® Official Store". Store.hp.com. Retrieved 20 July 2018.
103. "Processor Programming Reference (PPR) for AMD Family 17h Model 01h, Revision B1 Processors" (PDF). AMD Technical Documentation. AMD Developer Central: Advanced Micro Devices, Inc. 2017-04-15. p. 25. Retrieved 2019-11-01.
104. "AMD Athlon™ PRO 200U Mobile Processor with Radeon™ Vega 3 Graphics". AMD.
105. "AMD Athlon™ 300U Mobile Processor with Radeon™ Vega 3 Graphics". AMD.
106. "AMD Ryzen™ 3 2200U". AMD.
107. "AMD Ryzen™ 3 3200U Mobile Processor with Radeon™ Vega 3 Graphics". AMD.
108. "AMD Ryzen™ 3 2300U". AMD.
109. "AMD Ryzen™ 3 PRO 2300U". AMD.
110. "AMD Ryzen™ 5 2500U". AMD.
111. "AMD Ryzen™ 5 PRO 2500U". AMD.
112. "AMD Ryzen™ 5 2600H Mobile Processor with Radeon™ Vega 8 Graphics".
113. "AMD Ryzen™ 7 2700U". AMD.
114. "AMD Ryzen™ 7 PRO 2700U". AMD.
115. "AMD Ryzen™ 7 2800H Mobile Processor with Radeon™ RX Vega 11 Graphics". AMD.
116. "AMD Ryzen™ 3 3300U Mobile Processor with Radeon™ Vega 6 Graphics". Retrieved 2019-01-06.
117. "AMD Radeon Vega 6 Mobile Specs | TechPowerUp GPU Database". Techpowerup.com.
118. "AMD Ryzen™ 3 PRO 3300U Mobile Processor with Radeon™ Vega 6 Graphics".
119. "AMD Ryzen™ 5 3450U Processor".
120. "AMD Radeon Vega 8 Specs | TechPowerUp GPU Database". Techpowerup.com.
121. "AMD Ryzen™ 5 3500U Mobile Processor with Radeon™ Vega 8 Graphics".
122. "AMD Ryzen™ 5 PRO 3500U Mobile Processor with Radeon™ Vega 8 Graphics".
123. "AMD Ryzen™ 5 3500C".
124. "AMD Ryzen™ 5 3550H Mobile Processor with Radeon™ Vega 8 Graphics". Retrieved 8 January 2018.
125. "AMD Ryzen™ 5 3580U Microsoft Surface® Edition".
126. "AMD Ryzen™ 7 3700U Mobile Processor with Radeon™ RX Vega 10 Graphics".
127. "AMD Radeon RX Vega 10 Mobile Specs | TechPowerUp GPU Database". Techpowerup.com.
128. "AMD Ryzen™ 7 PRO 3700U Mobile Processor with Radeon™ Vega 10 Graphics".
129. "AMD Ryzen™ 7 3700C".
130. "AMD Ryzen™ 7 3750H Mobile Processor with Radeon™ RX Vega 10 Graphics".
131. "AMD Ryzen™ 7 3780U Microsoft Surface® Edition".
132. Cutress, Ian (2020-01-06). "AMD Ryzen 4000 Mobile APUs: 7nm, 8-core on both 15W and 45W, Coming Q1". anandtech.com. AnandTech. Retrieved 2020-01-07.
133. Alcorn, Paul (2020-01-07). "AMD Launches Threadripper 3990X and Ryzen 4000 'Renoir' APUs". tomshardware.com. Tom's Hardware. Retrieved 2020-01-07.
134. Gartenberg, Chaim (2020-01-06). "AMD's 7nm Ryzen 4000 CPUs are here to take on Intel's 10nm Ice Lake laptop chips". theverge.com. The Verge. Retrieved 2020-01-07.
135. https://www.techpowerup.com/264801/amd-renoir-die-shot-pictured
136. "AMD Ryzen™ 3 4300U". AMD.
137. "AMD Ryzen™ 3 PRO 4450U". AMD.
138. "AMD Ryzen™ 5 4500U". AMD.
139. "AMD Ryzen™ 5 4600U". AMD.
140. "AMD Ryzen™ 5 PRO 4650U". AMD.
141. "AMD Ryzen™ 5 4600HS". AMD.
142. "AMD Ryzen™ 5 4600H". AMD.
143. "AMD Ryzen™ 7 4700U". AMD.
144. "AMD Ryzen™ 7 PRO 4750U". AMD.
145. "AMD Ryzen™ 7 4800U". AMD.
146. "AMD Ryzen™ 7 4800HS". AMD.
147. "AMD Ryzen™ 7 4800H". AMD.
148. "AMD Ryzen™ 9 4900HS". AMD.
149. "AMD Ryzen™ 9 4900H". AMD.
150. "AMD Ryzen™ 3 5300U". AMD.
151. "AMD Ryzen™ 5 5500U". AMD.
152. "AMD Ryzen™ 7 5700U". AMD.
153. "AMD Ryzen™ 3 5400U". AMD.
154. "AMD Ryzen™ 5 5600U". AMD.
155. "AMD Ryzen™ 5 5600H". AMD.
156. "AMD Ryzen™ 5 5600HS". AMD.
157. "AMD Ryzen™ 7 5800U". AMD.
158. "AMD Ryzen™ 7 5800H". AMD.
159. "AMD Ryzen™ 7 5800HS". AMD.
160. "AMD Ryzen™ 9 5900HS". AMD.
161. "AMD Ryzen™ 9 5900HX". AMD.
162. "AMD Ryzen™ 9 5980HS". AMD.
163. "AMD Ryzen™ 9 5980HX". AMD.
164. Shimpi, Anand Lal. "Previewing AMD's Brazos, Part 1: More Details on Zacate/Ontario and Fusion". Anandtech.com. Retrieved 20 July 2018.
165. "Archived copy". Archived from the original on 2015-05-27. Retrieved 2015-05-26.CS1 maint: archived copy as title (link)
166. "HP ProDesk 405 G2 Microtower-PC". Retrieved 2015-02-24.
167. Cutress, Ian. "AMD's Carrizo-L APUs Unveiled: 12-25W Quad Core Puma+". Anandtech.com. Retrieved 20 July 2018.
168. "HP Pavilion Desktops - HP® Official Store". Store.hp.com. Retrieved 20 July 2018.
169. "AMD 3015e". AMD.com.
170. "AMD 3020e". AMD.com.
171. "AMD Athlon™ Silver 3050e". AMD.com.
172. "AMD Athlon™ Silver 3050U". Retrieved 2020-01-07.
173. "AMD Athlon™ Silver 3050C".
174. "AMD Athlon™ Gold 3150U". Retrieved 2020-01-08.
175. "AMD Athlon™ Gold 3150C".
176. "AMD Ryzen™ 3 3250U". Retrieved 2020-01-08.
177. "AMD Ryzen™ 3 3250C".
178. "Welcome to AMD - Processors - Graphics and Technology - AMD". Amd.com. Retrieved 20 July 2018.
179. "Embedded Products - High Performance GPU - AMD". Amd.com. Retrieved 20 July 2018.
180. https://www.amd.com/Documents/I-Family-Product-Brief.pdf
181. https://store.hp.com/us/en/pdp/hp-t630-thin-client-p-2zv00at-aba-1?pStoreID=epp
182. http://www.cpu-world.com/CPUs/Bulldozer/AMD-G-Series%20GX-420GI.html
183. https://www.amd.com/Documents/J-Family-Product-Brief.pdf
184. https://www.amd.com/Documents/2nd_Gen_Rseries_Product_Brief.pdf
185. https://www.amd.com/Documents/merlin-falcon-product-brief.pdf
186. "Embedded Processor Specifications". AMD.
187. "Processor Programming Reference (PPR) for AMD Family 17h Model 01h, Revision B1 Processors" (PDF). Processor Programming Reference (PPR) for AMD Family 17h Model 01h, Revision B1 Processors. AMD. Retrieved 14 July 2017.
188. "Embedded Processor Specifications". AMD.
189. "Embedded Processor Specifications". AMD.
190. "AMD Establishes Semi-Custom Business Unit to Create Tailored Products with Customer-Specific IP". Archived from the original on 2013-10-01. Retrieved 2013-11-10.
191. "Three for three: How AMD won the war for the heart of next-gen consoles". Retrieved 2013-11-10.
192. MACHKOVECH, SAM (2 August 2016). "Microsoft hid performance boosts for old games in Xbox One S, told no one". Ars Technica. Retrieved 2 August 2016.
193. Walton, Mark (10 August 2016). "PS4 Neo: Sony confirms PlayStation event for September 7". Ars Technica. Retrieved 10 August 2016.
194. Walton, Mark (19 April 2016). "Sony PS4K is codenamed NEO, features upgraded CPU, GPU, RAM—report". Ars Technica. Retrieved 10 August 2016.
195. Smith, Ryan (8 September 2016). "Analyzing Sony's Playstation 4 Pro Hardware Reveal: What Lies Beneath". Anandtech. Retrieved 8 September 2016.
196. Freedman, Andrew (3 November 2017). "Xbox One X vs. PlayStation 4 Pro: Which Powerhouse Should You Get?". Tom's Guide. Retrieved 3 November 2017.
197. "PS4 Pro's additional RAM frees up memory for game developers". Polygon. Retrieved 2018-11-23.
198. http://www.anandtech.com/show/11536/microsofts-project-scorpio-get-a-launch-date-xbox-one-x-499-november-7th
199. https://arstechnica.com/gaming/2017/04/xbox-scorpio-hardware-specs/
200. Cutress, Ian (21 August 2017). "Hot Chips: Microsoft Xbox One X Scoprio Engine Live Blog". Anandtech. Retrieved 21 August 2017.
201. Cutress, Ian (3 August 2018). "AMD Creates Quad Core Zen SoC with 24 Vega CUs for Chinese Consoles". Anandtech.
202. Cutress, Ian (6 August 2018). "More Details About the ZhongShan Subor Z+ Console, with Custom AMD Ryzen SoC". Anandtech.
203. Leadbetter, Richard (15 September 2018). "Hands-on with the Subor Z-Plus: AMD tech tested in new Chinese console". Retrieved 28 October 2018.
204. Judd, Will (16 May 2019). "The Subor Z+ console team has disbanded - but it's not game over yet". Gamer Network.
205. Leadbetter, Leadbetter (15 September 2018). Hands-On: Subor Z Plus Chinese PC/Console Hybrid - Ryzen+Vega AMD Analysis!. Eurogamer. Event occurs at 2 minutes 2 seconds. Retrieved 28 October 2018.
206. Smith, Ryan (16 April 2019). "Sony Teases Next-Gen PlayStation: Custom AMD Chip with Zen 2 CPU & Navi GPU, SSD Too". Anandtech.

External links

• AMD Accelerated Processing Units official website
• Technical specification AMD products
• AMD products and technologies