List of AMD accelerated processing unit microprocessors

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

Feature overview

Features of AMD Accelerated Processing Units

Brand	Llano	Trinity	Richland	Kaveri	Carrizo	Bristol Ridge	Raven Ridge		Desna, Ontario, Zacate	Kabini, Temash	Beema, Mullins	Carrizo-L
Platform	Desktop, Mobile			Desktop, Mobile	Mobile, Desktop	Desktop, Mobile			Ultra-mobile
Released	Aug 2011	Oct 2012	Jun 2013	Jan 2014	Jun 2015	Jun 2016	Mar 2017		Jan 2011	May 2013	Q2 2014	May 2015
Fab. (nm)	GlobalFoundries 32 SOI			28			14		TSMC 40	28
Die size (mm^2)	228	246		245	244.62	TBA	TBA		75 (+ 28 FCH)	~107		TBA
Socket	FM1, FS1	FM2, FS1+, FP2		FM2+, FP3	FP4, FM2+	AM4, FP4	AM4		FT1	AM1, FT3	FT3b	FP4
CPU architecture	AMD 10h	Piledriver		Steamroller	Excavator		Zen		Bobcat	Jaguar	Puma	Puma+[1]
Memory support	DDR3-1866 DDR3-1600 DDR3-1333		DDR3-2133 DDR3-1866 DDR3-1600 DDR3-1333			DDR4-2400 DDR4-2133 DDR4-1866 DDR4-1600			DDR3L-1333 DDR3L-1066	DDR3L-1866 DDR3L-1600 DDR3L-1333 DDR3L-1066		DDR3L-1866 DDR3L-1600 DDR3L-1333
3D engine[lower-alpha 1]	TeraScale 2 (VLIW5)	TeraScale 3 (VLIW4)		GCN 1.1 (Mantle, HSA)	GCN 1.2 (Mantle, HSA)		GCN 1.3 (Mantle, HSA)		TeraScale 2 (VLIW5)	GCN 1.1
	Up to 400:20:8	Up to 384:24:6		Up to 512:32:8			Up to 768:48:12		80:8:4	128:8:4
	IOMMUv1			IOMMUv2					IOMMUv1[2]			TBA
Unified Video Decoder	UVD 3			UVD 4.2	UVD 6		TBA		UVD 3	UVD 4	UVD 4.2	UVD 6
Video Coding Engine	N/A	VCE 1.0		VCE 2.0	VCE 3.1		TBA		N/A	VCE 2.0		VCE 3.1
GPU power saving	PowerPlay	PowerTune							N/A	Enduro
Max. displays[lower-alpha 2]	2–3	2–4		2–4	3	4	TBA		2			TBA
TrueAudio	N/A			✔[4]					N/A[2]
FreeSync	N/A			✔					N/A
/drm/radeon[5][6][7]	✔					N/A			✔
/drm/amd/amdgpu[8]	N/A			Experimental	✔				N/A	Experimental

1. Unified shaders : texture mapping units : render output units
2. To feed more than two displays, the additional panels must have native DisplayPort support.^[3] Alternatively active DisplayPort-to-DVI/HDMI/VGA adapters can be employed.

Desktop processors

Lynx: "Llano" (2011, 32 nm)

• Manufactured on GlobalFoundries' 32 nm SOI process for Socket FM1
• Die size: 228 mm², with 1.178 billion transistors^[9][10]
• CPU cores with an upgraded architecture known as Stars (or AMD 10h or Husky or K10.5) with no L3 cache
• GPU: TeraScale 2
• 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.^[11]
• Support for up to four DIMMs of up to DDR3-1866 memory
• 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
• MMX, SSE, SSE2, SSE3, SSE4a, Enhanced 3DNow!, NX bit, AMD64, Cool'n'Quiet, AMD-V

Model number	Stepping	CPU					GPU			Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Vcore	Model	Config^2	Frequency
E2-3200	B0	2	2.4 GHz	N/A	2 × 512 kB	0.9125 - 1.4125	HD 6370D	160:8:4	443 MHz	DDR3-1600	065 W	Q4 2011	ED3200OJZ22GX ED3200OJGXBOX
A4-3300	B0	2	2.5 GHz	N/A	2 × 512 kB	0.9125 - 1.4125	HD 6410D	160:8:4	443 MHz	DDR3-1600	065 W	Sep 7, 2011	AD33000OJZ22HX AD3300OJHXBOX
A4-3400			2.7 GHz						600 MHz			Sep 7, 2011	AD3400OJZ22GX AD3400OJGXBOX
A4-3420			2.8 GHz						600 MHz			Dec 20, 2011	AD3420OJZ22HX
A6-3500	B0	3	2.1 GHz	2.4 GHz	3 × 1 MB	0.9125 - 1.4125	HD 6530D	320:16:8	443 MHz	DDR3-1866	065 W	Aug 17, 2011	AD3500OJZ33GX AD3500OJGXBOX
A6-3600		4			4 × 1 MB								AD3600OJZ43GX AD3600OJGXBOX
A6-3620			2.2 GHz	2.5 GHz								Dec 20, 2011	AD3620OJZ43GX
A6-3650			2.6 GHz	N/A							100 W	Jun 30, 2011	AD3650WNZ43GX AD3650WNGXBOX
A6-3670K^4			2.7 GHz									Dec 20, 2011	AD3670WNZ43GX AD3670WNGXBOX
A8-3800	B0	4	2.4 GHz	2.7 GHz	4 × 1 MB	0.9125 - 1.4125	HD 6550D	400:20:8	600 MHz	DDR3-1866	065 W	Aug 17, 2011	AD3800OJZ43GX AD3800OJGXBOX
A8-3820			2.5 GHz	2.8 GHz								Dec 20, 2011	AD3820OJZ43GX
A8-3850			2.9 GHz	N/A							100 W	Jun 30, 2011	AD3850WNZ43GX AD3850WNGXBOX
A8-3870K^4			3.0 GHz									Dec 20, 2011	AD3870WNZ43GX AD3870WNGXBOX

Model number	Stepping	CPU					Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Vcore
Sempron X2 198	B0	2	2.5 GHz	N/A	2 × 512 kB	0.9125 - 1.4125	DDR3-1600	065 W	Q1 2012	SD198XOJZ22GX SD198XOJGXBOX
Athlon II X2 221	B0	2	2.8 GHz	N/A	2 × 512 kB	0.9125 - 1.4125	DDR3-1600	065 W	Q1 2012	AD221XOJZ22GX AD221XOJGXBOX
Athlon II X4 631	B0	4	2.6 GHz	N/A	4 × 1 MB	0.9125 - 1.4125	DDR3-1866	100 W	Aug 15, 2011	AD631XOJZ43GX AD631XWNZ43GX
Athlon II X4 638			2.7 GHz					065 W	Feb 8, 2012	AD638XOJZ43GX AD638XOJGXBOX
Athlon II X4 641			2.8 GHz					100 W	Feb 8, 2012	AD641XWNZ43GX AD641XWNGXBOX
Athlon II X4 651			3.0 GHz					100 W	Nov 14, 2011	AD651XWNZ43GX AD651XWNGXBOX
Athlon II X4 651K			3.0 GHz					100 W	Q1, 2012	AD651KWNZ43GX AD651KWNGXBOX

Virgo: "Trinity" (2012, 32 nm)

• Manufactured on GlobalFoundries' 32 nm SOI process for Socket FM2
• CPU: Piledriver
• GPU TeraScale 3 (VLIW4)
• Die Size: 246 mm², 1.303 Billion transistors^[12]
• 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 1.1, XOP, FMA4, CVT16, F16C
• 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.^[13][14] However, it has been found that this does not always improve 3D accelerated graphics performance.^[15][16]

Model number	Stepping	CPU					GPU			Memory support	TDP	Released	Part number[17]
		Cores	Frequency	Turbo	L2 Cache	Vcore	Model	Config^2	Frequency
Sempron X2 240[18]	A1	2	2.9 GHz	3.3 GHz	1 MB		N/A				065 W		SD240XOKA23HJ
Athlon X2 340	A1	2	3.2 GHz	3.6 GHz	1 MB	0.825 - 1.475 V	N/A			DDR3-1866	065 W	Oct 2012	AD340XOKA23HJ
Athlon X4 740	A1	4	3.2 GHz	3.7 GHz	2× 2 MB	0.825 - 1.475 V	N/A			DDR3-1866	065 W	Oct 2012	AD740XOKA44HJ AD740XOKHJBOX
Athlon X4 750k			3.4 GHz	4.0 GHz							100 W		AD750KWOA44HJ AD750KWOHJBOX
FirePro A300	B0	4	3.4 GHz	4.0 GHz	4× 1 MB	0.825 - 1.475 V		384	760 MHz	DDR3-1866	065 W	Aug 7, 2012	AWA300OKA44HJ
FirePro A320			3.8 GHz	4.2 GHz					800 MHz		100 W		AWA320WOA44HJ
A4-5300	A1	2	3.4 GHz	3.7 GHz	1 MB	0.825 - 1.475 V	HD 7480D	128:8:4	723 MHz	DDR3-1600	065 W	Oct 1, 2012	AD5300OKA23HJ AD5300OKHJBOX
A4-5300B	B0												AD530BOKA23HJ
A6-5400K	A1	2	3.6 GHz	3.8 GHz	1 MB	0.825 - 1.475 V	HD 7540D	192:12:4	760 MHz	DDR3-1866	065 W	Oct 1, 2012	AD540KOKA23HJ AD540KOKHJBOX
A6-5400B	B0												AD540BOKA23HJ
A8-5500	A1	4	3.2 GHz	3.7 GHz	2× 2 MB	0.825 - 1.475 V	HD 7560D	256:16:8	760 MHz	DDR3-1866	065 W	Oct 1, 2012	AD5500OKA44HJ AD5500OKHJBOX
A8-5500B	B0												AD550BOKA44HJ
A8-5600K	A1	4	3.6 GHz	3.9 GHz	2× 2 MB	0.825 - 1.475 V	HD 7560D	256:16:8	760 MHz	DDR3-1866	100 W	Oct 1, 2012	AD560KWOA44HJ AD560KWOHJBOX
A10-5700	A1	4	3.4 GHz	4.0 GHz	2× 2 MB	0.825 - 1.475 V	HD 7660D	384:24:8	760 MHz	DDR3-1866	065 W	Oct 1, 2012	AD5700OKA44HJ AD5700OKHJBOX
A10-5800K	A1	4	3.8 GHz	4.2 GHz	2× 2 MB	0.825 - 1.475 V	HD 7660D	384:24:8	800 MHz	DDR3-1866	100 W	Oct 1, 2012	AD580KWOA44HJ AD580KWOHJBOX
A10-5800B	B0												AD580BWOA44HJ

"Richland" (2013, 32 nm)

• Socket FM2
• CPU: Two or four Piledriver-cores
• GPU TeraScale 3 (VLIW4)
• MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AMD64, AMD-V, AES, AVX, AVX1.1, XOP, FMA3, FMA4, CVT16, F16C, BMI (Bit Manipulation instructions), ABM (Advanced Bit Manipulation), TBM (Trailing Bit Manipulation instructions), Turbo Core 3.0, NX bit
• PowerNow!
• HD Media Accelerator, Hybrid Graphics
• GPU based on 4-way VLIW architecture first introduced with the HD 6900

Model number	Stepping	CPU					GPU			Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Vcore	Model	Config^2	Frequency
Sempron X2 250[18]	A1	2	3.2 GHz	3.6 GHz	1 MB		N/A				065 W		SD250XOKA23HL
Athlon X2 350[19]	A1	2	3.5 GHz	3.9 GHz	1 MB	0.825 - 1.475	N/A			DDR3-1866	065 W		AD350XOKA23HL
Athlon X2 370K			4.0 GHz	4.2 GHz								Jun 2013	AD370KOKA23HL AD370KOKHLBOX
Athlon X4 750[19]	A1	4	3.4 GHz	3.9 GHz	2× 2 MB		N/A			DDR3-1866	065 W		AD750XOKA44HL
Athlon X4 760K			3.8 GHz	4.1 GHz							100 W	Jun 2013	AD760KWOA44HL AD760KWOHLBOX
A4-4000		2	3.0 GHz	3.2 GHz	1 MB	0.80 - 1.45	7480D	128	720 MHz	DDR3-1333	065 W	May 2013	AD4000OKA23HL AD4000OKHLBOX
A4-4020			3.2 GHz	3.4 GHz								Jan 2014	AD4000OKA23HL AD4020OKHLBOX
A4-6300	A1	2	3.7 GHz	3.9 GHz	1 MB		8370D	128	760 MHz	DDR3-1600	065 W	July 2013	AD6300OKA23HL AD6300OKHLBOX
A4-6300B													AD630BOKA23HL
A4-6320	A1	2	3.8 GHz	4.0 GHz	1 MB		8370D	128	760 MHz	DDR3-1600	065 W	Dec 2013	AD6320OKA23HL AD6320OKHLBOX
A4-6320B													AD632BOKA23HL
A4-7300	A1	2	3.8 GHz	4.0 GHz	1 MB		8470D	192	800 MHz	DDR3-1600	065 W	Aug 2014	AD7300OKA23HL
A4 PRO-7300B													AD730BOKA23HL
A6-6400K		2	3.9 GHz	4.1 GHz	1 MB		8470D	192	800 MHz	DDR3-1866	065 W	Jun 4, 2013	AD640KOKA23HL AD640KOKHLBOX
A6-6400B													AD640BOKA23HL
A6-6420K		2	4.0 GHz	4.2 GHz	1 MB		8470D	192	800 MHz	DDR3-1866	065 W	Jan 2014	AD642KOKA23HL AD642KOKHLBOX
A4-6420B													AD642BOKA23HL
A8-6500T	A1	4	2.1 GHz	3.1 GHz	2× 2 MB		8550D	256	720 MHz	DDR3-1866	045 W	Sep 18, 2013	AD650TYHA44HL AD650TYHHLBOX
A8-6500	A1	4	3.5 GHz	4.1 GHz	2× 2 MB		8570D	256	800 MHz	DDR3-1866	065 W	Jun 4, 2013	AD6500OKA44HL AD6500OKHLBOX
A8-6500B													AD650BOKA44HL
A8-6600K	A1	4	3.9 GHz	4.2 GHz	2× 2 MB		8570D	256	844 MHz	DDR3-1866	100 W	Jun 4, 2013	AD660KWOA44HL AD660KWOHLBOX
A10-6700T	A1	4	2.5 GHz	3.5 GHz	2× 2 MB		8650D	384	720 MHz	DDR3-1866	045 W	Sep 18, 2013	AD670TYHA44HL AD670TYHHLBOX
A10-6700	A1	4	3.7 GHz	4.3 GHz	2× 2 MB		8670D	384	844 MHz	DDR3-1866	065 W	Jun 4, 2013	AD6700OKA44HL AD6700OKHLBOX
A10-6790K[20]			4.0 GHz	4.3 GHz							100 W	Oct 29, 2013	AD679KWOA44HL AD679KWOHLBOX
FX-670K[21]	A1	4	3.7 GHz	4.3 GHz	2× 2 MB		N/A			DDR3-1866	065 W
A10-6800K	A1	4	4.1 GHz	4.4 GHz	2× 2 MB		8670D	384	844 MHz	DDR3-2133	100 W	Jun 4, 2013	AD680KWOA44HL AD680KWOHLBOX
A10-6800B													AD680BWOA44HL

"Kabini" (2014, 28 nm, SoC)

• Socket AM1, aka Socket FS1b (AM1 platform)
• 2 to 4 CPU Cores (Jaguar (microarchitecture))
• SSE4.1, SSE4.2, AVX, AES, F16C, BMI1 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	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Multi^1	Vcore	Model	Config^2	Frequency	Turbo
Sempron 2650	A1	2	1.45 GHz	N/A	1 MB		0.5–1.4V	R3 (HD 8240)	128:8:4	400 MHz	N/A	DDR3-1333	025 W	April 9, 2014	SD2650JAH23HM SD2650JAHMBOX
Sempron 3850	A1	4	1.30 GHz	N/A	2 MB		0.5–1.4V	R3 (HD 8280)	128:8:4	450 MHz	N/A	DDR3-1600	025 W	April 9, 2014	SD3850JAH44HM SD3850JAHMBOX
Athlon 5150	A1	4	1.60 GHz	N/A	2 MB		0.5–1.4V	R3 (HD 8400)	128:8:4	600 MHz	N/A	DDR3-1600	025 W	April 9, 2014	AD5150JAH44HM AD5150JAHMBOX
Athlon 5350	A1	4	2.05 GHz	N/A	2 MB		0.5–1.4V	R3 (HD 8400)	128:8:4	600 MHz	N/A	DDR3-1600	025 W	April 9, 2014	AD5350JAH44HM AD5350JAHMBOX
Athlon 5370	A1	4	2.20 GHz	N/A	2 MB		0.5–1.4V	R3 (HD 8400)	128:8:4	600 MHz	N/A	DDR3-1600	025 W	February, 2016	AD5370JAH44HM

"Kaveri" (2014, 28 nm)

• Socket FM2+,^[22] support for PCIe 3.0
• Two or four CPU cores based on the Steamroller microarchitecture
• Three to eight Compute Units (CUs) based on Graphics Core Next (GCN)^[23] 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^[24]
• Dual-channel (2× 64 Bit) DDR3 memory controller
• Integrated custom ARM Cortex-A5 co-processor^[25] with TrustZone Security Extensions^[26]
• Select models support Hybrid Graphics technology by using a Radeon R7 240 or R7 250 discrete graphics card^[27]
• Display controller: AMD Eyefinity 2, 4K Ultra HD support, DisplayPort 1.2 Support^[28]

Model number	Stepping	CPU				GPU			Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Model	Config	Frequency
Athlon X2 450[19]	A1	2	3.5 GHz	3.9 GHz	1 MB	N/A			DDR3-1866	065 W		AD450XYBI23JA
Athlon X4 840[19]	A1	4	3.1 GHz	3.8 GHz	2× 2 MB	N/A			DDR3-1866	065 W
Athlon X4 860K			3.7 GHz	4.0 GHz						095 W		AD860KXBI44JA AD860KXBJABOX AD860KWOHLBOX
Athlon X4 870K			3.9 GHz	4.1 GHz								AD870KXBI44JC AD870KXBJCSBX
Athlon X4 880K			4.0 GHz	4.2 GHz					DDR3-2133		Mar 1, 2016	AD880KXBJCSBX
A4 PRO-7350B	A1	2	3.4 GHz	3.8 GHz	1 MB	R5 (3 CUs)	192:12:8	514 MHz	DDR3-1866	065 W		AD735BYBI23JA
A6-7400K	A1	2	3.5 GHz	3.9 GHz	1 MB	R5 (4 CUs)	256:16:8	756 MHz	DDR3-1866	065 W	Jul 31, 2014	AD740KYBI23JA AD740KYBJABOX
A6 PRO-7400B												AD740BYBI23JA
A6-7470K	A1	2	3.7 GHz	4.0 GHz	1 MB	R5 (4 CUs)	256:16:8	800 MHz	DDR3-2133	065 W	Feb 2, 2016	AD747KYBI23JC AD747KYBJCBOX
A8-7600	A1	4	3.1 GHz	3.8 GHz	2× 2 MB	R7 (6 CUs)	384:24:8	720 MHz	DDR3-2133	065 W	Jul 31, 2014	AD7600YBI44JA AD7600YBJABOX
A8 PRO-7600B												AD760BYBI44JA
A8-7650K	A1	4	3.3 GHz	3.8 GHz	2× 2 MB	R7 (6 CUs)	384:24:8	720 MHz	DDR3-2133	095 W	Jan 7, 2015	AD765KXBI44JA AD765KXBJABOX
A8-7670K	A1	4	3.6 GHz	3.9 GHz	2× 2 MB	R7 (6 CUs)	384:24:8	757 MHz	DDR3-2133	095 W	Jul 20, 2015	AD767KXBI44JC AD767KXBJCSBX AD767KXBJCBOX
A10-7700K	A1	4	3.4 GHz	3.8 GHz	2× 2 MB	R7 (6 CUs)	384:24:8	720 MHz	DDR3-2133	095 W	Jan 14, 2014	AD770KXBI44JA AD770KXBJABOX
A10-7800	A1	4	3.5 GHz	3.9 GHz	2× 2 MB	R7 (8 CUs)	512:32:8	720 MHz	DDR3-2133	065 W	Jul 31, 2014	AD7800YBI44JA AD7800YBJABOX
A10 PRO-7800B												AD780BYBI44JA
A10-7850K	A1	4	3.7 GHz	4.0 GHz	2× 2 MB	R7 (8 CUs)	512:32:8	720 MHz	DDR3-2133	095 W	Jan 14, 2014	AD785KXBI44JA AD785KXBJABOX
A10 PRO-7850B											Jul 31, 2014	AD785BXBI44JA
FX-770K[29]	A1	4	3.5 GHz	3.9 GHz	2× 2 MB	N/A			DDR3-2133	065 W		FD770KYBI44JA
A10-7860K	A1	4	3.6 GHz	4.0 GHz	2× 2 MB	R7 (8 CUs)	512:32:8	757 MHz	DDR3-2133	065 W	Feb 2, 2016	AD786KYBI44JC AD786KYBJABOX AD786KYBJCSBX
A10-7870K	A1	4	3.9 GHz	4.1 GHz	2× 2 MB	R7 (8 CUs)	512:32:8	866 MHz	DDR3-2133	095 W	May 28, 2015	AD787KXDI44JC AD787KXDJCBOX AD787KXDJCSBX
A10-7890K	A1	4	4.1 GHz	4.3 GHz	2× 2 MB	R7 (8 CUs)	512:32:8	866 MHz	DDR3-2133	095 W	Mar 1, 2016	AD789KXDJCHBX

"Carrizo" (2016, 28 nm)

• Socket FM2+, support for PCIe 3.0
• Four CPU cores based on the Excavator microarchitecture
• Dual-channel (2× 64 Bit) DDR3 memory controller

Model number	Stepping	CPU				GPU			Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Model	Config	Frequency
Athlon X4 835[30]	?	4	?	?	2× 1 MB	N/A			DDR3-2133	065 W	?	?
Athlon X4 845			3.5 GHz	3.8 GHz							Feb 2, 2016	AD845XYBJCSBX AD845XACKASBX

Server processors

"Kyoto" (2013, 28 nm)

• Based upon the Jaguar microarchitecture
• For other model details see here

Model	Stepping	CPU						GPU			Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Multi^1	Vcore	Model	Config^2	Frequency
Opteron X2150	?	4	1.9 GHz	?	2 MB	?	?	HD ?	128:8:4	266-600 MHz	DDR3-1600	11 - 22 W	May 29, 2013	OX2150IAJ44HM

Mobile processors

Sabine: "Llano" (2011, 32 nm)

• Upgraded Stars (AMD 10h architecture) codenamed Husky CPU cores (K10.5) with no L3 cache, and with Redwood-class integrated graphics on die (BeaverCreek for the dual-core variants and WinterPark for the quad-core variants)
• Manufactured on GlobalFoundries' 32 nm SOI process (die size: 228 mm², with 1.45 billion transistors) for socket FS1
• 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
• SSE, SSE2, SSE3, SSE4a, Enhanced 3DNow!, NX bit, AMD64, AMD-V
• PowerNow!

Model	Stepping	CPU						GPU			Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Multi^1	Vcore	Model	Config^2	Frequency
E2-3000M	B0	2	1.8 GHz	2.4 GHz	2 × 512 kB	9 - 12×	0.9125 - 1.4125	HD 6380G	160:8:4	400 MHz	DDR3-1333	35 W	Jun 14, 2011	EM3000DDX22GX
A4-3300M	B0	2	1.9 GHz	2.5 GHz	2 × 1 MB	9.5 - 12.5×	0.9125 - 1.4125	HD 6480G	240:12:4	444 MHz	DDR3-1333	35 W	Jun 14, 2011	AM3300DDX23GX
A4-3305M					2 × 512 kB		0.8750 - 1.4125		160:8:4	593 MHz			Dec 7, 2011	AM3305DDX22GX
A4-3310MX			2.1 GHz		2 × 1 MB	10.5 - 12.5×	0.9125 - 1.4125		240:12:4	444 MHz		45 W	Jun 14, 2011	AM3310HLX23GX
A4-3320M			2.0 GHz	2.6 GHz		10 - 13×						35 W	Dec 7, 2011	AM3320DDX23GX
A4-3330MX			2.2 GHz			11 - 13×	0.8750 - 1.4125					45 W		AM3330HLX23GX
A4-3330MX			2.3 GHz		2 × 512 kB	11.5 - 13×	0.9125 - 1.4125		160:8:4	593 MHz				AM3330HLX23HX
A6-3400M	B0	4	1.4 GHz	2.3 GHz	4 × 1 MB	7 - 12.5×	0.9125 - 1.4125	HD 6520G	320:16:8	400 MHz	DDR3-1333	35 W	Jun 14, 2011	AM3400DDX43GX
A6-3410MX			1.6 GHz			8 - 12.5×					DDR3-1600	45 W		AM3410HLX43GX
A6-3420M			1.5 GHz	2.4 GHz		7.5 - 12×					DDR3-1333	35 W	Dec 7, 2011	AM3420DDX43GX
A6-3430MX			1.7 GHz			8.5 - 12×					DDR3-1600	45 W		AM3430HLX43GX
A8-3500M	B0	4	1.5 GHz	2.4 GHz	4 × 1 MB	7.5 - 12×	0.9125 - 1.4125	HD 6620G	400:20:8	444 MHz	DDR3-1333	35 W	Jun 14, 2011	AM3500DDX43GX
A8-3510MX			1.8 GHz	2.5 GHz		9 - 12.5×					DDR3-1600	45 W		AM3510HLX43GX
A8-3520M			1.6 GHz			8 - 12.5×					DDR3-1333	35 W	Dec 7, 2011	AM3520DDX43GX
A8-3530MX			1.9 GHz	2.6 GHz		9.5 - 13×					DDR3-1600	45 W	Jun 14, 2011	AM3530HLX43GX
A8-3550MX			2.0 GHz	2.7 GHz		10 - 13.5×							Dec 7, 2011	AM3550HLX43GX

Comal: "Trinity" (2012, 32 nm)

• Based on the Piledriver architecture
• 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, CVT16, F16C, 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	Stepping	CPU						GPU				Memory support	TDP	Socket	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Multi	Vcore	Model	Config	Frequency	Turbo
A4-4300M	B0	2	2.5 GHz	3.0 GHz	1 MB	25x	0.8125 - 1.3	HD 7420G	128:8:4	480 MHz	655 MHz	DDR3-1600	35 W	FS1r2	May 15, 2012	AM4300DEC23HJ
A6-4400M			2.7 GHz	3.2 GHz		27x		HD 7520G	192:12:4	496 MHz	685 MHz					AM4400DEC23HJ
A8-4500M		4	1.9 GHz	2.8 GHz	2× 2 MB	19x		HD 7640G	256:16:8							AM4500DEC44HJ
A10-4600M			2.3 GHz	3.2 GHz		23x		HD 7660G	384:24:8							AM4600DEC44HJ
A4-4355M	B0	2	1.9 GHz	2.4 GHz	1 MB	19x		HD 7400G	192:12:4	327 MHz	424 MHz	DDR3-1333	17 W	Socket FP2	Sep 27, 2012	AM4355SHE23HJ
A6-4455M			2.1 GHz	2.6 GHz	2 MB	21x	0.775 - 1.15	HD 7500G	256:16:8						May 15, 2012	AM4455SHE24HJ
A8-4555M		4	1.6 GHz	2.4 GHz	2× 2 MB	16x		HD 7600G	384:24:8	320 MHz			19 W		Sep 27, 2012	AM4555SHE44HJ
A10-4655M			2.0 GHz	2.8 GHz		20x	0.85 - 1.2	HD 7620G		360 MHz	496 MHz		25 W		May 15, 2012	AM4655SIE44HJ

"Richland" (2013, 32 nm)

• Elite Performance APU.^[31][32]
• CPU: Piledriver architecture
• GPU: TeraScale 3 (VLIW4)
• XOP, AVX, FMA and F16C support

Model number	Stepping	CPU						GPU				Memory support	TDP	Socket	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Multi	Vcore	Model	Config	Frequency	Turbo
A4-5150M		2	2.7 GHz	3.3 GHz	1 MB			HD 8350G	128:8:4	533 MHz	720 MHz	DDR3-1600	35 W	FS1r2	Q1 2013	AM5150DEC23HL
A6-5350M			2.9 GHz	3.5 GHz				HD 8450G	192:12:4	533 MHz	720 MHz	DDR3-1600		FS1r2	Q1 2013	AM5350DEC23HL
A6-5357M			2.9 GHz	3.5 GHz				HD 8450G	192	533 MHz	720 MHz	DDR3L-1600		Socket FP2	May 2013	AM5357DFE23HL
A8-5550M		4	2.1 GHz	3.1 GHz	4 MB			HD 8550G	256:16:8	515 MHz	720 MHz	DDR3-1600		FS1r2	Q1 2013	AM5550DEC44HL
A8-5557M			2.1 GHz	3.1 GHz				HD 8550G	256	554 MHz	720 MHz	DDR3L-1600		Socket FP2	May 2013	AM5557DFE44HL
A10-5750M			2.5 GHz	3.5 GHz				HD 8650G	384:24:8	533 MHz	720 MHz	DDR3-1866		FS1r2	Q1 2013	AM5750DEC44HL
A10-5757M			2.5 GHz	3.5 GHz				HD 8650G	384	600 MHz	720 MHz	DDR3L-1600		Socket FP2	May 2013	AM5757DFE44HL
A4-5145M		2	2.0 GHz	2.6 GHz	1 MB			HD 8310G	128	424 MHz	554 MHz	DDR3L-1333	17 W	Socket FP2	May 2013	AM5145SIE44HL?
A6-5345M			2.2 GHz	2.8 GHz				HD 8410G	192	450 MHz	600 MHz	DDR3L-1333			May 2013	AM5345SIE44HL?
A8-5545M		4	1.7 GHz	2.7 GHz	4 MB			HD 8510G	384	450 MHz	554 MHz	DDR3L-1333	19 W		May 2013	AM5545SIE44HL
A10-5745M			2.1 GHz	2.9 GHz				HD 8610G	384	533 MHz	626 MHz	DDR3L-1333	25 W		May 2013	AM5745SIE44HL

"Kaveri" (2014, 28 nm)

• Socket FP3 (µBGA-?)
• Up to 4 "Steamroller" x86 CPU cores with 4 MB of L2 cache.^[33]
• Three to eight Compute Units (CUs) based on Graphics Core Next (GCN)^[23] 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^[24]
• Dual-channel (2x64-bit) DDR3 memory controller
• Integrated custom ARM Cortex-A5 co-processor^[25] with TrustZone Security Extensions^[26]

Model number	CPU						GPU				Memory support	TDP	Socket	Released	Part number
	Modules (Cores)	Frequency	Turbo	L2 Cache	Multi	Vcore	Model	Config	Frequency	Turbo
A6-7000	1 (2)	2.2 GHz	3.0 GHz	1 MB	22×		R4	192:12:4	494 MHz	533 MHz	DDR3-1333	17W	Socket FP3	June 2014	AM7000ECH23JA
A6 Pro-7050B									533 MHz	N/A	DDR3-1600				AM705BECH23JA
A8-7100	2 (4)	1.8 GHz	3.0 GHz	2× 2 MB	18×		R5	256:16:4	450 MHz	514 MHz	DDR3-1600	20W	Socket FP3	June 2014	AM7100ECH44JA
A8 Pro-7150B		1.9 GHz	3.2 GHz		19×				553 MHz	N/A					AM715BECH44JA
A10-7300		1.9 GHz	3.2 GHz		19×		R6	384:24:8	464 MHz	533 MHz					AM7300ECH44JA
A10 Pro-7350B		2.1 GHz	3.3 GHz		21×				553 MHz	N/A					AM735BECH44JA
FX-7500		2.1 GHz	3.3 GHz		21×		R7	384:24:8	498 MHz	553 MHz					FM7500ECH44JA
A8-7200P	2 (4)	2.4 GHz	3.3 GHz	2× 2 MB	24×		R5	256:16:4	553 MHz	626 MHz	DDR3-1866	35W	Socket FP3	June 2014	AM740PDGH44JA
A10-7400P		2.5 GHz	3.4 GHz		25×		R6	384:24:8	576 MHz	654 MHz					AM740PDGH44JA
FX-7600P		2.7 GHz	3.6 GHz		27×		R7	512:32:8	600 MHz	686 MHz	DDR3-2133				FM760PDGH44JA

"Carrizo" (2015, 28 nm)

• Socket FP4
• Up to 4 "Excavator" x86 CPU cores
• GPU based on Graphics Core Next 1.2

Model number	CPU						GPU				Memory support	TDP	Socket	Released	Part number
	Cores	Frequency	Turbo	L2 Cache	Multi	Vcore	Model	Config	Frequency	Turbo
A6-8500P	2	1.6 GHz	3.0 GHz	1 MB	16×		R5	256:16:4	800 MHz	N/A	DDR3-1600	12-35W	FP4	June 2015	AM850PAAY23KA
Pro A6-8500B									800 MHz	N/A					AM850BAAY23KA
A8-8600P	4	1.6 GHz	3.0 GHz	2× 1 MB	16×		R6	384:24:8	720 MHz	N/A	DDR3-2133	12-35W	FP4	June 2015	AM860PAAY43KA
Pro A8-8600B		1.6 GHz	3.0 GHz		16×				720 MHz	N/A					AM860BAAY43KA
A10-8700P		1.8 GHz	3.2 GHz		18×		R6	384:24:8	800 MHz	N/A					AM870PAAY43KA
Pro A10-8700B		1.8 GHz	3.2 GHz		18×				800 MHz	N/A					AM870BAAY43KA
FX-8800P		2.1 GHz	3.4 GHz		21×		R7	512:32:8	800 MHz	N/A					FM880PAAY43KA
Pro A12-8800B		2.1 GHz	3.4 GHz		21×				800 MHz	N/A					FM880BAAY43KA
A10-8780P		2.0 GHz	3.3 GHz		20×		R8	512:32:8	800 MHz	N/A				December 2015	AM878PAIY43KA

Ultra-mobile processors

Brazos: "Desna", "Ontario", "Zacate" (2011, 40 nm)

• Based on the Bobcat microarchitecture,^[34] manufactured in TSMC's 40 nm process in BGA-413 package for socket FT1
• SSE, SSE2, SSE3, SSSE3, SSE4a, 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	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Multi^1	Vcore	Model	Config^2	Frequency	Turbo
Z-01	B0	2	1.0 GHz	N/A	2 × 512 kB	5×		HD 6250	80:8:4	276 MHz	N/A	DDR3-1066	5.9 W	Jun 1, 2011	XMZ01AFVB22GV
C-30	B0	1	1.2 GHz	N/A	512 kB	6×	1.25 - 1.35	HD 6250	80:8:4	276 MHz	N/A	DDR3-1066	9 W	Jan 4, 2011	CMC30AFPB12GT
C-50		2	1.0 GHz		2 × 512 kB	5×	1.05 - 1.35								CMC50AFPB22GT
C-60	C0			1.33 GHz		5× - 6,65×		HD 6290		276 MHz	400 MHz			Aug 22, 2011	CMC60AFPB22GV
E-240	B0	1	1.5 GHz	N/A	512 kB	7,5×	1.175 - 1.35	HD 6310	80:8:4	500 MHz	N/A	DDR3-1066	18 W	Jan 4, 2011	EME240GBB12GT
E-300	B0?	2	1.3 GHz		2 × 512 kB	6,5×				488 MHz				Aug 22, 2011	EME300GBB22GV
E-350	B0		1.6 GHz			8×	1.25 - 1.35			492 MHz				Jan 4, 2011	EME350GBB22GT
E-450	B0 C0		1.65 GHz			8,25×		HD 6320		508 MHz	600 MHz	DDR3-1333		Aug 22, 2011	EME450GBB22GV

Brazos 2.0: "Ontario", "Zacate" (2012, 40 nm)

• Based on the Bobcat microarchitecture,^[34] manufactured in TSMC's 40 nm process in BGA-413 package for socket FT1
• SSE, SSE2, SSE3, SSSE3, SSE4a, 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	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Multi^1	Vcore	Model	Config^2	Frequency	Turbo
C-70	C0	2	1.00 GHz	1.33 GHz	2 × 512 kB	5× - 6,65×		HD 7290	80:8:4	276 MHz	400 MHz	DDR3-1066	9 W	Sep 15, 2012	CMC70AFPB22GV
E1-1200	B0?	2	1.40 GHz	N/A	2 × 512 kB	7×		HD 7310	80:8:4	500 MHz	N/A	DDR3-1066	18 W	Jun 6, 2012	EM1200GBB22GV
E1-1500	?		1.48 GHz							529 MHz	N/A			Jan 7, 2013
E2-1800	B0?		1.70 GHz			8,5×		HD 7340		523 MHz	680 MHz	DDR3-1333		Jun 6, 2012	EM1800GBB22GV
E2-2000	?		1.75 GHz			8,75×				538 MHz	700 MHz			Jan 7, 2013

Brazos-T: "Hondo" (2012, 40 nm)

• Based on the Bobcat microarchitecture,^[34] manufactured in TSMC's 40 nm process in BGA-413 package for socket FT1. Found in tablet computers
• SSE, SSE2, SSE3, SSSE3, SSE4a, NX bit, AMD64, AMD-V
• PowerNow!
• DirectX 11 integrated graphics
• 2.50 GT/s UMI (PCIe 1.0 ×4)

Model	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Multi^1	Vcore	Model	Config^2	Frequency	Turbo
Z-60		2	1.0 GHz	N/A	2× 512 kB	5×		HD 6250	80:8:4	276 MHz	N/A	DDR3-1066	4.5 W	Oct 9, 2012	XMZ60AFVB22GV

"Kabini", "Temash" (2013, 28 nm)

• Socket FT3 (BGA)
• 2 to 4 CPU Cores (Jaguar (microarchitecture))
• SSE4.1, SSE4.2, AVX, AES, F16C, BMI1 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	Stepping	CPU					GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Vcore	Model	Config^2	Frequency	Turbo
A4-1200	B0	2	1.0 GHz	N/A	1 MB		HD 8180	128:8:4	225 MHz	N/A	DDR3L-1066	4 W		AT1200IFJ23HM
A4-1250							HD 8210		300 MHz		DDR3L-1333	8 W		AT1250IDJ23HM
A4-1350		4			2 MB	0.40 - 0.95 V	HD 8210				DDR3L-1066	8 W		AT1350IDJ44HM
A6-1450				1.4 GHz			HD 8250			400 MHz	DDR3L-1066	8 W	May 2013	AT1450IDJ44HM

Kabini, Mainstream APU

Model	Stepping	CPU				GPU			Memory support	TDP	Released	Part number
		Cores	Frequency	L2 Cache	Vcore	Model	Config^2	Frequency
E1-2100	B0	2	1.00 GHz	1 MB		HD 8210	128:8:4	300 MHz	DDR3L-1333	09 W	May 2013	EM2100ICJ23HM
E1-2200			1.05 GHz		0.50 - 1.40 V	HD 8210		300 MHz	DDR3L-1333	09 W	Feb 2014	EM2200ICJ23HM
E1-2500			1.40 GHz			HD 8240		400 MHz	DDR3L-1333	15 W	May 2013	EM2500IBJ23HM
E2-3000			1.65 GHz			HD 8280		450 MHz	DDR3L-1600	15 W	May 2013	EM3000IBJ23HM
E2-3800		4	1.30 GHz	2 MB	0.50 - 1.40 V	HD 8280		450 MHz	DDR3L-1600	15 W	Feb 2014	EM3800IBJ44HM
A4-5000			1.50 GHz			HD 8330		497 MHz	DDR3L-1600	15 W	May 2013	AM5000IBJ44HM
A4-5100			1.55 GHz		0.50 - 1.40 V	HD 8330		497 MHz	DDR3L-1600	15 W	Feb 2014	AM5100IBJ44HM
A6-5200			2.00 GHz			HD 8400		600 MHz	DDR3L-1600	25 W	May 2013	AM5200IAJ44HM
A4 Pro-3340B			2.20 GHz			HD 8240		400 MHz	DDR3L-1600	25 W	Nov 2014	AM334BIAJ44HM

"Beema", "Mullins" (2014, 28 nm)

• Socket FT3b (BGA)
• CPU: 2 to 4 (Puma cores)
• GPU based on Graphics Core Next (GCN)
• SSE4.1, SSE4.2, AVX, AES, F16C, BMI1 support
• Intelligent Turbo Boost
• Platform Security Processor, with an integrated ARM Cortex-A5 for TrustZone execution

Mullins, Tablet/2-in-1 APU

Model	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Multi^1	Vcore	Model	Config^2	Frequency	Turbo
E1 Micro-6200T		2	1.0 GHz	1.4 GHz	1 MB		0.50 - 1.40 V	R2	128:8:4		300 MHz	DDR3L-1066	3.95 W	Q2 2014	EM620TIWJ23JB
A4 Micro-6400T		4	1.0 GHz	1.6 GHz	2 MB			R3			350 MHz	DDR3L-1333	4.5 W	Q2 2014	AM640TIVJ44JB
A10 Micro-6700T			1.2 GHz	2.2 GHz	2 MB			R6			500 MHz	DDR3L-1333	4.5 W	Q2 2014	AM670TIVJ44JB

Beema, Notebook APU

Model	Stepping	CPU					GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Vcore	Model	Config^2	Frequency	Turbo
E1-6010		2	1.35 GHz	N/A	1 MB	0.5 - 1.4 V	R2	128:8:4		350 MHz	DDR3L-1333	10 W	Q2 2014	EM6010IUJ23JB
E1-6015[35]			1.40 GHz										Q2 2015
E2-6110		4	1.50 GHz		2 MB					500 MHz	DDR3L-1600	15 W	Q2 2014	EM6110ITJ44JB
A4-6210			1.80 GHz				R3			600 MHz	DDR3L-1600	15 W	Q2 2014	AM6210ITJ44JB
A4-6250J[36]			2.00 GHz						267 MHz	600 MHz	DDR3-1600	25 W
A6-6310			1.80 GHz	2.4 GHz			R4			800 MHz	DDR3L-1866	15 W	Q2 2014	AM6310ITJ44JB
A8-6410			2.00 GHz	2.4 GHz			R5		300 MHz	847 MHz	DDR3L-1866	15 W	Q2 2014	AM6410ITJ44JB

"Carrizo-L" (2015, 28 nm)

• Socket FP4 (µBGA)^[37]
• CPU: 2 to 4 (Puma+ cores)

Model	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Multi^1	Vcore	Model	Config^2	Frequency	Turbo
E1-7010		2	1.5 GHz	N/A	1 MB		0.50 - 1.40 V	R2	128:8:4		400 MHz	DDR3L-1333	10 W	May 2015	EM7010JCY23JB
E2-7110		4	1.8 GHz		2 MB			R2			600 MHz	DDR3L-1600	12 W-25 W	May 2015	EM7110JBY44JB
A4-7210			1.8 GHz	2.2 GHz				R3			686 MHz	DDR3L-1600	12 W-25 W	May 2015	AM7210ITJ44JB
A6-7310			2.0 GHz	2.4 GHz				R4			800 MHz	DDR3L-1866	12 W-25 W	May 2015	AM7310JBY44JB
A8-7410			2.2 GHz	2.5 GHz				R5			847 MHz	DDR3L-1866	12 W-25 W	May 2015	AM7410JBY44JB

Embedded processors

G-Series

Brazos: "Ontario" and "Zacate" (2011, 40 nm)

• Socket FT1 (BGA-413)
• CPU microarchitecture: Bobcat^[38]
• 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 number	Stepping	CPU					GPU			Memory support	TDP	Released	Part number
		Cores	Frequency	L2 Cache	Multi^1	Vcore	Model	Config^2	Frequency
G-Series T24L	B0	1	800 MHz 1.0 GHz	512 kB	4× 5×		N/A			DDR3-1066	5 W	Mar 1, 2011 May 23, 2011	GET24LFPB12GTE GET24LFQB12GVE
G-Series T30L	B0	1	1.4 GHz	512 kB	7×						18 W	Mar 1, 2011 May 23, 2011	GET30LGBB12GTE GET30LGBB12GVE
G-Series T48L	B0	2		2 × 512 kB								Mar 1, 2011 May 23, 2011	GET48LGBB22GTE GET48LGBB22GVE
G-Series T16R		1	615 MHz	512 kB	?×		HD 6250	80:8:4	276 MHz	DDR3L-1066	4.5 W	Jun 25, 2012	GET16RFWB12GVE
G-Series T40R		1	1.0 GHz	512 kB	5×				280 MHz	DDR3-1066	5.5 W	May 23, 2011	GET40RFQB12GVE
G-Series T40E		2		2 × 512 kB							6.4 W		GET40EFQB22GVE
G-Series T40N^3	B0	2	1.0 GHz	2 × 512 kB	5×		HD 6250 HD 6290	80:8:4	280 MHz 280 MHz^3	DDR3-1066	9 W	Jan 19, 2011 May 23, 2011	GET40NFPB22GTE GET40NFPB22GVE
G-Series T40R	B0	1	1.0 GHz	512 kB	5×		HD 6250		280 MHz		5.5 W	May 23, 2011	GET40RFSB12GVE
G-Series T44R	B0	1	1.2 GHz	512 kB	6×		HD 6250		280 MHz		9 W	Jan 19, 2011 May 23, 2011	GET44RFPB12GTE GET44RFPB12GVE
G-Series T48E	B0	2	1.4 GHz	2 × 512 kB	7×		HD 6250	80:8:4	280 MHz	DDR3-1066	18 W	Jun 25, 2012	GET48EGBB22GVE
G-Series T48N	B0	2	1.4 GHz	2 × 512 kB	7×		HD 6310	80:8:4	500 MHz 520 MHz	DDR3-1066	18 W	Jan 19, 2011 May 23, 2011	GET48NGBB22GTE GET48NGBB22GVE
G-Series T52R	B0	1	1.5 GHz	512 kB	7.5×				500 MHz	DDR3-1066 DDR3-1333		Jan 19, 2011 May 23, 2011	GET52RGBB12GTE GET52RGBB12GVE
G-Series T56E	B0	2	1.65 GHz	2 × 512 kB	8.25×		HD 6250	80:8:4	275 MHz	DDR3-1333	18 W	Jun 25, 2012	GET56EGBB22GVE
G-Series T56N^3	B0	2	1.6 GHz 1.65 GHz	2 × 512 kB	8× 8.25×		HD 6310 HD 6320	80:8:4	500 MHz 500 MHz^3	DDR3-1066 DDR3-1333	18 W	Jan 19, 2011 May 23, 2011	GET56NGBB22GTE GET56NGBB22GVE

"Kabini" (2013, 28 nm, SoC)

• Socket FT3 (769-BGA)^[39]
• CPU microarchitecture: Jaguar
• support for SSE4.1, SSE4.2, AVX, AES, F16C, BMI1, no support for FMA (Fused Multiply-Accumulate), AMD Virtualization technology
• GPU microarchitecture: Graphics Core Next (GCN)
• hardware acceleration for video decode through Unified Video Decoder 3 (H.264, VC-1, MPEG2, etc.) and new video encode capability not available in previous AMD Embedded G-Series APU
• Single channel DDR3-1600, 1.25 and 1.35 V voltage levels support, support for ECC memory
• integrates Controller Hub functional block as well
• G-Series 2.0
• Trusted Platform Module (TPM) 1.2 support
• integrates HD audio and 2 SATA channels
• integrates USB 2.0 and USB 3.0 (GX-210JA no USB 3.0)^[40]

Model number	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache (shared)	Multi	Vcore	Model	Config^2	Frequency	Turbo
GX-210JA	B0	2	1.0 GHz	N/A	1 MB			HD 8180	128:8:4	225 MHz	N/A	DDR3-1066	06 W	Jul 30, 2013	GE210JIHJ23HM
GX-210HA			1.0 GHz	N/A	1 MB			HD 8210E		300 MHz	N/A	DDR3-1333	09 W	Jun 1, 2013	GE210HICJ23HM
GX-217GA			1.65 GHz	N/A	1 MB			HD 8280E		450 MHz	N/A	DDR3-1600	15 W	Jun 1, 2013	GE217GIBJ23HM
GX-415GA		4	1.5 GHz	N/A	2 MB			HD 8330E		500 MHz	N/A	DDR3-1600	15 W	Jun 1, 2013	GE415GIBJ44HM
GX-416RA			1.6 GHz	N/A	2 MB			N/A	N/A	N/A	N/A	DDR3-1600	15 W	Jun 1, 2013	GE416RIBJ44HM
GX-420CA			2.0 GHz	N/A	2 MB			HD 8400E	128:8:4	600 MHz	N/A	DDR3-1600	25 W	Jun 1, 2013	GE420CIAJ44HM

"Steppe Eagle" (2014, 28 nm, SoC)

• Socket FT3b (769-BGA)
• CPU microarchitecture: Puma

Model number	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache (shared)	Multi	Vcore	Model	Config^2	Frequency	Turbo
GX-210JC		2	1.0 GHz	N/A	1 MB				128:8:4	267 MHz	N/A	DDR3-1600	06 W	June 4, 2014	GE210JIZJ23JB
GX-212JC			1.2 GHz	N/A						300 MHz	N/A	DDR3-1333	06 W		GE212JIYJ23JB
GX-216HC			1.6 GHz	N/A						300 MHz	N/A	DDR3-1066	10 W		GE216HHBJ23JB
GX-222GC			2.2 GHz	N/A						655 MHz	N/A	DDR3-1600	15 W		GE222GITJ23JB
GX-412HC		4	1.2 GHz	N/A	2 MB					300 MHz	N/A	DDR3-1333	7 W		GE412HIYJ44JB
GX-424CC			2.4 GHz	N/A						497 MHz	N/A	DDR3-1866	25 W		GE424CIXJ44JB

"Crowned Eagle" (2014, 28 nm, SoC)

• Socket FT3b (769-BGA)
• CPU microarchitecture: Puma
• no GPU

Model number	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache (shared)	Multi	Vcore	Model	Config^2	Frequency	Turbo
GX-224PC		2	2.4 GHz	N/A	1 MB			N/A	N/A	N/A	N/A	DDR3-1866	025 W	June 4, 2014	GE224PIXJ23JB
GX-410VC		4	1.0 GHz	N/A	2 MB							DDR3-1066	7 W		GE410VIZJ44JB
GX-412TC			1.2 GHz	N/A								DDR3-1600	6 W		GE412TIYJ44JB
GX-420MC			2.0 GHz	N/A								DDR3-1600	17.5 W		GE420MIXJ44JB

I-Family: "Brown Falcon" (2016, 28 nm, SoC)

• Socket FP4 ^[41]
• 2 "Excavator" x86 cores with 1MB shared L2 cache
• 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 number	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache (shared)	Multi	Vcore	Model	Config^2	Frequency	Turbo
GX-217GI		2	1.7 GHz	2.0 GHz	1 MB			R6E (4 CUs)	256:16:4	758 MHz	N/A	DDR3/DDR4-1600	015 W	Feb 23, 2016	GE217GAAY23KA

J-Family: "Prairie Falcon" (2016, 28 nm, SoC)

• Socket FP4 ^[42]
• 2 "Excavator" x86 cores with 1MB shared L2 cache
• 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

LX-Family (2016, 28 nm, SoC)

• Socket FT3b (769-BGA)
• 2 “Puma” x86 cores with 1MB shared L2 cache
• 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 number	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache (shared)	Multi	Vcore	Model	Config^2	Frequency	Turbo
GX-208JL		2	800 MHz	N/A	1 MB			R1E (1 CU)	64:4:1	267 MHz	N/A	DDR3-1333	0<6 W	Feb 23, 2016	GE208JIVJ23JB
GX-210JL			1.0 GHz										6 W		GE210JIYJ23JB
GX-215GL			1.5 GHz							497 MHz		DDR3-1600	15 W		GE215GITJ23JB
GX-218GL			1.8 GHz										15 W		GE218GITJ23JB

R-Series

Comal: "Trinity" (2012, 32 nm)

• Socket FP2 (BGA-827)
• CPU microarchitecture: Piledriver
• 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 number	Stepping	CPU						GPU				Memory support	TDP	Socket	Released	Part number
		Cores	Frequency	Turbo	L2 Cache	Multi	Vcore	Model	Config^2	Frequency	Turbo
R-252F	B0	2	1.9 GHz	2.4 GHz	1 MB	09.5x	0.775 - 1.15	HD 7400G	192:12:4	333 MHz	417 MHz	DDR3-1333	17 W	Socket FP2	May 21, 2012	RE252FSHE23HJE
R-260H			2.1 GHz	2.6 GHz	2? MB	10.5x	0.775 - 1.15	HD 7500G	256:16:8	327 MHz	424 MHz	DDR3-1333	17 W	Socket FP2	May 21, 2012	RE260HSHE24HJE
R-268D			2.5 GHz	3.0 GHz	1 MB	12.5x	0.8125 - 1.3	HD 7420G	192:12:4	470 MHz	640 MHz	DDR3-1600	35 W	FS1r2	May 21, 2012	RE268DDEC23HJE
R-272F			2.7 GHz	3.2 GHz	1 MB	13.5x	0.8125 - 1.3	HD 7520G	192:12:4	497 MHz	686 MHz	DDR3-1600	35 W	FS1r2	May 21, 2012	RE272FDEC23HJE
R-452L		4	1.6 GHz	2.4 GHz	2 × 2 MB	08.0x	0.775 - 1.15	HD 7600G	256:16:8	327 MHz	424 MHz	DDR3-1600	19 W	Socket FP2	May 21, 2012	RE452LSHE44HJE
R-460H			1.9 GHz	2.8 GHz	2 × 2 MB	09.5x	0.8125 - 1.3	HD 7640G	256:16:8	497 MHz	655 MHz	DDR3-1600	35 W	FS1r2	May 21, 2012	RE460HDEC44HJE
R-460L			2.0 GHz	2.8 GHz	2 × 2 MB	10.0x	0.85 - 1.2	HD 7620G	384:24:8	360 MHz	497 MHz	DDR3-1333	25 W	Socket FP2	May 21, 2012	RE460LSIE44HJE
R-464L			2.3 GHz	3.2 GHz	2 × 2 MB	11.5x	0.8125 - 1.3	HD 7660G	384:24:8	497 MHz	686 MHz	DDR3-1600	35 W	FS1r2	May 21, 2012	RE464LDEC44HJE

"Bald Eagle" (2014, 28 nm)

• Up to 4 "Steamroller" x86 cores ^[43]
• 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 number	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache (shared)	Multi	Vcore	Model	Config^2	Frequency	Turbo
RX-219NB		2	2.2 GHz	3.0 GHz	1 MB			N/A		N/A	N/A	DDR3-1600	15-17 W	May 20, 2014	RE219NECH23JA
RX-225FB			2.2 GHz	3.0 GHz				R4 (3 CUs)	192:12:4	464 MHz	533 MHz	DDR3-1600	15-17 W	May 20, 2014	RE225FECH23JA
RX-425BB		4	2.5 GHz	3.4 GHz	4 MB			R6 (6 CUs)	384:24:8	576 MHz	654 MHz	DDR3-1866	30-35 W	May 20, 2014	RE425BDGH44JA
RX-427BB			2.7 GHz	3.6 GHz				R7 (8 CUs)	512:32:8	600 MHz	686 MHz	DDR3-2133	30-35 W	May 20, 2014	RE427BDGH44JA
RX-427NB			2.7 GHz	3.6 GHz				N/A		N/A	N/A	DDR3-2133	30-35 W	May 20, 2014	RE427NDGH44JA

"Merlin Falcon" (2015, 28 nm, SoC)

• Up to 4 "Excavator" x86 cores ^[44]
• 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 number	Stepping	CPU						GPU				Memory support	TDP	Released	Part number
		Cores	Frequency	Turbo	L2 Cache (shared)	Multi	Vcore	Model	Config^2	Frequency	Turbo
RX-216GD		2	1.6 GHz	3.0 GHz	1 MB			R5 (4 CUs)		800 MHz	N/A	DDR3/DDR4-1600	12-15 W	October 21, 2015	RE216GAAY23KA
RX-216TD			1.6 GHz	3.0 GHz				N/A	N/A	N/A	N/A	DDR3/DDR4-1600	12-15 W	October 21, 2015	RE216TAAY23KA
RX-418GD		4	1.8 GHz	3.2 GHz	2 MB			R6 (6 CUs)		800 MHz	N/A	DDR3-2133 DDR4-2400	12-35 W	October 21, 2015	RE418GAAY43KA
RX-421BD			2.1 GHz	3.4 GHz				R7 (8 CUs)		800 MHz	N/A	DDR3-2133 DDR4-2400	12-35 W	October 21, 2015	RE421BAAY43KA
RX-421ND			2.1 GHz	3.4 GHz				N/A	N/A	N/A	N/A	DDR3-2133 DDR4-2400	12-35 W	October 21, 2015	RE421NAAY43KA

Semi-custom processors

As of May 1, 2013, AMD opened the doors of their "semi-custom" business unit.^[45] 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.^[46] AMD has yet to commercially sell an APU with the same number of unified shaders, texture mapping units, and render output units as either its custom PS4 or Xbox One APUs.

• ² Pixel fillrate is calculated as the number of ROPs multiplied by the base core clock speed.
• ³ Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.

Device	CPU			GPU					Memory				Special features
	Cores	Frequency	L2 Cache	Cores (Unified Shaders : Texture Mapping Units : Render Output Units)[47]	Frequency	GFLOPS	Pixel Fillrate (GP/s)^2	Texture Fillrate (GT/s)^3	Amount	Bus Width (bit)	Bus Type	Bandwidth (GB/s)
Sony PS4	dual 4 core modules	1.6 GHz	2 x 2 MB	1152:72:32	800 MHz	1840	25.6	57.6	8 GB	256	GDDR5	176	8 ACEs in the GPU and additional modules
Microsoft Xbox One	dual 4 core modules	1.75 GHz	2 x 2 MB	768:48:16	853 MHz	1310	13.6	40.9	8 GB	256	DDR3	68	2 ACEs in the GPU and 32MB ESRAM 204 GB/s

See also

• AMD Accelerated Processing Unit
• AMD Bulldozer
• Comparison of FCH (Fusion Controller Hub)
• Comparison of AMD graphics processing units
• List of AMD FX microprocessors

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 Mobile “Carrizo” Family of APUs Designed to Deliver Significant Leap in Performance, Energy Efficiency in 2015" (Press release). 2014-11-20. Retrieved 2015-02-16.
2. Thomas De Maesschalck (2013-11-14). "AMD teases Mullins and Beema tablet/convertibles APU". Retrieved 2015-02-24.
3. "How do I connect three or More Monitors to an AMD Radeon™ HD 5000, HD 6000, and HD 7000 Series Graphics Card?". AMD. Retrieved 2014-12-08.
4. "A technical look at AMD’s Kaveri architecture". Semi Accurate. Retrieved 6 July 2014.
5. Airlie, David (2009-11-26). "DisplayPort supported by KMS driver mainlined into Linux kernel 2.6.33". Retrieved 2016-01-16.
6. Airlie, David (2009-11-26). "DisplayPort supported by KMS driver mainlined into Linux kernel 2.6.33". Retrieved 2014-07-02.
7. "Radeon feature matrix". freedesktop.org. Retrieved 2016-01-10.
8. Deucher, Alexander (2015-09-16). "XDC2015: AMDGPU" (PDF). Retrieved 2016-01-16.
9. Theo Valich (28 May 2012). "AMD Comes Clean on Transistor Numbers With FX, Fusion Processors". Retrieved 23 August 2013.
10. Anand Lal Shimpi (27 September 2012). "AMD A10-5800K & A8-5600K Review: Trinity on the Desktop, Part 1". Retrieved 23 August 2013.
11. "AMD launches A-Series and the first 32nm Athlon II X4 CPUs". Retrieved 2013-11-10.
12. "Trinity Improvements Include Updated Piledriver Cores and VLIW4 GPUs". Retrieved 2013-11-10.
13. "AMD Trinity On The Desktop: A10, A8, And A6 Get Benchmarked! - Trinity: Coming Soon To A Desktop Near You". Retrieved 2013-11-10.
14. "AMD Trinity for Desktops. Part 1: Graphics Core". X-bit labs. 2012-09-27. Archived from the original on October 11, 2012.
15. "Review: AMD A10-5800K Dual Graphics evaluation - CPU". Retrieved 2013-11-10.
16. "The AMD A8-3850 Review: Llano on the Desktop". Retrieved 2013-11-10.
17. "Product Search Results - Bottom Line Telecommunications". Bottom Line Telecommunications Corporation. Retrieved 2013-11-10.
18. "AMD Sempron CPU". Retrieved 2015-03-02.
19. "AMD Athlon Processors". Retrieved 2015-03-02.
20. "AMD stellt A10-6790K offiziell vor". Retrieved 2013-11-10.
21. btarunr (23 March 2014). "AMD FX-670K CPU Shows Up in the Wild". TechPowerUp.
22. Anton Shilov (2013-05-30). "AMD’s Next-Gen "Kaveri" APUs Will Require New Mainboards". Retrieved 2014-12-17.
23. Hassan Mujtaba. "AMD Kaveri APU Architecture Detailed". Retrieved 2015-03-15.
24. "A technical look at AMD’s Kaveri architecture". SemiAccurate. 2014-01-15.
25. "AMD to add ARM processors to boost chip security". June 14, 2012. Retrieved September 3, 2013.
26. "AMD and ARM Fusion redefine beyond x86". Retrieved 2013-11-10.
27. "AMD A10-7850K Graphics Performance". Retrieved April 2, 2014.
28. "AMD A8-7600 Kaveri APU review - The Embedded GPU - HSA & hUMA". 2014-01-14.
29. Gennadiy Shvets (18 October 2014). "HP offers desktop PCs with AMD FX-770K Kaveri processor". OFweek.
30. Hassan Mujtaba (6 January 2016). "AMD Carrizo Based Athlon X4 845 and Athlon X4 835 Desktop CPUs Leaked - Feature 28nm Excavator Cores". WCCFtech.
31. "AMD intros 35W Richland mobile APUs". Retrieved 2013-11-10.
32. Poeter, Damon. (2013-03-12) AMD Bakes New Interface Capabilities Into Richland APUs | News & Opinion
33. http://www.technationnews.com/2013/11/24/amd-kaveri-apu-with-steamrollerb-core-features-20-cpu-and-30-gpu-performance-uplift-over-richland-platform-details-unveiled/
34. AMD Brazos Platform Preview
35. http://h10032.www1.hp.com/ctg/Manual/c04655538
36. "HP ProDesk 405 G2 Microtower-PC". Retrieved 2015-02-24.
37. http://www.anandtech.com/show/9246/amds-carrizo-l-apus-unveiled-12-25w-quad-core-puma
38. AMD Delivers the World’s First and Only APU for Embedded Systems
40. "AMD Embedded G-Series System-on-Chip (SOC)" (PDF). AMD. Retrieved 2013-11-10.
41. http://www.amd.com/Documents/I-Family-Product-Brief.pdf
42. http://www.amd.com/Documents/J-Family-Product-Brief.pdf
43. http://www.amd.com/Documents/2nd_Gen_Rseries_Product_Brief.pdf
44. http://www.amd.com/Documents/merlin-falcon-product-brief.pdf
45. "AMD Establishes Semi-Custom Business Unit to Create Tailored Products with Customer-Specific IP". Retrieved 2013-11-10.
46. "Three for three: How AMD won the war for the heart of next-gen consoles". Retrieved 2013-11-10.
47. "PlayStation 4 Xbox One Comparison Chart". Vgleaks. Retrieved 24 July 2014.

External links

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