List of Intel graphics processing units

This article contains information about Intel's GPUs (see Intel Graphics Technology) and motherboard graphics chipsets in table form. In 1982, Intel licensed the NEC μPD7220 and announced it as the Intel 82720 Graphics Display Controller.^[1][2]

The Intel Graphics badge

Gen1

Main article: Intel740

Intel's first generation GPUs:

Graphics	Launch	Market	Chipset	Code name	Device ID[3]	RAMDAC clock (MHz)	Pixel pipelines	Shader model (vertex/pixel)	API support			Memory bandwidth (GB/s)	DVMT (MB)	Hardware acceleration
									Direct3D	OpenGL	OpenCL			MPEG-2	VC-1	AVC
i740	1998	Desktop	stand-alone	Auburn	7800	220	1	3.0 (SW) / No	5.0	1.1	No	0.8	2–8	Optional external MPEG-2 decoder via Video Module Interface	No	No
i752	1999			Portola	1240	250			6.0 (full) 8.0 (some features, no hardware shaders)			0.8(PC100)–1.067(PC133) 1.067(AGP 4× for AIMM)	8–16	MC
3D graphics with Direct AGP			810	Whitney	7121	230							32
			810-DC100		7123
			810E 810E2		7125
	2000		815 815E 8925G 815EG	Solano	1132				6.0 (full) 9.0 (some features, no hardware shaders)

Gen2

Intel marketed its second generation using the brand Extreme Graphics. These chips added support for texture combiners allowing support for OpenGL 1.3.

Graphics	Launch	Market	Chipset	Code name	Device ID[3]	Core render clock (MHz)	Pixel pipelines	Shader model (vertex/pixel)	API support[4]			Memory bandwidth (GB/s)	DVMT (MB)	Hardware acceleration
									Direct3D	OpenGL	OpenCL			MPEG-2	VC-1	AVC
Extreme Graphics	2002	Desktop	845G 845GE 845GL 845GV	Brookdale	2562	200	2	3.0 (SW) / No	6.0 (full) 9.0 (some features, no hardware shaders)	1.3 ES 1.1Linux	No	2.1	64	MC	No	No
	2001	Mobile	830M 830MG	Almador	3577	166[5]						1
Extreme Graphics 2	2003	Desktop	865G 865GV	Springdale	2572	266						6.4
		Mobile	852GM 852GME 852GMV	Montara	3582	133–266						2.1–2.7
			854		358E
			855GM 855GME		3582

Gen3

Main article: Intel GMA § Gen3

Intel's first DirectX 9 GPUs with hardware Pixel Shader 2.0 support.

Graphics	Launch	Market	Chipset		Device ID[3]	Pixel pipelines	Clock rate (MHz)	Memory		API support[4]				Hardware acceleration
			Code name	Name				DVMT (MB)	Bandwidth (GB/s)	Shader model (vertex/pixel)	Direct3D	OpenGL	OpenCL	MPEG-2	VC-1	AVC
GMA 900	2004	Desktop	Grantsdale	910GL	2582 258A	4	333	128	3.2	3.0 (SW) / 2.0	6.0 (full) 9.0 (partial; no WDDM nor Aero support)	1.4 ES 2.0Linux	MC[6][7]	No	No
				915GL
				915GV					8.5
				915G
	2005	Mobile	Alviso	Mobile 915 Family	2592		133–333
GMA 950		Desktop	Lakeport	945GZ	2772		400	256[7][8]			9.0c FL9_1					No
				945GC					10.7
				945G
	2006	Mobile	Calistoga	Mobile 945 Family	27A2 27AE		166–400[9]
GMA 3100	2007	Desktop	Bearlake	Q33	29D2		400[10][11]		12.8
				Q35	29B2
				G31	29C2
				G33					12.8 (DDR2) 17 (DDR3)				Variable-Length Decoding (VLD) + iDCT + MC (Full)[7]
GMA 3150	2010	Nettop	Pineview	Atom D4xx Atom D5xx	A001	2		384	6.4
		Netbook		Atom N4xx Atom N5xx	A011		200		5.3

Gen4

Main article: Intel GMA § Gen4

The last generation of motherboard integrated graphics. Full hardware DirectX 10 support starting with GMA X3500.

• Each EU has a 128-bit wide FPU that natively executes four 32-bit operations per clock cycle.

Graphics	Launch	Market	Code name	Chipset	Device ID[3]	Core render clock (MHz)	Execution units	Shader model (vertex/pixel)	API support[12]			Memory bandwidth (GB/s)	DVMT (MB)	Hardware acceleration
									Direct3D	OpenGL	OpenCL			MPEG-2	VC-1	AVC
GMA 3000	2006	Desktop	Lakeport	946GZ	2972	667[13][14]	8[13][15]	3.0 (SW) / 2.0	9.0c FL9_1	1.4[16] ES 2.0Linux	No	10.6	256	MC[7]	No	No
			Broadwater	Q963	2992
				Q965								12.8
GMA X3000				G965	29A2			3.0		1.5[16] ES 2.0Linux			384	Full[7]	MC + (LF − WMV9 only)
GMA X3500	2007		Bearlake	G35	2982			4.0	10.0 FL10_0	2.1 ES 2.0Linux					MC + LF
GMA X3100		Mobile	Crestline	GL960	2A02 2A12	400[17]						8.5			MC + (LF − WMV9 only)
				GLE960
				GM965		500[17]						10.7
				GME965
GMA 4500	2008	Desktop	Eaglelake	B43	2E42 2E92	533	10					12.8 (DDR2) 17 (DDR3)[18]	1720		MC + LF	MC + LF
				Q43	2E12
				Q45
GMA X4500				G41	2E32	800
				G43	2E22
GMA X4500HD				G45											Full	Full
GMA 4500MHD		Mobile	Cantiga	GL40	2A42	400[19]
				GS40
				GM45		533[19]
				GS45
				GM47		640

Gen5

Main article: Intel Graphics Technology § Gen5

• Integrated graphics chip moved from motherboard into the processor.
• Improved gaming performance
• Can access CPU's cache
• Each EU has a 128-bit wide FPU that natively executes eight 16-bit or four 32-bit operations per clock cycle.^[20]
• Hierarchical-Z compression and fast Z clear^[21]

Specifications of Intel Gen5 graphics processing units^[22][23]

Name	Launch	Market	Processor		Device ID	Execution units	Core clock (MHz)	Memory		API support			Intel Clear Video HD
			Code name	Model				DVMT (MB)	Bandwidth (GB/s)	Direct3D	OpenGL	OpenCL
HD Graphics	2010	Desktop	Ironlake (Clarkdale)	Celeron G1101	0042	12	533	1720	17	10.1 FL10_0	2.1 ES 2.0Linux	No	No
				Core i3-5x0			733		21.3				Yes
				Core i5-6x0
				Core i5-655K
				Core i5-661			900
		Laptop	Ironlake (Arrandale)	Celeron U3xxx	0046		166–500		12.8				No
				Pentium U5xxx
				Core i3-3x0UM									Yes
				Core i5-5x0UM
				Core i7-6x0UE
				Core i7-6x0UM
				Core i7-620LE			266–566		17.1
				Core i7-6x0LM
				Celeron P4xxx			500–667						No
				Pentium P6xxx
				Core i3-330E									Yes
				Core i3-3x0M
				Core i5-4x0M			500–766
				Core i5-520E
				Core i5-5x0M
				Core i7-610E
				Core i7-6x0M

Gen6

Main article: Intel Graphics Technology § Gen6

• Each EU has a 128-bit wide FPU that natively executes eight 16-bit or four 32-bit operations per clock cycle.^[20]
• Double peak performance per clock cycle compared to previous generation due to fused multiply-add instruction.^[20]
• The entire GPU shares a sampler and an ROP.^[20]

Specifications of Intel HD Graphics series^[24]

Graphics	Launch	Market	Processor	Code name	Device id.[3]	Core clock (MHz)	Execution units	API support[12]			Memory bandwidth (GB/s)	DVMT (MB)	QSV
								Direct3D	OpenGL	OpenCL
HD Graphics	2011	Mobile	Celeron B7x0 Celeron 7x7 Celeron 8x7 Celeron B8xx Pentium B9x0 Pentium 9x7	Sandy Bridge	010A	350–1150	6 (GT1)	10.1 11.1Windows 8+ FL10_1	3.1Windows 3.3macOS[25] 3.3Linux ES 3.0Linux	No	21.3	1720	No
		Desktop	Celeron G4x0 Celeron G5x0 Celeron G530T Pentium G6xx Pentium G6x0T Pentium G8x0			650–1100
HD Graphics 2000		Desktop	Core i3-2102 Core i3-21x0 Core i3-21x0T Core i5-2xx0 Core i5-2x00S Core i5-2xx0T Core i7-2600 Core i7-2600S		0102	650–1350							Yes
		Workstation	Xeon E3-1260L
HD Graphics 3000		Mobile	Core i3-23x0E Core i3-23xxM Core i5-251xE Core i5-2xxxM Core i7-2xxxM Core i7-2xxxQM Core i7-271xQE Core i7-29x0XM		0116 0126	650–1300	12 (GT2)
		Desktop	Core i3-21x5 Core i5-2405S Core i5-2500K Core i7-2x00K		0112 0122	850–1350
HD Graphics P3000		Workstation	Xeon E3-12x5			850–1350

Gen7

Main article: Intel Graphics Technology § Gen7

• ¹ FP32 ALUs : EUs : Subslices
• Each EU contains 2 × 128-bit FPUs and has double peak performance per clock cycle compared to previous generation. One supports FP32 and FP64, and the other supports only FP32. Since the throughput of FP64 instructions are 2 cycles, the FP64 FLOPS is a quarter of the FP32 FLOPS. Only one of the FPUs supports 32-bit integer instructions.
• Each Subslice contains 6 or 8 (or 10 in Haswell GPUs) EUs and a sampler, and has 64 KB shared memory.

Specifications of Intel HD Graphics series^{[26][27][28][29][30][31][32]}

Graphics	Launch	Market	Processor	Code name	Device ID[3]	Core clock (MHz)	Core config1	API support[12][33][34][35]				Memory bandwidth (GB/s)	DVMT (MB)	QSV
								Direct3D	OpenGL[25]	OpenCL	Vulkan
HD Graphics	2012	Desktop	Celeron G16x0 Celeron G1610T Pentium G2xx0 Pentium G2xx0T	Ivy Bridge	015A	650–1050	48:6:1[36] (GT1)	11.1 FL11_0	4.0Windows 4.1macOS 4.2Linux ES 3.0Linux	1.2	1.0Linux	25.6	1720	No
		Mobile	Celeron 10x0M Celeron 10x7U Pentium 2117U Pentium 20x0M			350–1100
HD Graphics 2500[37]		Workstation	Xeon E3-1265LV2		0152	650–1150								Yes
		Desktop	Core i3-32x0 Core i3-32x0T Core i5-3xx0 Core i5-3xx0S Core i5-3xx0T
HD Graphics 4000[29]			Core i3-3225 Core i3-3245 Core i5-3475S Core i5-3570K Core i7-3770 Core i7-3770x		0162		128:16:2 (GT2)
		Mobile	Core i3-3110M		0166	650–1000
			Core i3-3120M Core i5-3210M			650–1100
			Core i3-3120ME			650–900
			Core i3-3217U Core i5-3317U			350–1050
			Core i3-3217UE			350–900
			Core i3-3229Y Core i5-3339Y Core i5-3439Y			350–850
			Core i5-33x0M			650–1200
			Core i5-3337U			350–1100
			Core i5-3427U			350–1150
			Core i5-3610ME			650–950
			Core i7-3520M Core i7-3xx7U Core i7-3xxxQM Core i7-3920XM			350–1300
HD Graphics P4000[38]		Workstation	Xeon E3-12x5V2		016A	650–1250

Gen7.5

Main article: Intel Graphics Technology § Gen7.5

• ¹ FP32 ALUs : EUs : Subslices
• Each EU contains 2 × 128-bit FPUs and has double peak performance per clock cycle compared to previous generation. One supports FP32 and FP64, and the other supports only FP32. Since the throughput of FP64 instructions are 2 cycles, the FP64 FLOPS is a quarter of the FP32 FLOPS. Only one of the FPUs supports 32-bit integer instructions.
• Each Subslice contains 6 or 8 (or 10 in Haswell GPUs) EUs and a sampler, and has 64 KB shared memory.

Graphics	Launch	Market	Processor	Code name	Device ID[3]	Core clock (MHz)	Core config1	API support[12][33][34][35]				Memory bandwidth (GB/s)	DVMT (MB)	QSV
								Direct3D	OpenGL[25]	OpenCL	Vulkan
HD Graphics	2013	Tablet	Atom Z3735D Atom Z3735E Atom Z3735F Atom Z3735G Atom Z3736F Atom Z3736G	Valleyview (Bay Trail)	0F30 0F31 0F32 0F33 0155 0157	311-646	32:4:1[39]	11[40]	4.0 ES 2.0/1.1Linux[41]	1.2	1.0Linux	10.7	2048
			Atom Z3680			311-667						8.5
			Atom Z3740 Atom Z3770									17.1
			Atom Z3680D Atom Z3740D Atom Z3770D			313-688						10.7
			Atom Z3745 Atom Z3775 Atom Z3795			311-778						17.1
			Atom Z3745D Atom Z3775D			311-792						10.7
			Atom Z3785			313-833						21.3
		Laptop	Celeron N2805			313-667		11.2	4.0Windows 4.2Linux ES 3.0Linux	1.2		8.5
			Celeron N2807			313-750						10.7
			Celeron N2830 Pentium N3510									21.3
			Celeron N2806			313-756						8.5
			Celeron N2810 Celeron N2815 Celeron N2820 Celeron N2910									17.1
			Celeron N2808			311-792						10.7
			Celeron N2840									21.3
			Celeron N2920			313-844						17.1
			Celeron N2930 Celeron N2940 Pentium N3520			313-854						21.3
			Pentium N3530 Pentium N3540			313-896
		Embedded	Atom E3815			400-400						8.5
			Atom E3825			533-533
			Atom E3826			533-667						17.1
			Atom E3827 Atom E3845			542-792						21.3
		Desktop	Celeron J1750			688-750
			Celeron J1800 Celeron J1850			688-792
			Celeron J1900 Pentium J2850			688-854
			Pentium J2900			688-896
		Mobile	Pentium A1020
HD Graphics[42]	2013	Desktop	Pentium G3xxx	Haswell	0402 0406 040A 040B 040E ULT: 0A02 0A06 0A0A 0A0B 0A0E	350–1150	80:10:1[43] (GT1)	12[44] FL11_1	4.3Windows 4.1macOS 4.6Linux[45] ES 3.2Linux[46]	1.2	1.0Linux	25.6	2048
			Pentium G3xxxT			200–1100
			Celeron G18xx			350-1050
			Celeron G18xxT			200-1050
		Mobile	Celeron 2950M Pentium 3550M			400–1100
			Celeron 29xxU Pentium 35xxU			200–1000
			Celeron 29xxY Pentium 35xxY			200–850
HD Graphics 4200		ULT Mobile	Core i3-40xxY Core i5-4xxxY Core i7-4610Y		0412 0416 041A 041B 041E ULT: 0A12 0A16 0A1A 0A1B 0A1E	200–850	160:20:2 (GT2)							Yes
HD Graphics 4400		Desktop	Core i3-4130 Core i3-4150 Core i3-4160 Core i3-4170			350–1150
			Core i3-4130T Core i3-4150T Core i3-4160T Core i3-4170T			200–1150
		Mobile	Core i3-4005U Core i3-4025U			200–950
			Core i3-4010U Core i3-4100U Core i5-4200U Core i3-4030U Core i3-4120U			200–1000
			Core i5-4300U Core i7-4500U Core i7-4600U			200–1100
HD Graphics 4600		Desktop	Core i3-4330 Core i3-4340 Core i5-4570 Core i5-4570S Core i5-4590 Core i5-4590S Core i5-4590T			350-1150
			Core i3-4330T Core i5-4570T			200-1150
			Core i5-4430 Core i5-4430S Core i5-4440 Core i5-4440S			350–1100
			Core i5-4670 Core i5-4670K Core i5-4670S Core i5-4670T Core i5-4690 Core i5-4690K Core i5-4690S Core i5-4690T Core i7-4765T Core i7-4770 Core i7-4770S Core i7-4770T Core i7-4771 Core i7-4790			350–1200
			Core i7-4770K Core i7-4790K			350–1250
		Mobile	Core i3-4xxxE Core i5-4402E			400–900
			Core i3-4xxxM			400–1100
			Core i5-4200M Core i5-4200H Core i7-47xxMQ Core i7-4702HQ			400–1150
			Core i5-43xxM			400–1250
			Core i5-4400E Core i7-4700EQ			400–1000
			Core i7-4700HQ			400–1200
			Core i7-4xxxM Core i7-4800MQ Core i7-4900MQ			400–1300
			Core i7-4930MX			400–1350
HD Graphics P4600		Workstation	Xeon E3-1225 v3 Xeon E3-1226 v3 Xeon E3-1245 v3 Xeon E3-1246 v3			350–1200
			Xeon E3-1275 v3 Xeon E3-1276 v3			350–1250
HD Graphics P4700		Workstation	Xeon E3-1285L v3 Xeon E3-1286L v3			350–1250
			Xeon E3-1285 v3 Xeon E3-1286 v3			350–1300
HD Graphics 5000		ULT Mobile	Core i5-4250U		0422 0426 042A 042B 042E ULT: 0A22 0A26 0A2A 0A2B 0A2E	200–1000	320:40:4 (GT3)
			Core i5-4350U Core i7-4550U Core i7-4650U			200–1100
Iris Graphics 5100			Core i3-4158U Core i5-4258U			200–1100
			Core i5-4288U Core i7-4558U			200–1200
Iris Pro Graphics 5200		Desktop	Core i5-4570R		0D22 0D26 0D2A 0D2B 0D2E	200–1150	320:40:4 + eDRAM (GT3e)
			Core i5-4670R Core i7-4770R			200–1300
		Mobile	Core i7-4750HQ Core i7-4850HQ			200–1200
			Core i7-49xxHQ			200–1300

Gen8

Main article: Intel Graphics Technology § Gen8

• ¹ FP32 ALUs : EUs : Subslices
• Each EU contains 2 x 128-bit FPUs. One supports 32-bit and 64-bit integer, FP16, FP32, FP64, and transcendental math functions, and the other supports only 32-bit and 64-bit integer, FP16 and FP32. Thus the FP16 (or 16-bit integer) FLOPS is twice the FP32 (or 32-bit integer) FLOPS. Since the throughput of FP64 instructions is one per 2 cycles, the FP64 FLOPS is a quarter of the FP32 FLOPS.
• Each Subslice contains 8 EUs and a sampler (4 tex/clk^[47]), and has 64 KB shared memory.
• Intel Quick Sync Video
• For Windows 10, the total system memory that is available for graphics use is half the system memory. For Windows 8, it is up to 3840 MB. On Windows 7, it is up to about 1.7 GB through DVMT.

Specifications of Intel HD Graphics series^[48][49]

Graphics	Launch	Market	Processor	Code name	Device ID[3]	Clock rate (MHz)	Core config1	API support[12][33][50][51][52]				eDRAM (MB)	Memory bandwidth (GB/s)
								Direct3D	OpenGL	OpenCL	Vulkan
HD Graphics	2015	Ultramobile	Atom x5-Z8300	Cherryview Braswell (Gen8LP)	22B0 22B1 22B2 22B3	200-500	96:12:2	11.2	4.3Windows 4.6Linux ES 3.2Linux	2.0Windows 1.2Linux	1.1Linux	-	12.8
			Atom x5-Z8500			200-600							25.6
			Atom x5-E8000 Celeron N3000 Celeron N3050			320-600
			Celeron N3150			320-640
			Atom x7-Z8700			200-600	128:16:2
			Pentium N3700			400-700
HD Graphics 400	2016		Atom x5-Z8350[53]			200-500	96:12:2
			Celeron N3010 Celeron N3060			320-600
			Celeron N3160			320-640
			Celeron J3060 Celeron J3160			320-700
HD Graphics 405			Pentium N3710			400-700	128:16:2
			Pentium J3710			400-740	144:18:2
HD Graphics	2015	Mobile	Celeron 3205U Celeron 3755U Pentium 3805U	Broadwell (Gen8)	1606	100–800	96:12:2 (GT1)	12 FL11_1	4.4Windows 4.1macOS 4.6Linux ES 3.2Linux	2.0Windows 1.2macOS 2.1Linux	1.1Linux	-	25.6
			Celeron 3215U Celeron 3765U Pentium 3825U			300–850
HD Graphics 5300	2014	Ultramobile	Core M-5Y10 Core M-5Y10a		161E	100–800	192:24:3 (GT2)
			Core M-5Y10c			300–800
			Core M-5Y70			100–850
			Core M-5Y31			300–850
			Core M-5Y51 Core M-5Y71			300–900
HD Graphics 5500	2015	Mobile	Core i3-5005U Core i3-5015U		1616	300–850	184:23:3 (GT2)
			Core i3-5010U Core i3-5020U			300–900
			Core i5-5200U Core i5-5300U				192:24:3 (GT2)
			Core i7-5500U Core i7-5600U			300–950
HD Graphics 5600		Mobile	Core i7-5700EQ		1612	300–1000
			Core i7-5700HQ			300–1050
HD Graphics P5700		Mobile	Xeon E3-1258L v4		?	700-1000
HD Graphics 6000		Mobile	Core i5-5250U		1626	300–950	384:48:6 (GT3)
			Core i5-5350U Core i7-5550U Core i7-5650U			300–1000
Iris Graphics 6100		Mobile	Core i3-5157U		162B	300–1000
			Core i5-5257U			300–1050
			Core i5-5287U Core i7-5557U			300–1100
Iris Pro Graphics 6200		Desktop	Core i5-5575R		1622	300–1050						128
			Core i5-5675C Core i5-5675R			300–1100
			Core i7-5775C Core i7-5775R			300–1150
		Mobile	Core i7-5850EQ			300–1000
			Core i5-5350H			300–1050
			Core i7-5750HQ Core i7-5850HQ			300–1100
			Core i7-5950HQ			300–1150
Iris Pro Graphics P6300		Workstation	Xeon E3-1278L v4		162A	800–1000
			Xeon E3-1265L v4			300–1050
			Xeon E3-1285 v4 Xeon E3-1285L v4			300–1150

Gen9

Main article: Intel Graphics Technology § Gen9

• ¹ FP32 ALUs : EUs : Subslices
• Each EU contains 2 x 128-bit FPUs. One supports 32-bit and 64-bit integer, FP16, FP32, FP64, and transcendental math functions, and the other supports only 32-bit and 64-bit integer, FP16 and FP32. Thus the FP16 (or 16-bit integer) FLOPS is twice the FP32 (or 32-bit integer) FLOPS. Since the throughput of FP64 instructions are 2 cycles, the FP64 FLOPS is a quarter (eighth in Apollo Lake) of the FP32 FLOPS.
• Each Subslice contains 8 EUs (two of which are disabled in GT1) and a sampler (4 tex/clk), and has 64 KB shared memory.
• Intel Quick Sync Video
• For Windows 10, the total system memory that is available for graphics use is half the system memory. For Windows 8, it is up to 3840 MB. On Windows 7, it is up to about 1.7 GB through DVMT.
• WDDM 2.2 support with Windows Mixed Reality begins with KabyLake-based GPUs.^[54]

Specifications of Gen9 Intel graphics processing units^{[55][56][57][58][59][60][61][62][63]}

Name	Release year	Market	Processor	Code name	Device ID	Clock rate		Core config1	API support[64][12][33][51][52]				eDRAM (MB)	Memory bandwidth (GB/s)
						Min (MHz)	Max (MHz)		Direct3D	OpenGL	OpenCL	Vulkan
HD Graphics 500	2016	Mobile/ Embedded	Atom x5-E3930	Apollo Lake (Gen9LP)	5A85	400	550	96:12:2	12	4.6Windows 4.6Linux ES 3.2Linux	3.0Windows 3.0Linux	1.3Windows 1.3Linux	-	68.2
			Atom x5-E3940				600
		Mobile	Celeron N3350			200	650							38.4
			Celeron N3450				700
		Desktop	Celeron J3355			250	700
			Celeron J3455				750
HD Graphics 505		Mobile/ Embedded	Atom x7-E3950		5A84	500	650	144:18:3						76.8
		Mobile	Pentium N4200			200	750							38.4
		Desktop	Pentium J4205			250	800
HD Graphics 510	2015	Mobile	Celeron 3855U Celeron 3955U	Skylake (Gen9)	1906	300	900	96:12:2 (GT1)	12 FL12_1	4.6Windows 4.1macOS 4.6Linux ES 3.2Linux	3.0Windows 1.2macOS 3.0Linux	1.3Windows 1.4Linux	-	34.1
			Pentium 4405U				950
		Desktop	Celeron G3900TE Celeron G3900E Celeron G3900T Celeron G3900 Celeron G3902E Celeron G3920 Pentium G4400TE Pentium G4400T Core i5-6402P		1902	350
			Pentium G4400				1000
			Core i3-6098P				1050
HD Graphics 515		Mobile	Pentium 4405Y		191E	300	800	192:24:3 (GT2)						29.8
			Core m3-6Y30				850
			Core m5-6Y54 Core m5-6Y57				900
			Core m7-6Y75				1000
HD Graphics 520		Mobile	Core i3-6006U		1916		900							34.1
			Core i3-6100U Core i5-6200U Core i5-6300U				1000
			Core i7-6500U Core i7-6600U				1050
HD Graphics 530		Mobile	Core i3-6100H		191B	350	900
			Core i3-6100E Core i3-6102E Core i5-6300HQ Core i5-6440HQ				950
			Core i5-6440EQ Core i5-6442EQ Core i7-6820EQ Core i7-6822EQ				1000
			Core i7-6700HQ Core i7-6820HK Core i7-6820HQ Core i7-6920HQ				1050
		Desktop	Pentium G4500T Core i3-6100T Core i3-6300T Core i5-6400T Core i5-6400		1912		950
			Core i3-6100TE Core i5-6500TE Core i7-6700TE Core i7-6700T				1000
			Pentium G4500 Pentium G4520 Core i3-6100 Core i5-6500				1050
			Core i5-6500T Core i5-6600T Core i7-6700				1100
			Core i3-6300 Core i3-6320 Core i5-6600 Core i5-6600K Core i7-6700K				1150
HD Graphics P530		Workstation	Xeon E3-1268L v5		191D		1000
		Mobile Workstation	Xeon E3-1505L v5
			Xeon E3-1505M v5 Xeon E3-1535M v5				1050
		Workstation	Xeon E3-1225 v5			400	1150
			Xeon E3-1235L v5				?
			Xeon E3-1245 v5 Xeon E3-1275 v5				1150
Iris Graphics 540		Mobile	Core i5-6260U		1926	300	950	384:48:6 (GT3)					64
			Core i5-6360U				1000
			Core i7-6560U Core i7-6650U Core i7-6660U				1050
Iris Graphics 550		Mobile	Core i3-6157U Core i3-6167U		1927		1000
			Core i5-6267U				1050
			Core i5-6287U Core i7-6567U				1100
Iris Pro Graphics P555	2016	Workstation	Xeon E3-1558L v5		192D	650	1000						128
Iris Pro Graphics 580		Mobile	Core i5-6350HQ		193B	350	900	576:72:9 (GT4)
			Core i7-6770HQ				950
			Core i7-6870HQ				1000
			Core i7-6970HQ				1050
		Desktop	Core i5-6585R				1100
			Core i5-6685R Core i7-6785R				1150
Iris Pro Graphics P580		Workstation	Xeon E3-1578L v5		193D	700	1000
		Mobile Workstation	Xeon E3-1515M v5			350
			Xeon E3-1545M v5				1050
			Xeon E3-1575M v5				1100
		Workstation	Xeon E3-1565L v5		193A		1050
			Xeon E3-1585L v5 Xeon E3-1585 v5				1150
UHD Graphics 600	2017	Mobile	Celeron N4000 Celeron N4020	Gemini Lake Gemini Lake Refresh (Gen9LP)	3185	200	650	96:12:2	12	4.6Windows 4.6Linux ES 3.2Linux	3.0Windows 3.0Linux	1.3Windows 1.3Linux	-	38.4
			Celeron N4100 Celeron N4120				700
		Desktop	Celeron J4005 Celeron J4025			250	700
			Celeron J4105 Celeron J4125				750
UHD Graphics 605		Mobile	Pentium Silver N5000 Pentium Silver N5030		3184	200	750	144:18:3						38.4
		Desktop	Pentium Silver J5005 Pentium Silver J5040			250	800
HD Graphics 610	2017	Mobile	Celeron 3865U Celeron 3965U	Kaby Lake (Gen9p5)	5906	300	900	96:12:2 (GT1)	12 FL12_1	4.6Windows 4.1macOS 4.6Linux ES 3.2Linux	3.0Windows 1.2macOS 3.0Linux	1.3Windows 1.4Linux	-	34.1
			Pentium 4415U				950
		Desktop	Celeron G3930TE		5902	350	950
			Celeron G3930E Celeron G3930T				1000
			Celeron G3930 Celeron G3950				1050
			Pentium G4560T Pentium G4560											38.4
			Core i3-7101TE Core i3-7101E				1100
HD Graphics 615		Mobile	Celeron 3965Y Pentium 4410Y Pentium 4415Y		591E	300	850	192:24:3 (GT2)						29.8
			Pentium Gold 6500Y Core m3-7Y30 Core m3-7Y32 Core m3-8100Y				900
			Core i5-7Y54 Core i5-7Y57 Core m3-8300Y				950
			Core i7-7Y75 Core m3-8500Y				1050
HD Graphics 620			Core i3-7020U Core i3-7100U Core i3-7130U Core i5-7200U		5916		1000							34.1
			Core i7-7500U				1050
			Core i5-7300U				1100
			Core i7-7600U				1150
UHD Graphics 620			Core i3-8130U		5917		1000							38.4
			Core i5-8250U Core i5-8350U				1100
			Core i7-8550U Core i7-8650U				1150
HD Graphics 630		Desktop	Core i5-7400T Core i5-7400		5912	350	1000							38.4
			Pentium G4600T				1050
			Pentium G4600 Pentium G4620 Core i3-7100T Core i3-7100 Core i3-7300T Core i5-7500T Core i5-7500 Core i5-7600T				1100
			Core i3-7300 Core i3-7320 Core i3-7350K Core i5-7600 Core i5-7600K Core i7-7700T Core i7-7700 Core i7-7700K				1150
		Mobile	Core i3-7100E Core i3-7100H Core i3-7102E		591B		950
			Core i5-7300HQ Core i5-7440EQ Core i5-7440HQ Core i5-7442EQ Core i7-7820EQ				1000
			Core i7-7700HQ Core i7-7820HK Core i7-7820HQ Core i7-7920HQ				1100
			Core i5-8305G		?		1000
			Core i7-8705G Core i7-8706G Core i7-8709G Core i7-8809G				1100
HD Graphics P630		Mobile Workstation	Xeon E3-1501L v6 Xeon E3-1501M v6 Xeon E3-1505L v6		591D		1000
			Xeon E3-1505M v6 Xeon E3-1535M v6				1100
		Workstation	Xeon E3-1225 v6 Xeon E3-1245 v6 Xeon E3-1275 v6 Xeon E3-1285 v6				1150
Iris Plus Graphics 640		Mobile	Core i5-7260U		5926	300	950	384:48:6 (GT3)					64	34.1
			Core i5-7360U				1000
			Core i7-7560U				1050
			Core i7-7660U				1100
Iris Plus Graphics 650			Core i3-7167U		5927		1000
			Core i5-7267U				1050
			Core i5-7287U				1100
			Core i7-7567U				1150
UHD Graphics 610	2018	Desktop	Celeron G4900T	Coffee Lake	3E93	350	1000	96:12:2 (GT1)	12	4.6Windows 4.6Linux ES 3.2Linux	3.0Windows 3.0Linux	1.3Windows 1.4Linux	-	38.4
			Celeron G4900 Celeron G4920 Celeron G4930 Pentium Gold G5400T Pentium Gold G5400				1050
UHD Graphics 630		Desktop	Pentium Gold G5500T		3E91		1050	184:23:3 (GT2)						38.4
			Pentium Gold G5500 Pentium Gold G5600 Core i3-8100T Core i3-8100 Core i3-8300T				1100
			Core i3-8300 Core i3-8350K				1150
			Core i5-8400T Core i5-8400 Core i5+8400		3E92		1050	192:24:3 (GT2)						42.7
			Core i5-8500T Core i5-8500 Core i5+8500				1100
			Core i5-8600T Core i5-8600 Core i5-8600K Core i5-9600K				1150
			Core i7-8700T Core i7-8700 Core i7+8700 Core i7-8700K Core i7-8086K Core i7-9700K Core i9-9900K Core i9-9900KS				1200
		Mobile	Core i5-8300H		3E9B		1000
			Core i5-8400B				1050
			Core i5-8400H Core i7-8750H				1100
			Core i5-8500B Core i7-8850H Core i7-9750H Core i7-9850H				1150
			Core i7-8700B Core i9-8950HK				1200
		Mobile Workstation	Xeon E-2176M Xeon E-2186M
Iris Plus Graphics 645		Mobile	Core i5-8257U		3EA6	300	1050	384:48:6 (GT3)					128	38.4
			Core i7-8557U				1150
Iris Plus Graphics 655			Core i3-8109U Core i5-8259U		3EA5		1050
			Core i5-8259U				1100
			Core i7-8559U Core i7-8569U				1200

Gen11

Main article: Intel Graphics Technology § Gen11

• ¹ FP32 ALUs : EUs : Subslices
• Each EU contains 2 x 128-bit FPUs. One supports 32-bit and 64-bit integer, FP16, FP32, FP64, and transcendental math functions, and the other supports only 32-bit and 64-bit integer, FP16 and FP32. Thus the FP16 (or 16-bit integer) FLOPS is twice the FP32 (or 32-bit integer) FLOPS. Since the throughput of FP64 instructions are 2 cycles, the FP64 FLOPS is a quarter of the FP32 FLOPS.
• Each Subslice contains 8 EUs and a sampler (4 tex/clk), and has 64 KB shared memory.
• Intel Quick Sync Video
• For Windows 10, the total system memory that is available for graphics use is half the system memory.
• No eDRAM.

Specifications of Intel HD Graphics series^[55][56][65]

Name	Release year	Market	Processor		Device ID	Core config1	Clock rate		API support[66][12][33][51][52]				Memory bandwidth (GB/s)
			Code name	Model			Min (MHz)	Max (MHz)	Direct3D	OpenGL	OpenCL	Vulkan
UHD Graphics	2019	Mobile	Ice Lake	Core i3-1000G1 Core i3-1005G1	8A58	256:32:4 (GT1)	300	900	12 FL12_1	4.6Windows 4.6Linux ES 3.2Linux	3.0Windows 3.0Linux	1.4Windows 1.4Linux	59.7
				Core i5-1035G1	8A56			1050
Iris Plus Graphics				Core i3-1000G4	8A5C	384:48:6 (GT1.5)		900
				Core i5-1030G4				1050
				Core i5-1035G4	8A5A
				Core i5-1030G7 Core i5-1030NG7	8A51	512:64:8 (GT2)		1050
				Core i7-1060G7 Core i7-1060NG7				1100
				Core i5-1035G7	8A52			1050
				Core i7-1065G7				1100
				Core i5-1038G7	8A53			1050
				Core i7-1068G7				1100

Gen12

Main article: Intel Graphics Technology § Gen12

Intel Xe is a GPGPU and dGPU product line first released in 2020, in the mobile Tiger Lake line and Rocket Lake line.

• ¹ FP32 ALUs: EUs: Subslices

Name	Release year	Market	Processor		Device ID[67][68][69]	Core config1	Clock rate		API support[70][71][12][33][51][52]				Memory bandwidth (GB/s)
			Code name	Model			Min (MHz)	Max (MHz)	Direct3D	OpenGL	OpenCL	Vulkan
UHD Graphics 730	2020	Desktop	Rocket Lake	Core i5-11400T	4C8B	192:24:3	350	1200	12 FL12_1	4.6Windows 4.6Linux ES 3.2Linux	3.0Windows 3.0Linux	1.4Windows 1.4Linux	51.2
				Core i5-11400				1300
UHD Graphics 750				Core i5-11500T	4C8A	256:32:4		1200
				Core i5-11500 Core i5-11600 Core i5-11600K Core i5-11600T Core i7-11700 Core i7-11700K Core i7-11700T Core i9-11900 Core i9-11900K Core i9-11900T				1300
UHD Graphics		Mobile	Tiger Lake	Core i3-1110G4 Core i3-1120G4	9A78	384:48:6	400	1100					59.7
				Celeron 6305 Pentium Gold 7505 Core i3-1115G4 Core i3-1125G4				1250
Iris Xe Graphics				Core i5-1130G7 Core i5-1140G7	9A40	640:80:6		1100					68.2
				Core i7-1160G7 Core i7-1180G7		768:96:6
				Core i5-1135G7 Core i5-11300H Core i5-1145G7	9A49	640:80:6	400	1300
				Core i7-1165G7		768:96:6		1300
				Core i5-11320H Core i7-1185G7 Core i7-11370H Core i7-11375H				1350
				Core i7-1195G7 Core i7-11390H				1400

Gen12.2

Main article: Intel Graphics Technology § Gen12

Intel Xe is a GPGPU and dGPU product line first released in 2021, in Alder Lake and Raptor Lake line.

• Support up to 4 screens^[72]
• ¹ FP32 ALUs: EUs: Subslices

Name	Release year	Market	Processor		Device ID[67][68][69]	Core config1	Clock rate		API support[70][71][12][33][51][52]				Memory bandwidth (GB/s)
			Code name	Model			Min (MHz)	Max (MHz)	Direct3D	OpenGL	OpenCL	Vulkan
Iris Xe Max[73]	2021	Mobile	DG1		4905	768:96:6	300	1650	12 FL12_1	4.6Windows 4.6Linux ES 3.2Linux	3.0Windows 3.0Linux	1.4Windows 1.4Linux	68.2
Iris Xe Pod		Desktop			4906
GPU SG-18M		Server			4907
Iris Xe Graphics		Desktop			4908
UHD Graphics 710	2021	Desktop	Alder Lake	Celeron G6900 Celeron G6900T	4693	128:16:2	300	1300					76.8
				Pentium Gold G7400 Pentium Gold G7400T				1350
UHD Graphics 730				i3-12100 i3-12100T	4692	192:24:3	300	1400
				i3-12300 i3-12300T i5-12400 i5-12400T				1450
UHD Graphics 770				i5-12500 i5-12500T i5-12600 i5-12600T	4690	256:32:4	300	1450
				i5-12600K i7-12700 i7-12700T i7-12700K	4680			1500
				i9-12900 i9-12900T i9-12900K i9-12900KS				1550
UHD Graphics		Mobile		Celeron 7300 Pentium 8500	46C3	384:48:6	300	800
				i3-1210U		512:64:8		850
				Celeron 7305 Pentium 8505	46B3	384:48:6	300	1100
				i3-1215U i3-1220P		512:64:8
				i5-12450H	46A3	384:48:6	300	1200
				i7-12650H		512:64:8		1400
Iris Xe Graphics				i5-1230U	46AA	640:80:6	300	850
				i5-1240U				900
				i7-1250U i7-1260U		768:96:6		950
				i5-1235U i5-1245U	46A8	640:80:6	300	1200
				i7-1255U i7-1265U		768:96:6		1250
				i5-1240P i5-12500H	46A6	640:80:6	300	1300
				i5-1250P i5-12600H				1400
				i7-1260P i7-1270P i7-12700H i7-12800H		768:96:6		1400
				i7-1280P i9-12900H i9-12900HK				1450
UHD Graphics 770	2022	Desktop	Raptor Lake	i5-13600K	A780	256:32:4	300	1500					89.6
				i7-13700K				1600
				i9-13900K				1650

Gen 12.5

Model[74][75]	Launch	Code name(s)	Process	Transistors (billion)	Die size (mm2)	Core config[a]	Cache		Core clock (MHz)[b]	Fillrate[c][d]		Memory					Processing power (TFLOPS)			TDP	Bus interface
							L1	L2		Pixel (GP/s)	Texture (GT/s)	Type	Size	Bandwidth (GB/s)	Bus width	Clock (MT/s)	Bfloat16	Single precision	Double precision
Data Center GPU Max 1100	Jan 10, 2023	Xe-HPC (Ponte Vecchio)	Multiple[76]	100	1280	7168:448:0:56:448:448	28 MB	204 MB	1000 1550	0	448.0 694.4	HBM2E	48 GB	1228.8	3072-bit	3200	352	14.336 22.221		300 W	PCIe 5.0 x16
Data Center GPU Max 1350	abandoned					14336:896:0:112:896:896	56 MB	408 MB	750 1550		672.0 1388.8		96 GB	2457.6	6144-bit		704	21.504 44.442		450 W
Data Center GPU Max 1550	Jan 10, 2023					16384:1024:0:128:1024:1024	64 MB	408 MB	900 1600		921.6 1638.4		128 GB	3276.8	8192-bit		832	29.491 54.423		600 W

• v
• t
• e

1. shading cores (ALU):texture mapping units (TMU):render output units (ROP):ray tracing units:tensor cores (XMX):execution Units
2. Boost values (if available) are stated below the base value in italic.
3. Pixel fillrate is calculated as the lowest of three numbers: number of ROPs multiplied by the base core clock speed, number of rasterizers multiplied by the number of fragments they can generate per rasterizer multiplied by the base core clock speed, and the number of streaming multiprocessors multiplied by the number of fragments per clock that they can output multiplied by the base clock rate.
4. Texture fillrate is calculated as the number of texture mapping units (TMUs) multiplied by the base (or boost) core clock speed.

Gen 12.7

Desktop

• v
• t
• e

Overview of Intel Arc Alchemist GPUs

Branding and Model[77]		Launch	MSRP (USD)	Code name	Process	Transistors (billion)	Die size (mm2)	Core config [a]	L2 cache	Clock rate (MHz)[b]	Fillrate		Memory					Processing power (TFLOPS)			TDP	Bus interface
											Pixel (GP/s)	Texture (GT/s)	Type	Size (GB)	Bandwidth (GB/s)	Bus width	Clock (MT/s)	Half precision (base)	Single precision (base)	Double precision (base)
Arc 3	A310	Sep 28, 2022	$110	ACM-G11 (DG2-128)	TSMC N6	7.2	157	6 Xe cores 768:32:16:6 (192:96:2)	4 MB	2000 2000	32	64	GDDR6	4 GB	124	64-bit	15500	6.144	3.072	n/a	75 W	PCIe 4.0 x8
	A380	Jun 14, 2022	$139					8 Xe cores 1024:64:32:8 (256:128:2)		2000 2050	64 65.6	128 131.2		6 GB	186	96-bit		8.192 8.3968	4.096 4.1984	n/a n/a
Arc 5	A580	Oct 10, 2023	$179	ACM-G10 (DG2-512)		21.7	406	24 Xe cores 3072:192:96:24 (768:384:6)	8 MB	1700 1700	163.2	326.4		8 GB	512	256-bit	16000	20.890	10.445	n/a	175 W	PCIe 4.0 x16
Arc 7	A750	Oct 14, 2022	$289					28 Xe cores 3584:224:112:28 (896:448:7)	16 MB	2050 2400	229.6 268.8	393.6 460.8						29.3888 34.4064	14.6944 17.2032	n/a n/a	225 W
	A770 8GB		$329					32 Xe cores 4096:256:128:32 (1024:512:8)		2100 2400	268.8 307.2	537.6 614.4						34.4064 39.3216	17.2032 19.6608	n/a n/a
	A770 16GB		$349											16 GB	560		17500

1. Shading cores (ALU): texture mapping units (TMU): render output units (ROP): ray tracing units
      (tensor cores (XMX): execution units: render slices)
2. Boost values (if available) are stated below the base value in italic.

Mobile

• v
• t
• e

Overview of Intel Arc Alchemist GPUs for mobile devices

Branding and Model[78]		Launch	Code name	Process	Transistors (billion)	Die size (mm2)	Core config[a][b]	L2 cache	Core clock (MHz)[c]	Fillrate[d]		Memory					Processing power (TFLOPS)			TDP	Bus interface
										Pixel (GP/s)	Texture (GT/s)	Type	Size	Bandwidth (GB/s)	Bus width	Clock (MT/s)	Half precision	Single precision	Double precision
Arc 3	A350M	Mar 30, 2022	ACM-G11 (DG2-128)	TSMC N6	7.2	157	6 Xe cores 768:48:24:6 (96:96:2)	4 MB	1150 2200	27.6 52.8	55.2 105.6	GDDR6	4 GB	112	64-bit	14000	3.5328 6.7584	1.7664 3.3792	0.4416 0.8448	25–35 W	PCIe 4.0 ×8
	A370M						8 Xe cores 1024:64:32:8 (128:128:2)		1550 2050	49.6 65.6	99.2 131.2						6.3488 8.3968	3.1744 4.1984	0.7936 1.0496	35–50 W
Arc 5	A530M	Q3 2023	ACM-G12 (DG2-256)				12 Xe cores 1536:96:48:12 (192:192:3)	8 MB	1300				4 GB 8 GB	224	128-bit					65–95 W
	A550M	Q2 2022	ACM-G10 (DG2-512)		21.7	406	16 Xe cores 2048:128:64:16 (256:256:4)		900 1700	57.6 108.8	115.2 217.6		8 GB				7.3728 13.9264	3.6864 6.9632	0.9216 1.7408	60–80 W
	A570M	Q3 2023	ACM-G12 (DG2-256)						1300											75–95 W
Arc 7	A730M	Q2 2022	ACM-G10 (DG2-512)		21.7	406	24 Xe cores 3072:192:96:24 (384:384:6)	12 MB	1100 2050	105.6 196.8	211.2 393.6		12 GB	336	192-bit		13.5168 25.1904	6.7584 12.5952	1.6896 3.1488	80–120 W	PCIe 4.0 ×16
	A770M						32 Xe cores 4096:256:128:32 (512:512:8)	16 MB	1650 2050	211.2 262.4	422.4 524.8		16 GB	512	256-bit	16000	27.0336 33.5872	13.5168 16.7936	3.3792 4.1984	120–150 W

1. Shading cores (ALU): texture mapping units (TMU): render output units (ROP): ray tracing units
      (tensor cores (XMX): execution units: render slices)
2. Texture fillrate is calculated as the number of texture mapping units (TMUs) multiplied by the base (or boost) core clock speed.
3. Boost values (if available) are stated below the base value in italic.
4. Pixel fillrate is calculated as the lowest of three numbers: number of ROPs multiplied by the base core clock speed, number of rasterizers multiplied by the number of fragments they can generate per rasterizer multiplied by the base core clock speed, and the number of streaming multiprocessors multiplied by the number of fragments per clock that they can output multiplied by the base clock rate.

Workstation

• v
• t
• e

Overview of Intel Arc Alchemist GPUs for Workstations

Branding and Model[79]		Launch	Code name	Process	Transistors (billion)	Die size (mm2)	Core config[a]	L2 cache	Core clock (MHz)[b]	Fillrate[c][d]		Memory					Processing power (TFLOPS)			TDP	Bus interface
										Pixel (GP/s)	Texture (GT/s)	Type	Size	Bandwidth (GB/s)	Bus width	Clock (MT/s)	Half precision	Single precision	Double precision
Arc Pro	A30M	Aug 8, 2022	ACM-G11 (DG2-128)	TSMC N6	7.2	157	8 Xe cores 1024:64:32:8 (128:128:2)	4 MB	1550			GDDR6	4 GB	112	64-bit	14000		4.20[79]		50 W	PCIe 4.0 x8
	A40												6 GB	192	96-bit	16000		5.02[79]
	A50								2050											75 W
	A60M	June 6, 2023	ACM-G12 (DG2-256)				16 Xe cores 2048:128:64:16 (256:256:4)		1300				8 GB	256	128-bit			9.42[79]		95 W	PCIe 4.0 x16
	A60								2000				12 GB	384	192-bit			10.04[79]		130 W

1. Shading cores (ALU): texture mapping units (TMU): render output units (ROP): ray tracing units
      (tensor cores (XMX): execution Units: render slices)
2. Boost values (if available) are stated below the base value in italic.
3. Pixel fillrate is calculated as the lowest of three numbers: number of ROPs multiplied by the base core clock speed, number of rasterizers multiplied by the number of fragments they can generate per rasterizer multiplied by the base core clock speed, and the number of streaming multiprocessors multiplied by the number of fragments per clock that they can output multiplied by the base clock rate.
4. Texture fillrate is calculated as the number of texture mapping units (TMUs) multiplied by the base (or boost) core clock speed.

Battlemage based

Desktop

• v
• t
• e

Overview of Intel Arc Battlemage GPUs

Branding and Model[80]		Launch	MSRP (USD)	Code name	Process	Transistors (billion)	Die size (mm2)	Core		Cache		Memory					Fillrate[a][b]		Processing power (TFLOPS)			TDP	Bus interface
								Core Config[c]	Clock (MHz)[d]	L1	L2	Type	Size	Bandwidth (GB/s)	Bus width	Clock (MT/s)	Pixel (GP/s)	Texture (GT/s)	Half precision	Single precision	Double precision
Arc 5	B570	Jan 16, 2025	$219	BMG-G21	TSMC N5	19.6	272	18 Xe Cores (144) 2304:144:72:18:144 (128:128:5)	1700 2500	4.5 MB	10 MB	GDDR6	10 GB	380	160-bit	19000	122.4 200.0	244.8 360.0	23.04	11.52	1.44	150 W	PCIe 4.0 x8
	B580	Dec 13, 2024	$249					20 Xe Cores (160) 2560:160:80:20:160 (160:160:5)	1700 2670	5 MB	12 MB		12 GB	456	192-bit		136.0 213.6	272.0 427.2	27.34	13.67	1.709	190 W

1. Pixel fillrate is calculated as the number of render output units (ROPs) multiplied by the base (or boost) core clock speed.
2. Texture fillrate is calculated as the number of texture mapping units (TMUs) multiplied by the base (or boost) core clock speed.
3. X^e2-HPG Cores (X^e Vector Engines)
   Unified Shaders : Texture Mapping Units : Render Output Units : Ray Tracing Cores : XMX Cores
4. Boost values (if available) are stated below the base value in italics.

Workstation

• v
• t
• e

Overview of Intel Arc Battlemage GPUs for Workstations

Branding and Model[81]		Launch	MSRP (USD)	Code name	Process	Transistors (billion)	Die size (mm2)	Core		L2 cache	Fillrate[a][b]		Memory					Processing power (TFLOPS)				TDP	Bus interface
								Config[c]	Clock (MHz)[d]		Pixel (GP/s)	Texture (GT/s)	Type	Size	Bandwidth (GB/s)	Bus width	Clock (MT/s)	Half precision	Single precision	Double precision	XMX Half Precision
Arc Pro	B50[82][83]	Sept 3, 2025	$349	BMG-G21	TSMC N5	198.6	272	16 Xe2-cores 2048:128:64:16:128 (128:128:4)	1700 2600	4 MB	87 133	218 332.8	GDDR6	16 GB	224	128-bit	14000	21.3	10.65	1.33	197	70 W	PCIe 5.0 x8
	B60	Q3 2025						20 Xe2-cores 2560:160:80:20:160 (160:160:5)	2400	16 MB	192	384		24 GB	456	192-bit	19000	24.5	12.8	1.54	170	120-200 W

1. Pixel fillrate is calculated as the lowest of three numbers: number of ROPs multiplied by the base core clock speed, number of rasterizers multiplied by the number of fragments they can generate per rasterizer multiplied by the base core clock speed, and the number of streaming multiprocessors multiplied by the number of fragments per clock that they can output multiplied by the base clock rate.
2. Texture fillrate is calculated as the number of texture mapping units (TMUs) multiplied by the base (or boost) core clock speed.
3. Shading cores (ALU): texture mapping units (TMU): render output units (ROP): ray tracing units
      (tensor cores (XMX): execution Units: render slices)
4. Boost values (if available) are stated below the base value in italic.

PowerVR based

Main article: PowerVR

Specifications of Intel PowerVR-based series^{[6][7][8][13][14][17][18][19][84][85][86][87][88][89][90][31][91][92][93][94][95][96][97][98][99][100][101][102][103][104][105][106][107][108]}

Graphics	Launch	PowerVR core	Market	Chipset	Code name	Device id.	Core render clock (MHz)	Pixel pipelines	Shader model (vertex/pixel)	API support			Memory bandwidth (GB/s)	DVMT (MB)	Hardware acceleration
										Direct3D	OpenGL	OpenCL			MPEG-2	VC-1	AVC
GMA 500	2008	SGX535	CE	CE3100 Atom Z520	Canmore	2E5B	?	2[109]	3.0	9.0c	2.0	—	4.2	256	Full	Full	Full
	2009			Atom CE4100	Sodaville
				Atom CE4110			200
				Atom CE4130
				Atom CE4150			400
				Atom CE4170
	2010			Atom CE4200	Groveland		?
	2008		MID	UL11L	Poulsbo (Menlow)	8108 8109	100
				US15L			200
				US15W
GMA 600	2010		MID	Atom Z6xx	Lincroft (Moorestown)	4102	400[110]	2	3.0	9.0c	2.0	—	6.4	759	Full	Full	Full
GMA	2012	SGX540	Smartphone	Atom Z24xx	Penwell (Medfield)	?	400[111]	4	—	—	ES 2.0	—	6.4	1024	Full	Full	Full
GMA 3600	2011	SGX545	Nettop Netbook	Atom D2500 Atom N2600	Cedarview (Cedar Trail)	0BE0 0BE1 0BE2 0BE3	400[112]	4	3.0	9.0c	3.0	—	8.5 6.4	1024[113]	Full	Full	Full
GMA 3650				Atom D2700 Atom N2800			640[112]						8.5
GMA	2012		Tablet	Atom Z2760	Cloverview (Clover Trail)	08C7 08C8 08C9 08CA 08CB 08CC 08CD 08CE 08CF	533	4	3.0	9.0c	2.0	—	6.4	2048	Full	Full	Full
GMA	2012	SGX544 MP2	Tablet	Atom Z2520 Atom Z2560 Atom Z2580	Cloverview (Clover Trail+)	?	300Mhz 400 MHz 533 MHz	?	?	9.0 L3	2.0ES, 2.0?	1.1	?	?	Full	Full	Full

See also

• Comparison of Intel processors
• Intel Arc
• Intel Quick Sync Video
• Intel Larrabee GPU
• List of AMD graphics processing units
• List of Intel chipsets
• List of Intel processors
• List of Nvidia graphics processing units
• Xeon Phi

Notes

Acronyms

The following acronyms are used throughout the article.

• EU: Execution Unit
• iDCT: Inverse discrete cosine transform
• iMDCT: Inverse modified discrete cosine transform
• LF: In-loop deblocking filter
• MC: Motion compensation
• VLD: Variable-length code (sometimes referred to as slice-level acceleration)
• WMV9: Windows Media Video 9 codec

Full hardware acceleration techniques

Intel graphic processing units employ the following techniques in hardware acceleration of digital video playback.

Codec used to encode the video	Technique employed
MPEG-2 Part 2	VLD, iDCT, and MC
VC-1	VLD, iMDCT, MC, and LF
H.264/MPEG-4 AVC	VLD, iMDCT, MC, and LF

Calculation

The raw performance of integrated GPU, in FLOPS, can be calculated as follows:

GPU	FLOPS
	FP16	FP32	FP64
Gen4 (GMA 3, 4)	-	(clock speed) * (# of FP32 ALUs)	-
Gen5 (HD Graphics)
Gen6 (HD Graphics 2000, 3000)		(clock speed) * 2 * (# of FP32 ALUs)
Gen7 (HD Graphics 2500, 4000 ~ 5200)			(clock speed) * (# of FP32 ALUs) / 2
Gen8 (HD Graphics 5300 ~ 6300)	(clock speed) * 2 * (# of FP32 ALUs) * 2
Gen9 (HD Graphics 5xx, 6xx)
Gen11

For example, the HD Graphics 3000 is rated at 125 GFLOPS,^[114] which is consistent with the formula (12 * 4 * 2 * 1,300 MHz).