graphic cards

Radeon

2009-07-08T07:38:00.000-07:00

ATI Radeon is a brand of graphics processing units (GPU) that since 2000 has been manufactured by ATI Technologies and subsequently AMD and is the successor to their Rage line. There are four different groups, which can be differentiated by the DirectX generation they support. More specific distinctions can also be followed, such as the HyperZ version, the number of pixel pipelines, and of course, the memory and processor clock speeds.

ATI Radeon Graphics
The Radeon Graphics logo
Invented by	ATI

1 ATI Radeon Processor Generations
2 Radeon Card Brands
3 Product naming scheme
4 Drivers
5 See also
6 References

7 External links

ATI Radeon Processor Generations

Series	Graphics APIs support		Notes
Series	DirectX	OpenGL	Notes
R100	DirectX 7.0	OpenGL 1.3	ATI's first graphics processor to be fully DirectX 7 compliant. It was first introduced in 2000. R100 brought with it large gains in bandwidth and fill-rate efficiency through the new HyperZ technology. Initial models included Radeon SDR, DDR and 7000/VE. The final release was the Radeon 7500.
R200	DirectX 8.1	OpenGL 1.4	ATI's second generation Radeon. This design included ATI's first programmable shader architecture and introduced the more advanced pixel shader 1.4. This line includes Radeon 8500 - 9200, 9250.
R300	DirectX 9.0	OpenGL 2.0	ATI's DirectX 9.0 technology, released in 2002, incorporated pixel shader. Included in this generation are Radeon 9500 - 9800, X300 - X600, X1050.
R420	DirectX 9.0b		While heavily based upon the previous generation, this line included extensions to the Shader Model 2 feature-set. Shader Model 2b, the specification ATI and Microsoft defined with this generation, offered somewhat more shader program flexibility. This generation's technology is used in Radeon X700 - X850.
R520	DirectX 9.0c		ATI's DirectX 9.0c series of graphics cards, with complete Shader Model 3.0 support. Launched in October 2005, this series brought a number of enhancements including the floating point render target technology necessary for HDR rendering with anti-aliasing. Cards released include X1300 - X1950.
R600	DirectX 10.0/ DirectX 10.1 (RV670)	OpenGL 3.0	ATI's first series of ATI Radeon GPUs supporting the Direct3D 10.0 specification and the company's second graphics solution to employ unified shader technology. Releases of this platform include the HD 2400, HD 2600 and HD 2900. There are also products supporting DirectX 10.1, known as the HD 3000 series, with a die shrink.
R700	DirectX 10.1	OpenGL 3.0	Based on the R600 architecture. Mostly a bolstered card with many more stream processors, with improvements to power consumption and GDDR5 support for the high-end RV770 chip. It arrived in late June 2008. The HD 4850 and HD 4870 have 800 stream processors and GDDR3 and GDDR5 memory respectively.
R800	DirectX 11		ATI's latest series. The Radeon R800 is expected to be launched on a 40 nm fabrication process, with 2000 stream processors and compatible with the next major version of the DirectX API, DirectX 11 which is aimed at a launch late July, 2009.

Radeon Card Brands

AMD no longer sells Radeon cards at the retail level. Instead, it sells Radeon GPUs to 3rd party board manufacturers, who build and sell the Radeon-based boards to the OEM and retail channel. Board manufacturers of the Radeon include Diamond Multimedia, Sapphire Technology, AsusTek, HIS - Hightech Information System, MSI - Micro-Star International, PowerColor, Gigabyte, VisionTek, & recently, XFX and Gainward
Product naming scheme
Since ATI's first DirectX 9-class GPU, the company has followed a naming scheme that relates each product to a market segment.
¹ Stream Processors only applicable to Radeon HD 2000 series video cards.

Product Category	Card Name (* denotes wildcard)	Usual Suffixes	Price range (USD)	Shader amount (VS/PS/SPU)¹	Memory			Outputs	Example products
Product Category	Card Name (* denotes wildcard)	Usual Suffixes	Price range (USD)	Shader amount (VS/PS/SPU)¹	Type	Width (bit)	Size (MiB)	Outputs	Example products
Enthusiast/high-end	9 8	XTX, XT, XT PE, XL, Pro, GTO, GT	>$150	75-100% 200% (X2, dual-GPU)	GDDR3, GDDR4, GDDR5	256-bit/ 512-bit	256/512/1024	Dual DVI with HDMI (HD 2000 dongle)	X800, X1950, HD 2900, HD 4870
Mainstream	7 6 5	XT, XL, Pro, SE, GTO, GT	$100–$150	37.5-75%	DDR2, GDDR3, GDDR4	128-bit	128/256/512	D-Sub, DVI/ Dual DVI with HDMI (HD 2000 dongle)	X700, X1600, HD 2600
Budget/Value	4 3 2 1 0 7x00, 9000, 9200, 9250	SE, HM	<$99	25-50%	DDR2, GDDR3	64-bit	64/128 (HM: 768/1024)	D-Sub, DVI with HDMI (HD 2000 Dongle)	X300, X1050, X1400, HD 2400

Note: Suffix indicate different layers of performance. See ATI Video Card Suffixes.

Since the release of the Radeon HD 3000 series products, previous PRO, XT, GT, and XTX suffixes were eliminated, products will be differentiated by changing the last two digits of the product model number (for instance, HD 3850 and HD 3870, giving the impression that the HD 3870 model having higher performance than HD 3850).^[1] Similar changes to the IGP naming were spotted as well, for the previously launched AMD M690T chipset with side-port memory, the IGP is named "Radeon X1270", while for the AMD 690G chipset, the IGP is named "Radeon X1250", as for AMD 690V chipset, the IGP is clocked lower and having fewer functions and thus named "Radeon X1200". The new numbering scheme of video products are shown below:

Product Category	Model number range (steps of 10)¹	Price range (USD)	Shader amount (VS/PS/SPU)²	Memory			Outputs	Product(s)
Product Category	Model number range (steps of 10)¹	Price range (USD)	Shader amount (VS/PS/SPU)²	Type	Width (bit)	Size (MiB)	Outputs	Product(s)
Enthusiast /high-end	800-990	>$150	75-100%	GDDR3, GDDR4, GDDR5	256-bit	256/512/1024	2 DVI, HDMI, DP (Dongle)	HD 3850/3870 HD 4850/4870/ HD 4830
Mainstream	600-790	$100–$150	37.5-75%	DDR2, GDDR3, GDDR4	128-bit	128/256/512/1024	D-Sub, DVI	HD 3650/ HD 4650/ HD 4670
Mainstream	600-790	$100–$150	37.5-75%	DDR2, GDDR3, GDDR4	128-bit	128/256/512/1024	DVI, 2 DP, HDMI (Dongle)	HD 3650/ HD 4650/ HD 4670
Budget/Value	350-590	<$99	25-50%	DDR2, GDDR3	64-bit	64/128 (HM: 768/1024)	D-Sub, DVI, HDMI, DP (Dongle)	HD 3450/3470
IGP	000-300	N/A	25-50%	UMA, side-port memory (GDDR2/GDDR3)	UMA + 16-bit (side-port)	64 + UMA (OS dependent)	D-Sub, DVI, HDMI, DP Component (YCbCr)	X1270/X1250/X1200 HD 3200/HD 3100/2100

¹ The last two digits denotes variant, similar to the previous suffixes, which "70" is in essence the "XT" variant while "50" is actually the "Pro" variant.^[2]
² Stream Processors only applicable to Direct3D 10-class video components (Radeon HD 2000/3000 series).
Drivers
Windows

Main article: ATI Catalyst Drivers

The ATI Radeon graphics driver package for Windows operating system is called ATI Catalyst.

The ATI Catalyst official drivers refuse to work with the mobile versions of Radeon series due to an agreement with OEM vendors.^[3] An alternative is an application called Mobility Modder, a third-party utility which modifies recent desktop Radeon drivers to work with Mobility Radeon graphics cards.

There are also unofficial modifications available such as Omega drivers or DNA drivers. These drivers typically consist of mixtures of various driver file versions with some registry variables altered and are advertised as offering superior performance or image quality. They are, of course, unsupported, and as such, are not guaranteed to function correctly. Some of them also provide modified system files for hardware enthusiasts to run specific graphics cards outside of their specifications.
Windows XP Professional x64

ATI has yet to produce mobile 64 bit drivers for the Windows XP Professional x64 Edition operating system. This may be due to a number of factors. One factor is that most people use the 32-bit version of Windows XP, due not only to video card driver issues, but other driver compatibility issues as well. Nonetheless, it is possible to obtain a proper driver for this type of setup. In order to do so, one requires the use of an unsupported application like Modtool.
Macintosh

ATI used to only offer driver updates for their retail Mac video cards, but now also offer drivers for all ATI Mac products, including the GPUs in Apple's portable lines. Apple also includes ATI driver updates whenever they release a new OS update. ATI provides a preference panel for use in Mac OS X called ATI Displays which can be used both with retail and OEM versions of their cards. Though it gives more control over advanced features of the graphics chipset, ATI Displays has limited functionality compared to their Catalyst for Windows product.
Linux

Main article: fglrx

Initially, ATI did not produce Radeon drivers for Linux, instead giving hardware specifications and documentation to Direct Rendering Infrastructure (DRI) developers under various non-disclosure agreements.

In mid 2004, however, ATI started to support Linux (XFree86, X.Org), hiring a new Linux driver team to produce fglrx. Their new proprietary Linux drivers, instead of being a port of the Windows Catalyst drivers, were based on the Linux drivers for the FireGL (the FireGL drivers worked with Radeons before, but didn't officially support them), a card geared towards graphics producers, not gamers; though the display drivers part is now based on the same sources as the ones from Windows Catalyst since version 4.x in late 2004. The proprietary Linux drivers neither support R100 (Radeon 7000-7500) nor R200 (Radeon 8500-9200, 9250) chips^[4].

The frequency of driver updates increased in late 2004, releasing Linux drivers every two months, half as often as their Windows counterparts. Then since late 2005 this has been increased to monthly releases, inline with the Windows Catalyst releases.

For information on alternative Open Source drivers, see below.
FreeBSD

FreeBSD systems have the same open-source support for Radeon hardware as Linux, including 2D and 3D acceleration for Radeon R100, R200, and R300-series chipsets. The R300 support, as with Linux, remains experimental due to being reverse-engineered from ATI's proprietary drivers.

ATI does not support its proprietary fglrx driver on FreeBSD, it has been partly ported by a third party as of January 2007. This is in contrast to its main rival, NVIDIA, which has periodically released its proprietary driver for FreeBSD since November 2002 (though 64-bit BSD systems are still not supported as of 2009). In the meantime the release is similar to Linux.
MidnightBSD

MidnightBSD supports 2D and 3D acceleration for Radeon R100, R200, and R300 chipsets. This support is similar to FreeBSD and Linux.
AmigaOS

Since AmigaOS 4 introduction AmigaOS users officially gained support for R100/R200 Radeon cards with the R300 chips being planned, although this depends on the available hardware documentations from ATI or the open source drivers from the Linux community.

Hans de Ruiter is developing on R5xx and R6xx drivers from AMD documentation. At the present time (07/MAR/2009) there is a basic P96 2D driver, which works with the PCI Radeon X1300, X1550 and HD2400 that Hans is using for development and testing.
BeOS

Although ATI does not provide its own drivers for BeOS, it provides hardware and technical documentation to the Haiku Project who provide drivers with full 2D and video in/out support. They are the sole graphics manufacturer in any way still supporting BeOS.
MorphOS

MorphOS supports 2D and 3D acceleration for Radeon R100 and R200 chipsets.^[5]
FOSS drivers
On September 12, 2007, AMD released documentation for the RV630 (Radeon HD 2600 PRO and Radeon HD 2600 XT) and M56 (Radeon Mobility X1600) chips for open source driver development, for its strategic open source driver development initiative.^[6] This initial "documentation drop" released sufficient programming information for a skeleton display detection and modesetting driver to be released. This was version 1.0.0 of the "radeonhd" driver. Further documentation releases and a baseline open source drivers are likely to follow in the near future. ^[7] The register reference guides for M76 (Mobility Radeon HD 2600/2700/3600/3800 series) and RS690 (AMD 690 chipset series) were also released on January 4, 2008, and is available from ATI website ^[8].

All specs are available without an NDA. AMD is collaborating with Novell to build a new, free driver called RadeonHD based on these specifications. At present it is reasonably stable, and supports DRI for r500 series cards. Its development can be tracked using the git repository at the Freedesktop.org website. ^[9]

Also available is a driver known as "ati", "xf86-video-ati", "video-ati" and "radeon". The main difference between video-ati and radeonhd used to be that video-ati uses AtomBIOS and radeonhd does not. AtomBIOS is an abstraction layer filled in by AMD to quickly add a new type of card or card series. AtomBIOS speeds up development of video-ati, but some have argued that it makes the open-source driver more legacy and untouchable.^[10] In July 2008 development has started to enable radeonhd to use AtomBIOS too, which should tremendously decrease the timeframe in which initial support for new hardware is developed. This development was started in a branch named atombios_support, and as of September 2008 is not yet merged with the master branch.^[11]^[12]

GeForce 200 Series

2009-07-08T07:33:00.000-07:00

The GeForce 200 Series is the tenth generation of NVIDIA's GeForce graphics processing units. The series also represents the continuation of the company's unified shader architecture introduced with the GeForce 8 Series and the GeForce 9 Series.

The GeForce GTX 280 and 260 are based on the same processor core. During the manufacturing process, GTX chips are binned and separated through defect testing of the core's logic functionality. Those that fail to meet the GTX 280 hardware specification are re-tested and binned as GTX 260 (which is specified with fewer stream processors, less ROPS and a narrower memory bus). In late 2008, in order to create more parity between the GTX 260 and the competing HD 4870, Nvidia re-released the GTX 260 with 216 stream processors up from 192. Effectively, there are two GTX 260 cards in production with non-trivial performance differences.

As of June 2008^[update], the G200 is the largest commercial GPU ever constructed. It consists of 1.4 billion transistors covering a 576mm² die surface area built on a 65nm process.^[1] To date, the G200 is the largest CMOS-logic chip that has been fabricated at the TSMC foundry.

NVIDIA GeForce 200 Series
Codename(s)	G92a/b, G200a/b
Release date	2008/2009
Mid-Range GPU	GTS 250, GTX 260, GTX 260 Core 216
High-end GPU	GTX 275, GTX 280, GTX 285, GTX 295
Direct3D and Shader version	D3D 10.0, Model 4.0

1 Technical summary
2 Future
3 See also
4 References

5 External links

Technical summary

¹ Unified Shaders (Vertex shader / Geometry shader / Pixel shader) : Texture mapping unit : Render Output unit
² The theoretical shader performance in single-precision floating point operations [FLOPS_sp, GFLOPS] of the graphics card with shader count [n] and shader frequency [f, GHz], is estimated by the following: FLOPS_sp ≈ f × n × 3.

Model	Year	Code name	Fab (nm)	Transistors (Billion)	Die Size (mm ²)	Bus interface	Memory min (MiB)	Config core ¹	Reference clock rate			Fillrate		Reference Memory Configuration			Graphics library support (version		GFLOPs² (MADD+MUL)	TDP (Watts)	Comments
Model	Year	Code name	Fab (nm)	Transistors (Billion)	Die Size (mm ²)	Bus interface	Memory min (MiB)	Config core ¹	Core (MHz)	Shader (MHz)	Memory (MHz)	Pixel (GP/s)	Texture (GT/s)	Bandwidth (GiB/s)	DRAM type	Bus width (bit)	DirectX	OpenGL	GFLOPs² (MADD+MUL)	TDP (Watts)	Comments
GeForce GTS 250	March 3, 2009	G92a/b	65/55	0.754	324/230	PCIe x16 2.0	512 or 1024	128:64:16	738	1836	2200	11.808	47.232	70.4	GDDR3	256	10	3.1^[2]	705	145	Some 512MB cards are rebranded GeForce 9800 GTX and GTX+ cards
GeForce GTX 260	June 26, 2008	G200	65	1.4	576	PCIe x16 2.0	896	192:64:28	576	1242	1998	16.128	36.864	111.9	GDDR3	448 32x14	10	3.1^[2]	715	182
GeForce GTX 260 216SP^[3]	September 16, 2008	G200	65	1.4	576	PCIe x16 2.0	896	216:72:28	576	1242	1998	16.128	41.472	111.9	GDDR3	448 32x14	10	3.1^[2]	805	182
GeForce GTX 260 216SP 55nm^[4]	December 22, 2008	G200b	55	1.4	470	PCIe x16 2.0	896	216:72:28	576	1242	1998	16.128	41.472	111.9	GDDR3	448 32x14	10	3.1^[2]	805	171
GeForce GTX 275^[5]	April 2, 2009	G200b	55	1.4	470	PCIe x16 2.0	896	240:80:28	633	1404	2268	17.724	50.6	127.0	GDDR3	448 32x14	10	3.1^[2]	1010.88	219
GeForce GTX 280 ^[6]^[7]	June 17, 2008	G200	65	1.4	576	PCIe x16 2.0	1024	240:80:32	602	1296	2214	19.264	48.16	141.7	GDDR3	512 32x16	10	3.1^[2]	933	236
GeForce GTX 285 ^[8] ^[9]	January 15, 2009	G200b	55	1.4	470	PCIe x16 2.0	1024	240:80:32	648	1476	2484	20.736	51.84	159.0	GDDR3	512 32x16	10	3.1^[2]	1062.72	183
GeForce GTX 295	January 8, 2009	G200b	55	2x 1.4	2x 470	PCIe x16 2.0	2x 896	2x 240:80:28	576	1242	1998	2x 16.128	2x 46.08	2x 111.9	GDDR3	2x 448 32x14	10	3.1^[2]	1788.48	289

Future

According to Expreview and other sources, Nvidia plans to release a single PCB version of the GTX 295 graphics card. The performance specifications of the new card will be identical to the dual PCB version. Improvements however, are speculated to be better power consumption, better thermal performance as well as cheaper manufacturing costs. The single PCB version of the GTX 295 is expected to be released in late May, 2009. The first confirmed model will be from Inno3D and is named the "GTX 295 Platinum Edition". EVGA will also release a single PCB model of the GTX 295 nicknamed the "GTX 295 Co-op Edition".^[10]

At CES 2009, Nvidia announced the low-end mobile version of the GTX 200 series, known as the G 100M series. Preliminary benchmarks have found that some chips are up to 50% faster than the GeForce 9 that precede them. The first three chips are the G 105M which replaces the 9300M GS, the G 110M which compares to the recently announced 9400M G, and the GT 130M which replaces the 9600M GT.

Nvidia has also released OEM budget and mainstream cards under the 100 series with similar naming schemes to the mobile cards. Current cards include the G 100, GT 120, GT 130 and GTS 150. The GT 120 is a rebranded 9500 GT with improved thermal designs while the GT 130 is a modified version of the 9600 GSO. The GTS 150 is an OEM version of the GTS 250 with some slight changes.

Nvidia also have announced plans to launch a revision and rebrand of the 9800 GT (8800 GT) which is based on the G92 chipset, slated for an April release called the GTS 240. The GTS 240 was to have been an overclocked version of the 9800 GT but there are reports that the GTS 240 has been cancelled. The GTS 250 is basically a 55nm G92b based 9800 GTX+ GPU on a new P361 PCB and internally Nvidia calls it D10P2. The differences are mainly on the power design; the core and ram speeds are identical to the 9800 GTX+ but power consumption has been lowered. All of the GTX 200 series cards support OpenGL 3.0.

Even more recently, Nvidia has launched the high-end mobile version of the GTX 200 series. The first two chips are the GTX 260M and the GTX 280M, which are fabricated at a smaller 55nm process allowing for 128 stream processors, up from the 9800M GTX's maximum of 112 stream processors. Also, Nvidia has released more midrange versions of the GT200s for mobiles. These include the GT 210M, GT 230M, GT 240M, GTS 250M, and GTS 260M. It is hard to place where these cards will slot in compared to the lower end GT100Ms, but it is believed these mobile cards will eventually completely erase the GT100s.

Nvidia will be launching a GTX 300 series GPU as its flagship model. The GTX 300 series is projected to launch in Q4 of 2009, with the first products to be fabricated on TSMC's 45 nanometer manufacturing process. It is rumored to be DirectX 11 compatible, and like AMD's recent GPUs, use GDDR5 RAM to reduce manufacturing cost. According to information released by The Bright Side of News on April 22 2009, the G300 architecture will feature a cGPU design. The cGPU is much closer to traditional CPUs and will be radically different from previous generations. The G300 chipset will use MIMD instead of SIMD.

GeForce 9M Series

2009-07-07T10:46:00.000-07:00

All graphical processing units in the GeForce 9M series feature:

Increased performance for similar power draw compared to GeForce 8M series for midrange and mid-high range notebooks,
DirectX 10.0 and OpenGL 2 compatibility,
16X antialiasing, and
Full HD DVD / Blu-ray hardware decoding.
9100M G^[32]
8 Stream Processors.
450 MHz core clock.
1100 MHz shader clock.
Memory Clock depend on System Memory.
Up to 256 MB shared memory, with Turbo Cache.
64 bit memory interface (single-channel mode) / 128 bit memory interface (dual-channel mode).
Memory Bandwidth depend on System Memory.
1.8 billion texels/s texture fill rate.
(specification based on Acer Aspire 4530 using GPU-Z v0.2.8 utility)
9200M GS^[33]
8 Stream Processors.
529 MHz core clock.
1300 MHz shader clock.
400 MHz memory clock.
Up to 256 MB memory.
64-bit memory interface.
6.4 GB/s memory bandwidth.
2.1GPixel/s Pixel Fillrate.
4.2GTexel/s Texture Fillrate
9300M G^[34]
16 Stream Processors.
400 MHz core clock.
800 MHz shader clock.
600 MHz memory clock.
Up to 256 MB memory.
64-bit memory interface.
4.8 GB/s memory bandwidth.
3.2 billion texels/s texture fill rate.
9300M GS^[35]
16 Stream Processors.
580 MHz core clock.
1450 MHz shader clock.
800 MHz memory clock.
Up to 512 MB memory.
64-bit memory interface.
6.4 GB/s memory bandwidth.
4.6 billion texels/s texture fill rate.
9400M G^[36]
16 Stream Processors.
Memory Clock depend on System Memory.
64 bit memory interface (single-channel mode) / 128 bit memory interface (dual-channel mode).
Memory Bandwidth depend on System Memory.
3.6 billion texels/s texture fill rate.
9500M G^[37]
16 Stream Processors.
500 MHz core clock.
1200 MHz shader clock.
800 MHz memory clock.
Up to 1024 MB memory.
128-bit memory interface.
12,8 GB/s memory bandwidth.
? billion texels/s texture fill rate.
9500M GS^[38]
32 Stream Processors.
475 MHz core clock.
950 MHz shader clock.
700 MHz memory clock.
Up to 512 MB memory.
128-bit memory interface.
22.4 GB/s memory bandwidth.
7.6 billion texels/s texture fill rate.
9600M GS^[39]
064A/8 core (G96.
32 Stream Processors.
430 MHz core clock.
1075 MHz shader clock.
800/1600 MHz memory clock (effective).
Up to 1024 MB memory.
128-bit memory interface.
12.8 GB/s (with DDR2 type) or 25.6 GB/s (with GDDR3 type) memory bandwidth.
6.8 billion texels/s texture fill rate.
103 GigaFLOPS.
9600M GT^[40]
32 Stream Processors.
500 MHz core clock.
1250 MHz shader clock.
1000 MHz memory clock.
Up to 1024 MB memory.
128-bit memory interface.
25.6 GB/s memory bandwidth.
8.0 billion texels/s texture fill rate.
9650M GS ^[41]
G84 core
32 Stream Processors.
625 MHz core clock.
1250 MHz shader clock.
800 MHz memory clock.
Up to 512 MB memory.
128 bit memory interface.
25.6 GB/s memory bandwidth.
10 billion texels/s texture fill rate.
9650M GT ^[42]
G96 core (65/55nm).
32 Stream Processors.
550 MHz core clock.
1325 MHz shader clock.
800 MHz memory clock.
Up to 1024 MB memory.
128 bit memory interface.
25.6 GB/s memory bandwidth.
8.8 billion texels/s texture fill rate.
9700M GT [4]
G96 core.
32 Stream Processors.
625 MHz core clock.
1550 MHz shader clock.
800 MHz memory clock.
128 bit memory interface.
25.6 GB/s memory bandwidth.
10.0 billion texels/s texture fill rate.
148.8 GigaFLOPS.
9700M GTS [5]
G94 core.
48 Stream Processors.
530 MHz core clock.
1325 MHz shader clock.
800 MHz memory clock.
256 bit memory interface.
51.2 GB/s memory bandwidth.
12.7 billion texels/s texture fill rate.
190.8 GigaFLOPS.
9800M GS [6]
G94 core.
64 Stream Processors.
530 MHz core clock.
1325 MHz shader clock.
800 MHz memory clock.
256 bit memory interface.
51.2 GB/s memory bandwidth.
17.0 billion texels/s texture fill rate.
254 GigaFLOPS.
9800M GTS [7]
G94 core.
64 Stream Processors.
600 MHz core clock.
1500 MHz shader clock.
800 MHz memory clock.
256 bit memory interface.
51.2 GB/s memory bandwidth.
19.2 billion texels/s texture fill rate.
288 GigaFLOPS.
9800M GT [8]
G92 core.
96 Stream Processors.
500 MHz core clock.
1250 MHz shader clock.
800 MHz memory clock.
256 bit memory interface.
51.2 GB/s memory bandwidth.
24.0 billion texels/s texture fill rate.
360 GigaFLOPS.
9800M GTX [9]
G92 core.
112 Stream Processors.
500 MHz core clock.
1250 MHz shader clock.
800 MHz memory clock.
256 bit memory interface.
51.2 GB/s memory bandwidth.
28.0 billion texels/s texture fill rate.
420 GigaFLOPS.

GeForce 9800 Series

2009-07-07T10:45:00.000-07:00

The GeForce 9800 series contains the GX2 (dual GPU), GTX and GT variants.^[15]

GeForce 9800 GX2

On March 18, 2008 the GeForce 9800 GX2 was officially launched.

The GeForce 9800 GX2 has the following specifications: ^[16]^[17].

Dual PCBs, dual GPU design
197 W power consumption ^[18].
Two 65nm process GPUs, with 256 total Stream Processors (128 per PCB)^[19].
Supports Quad SLI.
Power of Two underclocked Geforce 8800 GTS 512(G92) video cards in SLI Mode
1 GiB (512 MB per PCB) memory framebuffer.
Supports DirectX 10, Shader Model 4, OpenGL 2.1, and PCI-Express 2.0.
Outputs include two DVI ports, an HDMI output, and S/PDIF in connector on-board for routing audio through the HDMI cable ^[20].
An 8-pin and a 6-pin power connector.
Clocks (Core/Shader/Memory): 600 MHz/1500 MHz/2000 MHz ^[21]
256-bit memory interface^[21]
128 GB/s memory bandwidth^[21]
Release date: March 18, 2008
Launch price of $599 ^[22].
GeForce 9800 GTX

On April 1, 2008 the GeForce 9800 GTX was officially launched. It was basically an 8800 GTS 512MB with two SLI connectors, higher clock speeds, and support for Nvidia Hybrid Power, a technology that allows the discrete GPU to shut off during non resource intensive applications, and instead use the integrated GPU. With these extra features though, a high price came too.

Taken from an eVGA specification sheet:^[23]
128 Stream Processors.
Clocks (Core/Shader/Memory): 675 MHz/1688 MHz/2200 MHz
256-bit memory interface.
512 MB of GDDR3 memory.
70.4 GB/s memory bandwidth
Texture Fill Rate of 43.2 (billion/s).
DirectX 10, Shader Model 4.0, OpenGL 2.1, and PCI-Express 2.0.
Outputs include two DVI ports, an HDMI output(Using nVidia DVI to HDMI adapter(included)), and S/PDIF in connector on-board for routing audio through the HDMI cable.
Release date was 2008-04-01. ^[24]
Launch Price of $349. ^[25]

In July 2008 nVidia released the 55 nm refresh of the 9800 GTX: the 9800 GTX+. It has faster core (738 MHz) and shader (1836 MHz) clocks.

GeForce 9800 GT

The 9800GT is effectively a rebranded 8800GT, although some are being manufactured using a newer 55 nm technology instead of the older 65 nm first debuted on the 8800GT^[26]

ASUSTeK have released a 9800GT with Tri-SLI support.^[27]

Taken from the nVidia product detail page.^[28]

112 Stream Processors
512-1024MB Standard Memory
256-bit Memory Interface Width
600 MHz Graphics Clock (MHz)
1500 MHz Processor Clock (MHz)
900 MHz Memory Clock
Texture Fill Rate (billion/s) 33.6
Memory Bandwidth (GB/s) 57.6
DirectX 10, Shader Model 4.0, OpenGL 2.1, and PCI-Express 2.0.

GeForce 9600 Series

2009-07-07T10:44:00.001-07:00

GeForce 9600 GT

On February 21, 2008 the GeForce 9600 GT was officially launched.

55/65 nm G94 GPU.
64 Stream Processors.
16 Raster Operation(ROP) units, 32 Texture Address(TA)/Texture Filter(TF) units.
20.8 billion texels/s fillrate.
650 MHz core clock, with a 1625 MHz unified shader clock.
1800 MHz memory, with a 256-bit memory interface.
256 MB, 512 MB, or 1 GB of GDDR3 memory^[10].
57.6 GB/s memory bandwidth for boards configured with GDDR3 900 MHz memory.
505M transistor count
DirectX 10, Shader Model 4.0, OpenGL 2.1, and PCI-Express 2.0^[11].
Is compatible with HDCP, but the implementation will depend on the manufacturer.
Supports CUDA and the Quantum Effects physics processing engine.
Almost double the performance of the previous Nvidia mid-range card, the GeForce 8600GTS.
Estimated by NVIDIA to cost between $169–$189 MSRP.

Source: ^[12]

GeForce 9600 GSO

The GeForce 9600 GSO was originally essentially a renamed 8800 GS. This tactic has been seen before in products such as the GeForce 7900 GTO to clear unsold stock when it is made obsolete by the next generation. Just like the 8800 GS the 9600 GSO features 96 stream processors, a 550 MHz core clock with shaders clocked at 1,375 MHz, and 384MB memory clocked at 800 MHz on a 192-bit memory bus.^[13]

GeForce 9600 GSO 512

After clearing the old 8800 GS stock, nvidia revised the specification with a new core, and 512 MB of memory clocked at 900 MHz on a 256-bit bus.^[14] For these cards the number of stream processors is halved to 48, with the core frequency increased to 650 MHz and the shader frequency increased to 1625 MHz.

GeForce 9500 Series

2009-07-07T10:43:00.002-07:00

GeForce 9500 GT

On July 29, 2008 the Geforce 9500 GT was officially launched.

65 nm G96 GPU
32 Stream Processors.
550 MHz core, with a 1400 MHz unified shader clock.
8.8 billion texels/s fillrate.
256 MB/512MB 1600 MHz GDDR3 memory or 256 MB 1000 MHz GDDR2 memory, both with a 128-bit memory bus.
25.6 GB/s memory bandwidth for boards configured with GDDR3 800 MHz memory.
Support DirectX 10, Shader Model 4.0, OpenGL 2.1, and PCI-Express 2.0.
Supports 2nd generation PureVideo 2 technology with partial VC1 decoding.^[8]^[9]

GeForce 9500 GS

65 nm G96 GPU
32 Stream Processors.
8 Raster Operations (ROP) units
550 MHz Core, with a 1375 MHz unified shader clock.
8.8 billion texels/s Fillrate.
512MB 1000MHz DDR2 memory with a 128-bit memory bus.
16.0 GB/s memory bandwidth.
Supports DirectX 10, Shader Model 4.0, OpenGL 2.1, and PCI-Express 2.0
Supports 2nd generation PureVideo 2 technology with partial VC1 decoding.

GeForce 9400 Series

2009-07-07T10:43:00.001-07:00

GeForce 9400 GT

On August 27, 2008 the Geforce 9400 GT was officially launched.

65 nm G96 GPU
16 Stream Processors.
550 MHz core, with a 1350 MHz unified shader clock.
4.4 billion texels/s fillrate.
256 MB/512 MB/1024 MB 800 MHz DDR2 or 256 MB 1600 MHz GDDR3^[4] , both with a 128-bit memory bus
12.8 GB/s memory bandwidth for boards configured with DDR2 800 MHz memory.
Support DirectX 10, Shader Model 4.0, OpenGL 2.1, and PCI-Express 2.0.
Supports 2nd generation PureVideo technology and HybridPower technology.^[5]^[6]^[7]

GeForce 9 Series

2009-07-07T10:42:00.000-07:00

The GeForce 9 Series is the ninth generation of NVIDIA's GeForce series of graphics processing units, the first of which was released on February 21, 2008.

NVIDIA GeForce 9 Series
Codename(s)	G92a/b, G94a/b, G96a/b
Release date	2008
Entry-level GPU	9100, 9200, 9300 (IGP), 9400 (both integrated and discrete variants), 9500
Mid-Range GPU	9600
High-end GPU	9800
Direct3D and Shader version	D3D 10, Model 4

[hide]

1 New codename scheme
2 GeForce 9400 Series
- 2.1 GeForce 9400 GT
3 GeForce 9500 Series
- 3.1 GeForce 9500 GT
- 3.2 GeForce 9500 GS
4 GeForce 9600 Series
5 GeForce 9800 Series
6 Technical summary
7 GeForce 9M Series
8 See also
9 References
10 External links
New codename scheme

It had previously been thought that NVIDIA had decided to drop the G and NV nomenclature for a D (for Desktop) nomenclature on their processors. Following the D is the generation number and the target market indicator. NVIDIA's official designations for target markets include Mainstream, Performance, and Enthusiast. For example, the D9E indicates a 9th generation Desktop GeForce video card for the Enthusiast market^[1]. However, NVIDIA has actually forked their codenames into those of graphics processors, and those of graphics cards. The GPU cores have kept the prefix "G" and future versions will include the prefix "GT"; whereas the actual cards are now codenamed as D, generation number and target market. For example, the GeForce 8800 GT is designated D8P but contains a processor codenamed G92; the GeForce 9600 GT will most likely be designated D9M but it will contain the G94 core^[2], whereas the 9800 will likely contain the G92 core. The next-generation core after the GeForce 9 Series is designated G200^[3], it had previously been published as G100. It is worth noting that all of the GeForce 9 series is technically similar to the G92 GeForce 8 series (8800 GT/GTS 512), except for the use of slightly higher rated and clocked video memory. Also in the 9800 GTX+ and some 9800 GT, a manufacturing processing shrink to 55 nm was added. However the architecture of the G92 is identical, meaning clock for clock identical performance.

GeForce 8M Series

2009-07-07T10:39:00.000-07:00

On May 10, 2007, NVIDIA announced the availability of their GeForce 8 notebook GPUs through select OEMs. So far the lineup consists of the 8400M, 8600M, 8700M and 8800M series chips.^[36] It has been announced by nVidia that some of their graphics chips have a higher than expected rate of failure due to overheating when used in particular notebook configurations. Some major laptop manufacturers are making adjustments to fan setting and firmware updates to help delay the occurrence of any potential GPU failure. In late July, Dell released a set of BIOS updates that made the laptop fans spin more frequently^[37]. As of mid-August, nVidia is yet to give further details publicly, though it has been heavily rumored that all or most of the 8400 and 8600 cards have this issue.

GeForce 8400M Series

The GeForce 8400M is the entry level series for the GeForce 8M chipset. Normally found on midrange laptops as an alternate solution to integrated graphics, the 8400M is designed for watching high definition video content rather than gaming. Versions include the 8400M G, 8400M GS, and 8400M GT. While these GPUs are not oriented for high-end gaming, the GDDR3-equipped 8400M-GT can handle most modern games at medium settings,^[38] and is suitable for occasional gaming.

GeForce 8600M Series

The GeForce 8600M is offered in midrange laptops as a mid-range performance solution for enthusiasts who want to watch high-definition content such as Blu-ray Disc and HD DVD movies and play current and some future games with decent settings. Versions include the 8600M GS and 8600M GT, and provide decent gaming performance (due to the implementation of GDDR3 memory in the higher-end 8600M models) for current games.

GeForce 8600M Series

GeForce 8700M Series

The GeForce 8700M was developed for the high-end market. Currently the only version is the 8700M GT. This chipset is available on high-end laptops such as the Dell XPS M1730, Sager NP5793, and Toshiba Satellite X205. While this card is considered by most in the field to be a decent mid-range card, it is hard to classify the 8700M-GT as a high-end card due to its 128-bit memory bus, and is essentially an overclocked 8600M GT GDDR3 mid-range card.^[39] However, it shows strong performance when in a dual-card SLI configuration, and provides decent gaming performance in a single-card configuration.^[40]

GeForce 8800M Series

The GeForce 8800M was developed to succeed the 8700M in the high-end market, and can be found in high-end gaming notebook computers.

Versions include the 8800M GTS and 8800M GTX. These were released as the first truly high-end mobile Geforce 8 Series GPUs, each with a 256-bit memory bus and a standard 512 megabytes of GDDR3 memory, and provide high-end gaming performance equivalent to many desktop GPUs. In SLI, these can produce 3DMark06 results in the high thousands.^[40]

Laptop models which include the 8800M GPUs are: Sager NP5793, Sager NP9262, Alienware m15x and m17x, HP HDX9494NR and Dell M1730. Clevo also manufactures similar laptop models for CyberPower, Rock, and Sager (among others) - all with the 8800M GTX, while including the 8800M GTS in the Gateway P-6831 FX and P-6860 FX models.

GeForce 8800 Series

2009-07-07T10:35:00.004-07:00

The 8800 series, codenamed G80, was launched on November 8, 2006 with the release of the GeForce 8800 GTX and GTS. A 320 MB GTS was released on February 12 and the Ultra was released on May 2, 2007. The cards are larger than their predecessors, with the 8800 GTX measuring 10.6 in (~26.9 cm) in length and the 8800 GTS measuring 9 in (~23 cm). Both cards have two dual-link DVI connectors and a HDTV/S-Video out connector. The 8800 GTX requires 2 PCIe power inputs to keep within the PCIe standard, while the GTS requires just one.

EVGA GeForce 8800 GTX

8800 GS

The 8800 GS is a trimmed-down 8800 GT with 96 stream processors and 384 MB of RAM on a 192-bit bus.^[14] In May 2008, it was rebranded as the 9600 GSO in an attempt to spur sales.

On April 28 2008, Apple announced an updated iMac line featuring an 8800 GS.^[15] However, the GPU is actually a rebranded NVIDIA GeForce 8800M GTS.^{[citation needed]} It features up to 512 MB of 800 MHz GDDR3 video memory, 64 unified stream processors, a 500 MHz core speed, a 256-bit memory bus width, and a 1250 MHz shader clock.^[16]

Underside

8800 GTX / 8800 Ultra

The 8800 GTX is equipped with 768 MB GDDR3 RAM. The 8800 series replaced the GeForce 7950 Series as NVIDIA's top-performing consumer GPU. GeForce 8800 GTX and GTS use identical GPU cores, but the GTS model disables parts of the GPU and reduces RAM size and bus width to lower production cost.

As of September 2007^[update], the G80 was the largest commercial GPU ever constructed. It consists of 681 million transistors covering a 480 mm² die surface area built on a 90 nm process. (In fact the G80's total transistor count is ~686 million, but since the chip was made on a 90 nm process and due to process limitations and yield feasibility, NVIDIA had to break the main design into two chips: Main shader core at 681 million transistors and NV I/O core of about ~5 million transistors making the entire G80 design standing at ~686 million transistors).

A minor manufacturing defect related to a resistor of improper value caused a recall of the 8800 GTX models just two days before the product launch, though the launch itself was unaffected.^[17]

BFG 8800GTX with the heatsink removed

The GeForce 8800 GTX was by far the fastest GPU when first released, and 13 months after its initial debut it still remained one of the fastest. The GTX has 128 stream processors clocked at 1.35 GHz, a core clock of 575 MHz, and 768 MB of 384-bit GDDR3 memory at 1.8 GHz, giving it a memory bandwidth of 86.4 GB/s. The card performs faster than a single Radeon HD 2900 XT, and faster than 2 Radeon X1950 XTXs in Crossfire^{[clarification needed]} or 2 Geforce 7900 GTXs in SLI.^{[clarification needed]} The 8800 GTX also supports HDCP, but one major flaw is its older NVIDIA Purevideo processor that uses more CPU resources. Originally retailing for around US$600, prices came down to under US$400 before it was discontinued. The 8800 GTX is also very power hungry, using up to 185 watts of power and requiring two PCI-E power connectors to operate. The 8800 GTX also has 2 SLI connector ports, allowing it to support NVIDIA 3-way SLI for users who run demanding games at extreme resolutions such as 2560x1600.

The 8800 Ultra, retailing at a higher price,^{[clarification needed]} is identical to the GTX architecturally, but features higher clocked shaders, core and memory. Nvidia later^[when?] told the media the 8800 Ultra was a new stepping,^{[clarification needed]} creating less heat^{[clarification needed]} therefore clocking higher. Originally retailing from $800 to $1000, most users thought the card to be a poor value, offering only 10% more performance than the GTX but costing hundreds of dollars more. Prices dropped to as low as $500 before being discontinued on January 23, 2008. The core clock of the Ultra runs at 612 MHz, the shaders at 1.5 GHz, and finally the memory at 2.16 GHz, giving the Ultra a theoretical memory bandwidth of 103.7 GB/s. It has 2 SLI connector ports, allowing it to support NVIDIA 3-way SLI. An updated dual slot cooler was also implemented, allowing for quieter and cooler operation at higher clock speeds.^[18]

8800GT with cover removed.

8800 GT

The 8800 GT, codenamed G92, was released on October 29, 2007. The card is the first to transition to 65 nm process, and supports PCI-Express 2.0.^[19] It has a single-slot cooler as opposed to the double slot cooler on the 8800 GTS and GTX, and uses less power than GTS and GTX due to its 65 nm process. While its core processing power is comparable to that of the GTX, the 256-bit memory interface and the 512 MB of GDDR3 memory often hinders its performance at very high resolutions and graphics settings. The 8800 GT, unlike other 8800 cards, is equipped with the PureVideo 2 engine for GPU assisted decoding of the H.264 and VC-1 codecs. Performance benchmarks at stock speeds place it above the 8800 GTS (640MB and 320MB versions) and slightly below the 8800 GTX. A 256MB version of the 8800 GT which lower stock memory speeds (1.4 GHz as opposed to 1.8 GHz) but with the same core is also available. Performance benchmarks have shown that the 256 MB version of the 8800 GT has a considerable performance disadvantage when compared to its 512 MB counterpart, especially in newer games such as Crysis. Some manufacturers also make models with 1 GB of memory; and with large resolutions and big textures one can perceive a performance difference in the benchmarks. These models are more likely to take up to 2 slots of your computer.

The release of this card presents an odd dynamic to the graphics processing industry. At an NVIDIA projected initial street price of around $200, this card outperforms the ATI flagship HD2900XT and HD3870 in most situations, and even NVIDIA's own 8800 GTS 640mb (previously priced at an MSRP of $400). The card, only marginally slower in synthetic and gaming benchmarks than the 8800 GTX, also takes much of the value away from NVIDIA's own high end card. This release was shortly followed by the (EVGA) 8800 GTS SSC (the original 8800 GTS re-released with 96+ (112) shader processor units), and ATI's counter, the HD 3800 series.

The remaining 8800 GT cards are now being re-branded and sold under the 9800 GT name. (Once stocks of G92 chips run out, 9800 GT will receive a 55 nm chip.)^{[citation needed]}

Compatibility issue with PCI-E 1.0a

Shortly after the release, an incompatibility issue with older PCI Express 1.0a motherboards was unmasked. When using the PCI Express 2.0 compliant 8800 GT in some motherboards with PCI Express 1.0a slots, the card would not produce any display image, but the computer would often boot (with the fan spinning at a constant 100%). The incompatibility is mostly with motherboards with VIA PCI-E 1.0a chipsets.^{[citation needed]}

Some graphics cards had a workaround, which was to re-flash the graphics card's BIOS with an older GEN1 BIOS. However this effectively made it into a PCI Express 1.0 card, not being able to utilize the PCIE 2.0 functions. This could be considered a non-issue however since the card itself could not even utilize the full capacity of the regular PCIE 1.0 slots, there was no noticeable performance reduction. Also flashing of the video card BIOS voided the warranties of most video card manufacturers (if not all) thus making it a less-than-optimum way of getting the card to work properly. A workaround to this is to flash the BIOS of the motherboard to the latest version, which depending on the manufacturer of the motherboard, may contain a fix. In relation to this compatibility issue, the high numbers of cards reported as DOA (as much as 13-15%) were believed to be inaccurate. When it was revealed that the G92 8800 GT and 8800 GTS 512MB were going to be designed with PCI Express 2.0 connections, NVIDIA claimed that all cards would have full backwards-compatibility, but failed to mention that this was only true for PCI Express 1.1 motherboards. The source for the BIOS-flash did not come from NVIDIA or any of their partners, but rather ASRock, a mainboard producer, who mentioned the fix in one of their motherboard FAQs. ASUSTek, sells the 8800 GT with their sticker, posted a newer version of their 8800 GT BIOS on their website, but did not mention that it fixed this issue. EVGA also posted a new bios to fix this issue.^[20]

8800 GTS

The first releases of the 8800 GTS line, in November 2006, came in 640 MB and 320 MB configurations of GDDR3 RAM and utilized NVIDIA's G80 GPU.^[21] While the 8800 GTX has 128 stream processors and a 384-bit memory bus, these versions of 8800 GTS feature 96 stream processors and a 320-bit bus. With respect to features, however, they are identical because they use the same GPU. ^[22]

Around the same release date as the 8800 GT, NVIDIA released a new 640 MB of the 8800 GTS. While still based on the 90 nm G80 core, this version has 7 out of the 8 clusters of 16 stream processors enabled (as opposed to 6 out 8 on the older GTSs), giving it a total of 112 stream processors instead of 96. Most other aspects of the card remain unchanged. However, because the only 2 add-in partners who are making this card (BFG and EVGA) have decided to overclock it, this version of the 8800 GTS actually runs slightly faster than a stock GTX in most scenarios, especially at higher resolutions, due to the increased clock speeds.^[23]

NVIDIA released a new 8800 GTS 512MB based on the 65 nm G92 GPU on December 10, 2007.^[24] This 8800 GTS has 128 stream processors, compared to the 96 processors of the original GTS models. It is equipped with 512 MB GDDR3 on a 256-bit bus. Combined with a 650 MHz core clock and architectural enhancements, this gives the card raw GPU performance exceeding that of 8800 GTX, but it is constrained by the narrower 256-bit memory bus. Its performance can match the 8800 GTX in some situations, and it outperforms the older GTS cards in all situations.^[24]

GeForce 8500 and 8600 Series

2009-07-07T10:35:00.003-07:00

On April 17, 2007, NVIDIA released the GeForce 8500 GT, 8600 GT, and 8600 GTS for the mainstream market.

The GeForce 8500 GT isn't considered to be a high-end GPU, and has similar specifications to a GeForce 6600 GT.^[9] The 8500 GT is roughly half as fast as the GeForce 8600 GT, which has been considered disappointing and underpowered by many.^{[citation needed]} The main criticism is that the card does not outperform the higher-end cards from the previous GeForce series as well as other mid-ranges cards have in the past. For example, the 8600 GT only averages of approximately twenty percent improvement in framerates of most games over its predecessor, the GeForce 7600 GT. In some games, it can also be slightly slower or on par with the 7600 GT.^[10]. It's generally about as fast as a 7800 GT, which in turn doesn't make it faster than a GeForce 7600 GT (or any card of equal range, e.g. the GeForce 6800 Ultra, Radeon X1800 GTO, Radeon X850 XT, Radeon X800 XT, and Radeon X1650 XT).^{[citation needed]} However, because of the 8600 GT's higher number of stream processors and higher shader clocks, it generally performs better than its GeForce 7 predecessors in games that enhance the shaders. ^[11]

A 8600 GTS is about 15%-40% faster,^{[clarification needed]} and while overall, it's generally on pretty equal grounds with a GeForce 7900 GS (or anything of equal range, e.g. the 256MB GeForce 7800 GTX, a 256MB GeForce 7900 GT, a 256MB Radeon X1800 XT, etc) but, like the 8600 GT, it has an advantage in shader-heavy games for the same reasons, and outguns the 7900 GS in modern games by quite an amount.^{[clarification needed]}

The GeForce 8600 series in particular is hampered by its lack of potential processing power, having only 25% of the full G80 core's stream processors. The series also has a comparatively narrow 128-bit memory bus. Older video cards in the same price range, such as the GeForce 7900 series, featured a 256-bit memory bus.^[12] However, the series' lower power requirements of only a 350-watt power supply make it a possible choice for upgrading computers with weaker power supplies. In comparison, the 8800 GT requires a 400-watt power supply. ^[13]

Also compared with the high end 8800, the midrange 8600 and 8500 are extremely outperformed. However, some GPU mod enthusiasts have been able to push the cards to much higher speeds, in some cases almost double, by modifying the voltage.^{[citation needed]}

NVIDIA introduced one notable feature with the 8500/8600 series: 2nd-generation PureVideo. The first major update to PureVideo since the GeForce 6's launch, 2nd-gen PureVideo offered much improved hardware-decoding for VC-1 and H264 video.

GeForce 8300 and 8400 Series

2009-07-07T10:35:00.001-07:00

In the summer of 2007, NVIDIA released the entry level GeForce 8300 and 8400 series of graphics cards. Both series are based on the G86 core and as of December 2007, both series only have a GS version. The GeForce 8300 is also only available in the OEM market, and thus cannot be found in retail outlets. These graphics cards are targeted mainly for those who just need a discrete graphics solution, as the video card performs poorly in intense 3D applications such as high-end video games. It was originally designed to replace the 7200 and 7300 models, but was incapable of doing so due to its poor performance in high-end video games. It's able to play modern games at playable framerates at low settings and low resolutions making it popular among casual gamers and HTPC (Media Center) builders without a PCI Express or AGP motherboard.

At the end of 2007, NVIDIA released a new Geforce 8400 GS based on the G98 (D8M) chip.^[8] It is quite different from the G86 used for the "first" 8400 GS, as the G98 features VC-1 video decoding completely in hardware, lower power consumption, lowered 3D-performance and a smaller fabrication process. The G98 also features dual-link DVI support and PCI Express 2.0. G86 and G98 cards are both sold as "8400 GS", the difference can only be told from technical specifications.

GeForce 8 Series

2009-07-07T10:33:00.000-07:00

The GeForce 8 Series is a computer graphics processing unit the eighth generation of NVIDIA's GeForce line. The third major GPU architecture developed at NVIDIA, the Geforce 8 represents the company's first unified shader architecture.^[1]^[2]

NVIDIA GeForce 8 Series

Codename(s)	G80, G84, G86, G92, G98
Release date	2006
Entry-level GPU	8100 (IGP), 8200 (IGP), 8300 (both integrated and discrete variants), 8400
Mid-Range GPU	8500, 8600
High-end GPU	8800
Direct3D and Shader version	D3D 10.0, Model 4.0

[hide]

1 GeForce 8 Series overview
2 GeForce 8300 and 8400 Series
3 GeForce 8500 and 8600 Series
4 GeForce 8800 Series
5 GeForce 8M Series
6 Caveat
7 See also
8 References
9 External links
GeForce 8 Series overview
3D rendering

The GeForce 8 series arrived with NVIDIA's first unified shader Direct3D 10 Shader Model 4.0 / OpenGL 2.1 architecture. The design is a major shift for NVIDIA in GPU functionality and capability, the most obvious change being the move from the separate functional units (pixel shaders, vertex shaders) within previous GPUs to a homogeneous collection of universal floating point processors (called "stream processors") that can perform a more universal set of tasks.

Model Adrianne Curry watching a 3D animation of herself during a GeForce 8 demo.

GPU NVIDIA G80.

GeForce 8's unified shader architecture consists of a number of stream processors (SPs). Unlike the vector processing approach taken with older shader units, each SP is scalar and thus can operate only on one component at a time. This makes them less complex to build while still being quite flexible and universal. Scalar shader units also have the advantage of being more efficient in a number of cases as compared to previous generation vector shader units that rely on ideal instruction mixture and ordering to reach peak throughput. The lower maximum throughput of these scalar processors is compensated for by efficiency and by running them at a high clock speed (made possible by their simplicity). GeForce 8 runs the various parts of its core at differing clock speeds (clock domains), similar to the operation of the previous GeForce 7 Series GPUs. For example, the stream processors of GeForce 8800 GTX operate at a 1.35 GHz clock rate while the rest of the chip is operating at 575 MHz.^[2]

GeForce 8 performs significantly better texture filtering than its predecessors that used various optimizations and visual tricks to speed up rendering while impairing filtering quality. The GeForce 8 line correctly renders an angle-independent anisotropic filtering algorithm along with full trilinear texture filtering. G80, though not its smaller brethren, is equipped with much more texture filtering arithmetic ability than the GeForce 7 series. This allows high-quality filtering with a much smaller performance hit than previously.^[2]

NVIDIA has also introduced new polygon edge anti-aliasing methods, including the ability of the GPU's ROPs to perform both Multisample anti-aliasing (MSAA) and HDR lighting at the same time, correcting various limitations of previous generations. GeForce 8 can perform MSAA with both FP16 and FP32 texture formats. GeForce 8 supports 128-bit HDR rendering, an increase from prior cards' 64-bit support. The chip's new anti-aliasing technology, called coverage sampling AA (CSAA), uses Z, color, and coverage information to determine final pixel color. This technique of color optimization allows 16X CSAA to look crisp and sharp.^[3]

The claimed theoretical processing power for the 8 Series cards given in FLOPS may not be correct at all times. For example the GeForce 8800 GTX has 518.43 GigaFLOPs theoretical performance given the fact that there are 128 stream processors at 1.35 GHz with each SP being able to run 1 Multiply-Add and 1 Multiply instruction per clock [(MADD (2 FLOPs) + MUL (1 FLOP))×1350MHz×128 SPs ＝ 518.4 GigaFLOPs]^[4]. This figure may not be correct because the Multiply operation is not always available^[5] giving a possibly more accurate performance figure of (2×1350×128) = 345.6 GigaFLOPs.
Max Resolution

Dual Dual-link DVI Support: Able to drive the industry's largest and highest resolution flat-panel displays up to 2560x1600. Available on select GeForce 8800 and 8600 GPUs.

One Dual-link DVI Support: Able to drive the industry's largest and highest resolution flat-panel displays up to 2560x1600. Available on select GeForce 8500 GPUs and Geforce 8400 GS cards based on the G98.

One Single-link DVI Support: Able to drive the industry's largest and highest resolution flat-panel displays up to 1920x1200. Available on select GeForce 8400 GPUs.^[6] Geforce 8400 GS cards based on the G86 only support single-link DVI.
Display capabilities

The GeForce 8 series supports 10-bit per channel display output, up from 8-bit on previous NVIDIA cards. This potentially allows higher fidelity color representation and separation on capable displays. The GeForce 8 series, like its recent predecessors, also supports Scalable Link Interface (SLI) for multi-card rendering.

NVIDIA's PureVideo HD video rendering technology is an improved version of the original PureVideo introduced with GeForce 6. It now includes GPU-based hardware acceleration for decoding HD movie formats, post-processing of HD video for enhanced images, and optional High-bandwidth Digital Content Protection (HDCP) support at the card level.^[7]

GeForce 7900 Series

2009-07-07T10:27:00.000-07:00

Nvidia officially announced availability of the GeForce 7900 series on March 9, 2006.^[17]

Nvidia's 7900 series is a product refresh and not a new generation of Nvidia's GPU, running at 650 MHz. Officially this series is meant to support only PCI Express Interface but some companies released AGP versions.

A total of 5 models have been developed and are available: 7900 GX2, 7900 GTX, 7900 GT, 7900 GTO and 7900 GS.

Advanced Features Support

The 7900 series supports following advanced features:

Intellisample 4.0 Technology
Scalable Link Interface (SLI) Technology
Extreme HD Technology
High dynamic range rendering Technology
UltraShadow II Technology
CineFX 4.0 Engine
Nvidia PureVideo Technology

GeForce 7900 GS

Introduced during the fall of 2006, At a MSRP of US$199,^[18] the 7900 GS filled the gap between the mid-end GeForce 7600 GT and the high-end GeForce 7900 GT. The card was unofficially launched August 23 by woot! as a white box OEM. However, the product's company, MSI, made claims that these cards were stolen from MSI during transportation and sold to woot!.^[19] The referenced MSI customer notice has been changed to remove explicit references to woot!. As of March 2007, Nvidia had discontinued production of a number of GeForce 6 and 7 series products, including the 7900 GS.

The GeForce 7900 GS has 20 pixel processors, 7 vertex processors, 256-bit memory bus, and comes clocked at approximately 450 MHz/1320 MHz for core/memory, which should provide slightly lower performance than the 7900 GT. The GeForce 7900 GS is powered by the latest graphics chip code-named G71, thus, shares the same advantages as the G71 did over its immediate predecessor G70: dual-link DVI outputs, reduced power consumption, higher performance.^[20]

Performance Specs

Core Clock Speed: 450 MHz
Memory Interface: 256-bit
Memory Bandwidth: 42.2 GB/s memory bandwidth
Fill Rate: 9 Billion pixel/s
Vertex/s: 822.5 Million
Shader Power: 20 pixels per clock
SLI Support (PCI-E model only)
Memory Type: GDDR3

NOTE: XFX has developed AGP versions of this card as well.^[21]

GeForce 7900 GT

This video card was released on March 9, 2006. Like the 7900 GTX, it is a revised version of the G70 GPU (G71) that is produced at 90 nm. It too offers all the features of the 7800 series as well as an attractive performance-to-price ratio.

Performance Specs:

Core Clock Speed: 450 MHz
Memory Interface: 256-bit
Memory Bandwidth: 42.2 GB/s memory bandwidth
Fill Rate: 10.8 Billion pixel/s
Vertex/s: 940 Million
Shader Power: 24 pixels per clock
Memory Type: GDDR3

GeForce 7900 GTX

The GeForce 7900 GTX is the latest revision of the G70 Core, this 90 nm produced G70 (named G71) features all the same features as its older brother the 7800 GTX but is built upon the smaller manufacturing process.

Featuring a clock speed of 650 MHz, opposed to the 550 MHz speed of the 512 GTX, this card offers up to an 8 - 15% performance increase. It features a new 24 pixel shader design superscalar GPU model, much like the 512 MB 7800 GTX, but offers faster performance due to "improved pipeline design". "We changed the ROP performance as well as reconfigured some of the pipelines to make sure the card was more optimized over G70," Nvidia said.

Due to shortages of memory modules for the 512 MB GTX, Nvidia decided to use the more readily available 1600 MHz memory. This also allows the card to be priced very competitively, giving ATI Technologies a harder time. In turn, ATI made a massive price slash in its current lineup. It was released on March 9, 2006.

Performance Specs

Core Clock Speed: 650 MHz
Memory Interface: 256-bit
Memory Bandwidth: 51.2 GB/s memory bandwidth
Fill Rate: 15.6 Billion pixel/s
Vertex/s: 1.4 Billion
Shader Power: 24 pixels per clock
Memory Type: GDDR3

GeForce 7900 GTO

The 7900 GTO is a close cousin of the 7900 GTX.^[22] The GTO first arrived at a handful of retailers around October 1, 2006. At the time of launch, GTO boards sold for around US$250, compared to the 7900 GTX boards that cost in excess of $400 at the time. The GTO was essentially identical to the GTX, with the exception that it lacked HDCP and VIVO support, had underclocked memory running at 1320 MHz, and used tighter memory timings. Other than that, the two boards were identical: same PCB, same cooler, same GPU. The GTO used extremely fast 1.1ns Samsung BJ11 GDDR3 memory running at 1.8V, as opposed to the 2.1V it is rated at. Clock speeds on the two cards are identical, at 650 MHz. At stock memory speeds, most comparisons found the GTO to lag behind the GTX by roughly a 5-10% margin.

The majority of owners find that their GTO will overclock to 1600 MHz memory speeds, despite the under-volted RAM. Many flash their GTO to a GTX BIOS to officially make it a GTX. GTO owners having trouble reaching GTX speeds with BIOS version 5.71.22.39.13 or newer are advised to simply flash to an older BIOS version such as 5.71.22.39.08, this seems to solve overclocking problems for most users.

The GTO was an extremely popular card among enthusiasts as it offered near GTX performance at a considerably lower price. It was a limited production card aimed at cleaning out G70 inventories before the release of the G80, and only spent about a month in retail channels before selling out.

GeForce 7900 GX2

The GeForce 7900 GX2 is two videocards stacked to fit as a dual slot solution.^[23] This is not like products such as the ASUS Dual GeForce 7800 GT or nVidia's own 7950 GX2, where two GPUs are on the same card. This enables quad-SLI on two PCI Express x16 slots. Other OEM companies have access to the GX2 and it is now available from numerous vendors.

The card features a 500 MHz GPU and 1200 MHz effective RAM speed. Although the power of the GX2 is less than the 7900 GTX, each card is more powerful than the 7900 GT.

Many issues in this implementation of a dual-GPU unit convinced Nvidia to restrict its sale to OEM companies. The card is extremely long, with only the largest e-ATX cases being able to hold it. Two of the cards operating in quad-SLI also required extremely well designed airflow to function, and demanded a 1000 watt power supply unit.

GeForce 7950 Series

GeForce 7950 Series is the last addition in the GeForce 7 series. Officially this series was meant to only support PCI Express interface but some companies have released AGP versions as well.

Two models are available: 7950 GT and 7950 GX2.^[24]

Advanced Features Support

The 7950 series supports following advanced features:

Intellisample 4.0 Technology
Scalable Link Interface (SLI) Technology
High dynamic range rendering Technology
UltraShadow II Technology
CineFX 4.0 Engine
Nvidia PureVideo HD Technology

GeForce 7950 GT

On 14 September 2006 Nvidia released the 7950GT. Announced with a 550 MHz core clock, 700 MHz (1400 MHz effective) memory clock, 24 pixel shader units, standard configurations come equipped with both 512 MB GDDR3 memory and HDCP support. At an introductory price of US$300, the GeForce 7950 GT replaces the older GeForce 7900 GT and improves performance: the GeForce 7950 GT has a fillrate of 13,200 Megatexels/s and a memory bandwidth of 44.8 GB/s (versus 10800 Megatexels/s and 940 Megavertices/s for the 7900 GT).

Performance Specs

Memory Interface: 256-bit
Memory Bandwidth: 44.8 GB/s memory bandwidth
Fill Rate: 13.2 Billion pixel/s
Vertex/s: 1.1 Billion
Shader Power: 24 pixels per clock
SLI Support (PCI-E model only)
Memory Type: GDDR3

NOTE: XFX has developed and released AGP versions of this card. ^[25]

GeForce 7950 GX2

This is essentially a dual-GPU video card that takes up only a single PCIe x16 slot, allowing for 4 GPUs to run with only two PCIe x16 slots, in standard SLI motherboards. Unlike the 7900 GX2 before it, this version is available to consumers directly.^[26]

The 7950 GX2 was released to retail on June 5, 2006, and shares similar specs to the GeForce 7900 GX2, with 500 MHz GPU clock, and 1200 MHz effective RAM speed. 512 MB of memory per GPU, for a total of 1 GB, however total performance is more in line with 512 MB since each GPU can only access its own memory and not the memory of the other one. It does not offer any advantages over single-GPU cards with 512 MB, memory wise.

This card is designed for the DIY market; it addresses many problems which the previous 7900 GX2 had suffered from, such as noise, size, power consumption, and price. The 7950 GX2 requires only a single PCIe power connector, in contrast to the twin-connectors of its predecessor; technically, this is understandable, as there is no need for a ring bus configuration – frames need only be passed on to the primary GPU. It is much shorter, fitting easily in the same space as a 7900 GTX. Lesser board layout and the removal of cooling vents on the bracket have greatly declined cooling, allowing the fans to run at a lower speed, thereby lowering noise. As of September 2006, the board can be found for $299, half the cost of a 7900 GX2.

According to some review sites (such as Tom's Hardware - see above), a single 7950GX2 draws less power than a single ATI Radeon X1900 XT – some consider this an amazing feat considering the GX2 employs a pair of GPUs, when the Radeon uses only one. Other review sites say that a GX2 is quieter than the aforementioned Radeon,^[27] despite the GX2 boasting a pair of identical GPU coolers – however 'loudness' is highly subjective without the proper tools and testing conditions. If true, this would make a pair of GX2 cards cooler, quieter, and less power hungry than a pair of X1900 XT cards in CrossFire. However, there is no appreciable performance gain from pairing two 7950 GX2 cards in most applications, while dual X1900 XT configurations see large performance boosts in CrossFire mode.^{[citation needed]}

Performance Specs

Memory Interface: 2x 256-bit
Memory Bandwidth: 76.8 GB/s memory bandwidth
Fill Rate: 24 Billion pixel/s
Vertex/s: 2 Billion
Shader Power: 48 pixels per clock
Memory Type: GDDR3

On August 9, 2006, Nvidia released initial 91.45 drivers for Windows 2000 and XP that support Quad SLI.^[28] The Quad SLI support was soon merged in with the normal WHQL driver package, when version 91.47 was released on October 16, 2006.^[29]

GeForce Go 7 Series

Nvidia has not only targeted the desktop market but also the notebook market with the GeForce 7 series.^[30]

Advanced Features Support

The GeForce Go 7 series supports following advanced features:

Intellisample 4.0 Technology
Scalable Link Interface (SLI) Technology
Extreme HD Technology
PowerMizer Mobile Technology
MXM Graphics Module Technology
High dynamic range rendering Technology
UltraShadow II Technology
CineFX 4.0 Engine
Nvidia PureVideo HD Technology

The GeForce Go 7 GPU series line-up

The GeForce Go 7 GPU series line-up consists of following models:

GeForce Go 7950
GeForce Go 7900
GeForce Go 7800
GeForce Go 7700
GeForce Go 7600
GeForce Go 7400
GeForce Go 7300
GeForce Go 7200
GeForce Go 7150
GeForce Go 7000

GeForce 7800 Series

2009-07-06T10:11:00.000-07:00

GeForce 7800 Series

The 7800 series was designed to deliver exceptional performance and was targeted towards high-end market segment. This series has been discontinued and was replaced with the 7900 series in early 2006.

A total of 4 models were available: GeForce 7800 GTX 512, GeForce 7800 GTX, GeForce 7800 GT, and GeForce 7800 GS.^[11]

Advanced Features Support

The 7800 series supports following advanced features:

Intellisample 4.0 Technology
Scalable Link Interface (SLI) Technology
High dynamic range rendering Technology
UltraShadow II Technology
CineFX 4.0 Engine
Nvidia PureVideo Technology

GeForce 7800 GT

The GeForce 7800 GT is the second GPU in the series, launched on August 11, 2005 with immediate retail availability. It has 20 pixel pipelines, 7 vertex shaders, 16 ROPs and a 400 MHz core clock, 500 MHz memory clock (1 GHz effective) using GDDR3 memory.

The GeForce 7800 GT had been introduced as a more affordable alternative to the 7800 GTX. At the time it was considered the performance/cost champion of video cards.

GeForce 7800 GS AGP

On February 2, 2006, Nvidia announced the 7800 GS as the first AGP video card in the GeForce 7 series lineup, an AGP version of the high-end GeForce 7 Series.^[12]

A BFG TECH 7800 GS AGP

This card was promoted by several hardware enthusiasts as "the last high-ended AGP card in existence". It has 16 pixel shader units instead of the 20 that the 7800 GT has, but still benefits from the optimizations of the other 7-series GPUs enjoy. Clock speeds are 375 MHz for the GPU and 1200 MHz for the (GDDR3) memory. According to all benchmark tests, the performance of this card is faster than the GeForce 6800 GT and GeForce 6800 Ultra. Different vendors may deviate from the stated specification. It serves to provide a great upgrade path for those with high-end AGP systems who don't want to switch to a new high-end PCI-Express system.^[13] There was a special "Golden Sample" release from Gainward that was called "7800 GS+" or officially "Bliss 7800 GS 512 MB GS+" that had default clock speeds of 450 MHz core and 1250 MHz memory. Unlike a standard 7800 GS, the 7800 GS+ actually used a 7900 GT GPU that had the full 24 pixel shaders instead of the regular 16 pixel shaders that are normally found on a 7800 GS video card.

Gainward had previously released a "Bliss 7800 GS 512MB GS" card that was based on a 7800 GT but utilized the AGP bus. Its external appearance and name make it nearly indistinguishable from the 7900 GT-based Bliss 7800 GS 512MB GS+. Leadtek produced a similar card with 256MB memory.

In late 2006 Gainward released a third '7800 GS' card with 20 pixel shaders running at 500 MHz core and 1400 MHz memory called the "BLISS GS-GLH". This card is also based on the 7900 GS core.

There are no after-market cooling systems for the 7800 GS, stock cooling in the GeForce 7800 GS AGP is adequate. The board layout is radically different from other GeForce 7 boards so no universal aftermarket coolers would fit without significant modification to their mounting mechanisms.

GeForce 7800 GTX

The GeForce 7800 GTX (codenamed G70, and previously NV47) was the first GPU in the series, launched on June 22, 2005 with immediate retail availability. The GeForce 7800 GTX supported the highest specification DirectX 9 vertex and pixel shaders, at the time: Version 3.0. It was natively a PCI Express chip. SLI support had been retained and improved from the previous generation.

According to PC World, the 7800 GTX was "one of the most complex processors ever designed". The GPU had 302 million transistors (the Athlon 64 X2 4800+ CPU has 233.2 million transistors), along with 24 pixel and 8 vertex shaders.^[14] This card included new standard features, such as subsurface scattering^{[citation needed]}, HDR lighting, and radiosity^{[citation needed]}, to name a few. It was succeeded by the 7900 GTX on March 9, 2006.

Here is how the released versions of the "GeForce 7" series family compare to Nvidia's previous flagship GPU, the GeForce 6800 Ultra, and ATI's Radeon X1800 XT:

	GeForce 6800 Ultra	GeForce 7300 GS	GeForce 7600 GT	GeForce 7800 GTX	GeForce 7900 GTX	Geforce 7950 GX2	ATI Radeon X1800 XT	ATI Radeon X1900 XTX
Transistor count	222 million	112 million	178 million	302 million	278 million	2 * 278 Million	321 million	384 million
Manufacturing process	130 nm	90 nm	90 nm	110 nm	90 nm	90 nm	90 nm	90 nm
Die Area	288 mm²	77 mm²	125 mm²	333 mm²	196 mm²	2 * 196 mm²	288 mm²	352 mm²
Core clock speed	400 MHz	550 MHz	560 MHz	430 MHz	650 MHz	500 MHz	625 MHz	650 MHz
Number of Pixel Shader units	16	4	12	24	24	48	16	48
MADD ALUs per PS unit	1	2	2	2	2	2	1	1
Number of ROPs	16	2	8	16	16	32	16	16
Number of TMUs	16	4	12	24	24	48	16	16
Number of vertex pipelines	6	3	5	8	8	16	8	8
Peak pixel fill rate (theoretical)	6.4 Gigapixel/s	1.1 Gigapixel/s	4.48 Gigapixel/s	6.88 Gigapixel/s	10.4 Gigapixel/s	16.0 Gigapixel/s	10.0 Gigapixel/s	10.4 Gigapixel/s
Peak texture fill-rate (theoretical)	6.4 Gigatexel/s	2.2 Gigatexel/s	6.72 Gigatexel/s	10.32 Gigatexel/s	15.6 Gigatexel/s	24.0 Gigatexel/s	10.0 Gigatexel/s	10.4 Gigatexel/s
On-board memory interface	256 (4*64-bit)	64 (1*64-bit)	128 (2*64-bit)	256 (4*64-bit)	256 (4*64-bit)	2 * 256(4*64-bit)	256 (8*32-bit)	256 (8*32-bit)
Memory clock speed	1.1 GHz GDDR3	810 MHz DDR2	1.4 GHz GDDR3	1.2 GHz GDDR3	1.6 GHz GDDR3	1.2 GHz GDDR3	1.5 GHz GDDR3	1.55 GHz GDDR3
Peak memory bandwidth	35.2 GB/s	6.5 GB/s	22.4 GB/s	38.4 GB/s	51.2 GB/s	76.8 GB/s	48.0 GB/s	49.6 GB/s
Power Consumption Idle ^[15]	? Watts	8.7 Watts	14.6 Watts	29 Watts	31 Watts	? Watts	30.2 Watts	29.5 Watts
Power Consumption Peak 2D	? Watts	10.3 Watts	22.5 Watts	52 Watts	52 Watts	? Watts	52.1 Watts	50.1 Watts
Power Consumption Peak 3D	? Watts	16.1 Watts	35.8 Watts	81 Watts	84 Watts	110 Watts	103.1 Watts	120.7 Watts

GeForce 7800 GTX 512

The 512 MB version of the GeForce 7800 GTX was released on November 14, 2005. The card features more than simply an increased frame buffer from 256 MB to 512 MB. The card features a much improved core clock speed of 550 MHz vs. 430 MHz (27.9% increase) and fast 1.1 ns GDDR3 memory clocked at 1.7 GHz vs. 1.2 GHz (41.7% increase), when compared to the original version. Like ATI's X1800 XT, the addition of another 256 MB of memory, and to a lesser extent, the increased clock speeds, have raised the heat and power output significantly. To combat this, the GeForce 7800 GTX 512 sports a much larger yet quieter dual slot cooling solution when compared to the original 256 MB version.^[16]

Performance Specs

Core Clock Speed: 550 MHz
Memory Interface: 256-bit
Memory Bandwidth: 54.4 GB/s memory bandwidth
Fill Rate: 13.2 billion pixel/s
Vertex/s: 1100 million
Shader Power: 24 pixels per clock
Memory Type: GDDR3

GeForce 7600 Series

2009-07-06T10:07:00.000-07:00

Nvidia announced immediate availability of the GeForce 7600 series on March 9, 2006. Currently two Models are available and these are GeForce 7600 GT and 7600 GS.^[6] This series is available with AGP and PCI-Express interfaces, covering a wide range of market segments.

This series was released to replace the older GeForce 6600 series.

Advanced Features Support:

The 7600 series supports following advanced features:

Intellisample 4.0 Technology
Scalable Link Interface (SLI) Technology
Extreme HD Technology
High dynamic range rendering Technology
UltraShadow II Technology
CineFX 4.0 Engine
Nvidia PureVideo Technology

GeForce 7600 GS

A BFG 7600 GT

On March 22, 2006, Nvidia announced the immediate availability of the GeForce 7600 GS GPU targeted at the low-mid end. This new GPU assumed the place of the GeForce 6600 GT, which had been around for quite some time.

The AGP version was introduced in July 21, 2006. According to Nvidia, this card is identical to the PCI-e version other than the interface. In addition, the AGP version uses Nvidia's AGP-PCIe bridge chip.

Performance Specs:

Core Clock Speed: 400 MHz core frequency
Memory Clock Speed: 400 MHz (800 MHz effective)
Memory Interface: 128-bit
Memory Bandwidth: 12.8 GB/s
Fill Rate: 3.2 billion pixel/s and 4.8 billion texel/s
Vertex/s: 500 million
SLI support (Only for the PCIe version)
Cooling Solution: Passively cooled (Nvidia reference)
Memory Type: GDDR3 or DDR-2

Preliminary testing showed that the GeForce 7600 GS outperforms a GeForce 6600 GT and ATI's counterpart, the ATI Radeon X1600 Pro.^[7]

GeForce 7600 GT

This is the high-mid range product in the 7 Series family.

Performance Specs:

Core Clock Speed: 560 MHz
Memory Clock Speed: 700 MHz (1400 MHz effective)
Memory Interface: 128-bit
Memory Bandwidth: 22.4 GB/s memory bandwidth
Fill Rate:4.48 billion pixel/s and 6.72 billion texel/s
Vertex/s: 700 million
SLI Support (for PCI-E Model)
Shader Power: 12 pixels per cycle
Memory Type: GDDR3 or DDR2

The 7600 contains all the features of the GeForce 7 family, and is priced rather low for the mainstream market. It was made to provide a Geforce 7 series card to the mass market. By using the same PCB and GPU socket as the 6600, manufacturing costs should be lower due to available parts left over; and the fact that it is built on a smaller wafer. When benchmarks revealed that the 7600 GT seriously outperformed its original market opponent, the ATI Radeon X1600 XT, ATI reduced prices of its Radeon X850XT PE (the fastest video card of its previous-generation product line) and introduced the X1800 GTO, which was slightly more expensive than the 7600 GT, but marginally faster thanks to its 256-bit memory bus, higher peak pixel fill rate and more raw shading power. However, the memory speeds in the 7600 GT are underclocked, leaving quite a lot of headroom for overclocking. Card manufacturer Leadtek introduced an AGP version of the card in August 2006, which was one of the few AGP cards in the market including the new, faster, GDDR3 memory.^[8]

GeForce 7650 Series

GeForce 7650 GS

The GeForce 7650GS was never officially released, and was limited to a few OEM cards only. This card is seemingly very rare. Performance is speculated to be very similar to the 7600GS. Not much is known about this card, other than that it uses the 80 nm process.

Performance Specs:

These specifications are based on a card manufactured by Asus.^[9] There might be differences between OEM cards.

Core Clock Speed: 400 MHz core frequency
Memory Clock Speed: 400 MHz (800 MHz effective)
Memory Interface: 128-bit
Memory Bandwidth: 12.8 GB/s
Fill Rate: 3.6 GPixel/s and 5.4 GTexel/s
Cooling Solution: Passively cooled
Memory Type: DDR-2

A card manufactured by MSI gives the same specification, however it has a 5.4 GTexel/s rating.^[10] This is caused by a bug in earlier versions of GPU-Z. Since version 0.2.0 the fillrate calculation on G73 chips is fixed, so even the card manufactured by ASUS would show the real 5.4 GTexel/s.

GeForce 7 Series

2009-07-06T10:02:00.000-07:00

The GeForce 7 Series is the seventh generation of Nvidia's GeForce graphics processing units. It is the last series to feature support for AGP.

Nvidia GeForce 7 Series
Codename(s)	G70 (NV47), G71, G72, G73
Release date	June 2005 - 2006
Entry-level GPU	7025 (IGP), 7050 (IGP), 7100 (both integrated and discrete variants), 7150 (IGP), 7200, 7300
Mid-Range GPU	7500, 7600, 7650
High-end GPU	7800, 7900, 7950
Direct3D and Shader version	DirectX 9.0c with Shader Model 3.0

[hide]

1 GeForce 7100 Series
- 1.1 GeForce 7100 GS
2 GeForce 7200 Series
- 2.1 GeForce 7200 GS
3 GeForce 7300 Series
- 3.1 GeForce 7300 SE
- 3.2 GeForce 7300 LE
- 3.3 GeForce 7300 GS
- 3.4 GeForce 7300 GT
4 GeForce 7500 Series
- 4.1 GeForce 7500 LE
5 GeForce 7600 Series
- 5.1 GeForce 7600 GS
- 5.2 GeForce 7600 GT
6 GeForce 7650 Series
- 6.1 GeForce 7650 GS
7 GeForce 7800 Series
- 7.1 GeForce 7800 GT
- 7.2 GeForce 7800 GS AGP
- 7.3 GeForce 7800 GTX
- 7.4 GeForce 7800 GTX 512
8 GeForce 7900 Series
- 8.1 GeForce 7900 GS
- 8.2 GeForce 7900 GT
- 8.3 GeForce 7900 GTX
- 8.4 GeForce 7900 GTO
- 8.5 GeForce 7900 GX2
9 GeForce 7950 Series
- 9.1 GeForce 7950 GT
- 9.2 GeForce 7950 GX2
10 GeForce Go 7 Series
11 See also
12 References
13 External links
GeForce 7100 Series
The 7100 series was introduced on August 30, 2006 and is based on GeForce 6200 Series architecture. This series supports only PCI Express interface. Only one model is available and it is called 7100 GS.^[1]

Advanced Features Support:

The 7100 series supports following advanced features:

Intellisample 4.0 Technology (but without GCAA)

Scalable Link Interface (SLI) Technology

TurboCache Technology

Nvidia PureVideo Technology

However it is important to note that 7100 series does not support technologies such as: high dynamic range rendering (HDR) and UltraShadow II.

NOTE: Some of the above mentioned supported features can be made accessible through using the ForceWare 91.47 driver or later releases.
GeForce 7100 GS

Although the 7300 LE was originally intended to be the "lowest budget" GPU from the GeForce 7 lineup, the 7100 GS has now taken its place. As it is little more than a revamped version of the GeForce 6200TC, it is designed as a basic PCI-e solution for OEMs to use if the chipset does not have integrated video capabilities. It comes in a PCI Express Graphics Bus and 512MB DDR2 VRAM.

Performance specification
Graphics Bus: PCI Express
Memory Interface: 64-bit
Memory Bandwidth: 5.3 GB/s
Fill Rate: 1.4 billion pixel/s
Vertex/s: 263 million
Memory Type: DDR-II with TC
GeForce 7200 Series

The 7200 series was introduced May 8, 2007 and is based on (G72) architecture. It is designed to offer a low-cost upgrade from integrated graphics solutions. This series supports only PCI Express interface. Only one model is available, which is called 7200 GS.^[2]

Advanced Features Support:

The 7200 series supports following advanced features:

Intellisample 4.0 Technology

TurboCache Technology

High dynamic range rendering Technology

UltraShadow II Technology

CineFX 4.0 Engine

Nvidia PureVideo Technology

However it is important to note that 7200 series does not support Scalable Link Interface (SLI) Technology.
GeForce 7200 GS

The 7200 GS has the same memory speed as the 7300 GS, and the core frequency is the same as the 7300 LE. It has two pixel pipelines. Nvidia stated that the 7200 GS performance is 50% higher than the latest integrated graphics, it's the slowest card of the GeForce 7 Series and of the GeForce 6 Series but supports HDR and Nvidia PureVideo Technology.

Performance Specs:
Graphics Bus: PCI Express
Memory Interface: 64-bit
Memory Bandwidth: 6.4 GB/s
Fill Rate: 900 million pixel/s
Vertex/s: 225 million

Intellisample 4.0 Technology (but without GCAA)
Scalable Link Interface (SLI) Technology
TurboCache Technology
Nvidia PureVideo Technology

Memory Type: DDR-II with TCC

GeForce 7300 Series

Nvidia designed the 7300 series to be entry level gaming video cards. Currently 4 models are available: the 7300 GT, the 7300 GS, the 7300 LE, and the 7300 SE.^[3]

This series was released to replace the older Geforce 6200 series.

Advanced Features Support:

The 7300 series supports following advanced features:

Intellisample 4.0 Technology
Scalable Link Interface (SLI) Technology
TurboCache Technology
High dynamic range rendering Technology
UltraShadow II Technology
CineFX 4.0 Engine
Nvidia PureVideo Technology

GeForce 7300 SE

It uses the same core frequency and memory speed as the 7300 LE, and has two vertex and pixel shaders. In many ways, this card is actually inferior to the 7100 GS, although it still retains the HDR support.

Performance Specs:
Graphics Bus: PCI Express
Memory Interface: 64-bit
Memory Bandwidth: 5.2 GB/s
Fill Rate: 900 million pixel/s
Vertex/s: 225 million
Memory Type: DDR-II
GeForce 7300 LE

The 7300 LE (LE stands for light edition) is a scaled-down version of the 7300 GS. It has DDR2 memory, and a slightly lower core clock speed (450 MHz vs. 550 MHz) according to AnandTech^[4] It is only available in the PCI Express interface. With good performance/price, the 7300 LE serves as a budget video card, though most consider it too inferior for the relatively small difference in price from the GS version.

Performance Specs:
Graphics Bus: PCI Express
Memory Interface: 64-bit
Memory Bandwidth: 6.4 GB/s
Fill Rate: 1.8 billion pixel/s
Vertex/s: 338 million
Memory Type: DDR-II
GeForce 7300 GS

Card with the highest core clock speed of the 7300 series. Better performance than the 7300SE/LE.

Performance Specs:
Graphics Bus: PCI Express
Memory Interface: 64-bit
Memory Bandwidth: 6.5 GB/s
Fill Rate: 2.2 billion pixel/s
Vertex/s: 413 million
Memory Type: DDR-II
GeForce 7300 GT

Features a 350 MHz core frequency and a 333 MHz memory speed. It is the fastest card of the 7300 series, because of the 128-bit memory interface. The card is actually using a G73 core (instead of G72 cores like other 7300 series cards), which is usually found in the 7600 series.

Performance Specs:
Graphics Bus: PCI Express
Memory Interface: 128-bit
Memory Bandwidth: 27.7 GB/s
Fill Rate: 3.3 billion pixel/s
Vertex/s: 550 million
Memory Type: DDR-II

GeForce 6 Series

2009-07-06T09:48:00.000-07:00

The GeForce 6 Series (codename NV40) is Nvidia's sixth generation of GeForce graphic processing units. Launched on April 14, 2004, the GeForce 6 family introduced PureVideo post-processing for video, SLI technology, and Shader Model 3.0 support (compliant with Microsoft DirectX 9.0c specification and OpenGL 2.0).

Nvidia GeForce 6 Series

Codename(s)	NV40, NV41, NV42, NV43, NV44, NV45
Release date	April 2004 - 2005
Entry-level GPU	6100 (IGP), 6150 (IGP), 6200, 6500
Mid-Range GPU	6600
High-end GPU	6800
Direct3D and Shader version	D3D 9.0c Shader Model 3.0

[hide]

1 GeForce 6 Series features
2 GeForce 6800 Series
3 GeForce 6600 Series
- 3.1 6600 chipset table
4 GeForce 6500
- 4.1 GeForce 6500
5 GeForce 6200
- 5.1 GeForce 6200 chip specifications
  - 5.1.1 GeForce 6200
6 GeForce 6200 TurboCache / AGP
- 6.1 GeForce 6200 TurboCache / AGP chip specifications
7 GeForce 6100 and 6150 series
- 7.1 GeForce 6100 and 6150 series chip specifications
8 IntelliSample 4.0 and the GeForce 6 GPUs
9 See also
10 Notes and references

11 External links

11.1 Reviews

GeForce 6 Series features

SLI

Nvidia PureVideo Technology

Main article: Nvidia PureVideo

Nvidia PureVideo technology is the combination of a dedicated video processing core and software which decodes H.264, VC-1, WMV, and MPEG-2 videos with reduced CPU utilization.

Shader Model 3.0

While ATI was the first to deliver Shader Model 2.0 capability to the retail market, Nvidia was the first to deliver Shader Model 3.0 (SM3) capability. SM3 extends SM2 in a number of ways: standard FP32 (32-bit floating-point) precision, dynamic branching, increased efficiency and longer shader lengths are the main additions. Shader Model 3.0 was quickly adopted by game developers because it was quite simple to convert existing shaders coded with SM 2.0/2.0A/2.0B to version 3.0, and it offered noticeable performance improvements across the entire GeForce 6 line.

Caveats

There are reports of incompatibility between GeForce 6 series cards and some wide aspect ratio LCD panels when connected through DVI^{[citation needed]}. PureVideo functionality varies by model, with some models lacking WMV9 and/or H.264 acceleration.^[1]

In addition, motherboards with some VIA and SIS chipsets and an AMD Athlon XP processor seemingly have compatibility problems with the GeForce 6600 and 6800 GPUs. Problems that have been known to arise are freezing, artifacts, reboots, and other issues that make gaming and use of 3D applications almost impossible. These problems seem to happen only on Direct3D based applications and do not affect OpenGL.^[2]

Geforce 6 Series comparison

Here is how the released versions of the "GeForce 6" series family compare to Nvidia's previous flagship GPU, the GeForce FX 5950 Ultra, in addition to the comparable units of ATI's newly released for the time Radeon X800 and X850 Series:

	GeForce FX 5950 Ultra	GeForce 6200 TC-32	GeForce 6600 GT	GeForce 6800 Ultra	ATI Radeon X800 XT PE	ATI Radeon X850 XT PE
Transistor count	135 million	77 million	146 million	222 million	160 million	160 million
Manufacturing process	0.13 µm	0.11 µm	0.11 µm	0.13 µm	0.13 µm low-k	0.13 µm low-k
Die Area (mm²)	~200	110	156	288	288	297
Core clock speed (MHz)	475	350	500	400	520	540
Number of pixel shader processors	4	4	8	16	16	16
Number of pixel pipes	4	4	8	16	16	16
Number of texturing units	8(16*)	4	8	16	16	16
Number of vertex pipelines	3*	3	3	6	6	6
Peak pixel fill rate (theoretical)	1.9 Gigapixel/s	700 Megapixel/s	2.0 Gigapixel/s	6.4 Gigapixel/s	8.32 Gigapixel/s	8.64 Gigapixel/s
Peak texture fill rate (theoretical)	3.8 Gigatexel/s	1.4 Gigatexel/s	4.0 Gigatexel/s	6.4 Gigatexel/s	8.32 Gigatexel/s	8.64 Gigatexel/s
Memory interface	256-bit	64-bit	128-bit	256-bit	256-bit	256-bit
Memory clock speed	950 MHz DDR	700 MHz DDR	1.0 GHz GDDR3	1.1 GHz GDDR3	1.12 GHz GDDR3	1.18 GHz GDDR3
Peak memory bandwidth (GB/s)	30.4	5.6	16.0	35.2	35.84	37.76

(*) GeForce FX series has an Array based Vertex Shader.

GeForce 6800 Series

The first family in the GeForce 6 product-line, the 6800 series catered to the high-performance gaming market. As the very first GeForce 6 model, the 16 pixel pipeline GeForce 6800 Ultra (NV40) was 2 to 2.5 times faster than Nvidia's previous top-line product (the GeForce FX 5950 Ultra), packed four times the number of pixel pipelines, twice the number of texture units and added a much improved pixel-shader architecture. Yet, the 6800 Ultra was fabricated on the same (IBM) 130 nanometer process node as the FX 5950, and it consumed slightly less power.

Early benchmarks put the 6800 series at a disadvantage when compared to similarly priced ATI cards. Newer drivers have improved performance on both companies' products. Against the ATI's Radeon X800XT PE, its direct competitor, the 6800 Ultra performed comparably in most synthetic and game benchmarks, with each card showing its individual strengths in different gaming applications. Nvidia's part is strong in many applications programmed for OpenGL (a traditional strength of Nvidia), while ATI leads in many Direct3D applications. Thus, it is now generally accepted that the GeForce 6800 Ultra is similar in performance to the Radeon X800 XT, and that the GeForce 6800 GT generally performs better than the Radeon X800 Pro.

In the view of many, the 6800 Ultra gave Nvidia a performance boost it had not seen since the early days of the GeForce product-line. In the aftermath of the GeForce FX series (which could only offer competitive performance in OpenGL applications), the 6800 restored faith in Nvidia's ability to deliver a competitive product. This was quite important, as the 6800 Ultra made a strong positive impression on a skeptical market, helping Nvidia regain mindshare it had lost in the aftermath of the GeForce FX.

Like all of Nvidia's GPUs up until 2004, initial 6800 members were designed for the AGP bus. Nvidia added support for the PCI Express (PCIe) bus in later GeForce 6 products, usually by use of an AGP-PCIe bridge chip. In the case of the 6800GT and 6800Ultra, Nvidia developed a variant of the NV40 chip called the NV45. The NV45 shares the same die core as the NV40, but embeds an AGP-PCIe bridge on the chip's package. (Internally, the NV45 is an AGP NV40 with added bus-translation logic, to permit interfacing with a PCIe motherboard. Externally, the NV45 is a single chip with two separate silicon dies clearly visible on the top.)

The use of an AGP-PCIe bridge chip initially led to fears that natively-AGP GPUs would not be able to take advantage of the additional bandwidth offered by PCIe and would therefore be at a disadvantage relative to native PCIe chips. However, benchmarking reveals that even AGP 4x is fast enough that most contemporary games do not improve significantly in performance when switched to AGP 8x, rendering the further bandwidth increase provided by PCIe largely superfluous. Additionally, Nvidia's on-board implementations of AGP are clocked at AGP 12x or 16x, providing bandwidth comparable to PCIe for the rare situations when this bandwidth is actually necessary.

The use of a bridge chip allowed Nvidia to release a full complement of PCIe graphics cards without having to redesign them for the PCIe interface. Later, when Nvidia's GPUs were designed to use PCIe natively, the bidirectional bridge chip allowed them to be used in AGP cards. ATI, initially a critic of the bridge chip, eventually designed a similar mechanism for their own cards.

Nvidia's professional Quadro line contains members drawn from the 6800 series: Quadro FX 4000 (AGP) and the Quadro FX 3400, 4400 and 4400g (both PCI Express). The 6800 series was also incorporated into laptops with the GeForce Go 6800 and Go 6800 Ultra GPUs.

PureVideo and the AGP GeForce 6800

PureVideo expanded the level of multimedia-video support from decoding of MPEG-2 video to decoding of more advanced codecs (MPEG-4, WMV9), enhanced post-processing (advanced de-interlacing), and limited acceleration for encoding. But perhaps ironically, the first GeForce product(s) to offer PureVideo, the AGP GeForce 6800/GT/Ultra, failed to support all of PureVideo's advertised features.

Media player software (WMP9) with support for WMV-acceleration did not become available until several months after the 6800's introduction. User and web reports showed little if any difference between PureVideo enabled GeForces and non-Purevideo cards. The prolonged public silence of Nvidia, after promising updated drivers, and test benchmarks gathered by users led the user community to conclude that the WMV9 decoder component of the AGP 6800's PureVideo unit is either non-functional or intentionally disabled.

In late 2005, an update to Nvidia's website finally confirmed what had long been suspected by the user community: WMV-acceleration is not available on the AGP 6800. Of course, today's standard computers are fast enough to play WMV9 video and other sophisticated codecs like MPEG-4, H.264 or Theora without hardware acceleration.

GeForce 6 series general features

4, 8, 12, or 16 pixel-pipeline GPU architecture
Up to 8x more shading performance compared to the previous generation
CineFX 3.0 engine - DirectX 9 Shader Model 3.0 support
On Chip Video processor (PureVideo)
Full MPEG-2 encoding and decoding at GPU level (PureVideo)
Advanced Adaptive De-Interlacing (PureVideo)
DDR and GDDR-3 memory on a 256-bit wide Memory interface
UltraShadow II technology - 3x to 4x faster than NV35 (GeForce FX 5900)
High Precision Dynamic Range (HPDR) technology
128-bit studio precision through the entire pipeline - Floating-point 32-bit color precision
IntelliSample 4.0 Technology - 16x Anisotropic Filtering, Rotating Grid Antialiasing and Transparency Antialiasing (see here)
Max Resolution is 2048x1536@85 Hz
Video Scaling and Filtering - HQ filtering techniques up to HDTV resolutions
Integrated TV Encoder - TV-output up to 1024x768 resolutions
OpenGL 2.0 Optimizations and support
DVC 3.0 (Digital Vibrance Control)
Dual 400 MHz RAMDACs which support QXGA displays up to 2048x1536 @ 85 Hz

Dual DVI on select members (Depending on the Card Manufacturer.)

6800 chipset table

Board Name	Core Type	Core (MHz)	Memory (MHz)	Pipeline Config	Vertex Processors	Memory Interface
6800 Ultra	NV40/NV45	400	1100	16	6	256-bit
6800 GT	NV40/NV45	350	1000	16	6	256-bit
6800 GS	NV40/NV42	350/425	1000	12	5	256-bit
6800 GTO	NV40/NV45	350	900	12	5	256-bit
6800	NV40/NV41 NV42	325	700/600	12	5	256-bit
6800 Go	NV41M	300	600	12	5	256-bit
6800 Go Ultra	NV41M(0.13u)/NV42M(0.11u)	450	1100	12	5	256-bit
6800 XT	NV40/NV41/NV42	325/350/?	700/1000+	8	4	128/256-bit
6800 XE	NV40	275/300/325	533/700	8	3	128-bit
6800 LE	NV40	300	700	8	4	256-bit

Notes

The GeForce 6800 GS is cheaper to manufacture and has a lower MSRP than the GeForce 6800 GT because it has fewer pipelines and a smaller process (110 vs 130 nm), but performance is similar because it has a faster core clock. The AGP version, however, uses the original NV40 chip and 6800 GT circuit board and may be capable of re-activating the inactive pixel and vertex pipes. Unfortunately, the PCI Express version lacks them entirely, precluding such modifications.
The 6800 GTO (which was produced only as an OEM card) contains four masked pixel pipelines and one masked vertex shader, which are potentially unlockable.
The GeForce 6800 is often unofficially called the "GeForce 6800 Vanilla" or the "GeForce 6800 NU" (for Non-Ultra) to distinguish it from the other models. Recent PCIe variants have the NV41 (IBM 0.13 micrometre) or NV42 (TSMC 0.11 micrometre) cores, which are native PCIe implementations and do not have an integrated AGP bridge chip. The AGP version of the video card contains four masked pixel pipelines and one masked vertex shader, which are potentially unlockable through software mods. PCI-Express 6800 cards are incapable of such modifications, because the extra pixel pipelines and vertex buffers are nonexistent.
The 6800 XT varies greatly depending on manufacturer. It is produced on three cores (NV40/NV41/NV42), four memory configurations (128MB DDR, 256 MB DDR, 128 MB GDDR3, and 256 MB GDDR3), and has clock speeds ranging from 300-425 (core) and 600-1000 (memory). 6800 XT cards based on the NV40 core contain eight masked pixel pipelines and two masked vertex shaders, and those based on the NV42 core contain four masked pipelines and one masked shader (for some reason, the NV42 cards are almost never unlockable. It is speculated that the pipelines are being laser-cut).

The 6800 LE contains eight masked pixel pipelines and two masked vertex shaders, which are potentially unlockable.

GeForce 6600 Series

The GeForce 6600 (NV43) was officially launched on August 12, 2004, several months after the launch of the 6800 Ultra. With half the pixel pipelines and vertex shaders of the 6800 GT, and a smaller 128-bit memory bus, the lower-performance and lower-cost 6600 is the mainstream product of the GeForce 6 series. The 6600 series retains the core rendering features of the 6800 series, including SLI. Equipped with fewer rendering units, the 6600 series processes pixel data at a slower rate than the more powerful 6800 series. However, the reduction in hardware resources, and migration to TSMC's 110 nm manufacturing process (versus the 6800's 130 nm process), make the 6600 both less expensive for Nvidia to manufacture and less expensive for customers to purchase.

Their 6600 series currently has three variants: the GeForce 6600LE, the 6600, and the 6600GT (in order from slowest to fastest.) The 6600 GT performs quite a bit better than the GeForce FX 5950 Ultra or Radeon 9800 XT, with the 6600 GT scoring around 8000 in 3DMark03, while the GeForce FX 5950 Ultra scored around 6000, and it is also much cheaper. Notably, the 6600 GT offered identical performance to ATI's high-end X800 PRO graphics card with drivers previous December 2004, when running the popular game Doom 3 (afterwards ATI optimized their drivers and was able to distance itself slightly from the 6600GT). It was also about as fast as the higher-end GeForce 6800 when running games without anti-aliasing in most scenarios.

At introduction, the 6600 family was only available in PCI Express form. AGP models became available roughly a month later, through the use of Nvidia's AGP-PCIe bridge chip. A majority of the AGP GeForce 6600GTs have their memory clocked at 900 MHz, which is 100 MHz below the PCI-E card, on which the memory operates at 1000 MHz. This can contribute to a performance decline when playing certain games. However, many times it is possible to "overclock" the memory to its nominal frequency of 1000 MHz.

6600 chipset table

Board Name	Core Type	Core (MHz)	Memory (MHz)	Pipeline Config	Vertex Processors	Memory Interface
6700 XL	NV43	525	1100	8	3	128-bit
6600 GT GDDR3	NV43	500	900/1000	8	3	128-bit
6610 XL	NV43	400	800	8	3	128-bit
6600 DDR2	NV43	350	800	8	3	128-bit
6600	NV43	300	500/550	8	3	128-bit
6600 LE	NV43	300	500	4	3	128-bit

GeForce 6600GT GPU chip

Other data for PCI Express based cards:

Memory Interface: 128-bit
Memory Bandwidth: 16.0 GB/s.
Fill Rate (pixels/s.): 4.0 billion
Vertices per Second: 375 million
Memory Data Rate: 1000 MHz
Pixels per Clock (peak): 8
RAMDACs: 400 MHz

Other data for AGP based cards:

Memory Interface: 128-bit
Memory Bandwidth: 14.4 GB/s.
Fill Rate (pixels/s.): 4.0 billion
Vertices per Second: 375 million
Memory Data Rate: 900 MHz
Pixels per Clock (peak): 8
RAMDACs400 MH
GeForce 6500
Core Clock: 450 MHz
Memory Clock: 700 MHz
Pixel Pipelines: 4
Number of ROPs: 2
Vertex Processors: 3
Memory: 128MB/256MB DDR on a 64-bit interface
Fill Rate (pixels/s): 1.6 billion
Vertices per Second: 300 million
Effective Memory Bandwidth(GB/s): 13.44
GeForce 6200
Core Clock: 300 MHz
Memory Clock: 550 MHz
Pixel Pipelines: 4
Vertex Processors: 3
Memory: 128 MB/256 MB/512 MB ^[3] DDR on a 64-bit/128-bit interface
GeForce 6200 PCI-Express (NV44) TurboCache
Core Clock: 350 MHz
Memory Clock: 700 MHz
Pixel Pipelines: 4
Number of ROPs: 2
Vertex Processors: 3
Memory: 16 MiB/32 MiB/64 MiB/128 MiB DDR on a 32-bit/64-bit/128-bit interface

GeForce 6200 w/ TurboCache supporting 128 MiB, including 16 MiB of local TurboCache (32-bit)
GeForce 6200 w/ TurboCache supporting 128 MiB, including 32 MiB of local TurboCache (64-bit)
GeForce 6200 w/ TurboCache supporting 256 MiB, including 64 MiB of local TurboCache (64-bit)
GeForce 6200 w/ TurboCache supporting 256 MiB, including 128 MiB of local TurboCache (128-bit)
GeForce 6200 AGP (NV44a) without TurboCache
Core Clock: 350 MHz
Memory Clock: 500 MHz
Pixel Pipelines: 4
Number of ROPs: 2
Vertex Processors: 3
Memory: 128-256 MB DDR on a 64-bit interface
GeForce 6200 AGP (NV44a2) without TurboCache
Core Clock: 350 MHz
Memory Clock: 540 MHz
Pixel Pipelines: 4
Vertex Processors: 3
Memory: 128 MB/512 MB DDR2 with a 128-bit/64-bit interface
Cooling: Passive heatsink

(Only PNY is known to manufacture this card, which appears to be discontinued.) (XFX manufactured a 6200A AGP with 512MB of ram with a 64 bit interface)

GeForce 6200 AGP (NV44a) without TurboCache

Core Clock: 350 MHz
Memory Clock: 532 MHz
Pixel Pipelines: 4
Vertex Processors: 3
Memory: 256 MB DDR2 BGA on a 64-bit interface
GeForce 6100
Manufacturing process: 90 nm
Core Clock: 425 MHz
Vertex Processors: 1
Pixel Pipelines: 2
Shader Model: 3
DirectX support: v9
Video playback acceleration: SD video acceleration (HD video acceleration not supported)
Outputs: VGA only
Memory: Shared DDR/DDR2 (socket 939/AM2) system memory (selectable through BIOS - usually 32/64/128/256 MB)
GeForce 6150
Manufacturing process: 90 nm
Core clock: 475 MHz^[5]
Vertex processors: 1
Pixel pipelines: 2
Shader model: 3
DirectX support: v9
Video playback acceleration: HD video acceleration
Outputs: VGA, DVI, Video
Memory: Shared DDR2 (socket 939/AM2) system memory (selectable through BIOS - usually 32/64/128/256 MB)
GeForce 6150SE

GeForce 6150SE is new single-chip version of the nVidia GeForce 6100, MCP61 (also known as C61). The MCP61 uses less power than the original C51 2-chip version of 6100 and its onboard video outperforms the 6150 in many 3D benchmarks even despite lower core frequency (425 MHz) because of added hardware Z-culling.

MCP61 introduced a bug in the SATA NCQ implementation. In detail, nvidia employees have disabled NCQ operations under Linux[1]
Manufacturing process: 90 nm
Core Clock: 425 MHz
Vertex Processors: 1
Pixel Pipelines: 2
Shader Model: 3
DirectX support: v9

GeForce FX Series

2009-07-06T09:38:00.000-07:00

The GeForce FX or "GeForce 5" series (codenamed NV30) is a line of graphics processing units from the manufacturer Nvidia.

Nvidia GeForce FX Series

Codename(s)	NV30, NV31, NV34, NV35, NV36, NV38
Release date	2003
Entry-level GPU	5200, 5300, 5500
Mid-Range GPU	5600, 5700, 5750
High-end GPU	5800, 5900, 5950
Direct3D and Shader version	D3D 9.0a, Pixel Shader 2.a, Vertex Shader 2.a

[hide]

1 Specifications
2 Marketing
3 Delays
4 Disappointment
5 Competitive response
- 5.1 The way it's meant to be played
- 5.2 Windows Vista and GeForce FX PCI cards
6 GeForce FX models
7 Issues
8 See also
9 References

10 External links

Specifications

Nvidia's GeForce FX series is the fifth generation in the GeForce line. With GeForce 3, Nvidia introduced programmable shader units into their 3D rendering capabilities, in line with the release of Microsoft's DirectX 8.0 release, and the GeForce 4 Ti was an optimized version of the GeForce 3. With real-time 3D graphics technology continually advancing, the release of DirectX 9.0 ushered in a further refinement of programmable pipeline technology with the arrival of Shader Model 2.0. The GeForce FX series brings to the table Nvidia's first generation of Shader Model 2 hardware support.

The Dawn demo was released by Nvidia to showcase pixel and vertex shaders effects of the GeForce FX Series

The FX features DDR, DDR2 or GDDR-3 memory, a 130 nm fabrication process, and Shader Model 2.0/2.0A compliant vertex and pixel shaders. The FX series is fully compliant and compatible with DirectX 9.0b. The GeForce FX also included an improved VPE (Video Processing Engine), which was first deployed in the GeForce4 MX. Its main upgrade was per pixel video-deinterlacing — a feature first offered in ATI's Radeon, but seeing little use until the maturation of Microsoft's DirectX Video Acceleration and VMR (video mixing renderer) APIs. Among other features was an improved anisotropic filtering algorithm which was not angle-dependent (unlike its competitor, the Radeon 9700/9800 series) and offered better quality, but affected performance somewhat. Though Nvidia reduced the filtering quality in the drivers for a while, the company eventually got the quality up again, and this feature remains one of the highest points of the GeForce FX family to date (however, this method of anisotropic filtering was dropped by Nvidia with the GeForce 6 series for performance reasons, and then re-introduced with the GeForce 8 series).^[1]^[2]

Marketing

While it is the fifth major revision in the series of GeForce graphics cards, it wasn't marketed as a GeForce 5. The FX ("effects") in the name was decided on to illustrate the power of the latest design's major improvements and new features, and to virtually distinguish the FX series as something greater than a revision of earlier designs. The FX in the name also was used to market the fact that the GeForce FX was the first GPU to be a combined effort from the previously acquired 3DFX engineers and Nvidia's own engineers. Nvidia's intention was to underline the extended capability for cinema-like effects using the card's numerous new shader units. The result was instead to confuse people who simply wanted to know if this card was better than other competing cards.

The advertising campaign for the GeForce FX featured the Dawn fairy demo, which was the work of several veterans from the computer animation Final Fantasy: The Spirits Within. Nvidia touted it as "The Dawn of Cinematic Computing", while critics noted that this was the strongest case of using sex appeal in order to sell graphics cards yet. It is still probably the best-known of the Nvidia Demos.

Delays

The NV30 project had been delayed for three key reasons. One was because Nvidia decided to produce an optimized version of the GeForce 3 (NV 20) which resulted in the GeForce 4 Ti (NV 25), while ATI cancelled its competing optimized chip (R250) and opted instead to focus on the Radeon R300 (which would be released as the Radeon 9700) which had been recently acquired from ArtX. This enabled ATI to take the lead in development for the first time instead of trailing Nvidia.

A second reason was Nvidia's commitment with Microsoft. Many of Nvidia’s best engineers were working on the Xbox contract, developing a motherboard solution, including the API used as part of the SoundStorm platform and the graphics processor (NV2A). The Xbox venture diverted most of Nvidia's engineers over not only the NV2A's initial design-cycle but also during the mid-life product revisions needed to discourage hackers. The Xbox contract did not allow for falling manufacturing costs, as process technology improved, and Microsoft sought to renegotiate the terms of the contract, withholding the DirectX 9 specifications as leverage. As a result, Nvidia and Microsoft relations, which had previously been very good, deteriorated. (Both parties later settled the dispute through arbitration and the terms were not released to the public.)

Due to the Xbox dispute, Nvidia was not consulted when the DirectX 9 specification was drawn up, while ATI designed the Radeon 9700 to such specifications. Rendering color support was limited to 24 bits floating point, and shader performance had been emphasized throughout development, since this was to be the main focus of DirectX 9. Microsoft's shader compiler was also built using the Radeon 9700 as the base card instead of Nvidia's offering. In contrast, Nvidia’s cards offered 16 and 32 bit floating point modes, offering either lower visual quality (as compared to the competition), or slow performance. The 32 bit support made them much more expensive to manufacture requiring a higher transistor count. Shader performance was often only half or less the speed provided by ATI's competing products. Having made its reputation by providing easy to manufacture DirectX compatible parts, Nvidia had misjudged Microsoft’s next standard, and was to pay a heavy price for this error. As more and more games started to rely on DirectX 9 features, the poor shader performance of the GeForce FX series became ever more obvious. With the exception of the FX 5700 series (a late revision), the FX series lacked performance compared to equivalent ATI parts.

Finally, Nvidia's transition to a 130 nm manufacturing process encountered unexpected difficulties. Nvidia had ambitiously selected TSMC's then state-of-the-art (but unproven) Low-K dielectric 130 nm process node. After sample silicon-wafers exhibited abnormally high defect-rates and poor circuit performance, Nvidia was forced to re-tool the NV30 for a conventional (FSG) 130 nm process node. (Nvidia's manufacturing difficulties with TSMC spurred the company to search for a second foundry. Nvidia selected IBM to fabricate several future GeForce chips, citing IBM's process technology leadership. Yet curiously, Nvidia avoided IBM's Low-K process.)

Disappointment

Analysis of the hardware

Hardware enthusiasts saw the GeForce FX series as a disappointment as it did not live up to expectations^[who?]. Nvidia had aggressively hyped the card^{[citation needed]} up throughout the summer and autumn of 2002, to combat ATI Technologies' autumn release of the powerful Radeon 9700. ATI's very successful Shader Model 2 card had arrived several months earlier than Nvidia's first NV30 board, the GeForce FX 5800.

When the FX 5800 finally launched, it was discovered after testing and research on the part of hardware analysts that the NV30 was not a match for Radeon 9700's R300 core.^[3] This was especially true when pixel shading was involved. Additionally, the 5800 had roughly a 30% memory bandwidth deficit caused by the use of a comparatively narrow 128-bit memory bus (ATI and other companies moved to 256-bit).^[3] Nvidia planned to use the new, state-of-the-art GDDR-2 instead because of its support for much higher clock rates. It couldn't clock high enough to make up for the bandwidth of a 256-bit bus, however.

While the NV30's direct competitor, the R300 core, was capable of 8 pixels per clock with its 8 pipelines, the NV30 architecture was unable to render 8 color + Z pixels per clock.^[4] It was thus actually more easily categorized as a 4 × 2 design capable of 8 Z pixels, 8 stencil operations, 8 textures, and 8 shader operations per clock.^[3] This limited its pixel fill-rate in the majority of 3D applications. However, in games with heavy use of stencil shadows, such as those based on the Doom3 engine, NV30 did benefit from its 8 pixels/operations per clock capabilities, because the engine does a Z-only pass. This was not a typical rendering scenario, however.

The initial version of the GeForce FX (the 5800) was one of the first cards to come equipped with a large dual-slot cooling solution. Called "Flow FX", the cooler was stunningly apparent in comparison to ATI's small single-slot cooler on the 9700 series.^[3] Not only that, but it was very loud and garnered complaints from gamers and developers alike. It was even jokingly coined the 'Dustbuster'^[5] and graphics cards which happen to be loud are often compared to the GeForce FX 5800 for this reason^{[citation needed]}.

Shaders

With regards to the much-touted^{[peacock term]} Direct3D 9.0 shader model 2.a capabilities of the NV3x series and the related marketing claim of "cinematic effects" capabilities, the actual performance was quite poor.^[6] A combination of factors combined to hamper how well NV3x could perform these calculations.

Firstly, the chips were designed for use with a mixed precision programming methodology.^[4] A 64-bit precision "FP16" mode would be used for situations where high-precision math was seen as unnecessary to maintain image quality. In other cases, where mathematical accuracy was more important, a 128-bit "FP32" mode would be utilized. The ATI R300-based cards did not benefit from partial precision because they always operated at shader model 2's required minimum of 96-bit FP24 for full precision. For a game title to use FP16, the programmer had to specify which effects used the lower precision using "hints" within the code. Because ATI didn't benefit from the lower precision and the R300 performed far better on shaders overall, and because it took more effort to optimize shader code for the lower precision, the NV3x hardware was usually crippled to running full precision full-time.

The NV3x chips also used a processor architecture that relied heavily on the effectiveness of the video card driver's shader compiler.^[4] Proper instruction ordering and instruction composition of shader code could dramatically boost the chip's computational efficiency. Compiler development is a long and difficult task and this was a major challenge that Nvidia tried to overcome during most of NV3x's lifetime. Nvidia released several guidelines for creating GeForce FX-optimized code and worked with Microsoft to create a special shader model called "Shader Model 2.a". This model leveraged the design of NV30 in order to extract greater performance and flexibility. Nvidia would also controversially rewrite game shader code and force the game to use their shader code instead of what the developer had written. However, such code would often result in lower final image quality.

Valve's presentation

In late 2003, the GeForce FX series became known for poor performance with DirectX 9 shader model 2 vertex & pixel shaders because of a very vocal presentation by the popular game developer, Valve Software.^[7] Early indicators of potentially poor pixel shader performance had come from synthetic benchmarks (such as 3DMark 2003). But outside of the developer community and tech-savvy computer gamers, few mainstream users were aware of such issues.

Then, Valve Software came forth with their experience using the hardware with their upcoming game, Half-Life 2.^[7] Using a pre-release build of the highly anticipated game, powered by the Source engine, Valve published benchmarks revealing a complete generational gap (80–120% or more) between the GeForce FX 5900 Ultra and the ATI Radeon 9800 Pro. In shader 2.0-utilizing game-levels, Nvidia's top-of-the-line FX 5900 Ultra performed about as fast as ATI's mainstream Radeon 9600, which cost approximately a third as much as the Nvidia card. Valve had initially planned on supporting partial floating point precision (FP16) to optimize for NV3x, but they eventually discovered that this plan would take far too long to accomplish.^[7] ATI's cards did not benefit from FP16 mode, so all of the work would be entirely for Nvidia's NV3x cards, a niche too small to be worthy of the time and effort. When Half-Life 2 was released a year later, Valve opted to make all GeForce FX hardware default to using the game's DirectX 8 shader code in order to enable adequate performance from the Nvidia cards.^[7]

It is possible to force Half Life 2 to run in DirectX 9 mode on all cards with a simple tweak to a configuration file. When users and reviewers attempted this, they noted the significant performance loss on NV3x cards. Only the top of the line variants (5900 and 5950) remained playable.^[6] Later, there were two "fan-patches" to make Half-Life 2 run better on the GeForce FX cards. The first was a method of using an application called 3DAnalyze to force partial precision (FP16) on all shaders on the GeForce FX cards while running the game.^[8] This method allowed users of lower-end GeForce FX cards (such as 5600 and 5700) to run the game acceptably, while significantly improving performance on the FX 5800 and 5900/5950 series graphics cards. This method brought along an image quality degradation in several areas throughout the game. However, later a patch was developed by a fan using the Source SDK, which re-ordered and re-arranged the shaders to better suit the GeForce FX architecture, and also added partial precision hints to most of the shaders in the game (in contrast to the earlier method which would force partial precision).^[9] This patch brought about a similar (and significant) performance increase for the GeForce FX 5700/5800/5900 series of graphics cards, and also did not have any image quality loss.

Questionable tactics

Nvidia's GeForce FX era was one of great controversy for the company. The competition had soundly beaten them on the technological front and the only way to get the FX chips competitive with the Radeon R300 chips was to greatly optimize the drivers.

Nvidia historically has been known for their impressive OpenGL driver performance and quality, and the FX series certainly maintained this. However, with regard to image quality in both Direct3D and OpenGL, they aggressively began various questionable optimization techniques not seen before. They started with filtering optimizations by changing how trilinear filtering operated on game textures, reducing its accuracy, and thus visual quality.^[10] Anisotropic filtering also saw dramatic tweaks to limit its use on as many textures as possible to save memory bandwidth and fillrate.^[10] Tweaks to these types of texture filtering can often be spotted in games from a shimmering phenomenon that occurs with floor textures as the player moves through the environment (often signifying poor transitions between mip-maps). Changing the driver settings to "High Quality" can alleviate this occurrence at the cost of performance.^[10]

Nvidia also began to clandestinely replace pixel shader code in software with hand-coded optimized versions with lower accuracy, through detecting what program was being run. These "tweaks" were especially noticed in benchmark software from Futuremark. In 3DMark03 it was found that Nvidia had gone to extremes to limit the complexity of the scenes through driver shader changeouts and aggressive hacks that prevented parts of the scene from even rendering at all.^[11] This artificially boosted the scores the FX series received. Side by side analysis of screenshots in games and 3DMark03 showed noticeable differences between what a Radeon 9800/9700 displayed and what the FX series was doing.^[11] Nvidia also publicly attacked the usefulness of these programs and the techniques used within them in order to undermine their influence upon consumers. It should however be noted that ATI also created a software profile for 3DMark03.^[12] In fact, this is also a frequent occurrence with other software, such as games, in order to work around bugs and performance quirks. With regards to 3DMark, Futuremark began updates to their software and screening driver releases for these optimizations.

Both Nvidia and ATI have optimized drivers for tests like this historically. However, Nvidia went to a new extreme with the FX series. Both companies optimize their drivers for specific applications even today (2008), but a tight rein and watch is kept on the results of these optimizations by a now more educated and aware user community.

Competitive response

By early 2003, ATI had DirectX 9-compliant products spanning the mid-range and high-end portions of the video card market. They had also recently launched a new high-end refresh, the Radeon 9800 Pro, and the mid-range Radeon 9600 Pro. Nvidia's only initial part, the GeForce FX 5800, was intended as a high-end part and not surprisingly was too costly to meet with the price requirements of the lower tiers of the market.

In late April 2003, Nvidia introduced the mid-range GeForce FX 5600 and budget GeForce FX 5200 models to address these segments. Each had an "Ultra" variant and a slower, cheaper non-Ultra variant. With conventional single-slot cooling and a mid-range price-tag, the 5600 Ultra had respectable performance but failed to measure up to its direct competitor, Radeon 9600 Pro. The GeForce FX 5600 parts did not even advance performance over the GeForce 4 Ti chips they were designed to replace. In DirectX 8 applications, the 5600 lost to or matched the GeForce 4 Ti 4200.^[13] Likewise, the entry-level FX 5200 did not perform as well as the DirectX 7.0 generation GeForce 4 MX440, despite the FX 5200 possessing a notably better 'checkbox' feature-set.^[14] FX 5200 was easily outperformed by the older Radeon 9000. The utility of the DirectX 9 pixel shader 2.0 performance of these parts was questionable at best.

Also in May 2003, Nvidia launched a new top-end model, the GeForce FX 5900 Ultra. This chip, based on a heavily revised NV35 GPU, fixed many of the shortcomings of the 5800, which had been quietly discontinued. While the 5800 used fast but hot and expensive GDDR-2 and had a 128-bit memory bus, the 5900 moved to slower and cheaper DDR SDRAM, but it more than made up for it with a wider 256-bit memory bus. The 5900 Ultra performed somewhat better than the Radeon 9800 Pro in everything not heavily using shaders, and had a quieter cooling system than the 5800, but most cards based on the 5900 still occupied two slots.^[15]

In October 2003, Nvidia brought out a more potent mid-range card using technology from NV35; the GeForce FX 5700, using a new NV36 core. The FX 5700 was ahead of the Radeon 9600 Pro and XT in games with light use of pixel shaders.^[16] In December 2003, Nvidia launched the 5900XT, a board identical to the 5900, but clocked slower and using slower memory. It managed to more soundly defeat Radeon 9600 XT, but was still behind in a few shader-heavy scenarios.^[17]

The final GeForce FX model released was the 5950 Ultra, which was a 5900 Ultra with higher clock speeds. The board was fairly competitive with the Radeon 9800XT, again as long as pixel shaders were lightly used.^[18]

The way it's meant to be played

Nvidia debuted a new campaign to motivate developers to optimize their titles for Nvidia hardware at the Game Developers Conference (GDC) in 2002. In exchange for prominently displaying the Nvidia logo on the outside of the game packaging, Nvidia offered free access to a state of the art test lab in Eastern Europe, that tested against 500 different PC configurations for compatibility. Developers also had extensive access to Nvidia engineers, who helped produce code optimized for Nvidia products.^[19]

Windows Vista and GeForce FX PCI cards

Windows Vista requires a DirectX 9-compliant 3D accelerator to display the full Windows Aero user interface. During pre-release testing of Vista and upon launch of the operating system, the video card options for owners of computers without AGP or PCIe slots were limited almost exclusively to PCI cards based on the Nvidia NV34 core. This included cards such as GeForce FX 5200 and 5500 PCI. Since then, both ATI and Nvidia have launched a number of DirectX 9 PCI cards utilizing newer architectures.

GeForce FX models

Card Model	Codename	Core Design	Clocks core/mem	Memory Bus	Architecture Information
FX 5200	NV34	2:4:4	250/200	64 or 128 Bit	Entry level chip. Replacement for GeForce4 MX family. Quadro FX 330, 500, 600 is based on the GeForceFX 5200. The GeForce FX 5100 is an uncommon cutdown FX5200 available in 64 and 128 MB sizes, it was available only in AGP, and used a lower clocked nv34 core. Lacked IntelliSample technology. No lossless color compression or Z compression. PCX uses AGP to PCIe bridge chip for use on PCIe motherboards. Has 2 pixel pipelines if pixel shading is used, but a "fast" 4x1 mode exists as well. Each pixel pipe = 1 FP32 ALU handling 2 TMUs + 2 FX12 Mini-ALU (each one can do 2 MULs or 1 ADD or 1 MAD)
FX 5100	NV34	2:4:4	250/200	64 Bit
FX 5200 Ultra	NV34	2:4:4	325/325	128 Bit
PCX 5300	NV34	2:4:4	250/200	64 or 128 Bit
FX 5500	NV34B	2:4:4	270/200	64 or 128 Bit
FX 5600	NV31	2:4:4	325/275	64 or 128 Bit	Midrange chip. Sometimes slower than GeForce4 Ti 4200. No Quadro equivalent. Actually has 3 vertex shaders, but 2 are defective. Has 2 pixel pipelines if pixel shading is used, but a "fast" 4x1 mode exists as well. Each pixel pipe = 1 FP32 ALU handling 2 TMUs + 2 FX12 Mini-ALU (each one can do 2 MULs or 1 ADD or 1 MAD). Two 5600 Ultras exist; the "flipchip" version used a new production process common to the 5900 series, allowing higher clockspeeds.
FX 5600 Ultra	NV31	2:4:4	350/350	128 Bit
FX 5600 Ultra Flipchip	NV31	2:4:4	400/400	128 Bit
FX 5600 XT	NV31	2:4:4	235/200	64 or 128 Bit
FX 5700	NV36	3:4:4	425/250	128 Bit	NV36, like NV35, swapped hardwired DirectX 7 T&L Units + DirectX 8 integer pixel shader units for DirectX 9 floating point units. Again, like NV31 and NV34, NV36 is a 2 pipeline design but with a special 4x1 mode for some situations. Quadro equivalent is the Quadro FX 1100. Later models were equipped with GDDR3, which was also clocked higher than the DDR or GDDR2 modules previously used. On Ultra, RAM speed of 475 MHz also seen. PCX uses AGP to PCIe bridge chip for use on PCIe motherboards. Has 2 pixel pipelines if pixel shading is used. Each pixel pipe = 1 FP32 ALU handling 2 TMUs + 2 FP32 mini ALU (each one can do 1 MUL or 1 ADD or 1 FP16 MAD).
FX 5700 LE	NV36	3:4:4	250/200	64 or 128 Bit
FX 5700 Ultra	NV36	3:4:4	475/450	128 Bit (GDDR2/GDDR3)
PCX 5750	NV36	3:4:4	425/250	128 Bit
FX 5800	NV30	3:8:4	400/400	128 Bit (GDDR2)	Production was troubled by migration to 130 nm processes at TSMC. Produced a lot of heat. Cooler nicknamed the 'Dustbuster', 'Vacuum Cleaner', or 'Hoover' by some sites; Nvidia later released a video mocking the cooler. Due to manufacturing delays it was quickly replaced by the on-schedule NV35. Its Quadro sibling, Quadro FX 1000, 2000 was somewhat more successful. Double Z fillrate (helps shadowing). Each pixel pipe = 1 FP32 ALU handling 2 TMUs + 2 FX12 Mini-ALU (each one can do 2 MULs or 1 ADD or 1 MAD)
FX 5800 Ultra	NV30	3:8:4	500/500	128 Bit (GDDR2)
FX 5900	NV35	3:8:4	400/425	256 Bit	Swapped hardwired DirectX 7 T&L Units + DirectX 8 integer pixel shader units for DirectX 9 floating point units. Introduced a new feature called 'UltraShadow', upgraded to CineFX 2.0 Specification. Removed the noisy cooler, but still stole the PCI slot adjacent to the card by default. Quadro equivalent is QuadroFX 700, 3000. PCX uses AGP to PCIe bridge chip for use on PCIe motherboards. Double Z fillrate (helps shadowing). Each pixel pipe = 1 FP32 ALU handling 2 TMUs + 2 FP32 mini ALU (each one can do 1 MUL or 1 ADD or 1 FP16 MAD).
FX 5900 Ultra	NV35	3:8:4	450/425	256 Bit
PCX 5900	NV35	3:8:4	350/275	256 Bit
FX 5900 XT	NV35	3:8:4	400/350	256 Bit
FX 5950	NV38	3:8:4	475/475	256 Bit	Essentially a speed bumped GeForceFX 5900. Some antialiasing and shader unit tweaks in hardware. PCX uses AGP to PCIe bridge chip for use on PCIe motherboards. Quadro equivalent is QuadroFX 1300.
PCX 5950	NV38	3:8:4	350/475	256 Bit

GeForce 4 Series

2009-07-06T09:31:00.000-07:00

The GeForce4 (codenames below) refers to the fourth-generation of GeForce-branded graphics processing units (GPU) manufactured by Nvidia. There are two different GeForce4 families, the high-performance Ti family, and the budget MX family. The MX family spawned a mostly identical GeForce4 Go (NV17M) family for the laptop market. All three families were announced in early 2002; members within each family were differentiated by core and memory clock speeds. In late 2002, there was an attempt to form a fourth family, also for the laptop market, the only member of it being the GeForce4 4200 Go (NV28M) which was derived from the Ti line.

Nvidia GeForce 4 Series

Codename(s)	NV17, NV18, NV19, NV25, NV28
Release date	2002
Entry-level GPU	MX
Mid-Range GPU	Ti 4200, Ti 4400
High-end GPU	Ti 4600, Ti 4800
Direct3D and Shader version	D3D 7 (MX). D3D 8.1 with Pixel Shader 1.3 & Vertex Shader 1.1 (Ti)

[hide]

1 GeForce4 Ti
- 1.1 Architecture
- 1.2 Lineup
2 Performance
3 GeForce4 MX
- 3.1 Architecture
- 3.2 Lineup
4 GeForce4 model information
5 GeForce4 Go driver support
6 Known problems
7 See also
8 Notes and references
9 External links
GeForce4 Ti
Architecture

The GeForce4 Ti (NV25) was launched in April 2002 and was a revision of the GeForce 3 (NV20). It was very similar to its predecessor; the main differences were higher core and memory clock rates, a revised memory controller (known as Lightspeed Memory Architecture II), an additional vertex shader (the vertex and pixel shaders were now known as nFinite FX Engine II), hardware anti-aliasing (Accuview AA), and DVD playback.^[1] Proper dual-monitor support was also brought over from the GeForce 2 MX.^[2] The GeForce 4 Ti was superior to the GeForce 4 MX in virtually every aspect save for production cost, although the MX had the Nvidia VPE (video processing engine) which the Ti lacked.
Lineup

The initial two models were the Ti4400 and the top-of-the-range Ti4600. At the time of their introduction, Nvidia's main products were the entry-level GeForce 2 MX, the midrange GeForce4 MX models (released the same time as the Ti4400 and Ti4600), and the older but still high-performance GeForce 3 (demoted to the upper mid-range or performance niche).^[1] However, ATI's Radeon 8500LE was somewhat cheaper than the Ti4400, and outperformed its price competitors, the GeForce 3 Ti200 and GeForce4 MX 460. The GeForce 3 Ti500 filled the performance gap between the Ti200 and the Ti4400 but it could not be produced cheap enough to compete with the Radeon 8500.

In consequence, Nvidia rolled out a slightly cheaper model: the Ti4200. Although the 4200 was initially supposed to be part of the launch of the GeForce4 line, Nvidia had delayed its release to sell off the soon-to-be discontinued GeForce 3 chips. In an attempt to prevent the Ti4200 damaging the Ti4400's sales, Nvidia set the Ti4200's memory speed at 222 MHz on the models with a 128 MiB frame buffer—a full 53 MHz slower than the Ti4400 (all of which had 128 MiB frame buffers). Models with a 64 MiB frame buffer were set to 250 MHz memory speed. This tactic didn't work however, for two reasons. Firstly, the Ti4400 was perceived as being not good enough for those who wanted top performance (who preferred the Ti4600), nor those who wanted good value for money (who typically chose the Ti4200), causing the Ti4400 to fade into obscurity. Furthermore, some graphics card makers simply ignored Nvidia's guidelines for the Ti4200, and set the memory speed at 250 MHz on the 128 MiB models anyway.

Then in late 2002, the NV25 core was replaced by the NV28 core, which differed only by addition of AGP-8X support. The Ti4200 with AGP-8X support was based on this chip, and sold as the Ti4200-8X. A Ti4800SE replaced the Ti4400 and a Ti4800 replaced the Ti4600 respectively when the 8X AGP NV28 core was introduced on these.^[3]^[4] If the naming convention that had been applied to the AGP-8X capable Ti4200-8X was to have been applied consistently, these two cards should have been named Ti4400-8X and Ti4600-8X.

The only mobile derivative of the Ti series was the GeForce4 4200 Go (NV28M), launched in late 2002.^[5] The solution featured the same feature-set and similar performance compared to the NV28-based Ti4200, although the mobile variant was clocked lower. It outperformed the Mobility Radeon 9000 by a large margin, as well as being Nvidia's first DirectX 8 laptop graphics solution. However, because the GPU was not designed for the mobile space, it had thermal output similar to the desktop part. The 4200 Go also lacked power-saving circuitry like the MX-based GeForce4 4x0 Go series or the Mobility Radeon 9000. This caused problems for notebook manufacturers, especially with regards to battery life.^[6]
Performance

The GeForce4 Ti outperformed the older GeForce 3 by a significant margin.^[1] The competing ATI Radeon 8500 was generally faster than the GeForce 3 line, but was overshadowed by the GeForce 4 Ti in every area other than price and more advanced pixel shader (1.4) support.^[1] Nvidia, however, missed a chance to dominate the upper-range/performance segment by delaying the release of the Ti4200 and by not rolling out 128 MiB models quickly enough; otherwise the Ti4200 was cheaper and faster than the previous top-line GeForce 3 and Radeon 8500. Besides the late introduction of the Ti4200, the limited release 128 MiB models of the GeForce 3 Ti200 proved unimpressive, letting the Radeon 8500LE and even the full 8500 dominated the upper-range performance for a while.^[7] The Matrox Parhelia, despite having several DirectX 9.0 capabilities and other innovative features, was at most competitive with the GeForce 3 and GeForce 4 Ti 4200, but it was priced the same as the Ti 4600 at $399 USD. ATI had planned to develop a refresh to the 8500 to rival the GeForce 4 Ti, the 8500XT (R250), but ended up abandoning it to concentrate on the DirectX 9.0 compliant Radeon 9700.

ATI's resulting Radeon 9700 Pro defeated the Ti 4600 by 15–20% in normal conditions. However, when anti-aliasing (AA) and/or anisotropic filtering (AF) were enabled, the 9700 would beat the Ti 4600 by anywhere from 40–100%. Besides outclassing the Ti4600 in performance, the 9700 also had a notably superior feature-set with full DirectX 9.0 support.^[8] The next-generation GeForce FX 5800, despite being plagued by a loud fan and taking up two slots, as well as performing unimpressively against the Radeon 9700, nonetheless was still generally superior to and supplanted the 4600/4800 as Nvidia's flagship product. The Ti 4600 did hold a performance lead over the slower variants in the GeForce FX and Radeon R300 series, beating the FX 5600 and Radeon 9500. However, the continued proliferation of succeeding midrange DirectX 9.0 compliant cards, with the FX 5700 able to match or exceed, meant the obselesence and discontinuation of the Ti 4600 by mid-2003.

The GeForce 4 Ti4200 enjoyed considerable longetivity compared to its higher-clocked peers. At half the cost of the 4600, the 4200 remained the best balance between price and performance until the launch of the ATI Radeon 9500 Pro at the end of 2002, though the 9500 was only intended as a stopgap product.^[9] The Ti4200 still managed to hold its own against several next generation DirectX 9 chips released in late 2003; beating out the lackluster GeForce FX 5200 and the midrange FX 5600 and performing at parity with the midrange Radeon 9600, which was finally ATI's cost-effective permanent answer to the Ti4200.^[10]^[11]
GeForce4 MX
Architecture

If the capabilities of the GeForce4 generation are defined by the GeForce4 Ti, then the GeForce4 MX (NV17) is a GeForce4 in name only. Many criticized the GeForce MX name as a misleading marketing ploy since it was less advanced than the preceding GeForce 3. In the features comparison chart between the Ti and MX lines, it showed that the only "feature" that was missing on the MX was the nfiniteFX II engine—the DirectX 8 programmable vertex and pixel shaders.^[12] In reality, however, the GeForce4 MX was not a GeForce4 Ti with the shader hardware removed, as the MX's performance in games that did not use shaders was considerably behind the GeForce 4 Ti and GeForce 3. Disappointed enthusiasts described the GeForce4 MX as "GeForce 2 on steroids".

Though its lineage was of the past-generation GeForce 2, the GeForce4 MX did incorporate bandwidth and fill rate-saving techniques, dual-monitor support, and a multi-sampling anti-aliasing unit from the Ti series; the improved 128-bit DDR memory controller was crucial to solving the bandwidth limitations that plagued the GeForce 256 and GeForce 2 lines. It also owed some of its design heritage to Nvidia's high-end CAD products, and in performance-critical non-game applications it was remarkably effective. The most notable example is AutoCAD, in which the GeForce4 MX returned results within a single-digit percentage of GeForce4 Ti cards several times the price.

As the MX line was launched along with the rest of the GeForce4 in early 2002, id Software technical director John Carmack worried about the GeForce4 MX's potential success. Since Carmack feared that a widespread adoption of the MX would set back the development of advanced games that used programmable DirectX 8 vertex and pixel shaders, he warned gamers not to buy the chip. However, in mid 2004, id Software's Doom 3 was released with support for the GeForce4 MX; it is noteworthy that the MX is the only one in the list of supported chips that does not have DirectX 8 vertex and pixel shaders. Doom 3 is not supported on slower GPUs with an otherwise similar feature set to the MX, like the GeForce 2 and Radeon 7xxx series.

Despite harsh criticism by gaming enthusiasts, the GeForce4 MX was a market success. Priced about 30% above the GeForce 2 MX, it provided better performance, the ability to play a number of popular games that the GeForce 2 could not run well—above all else—to the average non-specialist it sounded as if it were a "real" GeForce4—i.e., a GeForce4 Ti. Although it was frequently out-performed by the older and more expensive GeForce 3, many buyers were unaware, particularly as Nvidia was quick not to let the GeForce 3 remain on the market. GeForce 4 MX was particularly successful in the PC OEM market, and rapidly replaced the GeForce 2 MX as the best-selling GPU.

In motion-video applications, the GeForce4 MX offered new functionality. It (and not the GeForce4 Ti) was the first GeForce member to feature the Nvidia VPE (video processing engine). It was also the first GeForce to offer hardware-iDCT and VLC (variable length code) decoding, making VPE a major upgrade from Nvidia’s previous HDVP. In the application of MPEG-2 playback, VPE could finally compete head-to-head with ATI's outstanding video engine.
Lineup

GeForce4 MX440-SE GPU

There were 3 initial models: the MX420, the MX440 and the MX460. The MX420 was designed for very low end PCs and replaced the GeForce 2 MX100 and MX200. The GeForce 4 MX440 was a mass-market OEM solution, replacing the GeForce 2 MX/MX400 and GeForce 2 Ti. The GeForce 4 MX460 was a midrange solution without a clear competitor. While the MX460 was not slow by any means, it was not priced far below the GeForce4 Ti4200, the GeForce 3 Ti200 and the Radeon 8500LE/9100 (even the full 8500 in some cases), each of which outperformed it easily as well as being fully DirectX 8 compliant. The end result was that the MX460 never had potential in the market and flopped.

In terms of 3D performance, the MX420 performed only slightly better than the GeForce 2 MX400 and below the GeForce 2 GTS, but this was never really much of a problem, considering its target audience. The nearest thing to a direct competitor the MX420 had was ATI's Radeon 7000. In practice however, its main competitors were actually chipset-integrated graphics solutions, such as Intel's 845G and Nvidia's own nForce 2.

Another version of MX440-SE GPU

The MX440 performed reasonably well for its intended audience, outperforming its closest competitor, the ATI Radeon 7500, as well as the discontinued GeForce 2 Ti and Ultra. When ATI launched its Radeon 9000 Pro in September 2002, it performed about the same as the MX440, but had crucial advantages with better single-texturing performance and proper support of DirectX 8 shaders. However, the 9000 was unable to break the MX440's entrenched hold on the OEM market. The MX440 also had a derivative called the MX440-SE. This was simply an MX 420 with increased memory bandwidth. Nvidia's answer to the Radeon 9000 was the GeForce FX 5200, but despite the 5200's DirectX 9 features it did not have the performance to match the MX440 even in DirectX 7.0 games. This kept the MX440 in production while the 5200 was discontinued, which could be considered ironic because the MX440 was supposed to be replaced by the 5200.

The GeForce4 Go was derived from the MX line and it was announced along with the rest of the GeForce4 lineup in early 2002. There was the 420 Go, 440 Go, and 460 Go. However, ATI had beaten them to the market with the similarly performing Mobility Radeon 7500, and later the DirectX 8.0 compliant Mobility Radeon 9000. (Despite its name, the short-lived 4200 Go is not part of this lineup, it was instead derived from the Ti line.)

Like the Ti series, the MX was also updated in late 2002 to support AGP-8X with the NV18 core. The two new models were the MX440-8X, which was clocked slightly faster than the original MX440, and the MX440SE, which had a narrower memory bus, and was intended as a replacement of sorts for the MX420. The MX460 was never updated; in fact, it had been discontinued several months previously. Another variant followed in late 2003—the MX 4000, which was a GeForce4 MX440SE with a slightly higher memory clock.

Surprisingly, the GeForce4 MX line received a third update in 2004, with the PCX 4300—an MX 4000 with support for PCI Express, and a wider memory bus. In spite of its new codename (NV19), the PCX 4300 is in fact simply an NV18 core with a chip bridging the NV18's native AGP interface with the PCI-Express bus.
GeForce4 Go driver support
This family is a derivative of the GeForce4 MX family, produced for the laptop market. The GeForce4 Go family, performance wise, can be considered comparable to the MX line. However, in terms of support, some users have become rather irritated at an uncharacteristic lack of driver support from Nvidia. Instead of supporting this family of chips, Nvidia redirects users to the manufacturer's webpage.

One possible solution to the lack of driver support for the Go family is the third party Omega Drivers. However, it is not recommended that one install these drivers unless one is willing to accept the risks. Using third party drivers can, among other things, invalidate warranties. The Omega Drivers are supported by neither laptop manufacturers, laptop ODMs, nor by Nvidia. Nvidia has also attempted legal action against a version of Omega Drivers that included the Nvidia logo.^[13] The Omega drivers are essentially stock drivers modified to deliver up to 30%-40% performance increases without overclocking.^{[citation needed]} The invalidation of warranties is usually seen by the expert users as a corporate safety net rather than an actual warning against devices failing.

Nvidia’s own solution to the problem is to try drivers from laptopvideo2go.com. This website hosts desktop display drivers which have been modified to install on a notebook. The drivers found on this website do not contain any laptop specific modifications and thus may or may not be better than drivers provided by your laptop's manufacturer.

Nvidia

2009-07-05T02:52:00.000-07:00

Nvidia (NASDAQ: NVDA, pronounced /ɛnˈvɪ.di.ə/), a multinational corporation, specializes in the development of graphics processing units and chipset technologies for workstations, personal computers, and mobile devices. Based in Santa Clara, California, the company has become a major supplier of integrated circuits (ICs) such as graphics processing units (GPUs) and chipsets used in graphics cards, and video-game consoles and personal-computer motherboards.

Notable Nvidia product-lines include the GeForce series for gaming, the Quadro series for computer aided design and for digital content creation on workstations, and the nForce series of integrated motherboard chipsets.

NVIDIA Corporation

Type	Public (NASDAQ: NVDA)
Founded	1993
Headquarters	2701 San Tomas Expressway Santa Clara, California USA
Key people	Jen-Hsun Huang, Co-founder, President and CEO Chris Malachowsky, Co-founder, NVIDIA Fellow, Senior Vice President, Engineering and Operations Jonah M. Alben, Vice President, GPU Engineering Debora Shoquist, Senior Vice President, Operations Dr Ranga Jayaraman, CIO
Industry	Semiconductors- Specialized
Products	Graphics processing units Chipsets
Revenue	▲$4.1 Billion USD (2007) [assets: 80 billion]
Net income	▲$797.6 Million USD (2007)
Employees	over 4,985 (as of June 2008^[update])
Website	www.nvidia.com

[hide]

1 Company history
2 Branding
3 Products
4 Market history
5 See also
6 References
7 External links
Company history

Three people co-founded Nvidia in 1993:
Jen-Hsun Huang (currently^[update] CEO), previously Director of coreware at LSI Logic and a microprocessor designer at Advanced Micro Devices (AMD)
Curtis Priem, previously a senior staff engineer and graphics chip designer at Sun Microsystems
Chris Malachowsky, an electrical engineer who also worked for Sun

The founders gained venture-capital funding from Sequoia Capital. ^[1]

In 2000 Nvidia acquired the intellectual assets of its one-time rival 3dfx, one of the biggest graphics-companies of the mid- to late-1990s.

On December 14, 2005, Nvidia acquired ULI Electronics, which at the time supplied third-party Southbridge parts for chipsets to ATI, Nvidia's competitor. In March 2006, Nvidia acquired Hybrid Graphics^[2] and on January 5, 2007, it announced that it had completed the acquisition of PortalPlayer, Inc.^[3]

In December 2006 Nvidia, along with its main rival in the graphics industry AMD (which acquired ATI), received subpoenas from the Justice Department regarding possible antitrust violations in the graphics card industry.^[4]

Forbes magazine named Nvidia its Company of the Year for 2007, citing the accomplishments it made during the said period as well as during the previous 5 years.^[5]

Branding

The company's name combines an initial n — a letter usable as a pronumeral in mathematical statements — and the root of video— from Latin videre, "to see", thus implying "the best visual experience"^{[citation needed]} or perhaps "immeasurable display".^{[original research?]} The name NVIDIA suggests "envy" (Spanish envidia or in Latin, Italian, or Romanian invidia); and Nvidia's GeForce 8 series product uses the slogan "Green with envy". The company-name appears entirely in upper-case ("NVIDIA") in the company's technical documentation.

Products

Nvidia headquarters in Santa Clara

A graphics processing unit on an Nvidia GeForce 6600 GT

Nvidia's product-portfolio includes graphics-processors, wireless-communications processors, PC platform (motherboard core-logic) chipsets, and digital-media-player software. The community of computer users arguably knows Nvidia best for its "GeForce" product-line, which not only offers a complete line of "discrete" graphics chips found in AIB (add-in-board) video cards, but also provides a core-technology in both the Microsoft Xbox game console, Sony PS3 game console, and nForce motherboards.

In many respects Nvidia resembles its competitor ATI: Both companies began with a focus in the PC market and later expanded their activities into chips for non-PC applications. Nvidia does not sell graphics boards into the retail market, instead focusing on the development of GPU chips. As a fabless semiconductor company, Nvidia contracts out chip-manufacturing to the Taiwan Semiconductor Manufacturing Company, Ltd. (TSMC). As part of their operations, both ATI and Nvidia create "reference designs" (circuit-board schematics) and provide manufacturing samples to their board-partners. Manufacturers of Nvidia cards include BFG, EVGA, Foxconn, and PNY. XFX, ASUS, ECS, Gigabyte Technology, and MSI exemplify manufacturers of both ATI and Nvidia cards.

December 2004 saw the announcement that Nvidia would assist Sony with the design of the graphics processor (RSX) in the PlayStation 3 game console. In March 2006 it emerged that Nvidia would deliver RSX to Sony as an IP-core, and that Sony alone would be responsible for manufacturing the RSX. Under the agreement, Nvidia will provide ongoing support to port the RSX to Sony's fabs of choice (Sony and Toshiba), as well as die shrinks to 65 nm. This is a departure from Nvidia's business arrangement with Microsoft, in which Nvidia managed production and delivery of the Xbox GPU through Nvidia's usual third-party foundry contracts. (Meanwhile, Microsoft has chosen to license a design by ATI and make their own manufacturing arrangements for Xbox 360's graphics hardware, as has Nintendo for their Wii console to succeed the ATI-based GameCube.)

On February 4, 2008, Nvidia announced plans to acquire physics software producer AGEIA, whose PhysX physics engine program forms part of hundreds of games shipping or in development for PlayStation 3, Xbox 360, Wii, and gaming PCs.^[6] This transaction completed on February 13, 2008^[7] and efforts to integrate PhysX into the GeForce 8800's CUDA system began. ^[8]^[9]

On June 2, 2008 Nvidia officially announced its new Tegra product-line.^[10] The Tegra, a System-on-a-Chip (SoC), integrates an ARM CPU, GPU, northbridge and southbridge onto a single chip. Commentators^[who?] opine that Nvidia will target this product at the smart-phone and mobile Internet device markets.

Graphics chipsets

NV1 – Nvidia's first product, based on quadratic surfaces
RIVA 128 and RIVA 128ZX – DirectX 5 support, OpenGL 1 support, Nvidia's first DirectX-compliant hardware
RIVA TNT, RIVA TNT2 – DirectX 6 support, OpenGL 1 support; the series that made Nvidia a market-leader
Nvidia GeForce - Desktop-graphics acceleration-solutions
Nvidia Quadro – High-quality workstation solutions
Nvidia Tesla - Dedicated GPGPU processing for High Performance Computing systems
Nvidia GoForce – Media processors for PDAs, Smartphones, and mobile phones featuring nPower technology
GPU for game consoles
- Xbox GeForce 3 - class GPU (on an Intel Pentium III/Celeron platform)
- PlayStation 3 - RSX 'Reality Synthesizer'
  Motherboard chipsets
- nForce series
  - nForce (AMD Athlon/Duron K7 line)
  - nForce2 (AMD Athlon/Duron K7 line, SPP (system platform processor) or IGP (Integrated Graphics Platform) and MCP (Media and Communications Processor), also features SoundStorm)
  - nForce3 (AMD Athlon 64/Athlon 64 FX/Opteron, MCP only)
  - nForce4 (AMD Athlon 64/Athlon 64 X2/Athlon 64 FX/Opteron, MCP only;Intel Pentium 4/Pentium D, SSP + MCP)
  - nForce 500 (AMD Athlon 64 FX/Athlon 64 X2/Athlon 64/Sempron or Intel Core 2 Extreme/Core 2 Duo/Pentium 4/Celeron D/Pentium D)
  - nForce 600 (AMD Quad FX or Intel Core 2 Quad/Core 2 Extreme/Core 2 Duo/Pentium 4/Celeron D/Pentium D)
  - nForce 700 (Intel Core 2 and AMD Phenom)
    Documentation and drivers
    
    Main article: Graphics hardware and FOSS
    
    Nvidia does not publish the documentation for its hardware, meaning that programmers cannot write appropriate and effective open-source drivers for Nvidia's products. Instead, Nvidia provides its own binary GeForce graphics drivers for X.Org and a thin open-source library that interfaces with the Linux, FreeBSD or Solaris kernels and the proprietary graphics software. Nvidia also supports an obfuscated open-source driver that only supports two-dimensional hardware acceleration and ships with the X.Org distribution. Nvidia's Linux support has promoted mutual adoption in the entertainment, scientific visualization, defense and simulation/training industries, traditionally dominated by SGI, Evans & Sutherland and other relatively costly vendors.
    
    Because of the proprietary nature of Nvidia's drivers, they continue to generate controversy within the free-software communities. Some Linux and BSD users insist on using only open-source drivers, and regard Nvidia's insistence on providing nothing more than a binary-only driver as wholly inadequate, given that competing manufacturers like Intel offer support and documentation for open-source developers, and that others like ATI at least release partial documentation.^[11] Because of the closed nature of the drivers, Nvidia video cards do not deliver adequate features on several platforms and architectures, such as FreeBSD on the x86-64 architecture and the other BSD operating systems on any architecture. Support for three-dimensional graphics acceleration in Linux on the PowerPC does not exist; nor does support for Linux on the hypervisor-restricted PlayStation 3 console. While some users accept the Nvidia-supported drivers, many users of open-source software would prefer better out-of-the-box performance^[12] if given the choice. However, the performance and functionality of the binary Nvidia video card drivers surpass those of open-source alternatives^{[citation needed]} following VESA standards.
    
    Nvidia drivers cause known issues^{[citation needed]} on computers running Windows Vista. The forums on the Nvidia homepage have various topics where users discuss the failure and recovery error of the driver without any solution.
    
    X.Org Foundation and Freedesktop.org have started the Nouveau project, which aims to develop free software drivers for Nvidia graphics cards by reverse-engineering Nvidia's current proprietary drivers for Linux.
    Market-share
    
    According to a survey^[13] conducted by Jon Peddie Research, a market-watch firm, in the third quarter of 2007, Nvidia occupied the top slot in the desktop graphic-devices market with a market share of 37.8%. However, in the mobile space, it remained third with 22.8% of the market. Overall Nvidia has maintained its position as the second-largest supplier of PC graphic shipments, which includes both integrated and discrete GPUs, with 33.9% market share, their highest in many years, which puts them just behind Intel (38%).
    
    According to the Steam hardware survey^[14] conducted by the game-developer Valve, Nvidia had 64.64% of PC video card market share (as of 1 December 2008 (2008 -12-01)^[update]). ATI had 27.12% of the PC video card market share. But this could relate to Valve releasing trial versions of The Orange Box to Nvidia graphics-card users, which link to the test. However, free copies of The Orange Box were also released^{[by whom?]} to ATI card purchasers^{[citation needed]}, notably those who purchased the Radeon 2900XT.
    Market history
    Before DirectX
    
    An Nvidia RIVA 128 AGP video card
    
    Nvidia released its first graphics card, the NV1, in 1995. Its design used quadratic surfaces, with an integrated playback-only sound-card and ports for Sega Saturn gamepads. Because the Saturn also used forward-rendered quadratics, programmers ported several Saturn games to play on a PC with NV1, such as Panzer Dragoon and Virtua Fighter Remix. However, the NV1 struggled in a market-place full of several competing proprietary standards.
    
    Market interest in the product ended when Microsoft announced the DirectX specifications, based upon polygons. Subsequently NV1 development continued internally as the NV2 project, funded by several millions of dollars of investment from Sega. Sega hoped that an integrated sound-and-graphics chip would cut the manufacturing cost of their next console. However, Sega eventually realized the flaws in implementing quadratic surfaces, and the NV2 was never fully developed.^{[citation needed]}
    
    Transition to DirectX
    
    Nvidia's CEO Jen-Hsun Huang realized at this point that after two failed products, something had to change for the company to survive. He hired David Kirk as Chief Scientist from software-developer Crystal Dynamics. Kirk would combined Nvidia's experience in 3D hardware with an intimate understanding of practical implementations of rendering.
    
    As part of the corporate transformation, Nvidia sought to fully support DirectX, and dropped multimedia functionality in order to reduce manufacturing costs. Nvidia also adopted the goal of an internal 6-month product-cycle, under the supposition that it could mitigate a failure of any one product by having a replacement moving through the pipeline.
    
    However, since the Sega NV2 contract remained secret, and since Nvidia had laid off employees, it appeared to many industry observers that Nvidia had ceased active research-and-development. So when Nvidia first announced the RIVA 128 in 1997, the specifications were hard to believe: performance superior to market leader 3dfx Voodoo Graphics, and a full hardware triangle setup engine. The RIVA 128 shipped in volume, and the combination of its low cost and high performance made it a popular choice for OEMs.
    
    Ascendency: RIVA TNT
    
    Having finally developed and shipped in volume the market-leading integrated graphics chipset, Nvidia set itself the goal of doubling the number of pixel pipelines in its chip, in order to realize a substantial performance-gain. The TwiN Texel (RIVA TNT) engine which Nvidia subsequently developed could either apply two textures to a single pixel, or process two pixels per clock-cycle. The former case allowed for improved visual quality, the latter for doubling the maximum fill-rate.
    
    New features included a 24-bit Z-buffer with 8-bit stencil support, anisotropic filtering, and per-pixel MIP mapping. In certain respects (such as transistor-count) the TNT had begun to rival Intel's Pentium processors for complexity. However, while the TNT offered an astonishing range of quality integrated features, it failed to displace the market leader, 3dfx's Voodoo 2, because the actual clock-speed ended up at only 90 MHz, about 35% less than expected.
    
    Nvidia responded with a refresh part: a die shrink for the TNT architecture from 350 nm to 250 nm. A stock TNT2 now ran at 125 MHz, an Ultra at 150 MHz. Though the Voodoo 3 beat Nvidia to the market, 3dfx's offering proved disappointing: it was not much faster and lacked features that were becoming standard, such as 32-bit color and textures of resolution greater than 256 x 256 pixels.
    
    The RIVA TNT2 marked a major turning-point for Nvidia. They had finally delivered a product competitive with the fastest on the market, with a superior feature-set, strong 2D functionality, all integrated onto a single die with strong yields, that ramped to impressive clock-speeds. Nvidia's six month cycle refresh took the competition by surprise, giving it the initiative in rolling out new products.
    
    Market leadership: GeForce
    
    A GeForce 4 MX 64MB card. Nvidia produced such cards from 2002 to 2003.
    
    The autumn of 1999 saw the release of the GeForce 256 (NV10), most notably bringing on-board transformation and lighting. It ran at 120 MHz; it implemented advanced video-acceleration, motion-compensation and hardware sub-picture alpha-blending; and had four pixel pipelines. The GeForce outperformed existing products — such as the ATI Rage 128, 3dfx Voodoo 3, Matrox G400 MAX, and RIVA TNT2 — by a wide margin.
    
    Due to the success of its products, Nvidia won the contract to develop the graphics hardware for Microsoft’s Xbox game-console, which earned Nvidia a large $200 million advance. However, the project drew the time of many of Nvidia's best engineers. In the short term, this was of no importance, and the GeForce 2 GTS shipped in the summer of 2000.
    
    The GTS benefited from the fact that Nvidia had by this time acquired extensive manufacturing experience with their highly integrated cores, and as a result they succeeded in optimizing the core for clock-speeds. The volume of chips produced by Nvidia also enabled it to bin-split parts, picking out the highest-quality cores for its premium range. As a result, the GTS shipped at 200 MHz. The pixel fill rate of the GeForce256 nearly doubled, and texel-fill rate nearly quadrupled because multi-texturing was added to each pixel pipeline. New features included S3TC compression, FSAA, and improved MPEG-2 motion compensation.
    
    Shortly afterward^[when?] Nvidia launched the GeForce 2 MX, intended for the budget and OEM market. It had two pixel-pipelines fewer, and ran at 165 MHz and later at 250 MHz. Offering strong performance at a mid-range price, the GeForce 2MX became one of the most successful graphics chipsets. Nvidia also shipped a mobile derivative called the GeForce2 Go at the end of 2000.
    
    Nvidia's success proved too much for 3dfx to recover its past market-share. The long-delayed Voodoo 5, the successor to the Voodoo 3, did not compare favorably with the GeForce 2 in either price or performance, and failed to generate the sales needed to keep the company afloat. With 3dfx on the verge of bankruptcy near the end of 2000, Nvidia purchased most of 3dfx's intellectual property (in dispute at the time)^{[citation needed]}. Nvidia also acquired anti-aliasing expertise and about 100 engineers (but not the company itself, which filed for bankruptcy in 2002).
    
    Nvidia developed the GeForce 3, which pioneered DirectX 8 vertex and pixel-shaders, and then refined it with the GeForce 4 Ti line. After the GeForce 2 MX came the GeForce 4 MX. Nvidia announced the GeForce 4 Ti, MX, and Go in January 2002, one of the largest releases in Nvidia history. Cleverly, the chips in the Ti and Go series differed only in chip and memory clock-speeds. (The MX series lacked the pixel and vertex shader functionalities; it derived from GeForce 2 level hardware.)
    
    Stumbles with the FX series
    
    At this point Nvidia’s dominated the GPU market. However, ATI Technologies remained competitive due to its new Radeon product, which performed mostly on a par with the GeForce 2 GTS. Though ATI's answer to the GeForce 3, the Radeon 8500, came later to market and initially suffered from issues with drivers, the 8500 proved a superior competitor due to its lower price and untapped potential for growth. Nvidia countered ATI's offering with the GeForce 4 Ti line, but not before the 8500 had carved out a niche. ATI opted to work on its next-generation Radeon 9700 rather than on a direct competitor to the GeForce 4 Ti.
    
    During the development of the next-generation GeForce FX chips, many of Nvidia’s best engineers focused on the Xbox contract, including the API used as part of the SoundStorm platform. Nvidia also had a contractual obligation to develop newer and more hack-resistant NV2A chips, and this requirement further shortchanged the FX project. The Xbox contract did not allow for falling manufacturing costs as processor technology improved, and Microsoft sought to re-negotiate the terms of the contract, withholding the DirectX 9 specifications as leverage. The previously very good relations between Nvidia and Microsoft deteriorated as a result. The two companies later settled the dispute through arbitration — without releasing the terms of the settlement to the public.
    
    Due to the Xbox dispute, no consultation with Nvidia took place during the development of the DirectX 9 specification. ATI limited rendering color support to 24-bit floating point^{[citation needed]}, and emphasized shader performance. Developers^[who?] built the shader-compiler using the Radeon 9700 as the base card.
    
    In contrast, Nvidia’s cards offered 16- and 32-bit floating point modes, offering either lower visual quality (as compared to the competition), or slower performance. The 32-bit support made them much more expensive to manufacture, requiring a higher transistor count. Shader performance often remained at half or less of the speed provided by ATI's competing products. Having made its reputation by designing easy-to-manufacture DirectX-compatible parts, Nvidia had misjudged Microsoft’s next standard and paid a heavy price: as more and more games started to rely on DirectX 9 features, the poor shader-performance of the GeForce FX series became more obvious. With the exception of the FX 5700 series (a late revision), the FX series did not compete well against ATI cards.
    
    Nvidia released an "FX only" demo called Dawn, but a hacked wrapper enabled it to run on a 9700, where it ran faster despite translation overhead. Nvidia began to use application detection to optimize their drivers. Hardware review sites published articles showing that Nvidia’s driver auto-detected benchmarks and that it produced artificially inflated scores that did not relate to real-world performance.^{[citation needed]} Often tips from ATI’s driver development team lay behind these articles^{[citation needed]}. While Nvidia did partially close the performance gap with new instruction-reordering capabilities introduced in later drivers, shader performance remained weak and over-sensitive to hardware-specific code-compilation. Nvidia worked with Microsoft to release an updated DirectX compiler that generated code optimized for the GeForce FX.
    
    Furthermore, GeForce FX devices also ran hot, because they drew as much as double the amount of power as equivalent parts from ATI. The GeForce FX 5800 Ultra became notorious for its fan noise, and acquired the nicknames "dustbuster" and "leafblower" - Nvidia jokingly acknowledged these accusations with a video in which the marketing team compares the cards to a Harley-Davidson motorcycle.^[15] Although the quieter 5900 replaced the 5800 without fanfare, the FX chips still needed large and expensive fans, placing Nvidia's partners at a manufacturing-cost disadvantage compared to ATI. As a result of Microsoft's actions, and the resultant FX series' weaknesses, Nvidia lost its market leadership position to ATI.
    GeForce 6 series and later
    
    The old Nvidia logo, in use until 2006
    
    With the GeForce 6 series, Nvidia had clearly moved beyond the DX9 performance problems that plagued the previous generation. The GeForce 6 series not only performed competitively where Direct 3D shaders were concerned, but also supported DirectX Shader Model 3.0, while ATI's competing X800 series chips only supported the previous 2.0 specification. This proved an insignificant advantage, mainly because games of that period did not employ extensions for Shader Model 3.0. However, it demonstrated Nvidia's desire to design and follow through with the newest features and deliver them in a specific timeframe. What became more apparent during this time was that the products of the two firms, ATI and Nvidia, offered equivalent performance. The two firms traded blows in specific titles and specific criteria — resolution, image quality, anisotropic filtering/anti-aliasing — but differences were becoming more abstract, and the reigning concern became price-to-performance. The mid-range offerings of the two firms demonstrated the consumers' appetite for affordable, high-performance graphics cards, and it is now this price segment in which much of the firms' profitability is determined. The GeForce 6 series were released in a very interesting period: the game Doom 3 was just released where ATI's Radeon 9700 struggled at the OpenGL performance. In 2004, the GeForce 6800 performed excellently, while the GeForce 6600GT remained as important to Nvidia as the GeForce2 MX a few years previously. The GeForce 6600GT enabled users of the card to play Doom 3 at very high resolutions and graphical settings, which was thought to be highly unlikely considering its selling price. The GeForce 6 series also introduced SLI (which is similar to what 3dfx was using on the Voodoo 2). A combination of SLI and the performance gain as a result returned Nvidia to market leadership.
    
    Badge displayed on products certified by Nvidia to utilize SLI technology
    
    The GeForce 7 series represented a heavily beefed-up extension of the reliable 6-series. The industry's introduction of the PCI Express bus standard allowed Nvidia to release SLI (Scalable Link Interface), a solution that employs two similar cards to share the workload in rendering. While these solutions do not equate to double the performance, and require more electricity (two cards vis-à-vis one), they can make a huge difference as higher resolutions and settings are enabled and, more importantly, offer more upgrade flexibility. ATI responded with the X1000 series, and their own dual-rendering solution called "CrossFire". Sony chose Nvidia to develop the "RSX" chip used in the PlayStation 3 — a modified version of the 7800 GPU.
    
    Nvidia released the 8-series chip towards the end of 2006, making the 8-series the first to support Microsoft's next-generation DirectX 10 specification. The 8-series GPUs also featured the revolutionary Unified Shader Architecture, and Nvidia leveraged this to provide an additional functionality for its graphics cards: better support for General Purpose Computing on GPU (GPGPU). A new product-line of "compute-only" devices called Nvidia Tesla emerged from the G80 architecture, and subsequently Nvidia also became the market leader of this new field by introducing the world's first C programming language API for GPGPU: CUDA.
    
    Nvidia released two models of the high-end 8-series (8800) chip: the 8800GTS (640MB and 320MB) and the 8800GTX (768MB). Later, Nvidia released the 8800 Ultra (essentially an 8800GTX with a different cooler and higher clocks). All three of these cards derive from the 90 nm G80 core (with 681 million transistors). The GTS model had 96 stream processors and 20 ROPS and the GTX/Ultra had 128 stream processors and 24 ROPS.
    
    In early 2007 Nvidia released the 8800GTS 320mb. This card resembles an 8800GTS 640, but with 32MB memory chips instead of 64MB (the cards contained 10 memory chips).
    
    In October 2007 Nvidia released the 8800GT. The 8800GT used the new 65 nm G92 GPU and had 112 stream processors. It contained 512Mb of VRAM and operated on a 256bit bus. It had several fixes and new features that the previous 8800s lacked.
    
    Later in December 2007 Nvidia released the 8800GTS G92. It represented a larger 8800GT with higher clocks and all of the 128 stream processors of the G92 unlocked. Both the 8800GTS G92 and 8800GT have full PCI Express 2.0 support.
    
    In February 2008 Nvidia released the 9600-series chip, which supports Microsoft's DirectX 10 specification, in response to ATI's release of the Radeon HD3800 series. After March Nvidia released the GeForce 9800 GX2, which, roughly put, packs two GeForce 8800 GTS G92s into a single card.
    
    In June 2008 Nvidia released their new flagship GPUs named the GTX 280 and GTX 260. The cards used the same basic Unified Architecture deployed in the previous 8 and 9 series cards, but with a tune-up in power. Both of the cards take as their basis the GT200 GPU. This GPU contains 1.4 billion transistors on a 65 nm fabrication. The GTX 280 has 240 shaders (stream processors) and the GTX 260 has 192 shaders (stream processors) . The GTX 280 has 1GB of GDDR3 VRAM and uses a 512-bit memory bus. The GTX 260 has 896MB of GDDR3 VRAM on a 448-bit memory bus (revised in September 2008 to include 216 shaders). The GTX 280 allegedly provides approximately 933 GFLOPS of floating point power.^{[citation needed]}
    
    In January 2009 Nvidia released a 55 nm die shrink of GT200 called the GT200b. The update to the GTX 280 (card called GTX 285) allegedly providing 1062.72 GFLOPS of floating point power; an update to the GTX 260 (still called the GTX 260) with 216 shaders and a dual-chip card (called GTX 295), featuring two GT200b (55 nm-shrinked GT200 chips, a hybrid of the GT200 cores that featured on the original GTX 280 and GTX 260). Distinctively, each individual GPU features 240 stream processors, but only a 448-bit memory bus. The GTX 295 has 1.75GB (1792MB, 896MB per GPU) of GDDR3 VRAM. The GTX 295 allegedly provides approximately 1788.48 GFLOPS of floating-point power.
    
    March 2009 saw the release of the GTS 250 mainstream chip, based on the previous generation G92s but 55 nm die shrink code named the G92b. The GTS 250 derives from the 9800GTX+ (some cards are rebranded 9800GTX+s) and has 128 shaders (stream processors) with a 256-bit memory bus and 0.5GB or 1GB of GDDR3 of VRAM.
    
    On May 12 2009, Nvidia released images of a new revised edition of the GTX295. This design, while similar to ATI's HD4870x2, differs from the original. In the first production run of the GTX295, it literally consisted of two separate graphics accelerators sandwiched in the same casing and connected by a ribbon SLI cable. The new design encompasses both GPUs on the one PCB. The card still has the same specifications of the first production run, although speculation admits it will sell for less due to lower manufacturing-costs for the more compact device.
    
    Defective mobile video adapters
    
    In July 2008, Nvidia noted increased rates of failure in certain mobile video adapters.^[16] A writer for The Inquirer alleged that the problems potentially affect all G84 and G86, mobile and desktop, video adapters,^[17] though NVIDIA have denied this.^[18]^[19] In response to this issue, Dell and HP released BIOS updates for all affected notebook computers which turn on the cooling fan earlier than before in an effort to keep the defective video adapter at a lower temperature. Leigh Stark has suggested that this may lead to the premature failure of the cooling fan.^[20] It is also possible that this resolution may only delay component failure past warranty expiration.
    
    In August 2008 rumors emerged that these issues also affected G92 & G94 mobile video adapters.^[21] But at the end of August 2008, Nvidia reportedly issued a product-change notification announcing plans to update the bump material of GeForce 8 and 9 series chips “to increase supply and enhance package robustness”. ^[22] In response to the possibility of defects in some mobile video adapters from Nvidia, some notebook manufacturers have allegedly turned to ATI to provide graphics options on their new Montevina notebook computers.^[23]
    
    On 18 August 2008, according to the direct2dell.com blog, Dell began to offer a 12-month limited warranty "enhancement" specific to this issue on affected notebook computers worldwide.^[24]
    
    On 8 September 2008, Nvidia made a deal with large OEMs, such as Dell and HP, that they will get $200 per affected notebook^[25]
    
    On 9 October 2008, Apple Inc. announced on a support page that MacBook Pro notebook computers had exhibited faulty Nvidia GeForce 8600M GT graphics adapters.^[26] The manufacture of affected computers took place between approximately May 2007 and September 2008. Apple also stated that they would repair MacBook Pros affected within two years of the original purchase date free-of-charge and also offered refunds to customers who had paid for repairs related to this issue.
    
    On 9 December 2008, The Inquirer conducted another series of tests to check whether the new MacBook Pro notebook computers used eutectic solder or high-lead solder.^[27] They found that the 9400M chipset used eutectic solder, while the 9600M used a high-lead solder which they associated with the "old process" responsible for the failures.

INTEL GMA

2009-07-05T02:48:00.000-07:00

The Intel Graphics Media Accelerator, or GMA, is Intel's current line of integrated graphics processors built into various motherboard chipsets.

These integrated graphics products allow a computer to be built without a separate graphics card, which can reduce cost, power consumption and noise. They are commonly found on low-priced notebook and desktop computers as well as business computers, which do not need high levels of graphics capability. 90% of all PCs sold have integrated graphics.^[1] They rely on the computer's main memory for storage, which imposes a performance penalty as both the CPU and GPU have to access memory over the same bus.

GMA X3000 on Intel DG965WHMKR motherboard

[hide]

History

The GMA line of GPUs replaces the earlier “Intel Extreme Graphics”, Intel’s first series of integrated graphics chips, and Intel740 line, which were discrete units in the form of AGP cards.

The original architecture of GMA systems supported only a few functions in hardware, and relied on the host CPU to handle at least some of the graphics pipeline, further decreasing performance. However, with the introduction of Intel’s 4th generation of GMA architecture (GMA X3000) in 2006, many of the functions are now built into the hardware, providing an increase in performance. The 4th generation of GMA combines fixed function capabilities with a threaded array of programmable executions units, providing advantages to both graphics and video performance. Many of the advantages of the new GMA architecture come from the ability to flexibly switch as needed between executing graphics-related tasks or video-related tasks. While GMA performance has been widely criticized in the past as being too slow for computer games, the latest GMA generation should ease many of those concerns for the casual gamer.

Despite similarities, Intel's main series of GMA IGPs is not based on the PowerVR technology Intel licensed from Imagination Technologies. Intel used the low-power PowerVR MBX designs in chipsets supporting their XScale platform, and since the sale of XScale in 2006 has licensed the PowerVR SGX and used it in the GMA 500 IGP for use with their Atom platform.

Intel has begun working on a new series of discrete (non-integrated) graphics hardware products, under the codename Larrabee.

Hardware: graphics cores

GMA 900

The GMA 900 was the first graphics core produced under Intel's Graphics Media Accelerator product name, and was incorporated in the Intel 910G, 915G, and 915Gx chipsets.

The 3D architecture of the GMA 900 was a significant upgrade from the previous Extreme 3D graphics processors. It is a 4 pixel per clock cycle design supporting DirectX 9 pixel shader model 2.0. It operates at a clock rate ranging from 160 to 333 MHz, depending on the particular chipset. At 333 MHz, it has a peak pixel fill-rate of 1332 megapixels per second. However, the architecture still lacks support for hardware transform and lighting and the similar vertex shader technologies.

Like previous Intel integrated graphics parts, the GMA 900 has hardware support for MPEG-2 motion compensation, color-space conversion and DirectDraw overlay.

The processor uses different separate clock generators for display and render cores. The display unit includes a 400MHz RAMDAC, 2 25-200Mpixel/s serial DVO ports, and 2 display controllers. In mobile chipsets, up to 2 18-bit 25-112MHz LVDS transmitters are included.

GMA 950

The GMA 950 is Intel's second-generation Graphics Media Accelerator graphics core, which was also referred by Intel as 'Gen 3.5 Integrated Graphics Engine' in datasheets. It is used in the Intel 940GML, 945G, 945GU and 945GT system chipsets. The amount of video-decoding hardware has increased; VLD, iDCT, and dual video overlay windows are now handled in hardware^{[citation needed]} . The maximum core clock is up to 400 MHz (on Intel 945G, 945GC, 945GZ, 945GSE), boosting pixel fill-rate to a theoretical 1600 megapixels/s.

The GMA 950 shares the same architectural weakness as the GMA 900: no hardware geometry processing. Neither basic (DX7) hardware transform and lighting,^[2] nor more advanced vertex shaders (DX8 and later) are handled in the GMA hardware.

GMA 3000

The 946GZ, Q965 and Q963 chipsets use GMA 3000.^[3]^[4] The GMA 3000 3D core is very different from the X3000, despite similar names. It is based more directly on the previous generation GMA 900 and GMA 950 graphics, and belonging to the same "i915" family with them. It has pixel and vertex shaders which only supports shader model 2.0 features, and the vertex shaders are still only software provided. In addition, hardware video acceleration such as hardware-based iDCT computation, ProcAmp (video stream independent color correction), VC-1 decoding are not implemented in hardware. Of the GMA 3000-equipped chipsets, only Q965 retains dual independent display support. The core speed is rated 400 MHz with 1.6 Gpixel/s fill rate in datasheets, but was listed as 667MHz core in white paper.^[5]

Memory controller can now address maximum 256MB memory and the integrated serial DVO ports has increased top speed to 270Mpixel/s.

GMA 3100

The G31, G33, Q33 and Q35 chipsets use the GMA 3100, which is DX9 capable. The 3D core is very similar to the older GMA 3000, including the lack of hardware accelerated vertex shaders. However, the RAMDAC is reduced to 350MHz, and the DVO ports were reduced to 225Mpixel/s.

GMA X3000

The GMA X3000 for desktop was "substantially redesigned" when compared to previous GMA iterations^[6] and it is used in the Intel G965 north bridge controller.^[7] The GMA X3000 was launched in July 2006.^[8] X3000's underlying 3D rendering hardware is organized as a unified shader processor consisting of 8 scalar execution units. Each pipeline can process video, vertex, or texture operations. A central scheduler dynamically dispatches threads to pipeline resources, to maximize rendering throughput (and decrease the impact of individual pipeline stalls.) However, due to the scalar nature of the execution units, they can only process data on a single pixel component at a time.^[9] The GMA X3000 supports DirectX 9.0 with vertex and pixel Shader Model 3.0 features.

The processor consists of different clock domains, meaning that the entire chip does not operate the same clock speed. This causes some difficulty when measuring peak throughput of its various functions. Further adding to the confusion, it is listed as 667MHz in Intel G965 white paper, but listed as 400MHz in Intel G965 datasheet. There are various rules that define the IGP's processing capabilities.^[9]

Memory controller can now address maximum 384MB memory according to white paper, but only 256MB in datasheet.

GMA X3100

The GMA X3100 is the mobile version of the GMA X3000 used in the Intel GL960 and GM965 chipsets. The X3100 supports hardware transform and lighting, up to 128 programmable shader units, and up to 384 MB memory. Its display cores can run up to 333 MHz on GM965 and 320 MHz on GL960. Its render cores can run up to 500 MHz on GM965 and 400 MHz on GL960. The X3100 display unit includes a 300 MHz RAMDAC, two 25-112 MHz LVDS transmitters, 2 DVO encoders, and a TV encoder. In addition, along with the latest drivers, the product supports DirectX 10.0^[10], Shader Model 4.0 and OpenGL 2.0. The latest Windows XP drivers only support OpenGL 1.4.

GMA X3500

GMA X3500 is an upgrade of the GMA X3000 and used in the desktop G35. The shaders support shader model 4.0 features. Architecturally, the GMA X3500 is very similar to the GMA X3000,^[11] with both GMAs running at 667MHz. The major difference between them is that the GMA X3500 supports Shader Model 4.0 and DirectX 10, whereas the earlier X3000 supports Shader Model 3.0 and DirectX 9.^[11] The X3500 also adds hardware-assistance for playback of VC-1 video.

GMA X4500

The GMA X4500 and the GMA X4500HD for desktop^[12] were launched in June 2008.^[13] The GMA X4500 is used in the G43 chipset^[14] and the GMA X4500HD is used in the G45 chipset.^[12] The GMA X4500 will also be used in the G41 chipset,^[15] which was to be released in the fourth quarter of 2008.^[16]

The GMA 4500MHD for laptop, launched on July 16, 2008. Featurewise, the 4500MHD is identical to its desktop cousin, the X4500HD.^{[citation needed]}It had been previously rumored that a cost-reduced version, the GMA 4500, was to be launched in late 2008 or early 2009^[17] and was to be used in the upcoming Q43 and Q45 chipsets.^[15] But in practice the Q43 and Q45 Chipsets also use the GMA X4500^[18]

The difference between the GMA X4500 and the GMA X4500HD is that the GMA X4500HD is capable of "full 1080p high-definition video playback, including Blu-ray disc movies",^[12] the GMA X4500 however does not have that capability.^[13] The G43 and the G45 chipsets are manufactured with 65nm technology.^[19]

Like the X3500, X4500 supports DirectX 10 and Shader Model 4.0 features. Intel designed the GMA X4500 to be 200% faster than the GMA 3100 (G33 chipset) in 3DMark06 performance^[20] and 70% faster than the GMA X3500 (G35 chipset).^[21]

GMA 500

The Intel System Controller Hub US15W for the Atom processor Z5xx series features a GMA 500 graphic system. Rather than being developed in-house, this core is a PowerVR SGX core licensed from Imagination Technologies.^[22] Since PowerVR is not cooperative with the open source movement, this has resulted in the reliance of out dated closed source Linux drivers.

Intel describes this as "a flexible, programmable architecture that supports shader-based technology, 2D, 3D and advanced 3D graphics, high-definition video decode, and image processing. Features include screen tiling, internal true color processing, zero overhead anti-aliasing, programmable shader 3D accelerator, and 32-bit floating-point operations."^[23]

Sony's VAIO P series, Fujitsu's Lifebook U820, Dell's Inspiron Mini 10 and Inspiron Mini 12, and Acer's Aspire One 751^[24] are some of the rare examples of using the GMA 500 US15W.

graphic cards

Radeon

Contents

ATI Radeon Processor Generations

Radeon Card Brands

Product naming scheme

Drivers

Windows

Windows XP Professional x64

Macintosh

Linux

FreeBSD

MidnightBSD

AmigaOS

BeOS

MorphOS

FOSS drivers

GeForce 200 Series

Contents

Technical summary

Future

GeForce 9M Series

9100M G[32]

9200M GS[33]

9300M G[34]

9300M GS[35]

9400M G[36]

9500M G[37]

9500M GS[38]

9600M GS[39]

9600M GT[40]

9650M GS [41]

9650M GT [42]

9700M GT [4]

9700M GTS [5]

9800M GS [6]

9800M GTS [7]

9800M GT [8]

9800M GTX [9]

GeForce 9800 Series

GeForce 9800 GX2

GeForce 9800 GTX

GeForce 9800 GT

GeForce 9600 Series

GeForce 9600 GT

GeForce 9600 GSO

GeForce 9600 GSO 512

GeForce 9500 Series

GeForce 9500 GT

GeForce 9500 GS

GeForce 9400 Series

GeForce 9400 GT

GeForce 9 Series

Contents

New codename scheme

GeForce 8M Series

GeForce 8400M Series

GeForce 8600M Series

GeForce 8600M Series

GeForce 8700M Series

GeForce 8800M Series

GeForce 8800 Series

8800 GS

8800 GTX / 8800 Ultra

8800 GT

Compatibility issue with PCI-E 1.0a

8800 GTS

GeForce 8500 and 8600 Series

GeForce 8300 and 8400 Series

GeForce 8 Series

Contents

GeForce 8 Series overview

3D rendering

Max Resolution

Display capabilities

GeForce 7900 Series

GeForce 7900 GS

GeForce 7900 GT

GeForce 7900 GTX

GeForce 7900 GTO

9100M G^[32]

9200M GS^[33]

9300M G^[34]

9300M GS^[35]

9400M G^[36]

9500M G^[37]

9500M GS^[38]

9600M GS^[39]

9600M GT^[40]

9650M GS ^[41]

9650M GT ^[42]