| GeForce 6 series | |
| Codename: | NV4x |
| Model: | GeForce nForce series |
| Model1: | GeForce SE series |
| Model2: | GeForce LE series |
| Model3: | GeForce XT series |
| Model4: | GeForce GTO series |
| Model5: | GeForce GS series |
| Model6: | GeForce GT series |
| Model7: | GeForce Ultra series |
| Model8: | GeForce Ultra Extreme series |
| Entry: | 6100 6150 6200 6500 |
| Midrange: | 6600 6700 |
| Highend: | 6800 |
| Enthusiast: | 6800 Ultra / Ultra Extreme |
| D3dversion: | Direct3D 9.0c Shader Model 3.0 |
| Openglversion: | OpenGL 2.1 |
| Predecessor: | GeForce 5 series |
| Successor: | GeForce 7 series |
| Support Status: | Unsupported |
| Architecture: | Curie |
The GeForce 6 series (codename NV40) is the sixth generation of Nvidia's GeForce line of graphics 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).
See main article: Scalable Link Interface.
The Scalable Link Interface (SLI) allows two GeForce 6 cards of the same type to be connected in tandem. The driver software balances the workload between the cards. SLI-capability is limited to select members of the GeForce 6 family; 6500 and above. SLI is only available for cards utilizing the PCI-Express bus.
See 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.
Nvidia was the first to deliver Shader Model 3.0 (SM3) capability in its GPUs. 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.[1] 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.
PureVideo functionality varies by model, with some models lacking WMV9 and/or H.264 acceleration.[2]
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.
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 | 1.18 GHz GDDR3 | ||||||
| Peak memory bandwidth (GiB/s) | 30.4 | 5.6 | 16.0 / 14.4** | 35.2 | 35.84 | 37.76 |
(*) GeForce FX series has an Array-based Vertex Shader.
(**) AGP 6600 GT variant.
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.
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 6800 GT and 6800 Ultra, 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 package with two separate silicon dies clearly visible on the top.) NV48 is a version of NV45 which supports 512MiB RAM.
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 4× is fast enough that most contemporary games do not improve significantly in performance when switched to AGP 8×, rendering the further bandwidth increase provided by PCIe largely superfluous. Additionally, Nvidia's on-board implementations of AGP are clocked at AGP 12× or 16×, 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 solution (known as Rialto[3]) 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 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 computers are fast enough to play and decode WMV9 video and other sophisticated codecs like MPEG-4, H.264 or VP8 without hardware acceleration, thus negating the need for something like PureVideo.
| Board Name | Core Type | Core (MHz) | Memory (MHz) | Pipeline Config | Vertex Processors | Memory Interface | |
|---|---|---|---|---|---|---|---|
| 6800 Ultra | NV40/NV45/NV48 | 400 | 550 | 16 | 6 | 256-bit | |
| 6800 GT | NV40/NV45/NV48 | 350 | 500 | 16 | 6 | 256-bit | |
| 6800 XT | NV42 | 450 | 600 | 12 | 5 | 256-bit | |
| 6800 GTS | NV42 | 425 | 500 | 12 | 5 | 256-bit | |
| 6800 GS | NV40 | 350 | 500 | 12 | 5 | 256-bit | |
| 6800 GTO | NV40/NV45 | 350 | 450 | 12 | 5 | 256-bit | |
| 6800 | NV40/NV41/NV42 | 325 | 300/350 | 12 | 5 | 256-bit | |
| 6800 Go | NV41M | 300 | 300 | 12 | 5 | 256-bit | |
| 6800 Go Ultra | NV41M(0.13u)/NV42M(0.11u) | 450 | 5500 | 12 | 5 | 256-bit | |
| 6800 XE | NV40 | 275/300/325 | 266/350 | 8 | 3 | 128-bit | |
| 6800 LE | NV40 | 300 | 350 | 8 | 4 | 256-bit |
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. 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 slower than the PCI-e cards, on which the memory operates at 1000 MHz. This can contribute to a performance decline when playing certain games. However, it was often possible to "overclock" the memory to its nominal frequency of 1000 MHz and there are AGP cards (for example from XFX) that use 1000 MHz by default.
| 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 | |
| 6600 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 |
Other data for AGP based cards:
The GeForce 6500 was released in October 2005 and is based on the same NV44 core as the value/budget (low-end or entry level) GeForce 6200TC, but with a higher GPU clock speed and more memory. The GeForce 6500 also supports SLI.
With just 4 pixel pipelines, the 6200 series forms Nvidia's value/budget (low-end or entry level) product. The 6200 omits memory compression and SLI support, but otherwise offers similar rendering features as the 6600s. The later 6200 boards were based on the NV44 core(s), which is the final production silicon for the 6200 series. The 6200 is the only card in the series to feature keying for 3.3V AGP slots (barring some rare exceptions of higher-end cards from vendors like PNY).
However, at introduction, production silicon was not yet ready. Nvidia fulfilled 6200 orders by shipping binned/rejected 6600 series cores (NV43V). The rejects were factory-modified to disable four pixel pipelines, thereby converting the native 6600 product into a 6200 product. Some users were able to "unlock" early 6200 boards through a software utility (effectively converting the 6200 back into a 6600 with the complete set of eight pixel pipelines total) if they owned boards with an NV43 A2 or earlier revision of the core. Thus, not all NV43-based 6200 boards could successfully be unlocked (specifically those with a core revision of A4 or higher), and as soon as NV44 production silicon became available, Nvidia discontinued shipments of downgraded NV43V cores.
The GeForce 6200 TurboCache / AGP (NV44/NV44a) is a natively four-pipeline version of the NV43. GeForce 6200 TurboCache cards only have a very small (by modern standards) amount of memory, but attempt to make up for this by using system memory accessed through the PCI-Express bus.
BFG Technologies originally introduced a unique PCI variant of the GeForce 6200 via its namesake B.F.G. and 3D Fuzion product lines. Subsequently, PNY (GeForce 6200 256 MiB PCI), SPARKLE Computer (GeForce 6200 128 MiB PCI and GeForce 6200 256 MiB PCI), and eVGA (e-GeForce 6200 256 MiB PCI and e-GeForce 6200 512 MiB PCI) released their own PCI versions of the Geforce 6200 featuring higher memory clocks and resultant memory bandwidth.
Until the release of the ATI X1300 PCI, these were the only PCI DirectX 9 capable cards not based on previous generation GeForce FX technology or discontinued XGI Technology Volari V3XT chipsets.
Excluding SPARKLE's GeForce 8400 and 8500 series, Zotac GT 610 cards and Club 3D HD 5450 cards in late 2012, the enhanced 512 MiB Geforce 6200 PCI variants[8] remain among the most powerful PCI based systems available, making these cards desired by users lacking the option of upgrading to an AGP or PCI Express based discrete video card.
In late 2005 Nvidia introduced a new member to the GeForce family, the 6100 series, also known as C51. The term GeForce 6100/6150 actually refers to an nForce4-based motherboard with an integrated NV44 core, as opposed to a standalone graphics card. Nvidia released this product both to follow up its immensely popular GeForce4 MX based nForce and nForce2 boards and to compete with ATI's RS480/482 and Intel's GMA 900/950 in the integrated graphics space. The 6100 series is very competitive, usually tying with or just edging out the ATI products in most benchmarks.
The motherboards use two different types of southbridges - the nForce 410 and the nForce 430. They are fairly similar in features to the nForce4 Ultra motherboards that were on the market before them. Both feature PCI Express and PCI support, eight USB 2.0 ports, integrated sound, two Parallel ATA ports, and Serial ATA 3.0 Gibit/s with Native Command Queuing (NCQ) – two SATA ports in the case of the 410, four in the 430. The 430 southbridge also supports Gigabit Ethernet with Nvidia's ActiveArmor hardware firewall, while the 410 supports standard 10/100 Ethernet only.
Both the 6100 and 6150 support Shader Model 3.0 and DirectX 9.0c. The 6150 also features support for High-Definition video decoding of H.264/VC1/MPEG2, PureVideo Processing, DVI, and video-out. The 6100 only supports SD decoding of MPEG2/WMV9.[9] Maximum supported resolution is 1920 × 1440 pixels (@75 Hz) for RGB display and 1600 × 1200 pixels (@65 Hz) for DVI-D display
In 2008, Nvidia took a $150 to 250M charge against revenue because the GPUs were failing at "higher than normal rates."[10] HP provided an extension to their warranty of up to 24 months for notebooks affected by this issue. A class action suit was filed against HP and Nvidia by Whatley Drake & Kallas LLC.
The GeForce 6150LE was primarily featured in the 2006 lineup of the Nvidia Business Platform.[12] The chip is used by Fujitsu-Siemens in its Esprimo green desktop, HP in its Pavilion Media Center a1547c Desktop PC and Compaq Presario SR1915 Desktop, and Dell in its Dimension C521 and E521 desktop PCs.
GeForce 6150SE (MCP61, also known as C61) is an updated, single-chip version of the Nvidia GeForce 6100. The MCP61 uses less power than the original C51 2-chip version of 6100. Its onboard video outperforms the 6150 in many 3D benchmarks despite its lower core frequency (425 MHz), because of added hardware Z-culling.
MCP61 introduced a bug in the SATA NCQ implementation. As a result, Nvidia employees have contributed code to disable NCQ operations under Linux.[13]
Upon launch of the GeForce 7 family of graphics processing units, IntelliSample 4.0 was considered to be an exclusive feature of the GeForce 7 series of GPUs. However, version 91.47 (and subsequent versions) of the Nvidia ForceWare drivers enable the features of IntelliSample 4.0 on the GeForce 6 GPUs. IntelliSample 4.0 introduces two new antialiasing modes, known as Transparency Supersampling Antialiasing and Transparency Multisampling Antialiasing. These new antialiasing modes enhance the image quality of thin-lined objects such as fences, trees, vegetation and grass in various games.
One possible reason for the enabling of IntelliSample 4.0 for GeForce 6 GPUs might be the fact that the GeForce 7100 GS GPUs are based on NV44 chips, the same as the GeForce 6200 models. Because of this, Nvidia had to backport IntelliSample 4.0 features to the NV4x GPUs, and as a result, the entire GeForce 6 family is able to enjoy the benefits of Transparency Antialiasing.
It was already well known across various communities that Transparency Antialiasing could be used on GeForce 6 GPUs by using some third party tweak tools. As of Nvidia ForceWare drivers 175.16, GeForce 6 IntelliSample 4.0 support has been removed.
Nvidia has ceased driver support for GeForce 6 series. The GeForce 6 series is the last to support the Windows 9x family of operating systems, as well as Windows NT 4.0. The successor GeForce 7 series only supports Windows 2000 and later (the Windows 8 drivers also support Windows 10).