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). GeForce 6 series features

SLI

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.

Nvidia PureVideo Technology

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 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. 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 PureVideo functionality varies by model, with some models lacking WMV9 and/or H.264 acceleration.Nvidia PureVideo – Product Comparison

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.

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 16Number of vertex pipelines 3* 3 3 6 6 6Peak 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/sPeak 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/sMemory interface 256-bit 64-bit 128-bit 256-bit 256-bit 256-bitMemory clock speed 950 MHz DDR 700 MHz DDR2 1.0 GHz / 950 MHz** GDDR3 1.1 GHz GDDR3 1.12 GHz GDDR3 1.18 GHz GDDR3Peak 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.

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. NV48 was a later version of NV40 manufactured in 110 nanometer process.

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.)

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) 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 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.

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) Maximum display resolution of 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 outputs on select members (implementation depends on the card manufacturer)

6800 chipset table Board Name Core Type Core(MHz) Memory(MHz) PipelineConfig VertexProcessors MemoryInterface 6800 Ultra NV40/NV45 400 550 16 6 256-bit 6800 GT NV40/NV45/NV48 350 500 16 6 256-bit 6800 Ultra EE NV40 450 600 16 6 256-bit 6800 GS PCIe 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/NV48 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) 450 600 12 5 256-bit 6800 LE / XT NV40/NV41/NV42/NV48 300/325 266/350 8 4 128/256-bit 6800 XE NV40 275 266 8 3 128-bit

Notes The limited-supply GeForce 6800 Ultra Extreme Edition was shipped with a 450 MHz core clock and (usually) a 1200 MHz memory clock, The eVGA contest page still says 1100 MHz, but the cards shipped by eVGA were in fact 1200 MHz. but was otherwise identical to a common 6800 Ultra. The GeForce 6800 GS is cheaper to manufacture and has a lower MSRP than the GeForce 6800 GT because it has fewer pipelines and is fabricated on 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 the inactive pixel and vertex pipelines may potentially be unlockable. However, the PCI Express version lacks them entirely, preventing 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 micrometer) 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 masked pixel pipelines and vertex buffers are nonexistent. The 6800 XT varies greatly depending on manufacturer. It is produced using three cores (NV40/NV41/NV42), four memory configurations (128 MiB DDR, 256 MiB DDR, 128 MiB GDDR3, 256 MiB GDDR3, and 512 MiB GDDR2), and has clock speeds ranging from 300 to 425 MHz (core) and 600-1000 MHz (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. The AGP version of the 6800 series does not have support for 2D acceleration in Adobe Reader/Acrobat 9.0 even though the GeForce AGP 6600, and PCI-e 6800 versions do.Adobe Knowledge Base - 2D Graphics Acceleration (GPU) support in Acrobat and Adobe Reader (9.0 on Windows)

GeForce 6600 series