NVIDIA
GeForce 7800 GTX 512MB
G70
$649 MSRP

Introduction

A little less than five months ago NVIDIA launched their latest high end graphics chip, G70. Given the competitive environment at the time, thanks to ATI's R520 misstep, NVIDIA had the luxury of being able to build up stock prior to release and to set, what would now appear to be, reasonably conservative clockspeeds on their flagship GeForce 7800 GTX product, based on the G70 chip.

In time for the holiday season, and just as the competitive environment is changing with ATI finally releasing parts of their new X1000 series, NVIDIA is giving their line a little refresh. With the mainstay of their 90nm based line-up yet to come, this pre-Christmas refresh is based on currently available parts moving into new price brackets, but while the lower end gets cheaper the high end gets more expensive - but also gains some fairly significant increases.

Here we're taking a look at NVIDIA's new GeForce 7800 GTX 512MB board to see how it has moved on from the previous GTX 256MB configuration.


The Graphics Chip

The new GeForce 7800 GTX 512MB board is based on the same G70 chip as the rest of the 7800 series, however NVIDIA are stating that due to some process changes they can now yield the part at higher clockspeeds for this new product. The details of the chip are as follows:

 

Chip Name G70
Silicon Process 110nm (TSMC)
Transistors 300M
Die Size 334mm²
[18.65mm (w) x 17.9mm (h)]
Packaging Flipchip
Pipeline Configuration 24 / 16 / 32
(Textures / Pixels / Z Samples per clock)
Memory Interface 256-bit (64x4 Crossbar)
DDR, GDDR-2, GDDR-3
DirectX Capability DX9.0 - VS3.0, PS3.0
Display Dual 400MHz RAMDAC's
Host Interface PCIe X16

Its interesting to note that the chip is marked as "7800-U-A2" giving an indication to this being a chip speed binned as an "Ultra" part, although NVIDIA ultimately shied away from the name due to the availability stigma attached to it.

As the specifications shows, the configuration of this chip is the same as previous parts on the G70 line, and as such the features it enables are the same as well. A quick recap of these capabilities follows:

  • CineFX 4.0 Architecture
    • Full DirectX9 Support
    • DirectX9 Shader Model 3.0 Support
    • Vertex Shader 3.0
      • Vertex Shader 3.0
      • Pixel Shader 3.0
      • Internal 128-bit Floating Point (FP32) Precisions
    • Unlimited Shader Lengths
    • Up to 16 textures per pass
    • Support for FP16 Texture Formats with Filtering, FP32 without
    • Non-Power of two texture support
    • Multiple Render Targets
  • NVIDIA High Precision Dynamic Range Technology
    • Full FP16 Floating Point Support throughout the entire pipeline
    • FP16 Floating Point Frame Buffer Support
  • Intellisample 4.0
    • Up to 4X, Gamma Adjusted, Native Multi-sampling FSAA with rotated grid sampling
    • Transparent MultiSampling and SuperSampling
    • Lossless color, texture, z-data compression
    • Fast Z Clear
    • Up to 16x Anisotropic Filtering
  • UltraShadow Technology
  • NVIDIA SLI Support
  • NVIDIA Pure Video Technology
    • Adaptable Programmable video processor
    • High Definition MPEG2 and WMV9 acceleration
    • Spatial Temporal de-interlacing
    • Inverse 2:2 and 3:2 pull-down (Inverse Telecine)
    • 4-tap horizontal, 5-tap vertical scaling
    • Overlay color temperature correction
    • Microsoft® Video Mixing Renderer (VMR) supports multiple video windows with full video quality and features in each window
    • Integrated HDTV output
  • Advanced Display options
    • Dedicated on-chip video processor
    • nView Multi Display technology
    • Digital Vibrance Control 3.0

For a more complete overview of the architecture behind the G70 graphics chip, read our article here.