NVIDIA GF100 graphics architecture details

Thursday 21st January 2010, 08:26:00 AM, written by Rys

Late last year I wrote a speculative piece on NVIDIA Fermi and GF100 for The Tech Report, outlining a best guess at the graphics capabilities based on research, NVIDIA's historical progression in graphics and good old journalism, probing the company's engineers where possible.  Along with a roll of the dice for the clocks, it set a reasonably good estimate on where things would land on launch.

I say reasonably good estimate since NVIDIA recently released a whitepaper containing lots of good details, and they also wheeled out their big graphics guns in the form of Henry Moreton, Emmett Kilgariff (whoa!) and Jonah Alben (a twelve year veteran at NV, now their Senior VP of GPU Engineering after joining from SGI way back when) to brief selected members of the press after CES.

The Tech Report were there, and they've published their findings, correcting where I got things wrong to get a better, fuller picture of where the graphics architecture stands.  The analysis is typically great, Scott painting a very nice picture of what it's capable of when drawing pixels.

Check out their analysis in full, and we'll be along with our own look as well as soon as we can.

Discuss on the forums

nvidia ± fermi, dx11, gf100

CUDA 4.0 and Parallel Nsight 2.0 released
NVIDIA Fermi GPU and Architecture Analysis
NVIDIA's Parallel Nsight finally released
NVIDIA GeForce GTX 460 - GF104 breaks cover
PhysX87, ancient tragedy in 5 acts by RWT
So long, Chris, and thanks for all the fish
NVIDIA Fermi: new GPU architecture, starting with GF100
NVIDIA release OpenCL GPU drivers for Linux and Windows
NVIDIA GeForce GTX 275 at $250 to fight HD 4890
A look at NVIDIA's SLI Multi-OS and new Quadros