X-bit labs

NVIDIA Multi-GPU SLI Technology: New Approach to Old Ideas

Category: Video

by Alexey Stepin , Yaroslav Lyssenko, Anton Shilov

[ 02/25/2005 | 02:15 PM ]

NVIDIA returned SLI abbreviation from the ancient days of the Voodoo 2 and Quake II to the modern age of the GeForce 6 and Doom III to once again prove its perfection and ability to deliver the fastest ever graphics solution. But how feasible is Multi-GPU technology nowadays and how high the performance can be with two top-of-the-range GeForce 6800 Ultra? We are trying to find this out here and now.

Table of contents:

• A Glance Back
  
• SGI: A Tool for Professionals
  
• 3dfx: Split It in Two!
  
• ATI Technologies: We Render Two Frames at Once!
  
• 3dfx’s Last Try
  
• XGI: An Unfortunate Hybrid
  
• NVIDIA SLI: How Does It Work?
  
• NVIDIA SLI: What Do You Need for the Multi-GPU Mode?
  
• Meet the SLI System: ASUS A8N-SLI Deluxe Mainboard
  
• Modest Luxury
  
• Closer Look
  
• There’s Nothing Perfect in This World
  
• ASUS A8N-SLI Deluxe: Pros and Cons
  
• ASUS Extreme N6600 GT Graphics Card
  
• GeForce 6800 Ultra PCI Express: Have You Ever Heard a Rocket Launch?
  
• NVIDIA SLI: Assembly and Launch
  
• Testbed Configurations and Methods
  
• NVIDIA SLI: Compatibility Issues
  
• Performance in First-Person 3D Shooters
  
• Call of Duty: United Offensive
  
• Doom III
  
• Halo: Combat Evolved
  
• Painkiller
  
• Half-Life 2
  
• Performance in Third-Person 3D Shooters
  
• Splinter Cell: Pandora Tomorrow
  
• Hitman: Contracts
  
• Thief: Deadly Shadows
  
• Deus Ex: Invisible War
  
• Performance in Simulators
  
• IL-2 Sturmovik: Aces in the Sky
  
• Microsoft Flight Simulator 2004
  
• FlatOut
  
• Performance in Strategy Games
  
• Command & Conquer Generals: Zero Hour
  
• Warhammer 40.000: Dawn of War
  
• Perimeter
  
• Rome: Total War
  
• Performance in Semi-Synthetic Benchmarks
  
• Final Fantasy XI Official Benchmark 3
  
• AquaMark3
  
• Performance in Synthetic Benchmarks
  
• Futuremark 3DMark 03
  
• Futuremark 3DMark 05
  
• Conclusion
  
• NVIDIA Multi-GPU SLI: Myths and Reality
  
• Price Factor
  
• Multi-GPU Prospects
  

Wise people say there is nothing new under the sun – brilliant ideas are all right here in the air waiting for someone to take and make them a reality. That’s true with computer hardware, too. In an attempt to validate its claim to the title of the manufacturer of fastest consumer graphics cards in the industry, NVIDIA Corporation went what was seemingly the most obvious way. The company suggested that the user united two graphics cards based on specific GeForce6 GPU models into an array that would ensure a much higher performance than that provided by single-chip solutions from ATI Technologies, NVIDIA’s archrival.

This “simple” idea gave the user an incentive to transition to PCI Express platforms that would support two graphics cards, but it was also associated with certain requirements like a special mainboard and a high-wattage power supply. As it turned out later, the support of particular games in NVIDIA’s driver was also necessary to get the desired speed boost and to avoid problems like hang-ups and visual artifacts.

Pursuing its promotion plan for multi-GPU solutions, NVIDIA surely expects a growth of its profits, an increase of its market share, and a universal recognition among the users, but the company will also have to optimize the driver for graphics card arrays and to do other word like collaborating with game developers. Anyway, despite all the difficulties, we can say that NVIDIA’s multi-GPU technology called Scalable Link Interface (SLI) has a real chance to conquer the market: the necessary graphics cards and mainboards are already available and can be purchased freely, although at a rather high price.

Today we will study the operation of multi-GPU arrays based on NVIDIA’s GeForce6 graphics cards and the difficulties or possible problems you may encounter with them. We will also offer you the results of our testing the arrays in a wide range of popular computer games.