Intervju med nVidia om SLi

[HKS]

Penstarsys har et intervju med nVidia hvor de diskuterer SLi, og designvalg rundt SLi. Ganske interesant å lese.

 

http://www.penstarsys.com/editor/tech/grap...nter/index.html

 

Can you quickly take us over the advantages and disadvantages of SLI as compared to a supertiling solution?

 

NVIDIA has been working on SLI technology for many years.  In fact, NVIDIA has been designing scalability logic into their GPUs since GeForce 3.  However, an effective multi-GPU technology is non-trivial, requiring extensive research & development in both hardware and software. NVIDIA designed SLI technology with the flexibility to support multiple rendering algorithms, offering optimal performance for different types of applications.  Our two primary algorithms are dynamic split frame rendering (SFR) and alternate frame rendering (AFR), but there are others.

 

Supertiling is another algorithm that may be used to scale performance. The problem with supertiling is that it isn’t able to scale geometry like AFR can. Supertiling also has a problem with over-fetching textures (as did scanline interleaving) because of the number of textures that cross the tiling boundaries.  This means that each GPU would have to fetch the same texture for neighboring tiles.  In SFR, we have one edge where textures can cross boundries.  In supertiling, you have many, many more edges and the problem is multiplied linearly with the number of edges. These double-fetched textures can eat up valuable bandwidth. 

 

When developing SLI technology a number of different algorithm options were investigated. In fact NVIDIA looked at supporting supertiling as well, however it simply wasn’t the optimal choice for delivering the highest scaling performance.

 

What advantages does the over-the-top connector in SLI bring to the architecture?

 

The SLI connector enables inter-GPU communication of up to 1GB/s, improving performance by consuming no bandwidth over the PCI Express bus. The connector also provides perfect, digital compositing of pixel data that is asynchronous with the rendering rate, eliminating the need for a separate compositing chip or separate video mixing box/card.

 

Og til slutt for å avlive en myte... BIOS versjonen på kort som kjøres i SLi trenger ikke nødvendigvis være den samme...

SLI is being touted as a “buy one now, get a second one much later for cheap” upgrade plan. Let’s say that I buy a SLI motherboard with a 6800 GT today, and in six months I want to buy another one. What are the chances that I can buy an identical model? How do other factors such as BIOS revision affect compatibility and overall performance? With the graphics industry moving forward as fast as it is, and manufacturers updating and upgrading their SKUs, how will these factors affect the true upgradeability of this setup?

 

A common misconception about SLI is that the BIOS revision has to be identical between the cards. This is not true. A manufacturer can rev the BIOS without affecting SLI. However, the two cards do currently need to be identical models from the same manufacturer. With the majority of SKUs lasting on shelves for over a year, often much longer, SLI offers a strong path for upgradeability. We do however suggest that you check with the manufacturer about each particular SKU that you are considering.

Endret 20. april 2005 av [GDI]Raptor