NVIDIA's SLI Gets Busier - Notebook and Quad SLI Versions
Quad SLI Comes to Life
Today is busy day for the folks at NVIDIA. Not only are they announcing immediate availability of their new G71 part, the 7900 GTX and 7900 GT, availability of the G73, the 7600 GT but they are also making two other announcement on SLI this morning.
Quad SLI has been the talk of the GPU industry since we first previewed it during CES, with the first pictures as well as the first video of the demonstration Dell machine on display. While the idea of having 96 pixel processors was simply astounding at the time, more had more doubts have crept up on issues like efficiency and power management that might put a hinder any kind of acceptance of the quad SLI format, beyond the beyond-wealth-systems that are going to be offering them today.
The first quad SLI demonstration we were shown was on four 7800 GPU cores though the now officially announced quad SLI technology will only run on 7900 GTX parts. Coupling two of these extreme dual GPU cards together on an nForce4 SLI X16 motherboard and you have the beginnings of a beautiful gaming relationship.
The Technology Behind Quad SLI
Until today though, much of how quad SLI works has been clouded in an NVIDIA-induced mystery. Now we can share some more information about the technology and the design decisions behind it.
Above you can see a high-level block diagram of how quad SLI logic works. Each large green area represents a single, dual GPU card. In the center of each card you'll notice there is an object labeled 'X48 PCI-E' that is an NVIDIA developer x48 lane PCIe connection chip. It accepts a single x16 PCIe connection input and creates two additional x16 links that lead to each of the two G71 GPUs on the card. This chip is responsible for splitting the data between the two GPUs and making sure that the data the each passes back to it makes it to the PCIe bus on the motherboard without issue.
Each card features two G71 cores and two separate 512 MB frame buffers, for a total of 2 GB of frame buffer memory in a quad SLI computer. Excessive much? Perhaps, but the technology is simply impressive to think about. Do you remember when NVIDIA first introduced SLI into the market and discussed that they had implemented the SLI connection logic into the GPU from the beginning? Well it turns out that NVIDIA did not simply include a single SLI connection; they actually developed two of them. Both of these logical connections are utilized in a quad SLI system.
For our discussions, referencing the block diagram above, I'll call the left hand side G71 core the primary GPUs on each card and the right hand side G71 core the secondary. Each primary GPU is connected to the secondary GPU on the same board through one of the two SLI connections, made with an external connection between the two PCBs on the same card.
Each primary GPU is connected to the other primary GPU as well through the second SLI connection, this time using the standard SLI bridge connection we are used to see in SLI configurations. The same connection is made between the two secondary GPUs, creating an SLI bridge configuration that resembles the below on display at IDF.
All of these connections allow each of the cores to communicate with any other core through at most two jumps.
Page 2 - Quad SLI Rendering Modes