Bookmark and Share


As expected months ago, Nvidia either had to change its policy regarding core-logic support for its multi-GPU SLI technology, or to cease further development of the latter. The graphics company apparently decided to allow SLI support on third-party chipsets in special cases, but makers of mainboards will have to pay Nvidia licensing fees for SLI.

At present only Nvidia nForce chipsets enable the company’s SLI multi-GPU technology, thus, users, who plan to utilize two or more Nvidia GeForce-based graphics cards to speed up their video games, have to acquire nForce-based mainboards, in spite of the fact that there are no technical limitations for SLI operation on third-party chipsets. Those, who use multi-GPU capable core-logic sets from AMD, Intel or other chipset vendors cannot use SLI technology, but may utilize competing ATI CrossFire array consisting of several ATI Radeon graphics cards by Advanced Micro Devices.

It is believed that Nvidia did not manage to get a license for Intel’s quick-path interconnect (QPI) bus, thus, it will not be able to create and sell chipsets compatible with Intel Core i7 (Nehalem, Bloomfield) processors. Nvidia’s positions on the market of high-end chipsets for AMD processors are also not very strong now that the Sunnyvale, California-based chipmaker develops its own core-logic sets.

Earlier this year Nvidia proposed to sell its nForce 200 PCI Express hubs to enable various SLI configurations, however, additional hubs cost money and dramatically increase complexity of mainboards, which is why many motherboard manufacturers started to complain about the idea.

At the Nvision event in San Jose, California, Nvidia outlined another plan: it will certify certain Intel X58-based mainboards for SLI compliance and will provide “approval keys that will be integrated into the system BIOS for boards that pass certification”. The company said that it will charge mainboard makers for SLI compliance, but right now the terms are unknown. One of the options would be to charge a fixed sum for every SLI-compatible mainboard, another option would be to charge a fixed sum for a model with no fees for every unit. In any case, such certification will be cheaper than placing nForce 200 that costs $30 on every motherboard.

Nvidia stressed that such certification is only valid for Intel X58-based mainboards. Moreover, the company will continue to promote its nForce 200 chip for more advanced systems. Nevertheless, Nvidia’s new position towards SLI support by third parties’ chipsets seems to be only the beginning of a major change.

Tags: Nvidia, Nforce, SLI, Intel, Core i7, Nehalem, Chipsets


Comments currently: 4
Discussion started: 08/28/08 02:30:11 PM
Latest comment: 12/19/15 05:12:31 PM


Goddamn you Nvidia!!! Your greed with be the death of you!!!
0 0 [Posted by: Pixelated  | Date: 08/28/08 02:30:11 PM]

Soon it will be open slather for those wanting SLI on ANY board with two PCIe x16 slots

There has been a hacked driver available for years that does this already
0 0 [Posted by: alpha0ne  | Date: 08/29/08 12:25:22 AM]

Nvidia will charge mainboard makers stupid enoughs to being Nvidia customers.

What next?
0 0 [Posted by: Janissary  | Date: 08/29/08 06:43:48 AM]


Add your Comment

Related news

Latest News

Wednesday, November 5, 2014

10:48 pm | LG’s Unique Ultra-Wide Curved 34” Display Finally Hits the Market. LG 34UC97 Available in the U.S. and the U.K.

Wednesday, October 8, 2014

12:52 pm | Lisa Su Appointed as New CEO of Advanced Micro Devices. Rory Read Steps Down, Lisa Su Becomes New CEO of AMD

Thursday, August 28, 2014

4:22 am | AMD Has No Plans to Reconsider Recommended Prices of Radeon R9 Graphics Cards. AMD Will Not Lower Recommended Prices of Radeon R9 Graphics Solutions

Wednesday, August 27, 2014

1:09 pm | Samsung Begins to Produce 2.13GHz 64GB DDR4 Memory Modules. Samsung Uses TSV DRAMs for 64GB DDR4 RDIMMs

Tuesday, August 26, 2014

10:41 am | AMD Quietly Reveals Third Iteration of GCN Architecture with Tonga GPU. AMD Unleashes Radeon R9 285 Graphics Cards, Tonga GPU, GCN 1.2 Architecture