PCIe Scaling Summary
Today’s benchmarks include a wide variety of data on different games and resolutions, making it hard to keep track of the score. We're bundling those titles to give you a better idea of the general performance profile for the most common enthusiast-level monitor resolutions.
Enthusiasts on lower budgets will find a general performance loss of 2% to 4% when switching from an x16 to an x8 slot. That's not altogether bad. Some of that difference will accumulate in SLI and CrossFire configurations, and we will address that topic in a later article.
PCIe x4 slots hurt performance by an even greater amount, and the loss is most significant when using an AMD graphics card. The real shame is that, even though the performance drop is less dramatic for GeForce graphics, the x4 slots of P55 and P67 motherboards don’t support SLI due to an artificial cap imposed by Nvidia, presumably to sell more NF200s.
Performance losses shrink marginally at 1920x1080, but one can still expect a 10% to 18% drop when using a x4 slot.
At 2560x1600, the performance loss of an x8 slot drops to 1-3% as the bottleneck shifts to the GPU, rather than the pipeline to which it's connected. The x4 slot is still a poor compromise, losing 7% to 14% compared to what most of us would probably consider the proper configuration.
Current page: PCIe Scaling SummaryPrev Page Benchmark Results: S.T.A.L.K.E.R.: Call Of Pripyat Next Page Bonus Page: Does CrossFire Work At x16/x4?
Stay on the Cutting Edge
Join the experts who read Tom's Hardware for the inside track on enthusiast PC tech news — and have for over 25 years. We'll send breaking news and in-depth reviews of CPUs, GPUs, AI, maker hardware and more straight to your inbox.
These tests were done with a single card, on X16/X8/X4 slots. Fine.Reply
But... Who would use anything other than a X16 slot if they had one?
The only real use for a X8 slot would be for sli/crossfire where the addition of a second card should result in an Increase of performance, not a decrease.
it would be nice if you included the GTX 570 in the x8/x8 and x16/x4 test. the 570 flies over the 6950 on the single card config but i was curious how it would do since i think the AMD's scale better than nvidia's. would the 570 still lead because of its advantage? or would AMD even it out because of its scaling (if any) "advantage"Reply
^They already did an article on that manReply
Can you guy's do an article on how performance is affected if you SLI/Xfire using PCI-E 16x slots running @ 4x?Reply
3 way would be preferable because if performance is still adequately faster I'll consider it.
Good comments. Can we please see 8x/8x and 16x/4x since that comparison is relevant? I get the impression that somehow SLI/crossfire reduces the performance hit of x4 lanes but I'd like to see numbers.Reply
joytech22Can you guy's do an article on how performance is affected if you SLI/Xfire using PCI-E 16x slots running @ 4x?I think you missed a page then!Reply
The numbers were there all along!
carlhenryit would be nice if you included the GTX 570 in the x8/x8 and x16/x4 test.Well, you should probably read the linked page too then. There's no point in artifically creating a configuration (by taping lanes or whatever) that doesn't exist in real life, is there?
"While Nvidia prevents SLI from functioning on PCH-hosted lanes, x16/x4 configurations are completely possible in CrossFire. But should they be? We tested our motherboard in both x8/x8 and x16/x4 configurations to find out."
dalauderYeah...my bad.I didn't mean to call you out to that extent, here's a link to the forum part of this thread:Reply
I'm going there to delete your quote from my response.
Looking forward to see the third article!Reply
Im guessing that 8x lanes are mostly enought. I do belive that it would depend on how fast an actual gpu is, as well as how much ram it has, and how big is its bandwidth.Reply
I means, its logical, but mayb not true :D. Would be nice to see this test on a GTX560 Ti, since it has a lot of headroom for OC, then compare oced version vs non oced. Also this might be interesting in GPUs that have diffrent versions with more and less RAM.
Just my 2 cents :D.