Multi-GPU SLI/CF Scaling: Lynnfield's Blemish

When running in single-GPU mode, the on-die PCIe controller maintains a full x16 connection to your graphics card:


Hooray.

In multi-GPU mode, the 16 lanes have to be split in two:

To support this the motherboard maker needs to put down ~$3 worth of PCIe switches:

Now SLI and Crossfire can work, although the motherboard maker also needs to pay NVIDIA a few dollars to legally make SLI work.

The question is do you give up any performance when going with Lynnfield's 2 x8 implementation vs. Bloomfield/X58's 2 x16 PCIe configuration? In short, at the high end, yes.

I looked at scaling in two games that scaled the best with multiple GPUs: Crysis Warhead and FarCry 2. I ran all settings at their max, resolution at 2560 x 1600 but with no AA.

I included two multi-GPU configurations. A pair of GeForce GTX 275s from EVGA for NVIDIA:


A coupla GPUs and a few cores can go a long way

And to really stress things, I looked at two Radeon HD 4870 X2s from Sapphire. Note that each card has two GPUs so this is actually a 4-GPU configuration, enough to really stress a PCIe x8 interface.

First, the dual-GPU results from NVIDIA.

NVIDIA GeForce GTX 275 Crysis Warhead (ambush) Crysis Warhead (avalanche) Crysis Warhead (frost) FarCry 2 Playback Demo Action
Intel Core i7 975 (X58) - 1GPU 20.8 fps 23.0 fps 21.4 fps 41.0 fps
Intel Core i7 870 (P55) 1GPU 20.8 fps 22.9 fps 21.5 fps 40.5 fps
Intel Core i7 975 (X58) - 2GPUs 38.4 fps 42.3 fps 38.0 fps 73.2 fps
Intel Core i7 870 (P55) 2GPUs 38.0 fps 41.9 fps 37.4 fps 65.9 fps

 

The important data is in the next table. What you're looking at here is the % speedup from one to two GPUs on X58 vs. P55. In theory, X58 should have higher percentages because each GPU gets 16 PCIe lanes while Lynnfield only provides 8 per GPU.

GTX 275 -> GTX 275 SLI Scaling Crysis Warhead (ambush) Crysis Warhead (avalanche) Crysis Warhead (frost) FarCry 2 Playback Demo Action
Intel Core i7 975 (X58) 84.6% 83.9% 77.6% 78.5%
Intel Core i7 870 (P55) 82.7% 83.0% 74.0% 62.7%

 

For the most part, the X58 platform was only a couple of percent better in scaling. That changes with the Far Cry 2 results where X58 manages to get 78% scaling while P55 only delivers 62%. It's clearly not the most common case, but it can happen. If you're going to be building a high-end dual-GPU setup, X58 is probably worth it.

Next, the quad-GPU results from AMD:

AMD Radeon HD 4870 X2 Crysis Warhead (ambush) Crysis Warhead (avalanche) Crysis Warhead (frost) FarCry 2 Playback Demo Action
Intel Core i7 975 (X58) - 2GPUs 25.8 fps 31.3 fps 27.0 fps 70.9 fps
Intel Core i7 870 (P55) 2GPUs 24.4 fps 31.1 fps 26.6 fps 71.4 fps
Intel Core i7 975 (X58) - 4GPUs 27.0 fps 57.4 fps 47.9 fps 117.9 fps
Intel Core i7 870 (P55) 4GPUs 24.2 fps 50.0 fps 36.5 fps 116 fps

 

Again, what we really care about is the scaling. Note how single GPU performance is identical between Bloomfield/Lynnfield, but multi-GPU performance is noticeably lower on Lynnfield. This isn't going to be good:

4870 X2 -> 4870 X2 CF Scaling Crysis Warhead (ambush) Crysis Warhead (avalanche) Crysis Warhead (frost) FarCry 2 Playback Demo Action
Intel Core i7 975 (X58) 4.7% 83.4% 77.4% 66.3%
Intel Core i7 870 (P55) -1.0% 60.8% 37.2% 62.5%

 

Ouch. Maybe Lynnfield is human after all. Almost across the board the quad-GPU results significantly favor X58. It makes sense given how data hungry these GPUs are. Again, the conclusion here is that for a high end multi-GPU setup you'll want to go with X58/Bloomfield.

A Quick Look at GPU Limited Gaming

With all of our CPU reviews we try to strike a balance between CPU and GPU limited game tests in order to show which CPU is truly faster at running game code. In fact all of our CPU tests are designed to figure out which CPUs are best at a number of tasks.

However, the vast majority of games today will be limited by whatever graphics card you have in your system. The performance differences we talked about a earlier will all but disappear in these scenarios. Allow me to present data from Crysis Warhead running at 2560 x 1600 with maximum quality settings:

NVIDIA GeForce GTX 275 Crysis Warhead (ambush) Crysis Warhead (avalanche) Crysis Warhead (frost)
Intel Core i7 975 20.8 fps 23.0 fps 21.4 fps
Intel Core i7 870 20.8 fps 22.9 fps 21.5 fps
AMD Phenom II X4 965 BE 20.9 fps 23.0 fps 21.5 fps

 

They're all the same. This shouldn't come as a surprise to anyone, it's always been the case. Any CPU near the high end, when faced with the same GPU bottleneck, will perform the same in game.

Now that doesn't mean you should ignore performance data and buy a slower CPU. You always want to purchase the best performing CPU you can at any given pricepoint. It'll ensure that regardless of the CPU/GPU balance in applications and games that you're always left with the best performance possible.

The Test

Motherboard: Intel DP55KG (Intel P55)
Intel DX58SO (Intel X58)
Intel DX48BT2 (Intel X48)
Gigabyte GA-MA790FXT-UD5P (790FX)
Chipset: Intel X48
Intel X58
Intel P55
AMD 790FX
Chipset Drivers: Intel 9.1.1.1015 (Intel)
AMD Catalyst 9.8
Hard Disk: Intel X25-M SSD (80GB)
Memory: Qimonda DDR3-1066 4 x 1GB (7-7-7-20)
Corsair DDR3-1333 4 x 1GB (7-7-7-20)
Patriot Viper DDR3-1333 2 x 2GB (7-7-7-20)
Video Card: eVGA GeForce GTX 280
Video Drivers: NVIDIA ForceWare 190.62 (Win764)
NVIDIA ForceWare 180.43 (Vista64)
NVIDIA ForceWare 178.24 (Vista32)
Desktop Resolution: 1920 x 1200
OS: Windows Vista Ultimate 32-bit (for SYSMark)
Windows Vista Ultimate 64-bit
Windows 7 64-bit

Turbo mode is enabled for the P55 and X58 platforms.

The Best Gaming CPU? SYSMark 2007 Performance
POST A COMMENT

341 Comments

View All Comments

  • Ann3x - Wednesday, September 09, 2009 - link

    1/ There is no chance that any of these chip can run safely with no fan.
    2/ You dont get huge temperature increases if you dont overvolt, just clock changes result in very small temperature changes. look at the article you linked. The 3 new chips use EXACTLY the same power despite their differing clock speeds.
    3/ New energy saving technology works with overclock just like it does with stock clock ed CPUs (eg energy states, my i7 is overclocked to 4ghz on stock volts, when its not needed it clock down - same end effect as these new chips (albeit slightly less elegant)).

    This whole fuss about turbo mode is just marketing gumph and yet people are totally sucked in by the hype.
    Reply
  • coconutboy - Wednesday, September 09, 2009 - link

    1- I never said anything about running the CPU w/o a fan. Fanless watercooling is an option, as is quiet low rpm fans.

    2- Clocking w/o increasing voltage does increase heat and whether or not you consider that to be a significant amount depends on the cooling solution you use. I made no claim that OC'd temps would increase as much as overvolting.

    Your opinion about the validity of turbo mode is just that, you opinion. You and I can agree to disagree.
    Reply
  • titanium001 - Wednesday, September 09, 2009 - link

    I was excited to see the article, but was left wondering and scratching my head when gaming performance was evaluated. I didn't see any 1920 x 1200 or 2560 x 1600 comparisons anywhere. Do the i7 800 series take a significant performance hit in these settings. I guess everything can't be delivered until a full in depth review. Have to just wait. I'll reserve my judgment about the 800 series until then, for now, it's just another proc. Thanks for the initial preview Anandtech.com. Reply
  • Anand Lal Shimpi - Wednesday, September 09, 2009 - link

    Have a look at the SLI/CF Multi-GPU Gaming page, I include some GPU limited tests at the bottom of that page.

    At higher resolutions P55, X58 and even Phenom II/790FX all perform the same if you're GPU limited. The PCIe limitations of P55/Lynnfield only come into play when you're running in multi-GPU mode because the x16 interface gets broken up into a pair of x8s.

    Take care,
    Anand
    Reply
  • NoobyDoo - Tuesday, September 08, 2009 - link

    ... remember when C2D was released ? Reply
  • coconutboy - Tuesday, September 08, 2009 - link

    After thoroughly reading a lot of the articles at Toms, Anand, xbit etc, Lynnfield looks great and has been worth the wait. However, it's not an absolute sell as a gamer box IMO. My g/f and I have been waiting to build a pair of new gaming computers, but wanted to see what i5 had to offer first. Now that NDAs are down, the $30-70 savings for p55 versus comparable x58 mobos is great, but some things about i5 still make me want an i7 920 instead.

    My g/f and I plan on buying a pair of GTX 275s, one for each computer. Then later on as our systems age, we'll put both 275s in one box and buy a newer vid card for the other system. We also moderately overclock our CPUs (3.2-3.4 would be what I expect for a i7 920) to boost performance w/o shortening the lifespan too much because our gamer boxes usually end up moving down the line in our home network to become servers or some such.

    Taking into account everything I've been reading at hardware sites thus far, we'll likely build one Lynnfield and one i7 for our gaming rigs. I expect one of the current gamer computers we build will migrate to become a VMware machine later on which means an i7 920 w/ (eventually) 24GBs of RAM is very attractive. The ability to use a 6 core CPU later on counts for a lot as well.
    Reply
  • coconutboy - Wednesday, September 09, 2009 - link

    edit- I meant to be comparing an mildly overclocked i7 920 @ stock voltage and 3.3-3.4GHz versus an i7 860/870, not an i5. I'd often prefer the 920 (but not always of course) for my uses. Reply
  • thebeastie - Tuesday, September 08, 2009 - link

    Such a good complete review, EXCEPT there is no information of how much power the CPU used with it was hard overclocked to its 4.2Ghz mark.
    With its intergrated PCIe 100million transistor count controller inside the CPU this would of been really interesting info.
    Reply
  • Gary Key - Wednesday, September 09, 2009 - link

    The system power utilized (measured at the wall) was 301W for the 4.2GHz overclock on the 870 under an eight thread 100% load test on the board. Reply
  • justme2009 - Tuesday, September 08, 2009 - link

    Why are you overhyping this garbage? I'm waiting for Clarkdale. I'm still ticked off that Intel caved to the manufacturers and held off on releasing it, we were supposed to have it in the 4th quarter of this year, now it will be first half of 2010.
    This new nehalem (even if it's for desktops) will be nothing compared to the mobile nehalem next year.
    My only other question is, why the hell has Clarkdale/Arrendale information been buried? There hasn't been a peep from anyone about it since February.
    Reply

Log in

Don't have an account? Sign up now