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
Comments Locked

343 Comments

View All Comments

  • ash9 - Tuesday, September 8, 2009 - link

    As per Anand's article, "How Much Does it Cost to Build a P55 Motherboard?" Intel is getting around $50 min everytime a P55 board is sold with its new chips...nice, most folk wont link board prices to Intel..way to go Intel; so how much is Intel really making on its $196 i5??
  • JonnyDough - Tuesday, September 8, 2009 - link

    I love you.
  • Avalon - Tuesday, September 8, 2009 - link

    Hey Anand, how did you test stability on your max i5 750 overclock with turbo mode enabled? You said your max overclock on your i5 75 with turbo was 3.2Ghz. Do you just simply run Prime or some similar burn in that runs on all 4 cores (which would have turbo'd you to 3.96Ghz), or did you actually check a single threaded run on a single/two core(s) at 100% while getting it to run at turbo speed of 4.16Ghz(4Ghz for 2) at the same time? Thanks!
  • Gary Key - Tuesday, September 8, 2009 - link

    Stability testing is accomplished by running large renders in Lightwave 3D 9.6 x64 and Cinema4D R11 x64 at the same time while playing FarCry 2 in a window, along with Espresso, Mainconcept Reference, Lightroom, several IE windows, and Maya opened in the background. Also, it was not shown but all of the overclock results were with an 8GB memory load at DDR3-1800 or above. We try to test them like you use them. ;)
  • Anand Lal Shimpi - Tuesday, September 8, 2009 - link

    When turbo mode was enabled we made sure the system was stable with 1, 2 and 4 cores active. It had to pass all tests to be considered stable.

    Take care,
    Anand
  • chizow - Tuesday, September 8, 2009 - link

    Comments like this make me think you're losing touch Anand.

    [quote] I'm going to go ahead and say it right now, there's no need for any LGA-1366 processors slower than a Core i7 965[/quote]

    [quote]For $196 you're getting a processor that's faster than the Core i7 920. I'm not taking into account motherboard prices either, which are anywhere from $50 - $100 cheaper for LGA-1156 boards. I don't believe LGA-1366 is dead, but there's absolutely no reason to buy anything slower than a 965 if you're going that route.[/quote]

    There's about 800 reasons I can think of for other LGA1366 chips besides the Core i7 965, and there was a time you tipped your hat to amazing value gained from overclocking. I guess you're too enamored nowadays throwing that money away on those overpriced $1500 Intel Nehalems on boring Mac platforms that aren't conducive to user modifications to begin with.
  • jordanclock - Tuesday, September 8, 2009 - link

    I fail to see how Anand is "losing his touch." He has a very valid point: Buying anything less than the highest range i7's doesn't make sense right now. Lynnfield is very competitive to the sub-965 i7's, but with a much lower price (for both the CPU and motherboard). The 965/975 have many situations where they out-perform the i5's by a great deal, but unless you're buying a CPU for extreme performance, the i5 is a much better deal no matter how you slice it.
  • chizow - Tuesday, September 8, 2009 - link

    It seems you missed the point, entirely. Once you factor in overclocking, there is about 800 reasons to buy a cheaper LGA1366 CPU than the i7 965 because those cheaper processors tend to reach the same maximum clockspeeds as their overpriced siblings. Even a modest 500-600MHz overclock on a "pointless" $200 i7 920 surpasses the performance level you could buy with a $1000 stock XE part from Intel. Failing to acknowledge this reality tells me both you and he are losing touch....
  • Anand Lal Shimpi - Tuesday, September 8, 2009 - link

    Forgive me as apparently I wasn't clear enough in what I was trying to say there.

    I would absolutely recommend the Core i7 920 over a $1000 Core i7 Extreme. In fact, I did back when the Core i7 first launched.

    What I was trying to say in those sentences was Lynnfield changes all of that. Instead of buying a Core i7 920, I'd recommend a Core i5 750 (and saving money) or a Core i7 860 (and saving a bit less money). Those are both LGA-1156 processors.

    The only reason anyone would want LGA-1366 is if they want to build something faster than a Core i7 870, which only leaves the Core i7 965/975.

    My recommendation *isn't* to buy a $1000 CPU, it's to buy something much cheaper. Because of this, most of the LGA-1366 lineup is made obsolete by Lynnfield.

    Does that make more sense?

    Take care,
    Anand
  • chizow - Tuesday, September 8, 2009 - link

    I see your point and thought it might be what you were hinting at, but the message did come off awfully distorted with the way it was worded. If there was a 3.2-3.3GHz Lynnfield I suppose that would have made the 965 XE obsolete as well? The reality of it is, if there weren't other options besides $1000+ XE CPUs, X58 would be a dead platform akin to other failed Intel efforts of the past like Skulltrail.

    But that's not the case. X58 still has a place even though performance overlaps with Lynnfield on the low-end. In multi-GPU and gaming situations there's still clearly a place for X58/LGA1366 as Page 9 indicates. In situations where the end-user intends to overclock, any of the artificial gains from Lynnfield's Turbo modes are going to be negated.

    Personally, from a consumer standpoint, I feel Intel botched the whole X58/P55 design and launch starting with the decision to go with 2 sockets. Not only did the feature that provided the least benefit (triple vs. dual channel) drive the reason for the socket/pin count difference, they gimp the platform with superior tech by cutting PCIE lanes in half.

    I would've much rather have seen a 32-lane integrated PCIE controller on X58 and have a unified LGA1188 socket instead of 2 sockets, both of which have blemishes and signficant downsides as we have now.

Log in

Don't have an account? Sign up now