Intel's Core i7 870 & i5 750, Lynnfield: Harder, Better, Faster Stronger
by Anand Lal Shimpi on September 8, 2009 12:00 AM EST- Posted in
- CPUs
Overclocking Lynnfield at Stock Voltage: We're PCIe Limited
Remember the on-die PCIe controller? Yep. It's to blame.
Lynnfield is Intel's first attempt at an on-die PCIe controller and it actually works surprisingly well. There are no performance or compatibility issues.
The on-die PCIe controller needs more voltage as you overclock Lynnfield, limiting Lynnfield's stock vt overclocking potential.
Unfortunately the PCIe controller on Lynnfield is tied to the BCLK. Increase the BCLK to overclock your CPU and you're also increasing the PCIe controller frequency. This doesn't play well with most PCIe cards, so the first rule of thumb is to try and stay at 133MHz multiples when increasing your BCLK.
The second issue is the bigger one. As you increase the BCLK you increase the frequency of the transistors that communicate to the GPU(s) on the PCIe bus. Those transistors have to send data very far (relatively speaking) and very quickly. When you overclock, you're asking even more of them.
We know that Bloomfield can easily hit higher frequencies without increasing the core voltage, so there's no reason to assume that Lynnfield's core cannot (in fact, we know it can). The issue is the PCIe controller; at higher frequencies those "outside facing" transistors need more juice to operate. Unfortunately on Lynnfield rev 1 there doesn't appear to be a way to selectively give the PCIe transistors more voltage, instead you have to up the voltage to the entire processor.
Intel knows the solution to Lynnfield's voltage requirement for overclocking, unfortunately it's not something that can be applied retroactively. Intel could decouple the PCIe controller from BCLK by introducing more PLLs into the chip or, alternatively, tweak the transistors used for the PCIe interface. Either way we can expect this to change in some later rev of the processor. Whether that means we'll see it in the 45nm generation or we'll have to wait until 32nm remains to be seen.
The good news is that Lynnfield can still overclock well. The bad news is that unlike Bloomfield (and Phenom II) you can't just leave the Vcore untouched to get serious increases in frequency.
Facebook
Twitter
RSS
343 Comments
View All Comments
lordmetroid - Tuesday, September 8, 2009 - link
I am using Linux!andrenb91 - Wednesday, September 9, 2009 - link
c'mon probably u still running windows for somethings...wine doesn't work owith every thin...i run liux on dual boot for years and still trying to make wine run fligh simulator x..which is the only game I play...remember, these benchmarkes are only for win bases pcs, in linux the history is diferent, see it at phoronix.com...james jwb - Tuesday, September 8, 2009 - link
is turbo boost on for the benchmarks?snakeoil - Tuesday, September 8, 2009 - link
yes they benchmarked with turbo boost, that is cheating because thats overclocking the processor at least 600 mhz and presenting the results as it were at stock speeds.that's abusing the reader's trust.
maxxcool - Tuesday, September 8, 2009 - link
Hahaha, you are just as much of a idiot here as on techreport snake! ... did you come here and claim to have proof that i5 will not run xp-mode to?hahahaha, your just sad that Amd did not come up with this feature 1st.
Jarp Habib - Tuesday, September 8, 2009 - link
"yes they benchmarked with turbo boost, that is cheating because thats overclocking the processor at least 600 mhz and presenting the results as it were at stock speeds.that's abusing the reader's trust. "
This statement is a load of bullcrap. Anand's intent is to present the benchmarks in a way reflective of the chip's standard performance in normal use- hence not manually overclocking for maximized performance. The processor's very design revolves on itself automatically shutting down inactive cores and boosting the speed of active cores, *regardless* of what the end user does to the chip in BIOS or what apps he's running. Since all you need to do to use Turbo Boost is just *install the CPU in your system* then benchmarks should be run with it enabled.
If you want to COMPLETELY level the playing field, then TurboBoost should be shut down, for both Bloomfield i7 chips and Lynnfield i5 AND Lynnfield i7, as well as future i3 and i9. Also, HyperThreading must be disabled from all chips, 3DNow!, SpeedStep, Cool N' Quiet, MMX and the entire SSE instruction sets. After all, each different type of CPU executes those standard instruction sets differently. And since the SpeedStep and Cool N Quiet instructions force the chip to underclock and shut off cores while at idle, they must be eliminated from testing as well, or they'll throw off your idle power consumption benchmarks.
Since you will be normalizing the clock frequencies as well, you can save time by only needing to test just one chip from each product line. I'm not sure just how you will normalize the clock frequencies of your test units *without overclocking or underclocking* some of them though. Perhaps you'll let me know?
Meanwhile, back in the real world...
Voo - Tuesday, September 8, 2009 - link
The difference is, that turbo mode impairs the possible benefit of overclocking the chip, while most things you enumerated do not.If you want to get the maximum out of the 860 you've got to disable turbo mode as we see in the review, so for everyone who'd want to overclock their CPU the most interesting test would be a comparison between the two chips both at their maximum stable performance. Which at the moment means disabling turbo mode as we can see.
erple2 - Tuesday, September 8, 2009 - link
A-HA! So really, you're just interested in the benchmark "What does the maximum overclock do", not "How does the CPU perform at normal operations". BTW, does disabling HT does improve overclocking a little bit, so should that also be disabled? Cool-n-Quiet plus SpeedStep may also affect overclocking capabilities. Should those be disabled? I fail to see the difference between what the GP said and your justifications.MadMan007 - Tuesday, September 8, 2009 - link
I'm not bothered by enabled Turboboost in a 'stock speed' review either but I would really like to see more sites run their benchmark suite with 3.6-4.0GHz (or higher) C2D, C2Q and Phenom II versus overclocked but non-Turboboost i5/i7. The reason is that this type of comparison would be most directly useful for the site's enthusiast readerships to know what the actual difference between *their rig* and an i5/i7 would be.Kaleid - Thursday, September 10, 2009 - link
Seconded.