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
Ben90 - Tuesday, September 8, 2009 - link
Was reading it pretty casually thinking it was just a preview because i didnt think the NDA lifted yet.... then i saw a next page... looked at the tab and it has like 20 pages OMGOMGOMGOMG!!! ITS OUT LOL....Im gonna try really really hard to read the article before i go to the gaming performance though...prolly wont make itLashek - Wednesday, September 9, 2009 - link
you compare it to the Q6600 a lot in the text, but no comparison with an overclocked Q6600 is made in the benches...If you have figures of an overclocked Q6600, could you add them? all over the web these question are asked but business leaders who own these web sites dont want to challenge a overclocked core 2 duo,and quads,or is it politics?
coldpower27 - Thursday, September 10, 2009 - link
You will have to compare an overclocked I750 or i860 to the Q6600 as that would only be fair, no sense doing a stock vs overclocked comparison.It is well known you can equal todays stock performance by overclocking to some degree, but if your going to compare overclock then you need to overclock both processors.
Q6600 will be destroyed by i750 and i860 if you compare perf/watt however.
Joshaze - Wednesday, September 9, 2009 - link
Anand,When testing World of Warcraft what processAffinityMask value where you using?
The default value for this variable does not take advantage of all cores on the Core i7 processors.
Here is the article discussing the CVAR: http://forums.worldofwarcraft.com/thread.html?topi...">http://forums.worldofwarcraft.com/thread.html?topi...
The value should be 255 for 8 cores and 15 for 4 cores.
If not, any chance you could retest using the above values and report back on any changes?
Googer - Wednesday, September 9, 2009 - link
The lack of PS2 is a real deal killer for me, I have a beloved IBM Clicky Model M keyboard (1391401) and I will not give it up for anything. I know PS2-usb keyboard adapter exist but they just don't work very well.I am not alone, there are tens of thousands of vintage keyboard lovers out there and the IBM Model 1391401 is one of the more popular ones among keyboard aficionados.
Kind of sad that a 20-30 year old keyboard still works as well as they day it was made, new cheaper keyboards are less acuurate, uncomfortable, very flimsy and are poorly made. You would be lucky to get 5-6 years out of 'some' of these newer $90+ keyboards.
Save PS2, keep it alive. PS/2 has less lag than any USB keyboard I have tried. There are a lot of great keyboards still in use. There is no shortage of real estate on the back IO shields, so there should be no reason not to include a PS/2 port..
MamiyaOtaru - Thursday, September 10, 2009 - link
Seconding this. USB is incapable of providing n-key rollover for keyboards. PS2 can. Not everyone needs that, but I won't do without it.Zoomer - Wednesday, September 9, 2009 - link
I saw at least one PS2 port on these motherboards. What are you talking about again? Yes, they seem to be shared with the PS2 port for mice, but mice work the same on USB anyway.Taft12 - Wednesday, September 9, 2009 - link
This is probably the most off-topic post I've seen on this site. Fortunately for all of us, your rant is invalid and you never have to say anything about this ever again:http://www.syba.com/index.php?controller=Product&a...">http://www.syba.com/index.php?controller=Product&a...
boogerlad - Tuesday, September 8, 2009 - link
where't ta152h now? That idiot is finally done trolling.snakeoil - Wednesday, September 9, 2009 - link
all the results of this review are biased because they were made with turbo enabled, that's at least 600 mhz overclocking.to be fair you must compare this results against a phenom 2 overclockded at least 600 mhz
people is not stupid.