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.
343 Comments
View All Comments
mschira - Tuesday, September 8, 2009 - link
I wonder if a 4xPCIe RAID adapter directly connected to a PCIe slot that is connected to the CPU is any faster than it is for a Core i7 920....Cheers
Gary Key - Tuesday, September 8, 2009 - link
Less than a one percent difference in my testing so far.Jamahl - Tuesday, September 8, 2009 - link
Why do your benches falsely state 2.66ghz when they are clearly running faster than that?rbbot - Tuesday, September 8, 2009 - link
lol - I've just been berating a reviewer on another site for benchmarking with turbo off! In that case the review wasn't targeted at an overclocking audience, but even here I can't see the argument for benchmarking with it disabled.Yes you do need to turn it off for extreme overclocking, but this review is comparing the chips in their stock configuration and stock configuration is on.
maxxcool - Tuesday, September 8, 2009 - link
As for false, well gee, you were told it was on. Didn't you read that? or are you snakeoils brother?goinginstyle - Tuesday, September 8, 2009 - link
They list the base CPU speeds, it was discussed clearly in the article that turbo is enabled, it is not a false statement for reporting what you will purchase. Apparently you just want to flame bait here and I hope they ban you and the two other nut jobs.rgallant - Wednesday, September 9, 2009 - link
people see what they want to see I guess-I wanted to see the multi gpu test, 1156 vs 1366 , clock vs clock ,fps vs fps ,16x vs 8x on die , not one chip overclocking it's self unless you show the numbers for turbo on and off, what if the 1366 mb used for the benches came out of the box and by the default bios overclocked the i7 920 to 3.8 ,would those numbers be included as stock out of the box. I don't think so , that feature would be turned off on the mb.for the benches. 1156 numbers could mean nothing really.
-all cpu's should been locked at 3.6 at least for the multi gpu test or one test anyways.
-the 8x 8x lane issue is the only crippled feature on the new chips ,and it seems to take a back seat to the $50.00 savings for a mb for a $600.00 i7 870 chip ,or $900.00 CND .lol On sept.05 my local shop had the i7 920 D0 and the i7 860 both at $345 CND.
-good review as always ,just missing that part for me , looking to commit on a 1156 or a 1366 upgrade.
maxxcool - Tuesday, September 8, 2009 - link
Yeah, you got to get rid of snakeoil, he is quiet the troll on the TechReport forums as well. He has been banned from several sites already.andrenb91 - Tuesday, September 8, 2009 - link
i5 is faster than PII's! but gotta wait for the lower end ones come outbecause these $190+ chips aren't the one ones that brings up revenue for companies like amd or intel...of course intel has the upper hand here, it could use as a propaganda do deliver up the slower parts. Amd has value and some good cpus at the lower end... that ones bring profits to the company,amd strategy is looking good for now, but it's design must change (native dual/tripe core versions of Phenom II) and the die size have to get smaller to compete next year (against 32nm low end ones...) well I use amd budget ones, for what I do is good enough, ( thin about $400 pc in USA, live in Brazil...) still, I can play some 40fps games and do some video encoding with my gpu,my point is, amd still have the lower-end market, the problem is, if were some of that people that think pentium is a company name, I would by the pentium cpus instead of amd strange cpus. that's why intel sells a lot more desktops and notebooks, of course the performace is great at some 700+ pcs and laptops, but amd has the lower-end, and there it is what amd is looking for: market share, and taht will pump amd back again by 2011 with its fusion apu, intel already controls 80% of mainstream,and high-end markets, but doesn't have a player for the lower-end, thats what I'm looking for a good old intel cpu that beats p2x3 or athlonIIx4 by intel at about $100. then I'll buy my next cpu, probably an intel, or continue with Amd, time will tell...
andrenb91 - Tuesday, September 8, 2009 - link
sorry for my english and, these benchmarks are for windows only, over linux intel i5 will not have this crazy advantage at all, well but who of us uses linux anyway?(don't lie to me, it's a dual boot...) well my system specs are: phenomII x3 705e,4gb ddr3 1333,hd 4650 basicaly a low-end to mainstream..