Nehalem Part 3: The Cache Debate, LGA-1156 and the 32nm Future
by Anand Lal Shimpi on November 19, 2008 8:00 PM EST- Posted in
- CPUs
What to Buy: Mainsteam vs. High End Nehalem
With two sockets targeted at desktops, how will the Core i7s that launched this month stack up to the mainstream Lynnfield and Havendale parts?
The absolute highest frequencies will only be available in LGA-1366 packages and I’d expect this is where we’d see 8-core/16-thread Nehalem parts first (if not exclusively). We’ve already shown that the three DDR3 channels don’t really help for most desktop applications, but this could change when Nehalem moves to 8 cores. Overclockability may also be better on LGA-1366 as the CPUs themselves will be higher bins.
Intel’s roadmaps show three pricepoints of Lynnfield processors in 2009. The top end Lynnfield part looks to be something that’s similar in price/frequency to the i7-940 (or whatever replaces it in Q3 2009). If I were to guess I’d say that’d be a $562 3GHz+ Lynnfield with performance somewhere in between an i7-940 and i7-965.
There will be a midrange Lynnfield, most likely priced/clocked similarly to the i7-920 or its eventual replacement. I’d guess a 2.66GHz - 2.93GHz CPU priced at around $284. Finally the low-end Lynnfield will be somewhere near $200 and probably weigh in at 2.4/2.53GHz. With Havendale not arriving until 2010, it’s currently absent from all Intel roadmaps.
Intel is going to support both platforms, LGA-1366 and LGA-1156 for the long term, the difference will be in the type of processors enabled. LGA-1366 may end up being more of a high end enthusiast play, Intel indicated that LGA-1366 CPUs would be binned higher so you can expect higher overclocks and obviously higher top end frequencies.
At the same time you should be able to get pretty far with LGA-1156, simple 500MHz overclocks shouldn’t be a problem but the 1GHz+ overclocks we’re used to on LGA-1366 and LGA-775 may not be as possible - at least not at 45nm.
Intel isn’t going to do anything to limit overclocking on LGA-1156 platforms, the same current limit bypass that’s on LGA-1366 boards will be optional on 1156 boards should the motherboard manufacturer choose to support it.
The breakdown seems pretty simple: if you’re the type of person who bought the Q6600/Q9300, then Lynnfield may be the Nehalem for you. If you spent a bit more on your CPU or are more of an enthusiast overclocker, the current Core i7 seems like the path Intel wants you to take.
The issue with Lynnfield is that it’s a good 6+ months away, and if Core i7 can speedup your workloads a lot today then you’ll be tempted to make the upgrade now. In notebooks we’ll see Lynnfield in the larger machines and Havendale in most of the platforms.
Without mainstream mobile Nehalem until Q1 2010, next year will be a very long wait for a serious mobile upgrade. But if you can wait it out, or buy something cheaper today, the time to upgrade will be in Q1 2010. I’m going to go ahead and revise my Apple notebook recommendation given that we probably won’t see a Nehalem based MacBook until 2010. Buy the cheapest MacBook you can today and make it last, upgrade again in 2010. Ooh, that rhymes.
Facebook
Twitter
RSS
33 Comments
View All Comments
blyndy - Thursday, November 20, 2008 - link
Yeah I think that Intel has failed to be consistant between Penryn/Nehalem, or at least bit off more than it could chew...I mean, tick-tock is fine and all, but Penryn has really held up as an ideal architecture, as something to grow off, not as something that should be immediately succeeded by 'the biggest architectural redesigns since the Pentium 1'. After all Core/2 IS the fruit of the P3/Pentium M. Nehalem on the other hand smells unpleasantly P4-like, due in large part to hyperthreading.
HT's something that you either see as 'reduces single thread performance, consumes transistors adds arch bloat and adds heat' or as 'OMG MOAR CPUs IN TASK MANAGERZOMG!!!'. And it's funny because at the end of the day it still runs into the same question as the core-count issue --'are these additional execution units adequately utilisable by a DIVERSE set of applications (i.e. NOT JUST vid encode...)?'. Because we know threading is HARD.
OK I'll come clean-I just what to know when are they going to dust off the wolfdale masks and shrink 'em onto 32nm? :D
esgreat - Thursday, November 20, 2008 - link
Well tell me where does the mainstream user want for in performance other THAN video encoding and image processing?Games? Games have shown to be much more limited to GPU side. Most CPU enhancements can't really make huge impacts on games nowadays. This is unless they try to utilize more cores, which is what they have done: provide the hardware so that software could use it. The software is fast right now because things like SSE were introduced years ago (although they weren't beneficial then).
As for video encoding, cutting down encoding time from 30 minutes to 10 minutes IS A BIG DEAL. And this is one application where many users (non gamers) would really use.
Enabling of multicore now means fantastic applications in the future.
cocoviper - Thursday, November 20, 2008 - link
Pretty good read.I'm hoping we can get some more detailed info about Intel's 32nm process in the next couple months- especially what they're planning to do with Atom and 32nm.
CEO Ballmer - Wednesday, November 19, 2008 - link
AMD is still in the game?I had written them off!
http://fakesteveballmer.blogspot.com">http://fakesteveballmer.blogspot.com
Derbalized - Thursday, November 20, 2008 - link
AMD is still in the game.AMD is designing Intels next chip.
Probaly with an integrated memory controller also.
Derbalized - Thursday, November 20, 2008 - link
I probaly should have spelled probably right. LOLpiesquared - Wednesday, November 19, 2008 - link
Nope, don't give a shit. But do want to know what keeps happening to all these AMD and ATI reviews you keep promising over and over.chizow - Thursday, November 20, 2008 - link
LOL. There was a brilliant post on DT that basically claims AMD has now shifted their focus to producing Roadmaps. A bit harsh, but honestly pretty accurate.Wait til AMD actually releases a new product before getting all emo about a lack of AMD reviews.
whatthehey - Thursday, November 20, 2008 - link
You want an AMD review? Here's one for you: AMD's current products suck for the vast majority of users. The only place they're worthwhile is in the 8S server space; otherwise, they cost too much and deliver too little. Their dual-core parts were awesome when all they had to do was beat Pentium D, but Intel has progressed substantially since then and all AMD has got is a bloated, buggy, slow POS known as Phenom. At least the name is right: it's a phenomenal failure.Or maybe you mean the various ATI reviews posted during the past couple months?
http://www.anandtech.com/video/showdoc.aspx?i=3441">http://www.anandtech.com/video/showdoc.aspx?i=3441
http://www.anandtech.com/video/showdoc.aspx?i=3437">http://www.anandtech.com/video/showdoc.aspx?i=3437
http://www.anandtech.com/video/showdoc.aspx?i=3420">http://www.anandtech.com/video/showdoc.aspx?i=3420
http://www.anandtech.com/video/showdoc.aspx?i=3415">http://www.anandtech.com/video/showdoc.aspx?i=3415
http://www.anandtech.com/video/showdoc.aspx?i=3405">http://www.anandtech.com/video/showdoc.aspx?i=3405
Oh, but that's not good enough for the AMD fanboyz! Everyone needs to baby AMD and talk about how awesome they are, when AMD is busily circling the drain and getting ready to spin off their fabrication to a separate company. ATI is doing pretty well, and AMD made some good hardware in the past; unfortunately, it doesn't look like they were able to continue to compete.
And honestly, it's no big surprise. Even Intel is having a tough time competing with their own products. Nehalem is a nice design, but as I've told others we are at the point where 95% of people don't need anything more than a three year old Athlon 64 X2. Quad-core only matters to a small number of desktop users at best, and here Intel and AMD are both looking to hex-core and octal-core in the not too distant future. That's great if you do video work or 3D rendering, but pretty much useless for everyone else.
I lust after the new Nehalem upgrades as much as the next guy, but invariably I come back to the realization that my pathetic Q6600 @ 3.00GHz (yes, I backed off from 3.6GHz when I realized that the extra voltage and stress on the system wasn't actually improving performance in any of the applications I use on a regular basis) was more than fast enough for any current program. About the only thing I need right now is an upgrade in the video card department, and I don't need Nehalem for that!
Griswold - Thursday, November 20, 2008 - link
After reading"AMD's current products suck for the *vast majority* of users"
I knew that your entire posting would have less substance than a steaming pile of cow dung. Why is it that the most clueless people always type up the biggest shitstorm of incoherent garbage..?