Intel's 65nm Gameplan: Presler and Cedar Mill Updates
by Kristopher Kubicki on September 9, 2005 6:42 AM EST- Posted in
- CPUs
65nm and Dual Core for Everyone
Intel's WW36 and WW31 roadmaps came and went with relatively little fanfare. Even though we just had an extensive Fall IDF, there were several things mentioned in the roadmaps that were not at the show; like Intel's 975X chipset. We have some in depth articles concerning Broadwater, 975X and other finer points of the roadmap, but in the meantime it's important that we list the upcoming processor codenames and cores.
Intel's Extreme Edition series is nothing more than a series of low volume chips designed to showcase Intel's best of breed, but then again many argue the same for AMD's FX line. We don't expect any of the chips listed below to work their way into your family PC anytime soon, but they do give us a frame of reference for the desktop processor direction.
Intel Extreme Edition |
||||
| CPU | Core | Clock | FSB | Mass Production |
| EE 955 | Presler | 3.46GHz | 1066MHz | Q1'06 |
| EE 840 | Smithfield | 3.2GHz | 800MHz | Now |
| EE 3.73 | Prescott | 3.73GHz | 1066MHz | Now |
The Intel 955 Extreme Edition will be the first 65nm dual core Presler introduced. Presler, as you may recall, differs slightly from Smithfield in the fact that each individual Cedar Mill core comes from a separate die on the processor packaging. This is partially due to the fact that the smaller 65nm process changes the optimal configuration of the chip layout, but mostly due to the increased yield -- it's easier to throw out one core at a time than to scrap both cores even if only one fails QA. The new Presler Extreme Edition will feature two banks of 2MB L2 cache, and will feature Intel's VT virtualization technology. As with the 840EE, HyperThreading will also come enabled on the 955EE.
The desktop dual core roadmap is significantly more relevant and interesting. Intel and AMD both predict the mainstream desktop to fully embrace dual core, so the majority of both companies' roadmaps are targeted at that sector.
Intel Dual Core Desktop |
||||
| CPU | Core | Clock | FSB | L2 Cache |
| ??? | Conroe | ??? | ??? | 4MB |
| ??? | Conroe | ??? | ??? | 2MB |
| 950 | Presler | 3.4GHz | 800MHz | 2x2MB |
| 940 | Presler | 3.2GHz | 800MHz | 2x2MB |
| 930 | Presler | 3.0GHz | 800MHz | 2x2MB |
| 920 | Presler | 2.8GHz | 800MHz | 2x2MB |
We've already talked a little bit about Presler in previous roadmaps and with the 955EE. All of the 65nm Presler processors listed are scheduled for a Q1'06 launch and are virtually identical to the existing Intel Pentium D 8xx series with a few new features:
- 65nm die process with two separate dies, but a single packaging still
- 2x2MB L2 cache
- Virtualization Technology (VT)
As with Smithfield, HT will not be enabled on non-Extreme parts. Barring a miracle, the new Presler chips would need to have some new feature not listed on the roadmap to really make them outshine the existing Smithfield and Athlon 64 X2 chips. The smaller process might allow them to run slightly cooler, and we might even see 4.0GHz chips at some point, but that's about the only changes.
It's clear the NetBurst architecture is nearing the end of the road, but we find it odd that the Conroe unveiling is less than a year away from Intel's 65nm NetBurst launch! The current roadmap claims an H2'06 launch for Conroe. Conroe features a completely new architecture for Intel, with new features like a 4-issue core and a shared L2 cache between cores. Although the roadmaps have virtually no information on clock speeds, we do know that there will be two versions of the chip, one with a 4MB shared L2 cache and another with a 2MB shared L2 cache. The chips will also feature EIST, VT and EM64T.
Intel still thinks there is life in Prescott, and even after the die shrink to 65nm (Cedar Mill), the Intel roadmap claims new single core Prescott-2M versions will be made available with VT. Perhaps the only interesting detail below is the fact that Intel canceled the VT versions of Cedar Mill. Why Intel will even bother to pursue VT on the 90nm core and not the 65nm core is a total mystery. Some of the product names have also changed a bit since the previous roadmap.
Intel Desktop Performance Roadmap |
||||
| Processor | Core Name | Clock Speed | Socket | Launch Date |
| Pentium 672 | Prescott 2M + VT | 3.8 2MB | LGA 775 | Q4'05 |
| Pentium 671 | Cedar Mill | 3.8 2MB | LGA 775 | 2H'06 |
| Pentium 662 | Prescott 2M + VT | 3.6 2MB | LGA 775 | Q1'06 |
| Pentium 661 | Cedar Mill | 3.6 2MB | LGA 775 | Q1'06 |
| Pentium 651 | Cedar Mill | 3.4 2MB | LGA 775 | Q1'06 |
| Pentium 641 | Cedar Mill | 3.2 2MB | LGA 775 | Q1'06 |
| Pentium 631 | Cedar Mill | 3.0 2MB | LGA 775 | Q2'06 |
| Pentium 670 | Prescott 2M | 3.8 2MB | LGA 775 | Now |
Virtually everything else on the CPU roadmap remains unchanged since our last revision. Intel has been good to ship processors and chipsets on its set launch dates over the last year, but the 65nm chip launch looks to be one of Intel's shortest product cycles yet with Conroe just around the corner in the same year. In all likelihood, Intel is probably just testing their 65nm yields with the initial Cedar Mill and Presler chips before moving onto bigger and better projects like Conroe. Intel's launch of Broadwater (i965X) also comes about the same time as the new CPU launch; and nothing sells chipsets quite like new CPUs. We have more details coming up on Intel's new 965X, 975X, Viiv and Yonah very soon, so stay tuned!
Facebook
Twitter
RSS
27 Comments
View All Comments
theteamaqua - Wednesday, December 21, 2005 - link
what socket is the pentium D 900 series going to be? b/c i have the nForce4 SLI with LGA 775 and i would hate to change another moboThatguy97 - Tuesday, June 16, 2015 - link
lolAnemone - Monday, September 12, 2005 - link
I believe by now it's rather apparent to most folks that all things P4 in the way of new releases are bandaids. Even Yonah, for all its "new completely revised architecture" is pretty much the same thing, a bandaid until Conroe/Merom.There are a number of insider reports indicating that there is very little chance Merom/Conroe will be out by Q3 2006. Q4 is going to be more likely, and after watching Dothan and now Yonah slip their predicted schedules, it's not unreasonable to think this could be true. That would fit as well with Pressler and Yonah seemingly so close to an entire product revision, Merom/Conroe. They need to keep the hype and the products flowing till they can make Merom/Conroe a reality.
Do remember something else. The part of the reason the P3 was cancelled and the P4 introduced was because the P3 was failing to keep up with the Athlon clockspeeds. In several comparisons of the P-M (who's performance is only really boosted by cache) and the A64, you'll find that at about equal clockspeed and half the cache (A64 1m/P-M 2m), you'll find about equal performance. When overclocked, the P-M seems to do very well, but again, you'll find it about equals the A64 at that higher speed. Now a lot of folks seem to be believing that the P-M and its reincarnation, Merom/Conroe, are going to hit speeds high enough to compete with the A64, even while lengthening the pipeline somewhat. I'm pretty positive that's what Intel's engineers were told to deliver as well. But there is a good bet that may not exactly play out as Intel would have you believe.
Why, you ask? Well have a look at Yonah's speed. Even though there will be a single core version, they aren't going to release the chip at higher speeds. The likely fact here is that Intel knows perfectly well that what is propping up the P-M's performance is really the cache, and that getting the actual cpu to perform at higher speeds (over long term not just a 2 hour overclocked benching session) is not happening on current chips. Remember the tidbit about how Intel solved the "power issue" at 45nm? You can bet that Intel believes the real combination that will work is Merom/Conroe in a 4mb 45nm version, and they are actually probably trying to see how fast they can get that process online and mass producing chips. So if you see a 65nm Merom/Conroe with a 2mb cache, it will again, be a bandaid until they get the real thing out. So really this whole race takes you to Q1/Q2 of 2007, but they want you to be lead there carefully while never dropping enthusiasm for "the next big thing". Now if your real "golden product" isn't going to be out till Q1/Q2 of 07, you understand far better why you can still introduce a "new" product in Q1 of 06, that is based on the last of the old tech.
The only thing you need to read between the lines is that the timing you think your getting on the new chips you are most interested in, Merom/Conroe, isn't nearly as soon as is being advertised.
$.02
michaelpatrick33 - Friday, September 9, 2005 - link
Intel's lead in the performance/watt claim seems to mask lower performance against todays X2's which isn't good. From the claims made by Intel the current dualcore Opterons are already faster than the fastest Sassaman's (spelling, lol) but will obviously use more wattage. With low power dualcore Opterons already out at 55watt I just don't see Intel's stuff as very exciting from a performance standpoint. Marketing dictates fastest performance per watt but reality defined means the same as what we have now or a little faster but uses less power so we can use dualcores in notebooks etc. I will be curious to see what 4megs of L2 cache will do on a low pipeline processor.Shintai - Friday, September 9, 2005 - link
You mix a few things up.Low power opterons uses a max of 55W yes. What does low power Xeon use?, What does low power Yonah use? What does low power verions of Meron/Conroe/Woodcrest use?
Currently AMD leads the performance/watt on servers (cept blades) and desktops (Cept for the geeks running Pentium M as desktop :) Intel leads in mobile over AMD.
But intels performance/watt forecast is based on yonah/meron/conroe/woodcrest.
For the 4MB L2 cache question on a low pipeline CPU. Simply compare Banias to Dothan and you got the answer.
What Intel and AMD seem´s to finally wake up to is, that a PC user don´t want a huge megaheatsink, lots of fans spinning at 12000rpm and a 800W PSU for their future PC.
Now we just need nVidia and ATi to wakeup aswell :)
Furen - Friday, September 9, 2005 - link
Not quite. L2, like all other things, gives you diminishing returns. The L2 in dothan makes up for its weak FSB and memory interface. Conroe will have a much faster FSB than the initial 400MHz FSB Dothans and its memory bandwith will be significantly better as well.sprockkets - Friday, September 9, 2005 - link
No 1066 FSB support til '06, did I read that right, yet the latest chipsets support it, why?Intel says they will lead with good performance/watt, and probably will, but it is not as if AMD's chips ran hot to begin with haha.
Shintai - Friday, September 9, 2005 - link
Increasing FSB increases heat generated by the CPU. Aswell as making it more complicated and more expensive to make a motherboard. The answer is the industry ain´t ready to make 1066 FSB cheap enough yet.sprockkets - Friday, September 9, 2005 - link
But if the chipset's support it wouldn't the motherboard as well support it? Look at the 945G chipsets, and all the MB at newegg with it, they support the 1066FSB, yet no processor can use it without overclocking.ksherman - Friday, September 9, 2005 - link
any chance we could get a little more information on what VT actually does? I have heard of a lot of things that will use VT, but I dont quite get what it does