Intel CPU Roadmap Update

We have already covered some of the major announcements from Intel in our look at Intel's Dual-Core Strategy, but plenty of processors will still be sold between now and when the first dual-core chips ship. We are going to focus primarily on the changes in this roadmap update, but we will list basic information on most currently shipping Intel processors for comparison. There are not that many updates from month to month in Intel's roadmaps, so to help you find the changes from our last Intel Desktop Roadmap we have highlighted them with red text. We will cover all three sectors - desktop, mobile, and server/enterprise - starting with what remains the largest in terms of volume, the desktop sector.


Intel Desktop Lineup LGA775
Performance Processors
Processor Speed Cache FSB Launch Date Other
x40 Dual Core 3.20 GHz 2x1MB 800MHz Q3'05 EM64T, EIST, EDB
x30 Dual Core 3.00 GHz 2x1MB 800MHz Q3'05 EM64T, EIST, EDB
x20 Dual Core 2.80 GHz 2x1MB 800MHz Q3'05 EM64T, EIST, EDB
Pentium 4 XE 3.73GHz 3.73GHz 2MB 1066MHz Q1'05 EM64T, EIST, EDB
Pentium 4 XE 3.46GHz 3.46GHz 512K+2MB L3 1066MHz Nov'04  
Pentium 4 670 3.80GHz 2MB 800MHz Q2'05 EM64T, EIST, EDB
Pentium 4 660 3.60GHz 2MB 800MHz Q1'05 EM64T, EIST, EDB
Pentium 4 650 3.40GHz 2MB 800MHz Q1'05 EM64T, EIST, EDB
Pentium 4 640 3.20GHz 2MB 800MHz Q1'05 EM64T, EIST, EDB
Pentium 4 630 3.00 GHz 2MB 800MHz Q1'05 EM64T, EIST, EDB
Pentium 4 580J 4.00GHz 1MB 800MHz Cancelled  
Pentium 4 570J 3.80GHz 1MB 800MHz Q4'04 EDB
Pentium 4 560J 3.60GHz 1MB 800MHz Already available EDB
Pentium 4 550J 3.40GHz 1MB 800MHz Already available EDB
Pentium 4 540J 3.20GHz 1MB 800MHz Already available EDB
Pentium 4 530J 3.00GHz 1MB 800MHz Already available EDB
Pentium 4 520J 2.80GHz 1MB 800MHz Already available EDB
Budget Processors
Processor Speed Cache FSB Launch Date Other
Celeron D 350 3.20GHz 256KB 533MHz Q2'05 EDB
Celeron D 345 3.06GHz 256KB 533MHz Nov'04 EDB
Celeron D 340 2.93GHz 256KB 533MHz Already Available EDB
Celeron D 335 2.80GHz 256KB 533MHz Already Available EDB
Celeron D 330 2.66GHz 256KB 533MHz Already Available EDB
Celeron D 325 2.53GHz 256KB 533MHz Already Available EDB

The biggest news is of course the announcement of the x20, x30 and x40 dual-core processors. At present, it is not clear if these are the final names for these parts or simply placeholders. The "x" may be replaced by whatever number eventually gets assigned to the dual-core parts. That's one interpretation of it, anyway, as Intel's roadmap refers to "6xx series" and "xxx" series parts - note the use of the lowercase "x" here. With the addition of the 600 series in the last roadmap, it stands to reason that the dual-core NetBurst chips will eventually be given a numerical designation. "X" is already one of the most overused letters in the alphabet as far as marketing goes, so we can hope that Intel will refrain from adding another component to the already crowded "Generation X" hardware genre. The Pentium 4 eXtreme Edition (TM) has already paved the way, however, so don't get your hopes up. There is no HyperThreading support scheduled for the dual core Processors.

Besides the introduction of the dual core parts, most of the roadmap remains unchanged. A few parts have been pushed back one quarter on their launch date, and in the case of the 4.0 GHz 580J, it has been cancelled. Some will point to the product cancellations - there are a couple more elsewhere in this roadmap - as a sign of Intel's pending doom. We prefer a slightly less alarmist view and believe that Intel is simply being cautious. Overclocking headroom on Intel parts has always been pretty good relative to their competitors, and rather than pushing parts through validation at close to their maximum speed, it is probable that Intel is making sure the parts run reliably. Other than the ill-fated Pentium III 1.13 GHz Coppermine, Intel CPUs have usually been binned at least two levels below their maximum clock rate. Many enthusiasts are already overclocking Prescott cores to 4.0 GHz using only air-cooled HSFs, so such clock speeds are certainly attainable. With more recent steppings of the Prescott core (akin to minor software revisions), we would expect slightly more headroom that 4.0 GHz. Time will tell us whether Intel is really having problems or is simply being conservative - they could have always gone with a water cooled CPU setup like the Apple G5 systems if they felt the increased speed was truly worthwhile.

If you look at the 600 series of processors, Intel has now announced plans to include a 3.0 GHz part, the 630. As these processors will all include 2 MB of L2 cache compared to the 512K L2/2M L3 cache of the earlier Gallatin-based P4EE (or the 1M L2/2M L3 of the socket 775 P4XE), performance should at worst match the older 3.2EE and 3.4EE parts on a clock-for-clock basis. Performance of the Irwindale chips (also referred to as Prescott 2M and Nocona 2M) should also at least match the current Prescott chips, and in most instances it will surpass them. NetBurst remains an extremely bandwidth hungry design, and you can almost see the gears turning in the brains at Intel: The P4EE was able to keep Intel competitive with AMD in the race for the performance crown, and if they combine the 2M cache of the P4EE with the higher clockspeeds and other architectural tweaks of the Prescott design, they ought to get the best of both worlds! With the 630 and 640 targeting the mainstream market, prices should be under $300 when the parts ship in early 2005. The P4XE will continue to be an ultra-expensive part, and to help it maintain a lead relative to the 600 series parts, it will be getting a 1066 MHz FSB on the future versions. Say what you want about the elegance of the design, but the fact is that a 2 MB L2 cache NetBurst chip will remain competitive with most of AMD's Athlon 64 parts. AMD will still hold the lead in certain applications - i.e. gaming - but Intel is not out of the picture yet.

The only remaining change on the desktop platform is that the 600 series of processors as well as the P4XE 3.73 will now have their EM64T support activated. (The P4XE 3.43 uses the older Gallatin design, which is a Northwood core with L3 cache, so there is no 64-bit support to activate.) As Intel's position has always been that they will "have 64-bit enabled processors available when software support is ready," this makes sense. Windows XP-64 should finally ship within the next couple quarters, and 64-bit versions of Linux have been available for a while now. We have yet to see any significant benefit for 64-bit applications, but that should come as 32-bit applications are recompiled and tuned for the additional registers. One topic that comes up repeatedly in the latest Intel roadmap is Intel's "leadership role" in getting 64-bit computing to the desktop. Revisionist history at it's finest! The important thing is that, regardless of who did the work, both x86-64 solutions will be compatible. The same is true of Intel's "Execute Disable Bit" (EDB); in practice, it functions the same as AMD's XD and they are compatible.

Mobile Processors
POST A COMMENT

22 Comments

View All Comments

  • RotoSequence - Tuesday, November 23, 2004 - link

    I think I have gotten a hold of the true reason behind the cancellation of the 4 Ghz Pentium 4. For at least now, there are some serious issues resulting after extended use of Pentium 4s that are clocked at 4 Ghz+. I E-mailed an Intel Engineer and asked why they dont use FSB increases instead of higher multipliers (as the Pentium 4s tend to like that). When you drive the processor that hard, there is electron polarization that occurs in the processor. Over the course of a few years, this permanent electron polarization (As a result of the electron density in such a small area) results in an open circuit-and an un-bootable CPU. Evidently, this is the average net effect, and in the Intel Guy's own words, "We would rather sell an underclocked processor than one that will fail in a couple of years." So potentially, there you have it people; the reason behind Intel's (possibly temporary?) reason for the cancellation of the Pentium 4 4Ghz. Reply
  • JarredWalton - Saturday, November 06, 2004 - link

    #20: Personally, I won't be surprised to see the dual-core "x" chips slip into Q4 or possibly even '06. Actually, Intel will probably ship limited samples in Q3'05, which may allow them to claim that they have "shipped". Yonah/Jonah is not yet on the roadmaps, which is what this article is about. See Kristopher's recent look at code names, chipsets, and features for an overview of other stuff coming down the pipe from Intel. Reply
  • knitecrow - Thursday, November 04, 2004 - link

    Does anyone seriously expect intel to keep the q3 2005 timeline for x** chips?

    Do they even have working engineering samples?

    ---
    why isn't there anything said about dual-cored pentium M chips?

    I guess we won't seem then untill 2006
    Reply
  • JarredWalton - Thursday, November 04, 2004 - link

    Oops.... my bad. I thought that the 5xxJ actually included EDB as well as EIST, but on closer inspection this is not the case. Urg... So I removed it from the 5xx chips. A new inspection of the roadmap reveals that EIST is apparently enabled on all "Prescott" core Xeons (really Nocona, Cranford and Potomac), and any 775-LGA chips with EM64T also have it. So for now that means the 5xx series is without speedstep. The x.xxF revision Xeons are the same as the 5xxJ revision Prescotts, but EIST and EM64T are not enables for the desktop parts (yet?). Reply
  • jarthel - Wednesday, November 03, 2004 - link

    A member of an Australian computer forums mentioned that the Intel channel roadmap does not mentioned EIST in the J CPUs.

    Also this publicly available page (http://www.intel.com/products/processor_number/inf... does not discuss EIST with J CPUs.

    Can you clarify?
    Reply
  • JarredWalton - Saturday, October 30, 2004 - link

    For official 1066 FSB support, you will need the 925XE chipset, which is not yet available. EM64T support should still work in older chipsets - a BIOS update might be required, however.

    As for EIST and unlocked lower multipliers, I read something somewhere (yeah, I know - highly specific information) about some mod that could be done to unlock lower multipliers on new P4 chips. I don't even recall if it was a software mod or a hardware mod, or maybe just something that needed to be enabled in the BIOS. If I find out more information, I'll let you know, but for now that's about as specific as I can get. :|
    Reply
  • danidentity - Saturday, October 30, 2004 - link

    Thanks Jarrad...about my question in post 8, the 5xxJ CPUs include EIST. Does that mean they'll have unlocked downward multipliers like Athlon 64's? Reply
  • Foxbat121 - Friday, October 29, 2004 - link

    Current Intel chipset (915 and 925) does not support 1066 FSB, IIRC. Reply
  • MIDIman - Friday, October 29, 2004 - link

    Is it safe to say that everything here will be compatible with current LGA775-based chipsets and motherboards, including 1066mhz FSB?

    Does 925x and 915p support EM64T and dual-core CPUs?

    Just curious if its too early to buy into LGA775.
    Reply
  • JarredWalton - Friday, October 29, 2004 - link

    Pumpkin (happy halloween!): The roadmap I have has no mention of any new socket 478 parts other than a Celeron D 345. There have been rumors on and off that Intel may introduce a faster socket 478 part, but to my knowledge Intel has said nothing official about this.

    Danidentity (no relation to Bourne?): "Q1" is as specific as the roadmap gets in relation to the 6xx series right now. Typically, Intel will narrow that down to an actual month (and day even) a couple months prior to launch. We'll update the roadmaps with this information when we get it. I'll take the middle ground right now and guess at February - that way I can't be more than 30 days off. :)
    Reply

Log in

Don't have an account? Sign up now