Besides all the talk about the future architecture, there's not much to say about the desktop parts. Here's the current roadmap.

Intel Desktop Performance Roadmap
Processor Core Name Clock Speed Socket Launch Date
Pentium 673 Cedar Mill 3.8 2MB LGA 775 2H'06
Pentium 672 Prescott 2M + VT 3.8 2MB LGA 775 Q4'05
Pentium 663 Cedar Mill 3.6 2MB LGA 775 Q1'06
Pentium 662 Prescott 2M + VT 3.6 2MB LGA 775 Q4'05
Pentium 653 Cedar Mill 3.4 2MB LGA 775 Q1'06
Pentium 643 Cedar Mill 3.2 2MB LGA 775 Q1'06
Pentium >= 633 Cedar Mill 3.0 2MB LGA 775 Q2'06
Pentium 631 Cedar Mill (no VT) 3.0 2MB LGA 775 Q1'06
Pentium 571 Prescott 3.8 1MB LGA 775 Now
Pentium 561 Prescott 3.6 1MB LGA 775 Now
Pentium 551 Prescott 3.4 1MB LGA 775 Now
Pentium 541 Prescott 3.2 1MB LGA 775 Now
Pentium 531 Prescott 3.0 1MB LGA 775 Now
Pentium 521 Prescott 2.8 1MB LGA 775 Now

The single core Pentiums remain unchanged from last month, with the exception of the 673 showing up at the top. Processor models ending with a 3 will use the new Cedar Mill core, the single core version of Presler. They will be based on 65nm process technology and will include all the same extra technologies we mentioned earlier. They will also have HyperThreading enabled, where the dual core Presler chips do not. There is also a potential lower end 633 model scheduled to be introduced in Q2'06, though it may or may not be released, likely depending on demand and yields.

One final update for the mainstream desktop market is that the EM64T enabled 5x1 Pentium chips are finally available. We've been talking about them for a few months, and retail availability was expected before now. They were probably held back to let inventory of the earlier versions clear out. You can see the new chips in our Pricing Engine.

Intel Desktop Value Roadmap
Processor Core Name Clock Speed Socket Launch Date
Celeron D ??? Cedar Mill 512K + EM64T ??? LGA 775 2H'06
Celeron D 355 Prescott 256K + EM64T 3.33 256K LGA 775 Q4'05
Celeron D 351 Prescott 256K + EM64T 3.2 256K LGA 775 Now
Celeron D 346 Prescott 256K + EM64T 3.06 256K LGA 775 Now/Soon
Celeron D 341 Prescott 256K + EM64T 2.93 256K LGA 775 Now/Soon
Celeron D 336 Prescott 256K + EM64T 2.8 256K LGA 775 Now/Soon
Celeron D 331 Prescott 256K + EM64T 2.66 256K LGA 775 Now/Soon
Celeron D 326 Prescott 256K + EM64T 2.53 256K LGA 775 Now/Soon

The Celeron picture is similar to the single core Pentium market. The EM64T enabled Celeron D chips are all starting to ship, after a month or two of waiting. Once again, you can check the current prices and availability on our Pricing Engine - at present the 351 is available, but we aren't picking up any of the slower "+1" parts. Current generation Celerons do not have VT, HT, or EIST support, but they do include XD (as have all Celeron D chips since the "J" variants started shipping almost a year ago).

Once Intel transitions to 65nm, a new version of the Celeron based off the Cedar Mill core will arrive. Clock speeds are not yet set, but we do know that it will continue to use a 533 MHz FSB, and it will increase the amount of L2 cache to 512K. That will make the chip relatively interesting, as the old Northwood core also included 512K of cache. Of course, the pipeline of Northwood was only 20 stages rather than 31, so clock for clock Northwood may still be faster. With a 65nm process, however, we expect the chips to be able to hit relatively high clock speeds, and architectural tweaks may help them to surpass Northwood performance. You're still looking at relatively equivalent performance for around $100 a CPU, which compares favorably to the higher end Northwood cores of the past.

If you're in the market for a value system and you feel the need to purchase a 64-bit processor, we'd recommend that Intel buyers get a motherboard that uses the 945P or 945G chipsets. If you don't feel the support for dual core processors is important, we'd still recommend 915G/P as being the next best alternative. We would stay away from the 915GV/GL/PL chipsets as they have limitations that make them unattractive; not to mention the fact that those chipsets are almost EOL by now too. 915GV is like 915G, but no external graphics port is provided. 915GL has the same problem, but it only supports DDR memory instead of DDR or DDR2. Finally, 915PL supports an external X16 PCIe slot but eliminates DDR2 support and allows the use of 1 DIMM per memory channel, limiting you to a maximum of 2GB RAM. The bottom line is that the P or the G versions are what most mainstream users will desire. There's also the 955X chipset on the high end, which allows the use of up to 8GB of RAM. Those who really need the increased address space of a 64-bit OS will likely want the option to use more than 4GB of RAM as well.

Final Thoughts

Most of the major releases of 2005 have now occurred, and other than a speed bump or two, there's not much else awaiting Intel owners (at least in the desktop market) this year. 2006 has quite a bit more in store. We haven't covered the mobile section, but many expect to see the dual core Pentium M Yonah available for the desktop as well as mobile markets. Beyond that, we're all waiting for Intel's answer to the performance conundrums of the past year, where they officially lost the performance crown to AMD and haven't been able to regain it. The change to 65nm processes will likely have some advantages, but the real counterattack is going to come in the form of the next Intel architecture. We've given some speculation as to what may be present, but most of the real details are still closely guarded secrets.

For nearly 25 years Intel was the leader in PC processor technology and performance, and we have a suspicion that they will be pulling out all the stops to regain that lead in 2006. The fact that they still lead in profits and market share gives them a lot of resources they can apply to that goal, and we eagerly await additional details of the new architectures. AMD will naturally have their own new processors and architectures, but we know even less about K9 than we do about Conroe. Waiting is the hardest part, unfortunately.

Thinking About Conroe
Comments Locked

33 Comments

View All Comments

  • JarredWalton - Friday, August 12, 2005 - link

    Heheh... 45nm? Let us reach 65nm first. ;)

    The roadmaps don't typically go that far out. Once the transition to 65nm is complete, we'll probably start getting information on their 45nm transition. Rough guess would be that it will launch around 18 months after 65nm, so mid-2007 give or take.
  • nserra - Wednesday, August 17, 2005 - link

    65nm will put intel in line with what AMD have already achived with 90nm.
  • NFS4 - Wednesday, August 10, 2005 - link

    I can't wait for the Intel Cornrows :D
  • BitByBit - Thursday, August 11, 2005 - link

    I'm interested in what AMD's response to Conroe will be.
    If Conroe is indeed going to be a wide-issue, efficient design, then its average IPC should easily exceed that of the K8, while its longer pipeline (in comparison with K8/Dothan) will enable it to hit higher clock speeds. The lessons Intel learned with Netburst will likely compliment its Next Generation architecture nicely, such as the importance of good branch prediction, along with innovations such as Trace Cache.

    If we assume Conroe will be released at speeds in the lower 2Ghz range initially, then AMD should have time to hold out until it is ready to release K10.
    The question is: what will K10 bring us?
  • segagenesis - Friday, August 12, 2005 - link

    I would argue that AMD's response *was* the K8. It seems that Intel is playing catch up as far as architecture goes and were not going to see these new cpus for a long time still. As long as they dont come out and say "sorry, no more x86 even though the entire damn world still uses it".
  • nserra - Wednesday, August 17, 2005 - link

    Maybe the K8 on socket M2 will come with some surprises, that just the DDR2 support.
  • ZobarStyl - Thursday, August 11, 2005 - link

    Yeah, I'm more interested in what the K10 can do better that what Conroe finally just manages to get right. Here's hoping AMD has something more than just clockspeed and cache updates coming.
  • reactor - Friday, August 12, 2005 - link

    eliminate the southbridge? ;D
  • coldpower27 - Wednesday, August 10, 2005 - link

    Yeha I am really interested to see how this 4th architecture will relate to the other 3 Intel has.
  • Doormat - Wednesday, August 10, 2005 - link

    The real question is how much ILP can the chip squeeze out of the code (and compilers). If intel can get more ILP and non-dependant instructions dispatched to the execution units, then they'll be ahead. I just dont know that there is more to ILP to get out of current code with the technologies known about and used in today's processors. Otherwise, wider execution paths would help only if there was Hyperthreading (or some derivative) available to process two threads at once, and fill up all the execution units with instructions to perform.

    Otherwise you might as well just use the extra die space and go multicore or hybrid multicore (main cores plus specialized cores for TCP/IP offloading, encryption, etc).

Log in

Don't have an account? Sign up now