Comments Locked

48 Comments

Back to Article

  • Spajky - Saturday, May 14, 2005 - link

  • Spajky - Saturday, May 7, 2005 - link

    Some comments:
    http://www.anandtech.com/cpuchipsets/showdoc.aspx?...

    >WinRAR 3.40
    Pulling the hard disk out of the equation, we can get a much better idea of which processors are truly best suited for file compression<
    >The WinRAR test is particularly memory bandwidth intensive, so the move to a platform that can feed the Pentium M adequately increases performance tremendously. However, even with the boost, the best that the Pentium M can do is match the performance of Intel desktop CPUs. It still can't touch the Athlon 64s<

    Data compression, WinRAR 3.42, KB/s - Irrelevant CPU bench/graph !!!
    It can be treated as a real life memory subsystem benchmark instead !

    WinRAR´s built_in benchmark & hardware test" is NOT a Data Compression Bench :
    some tests/benchmarks & explanation HOW IT WORKS, here:
    http://freeweb.siol.net/jerman55/HP/benchMem.htm
  • Spajky - Saturday, May 7, 2005 - link

    Some comments:
    http://www.anandtech.com/cpuchipsets/showdoc.aspx?...

    >WinRAR 3.40
    Pulling the hard disk out of the equation, we can get a much better idea of which processors are truly best suited for file compression<
    >The WinRAR test is particularly memory bandwidth intensive, so the move to a platform that can feed the Pentium M adequately increases performance tremendously. However, even with the boost, the best that the Pentium M can do is match the performance of Intel desktop CPUs. It still can't touch the Athlon 64s<

    Data compression, WinRAR 3.42, KB/s - Irrelevant CPU bench/graph !!!
    It can be treated as a real life memory subsystem benchmark instead !

    WinRAR´s built_in benchmark & hardware test" is NOT a Data Compression Bench :
    some tests/benchmarks & explanation HOW IT WORKS, here:
    http://freeweb.siol.net/jerman55/HP/benchMem.htm
  • Spajky - Saturday, May 7, 2005 - link

    Some comments:
    http://www.anandtech.com/cpuchipsets/showdoc.aspx?...

    >WinRAR 3.40
    Pulling the hard disk out of the equation, we can get a much better idea of which processors are truly best suited for file compression<
    >The WinRAR test is particularly memory bandwidth intensive, so the move to a platform that can feed the Pentium M adequately increases performance tremendously. However, even with the boost, the best that the Pentium M can do is match the performance of Intel desktop CPUs. It still can't touch the Athlon 64s<

    Data compression, WinRAR 3.42, KB/s - Irrelevant CPU bench/graph !!!
    It can be treated as a real life memory subsystem benchmark instead !

    WinRAR´s built_in benchmark & hardware test" is NOT a Data Compression Bench :
    some tests/benchmarks & explanation HOW IT WORKS, here:
    http://freeweb.siol.net/jerman55/HP/benchMem.htm
  • Anemone - Sunday, April 17, 2005 - link

    Curious how the XPS Gen2 would have faired in this battery of testing... the 915M seems to slightly better exploit the P-M from what I've been seeing, even though the XPS doesn't really focus on things other than gaming. However it would show what a performance focused chipset (and one that is meant to attempt to bring out the most in Dothan) is able to do under these same conditions. Yonah seems to be the magic juice though, but its sad that is really so far away from market. Intel would do well if they could bring Yonah faster to market, even if they had to keep speeds to the 2.2-2.4 range to do it.

    Quite an interesting article, and one I read carefully on every point.

    ty
  • Calin - Tuesday, March 29, 2005 - link

    An overclocked PM on top of the competition - even in a single benchmark? This chip is a big win for Intel, too bad that the big money come from the laptop world, where there is no competition. This is a guarantee for never decreasing prices for the Pentium M platform
  • Zebo - Monday, March 28, 2005 - link

    Why's it so expensive? As far as overclocking, I don't see as it has value compared to A64, an already better rounded processor. You get a A64 3000 (which BTW has PCIe support) for $145 slam it to 2600Mhz pretty easy, 2900Mhz when Veince comes and it will destory any clock you can get out of PM. $145 super screamer :::slobber:::

    Meh. I'm not as excited as I once was about this chip. Everyone was saying how it's bandwidth staved in the 855 reveiws, turns out, yet again this was wishful thinking for the PM crowd desperate to see any light at end of intel tunnel. I notice no change in benchmarks with added BW.:|
  • fitten - Sunday, March 27, 2005 - link

    #33, there's also the issue about how many data pins are exposed to the outside world. System memory DDR is 64-bits wide, as is the data bus external to the Pentium-M. Having dual channel (basically 128-bit wide memory) memory will help because the memory controller can read, in effect, two times the width each clock, but it still takes two transfers to get it across. The Athlon64 (S939 and S940) have 128-bit wide paths to memory and can transfer the entire width each transfer.
  • valnar - Sunday, March 27, 2005 - link

    I think many people, including Anand, are missing the point of the Pentium M. It was made to be a low powered, low heat processor. The fact it can even HANG with the big boys at their level is a remarkable achievement. (You can't say that about the VIA C3 processor.)

    Megahertz for megahertz, and watt for watt, it is easily the best processor on the market. You're comparing that against 3.8Ghz CPU's!! Of course it won't be first place. After all, it's just a 2.13Ghz. It uses 1/4 the power of the highest P4's. Compared against any other processor which comes close to those speed/power specs, it'll wipe the floor with them.

    If Shuttle made their XPC's with this processor, I'd buy it in a heartbeat.

    Rob
  • Slaimus - Sunday, March 27, 2005 - link

    The real gem is the Celeron M Dothan. Need some benchmarks for that chip.
  • ElFenix - Sunday, March 27, 2005 - link

    i'm confused, were all the benches done at 5:4 memory ratio? how is the performance at 1:1? if the added bandwidth from running 5:4 can't be used, isn't it better to run synchronus?
  • joe360 - Saturday, March 26, 2005 - link

    I have a socket-478 P4 2.8 Presscott in a laptop, is there a way I can get the Dotan in there instead?
  • Hardtarget - Friday, March 25, 2005 - link

    Wow thanks for the update Anand. I just read both of these articles and was extremely impressed with them.

    Real good work, I can't wait for the Yonah just to see what happens!
  • drewski - Friday, March 25, 2005 - link

    i agree w/ posts 9, 18, & 28 regarding the changing of multiple variables making some of the comparisons between architecture's a bit of a guess.

    thanks for your post, Anand. it helps clarify things, though having the benches would help. maybe you can cut and paste it into the article! ;-)

    still, i think this was less of an oversight than that terrible article on the OCZ Vx memory by Wesley. has that ever been corrected?

  • Anand Lal Shimpi - Friday, March 25, 2005 - link

    For those wondering about the 865 vs 855 comparison, one thing I tried to stress in the article (especially during the benchmark comments) is that in many cases the performance improvement was barely anything, thus meaning that the magic solution to the Pentium M's desktop viability was far from just add more memory bandwidth. The reason that point is important is because after the first article, many assumed that more memory bandwidth and a faster FSB would make the Pentium M infinitely more competitive. But look at media encoding and the majority of the MCC tests and those two improvements didn't change things all that much.

    The Pentium M 770 has a 6.65% increase in core clock speed over the Pentium M 755, in any benchmark where the 770 offers a greater than 6.65% increase in performance you know that performance improvement is due to more than just the clock speed, mainly the faster FSB and the correspondingly higher memory bandwidth. Since the 855GME is already memory bandwidth limited with a 400MHz FSB, increasing the bus frequency to 533MHz won't do anything for performance on that chipset, so that's why you can attribute the performance gains that do exist to the 865 platform as a whole. Also keep in mind that most applications rarely scale at a 1:1 ratio with CPU clock speed; even some of the more CPU limited applications will scale at a 50% rate with clock speed - so really what you're looking for are any performance improvements greater than about 3%, those are due to the 865 platform.

    There are a few areas where the added memory bandwidth does make a huge difference - mostly in the workstation level SPEC tests.

    So although we didn't run direct comparison numbers between the 855GME and the 865, there is enough information in this article to (as many of you have already concluded) find out that for the most part, the added memory bandwidth does very little (on the order of a few percent). The real benefit of the ASUS solution is that you get a much more mature motherboard, more stable, and a lot cheaper. I apologize if I didn't properly stress this information throughout the article and in the conclusion.

    Take care,
    Anand
  • PrinceGaz - Friday, March 25, 2005 - link

    #31- the P-M 770 has a 533MHz FSB. That's how fast data moves to and from the northbridge memory-controller. The CPU doesn't care about whether the chipset memory-controller is single or dual-channel. Using dual-channel DDR333 provides 667MHz of memory bandwidth for the northbridge, of which the P-M 770 will utilise a maximum of 533MHz (when not overclocked), so it is taking advantage of dual-channel.

    Unfortunately, as others have pointed out, the article was very poor because there was no comparison of the same P-M on the i855 (single channel) and i865 with adapter (dual channel) chipsets. The purpose of the article was to see what effect the adapter and i865 had on performance. Of course the P-M 770 on the i865 was faster than the P-M 755 on the i855, because the P-M 770 has a higher core speed. What you did was like comparing a S754 3000+ (2GHz) and a S939 3500+ (2.2GHz), and concluding that S939 provides a good performance boost over S754 because it is dual-channel, whilst overlooking the clock-speed difference which has a much greater impact.
  • classy - Friday, March 25, 2005 - link

    I don't even see this even as a viable solution. It is a real dog in many instances and the biggest problem is you have to overclock it. Now for many of us that is not a problem, until you factor in that your talking about a rather extreme overclock, even for an Intel Processor. If you can't reach these speeeds with a low priced one, only a fool would buy one. Especially now since I can go over to Zip and buy a retail AMD 64 4000+ for $550 dollars. And don't forget AMD 64 chips overclock fairly well too. If this was 2 years ago it would be viable or even if was say the priced like an XP or 64 3000+ chip you might consider it. But given the necessiity that it has to be overclocked to get good performance, high price, and extremely limited platform support I see no reason whatsoever to buy a Pentium M. And I am running an Intel setup as I type this. They have just fallen behind and it doesn't look like they are going to catch up any time soon either.
  • fitten - Friday, March 25, 2005 - link

    Something to remember about the PentiumM, while the chipset it sits on may be dual channel memory, the PentiumM itself, is not. It's much like the Athlon XPs and the nForce2 chipset (CPU is single channel, chipset is dual channel). So, you really aren't comparing a "real" dual channel processor like the S939 and S940 Athlon64/Opterons. The PentiumM can only pull data in one channel width per read, regardless of the chipset it sits on. The S939/S940s can pull in two channel widths per read.

    That being said, there definitely seems to be some improvement in going to the hybrid dual channel boards.
  • Quanticles - Friday, March 25, 2005 - link

    What about HL2 preformance when it's not overclocked?
  • xsilver - Friday, March 25, 2005 - link

    Where this cpu would really work is in a xpc system where extreme performance isnt really nessessary... but think of running the whole pc on only the 1 PSU fan
  • merkmal - Thursday, March 24, 2005 - link

    I don't understand why there wasn't a direct comparison here between the i855 and the i865. It seems very un-anandtech like to go on and on about how this is such an improvment over the i855 setups and then not even show 2 of the same clocked processors in both setups to show if that really is the case. Testing a "faster" setup with a processor that is already known to be faster simply by the fact that it is clocked at stock speeds faster isn't a very good comparison or argument for better performance either.

    I understand the fact that lots of readers are interested in using a Pentium-M on the desktop and would like to know how it compares to other desktop processors, but I thought that was clear from the previous article on exactly that. This article should have been only Pentium-Ms in a variety of setups. It's easy to check back at the old article and see relatively how the new setup compares to the other desktop only processors.

    I'm just very dissapointed in this article. I appauled you on the reviewing of the adapter, but think the comparisons drawn were just shoddy and un-thought out.
  • VIAN - Thursday, March 24, 2005 - link

    Can't wait for Intel to do away with the P4 and step in with a suped-up PM.

    Or at least do away with the EE, market the PM as a multimedia chip and the P4 as a workstation chip.
  • kmmatney - Thursday, March 24, 2005 - link

    NewEgg doesn't sell the 770 cpu, and it would be incredibly expensive if they did. Can you test the cheapest P-M, and see how it overclocks?
  • PandaBear - Thursday, March 24, 2005 - link

    Yeah PM is the way to go in the future. P4 architecture is getting way too inefficient and burn way too much power that it is not going to grow from where we are now. I am sure Intel is fully aware of this but keep it under the cover to avoid tanking the P4 sales. What would the customer think the PC they spend big bucks for is slower and hotter than a laptop CPU hacked from last generation technology, that would be a slap on the face.

    Anyhow, I still think A64 has better architecture for long term growth. Now if they come up with integrated North Bridge that has 20 PCIe lane in replacement of the HT port....
  • RockHydra11 - Thursday, March 24, 2005 - link

    I don't understand the "desktop killer" thing...It never was intended for the desktop.It was centered to compete with anything else that was on the notebook platform, so Intel was not generating it to perform well against desktop processors, let alonre FLAGSHIP desktop processors. It is what it is, and that's that. Yonah is going to be the one centered toward real desktop performance.
  • Mingon - Thursday, March 24, 2005 - link

    Would have been nice to have run in both single and dual channel configs so as to see if the chip is bandwidth starved.

  • 68GTX - Thursday, March 24, 2005 - link

    Looks like Legit reviews is currently testing with a new beta bios with voltage options.

    "Part 2 is being updated... ASUS-USA sent me over a new BETA BIOS that is awesome. Fixes the performance issues and the voltage issues that were noted in the article... Take a look at the new voltages..."

    http://forums.legitreviews.com/viewtopic.php?t=157...
  • Mangler - Thursday, March 24, 2005 - link

    Legit Reviews also has this adapter reviewed today at: http://www.legitreviews.com/article.php?aid=181

    They compared an Intel 770 CPU on both the DFI 855GME-MGF motherboard and the ASUS P4P800SE for an apples to apples look. (i855GM versus i865PE)

    They focus more on overclocking and use of the kit. A must read for any enthusiast.
  • Goi - Thursday, March 24, 2005 - link

    #12, you can't say that tha Pentium M is based on old technology. There are many power saving techniques on the Pentium M that aren't implemented in the P4, both in the microarchitectural level, circuit level and logic level. The Pentium M is a hybrid between the P3 and the P4, but to say that it's closer to the P3, I'm not sure I agree with that. It does use executation units that are simialr to the P3's, but there are many areas where they are different, including the issue/control logic, which is a BIG part of microprocessors nowadays(and really, in the past decade or so).
  • mrmorris - Thursday, March 24, 2005 - link

    I'd like to point out that while the Pentium-M offer sub-desktop performance at worst, it does so with out heating up the room or requireing earplugs to dampen the fan noise! Therefore, as an office/coorporate workstation it fits perfect.
  • Avalon - Thursday, March 24, 2005 - link

    In Soviet Russia, the Pentium-M owns you!
    In all seriousness, though...I was reading the benchmarks and wondering where the 855GME desktop P-M 770 benchmarks were. You only had the 770 on the Asus board. While this is all fine and dandy, it doesn't show us the full extent of the benefits of the Asus pin adapter over using an 855GME desktop board. While you could extra some data, I would have liked 770 desktop benches as a comparison. All in all, though, the Asus adapter is definitely nice due to the price alone.
  • Wonga - Thursday, March 24, 2005 - link

    I don't think anyone can criticise Intel too harshly for releasing the Netburst architecture. Yes, Willamet stank, and Prescott isn't exactly an efficient core, but a Northwood processor was the best CPU money could buy for about 18 months before the K8 hit the scene. So, it doesn't really matter how Intel got there, but Netburst was the architecture to have for those 18 months.

    Anyway, Anand, I'd appreciate it if you could see if those adaptors would work on other S478 motherboards :)

    Oh, and thanks for a great article! Perhaps that Pentium M horse that was beaten so much can now finally rest in peace!
  • sprockkets - Thursday, March 24, 2005 - link

    While the boards and tech mentioned here are nice, why not also test some of the PM mini-itx boards at www.logicsupply.com and see how badly it can kick an Mac Mini's ass? OR, how well it can perform in such small space with little heat and noise output?

  • xtknight - Thursday, March 24, 2005 - link

    amazing it beats the fx-55 at q3 source compile. maybe i need to get my eyes checked but does that say INTEL?
  • mkruer - Thursday, March 24, 2005 - link

    Here is what I get out of this,

    1. P-M is better clock then the P4 and apparently the AMD64, (at least in some applications)
    2. Future versions of the P-M while adding better FP and SSEx Instructions will still not have 64-bit technology.
    3. Adding better FP and SSEx, will also increase the minimal thermal rating, resulting in a lower maximum over clocking ability, and higher heat dissipation

    All and all, it looks to be about the same as AMD64, when all the upgrades are added in.
  • ncage - Thursday, March 24, 2005 - link

    #5 It probably wouldn't be that good for intel to drop Pentium M prices. Yes there would get more sales from techies like us but that wouldn't increase there sales that much. Where they get sales would be from labtops and their profit margins would drop for that that is why overall it would be stupid for intel to drop the prices on them.
  • mlittl3 - Thursday, March 24, 2005 - link

    I'm sorry but I have to say a few more things.

    I counted up all the benchmarks (not including overclocking ones) and the 2.13 GHz PM beats a 3.2 GHz PIV in 22 out of 33 benchmarks. For a 1 GHz+ underclocked processor, the PM wins in two-thirds of the benchmarks. Now correct me if I'm wrong but doesn't the 2.13 GHz PM consume 25W of power and the 3.2 GHz PIV consume around 100W. That's four times the power for 66% less performance.

    Multiply that 4x waste by all the PIV's that Intel sold and we must have wasted megawatts upon megawatts of power for nothing. You can't say its technology improving because the PM is based on old technology.

    Intel wasted so much electricity and polluted so much more of the environment because what it couldn't save face when it released the 1.13 GHz coppermine PIII and had to recall it because of architectural problems. Therefore, it had to release the PIV to make itself look better from a marketing standpoint.

    This just blows my mind.
  • EODetroit - Thursday, March 24, 2005 - link

    Nice article. While now we know that the Pentium M probably isn't practical for the desktop in most situations when price is considered, this review is important because it gives us something to compare the Yonah processors to when they come out. And those of us that were curious about the P-M on the desktop finally have some answers, so thanks for that.

    How high could it overclock, anyways? It sounded like you got it up to the point where the memory would be at DDR400 with the 5:4 ratio, and called it good. But how much more can it be pushed? What about with better cooling?
  • Googer - Thursday, March 24, 2005 - link

    Thank God there are no Russian Jokes on this page!
  • Googer - Thursday, March 24, 2005 - link

    I did not see any benchmarks of the Pentium M 770 on the 855GME so we could compaire APPLES to APPLES the only system it was run on was 865, It's a bit of an unbalanced compairison. Anand, Just how much of a differance does 865 offer the P-M 770 over 855?
  • Houdani - Thursday, March 24, 2005 - link

    With updates to floating point calculations and adding another core, Intel will need to think long and hard about putting their desktop chips into premature end-of-life in favor of going forward with the PM as their base product.

    Or, to summarize:

    Blah blah blah nothing new that hasn't already been said before blah blah blather.
  • mlittl3 - Thursday, March 24, 2005 - link

    Anand,

    You completely missed the point of the excellent data you obtained. Of course, this is just my point of view but here is my take on things.

    The Pentium III stopped at 1.4 GHz. The Pentium picked up at 1.5 GHz (not including the low and ultra low voltage versions). We all know that the Pentium M is much more similar to the Pentium III than the Pentium IV. What if Intel never created the Pentium IV and continued improvements with the Pentium III? We would have had the Pentium M three to four years ago.

    Intel screwed us all with its monopoly powers and sold high clock speeds to the masses with no thought about the performance of the Pentium IV. The last four years have shown us just that but no one complains or holds Intel accountable. As you have pointed out numerous times, the capital processor of the Pentium IV series, the Pentium IV EE is a complete waste of money.

    In almost all of your benchmarks, the Pentium M shows almost the EXACT same performance as an Athlon 64 clock for clock. I say again, what if the Pentium M was developed at the time the Pentium III was discontinued? Intel and AMD would have matched clock speeds and we would have a Pentium M around 2.6 GHz right now with the similar performance of the Athlon 64 FX-55. The improvements you mentioned in the conclusion for Yonah (SSE and floating point) would probably already be implemented.

    The Pentium M is THE processor from Intel. We had to wait four years for Intel's monopoly to be weakened but now we have a processor worth something. With multiple cores (each running at the speed of single cores since the Pentium M runs so cool) and all the other improvements from Yonah, that processor is going to be awesome.

    Thank god for AMD challenging Intel with their terrific Athlon 64 architecture. Without them, computer processing would be in the dark ages. Guys, we need to stop supporting companies when they get to a certain size. The market needs to shift or we are going to get software like Windows and processors like the Pentium IV. With an even market share split between at least two companies, technology will excel past our wildest imaginations.

    Okay, I will shut up now. I do want to add one thing. The ASUS adapter does nothing over the Aopen motherboard. If I am not mistaken, you compared a 533 MHz FSB, 133 MHz faster Dothan Pentium M to 400 MHz FSB, slower Dothans (I hope the other processors were Dothans and not Banias). The performance delta between the 770 and the 750 is exactly what you would expect from a faster clocked processor and a faster FSB. The 865 vs. the 855GME had nothing to do with the performance difference. The only advantage of the ASUS adapter is a cheaper overall cost of ownership.
  • bob661 - Thursday, March 24, 2005 - link

    Oh yeah, if you're going Intel, this is the only CPU to own.
  • bob661 - Thursday, March 24, 2005 - link

    Intel really needs to lower the price of this CPU. A 765 is $645 on newegg. I can only imagine what the 770 would cost. If it was more price competitve, the P-M would be an excellent processor choice.
  • rqle - Thursday, March 24, 2005 - link

    i thought it did pretty well clock for clock on majority of the benchmark against the amd64 and did on par or so on gaming against the amd FX chips. Where it exceeds the PM it deal extremely well, and falls really shorts on things it didnt fair to well.

    Price wise for a "Desktop", i still believe AMD64 chip is the way to go. Great notebook chip that is not quite ready for the desktop area yet, need to improve its floating point performance and some desktop area. Did pretty well as gaming chip.
  • clarkey01 - Thursday, March 24, 2005 - link

    Multitasking..lol...

    I mean, your going to get Intel fanboys saying " Its only has a 400 MHZ FSB" and what not. Well, why has it > ? its like saying the FX only has one meg cache, why doesnt it have two ?
  • clarkey01 - Thursday, March 24, 2005 - link

    Mixed bag or what.
  • Aileur - Thursday, March 24, 2005 - link

    All in all seems like a middle of the pack solution. I thought the dual channel would give it a more significant boost but the pentium m seems to stay in the middle of the pack most of the time.
    I would still get it before i ever touched a prescott with a ten foot pole (and im an ex northwood user) but for the price theyre asking for dothans I dont see it being the desktop chip killer i was expecting.

    I wonder though how Intel could clock this thing if it didnt have low power/heat in mind.

Log in

Don't have an account? Sign up now