Please create an account to participate in the Slashdot moderation system

 



Forgot your password?
typodupeerror
×
Intel IT Hardware

Centrino Mobile Equals Desktop Pentium 4 in Speed 251

Spy Handler writes "On Wednesday during the launch of its new Sonoma Centrino Mobile, Intel put on a demonstration running a video game on a laptop. It matched the performance of a high-end Pentium 4 desktop running the same game, declared Intel. The contenders were a laptop sporting a 2.13 GHz Pentium M processor, 1GB RAM, and the Alviso chipset versus a desktop with a 3.6 GHz Pentium 4 with hyperthreading, 1GB RAM, and the Grantsdale chipset. Is this a testament to how far the Pentium Mobile architecture has come, or a sad comment on the clockspeed-pushing design of the Pentium 4?"
This discussion has been archived. No new comments can be posted.

Centrino Mobile Equals Desktop Pentium 4 in Speed

Comments Filter:
  • Both! (Score:4, Insightful)

    by Theovon ( 109752 ) on Saturday January 22, 2005 @09:21AM (#11440937)
    Intel's finally learning the lesson everyone else knew about 5 years ago. Too little, too late? Or can Centrino save them?
    • by Anonymous Coward
      It's a valid point. the question: "Is this a testament to how far the Pentium Mobile architecture has come, or a sad comment on the clockspeed-pushing design of the Pentium 4?"... I'd say the latter. The pentium mobile architecture hasn't come a long way, it's been dragged along by AMD's use of similar technology (hell, and even IBM with its PPC970) to run better at lower clock speeds.

      It's a sad comment on how damned long the clockspeed-pushing went on for.
    • Re:Both! (Score:4, Interesting)

      by 0111 1110 ( 518466 ) on Saturday January 22, 2005 @10:26AM (#11441181)
      Exactly. The only news here is Intel essentially admitting their mistake with the marketing driven P4. For those who are surprised by these results see previous [slashdot.org] stories [slashdot.org] on the subject. See this Doom3 and Far Cry benchmark [gamepc.com] from the link in the first slashdot article and this [extremetech.com] extremetech article and this [x86-secret.com] French benchmark. And these are not the only sources. The fact is that on a modern platform the Pentium M is quite competitive with not only a P4 at nearly twice the clock speed, but also with Athlon64 chips at nearly half the power of even a 90 nm Winchester Athlon64 with a max TDP of either 21 or 29 Watts for the older and newer chips respectively.

      That's not to say that it is competitive in every domain, but for gaming it is tough to beat. And, yes, many modern games do scale with CPU power.
      • I've read some reviews on the Pentium M, and its power requirements are impressively low. I wonder what kind of performance you could get out of it if you overclocked it to the point where its power requirements were similar to the P4. There may be other reasons why that's impossible, but I'm sure you could still overclock it significantly, and that seems like a resonable thing to do for desktops which can afford the power requirements.
        • The same reason Athlon64s and PPCs aren't running at high clock speed. Unless it's doing very little work per clock or has monstrous cooling, the CPU will heat up like a fireball at Pentium 4 clock speeds.
          • Sometimes when you are participating in a discussion on the internet, you have to read. From the parent: "I wonder what kind of performance you could get out of it if you overclocked it to the point where its power requirements were similar to the P4." He said nothing about clock speeds whatsoever. He said run the processor at a speed where it's power usage is equal to that of a Pentium 4. Power usage pretty much has a direct correlation to heat dissipated as long as you ignore minor EM radiation, etc.

            N

      • Exactly. The only news here is Intel essentially admitting their mistake with the marketing driven P4
        Yes I'm sure Intel hates that they drove down AMD market share from 20% to 12% with their marketing driven scheme. Like it or not, keeping the Mhz-Myth alive worked, the mistake was they kept it going one generation too long (Prescott) before making the switch.
        • I honestly don't think even that was a mistake, I just don't think they could turn themselves around any faster than that. The P4 has made them plenty of money and mindshare. If they made a mistake it was itanic.
    • In doing some benchmarking Pentium III's against Pentium 4s a long time ago, it was very obvious the P3 seemed to be much faster than the P4 at similar clockspeed. About the only place that the P4 did much better was 3d graphics. And nowadays, we are moving to snazzy graphics cards with gobs of memory and processing power, so we don't need as much specialized 3d processing on the CPU.

      I am guessing that the Centrino has more in common with the P3, as I haven't had time to dig into the Centrino...but those r
      • Centrino is the combination of Pentium M and a chipset with wifi. With that out of the way, Pentium M is based on the P3 but has very large parts of P4's SIMD engine attached to it, and IIRC the new one goes all the way up to SSE3.

        I sometimes wonder if the PC is going to see the return of the math coprocessor. Since the data used in SIMD operations is stored in wholly separate registers I'd think that you could hang all that stuff out on another chip using some decent interconnect... say, hypertransport.

    • Too late? Hardly. Did Intel lose money on the Pentium 4? They may have lost ground in marketshare, but they're still highly profitable.
  • Not CPU-limited. (Score:5, Informative)

    by Temporal ( 96070 ) on Saturday January 22, 2005 @09:23AM (#11440947) Journal
    Is this a testament to how far the Pentium Mobile architecture has come, or a sad comment on the clockspeed-pushing design of the Pentium 4?

    I think it's a testament to the fact that whatever game they were running doesn't bottleneck at the CPU. Most video games are not CPU-limited beyond a GHz or two.
    • by gl4ss ( 559668 ) on Saturday January 22, 2005 @09:36AM (#11440993) Homepage Journal
      maybe they were using intels graphic chips too? that would explain it.

      also. what kind of idiot they got in marketing? the whole comparision is just saying "look, our top of the line desktop chip is shit for gaming!"(not totally true even).
      • Not really. It says: "Don't cry if we phase out the Pentium IV line. Pentium M processors will be a valid alternative, and we might even ramp them up to Pentium IV clock speeds with further increased performance."
    • Benchmark time (Score:5, Interesting)

      by Zeinfeld ( 263942 ) on Saturday January 22, 2005 @09:44AM (#11441029) Homepage
      I think it's a testament to the fact that whatever game they were running doesn't bottleneck at the CPU. Most video games are not CPU-limited beyond a GHz or two.

      Its time to do what we used to do back in 1990 before the Pentium arrived, run benchmarks to determine how fast the machine is.

      The only interesting thing about using a game as a benchmark is if the thing will run. Its not unusual to find that a game simply does not run on a laptop.

    • by Anonymous Coward on Saturday January 22, 2005 @09:52AM (#11441048)
      The sad thing is, they were testing using Solitare.
    • I wouldn't go that far. It was generally well reported at the release of the Pentium 4 CPU several years ago that an equivalently clocked Pentium III was considerably faster. The Pentium M platform is based on the Pentium III architecture, which is more performance driven than the Pentium 4. The Pentium 4 was designed so that the clock speed could be ramped high, quickly. To do that they had to take a performance hit.

      But really, where's the news here? AMD has been able to create Athlon 64 CPUs that p
  • by holymoo ( 660095 ) on Saturday January 22, 2005 @09:24AM (#11440949)
    hmm I would like to know which video game it ran to get equal performance. Also, was the game software rendered or was there a graphics chipset involved?
  • by MarcoPon ( 689115 ) on Saturday January 22, 2005 @09:26AM (#11440956) Homepage
    > Is this a testament to how far the Pentium Mobile architecture has come, or a sad comment on the clockspeed-pushing design of the Pentium 4?

    No, it's probably only a testament on not showing enough info about the benchmark system/conditions to provide any useful technical data, but only marketing data.
    Who know? Maybe the game was simply framerate limited by the similar integrated graphics chipset.

    I'm not saying that the Pentium M isn't fast, or as fast as a desktop P4; only that probably that demo don't prove that.
    Just my 2c.

    Bye!
    • Here

      http://www.heise.de/newsticker/meldung/55276

      support Intel pretty well.

      If you don't get the German, don't worry, it's all Geek to me.

      Now please give me fast disks on a laptop. One gig on mine plays away as a RAMdrive (heavy P'shop load) and it runs way too hot for comfort.
      • Most interestingly they state that the Pentium M performs as good as a Pentium 3,8 GHz or Athlon 64 4000+ when running the SPEC-benchmark CINT2000.

        So this really seems to be more than a marketing trick.

        I wonder if they'll merge the desktop and mobile brachens sometime. Afterall power consumption on desktop systems really is out of all proportion to speed. Since I'm quite sure that people won't buy slower systems (even if they don't need faster ones) it's rather obvious that they'll have to use more effici
    • Is this a testament to how far the Pentium Mobile architecture has come, or a sad comment on the clockspeed-pushing design of the Pentium 4?"

      What about "both"?

      Or, of course, as the parent points out, perhaps the bottleneck is somewhere completely different. Maybe the processor speed is less important than something else (gasp!).

      Personally, I'm much more excited by increases in network, disk and bus bandwidth than CPU. I don't spend much time waiting for my CPU; I spend time waiting for data to ge

    • Who know? Maybe the game was simply framerate limited by the similar integrated graphics chipset.

      Or maybe they left VSync on!

    • No.

      Those that pay attention to mobile benchmarks can assure you, Pentium M chips have been roughly 1.5x faster than Pentium 4 chips on a per-Mhz basis. So, a 2GHz P-M performing as well as a 3GHz P4 is hardly surprising.

      It is impressive, though, as the P-M is incredibly energy efficient. If it were cheaper, I'd get one in my next desktop and get rid of all those fans...
  • Drivers (Score:4, Insightful)

    by StevenHenderson ( 806391 ) <stevehenderson&gmail,com> on Saturday January 22, 2005 @09:35AM (#11440987)
    Is this a testament to how far the Pentium Mobile architecture has come, or a sad comment on the clockspeed-pushing design of the Pentium 4?"

    I am sure that they got together with NVidia and came up with some crazy optimized drivers (read: cheating).

    Sounds like Intel is ready to write off the P4 as done for, and is putting all of thier eggs in the Centrino basket until the launch of their dual-core chips...

  • ...Intel confirms that its desktop chips and chipsets suck?!

  • that your mature, fast chip that people have been designing for for the better part of a decade combined with spanking new memory and hardware works well! my god, it boggles the mind! carl not like that's stopping me from representin with a wack AMD64 chip and gear that makes the inside of my tower a good substitute for a microwave oven(tea, anyone?))
  • by SharpFang ( 651121 ) on Saturday January 22, 2005 @09:38AM (#11440997) Homepage Journal
    ...with the fan attached or without?

    I had the "pleasure" of performing a heavy number crunching on a P4 laptop. Luckily it was winter and one of the rooms in my house is unheated. Leaving the laptop there (temp. about +3C) with bottom lifted off the floor by some books to allow free access to the built-in fan prevented it from entering thermal throttling mode and allowed it to run at full speed...
    • A badly designed laptop isn't intel's fault. Granted P4 power consumption is pretty ridiculous but it is possible to design efficient laptop cooling solutions. The problem is usually some jackass in marketing who sold some other jackass on making a P4 laptop that is barely big enough to hold and cool a Mobile P3.
  • by Spacejock ( 727523 ) on Saturday January 22, 2005 @09:38AM (#11440998)
    I 'upgraded' from a P3-1 ghz to a P4-2.26 ghz and noticed hardly any difference. I upgraded from my P4 to an Athlon64 3400+ and it not only smokes it, it also has a variable clock speed which only ramps up when needed.

    I've been a loyal intel user since the Pentium 90 came out, but after building several cheap and stable AMD systems for friends and family I took the plunge myself, and I'm more than happy.
    • Sounds like typical system bottlenecks to me, as others have posted.

      For a long time now, CPUs have not been the bottleneck in a typical computer setup. Even more so with laptops.

      Generally, you'll get much better ROI if you upgrade the following components/subsystems in this order:

      Disk latency
      Disk throughput
      Memory throughput
      Memory latency

      This all depends on what you use your system for, of course. But for the average computer performing a mix of home/office tasks, this is roughly where things need to g
    • Well, the Pentium 4 solves complex differential equations like a Pentium 3 at half the clock frequency, so if you were exercising the FPU, it would run as fast as a 1.13GHz Pentium 3, which would explain why you didn't notice any difference...
  • As an earlier poster mentioned, most newer games depend more on the GPU than the CPU; anything over 2Ghz is almost overkill.
    Intel and AMD are in the awkward position of needing to create a market for new processors in a world where a 1Ghz processor will do most office tasks brilliantly. They pushed speed, speed and more speed for so long that the average consumer doesn't give a whit about HyperThreading or anything else. Tech heads and researchers and universities are different, but is that enough to support to very large chip manufacturers forever?
  • by The Munger ( 695154 ) on Saturday January 22, 2005 @09:42AM (#11441018) Homepage
    Is this a testament to how far the Pentium Mobile architecture has come, or a sad comment on the clockspeed-pushing design of the Pentium 4?

    Or perhaps a testament to how fill-rate limited the game was? Honestly, what was the game? Doom 3? Or Monkey Isnald 3? It makes a difference.
  • by antifoidulus ( 807088 ) on Saturday January 22, 2005 @09:43AM (#11441026) Homepage Journal
    They don't really mention any of these factors about the laptop. What good is having good performance if it weighs 10 pounds and has a battery life of an hour?
    • by Slack3r78 ( 596506 ) on Saturday January 22, 2005 @09:54AM (#11441054) Homepage
      That's part of the beauty of the Pentium M: most of the notebooks based on it are in the 6lbs or less range, and I've yet to see one with a battery life of less than four hours.
      • That's part of the beauty of the Pentium M: most of the notebooks based on it are in the 6lbs or less range, and I've yet to see one with a battery life of less than four hours.

        My Dell Inspiron 500m (Centrino, first generation) has a battery life of about 1h 40m... Windows or Linux both, and yes, cpu scaling does work.

        • Well, dell laptops are __CRAP__...
          Cheap plastic construction, corners cut at every opportunity, comparable quality but higher price than the cheapest of brandless laptops available from asia..
          Theyre unreliable, the battery life is poor, the build quality is terrible, in the cheap nasty ones you cant even remove/replace the cdrom etc, virtually none of them have onboard serial ports, and linux compatibility with dell laptops has been getting worse and worse... One bios upgrade for the latitude 2500 breaks X1
  • Answer (Score:2, Funny)

    by Anonymous Coward
    Is this a testament to how far the Pentium Mobile architecture has come, or a sad comment on the clockspeed-pushing design of the Pentium 4?

    Yes.
  • by StandardCell ( 589682 ) on Saturday January 22, 2005 @09:54AM (#11441056)
    As I had mentioned in a previous comment [slashdot.org], the front side bus speed is the biggest limiting factor on Pentium M processors. The day we see an 800MHz FSB Pentium M is the day the direct MHz comparisons will apply (i.e. 1.8GHz P-M vs. 1.8GHz A64). Even the Tom's Hardware Guide review [tomshardware.com] of the new Sonoma chipset for P-M shows fairly marginal gains and proves the FSB is the limitation, PLUS they do the stupid thing here and put in DDR-2 which does little for performance but increases system costs.
    • by pla ( 258480 ) on Saturday January 22, 2005 @10:39AM (#11441238) Journal
      the front side bus speed is the biggest limiting factor on Pentium M processors.

      Thank you... So far, I consider this the only "insightful" comment in this entire topic.

      In terms of raw performance, though, Anand and Tom (of which you mention the latter) have both done "real world" tests that don't include the GPU as the bottlenext, and found that, for heavily CPU-bound tasks (such as compression, which also eats memory but mostly just CPU), the Pentium-M (Dothan, in particular) holds its own against both the Prescott (P4) and the Athlon 64. On some tasks any of those three would take the lead, though the Dothan does only take 2nd or 3rd most of the time (but still beats the Athlon XP and the Northwood P4).

      For second best, and less than a quarter of the power consumption (less than a tenth when idle) for comparable performance, I fully plan to get a Pentium M as my next desktop upgrade. I care about raw performance, but I also care about my electric bill and about having something that sounds like a jet engine three feet from my head (lower power = less cooling needed = quieter).


      PLUS they do the stupid thing here and put in DDR-2 which does little for performance but increases system costs.

      Strange opinion... Yes, it increases the system cost a tad, but consider it from two POVs...First, since the Centrino line primarily targets laptops, 2.5V vs 1.8V means significantly lower power consumption (and correspondingly less need for active cooling, making battery life even better). And second - DDR2 picks up where DDR stops, FSB-wise... You could just as well say the original P4s did nothing for performance over the best-of-breed PIIIs, but after three core gens and a doubling of the clock speed, no one would now claim a "modern" PIII will outperform a modern P4.
      • by BoomerSooner ( 308737 ) on Saturday January 22, 2005 @11:29AM (#11441476) Homepage Journal
        Isn't the Pentium-M based off the PIII core? In that case a PIII that is modern as you put it is the Pentium-M which matches or outperforms the P4.
        • Isn't the Pentium-M based off the PIII core?

          No. Or at least, not proveably so.

          Intel has released very few architectural details of the Centrino line. From what little the public actually knows about it, it does seem more similar to a PIII than a P4, but by all (credible) accounts, it uses a complete core redesign, optimized based on different criteria than most desktop CPUs. As a result, it consumes a reasonable amount of power, and the performance seems like almost an unintended perk.
      • Other chip design companies have found that some of the "de rigeur" optimizations either don't buy anything or cost so much silicon that applying them forces the designer to pessimize something else.

        An example I know about from an old version of Samba is that using branch prediction to compile a binary that expects all debugging code to be branched-around shows no detectable speed improvement.

        It turned out that a complex debug macro expanded to a chunk of code which was bigger than a cache line on the

      • but I also care about my electric bill and about having something that sounds like a jet engine three feet from my headYou should also consider the noise of hard drives. I'm carrying 4 old hard drives (60-160GB) into my new machine every time I upgrade, and the hard drives are always the noisiest component. I always put resistors on my fans. Two of them (The older ones probably) make a high-pitched whine. Make sure you get fluid bearing drives. I can't afford to part with 160 GB of space just for nois
        • I can't afford to part with 160 GB of space just for noise reasons, but I'm sure a lot of other people could.

          You might want to take the same approach to this problem that I used...

          Set yourself up a cheap Linux box as a fileserver, throw your big, cheap, noisy drives in there, and keep it in a room you don't use (guest bedroom?).

          Then on your "real" machine(s), you don't need a huge drive... I currently use a 40GB, just because you can't even get smaller ones anymore (well, you can, but you don't actua
    • PLUS they do the stupid thing here and put in DDR-2 which does little for performance but increases system costs.

      Well presumably DDR-2 will decrease in price eventually. At the moment cost is certainly an issue. But don't forget that DDR2 is lower voltage and saves power, which for a mobile chipset is extremely important. Whether it makes sense for a desktop chipset is another question. I just hope Aopen continues to release desktop motherboards for the Pentium M. It would be nice to see one based on this
  • This is noise (Score:2, Interesting)

    The poser of the question (that started this thread) signals his ignorance of microprocessor design and underscores what AMD has said all along, and everyone else who hasfollowed the industry since when there was much more competition in the microprocessor, namely you can't juxtpose microprocessors on clock frequency alone. Anyone remember the Intel i860? Or when MIPS was a stand alone company competing against Intel (seemingly). If you say no to these things, that probably explains why you're even ponderin
  • by heffrey ( 229704 ) on Saturday January 22, 2005 @10:07AM (#11441094)
    One area where Pentium M is fantastic is in scientific and engineering simulation software. My company produces such a piece of software called OrcaFlex (www.orcina.com). The code is mainly old fashioned 8087 FPU instructions doing 3 dimensional vector operations.

    In the past few years clock speed has become much less important than memory architecture in determining how fast the simulations run. Of current architectures P4 stinks and is comprehensively stuffed by Opteron. However, PM even beats Opteron. Our fastest machine for OrcaFlex is a DELL Centrino notebook! This just edges out our top of the range Opteron workstation.

    Has anyone else out there seen anything similar with other applications?
  • by cjc1103 ( 787208 ) on Saturday January 22, 2005 @10:08AM (#11441099)
    So what.. if Intel is going to compete with AMD, they need to make a 64 bit version of the P-M chip. AMD already has a mobile Athlon 64.
    • Just like how AMD if they want to compete with the Pentium M will have to make a CPU with a name starting with "p".

      Being 32 bit is not a deal-breaker for 98% of the market at this point.

    • Intel has't had very good luck in 64-bit. Probably a good chunk of 64-bit desktop computers (NOT servers or systems marketed as workstations) out there are G5s, and almost all all the rest are AMD.

      Which is to say that if Dell switched over to AMD64 processors in everything, Intel would really be in the soup; even if most people probably don 't need 64-bit processors, once Apple gets the G5 in everything and AMD starts making mostly 64-bit chips, people will want it whether they need it or not.
    • Why does it need to be 64 bit? There's no software for 64 bit. The only reason why AMD64 runs so fast, is because they did a great job on the 32 side of things.
  • by TheSunborn ( 68004 ) <mtilstedNO@SPAMgmail.com> on Saturday January 22, 2005 @10:12AM (#11441125)

    Here is a link to a benchmark [gamepc.com] that show that intel might be right.

    This benchmark shows that a Pentium M 2.3 (Yes it is overclocked) is as fast as a AMD Athlon64 FX-53 (2.4 GHz) in many games


  • In the good old days, when the P-III was being replaced by the P-IV, you could roughly multiply the P-IV speed by 0.6 to get the comparable P-III speed. (Specifically, a 2Ghz P-IV was about the same as a 1.2Ghz P-III.)

    So a P-IV at 3.6 Ghz, is roughly equal to a 2.16 Ghz P-III.

    And guess what? The Pentium-M is a repackaged version of the Pentium-III core.

    Maybe Intel and AMD and the rest of the world will start using something useful, like SPEC results to market their processors, instead of Hz ratings?
  • I had a professor who still swears by the P3-based Xeon for his work and that it will always smoke anything that the P4 has to offer. Why? Strong integer performance.

    The professor I speak of is Bob Hyatt [uab.edu], and his research is on computer chess (specifically Crafty, the chess engine we all know and love). The reason the P3-family of chips does such a good job with it is because of the strength of integer calculations. Dr. Hyatt has repeatedly stated that there is not a single floating point instruction t
  • All Intel need to do is get off their arse and produce a Pentium-M with an 800MHz FSB and 64-bit support, and AMD finally have some competition in terms of performance again.
  • So what would I get if I paid for the new P4 over that Centrino? Why would I?
  • Impossible! (Score:2, Funny)

    by ratboot ( 721595 )
    3.6 GHz is more speed than 2.13 GHz!

    It's like saying a G5 2.5 GHz is faster than a P4 3.6 GHz, psttt!

    Intel said it, not me.
  • by mriya3 ( 803189 )
    Pentium-M has 2MB of on-die cache.
    Athlon 64 has a cache size of 512kb or 1MB; interestingly 3800+ and 4000+ both run at 2.4Ghz but the latter gains in speed by having a double sized cache... so what if we add more cache?
    To effectively compare Pentium-M architecture (by architecture NOT price!) to Athlon 64 we would need a 2MB cache version of it...
  • The last generation Centrino processor, the Dothan-bsaed Pentium-M, was just as good as games as this new generation. Nothing has really changed. In fact, the Pentium M has always been very good at games, though it really came into it's own with the Dothan core upgrade.

    The Pentium M is a very impressive chip. It's not all fun and games though (pardon the pun), it's very good at some things (games) and very bad at others (media encoding).
  • For those of us in the laptop market, which one do we buy? I have been looking at the Centrino, P4, the AMD Athlon XP-M and the AMD 64. But the problem is, I can't figure out which one I want. I _think_ that I want AMD, but I am unsure about whether I want a XP-M or and AMD64. Can some explain what an IS major who wants to use the thing for programming and a little mobility would want? Does anyone know of a good site that compares the four in performance?
  • We need parallel processing chips.

    http://radio.weblogs.com/0105910/2003/12/01.html

    Something like Merrimac .
  • by argent ( 18001 ) <peter@slashdot.2 ... m ['ong' in gap]> on Saturday January 22, 2005 @04:29PM (#11443727) Homepage Journal
    Is this a testament to how far the Pentium Mobile architecture has come, or a sad comment on the clockspeed-pushing design of the Pentium 4?

    The Pentium III has veen embarassing the Pentium 4 as long as the Pentium 4 has been shipping. This is merely another act in the continuing Greek Tragedy that is the Pentium 4.

"If value corrupts then absolute value corrupts absolutely."

Working...