Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 


Forgot your password?
Close
typodupeerror
×
AMD Hardware

AMD Stirs Athlon Into Geode Embedded Soup 231

Posted by timothy from the need-my-own-focus-group dept.
An anonymous reader writes "AMD, which in recent months has gained ground against Intel in the battle for the desktop, today announced the addition of a line of high-performance, low-power embedded processors to its Geode embedded x86 processor family. The new processors will be known as the "Geode NX 1500@6W" and the "Geode NX 1750@14W," reflecting a new naming convention based on relative performance and power consumption. The Geode NX 1500@6W processor operates at 1GHz and the Geode NX 1750@14W operates at 1.4GHz. The two new embedded processors are essentially identical to AMD's Mobile Athlon processors, including packaging, but with tweaks to process technology and transistor selections that result in lower power consumption at reduced clock rates." If it meant better battery life, I could live with a processor this slow in a laptop, but according to the linked story, AMD doesn't see much of a market for that.
This discussion has been archived. No new comments can be posted.

AMD Stirs Athlon Into Geode Embedded Soup More

AMD Stirs Athlon Into Geode Embedded Soup

Comments Filter:

  • AMD is starting to make my head hurt... (Score:5, Interesting)

    by Kenja ( 541830 ) on Monday May 24, 2004 @07:00PM (#9243073)
    Ok, check me on this. "The Geode NX 1500@6W processor operates at 1GHz and the Geode NX 1750@14W operates at 1.4GHz." However, 1500 x 1.4 (since the 1500 is 1Ghz and the 1750 is 1.4Ghz) = 2100. So shouldn't the 1750 be the 2100, or are they no longer trying to be even internally consistent?
    • They were never consistant in the first place! I put the model number vs. MHz on a scatterplot a while ago and it wasn't linear, though it was close.

      • Re:AMD is starting to make my head hurt... (Score:5, Informative)

        by Sivar ( 316343 ) <charlesnburns[.]gmail@com> on Monday May 24, 2004 @07:45PM (#9243322)
        They were never consistant in the first place! I put the model number vs. MHz on a scatterplot a while ago and it wasn't linear, though it was close.
        Again, the numbers are not based on clockspeed. Even Intel's "Clockspeed is all that matters" platform does not scale linearly with clockspeed. Remember, during the life of the Athlon rating system, Intel's Pentium IV had minor overhauls that greatly boosted the performance-per-clock.
        The change to the Northwood core, the change to a two-channel DDR400 memory subsystem with a 200MHz (QDR) bus are two big examples.
        AMD had similar (but less significant) performance increases as well.
        If they would have stupidly stuck with Intel's "Clockspeed is performance" mantra, the model numbers would have eventually become extremely misleading.
        First generation Palomino Athlons do not perform as well as modern Thoroughbred Athlons anymore than Williamette Pentium IV's can compare to 800MHz FSB Northwoods.

        If you plot your graph according to the average score of major benchmarks, you will find that up until about the AthlonXP 3200+ (possibly the 3000+), the rating system has been surprisignly accurate, and even a little conservative. The 3200+ rating is a bit overenthusiastic.

        Athlon64's are now back to a conservative system of comparing performance.

    • Re:AMD is starting to make my head hurt... (Score:5, Informative)

      by PhrostyMcByte ( 589271 ) <phrosty@gmail.com> on Monday May 24, 2004 @07:05PM (#9243098) Homepage
      AMD's scoring isn't based on MHz, but speed.

    • Re:AMD is starting to make my head hurt... (Score:4, Interesting)

      by justforaday ( 560408 ) on Monday May 24, 2004 @07:09PM (#9243135)
      Also note the different wattages on both chips. Although, quite honestly, that just makes this whole scheme even more confusing...

      • Re:AMD is starting to make my head hurt... (Score:5, Informative)

        by CTho9305 ( 264265 ) on Monday May 24, 2004 @08:41PM (#9243675) Homepage
        Power = C*V^2*F. C is a constant (capacitance switched), V is voltage, F is frequency. The 1GHz part runs at 1V, and is 6 watts typical:
        6 Watts = C*1v*1v*1000000000hz
        C = 6/1000000000
        13.125 = C*1.25v*1.25v*1400000000Hz = C*1.56*1400000000Hz

        Since they're the same core, the factor C is the same. The reason it isn't exactly 14 watts is most likely the static (leakage) power... even when nothing is switching, a small amount of current is flowing, just producing heat.

    • Old hat... (Score:5, Insightful)

      by hot_Karls_bad_cavern ( 759797 ) on Monday May 24, 2004 @07:13PM (#9243158) Journal
      ....'tis only what happens when good ideas go down the hall to that horrible place called: "marketing".

      Hung over from last night's lounge soire and still buffing that shiny new degree in "marketing"...stupid ideas (and numbering schemes) are rampant, especially in light of competing with Intel.
    • If you take a look at the benchmark suite [amd.com] used to come up with the performance ratings, you'll see a few highly-memory-performance-dependent benchmarks, whose results would not have scaled much with a higher clock speed.
    • Basically, we're left with model numbers now. The numbers slapped on by marketing will now have nothing to do with the actual content of the chip by any known benchmark.

    • Re:AMD is starting to make my head hurt... (Score:4, Informative)

      by smartdreamer ( 666870 ) on Monday May 24, 2004 @07:21PM (#9243193)
      There's nothing like this in AMD numbering scheme. Like they did with desktop computers, the numbers are comparaisons.
      For example, a 3000+ is not 3Ghz but an estimate Mhz comparison with Intel's processors.

      Here the comparison is made against VIA processors. So a 1500 is a 1Ghz comparable with a 1500Mhz VIA processor.

      It is better explained here http://www.theregister.co.uk/2004/05/24/amd_geode/

      • Re:AMD is starting to make my head hurt... (Score:5, Informative)

        by The Analog Kid ( 565327 ) on Monday May 24, 2004 @07:43PM (#9243315)
        For example, a 3000+ is not 3Ghz but an estimate Mhz comparison with Intel's processors.

        Uhhh..no, the rating is not used to compare Intel processors it's suppose to compare to the Athlon T-bird.

        An XP 3000+ is suppose to run like a T-Bird clocked at 3Ghz.

        It just so happened that the XPs beat out the P4 at that same clockrating as well.
      • Performance based on the performance of thunderbird running at those speeds.

        And since a thunderbird running at the same clock as a p4 northwood would have about equal perormance that's how it works out.

        Yes you still need benchmarks (The HORROR!) but since CPU's are only the bottleneck in a few programs I don't even really care anymore.

    • Re:AMD is starting to make my head hurt... (Score:5, Insightful)

      by Sivar ( 316343 ) <charlesnburns[.]gmail@com> on Monday May 24, 2004 @07:31PM (#9243255)
      So shouldn't the 1750 be the 2100, or are they no longer trying to be even internally consistent?
      Not trying to be rude, but RTFA [deviceforge.com]!
      Model numbering philosophy

      AMD says its new model numbers are based on benchmarks developed by Synchromesh Computing. The scheme consists of the processor's family name (Geode NX or Geode GX) followed by its performance rating, followed by its power usage. Performance ratings reference performance relative to VIA's Centaur processors.
      Thus, the models numbers are based on performance relative to a competitor's product, not on clockspeed. These are not, and have never been, the same thing. I suspect that the performance in this case does not scale linearly with the processor speed due to bottlenecks outside of the processor; perhaps the memory or chipset that the samples were provided with, or perhaps VIA's platform has significant performance tweaking in their higher-clockspeed cores. It does seem to be a fairly substantial difference within the same architecture.
      • From what I recall 'Geode' is what National Semiconductor kept of Cyrix after they bought it & then sold it to VIA.

        'Geode' being National Semi's name for Cyrix's MediaGX line. The MediaGX being basically a Cyrix 686 with a IO/logic chipset (memory controller, PCI & ISA bus, Floppy/IDE controllers, Serial/parrallel/PS2, etc, etc), video chipset & Audio all embedded on the core.

        The concept was to make it possible for venders to build really super cheap Pentium clone systems, as not much more wo
        • I know that reading the article before posting isn't a very popular passtime, but if you had bothered takign the time you would have seen that your questioned is answered there.

          The Geode GX is what AMD calls the system-on-chip Cyrix/National Semi product that was purchased a little while back. The Geode NX is the new Athlon-based chip. Basically the Geode NX is just an "Ultra Low Voltage" AthlonXP-M, to use Intel's name for things.

  • ... uh ... (Score:3, Insightful)

    by Anonymous Coward on Monday May 24, 2004 @07:01PM (#9243075)
    You could live with a processor that slow, in a laptop, you guess?

    I'm running a slower processor than that on my desktop, and am still perfectly happy since I have lots of RAM and never close the programs I use. What more does one need?

    Or maybe the fearless editor runs Gentoo? Silly Gentoo kids...
    • I have a Pentium 166 MMX and 64MB of RAM running Slackware 9.1. Hey, it works, even if it can't play Quake very well.

      • I have a Pentium 166 MMX and 64MB of RAM running Slackware 9.1. Hey, it works, even if it can't play Quake very well.

        Really? I played all the way through Quake on my "Pentium 75" machine. Then I discovered it was some sort of overclocked 133mhz 486 made by AMD. That's another story...

        Anyway, when I upgraded that brute with real 166mhz Pentium (no mmx) it absolutely ripped through any Quake levels I cared to try. Maybe you need a better graphics card? A Matrox Millenium 1 worked pretty good for me. God,

        • I tried GLQuake on the machine above, got about 3 frames a second. My video card is a Matrox Mystique 4MB, similar to what you used, but the drivers in Linux suck. Oh well-it runs Nethack fine, and that game satisfies enough of my addictions;) I'm beginning to surf the local garage sales, maybe someone will accidently throw a Voodoo out.

    • Re:... uh ... (Score:2, Interesting)

      by Anonymous Coward
      I'm running Gentoo on a celeron 566@850, and it's more than fast enough. I mean for crying out loud, how often do you need to install a large piece of software *within the next 5 minutes*?

      I even have gentoo on a p166. It's a bit slow, but you know what? Set PORTAGE_NICENESS to 17 and let a new kernel compile for a few days. If it's a security problem I can build a kernel on another system and copy it over in a few minutes. Big deal. Your assertion that "silly kids" run Gentoo is entertaining, yet there's a

  • are the power numbers correct? (Score:5, Funny)

    by Anonymous Coward on Monday May 24, 2004 @07:05PM (#9243096)
    I'm hoping that the power numbers are a bit more accurate than the speed numbers...
    "well, it's got the performance of a six watt chip..." just wouldn't do it for me.

  • The English Language Surrenders (Score:2, Funny)

    by Anonymous Coward
    It seems as if there has been a lack of proofreading for stories lately.

    ex: "AMD doesn't see much a market for that"

  • Very cool (Score:4, Insightful)

    by russianspy ( 523929 ) on Monday May 24, 2004 @07:07PM (#9243115)
    I'd love these things in PDA style devices.

    Add a decent amount of ram/storage and you can have voice recognition system, store your white/yellow pages for reference, store your digital photos (and edit them), store a high resolution map of your camping trip, etc....

    There is no such thing as too much power. If you have enough power you don't need that much screen space. If you could use most of the functions of a PDA by actually speaking to it (like to another human), wouldn't you?
  • Erm, I thought that the Geode was a National Semiconductor [da-cha.org] SOC product... have they sold this line of products to AMD?

  • Before you say, "Pentium M". (Score:4, Informative)

    by CTho9305 ( 264265 ) on Monday May 24, 2004 @07:09PM (#9243136) Homepage
    At $65 and $55, they're a LOT cheaper than the Pentium M (I can't find one for under $195), although they are aimed at different markets.

  • In related news... (Score:3, Funny)

    by k4_pacific ( 736911 ) <k4_pacificNO@SPAMyahoo.com> on Monday May 24, 2004 @07:11PM (#9243141) Homepage Journal
    Intel phrases Itanium into a complicated metaphor.

  • Competition is a Good Thing (Score:5, Insightful)

    by malia8888 ( 646496 ) on Monday May 24, 2004 @07:13PM (#9243151)
    AMD, which in recent months has gained ground against Intel in the battle for the desktop, today announced the addition of a line of high-performance, low-power embedded processors to its Geode embedded x86 processor family.

    Perhaps I am stating the obvious; but, I am very glad AMD is around to keep Intel sharp and vice versa. IMHO if Intel were the only game in town inovation would go down and price would go up. Every product announcement AMD and Intel make warms my heart. As consumers we benefit.

  • We're fast enough... (Score:5, Interesting)

    by LostCluster ( 625375 ) * on Monday May 24, 2004 @07:13PM (#9243154)
    Processor makers have made their living by speeding up their chips at a Moore's Law pace with faith that the latest Microsoft Windows, Microsoft Word, Photoshop and 3d shoot-em-up game will find a use for the newfound power.

    But really, I think the processor market is about to hit a wall where faster really doesn't speed things up much. Afterall, you need hardly any proc power to browse the WWW, read e-mail, or do IM chat. Sure, some people want "desktop replacement" laptops, but others want their laptop to just do some simple things.

    I think the next killer app processors are a generation that use less power and run cooler. The only problem is that consumers have been trained to only ask "How many MegaHertz does it have?" when shopping for processors. Therefore, there's going to be quite a bit of marketing work that needs to be done before such chips become viable.
    • There isn't much sense in bossting MegaHertz numbers anyway, as long as technologies like IDE, PCI and SD-RAM are around. It's like putting an airplane engine into a Ford Fiesta.

    • Re:We're fast enough... (Score:4, Informative)

      by SEE ( 7681 ) on Monday May 24, 2004 @07:34PM (#9243272) Homepage
      I heard the same "you need hardly any proc power to browse the WWW, read e-mail, or do IM chat" type of comments back when 120 MHz chips were high-end and P75s were in the low-end computers. And that was true then, too, but it doesn't seem to stop the standard chips from becoming 25-or-so times faster.

      • Re:We're fast enough... (Score:4, Insightful)

        by isomeme ( 177414 ) <cdberry@gmail.com> on Monday May 24, 2004 @07:58PM (#9243390) Journal
        Yep, dead on. I had a friend who was agonizing over the choice between 2.2 and 2.5 GHz processors; when I asked him what he planned to do with the machine, he told me it was for web surfing and light bookkeeping. But he wouldn't believe that a reconditioned 500 MHz PII box would do those just fine.

      • Re:We're fast enough... (Score:5, Insightful)

        by ejaw5 ( 570071 ) on Monday May 24, 2004 @08:00PM (#9243401)
        If you talk to enough laptop owners who would build their own desktop computers, you'll hear more complaints about a laptop sluggish HDD transfer speed than the CPU speed. For many of the laptops I've come across (and most mainstream store-bought boxes) is that the Harddrive and/or I/O controller is the bottleneck that makes the computer feel slower.

        I'd rather see advancements in laptop I/O and memory access than faster CPUs. Most of the mid to high range laptops on the market today have plenty CPU power to run presentations and and with decent decidated video chipset, FPS games. HDD access is what kills faster framerates IMO.
        • HDD access is what kills faster framerates IMO.

          No. Data is loaded before you start on almost every game. 3D cards are almost always the bottleneck and the bottleneck of the 3D card is usually memory bandwidth.

          Every laptop come with a shitty chipset compared to desktops. The highest spec laptop chips are 9700M and 5650Go. Both of those are nowhere near the power of a 9800XT or a 5900U. Sure the chips may be good for games at 800x600 but not for a laptop panel's native resolution.

          I/O will help your regula
        • yes, amen; I feel exactly this way. When I'm doing something for a while, its cool, but when I need to switch task, or open large files, or compile it hits a wall. I'm going to have to get a desktop system again because of this (I use a Thinkpad T40 with the 1.6 Pentium M)

        • Solid-state laptops (Score:3, Interesting)

          by MarcQuadra ( 129430 ) *
          I'm waiting for solid-state laptops. My desktop systems use about 2.5 - 4GB of disk space, with my files on the server, but I could get some serious stuff done with an 8GB solid-state laptop, and they'd be virtually indestructible.

          Maybe it would work better to have a boatload of RAM (4-8GB) caching the most-used parts of a filesystem on a very low level, so the drive only spins up when the cache can't satisfy. The RAM could also hold a shadow file for periodic writes to mass storage (be it network or spinn
      • Same here. But the problem is then people write thier apps for that more computing power, and it just seems to get wasted.

        Most current-day coders don't seem understand the word optimize very well.

        And I'm not talking in-lining assembly, or using C vs. an interpreted language, I'm talking about really stupid algorithms that are slow in any language.
    • I'd like that. Both Intel and AMD are seeing the light, it seems.

      Intel is side-stepping away from the P4 line in favor of the Pentium M line for its dual core chips, even for desktops, workstations and servers, despite its rebaked-for-laptop heritage.

      Now, I'd like to see AMD (or somebody) make a good mobile chipset for this. Whenever I looked, mobile chipsets for AMD parts weren't that impressive, IMO.

      One thing that this doesn't help is that other items take power too, most notably the backlight and ha

      • Re:We're fast enough... (Score:2, Informative)

        by Kynes ( 45273 )
        The reason that Intel is side-stepping the P4 for dual core is because dual core (and blades, while we're at it) has one purpose... When big computing powerhouses were building "10 year" datacenters 5 years ago they assumed that the speed, power consumption, and cooling needs of servers couldn't continue to grow at the rate that they were forever. They were wrong, they grew faster (look at Moore's law mapped out over the last decade or so, the last 2-3 years are beating the curve but the wall is coming).
        Du
    • Not entirely sure why you are ranting about high end desktop/notebook CPU's in a thread about embedded CPU's. These CPU's ARE focused on lower power consumption, fanless operation (cooler) and lower price point.

      These CPU's are targeted at set top boxes in particular so they may need either enough CPU horsepower or a coprocessor to process digital video. That's not so demanding at NTSC/PAL resolutions but it is fairly demanding for HDTV.

      If you get down to the old National Geode line which is the bottom o
      • Forgot to comment on your last point. This product line isn't being marketed to consumers. Its being marketed to EE's who are balancing horsepower, cost, heat and power consumption to get the best fit for the appliance they are building.

        The consumer probably wont even know what CPU is inside the box they are getting from their cable company or are buying from the electronics department in a department store.
    • How about Games?
    • But really, I think the processor market is about to hit a wall where faster really doesn't speed things up much. Afterall, you need hardly any proc power to browse the WWW, read e-mail, or do IM chat. Sure, some people want "desktop replacement" laptops, but others want their laptop to just do some simple things.

      Not true. As the internet becomes more and more multimedia oriented (Flash etc) we will need more and more CPU. And it's not going to stop. Right now with my XP 3200+, large flash sites stil

    • But really, I think the processor market is about to hit a wall where faster really doesn't speed things up much. Afterall, you need hardly any proc power to browse the WWW, read e-mail, or do IM chat. Sure, some people want "desktop replacement" laptops, but others want their laptop to just do some simple things.

      I think you have a point there (and with desktops as well as laptops). Also, especially as people keep bringing up some sort of hard-limit that will get hit, hurtling full-speed (no pun intende

  • I am typing this on a 867 MHz G4 PowerBook and it seems plenty fast - no urge to upgrade at all (unless Steve unleashes the G5 PB but that's another story). 6W for a CPU is awesome though. This G4 is ~20 W and the laptop lives anywhere from 2.5 to 4 hr.
  • Geode NX 1500@6W" and "Geode NX 1750@14W

    Hello... whatever happened to marketing making things easy for consumers? Why not just go back to the K6, K7 route. Hey, you know the next K is better than the previous K.

    • Geodes aren't really aimed at consumers, but rather manufacturers of products like printers, handheld computers, point-of-sale systems, thin clients, set-top boxes, etc.

    • Re:What is up with the name (Score:4, Interesting)

      by YankeeInExile ( 577704 ) * on Monday May 24, 2004 @07:39PM (#9243296) Homepage Journal

      Well, I think it has something to do with the fact that there are two dimensions that consumers are using to quantify merit.

      A processor that emits 1000 cluons per microsecond, but dissipates as much heat as a blow-dryer might be far inferior to a processor that only emits 500 cluons per microsecond, but will run on the electricity from one key lime, depending on the users' application.

      As much as consumers want to have a single "figure of merit" to make their shopping easier, it just ain't so.

      Actually, this single-number-shopping has always driven me somewhat crazy about the wintel hardware fanboys -- and how the One Metric That Matters changes over time (remember when disk drive vendors proudly published the avg. seek time? Now it seems to be RPM. Next year, I assume it will be specific gravity).

      • ...we're probably just as bad, simply in some other field of business. When it's too complex, we look to a simpler metric. The star example is insurance. Do you know the terms of your insurance? Compared to the other offers you recieved? With 99,99% certainty, you don't.

        In most cases, you simplify to "price" and a "performance" metric. You can pay X$ and get Y performance, or 2X$ and get ?.?Y performance. Or in many cases like e.g. toothpaste, replace performance with "brand value". I think the marketing t

  • These would make great home server processors (Score:5, Interesting)

    by Sivar ( 316343 ) <charlesnburns[.]gmail@com> on Monday May 24, 2004 @07:21PM (#9243196)
    It wasn't long ago that 1GHz was the magic number that both Intel and AMD were trying to hit. (AMD won).
    The performance of a 1GHz Athlon is plenty for a home server, and probably just fine for 90% of desktop PC users. My stepfather noticed zero difference moving from an Athlon 800 T-bird to an Athlon 1600+ Palomino, but it would be very noticeable for many people to not have the noise of a CPU cooling fan. Passively cooling a 6W processor would be a breeze (no pun intended).
    As an added bonus, the extremely low power usage and low heat output (thus lower air conditioning bills) would allow the chip to eventually pay for itself. I do hope that these chips are eventually made available through normal retail channels such as Newegg.com, since Transmeta products have certainly not been a choice outside of small laptops and diskless X terminals [disklessworkstations.com].
    • Maybe this might open the door to more third parties in the mini-ITX field. None of my machines with the mini-ITX have fans on them, and they work very well for dedicated units.

      I'm going to be replacing the last of my oldschool computers - a p100 dating from 1995 - with a VIA miniITX soon because of the power consumption and reliability gains, to say nothing of the space savings.

      Great for little video and MAME computers as well.
    • This is exactly the thing that popped into my mind, too. I got a T-bird 750 sitting under the desk here and would just love to get rid of the noise.

      I honestly don't get the "not for laptop market" idea, either. Like stated in a previous post somewhere the real bottleneck in laptops is the HDD anyway. I think you could make a killing selling laptops that actually do have a longer operating time on battery power alone as opposed to 1.5 hours but you can play Half Life on it and it looks GREAT.

      I don't g

  • Competing with VIA? (Score:2, Interesting)

    by tktk ( 540564 )
    I wonder if and how much these chips will cut into the VIA mini-itx market?

    I've got an Epia M10000 but the only way to upgrade will involve me buying a new Epia mobo/processor in a single package. I would love to have a Geode-based chip and mini-itx motherboard that could be upgraded separately.

  • If it meant better battery life, I could live with a processor this slow in a laptop, but according to the linked story, AMD doesn't see much a market for that.

    Yes, it would sure be nice to see this improvement moved to the laptop; but don't forget, all of the other power consumption (hard drive, lighted display, support chips, wireless NIC, CD/DVD and so on stays the same). So the improvement in laptop battery life isn't as great as you might think. Still, any improvement would be very welcome.

    And be h

  • Via C3 anyone (Score:5, Interesting)

    by IceFox ( 18179 ) on Monday May 24, 2004 @07:31PM (#9243259) Homepage
    I have a small box running 24/7. It doesn't do much, but it still needs to run 24/7. I have been using a Via C3 for over a year now with very happy results. The only downside being that a 800Mhz C3 is well... slow. Now to be able to put a AMD at twice the speed (4x the performance?) and still use that level of power is fantastic and I will be first in line to check these out. At 6W Fanless CPU heatsinks are a reality. Compined with a good case and a quiet hard drive and you have a little box you can run 24/7 without worrying about power or noise.

    -Benjamin Meyer

  • Why you probably won't see it in laptops (Score:5, Insightful)

    by boots@work ( 17305 ) on Monday May 24, 2004 @07:37PM (#9243286)
    Reducing CPU consumption down to 5W is not a great win when you still have backlit screens and hard disks chewing up power. It's a simple application of Amdahl's law [wikipedia.org].

    Intel CPUs use a lot of power at full load, but rather less when sleeping. The typical client machine spends a lot of time idle. Probably the heaviest loaded laptops are those running Gentoo, and even those are not building absolutely all the time. As I write this now, my machine's CPU is probably asleep except for a couple of ms after I hit a key.

    On the other hand the screen and backlight stay on all the time, and the disk stays spun up most of the time.

    This is one reason why Crusoe was less successful than people hoped. For laptops, CPU power consumption is just not the dominant factor.

    If passive screens and solid-state storage became popular for laptops then CPU consumption would matter again. In devices like PDAs where there is no hard disk and the screen is not always backlit, then low-power CPUs are more popular.

    Even then, power usage in flat-out benchmarks doesn't matter. The most important thing is that the CPU and memory should use little power when idle. If you run a CPU benchmark on your laptop or PDA it is expected that the battery will go flat quickly. So, don't do that when you're disconnected.

    • Re:Why you probably won't see it in laptops (Score:4, Informative)

      by the_ed_dawg ( 596318 ) on Tuesday May 25, 2004 @02:08AM (#9245102) Journal
      Just to back up your argument, according to Benini et al. in "Policy Optimization for Dynamic Power Management," the breakdown of power consumption by subsystem is:

      1. 36% display
      2. 21% digital circuitry (CPU, RAM, etc.)
      3. 18% Hard disks
      4. 18% Networking
      5. 7% Non-critical components
      It definitely takes more than replacing the CPU to really save power. Amdahl's Law in action...

      For those exceptionally motivated with IEEE membership, search IEEE Xplore [ieee.org] for "predictive shutdown," "dynamic voltage scaling," or "dynamic power management."

  • I'd like to use one of these as a desktop PC as well. My PC is a workstation but I play occasional games on it as well. I have a 9600 XT video card in my P3 system and it works very well. I could see the 1750@14W being adequte upgrade and I'd be able to get rid of some fans in my system.

    I think even if AMD can't beat Intel in sales numbers, they're cornering them in certain markets. The cost/performance/heat ratio is great.

  • It's hard to get over the MHz, I know (Score:4, Interesting)

    by Peter Cooper ( 660482 ) on Monday May 24, 2004 @07:39PM (#9243295) Homepage Journal
    If it meant better battery life, I could live with a processor this slow in a laptop, but according to the linked story, AMD doesn't see much a market for that.

    A month ago I was in the market for a notebook, and I saw the regular P4 books, Celerons, Centrinos and the Apples, and I thought having an Apple would be great.. but the MHz for the price was just too low. Could I live with a 1GHz iBook I wondered?

    A month later, I'm here sitting in my garden at 1.37am with my 1GHz iBook, and honestly can't work out why I'd need those extra MHz. I program, do some MySQL stuff, SSH a lot, play MP3s.. it seems the 1GHz copes with this excellently.

    So, you could say I'm a convert.. not just to Apple or OS X, but to the concept that more megahertz aren't always needed. Unfortunately PC diehards (as I was) find this a really hard barrier to break through, and want the 2-3GHz crazy stuff going on in their notebooks. Well, I know my battery here will last me till at least 6am (though it's a bit too cold to stay out here till then, I think!) and I know it's fast enough for everything I want to do.

    Could AMD convince people of this? Sadly I don't think so.
    • "Well, I know my battery here will last me till at least 6am (though it's a bit too cold to stay out here till then, I think)."

      Hey mister, what you need is a Prescott chip or two... Guaranteed to keep you warm and toasty till the wee hours of the morning.

      (nuclear batteries not included).

  • Geode's claim to fame is its x86-ness. It can leverege x86 software. With good software now available for ARM and MIPS, the motivation to use x86 for embedded goes away.

    Many/most of the power saving tweaks involve taking away stuff that has been used to make Pentiums fast. This means that a Geode is unlikely to perform as fast as a similarly clocked Pentium.

    Now this is a whole new architecture, but on the previous (current) generation of Geodes, I found that a 200MHz ARM was faster than a 300MHz Geode. The

    • Re:Geode is dying (Score:2, Informative)

      by hattig ( 47930 )
      These Geodes are actually Mobile Athlon XP processors tweaked to run at low speeds and low power. I.e., they will spank the pants off of an old school Geode both in terms of Instructions per Clock and clock rate. It would be like putting a mouse up against a 3 headed fire breathing dragon in battle.

      Of course, the Athlon based Geodes are using 5x the power of the old Geode, etc.

      I think that AMD has just bought out the Geode name and is repositioning it slowly against the Pentium-M and Centrino now, and ign

  • Intel got served! (Score:3, Funny)

    by Mustang Matt ( 133426 ) on Monday May 24, 2004 @08:01PM (#9243404)
    Ouch!

  • NOT FOR LAPTOPS! (Score:4, Insightful)

    by moosesocks ( 264553 ) on Monday May 24, 2004 @08:23PM (#9243534) Homepage
    Um... the Press Release doesn't mention Laptops.... anywhere!

    These processors are meant for non-computers :) Seriously, folks... they're intended to power the next generation of "Dumb Terminals" and thin clients. 1.4ghz is severe overkill for a thin client, although AMD's prices are highly competitive.

    The article also mentions a MIPS chip AMD plans to put out to be targeted at the Handheld PC market. Imagine a 1.4ghz Pocket PC?

    Think of the other possibilities....
    Routers would definitely be able to make use of such a chip.
    As color laser printeres get faster, faster processors will be needed to run them. Right now, the fastest top out at around 400mhz for the very high end models.
    Cisco could definitely use something like this in their routers.
    Set-top boxes could also benefit, although, TiVo has demonstrated that you can do a lot with a little (the Series1 Tivos ran on a 75mhz PowerPC)
  • "I think there is a market for 5 computers in the whole world." (1943)
    Thomas Watson, President from IBM

    • Re:"AMD doesn't see much of a market for that" (Score:4, Insightful)

      by THotze ( 5028 ) on Monday May 24, 2004 @10:18PM (#9244236) Homepage
      You've got to remember that AMD might look at their profit margins on these 'embedded' processors and their normal laptop ones and decide for the simple reason of wanting a profit, that it makes more sense to push a 2.5GHz laptop power-hungry processor than their cheaper, power-sipping ones. And if a market grows quickly for small, power-sensitive processors in laptops (say, Transmetta or VIA start making major headway), then *wow* AMD's got a processor that can compete as soon as they can change their marketing material...

      But the real issue is where power goes in laptops. You've got HDDs, screens which need to be "big and bright" these days (even say, 5-6" screen with a good backlight is power hungry), graphics processors, optical drives, etc.

      I know someone will say "well, I don't need an optical drive or a graphics processor..." but, well, lots of people do for a laptop, and although you might not need a graphics processor that's powerhungry... remember when you compare a 1.4GHz embedded processor without a graphics processor, don't expect it to come close in performance to a PC in the similar speed range on *any* real applications.

      But yeah, i think that AMD not seeing the market might be because of voluntary blindness because seeing this market means eating into other markets.

      Tim
  • With so many OSS people using AMD CPUs, and uCLinux heating up, has anyone gotten Linux to run on the 3COM Audrey [linux-hacker.net]? It looks like the bottleneck is running LinuxBIOS on the HW. Who can breathe (after)life into this dying platform?

  • Imagine... (Score:5, Interesting)

    by Ed Avis ( 5917 ) <ed@membled.com> on Tuesday May 25, 2004 @02:27AM (#9245159) Homepage
    I wonder if they do SMP, or can be made to do SMP by cutting a couple of pins? With six watt power consumption you could build a big SMP box and use less power than a single Xeon.
  • "If it meant better battery life, I could live with a processor this slow in a laptop"

    Slow ? Hey you insensitive clod ! My workstation at home is a Celeron 633 !!! ;-)

Slashdot Top Deals

<<<<< EVACUATION ROUTE <<<<<

Close