Slashdot Mirror


AMD Stirs Athlon Into Geode Embedded Soup

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.

231 comments

  1. AMD is starting to make my head hurt... by Kenja · · Score: 4, Interesting

    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?

    --

    "Have you ever thought about just turning off the TV, sitting down with your kids, and hitting them?"
    1. Re:AMD is starting to make my head hurt... by Mr.Radar · · Score: 3, Informative

      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.

      --
      What if this signature were clever?
    2. Re:AMD is starting to make my head hurt... by PhrostyMcByte · · Score: 4, Informative

      AMD's scoring isn't based on MHz, but speed.

    3. Re:AMD is starting to make my head hurt... by justforaday · · Score: 3, Interesting

      Also note the different wattages on both chips. Although, quite honestly, that just makes this whole scheme even more confusing...

      --
      I'll turn into a supernova and burn up everything. Well I'll turn into a black little hole and you'll turn into string.
    4. Re:AMD is starting to make my head hurt... by pseudochaotic · · Score: 1

      They might have reduced the score because of the increased power consumption. Or something.

      --
      And the l33t shall inherit the 34r7h.
    5. Re:AMD is starting to make my head hurt... by CTho9305 · · Score: 2, Interesting

      If you take a look at the benchmark suite 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.

    6. Re:AMD is starting to make my head hurt... by LostCluster · · Score: 1, Insightful

      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.

    7. Re:AMD is starting to make my head hurt... by smartdreamer · · Score: 4, Informative
      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/

    8. Re:AMD is starting to make my head hurt... by CTho9305 · · Score: 3, Informative

      Benchmarks used to determine model numbering.

    9. Re:AMD is starting to make my head hurt... by Sivar · · Score: 4, Insightful
      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!
      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.
      --
      Computer Science is no more about computers than astronomy is about telescopes. --E. W. Dijkstra
    10. Re:AMD is starting to make my head hurt... by Vihai · · Score: 3, Informative

      Yes... but one assumes that for the same family of processors the clock cycles per instruction remains the same so it should grow linearly.

    11. Re:AMD is starting to make my head hurt... by Elusive_Cure · · Score: 1, Troll

      Sorry to spoil your party mate but you're totally wrong. AMD's cpus are focused on a better efficiency on the instruction pipeline, i.e. they are designed in such manner that the processing of the instructions given to the microprocessor is up to three times more efficient when compared to a similar clocked Intel cpu. Therefore, when you compare/benchmark for example the Athlon XP 2500 (1.8 GHz) with an equally clocked P4 (1.8GHz), the AMD smokes the hell out of the P4 and its performance is similar to a higher rated P4 cpu (2.5GHz). Thats it...i rest my case...Slashdotters who know nothing get modded by people who know nothing...

      --
      Roses are red, violets are blue, most poems rhyme, but this one doesn't... ;^)
    12. Re:AMD is starting to make my head hurt... by The+Analog+Kid · · Score: 4, Informative

      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.

    13. Re:AMD is starting to make my head hurt... by Sivar · · Score: 4, Informative
      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.
      --
      Computer Science is no more about computers than astronomy is about telescopes. --E. W. Dijkstra
    14. Re:AMD is starting to make my head hurt... by pavon · · Score: 4, Insightful

      Thats the first thought I had too, but cache misses and other things can eat away at linearity. AMD has been pretty good at assigning model numbers that accurately reflect the real world performance of the chip compared to intel, so something like that must be going on.

    15. Re:AMD is starting to make my head hurt... by antic · · Score: 2, Funny
      "AMD's scoring isn't based on MHz, but speed."


      I'd say that AMD's naming scheme is based on something a bit more mind-altering than speed too...
      --
      'Thats they exact same thing a banana wrench monkey.'
    16. Re:AMD is starting to make my head hurt... by nick_davison · · Score: 1, Funny

      AMD's scoring isn't based on MHz, but speed.

      Which is contradictory to most people's belief that AMD's scoring is based on too much acid.

    17. Re:AMD is starting to make my head hurt... by Anonymous Coward · · Score: 0

      Check your facts -- AMD doesn't even pretend that they are comparing to the T-bird any more. It's all a magic formula that just so happens to come out about where Intel is.

    18. Re:AMD is starting to make my head hurt... by Anonymous Coward · · Score: 0

      I put the model number vs. MHz on a scatterplot a while ago and it wasn't linear, though it was close.

      It's all based on a simple formula, so it should be exactly linear, except where they changed the equasion. (For Ex, I think the 1800 was actually a little slower than the 1700 in most benchmarks.)

    19. Re:AMD is starting to make my head hurt... by CTho9305 · · Score: 4, Informative

      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.

    20. Re:AMD is starting to make my head hurt... by Anonymous Coward · · Score: 0

      True, though it would appear that the lower-speed 6W part is more expensive than the faster part that dissipates more power. So apparently the idea is that the more valuable part is the one that dissipates only 6W at 1 GHz and Vcore=1.0V, and that the part that runs a bit faster but dissipates a lot more power (since Vcore=1.2V or thereabouts) sells for less $$.

      So given those trade-offs, I can see how AMD might want to emphasize the various power dissipations within the part numbers.

    21. Re:AMD is starting to make my head hurt... by Fweeky · · Score: 4, Informative

      Memory bandwidth doesn't tend to scale up with CPU speed, so while you can expect a linear speed increase for executing instructions in cache, most applications are going to be hitting system memory a lot and dragging performance down.

      Check AMD's white paper on XP product numbering; you'll see they actually base their numbers on a wide range of benchmarks to try to give customers a number which actually reflects performance fairly well; that's important when, say, they increase the amount of on-die cache, as with the Barton; a 2500+ Tbred has a higher clockrate than a 2500+ Barton -- can you think of a clearer way of showing that their performance is largely the same?

    22. Re:AMD is starting to make my head hurt... by the+melon · · Score: 1

      they also have had overhauls that have reduced the output per clock a fair bit:

      the move to a 32 stage pipeline in the prescott core from 20 in northwood is the biggest one.

      clock for clock perf is about the same as northwood in most cases but remember prescott has 2x the L2 cache to make up for it's shortcommings.

    23. Re:AMD is starting to make my head hurt... by Anonymous Coward · · Score: 0
      Bush a terrorist? 89% say yes.

      Hooray! You've discovered selection bias!
    24. Re:AMD is starting to make my head hurt... by Anonymous Coward · · Score: 0

      Like the Athlon 3000+ XP vs the P4 3GHz/800MHz? You've gotta be fucking kidding. The Athlon gets raped.

    25. Re:AMD is starting to make my head hurt... by rpozz · · Score: 1

      It just so happened that the XPs beat out the P4 at that same clockrating as well.

      Have you been at Mr McBride's crack stash?
      The P4 kicks the ass of the XP

      (Score -1 : Unpopular With Fanboys)

    26. Re:AMD is starting to make my head hurt... by standing_still · · Score: 0

      Actually, I recall reading some time ago that a 3000+ is equiv. performance of an 1Ghz Duron multiplied by 3 ( 1000 * 3 = 3000 ). While a 2700+ provides the performance of 1Ghz Duron * 2.7, etc...

    27. Re:AMD is starting to make my head hurt... by Deliveranc3 · · Score: 1

      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.

    28. Re:AMD is starting to make my head hurt... by Anonymous Coward · · Score: 0

      Nope, AMD intended the speed rating for Athlon XP processors to be compared against the Pentium 4 speed in Mhz, not the TBird, the TBird is only a little slower than the XP.

    29. Re:AMD is starting to make my head hurt... by aka1nas · · Score: 1

      The PR rating was introduced when willamette was still the current P4 core. The suceeding northwood cores improved per clock performance enough that the PR rating was no longer accurate compared to Northwood Cs(800Mhz FSB).

    30. Re:AMD is starting to make my head hurt... by PingPongBoy · · Score: 1

      So why not just name the processor after a benchmark, such as Athlon SPECfp2000Base 772?

      --
      Know your pads. One time pad: good for cryptography. Two timing pad: where to take your mistress.
    31. Re:AMD is starting to make my head hurt... by Crazy+Eight · · Score: 1

      Isn't that just what the parent poster said in one sentence?

    32. Re:AMD is starting to make my head hurt... by ergo98 · · Score: 1

      If by "raped" you mean "performs comparably", then sure.

      http://www6.tomshardware.com/cpu/20030210/barton-1 5.html

    33. Re:AMD is starting to make my head hurt... by Anonymous Coward · · Score: 0
      Java, Perl, Python, Ruby, etc are little bit slow in Athlon XP Barton 2800+ at aprox. 2.2 GHz.

      Java, Perl, Python, Ruby, etc are very very SLOW in Geode NX 1500@6W at aprox. 1.0 GHz.

      Use Athlon XP Barton 2800+, forget Geode NX 1500@6W forever!!!

      open4free ©

    34. Re:AMD is starting to make my head hurt... by Anonymous Coward · · Score: 0
      Is Geode NX our future Athlon32 SOI 90nm?

      The micros of 32 bits have to die the next 2 years, it's very BAD starting to sell Geode of 32 bits.

      AMD should start to produce Athlon64 SOI 90nm for laptops because a laptop with 1536 MiB of RAM and 16 GB of swap's partition and 44 GB of filesystem's partition is a good portable supercomputer of 64 bits.

      Forget the i386 architecture, start the x86-64 architecture long-mode only, and put the tri-level pagination of 8 KiB (or 16 KiB) (not four-level pagination of useless 4 KiB). open4free ©

    35. Re:AMD is starting to make my head hurt... by Lord+Kano · · Score: 1

      My Barton 2800+ has a lower clock speed than the Thorobred B 2800+, but it crunches numbers faster.

      LK

      --
      "Hi. This is my friend, Jack Shit, and you don't know him." - Lord Kano
  2. ... uh ... by Anonymous Coward · · Score: 3, Insightful

    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...

    1. Re:... uh ... by linzeal · · Score: 1

      My bare minimium for responsiveness is an AMD 1700+ or therabouts, even with 1 gig of ram. Running 2 mozilla windows with 10-15 tabs in each, playing MP3's off the home media server, and a CAD package or astronomy package of some sorts.

    2. Re:... uh ... by irokitt · · Score: 1

      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.

      --
      If my answers frighten you, stop asking scary questions.
    3. Re:... uh ... by BenjyD · · Score: 4, Insightful

      We're talking about laptops here, not workstations. Most laptop use is running presentations, reading email and writing documents. For that, a 500Mhz P3 or so is fine. Yes, if you want to demonstrate a new numerical solver you may want a faster machine, but otherwise the disadvantages outweigh the benefits.

      I don't understand the drive for such powerful laptops for non-specialist use these days. A 5kg doorstop with a short battery life that runs so hot it needs a fan on while idle and burns your hands doesn't seem my ideal portable computing platform.

    4. Re:... uh ... by Anonymous Coward · · Score: 2, Interesting

      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 ring of truth to it. I'm certainly no kid, but I would agree that there's a good deal of, how shall I put this, one trick monkeys out there that fear new and improved ways of doing things. It's true in any field.

      On a topical note, I love the move toward low power chips. It'll save me more than the value of the chip in energy costs over the life of the chip, as well as enable me to build systems without active cooling (Though I'm looking at their 30W and 55W Athlons for that job)

    5. Re:... uh ... by mcrbids · · Score: 1

      We're talking about laptops here, not workstations.

      Why would you separate the two? Why would you have a laptop that's not also your "desktop" system?

      It's amazingly nice, when you are out on the road, you find that you have to update XYZ source code or log into ABC server, and you already have all the documents and server keys in your hand!

      The only downside that I can see is (perhaps) expandability and expense...

      --
      I have no problem with your religion until you decide it's reason to deprive others of the truth.
    6. Re:... uh ... by Anonymous Coward · · Score: 1, Interesting

      I've often had 3 or 4 FireFox windows with 6+ tabs in each, plus 4 copies of MS DevStudio, Foobar2k running, and a few other assorted apps open on a 600MHz P3 with no trouble with responsiveness. 768MB ram (not even ddr), though I do have a significant amount of swap space.

      Either hardware has gone downhill, you've got some lousy software, or you're just being picky.

    7. Re:... uh ... by BenjyD · · Score: 1

      I separate them because they serve different purposes. The criteria for the two are different: my desktop should be fast enough to run automated tests quickly, run BF1942 and generally be powerful enough to run all the complex tasks (MILP/CLP solvers etc) it has to do comfortably fast. Size, power, weight and heat aren't much of an issue.

      My laptop is for taking with me on trips away. It needs to fit neatly in a small rucksack, weigh about as much as a programming textbook and last at least three hours on batteries. Provided I can compile small projects, run LaTeX, kmail, firefox and openoffice at reasonable speed, performance isn't vital. Disk space isn't an issue - my home directory is only a gigabyte or so at maximum, and syncing the two systems is simple (rsync/NFS etc). The cost of the two systems is probably less than $1000 at current prices.

      I used a "desktop replacement" laptop recently - the heat pouring off the keyboard was enough to make my hands drip with sweat, which doesn't help typing speed much! That was x86 though - I imagine the bigger powerbooks are probably better, although you pay for the privilege.

    8. Re:... uh ... by BrookHarty · · Score: 2, Insightful

      I Dont know where you work, but at my company, all the engineers, operations and salesmen have laptops. Since we work everywhere, and have to be able to take the office with us. They just give a docking station for work and home. Same goes for all the vendors that show up, Nortel, Lucent, etc, all have laptops.

      Now I started with a P2-300, 5 years ago, and finally worked my way up to a p4-2.4ghz. The new guys get 1.4ghz mobile intel dell's. If they dont get a hand me down 600mhz machine.

      BTW, presentations? Not even close. A few putty terminals, tab'ed webbrowser, java apps, excel, outlook, remedy ticket system, multiple admin gui's, remote desktop, vnc, and winamp going in the background. Java app's alone need some hefty CPU. I'm so freaking glad to have a machine that keep up with the bloat of the applications I run.

      You keep the slow CPU's, I want more speed, ram and faster HD's. I'd trade the battery for more speed.

    9. Re:... uh ... by MarcQuadra · · Score: 2, Funny

      The reason is that people really do think that MHz matters. I heard the procurement manager explain tot he CIO a few days ago that "The 2.4GHz celeron is the same SPEED as the 2.4GHz Pentium 4, and it's almost twice as fast as the 1.2GHz Macs that we could buy, so we should buy the celerons."

      I had to stop myself from busting some faces at his comment for political reasons, but I DID do a demonstration for the dean of students of a 500MHz Mac G4 kicking a 1.4GHz Dell's ass in start time, digitizing media, compression, and browsing speed.

      --
      "Sometimes, I think Trent just needs a cup of hot chocolate and a blankie." -Tori Amos on Nine Inch Nails
    10. Re:... uh ... by tomstdenis · · Score: 0, Flamebait

      You have 15 tabs open in two mozilla windows? You sir are a fucking moron. Do you honestly need that many websites open at once?

      I mean sure it would be nice to load EVERY application into ram [multiple times] but that's not entirely smart.

      Tom

      --
      Someday, I'll have a real sig.
    11. Re:... uh ... by mihalis · · Score: 1

      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, Quake was soooo unbelievable at the time ... :)

    12. Re:... uh ... by ian+mills · · Score: 1

      I'm typing this on a 500mhz p3 because running my athlonXP heats my room up by a good 5 degrees fahrenheit. Dual monitors don't help of course, but the athlonXP put out 70watts, and thats just the chip, factor in the motherboard and videocard and you're looking at a 200 watt space heater. Great in the winter, horrible in the summer in Texas. Power efficency is going to become an ever bigger problem with modern chips.

    13. Re:... uh ... by irokitt · · Score: 1

      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.

      --
      If my answers frighten you, stop asking scary questions.
    14. Re:... uh ... by Kreigaffe · · Score: 1

      I've got an athlon 2400+ and an ati9600 in a 10x12 room and constantly play FPS

      between the computer and me, it's all the AC can do to keep even with us. Great in the winter though. Need to make a summertime PC that doesn't put out heat, but rather ice-cold beer..

      --
      ... still waiting for this free-as-in-beer free beer I keep hearing about. :|
    15. Re:... uh ... by Fred_A · · Score: 1

      I'm running an 800MHz Athlon w/256MiB of RAM as my desktop system w/Mandrake and have absolutely no issues with either speed or memory. The only thing that does hit the system is Scribus when I create a document with very large images (like 10GiB a pop). But for my usual tasks, programming, browsing web sites, retouching my photos, office stuff, listening to music, watching the occasional movie, covering my six virtual desktops with windows, it works just fine.

      My laptop is a 400MHz PII w/ 192MiB of RAM and it runs fine as well (admittedly, it usually doesn't run as much stuff as once since it's not as comfortable as a 21" screen).

      I will probably upgrade the desktop box this fall when I've decided if it's worth it to switch to Athlon 64 but that's just so I can play Windows games every now and then. Apart from that, unless you have some very specific needs, like real time video encoding, or do some very complex modeling, I really don't see what the point is of a machine faster than 1 GHz...

      --

      May contain traces of nut.
      Made from the freshest electrons.
    16. Re:... uh ... by Toraz+Chryx · · Score: 1

      um, GLQuake needs hardware opengl support, which neither the Matrox Millennium nor Mystique had any sign of.

    17. Re:... uh ... by mihalis · · Score: 1
      I tried GLQuake on the machine above, got about 3 frames a second

      Ah, GLQuake, yes, that was much more demanding. I was only talking about original software rendering Quake. You know... I am going to have to play that through again!

    18. Re:... uh ... by linzeal · · Score: 1
      That's just the way I work. I have one mozilla for school related research open to Science Daily, Nature, and the like; the other instance has things like slashdot, other forums, and the art I am currently eBaying. You see I don't ever turn off my machines, as I use hibernate, so if I want to go to a website I just know by visual memory that slashdot is below the reload button in the second instance.

      My home machine has 2 gig of ram. Currently Mozilla is taking up only 87 megs of that. My laptop is a different story as it only has 512 megs shared with the video card; damn it all, but I manage.

    19. Re:... uh ... by OrangeTide · · Score: 1

      Yea no kidding. My main development machine is a 500MHz G3 iBook. But it's for coding not for playing whatever first person shooter is supposed to be the best today.

      It plays othello, chess, and MAME very well. What more could I want? (other than a bigger hdd because mine is full of mp3s thanks to iTunes making it overly easy to rip my entire CD collection)

      --
      “Common sense is not so common.” — Voltaire
    20. Re:... uh ... by tomstdenis · · Score: 0

      You bitch about "potential slowdowns" but then misuse the tools. Well maybe Mozilla wasn't meant to have a dozen tabs open on a 300Mhz processor?

      I am not understanding your goat-raping argument.

      --
      Someday, I'll have a real sig.
    21. Re:... uh ... by linzeal · · Score: 1

      I have a 2400 AMD in my laptop, first of all. Secondly, the memory upgrade is too expensive for me right now. How am I "misusing the tools", by the way? Is there some sort of rulebook to use tabbed browsing somewhere? Maybe you are not much a power user yourself, but I am. Do not attempt to insult what you cannot understand, it makes you look like a fool and a fool who does not know he is a fool is a philistine.

    22. Re:... uh ... by tomstdenis · · Score: 0

      I have a Mobile 2400+ Athlon in my laptop as well. It's plenty powerful. Doesn't mean I'm going to tax it by keeping dozen of applications open.

      For example, right now I have xmms, gaim, mozilla [one tab], mozilla mail, gedit and a shell open. I dunno about you but when I'm coding/developing software I don't routinely need access to dozens of websites and other documents. I may have a tab or two at the most or maybe a PDF or two at most...

      See the problem I have with people like you is that you "deck out" your desktop to show off how cool you are but rarely do people like you really produce anything of substantial value worth attention. Why not go back to putting wings and blue lights on your honda civic loser.

      --
      Someday, I'll have a real sig.
    23. Re:... uh ... by linzeal · · Score: 1
      Um, heh. What codebase have you contributed to, oh great one?

      I design small projects for school now, of which some are linked to on my home page. Your, "I'm a loser" link says it all.

      "Substantial value worth attention", sounds like an ad for a knock-off Hello Kitty vibrator.

      I'm not a coder per se, I do scripting work when it is absolutely neccesary but I use my computers for projects ranging from creative projects such as Digital Art to Scriptwriting which require sometimes 3-4 instances of Mozilla with 10+ tabs when I am looking for textures or doing research on a subject new to me. When I am doing engineering and science projects I am much more lean on tabebd browsing, but that is because I have awesome book and electronic references in eBook form on my computer.

      See beyond the length of your nose. I have art hanging in 3 places right now and am getting a short play read for a chance for the fall semester playwright festival. I'm desiging a zen garden using architect programs and if my school ever gives me enough money I know enough about Small Radio Telescopes to build one for them.

      Who are you and why should I care?

    24. Re:... uh ... by tomstdenis · · Score: 0

      Don't you fucking get it? I tear a strip off total strangers and they go away crying or get all pissy. You're no fun to pick on.

      Die in a horrible car fire.

      --
      Someday, I'll have a real sig.
    25. Re:... uh ... by linzeal · · Score: 1

      Well can you tell them to send a better troll next time, I give you rating of 2.5 out 10. If you are still undergoing the perfunctory duties of an acolyte troll I would suggest observing others in their craft like british parliment which has execellant jibes, roasts, and retorts going on every session.

    26. Re:... uh ... by tomstdenis · · Score: 0

      Yeah, sorry about that. I wasn't on my game today. I'll put forth a better effort next time. I promise!

      Tom

      --
      Someday, I'll have a real sig.
  3. One Point Four? by Daemonik+CyCow · · Score: 0, Offtopic

    What? I don't get the giga hyper active stuff... T00 ADD?HD

    1. Re:One Point Four? by Anonymous Coward · · Score: 0

      video?

  4. are the power numbers correct? by Anonymous Coward · · Score: 5, Funny

    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.

    1. Re:are the power numbers correct? by CTho9305 · · Score: 1

      It has the performance of a 1.5GHz Cyrix C3, and in the benchmarks used, burned six watts. The TDP is higher, but the TDP is higher than the power you'd see in any normal situation anyway.

    2. Re:are the power numbers correct? by Anonymous Coward · · Score: 0

      You mean you wouldn't touch it (pardon the pun) if the AMD chip got the performance of a six watt Pentium IV chip.

  5. In the next ten years.... by Anonymous Coward · · Score: 0

    I see a world market for about 4 battery sipping laptops.

  6. The English Language Surrenders by Anonymous Coward · · Score: 2, Funny

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

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

    1. Re:The English Language Surrenders by Nasarius · · Score: 1

      Advanced Micro Devices is a single entity. Therefore, you're wrong.

      --
      LOAD "SIG",8,1
    2. Re:The English Language Surrenders by Anonymous Coward · · Score: 0

      Advanced Micro Devices is a single entity. Therefore, you're wrong.

      Read that again:

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

      Now compare with:

      "AMD doesn't see much of a market for that"

      Now hang your head in shame.

    3. Re:The English Language Surrenders by TheLink · · Score: 0

      The first isn't wrong.

      --
    4. Re:The English Language Surrenders by Crazy+Eight · · Score: 1

      ...much of a market...

    5. Re:The English Language Surrenders by MasTRE · · Score: 1

      > It seems as if there has been a lack of proofreading for stories lately.

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


      The chips are too slow to perform proofreading.

      --
      Must-not-watch TV!
  7. Very cool by russianspy · · Score: 3, Insightful

    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?

    1. Re:Very cool by Anonymous Coward · · Score: 0
      If you could use most of the functions of a PDA by actually speaking to it (like to another human), wouldn't you?

      No. I would find that annoying. There are times when I want to talk to someone while I'm using my PDA, such as when they are explaning something to me and I'm writing down the essentials of what they're saying. There are times when I'm using the PDA and shouldn't speak, like when I'm looking at my to-do list while I'm in the library studying (and thus, not supposed to talk!). There are times when I just don't *want* to talk while using the PDA, like when I'm in bed relaxing by playing some sort of card game or something. Or like when I'm using the timer to record how long something runs while I'm running live sound with 500 people in the audience: if I talk to my PDA, there are times (quiet parts in the program) when it will be really obvious and unprofessional if I'm talking out loud, or even whispering. Or like when I'm on the phone with someone. Or, most importantly, just any time when there are other people around and I want to put personal private information into the damn thing without broadcasting that personal private information for everyone around to hear.

      Bottom line is, if I have a PDA, part of the whole purpose is to be able to take it with me into (almost) any situation and do stuff with it. There are many, many situations where I simply can't talk, or I'm already talking about something else and need to silently interact with the PDA in the background.

  8. Too slow, eh? by Anonymous Coward · · Score: 0

    And here I am, doing most of my computing these days on a 500MHz laptop. It's running a modern OS: OSX 10.3. And X11.

    The only trouble I have is one or two web sites that bring my 1.5GHz desktop to its knees to render, full of tables as they are.

  9. You must be new here by Anonymous Coward · · Score: 0

    Stupid lameness filter...

    Cat got your tongue? (something important seems to be missing from your comment ... like the body or the subject!)

    1. Re:You must be new here by rokzy · · Score: 1

      Caught out by the lameness filter?

      YOU must be new here.

  10. AMD Geode? by jmcneill · · Score: 1

    Erm, I thought that the Geode was a National Semiconductor SOC product... have they sold this line of products to AMD?

    1. Re:AMD Geode? by CTho9305 · · Score: 4, Informative

      Yes, in August 2003. AMD has decided to include all of its low-power x86 processors in the "Geode" brand.

    2. Re:AMD Geode? by Voivod · · Score: 3, Insightful

      You see, there's this thing called Google... National Semi sells unit to AMD.

  11. Before you say, "Pentium M". by CTho9305 · · Score: 3, Informative

    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.

  12. Comparison by Anonymous Coward · · Score: 1, Interesting

    How do these new processors compare in power usage to their athlon mobile counterparts? How about compared to the desktop machines?

    If they use less energy, does that also mean that these processors will give off less heat?

    1. Re:Comparison by cbreaker · · Score: 3, Funny

      "If they use less energy, does that also mean that these processors will give off less heat?"

      I'll let you ponder that one for awhile.

      --
      - It's not the Macs I hate. It's Digg users. -
    2. Re:Comparison by CTho9305 · · Score: 2, Informative

      All the power "used" in a CPU is turned into heat. So yes, these Geodes give off less heat (hence the lack of a fan in Geode NX cooling solutions).

    3. Re:Comparison by Anonymous Coward · · Score: 0

      as so far as I know, they ARE Athlon XP-Mobile processors. AMD was already selling these things as ultra low power Athlon XP-Ms. AMD has now started trying to play the game known has "marketing"

    4. Re:Comparison by Hoser+McMoose · · Score: 2, Informative

      Well, I'll answer you second question first because it's a quick and easy: Yes. Less power consumption == less heat. Your processor is not giving off any energy as noise and (hopefully) it's not glowing so it's not giving off any light energy. There might be a TINY fraction of energy given off as a signal on the bus, but for all practical purposes *ALL* energy consumed has to be given off as heat.

      Now, to get back to the first question, the AthlonXP-M is available with power consumption of 25W, 45W or 62W TDP (Thermal Design Power), depending on the model you get.

      These new products are rated at 9W TDP for the "1500@6W" model and somewhat higher for the 1750@14W model (the wattage listed in the chips model number is a "typical" wattage, while TDP is the maximum, hence the disparity in numbers).

      Otherwise the processors are basically the same as the AthlonXP-M chips. Basically these are just "Low Voltage" and "Ultra-Low Voltage" versions of the AthlonXP-M chips, to use Intel's name for things. They are very directly competing with Intel's ULV Pentium-M chips that run at 1.0GHz and have a TDP of 7W. Performance and power consumption should be about the same, though the AMD chips sell for about 1/3 to 1/4 the price of what the Intel chips sell for.

      As compared to desktop chips they consume quite a bit less power. Power consumption isn't quite such a big deal for desktop chips, so the numbers aren't pushed as much, but generally you're looking at 50-100W or more for a top-end desktop chip. AMD's AthlonXP 3200+ processor is rated for 76.8W.

      Note that the definition of TDP (Thermal Design Power) varies from one chip to another. AMD defines the TDP of their desktop AthlonXP chips as the maximum power it will consume while running an absolute worst-case bit of code. They define their TDP for their mobile AthlonXP-M, mobile and desktop Athlon64 and workstation/server Opteron chips as being the maximum power consumption for any chip in that line (eg all of the "Low Power" AthlonXP-M chips are rated for 25W, regardless of clock speed, and all the "Mainstream" AthlonXP-M chips are rated for 45W, even though there is some overlap in clock speeds between the two lines).

      Intel's TDP is defined slightly differently again. The Pentium-M and Celeron-M is defined much like AMD's desktop AthlonXP chips, ie absolute maximum power the chip can consume. The Mobile Pentium4-M is defined like AMD's mobile chips and their Athlon64/Opteron line, ie maximum for the line of processors. And then there's Intel's desktop P4 chips, which use a TDP that is kinda-sorta-almost the maximum power the chip will consume.

      Ohh, and it just goes downhill from there. Don't even bother trying to figure out how Transmeta calculates the power consumption of their chips, because as best as I can tell they are just pulling numbers from a hat! Maybe there more info if you sign a bunch of NDAs as a developer, but from what I've seen on their website the actual power consumption of Crusoe and Efficeon chips seems to be firmly in the hands of the marketing department, not the actual specs.

    5. Re:Comparison by meringuoid · · Score: 1
      If they use less energy, does that also mean that these processors will give off less heat?

      No, they'll use less power, but give out the same amount of heat as before. I've already filed a patent for a device that will sit on top of one of these new CPUs and use that heat to run a generator, and feed part of the power produced back into the CPU. The result is a self-powering processor, with enough left over to run the video card.

      In future, before you say anything, run it through in your head and think 'Does this allow a perpetual motion machine?' If the answer is yes, keep quiet :-)

      --
      Real Daleks don't climb stairs - they level the building.
  13. In related news... by k4_pacific · · Score: 3, Funny

    Intel phrases Itanium into a complicated metaphor.

    --
    Unknown host pong.
  14. Wrong. by Anonymous Coward · · Score: 0

    English adapts, expands and exploits. When it comes to surrendering I think we know in which language we're speaking.

    In socialist France this joke explains itself.

  15. Competition is a Good Thing by malia8888 · · Score: 4, Insightful
    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.

    --
    Harpo Tunnel Syndrome--my wrist feels funny.
    1. Re:Competition is a Good Thing by Anonymous Coward · · Score: 1, Interesting

      Couldn't agree more. In recent years, maybe intel sitting on top of the heap wondering what next is what lead to the current enviroment. They know where they came from, Operation Crush is almost computer legend now. The future looks bright even if you can only see it in an electron microscope.

    2. Re:Competition is a Good Thing by Anonymous Coward · · Score: 0

      Hence.... capitalism! This is the way things are supposed to work!

  16. We're fast enough... by LostCluster · · Score: 5, Interesting

    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.

    1. Re:We're fast enough... by MikTheUser · · Score: 3, Insightful

      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.

    2. Re:We're fast enough... by mduell · · Score: 2, Interesting

      Airplane engines are typically low rpm (analogous to low clockrate). But nice try :)

    3. Re:We're fast enough... by SEE · · Score: 3, Informative

      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.

    4. Re:We're fast enough... by Jeff+DeMaagd · · Score: 2, Interesting

      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 hard drive.

      A 1GHz to 1.5GHz chip really isn't so bad if the overall system is well-designed. I was VERY impressed with the 866MHz PIIIm laptop I bought. Even with an old battery, it still managed about 2 1/2 hours of run time on battery and the performance was very zippy for everything I do.

      The one thing I'd expand first is just the hard drive. Tom's Hardware did a test with the new Travelstar 7200 RPM drives, which provides a pretty non-negligible speed improvement for what looked like a miniscule drop in battery life.

    5. Re:We're fast enough... by isomeme · · Score: 3, Insightful

      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.

      --
      When all you have is a hammer, everything looks like a skull.
    6. Re:We're fast enough... by ejaw5 · · Score: 4, Insightful

      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.

      --

      $cat /dev/random > Sig
    7. Re:We're fast enough... by Kynes · · Score: 2, Informative

      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).
      Dual core is meant as a solution for companies who have maxed out their rack space, power, and cooling (virtually every company I know of and I work in a financial shop in NY with 6 digits worth of servers). Dual core is meant to stretch the life of that datacenter in all dimensions (space, power, and cooling) so that companies don't have to spend an (unbudgeted) small fortune to build new datacenters for a few more years.
      I think they're going to be pretty popular. Now if AMD could get their foot in the door (the techies pulled for opteron but we're buying Itanics now) I'd be happy.

    8. Re:We're fast enough... by demachina · · Score: 2, Insightful

      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 of this new produce line up they are dirt cheap in quantity, very low power and don't have a lot of horsepower.

      --
      @de_machina
    9. Re:We're fast enough... by Woody77 · · Score: 3, Insightful

      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.

    10. Re:We're fast enough... by demachina · · Score: 2, Insightful

      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.

      --
      @de_machina
    11. Re:We're fast enough... by Nutria · · Score: 0

      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.

      Not much "power" is needed to display a mostly text page with a few static images, but the WWW has changed since 1998.

      Now, it's not uncommon to have pages with 3 or 4 complicated Flash animations, and loads of animated GIFs. That puts a significant burden on a CPU.

      --
      "I don't know, therefore Aliens" Wafflebox1
    12. Re:We're fast enough... by Talez · · Score: 1

      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 regular old Windows but FPS games will always benefit from more fillrate and more memory bandwidth before hard drive. Always.

    13. Re:We're fast enough... by Anonymous Coward · · Score: 0
      Turbine engines generally run at speeds from 10,000rpm to over 100,000rpm for small engines. This includes turboprops, which have a reduction gear to get prop speed down to 1500-2000rpm.

      (I assume you were referring to the piston engines found in general aviation aircraft - they generally run at low rpm like you said).

    14. Re:We're fast enough... by mrchaotica · · Score: 1

      I'm very impressed with the 800MHz Laptop I have too, but it's a G4, not a PIII - and I get 4-5 hours with a new battery. The hard drive isn't upgradeable though.

      Of course, these Geode processors seem like they might be even better at low power consumption. I'm personally looking forward to them being available in wearable computers and such, as well as laptops

      --

      "[Regarding the 'cloud,'] ownership was what made America different than Russia." -- Woz

    15. Re:We're fast enough... by PhrostyMcByte · · Score: 1

      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 still run sluggish when displayed with full quality (anti-aliasing).

      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.

      Agreed. I would love to see AMD/Intel give more attention to heat. Things are getting ridiculous now, with recent CPUs running upwards of 140 degrees. Not everyone can have a water cooling system.

    16. Re:We're fast enough... by mad.frog · · Score: 1

      Dude, it's not all about games. The drive on my work laptop is agonizingly slow, so much so that the system pretty much goes to its knees during I/O bound activity, like, say, recompiling lots of code. I would kill to have a developer-oriented laptop with really, really fast internal drive speed. (Any manufacturers listening out there? :-)

    17. Re:We're fast enough... by ashot · · Score: 1

      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)

      --
      -ashot
    18. Re:We're fast enough... by mduell · · Score: 1

      You did not just suggest putting a turbine in a Ford Fiesta!

    19. Re:We're fast enough... by Talez · · Score: 1

      I know that. The parent of my post thought for some reason a faster hard drive would give him more frames in his FPS.

    20. Re:We're fast enough... by Anonymous Coward · · Score: 0

      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 still run sluggish when displayed with full quality (anti-aliasing).


      Dude, if it doesn't run well on that CPU, the problem is the site, not the CPU. Tried Flash-click-to-play?

    21. Re:We're fast enough... by TiggsPanther · · Score: 1
      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 intended...) towards it seems rather short-sighted of the manufacturers.
      I know the CPU manufacturers want to keep pushing up "the numbers" so that people will but more new stuff, but maybe it's time they slowed down that side of things for a while.

      Yes, for some things more raw CPU power is an advantage. But it's not the only bottleneck. In laptops there's power-consumptions (mentioned already - especially in non-CPU components). In graphics/media/gaming platforms then ramping up the GPU can have quite an effect. Heck, even just having software that makes better use of the hardware can be damned impressive.

      If anything, increasing the efficiency (SMP?) rather than the raw power/speed of a CPU is what's needed. Also working on the graphics, and the local bus. Having a 10GHz CPU will only increase performance so much, mainly getting held back by the power and speed of the graphics, memory, and motherboards.
      Of course (as you mentioned above) "We have a lower clock-speed but can still get the job done more efficiently" simply won't sell units. Especially when many non-technical buyers will go around the shops saying that "This one here has 3.2 gigabytes (sic) whereas this one here only has 2.8 in it."

      Tiggs
      --
      Tiggs
      "120 chars should be enough for everyone..."
    22. Re:We're fast enough... by duggy_92127 · · Score: 1
      It's like putting an airplane engine into a Ford Fiesta.

      Is it just me, or does that sound like a ton of fun??

      Doug

    23. Re:We're fast enough... by Stregone · · Score: 1

      It would, if the swap file is being used at all.

  17. Old hat... by hot_Karls_bad_cavern · · Score: 4, Insightful

    ....'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.

  18. 1 GHz slow? by dusanv · · Score: 1

    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.

    1. Re:1 GHz slow? by pedantic+bore · · Score: 1

      And I'm typing this on a 400MHz powerbook... which is just fine for everything I do on my laptop. I don't need something faster -- what I'd like is a laptop that gives me more time on battery. When am I going to get a laptop that will run all day without recharging? A 6W CPU is a start...

      --
      Am I part of the core demographic for Swedish Fish?
    2. Re:1 GHz slow? by Woody77 · · Score: 1

      I've been looking more and more at the EPIAs, and the mini-ITX stuff. My home boxes are likely to start being of two flavors either a silent, air-cooled "appliances" running an EPIA or similar, in a smallish, durable case. Or a full-blown workstation designed for doing workstation things (development, graphics processing (ie, digital camera), mp3/mpeg encode/rip, etc.). Although that workstation sure would be nice if it was in the form of a durable laptop...

    3. Re:1 GHz slow? by robertchin · · Score: 2, Informative

      According to Motorola, the 7457 running at 1GHz dissipates less than 10 watts (8.3 typical, 11.5 max). By contrast, your 400Mhz powerbook dissipates 3.29 watts typical, 7.43 max. Of course Apple runs their 7457 chips at 1.33 and 1.5GHz, because speed seems to sell more than battery life.

      If you bought a newer battery for your powerbook, you would see it last a very long time -- they upped the wattage of the titanium powerbook batteries with each rev., and it got fairly high at the last rev compared to the first one (original ones were 50 watts, the last rev of the pbg4 batteries were around 65 watts).

  19. What is up with the name by superpulpsicle · · Score: 2, Informative

    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.

    1. Re:What is up with the name by CTho9305 · · Score: 1

      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.

    2. Re:What is up with the name by YankeeInExile · · Score: 3, Interesting

      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).

      --
      How does the Slashdot Effect happen given that no slashdotters ever RTFA?
    3. Re:What is up with the name by Anonymous Coward · · Score: 0

      Do you remember why the i586 was named the Pentium?

    4. Re:What is up with the name by Woody77 · · Score: 1

      At least with the seek times vs. rpm, we're now to a point where it pretty much looks like (on any decent drive) seek time is dependent on RPM.

  20. Transmeta by stone2020 · · Score: 0

    Transmeta already has Effecon out which runs at similar speeds and wattage. The Sharp MM20 has the Transmeta chip inside. It only weighs 2 lbs and is very thin.

    1. Re:Transmeta by Hoser+McMoose · · Score: 2, Insightful

      Yes, but a 1GHz AthlonXP-M chip (basically what these Geode NX chips are) will run circles around an Efficeon running at 1GHz. The 1GHz Efficeon will typically give you performance in the same sort of range of a 500MHz AthlonXP.

      Ohh, and the Transmeta chips are more expensive to boot.

    2. Re:Transmeta by corngrower · · Score: 1

      I read a review the other day of the efficeon chip. Their conclusion: efficieon = looser - the cpu power/watt wasn't anything to brag about. - the cpu wasn't all that fast. - choose an Athon XP-M or the new low power intel chip instead.

    3. Re:Transmeta by stone2020 · · Score: 0

      People are paying $1500 for a 500mhz notebook? Performance is better than that. How much is Efficeon compared to Geode?

    4. Re:Transmeta by stone2020 · · Score: 0

      If your talking about the Van's Hardware review, please find a fair review not done by an AMD fanboy.

    5. Re:Transmeta by corngrower · · Score: 1
      If your talking about the Van's Hardware review, please find a fair review not done by an AMD fanboy. >

      Yes it was the Van's Hardware review. I didn't get the impreesion that the reviewer was an 'AMD fanboy' since one of the Intel processors was also mentioned as a good choice. Just the same, I'll keep my eyes opened for other reviews of the effeceon processor.

  21. How about a desktop version of this ? by Anonymous Coward · · Score: 1, Insightful

    Why are all the "eco-friendly" processors only released for notebooks. How about releasing a nice low power chip for the desktop?

    1. Re:How about a desktop version of this ? by CTho9305 · · Score: 1

      These processors work in standard Socket A motherboards, so long as the motherboard can supply a core voltage as low as 1 volt. You don't really need a "desktop" version. It's up to marketing to determine what to call "embedded", "mobile", or desktop/consumer/server.

    2. Re:How about a desktop version of this ? by MarcQuadra · · Score: 1

      That's what I want, a low-power fanless micro-atx motherboard with high-quality integrated LAN (3Com or Intel).

      These chips sound ideal for my purposes (cheap and fast fanless general-purpose machines for desktops, set-tops, and file serving)

      I get by just dandy on anything 800MHz or above. It would be nice to have the north and south bridges integrated into one package on the underside of the CPU, the whole unit could live on a daughtercard to the main board which would really be a PCI-X bus with all the ports and gadgets. Think of how flexible that would be, you could get some SERIOUS upgrade potential with that configuration, since the MoBo and DoBo would be joined by PCI-X instead of this integrated proprietary v-link-type crap.

      --
      "Sometimes, I think Trent just needs a cup of hot chocolate and a blankie." -Tori Amos on Nine Inch Nails
  22. These would make great home server processors by Sivar · · Score: 5, Interesting

    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.

    --
    Computer Science is no more about computers than astronomy is about telescopes. --E. W. Dijkstra
    1. Re:These would make great home server processors by Phekko · · Score: 1

      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 get it that everyone is truly happy with laptops that run out of juice in an hour or two and PDAs that die in 3 or 4. My Palm V did quite a nice mileage on the battery before recharging was necessary and I have to admit I miss those days. Sure, it didn't play MP3s. But it did the job it was meant to do, which is taking notes and keeping dates and suchlike.

      Oh well, apparently I'm a minority among consumers.

      --

      Sigs for Nerds. Sigs that Matter.
  23. Competing with VIA? by tktk · · Score: 2, Interesting
    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.

    1. Re:Competing with VIA? by CaptainPinko · · Score: 1

      I don't think that would happen or actually help. I read somewhere that a large part of mobo manufacturing costs is the ZIF. That means your mini-ITX board with ZIF would suddenly cost A LOT more.

      --
      Your CPU is not doing anything else, at least do something.
    2. Re:Competing with VIA? by corngrower · · Score: 1
      That means your mini-ITX board with ZIF would suddenly cost A LOT more.

      Probably in the range of $25 - $50 more. This would probably add a noticable amount to the price of your mommaboard. Subtract the cost of the cpu to get the cost of a mini-ITX mobo without a CPU, then see how much the price of the zip socket is compared to the mobo cost. My guess is that it would be about 30%.

  24. Of course when AMD says... by sryx · · Score: 0, Troll

    @6W what they mean is they consume 22KW, but thats like 6W of Intel power :P
    -Jason

    1. Re:Of course when AMD says... by Anonymous Coward · · Score: 0

      They mean it consumes 6W in typical situations. The fact that it CAN use up to 9W isn't generally as important.

  25. Via C3 line of SBC / Mini-ITX boards do this now by xtal · · Score: 1

    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.

    --
    ..don't panic
  26. Another Bad Idea? by Jozer99 · · Score: 1

    In my experence, these low power chips never do well The National Semiconductor Geode, The Transmetia Crusoe, The Cyrix GXm and GX1. These low power chips had horrible performance per clock cycle, and in the end just made no sense for embedded devices, they generated as much heat as Intel and AMD chips 2x as fast. I doubt that AMD can pull off a low power processor that ISN'T made for laptops.

    1. Re:Another Bad Idea? by Chad+Page · · Score: 1

      This is a full Athlon CPU w/256K L2 at 1ghz, reduced to 9W max by (maybe) tweaking the process so it runs at 1.0V, which greatly reduces power draw. It has excellent performance per clock cycle and will run circles around any of the chips you mentioned.

    2. Re:Another Bad Idea? by corngrower · · Score: 1
      The high end embedded market is dominated by ARM chips IIRC. There's really not a big demand for these chips to be x86 compatible chips, as thay don't have to run any existing software base.


      AMD might have some success with these chips in PDA type devices. We will see.

  27. Battery life is a sum of many parts by frovingslosh · · Score: 1
    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 honest, if you could buy a 1 ghz laptop or a 1.4 ghz laptop for the same price, wouldn't you really buy the 1.4 gig system, even though the CPU ate more power? Of course, if the faster chip could be stepped down to the slower speeds and take power usage with it, then that would be the best of both worlds. But we really need better support here from the support chip and notebook makers, as well as from AMD.

    --
    I'm an American. I love this country and the freedoms that we used to have.
  28. Not a laptop processor... by Svartalf · · Score: 1

    Think embedded systems, like printers, server appliances, etc.

    It's an extreme low-power Athlon XP intended for things like I do for a living. I'd love to see a PC-104+ system or an EBX with PC-104+ expansion with one of these on the board. I'd love to see something along those lines without need of a fansink and extended temperature ranges.

    --
    I am not merely a "consumer" or a "taxpayer". I am a Citizen of the State of Texas
    1. Re:Not a laptop processor... by jelle · · Score: 1

      Mee too...

      --
      --- Hindsight is 20/20, but walking backwards is not the answer.
  29. Via C3 anyone by IceFox · · Score: 5, Interesting

    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

    --
    Do you changes clothes while making the "chee-chee-cha-cha-choh" transformation sound?
    1. Re:Via C3 anyone by tji · · Score: 1

      VIA keeps bumping up the speed of their processors. Their newest core is reported to use 3W @ 1GHz. The newer cores also have performance improvements, so it should be faster at the same clock speed too.

      The AMD chips are Geode cores, which are not known for blazing performance. It would be intersting to see a comparison among the C3, Geode, Pentium-M, and Transmeta chips. Raw performance and performance per watt would be nice to know.

  30. Why you probably won't see it in laptops by boots@work · · Score: 4, Insightful

    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.

    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.

    1. Re:Why you probably won't see it in laptops by the_ed_dawg · · Score: 4, Informative
      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 for "predictive shutdown," "dynamic voltage scaling," or "dynamic power management."

      --
      There are two types of people: those prepared for the zombie apocalypse and those who will be eaten.
    2. Re:Why you probably won't see it in laptops by tyldis · · Score: 1

      Which is probably why AMD is downplaying the use of these processors in laptops. I can certainly see a place for these in a HTPC, as they appear to work better than VIA's processors.

  31. Compatible with Mobile Mobos? by failedlogic · · Score: 1

    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.

  32. It's hard to get over the MHz, I know by Peter+Cooper · · Score: 3, Interesting

    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.

    1. Re:It's hard to get over the MHz, I know by legion9 · · Score: 1

      But if you had an IBM T4x or X40, you could be out in that garden until 8:30am AND actually have some serious computing power (and it would stay way cooler than any G4-based laptop, so there would be no need for cooling pads that are so common in the powerbook/ibook market since they heat up so much)

      Some people use their laptops for more than a walkman and a typewriter.

    2. Re:It's hard to get over the MHz, I know by Anonymous Coward · · Score: 0

      You're right. I use my 1.33Mhz G4 Powerbook for a desktop replacement. With 64MB of dedicated ram for the GeForceFX, 1.25GB of general purpose RAM, and an 80GB hard disk, I can do anything that I would normally do. This includes compiling apps (I use KDE on MacOS X and it's a custom compile.) digital audio editing, movie editing, designing websites (Quanta + GIMP owns all), and playing the Unreal Tournament 2004 demo (I really need to buy a copy). I also burn my movies to DVD with the superdrive in my powerbook.

      And my powerbook is still cheaper.

      bja

    3. Re:It's hard to get over the MHz, I know by TheLink · · Score: 1

      "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).

      --
    4. Re:It's hard to get over the MHz, I know by Peter+Cooper · · Score: 1

      Some people use their laptops for more than a walkman and a typewriter.

      I can't think of many people, beyond video producers and 3d modellers, who'd need more CPU power than I need to do development work, use the Internet quickly, play music, use Photoshop and Illustrator, and all that jazz. And sure, those people can spend 2x the money on the IBM. For the majority of the world, however, we've already got the technology there for the right price.

      I'd already been using the notebook for two hours when I made my comment, I can get about 6.5 hours out of the iBook so far (it's new, this will fall in a few months). Tom's Hardware gives the T40 an average of 300 minutes' battery time, which is somewhat less, for double the money.

      I am rarely interested in justifying my purchases, but unlike most other times, it appears this one time I haven't made a significant screw up ;-) (I must confess, I know someone with a Centrino 1.6GHz with USXGA+ screen, and it's pretty cool having that extra power there.. but now I've been won over to OS X, which has made me ridiculously more productive than I ever was in Windows, I don't care too much ;-))

  33. Geode is dying by EmbeddedJanitor · · Score: 1
    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 ARM also only used about 10-15% the power that the Geode was using and was also smaller, lighter etc... Geodes were quite popular in embedded systems but this has largely stagnated. I really struggle to see how Geode will make a comeback.

    --
    Engineering is the art of compromise.
    1. Re:Geode is dying by hattig · · Score: 2, Informative

      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 ignoring the markets that Geode used to sell in.

    2. Re:Geode is dying by Anonymous Coward · · Score: 0

      windows doesn't run on an ARM.

    3. Re:Geode is dying by corngrower · · Score: 1
      You're comparing the new Geode with an older Geode. This would make the new Geode look good. But if you compare the new Geode with an ARM chip, as the grandparent was suggesting, you find the ARM base chips 'spank the pants off' the Geode. IIRC some of the new ARM cores use only .2 Watts of power, vs 6 for the Geode. That's a big difference in power consumption.

      Since the Geode was targeted at embedded applications, it would be competing against ARM based chips, not just x86 type chips. The grandparent is justified in comparing the two.

    4. Re:Geode is dying by corngrower · · Score: 1

      windows isn't an embedded application.

    5. Re:Geode is dying by hattig · · Score: 1

      I compared in terms of computing power, where the new Geode spanks an ARM into the ground.

      I then said that in terms of power consumption, the new Geode was pretty bad, even compared to an old Geode. I then said that the new Geode is clearly a move away from low power embedded use (where it goes up against ARM, etc) to more standard low power x86 systems.

      So ... ?

  34. Is a competitor to VIA's Eve posible now? by mangamuscle · · Score: 1

    OK, how much would it cost a portable console with a Geode NX 1500@6W, Nforce 3 chipset, 256MB DDR400 and a 20GB hard drive. A built-in 5-inch LCD screen supports resolutions up to 720 x 480? Make it run linux from the bios to avoid the Windows tax and to get ultra fast boot times.

    1. Re:Is a competitor to VIA's Eve posible now? by waferhead · · Score: 1

      Nforce2, not 3. Lots of boards already exist that could use this chip.

      I'd but 3 tomorrow if they were available.

      Same chip as a Athlon mobile, probably pin compatible.

      There is a huge market for these, AMD is being coy IMHO.

      Shove them in your setop boxes/mythtv frontends.
      Shove them in Blade servers..
      Build a dual proc desktop, and passively cool it.

      The mobiles at least are known to work in dual proc boards... and they are inherently unlocked or power now or whatever it's called this week won't work.

      And I'd kill to have a laptop with a transparent lid so I could use natural backlighting as an option. (and the battery life of a Newton)

    2. Re:Is a competitor to VIA's Eve posible now? by Hoser+McMoose · · Score: 1

      Same chip as a Athlon mobile, probably pin compatible.

      Same chip, not pin-compatible. The Geode NX comes in a 453-pin chip and is designed to be soldered right onto boards. Socket-A uses 462 pins (if my memory is working right) and fits in a ZIF socket.

      It is, however, electrically compatible, so it's fairly straightforward for a company to modify a product to use these new chips instead of the desktop Athlons.

  35. ?are the number's power =? by Daemonik+CyCow · · Score: 1

    IT reminds me of marti in back to the future...

  36. wth by Anonymous Coward · · Score: 0

    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.
    That's faster than my desktop you insensitive clod! What the hell are you doing on a laptop that needs this?

  37. My Buddy.. My Buddy - SING!! Where-ever I go... by Anonymous Coward · · Score: 0

    No. A PDA is not a "li'l buddy", but a device - a tool. I don't talk to my wrench, screwdriver, or hammer - it's just not practical. There are too many things that require physical manipulation to make useful things happen.

    itomato

  38. Intel got served! by Mustang+Matt · · Score: 2, Funny

    Ouch!

    --
    The man who trades freedom for security does not deserve nor will he ever receive either. - Benjamin Franklin
  39. Re:Via C3 line of SBC / Mini-ITX boards do this no by hattig · · Score: 1

    Whilst this is a development board, if you are into mini-iTX but want more power than the VIA C3 currently provides (i.e., you want this AMD Geode processor) without extra noise that higher-wattage processors (there is a mini-iTX P4 board out there somewhere) then ...

    http://www.amd.com/us-en/assets/content_type/Dow nl oadableAssets/31760a-nxdb1500_devbrd.pdf

    It surely can't be long until a motherboard maker creates and markets one of these at a cheap reasonable price.

  40. NOT FOR LAPTOPS! by moosesocks · · Score: 3, Insightful

    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)

    --
    -- If you try to fail and succeed, which have you done? - Uli's moose
    1. Re:NOT FOR LAPTOPS! by TheLink · · Score: 1

      And AMD can still continue to sell 32 bit chips, and possibly those that don't make the cut for desktops, mobiles etc.

      --
    2. Re:NOT FOR LAPTOPS! by glitchvern · · Score: 2, Informative
      Routers would definitely be able to make use of such a chip.

      Soekris uses them in some of their computers. Soekris's computers are primarily used as routers, firewalls, WAP, etc. Cool stuff.
    3. Re:NOT FOR LAPTOPS! by ajlitt · · Score: 2, Informative

      Actually, it's 28% more amazing: According to my TiVo series 1 kernel log, the CPU is running at 54MHz.

    4. Re:NOT FOR LAPTOPS! by corngrower · · Score: 1

      For an embedded application, the processor only needs to be sufficiently fast to perform the given application. It only adds to the cost of producing the product if a more expensive processor is used in the product. In fact it could even be detremental. A faster processor may require more power, thereby reducing battery life.

    5. Re:NOT FOR LAPTOPS! by soccerisgod · · Score: 1

      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?

      That platform is called AU and it's been out for quite a long time now - albeit a lot slower. These are aimed at the embedded market. I've worked with those and they're quite usable System-on-Chip (SoC) devices.

      The development board I had had a AU1500 I think, complete with mini-PCI and all the other interfaces you could possibly want. It was clocked at something like 300-400 MHz, but in the embedded area, that usually is not as important as you might think. In fact, often enough CPUs get their clock reduced to minimize heat development and EM interferences produced by the device.

      Because of that and many other things I doubt there's many applications where speed is the biggest issue. Features (many interfaces, a good number of general-purpose IOs [GPIOs]) are an important part of the success too. Having a great many interface components implemented in the CPU itself means that designing your own carrier board is much easier and faster, and thus also a lot cheaper.

      --
      If a train station is a place where a train stops, what's a workstation?
  41. I won't buy it... by Anonymous Coward · · Score: 0

    ...looks like it doesn't execute (NX) a thing.

  42. There are massive professional benefits for this by shelterit · · Score: 1

    In fast businesses like the consultancy world, a fast and powerful laptop is at the core of the workings. In my last work in that business, we had top-notch IBM laptops which enabled us to move around internally and externally, running the systems we created locally and on servers, and as most developers know, this is paramount to fast development. I'd rather have a powerful laptop than a powerful desktop anyday. And it isn't about battery-life; it is more about moving your environment over distances and then plug back in again.

    --
    -- Home, James - it doesn't matter where that thing has b
  43. If I were VIA.. by Anonymous Coward · · Score: 0

    ..I would be worried right about now.

    -

  44. At This Rate... by Anonymous Coward · · Score: 1, Funny

    Moore's Law says that soon, AMD will have the entire datasheet encoded into the part name. There will be no need to look at external documentation at all to find out power consumption, or packaging, or pin count, or the instruction set manual. It'll all be right there in the name of the chip.

  45. "AMD doesn't see much of a market for that" by Cyb3r · · Score: 2, Funny

    "I think there is a market for 5 computers in the whole world." (1943)
    Thomas Watson, President from IBM

    1. Re:"AMD doesn't see much of a market for that" by THotze · · Score: 3, Insightful

      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

  46. You Tool by Talez · · Score: 1

    How about Games?

  47. Agree But... by EventHorizon · · Score: 1

    It wouldn't hurt to get rid of bloatware, either. Mozilla Firefox may be a brilliant marketing campaign, but frankly it's not that much lighter than the full suite. And Win2K boot is unbearable compared to Linux...

    Sadly the nice things about laptop drives (low power and noise level, spin-up-down life) are hard to preserve as you increase speed.

  48. 500MHz Geode = 1 Watt by Anonymous Coward · · Score: 0

    But a 1GHz Geode has more processing grunt than a 200MHz ARM. The article states that the 500MHz AMD Geode consumes 1W!

    Depends on your application.

    Personally for my cool low-power beowulf cluster I'd choose a bunch of dual-core 1GHz RM9222 with Hyperthreading and integrated 160Gbps multi-port Packet Switch 12W is a bargain

    1. Re:500MHz Geode = 1 Watt by Anonymous Coward · · Score: 0

      622MHz xscale consumes less than .5 watts.

  49. Audrey? by Doc+Ruby · · Score: 1

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

    --

    --
    make install -not war

  50. Wasn't the Geode once the Cyrix 5x86? by emil · · Score: 1

    As I remember, the 5x86 fit into the same form factor as the Intel 486.

    Cyrix later integrated VGA and sound onto the same die as the 5x86 and called it the "MediaGX" (I think).

    Cyrix wasn't able to scale their 6x86 up beyond 400MHz (it was very CISCish in design). How were NS or AMD able to scale the inferior design so far?

  51. Quiet/Silent Computing by Anonymous Coward · · Score: 0

    The most applicable domain for these (besides non-pc devices) is quiet computing. I'd definitely settle for a slower CPU, if it didn't need a fan. I already spend extra money on every PC I get, for quieter fans. Products like this can make my PCs even quieter.

    Peter

  52. What is special about the development boards? by SnakeJG · · Score: 1

    From the article:
    AMD provides development boards, which are intended to serve as "complete hardware and software" reference designs for embedded applications, for all of its Geode embedded processors.

    Could someone who has worked in the area of embedded processors explain a little more about what a development board provides?
    Thanks

    1. Re:What is special about the development boards? by pewterfish · · Score: 1

      IANA Embedded Systems Developer, but I'm planning on doing an MSc in the field next year.

      A development board is essentially a multipurpose computer for prototyping embedded systems. It will have little or no specialist hardware, instead having every port terminated in a socket array. In this way, you can plug together the hardware you want, using the dev board as a 'brain'.

      Once your development cycle is complete and you have a working app, you can then transfer to a production board which has none of the excess features of the dev board, and has all the hardware you need built onto the PCB.

      Hope this helps

      --
      :D > £/$
    2. Re:What is special about the development boards? by AVee · · Score: 1

      Plus the fact that dev board tend to ship with each and every piece of documentation you can find about a device including sample programs. Another thing is the fact they tend to spacier wich makes it easier to access all the connectors.

  53. What can I say... by Kjella · · Score: 1

    ...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 term is "substitution variable".

    If your market is heavily driven by that, only focus on that and screw the rest. Why you e.g. see multi-GHz machines choked by no RAM. They know better, but the consumers don't. They want it simple, you make it simple for them. Capitalism at its simplest, deliver what the consumer wants, not what he needs.

    Kjella

    --
    Live today, because you never know what tomorrow brings
  54. Ah, Nostalgia... by Anonymous Coward · · Score: 0

    I never thought I would see the day when a 1.4 gig processor would be described as "slow"...

  55. Imagine... by Ed+Avis · · Score: 4, Interesting

    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.

    --
    -- Ed Avis ed@membled.com
  56. 6 W is a lot of power for a PDA! by Serious+Simon · · Score: 1

    A typical PDA battery (3.7 V, 950 mAh = 3.5 Wh) would be drained after about half an hour...

  57. Geode's NS's Cyrix MediaGX by DABANSHEE · · Score: 2, Interesting

    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 would be needed on the motherboard but a propietry CPU socket, a RAM slot, the drive connectors, the backplane connectors & the BIOS flashchip, plus no video card or audio card would be needed either.

    You see Cyrix saw this as the only way to get the economies of scale to beat Intel. As many venders were happy to pay more for Intel, they saw the only way to beat them was to provide a platform that undercut Intel so much that venders wouldn't be able to resist 'taking the Pepsi challenge'.

    Now even though the Cyrix 686 had the fastest X86 integer core ever (per clock), it's floating point performance was weak & it just didn't ramp up clock wise. Of course this was more a problem of perception & marketing than reality. The vast majority of office productivity apps (circa 97) worked quite competitively on it, but clock speed was the marketing king & gamers 'n benchtests were heavily floating point biased & gamers 'n benchtests had heavy undue influence on what systems people bought.

    Which gets us to Cyrix's 7G Joshua/Cayenne core. The pre-production samples had the 686 Integer core (still quite sufficient as it was still the fastest & most efficient X86 integer core per clock ever), 2 floating point cores (& each one singularly outperformed the old 686 one), 2 3DNow units, 64KB of L1 cache & 256KB of L2 cache, all running on a 133mhz bus.

    Only problem was it still had the 686 issue of poor rampability. This meant that VIA (whic,h as previously mentioned, had purchased most of Cyrix from National Semi) released the pre-production samples with too overly ambitious/misleading PR-ratings, meaning they benchmarked against their competition piss-poorly, even though if they were benchmarked on the bassis of their real clock speeds they out did anything released by Intel & AMD at the same clock speed. Of course that means nothing if the oppositions ramping at much higher speeds. Which is why VIA went with the IDT Winchip II 'n III & the VIA C3.

    It was this problem that killed Cyrix's super cheap Pentium clone platform based on a propietry 886 with embedded everything chip, the Cyrix MediaGX. However National Semi saw the potential of such a chip in the embedded market, which wasn't so influenced by Moores law. Yes in the embedded market a X86 chip with embedded everything can be quite useful, even if it's not ramping up at the same speed as the PC market does. So National Semi kept the MediaGX & renamed it the Geode.

    What this has to do with AMD I don't know? I assume, going by this thread though, that AMD must've bought the Geode off AMD, & AMD's now basing the Geode off Athlon cores.

    My question is do these new Athlon Geodes have 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, like the Cyrix MediaGX did? Which would I assume mean a propietry form factor?

    1. Re:Geode's NS's Cyrix MediaGX by Hoser+McMoose · · Score: 1

      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.

  58. this slow by __aahlyu4518 · · Score: 1

    "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 !!! ;-)

  59. This slow ?! by smoker2 · · Score: 1

    I am writing this on a Sony Vaio with the AMD Athlon 1Ghz cpu, supposedly with "power-stepping" technology. Ok, if its not in use it drops down to maybe 600Mhz, but since the day I got it, (in November 2001) I have never had a battery life of more than 1 hour !

    In fact, these days, I would be lucky to get 40 minutes from a full charge.
    I guess I need a new battery, but as its a mobile desktop replacement, and I use it for video capture and conversion, it spends a whole lot of its life plugged in to the mains anyway.

    But, a nice 1.4 Ghz machine running with lower power would definitely be better.

    I am currently running the Climateprediction.net modelling software as a service, and the fan has been running constantly for around 12 hours now !

  60. Guess you forgot of Centrino! by Anonymous Coward · · Score: 0

    subj!

    I hope those Geode's sometime will join power of Athlon64 and little power consumption of PDAs :-)

  61. So they've copped out? by DABANSHEE · · Score: 0

    Instead of making a genuine update on the MediaGX/Geode line by creating a Athlon with an embedded logic/IO chipset & embedded multimedia chipset, they've just given the name to a range of underclocked Athlons.

    What a bloody wank.

  62. Yeh AMD's wanking off by DABANSHEE · · Score: 1

    '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 would be needed on the motherboard but a propietry CPU socket, a RAM slot, the drive connectors, the backplane connectors & the BIOS flashchip, plus no video card or audio card would be needed either.

    You see Cyrix saw this as the only way to get the economies of scale to beat Intel. As many venders were happy to pay more for Intel, they saw the only way to beat them was to provide a platform that undercut Intel so much that venders wouldn't be able to resist 'taking the Pepsi challenge'.

    Now even though the Cyrix 686 had the fastest X86 integer core ever (per clock), it's floating point performance was weak & it just didn't ramp up clock wise. Of course this was more a problem of perception & marketing than reality. The vast majority of office productivity apps (circa 97) worked quite competitively on it, but clock speed was the marketing king & gamers 'n benchtests were heavily floating point biased & gamers 'n benchtests had heavy undue influence on what systems people bought.

    Which gets us to Cyrix's G7X86 Joshua/Cayenne core. The pre-production samples had the 686 Integer core (still quite sufficient as it was still the fastest & most efficient X86 integer core per clock ever), 2 floating point cores (& each one singularly outperformed the old 686 one), 2 3DNow units, 64KB of L1 cache & 256KB of L2 cache, all running on a 133mhz bus.

    Only problem was it still had the 686 issue of poor rampability. This meant that VIA (which as previously mentioned, had purchased most of Cyrix from National Semi) released the pre-production samples with too overly ambitious/misleading PR-ratings, meaning they benchmarked against their competition piss-poorly, even though if they were benchmarked on the bassis of their real clock speeds they out did anything released by Intel & AMD at the same clock speed. Of course that means nothing if the opposition's ramping at much higher speeds. Which is why VIA went with the IDT Winchip as the VIA C3.

    It was this problem that killed Cyrix's super cheap Pentium clone platform based on a propietry 886 with embedded everything chip, the Cyrix MediaGX. However National Semi saw the potential of such a chip in the embedded market, which wasn't so influenced by Moores law. Yes in the embedded market a X86 chip with embedded everything can be quite useful, even if it's not ramping up at the same speed as the PC market does. So National Semi kept the MediaGX & renamed it the Geode. Going by this thread though, AMD bought Geode off National Semi some 6 months ago, & AMD's now basing the Geode off Athlon cores.

    But instead of making a genuine update on the MediaGX/Geode line by creating a Athlon with an embedded logic/IO chipset (memory controller, PCI & ISA bus, Floppy/IDE controllers, Serial/parrallel/PS2, etc, etc) & embedded multimedia chipset (video & audio out), they've just given the name to a range of underclocked Athlons.

    What a bloody wank.

  63. it's called underclocking by DABANSHEE · · Score: 1

    In reality Moore's law works for low powered cool chips too.

    Using Moore's law one can make chips faster 'n faster, relative to the voltage they're running at.

    Meaning one can get these faster chips & underclock them, which lets them run at lower voltages & thus at less consumption.

    From what I understand these low power/low heat chips are basically just their best chips underclocked

    So really AMD's copping out on what the Geode's really about, which was traditionally a X86 chip with a embedded I0/logic chipset & multimedia chipset, all on the one core (X86 CPU, memory controller, PCI & ISA bus controller, Floppy/IDE controllers, Serial/parrallel/PS2, video out & audio out).

  64. "This Slow" by ab762 · · Score: 1

    about 1GHz. My primary home machine is still a Pentium 180. It isn't any slower than it ever was.

  65. Never heard about swapping? by tempmpi · · Score: 1

    Swapping can easily kill the framerate more than a slow videocard. Especially when a game is playable most of the time, but the framerate goes down to single digit numbers from time to time not enough ram is often the problem.
    Trying to fix swapping with a faster HDD is obviously stupid, more ram is needed.

    --
    Jan
  66. No market? by deno · · Score: 1

    I don't know about other folks out there, but *MY* next computer is going to be a SILENT one:

    No fans, possibly no moving parts at all, and with power consumption low enough that my living room and my electricity bill don't need aditional cooling either. .-)

    I've been watching the VIA EPIA based mini boards for a while, and I like what I see. If AMD wants to compete in this segment, I may buy an AMD offer again - they stil have a few more months to make up thir minds.

    1. Re:No market? by MarcQuadra · · Score: 1

      Mine almost is. I built it as a hot and nasty workstation about three years ago, everything had a fan (CPU, GPU, HD slot, northbridge, and case x4). Slowly I've been replacing all the parts with newer revions that don't need fans.

      I went from a RADEON to a fanless RADEON 7500, the CPU is an Athlon-XP Barton 1.8GHz underclocked to 1.4GHz, and I'm switching from the KT-266a to the KT-600 chipset, which is fanless and less juice-hungry.

      I've also disabled all fans but the top case fan and the CPU fan, and it's cooler than my old parts were with 4 case fans!

      --
      "Sometimes, I think Trent just needs a cup of hot chocolate and a blankie." -Tori Amos on Nine Inch Nails
    2. Re:No market? by deno · · Score: 1

      I assambled a little living-room machine few months ago, and went for a nforce2 based MoBo and an underclocked Athlon (2500+) as well.

      The whole machine needs around 60W now, and thanks to temperature regulated fans isn't very laud, but I still have to switch it off whenever someone stays overnight in my place.

      As soon as I get some free again, this machine will become a "workstation", and I'll get something that makes no noise at all for the living room.

  67. Solid-state laptops by MarcQuadra · · Score: 2, Interesting

    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 spinning media). Your hard drive would only kick in for a few seconds every hour to flush it's write buffers.

    --
    "Sometimes, I think Trent just needs a cup of hot chocolate and a blankie." -Tori Amos on Nine Inch Nails
  68. VIA C5J by OrangeTide · · Score: 1

    Seems to me that the VIA C5J has better power (3.5W at 1GHz) and 800MHz FSB. The only advantage of Geode is the integrated peripherals. But you can get a two chip solution through VIA that has more peripherals than a Geode and better price point.

    The videocard on the Geode is pretty low-end, VIA's beats it. Also the built-in cryptography accelleration on the C5J would make it useful for kiosks that would like to use encrypted media or encrypted connection and it vastly improves key exchanges and certificate signing (assuming you have software to support the feature).

    --
    “Common sense is not so common.” — Voltaire
  69. So this different from National Semi's GEODE? by kriston · · Score: 1

    Does this mean that AMD is phasing out the Cyrix MediaGX GEODE platform in favor of an Athlon/NexGen-based platform? Do they keep the Cx55x0 companion chipset or does it also go away?

    --

    Kriston

  70. WTF are you talking about?? by Elusive_Cure · · Score: 1

    Time for a bit of karma burning...How the fuck you insensitive clods moderated that as troll??And fyi,nope the parent post did not say that...he was talking about speed which is a differnet matter rather than the one i described.You see SPEED is not HORSE POWER, or in other words PROCESSING POWER HAS NOTHING TO DO WITH SPEED (at least not in the way the parent post was modded as informative).AFAIK the amount of instructions processed depends on how "fat" the instruction pipeline is. Having said that AMD designs the cpu's with fatter pipelines than the P4s, you have a LOWER CLOCKED CPU doing the WORKLOAD of a HIGHER RATED INTEL cpu. In other words "HORSEPOWER is not necessarily connected to SPEED" I havent got a clue if anyone will read this post. I dont give a fuck to be honest. BUT DEFINATELLY MY PREVIOUS POST WAS NOT A FUCKIN TROLL...

    --
    Roses are red, violets are blue, most poems rhyme, but this one doesn't... ;^)
  71. CPU burden? Not if you filter that crap. by bcaulf · · Score: 1

    I find it uncomfortable to read with a flashing or animated display. Any computer that I use or set up for a friend will filter popups, banner ads, animated GIFs and Flash. Which is why I have a friend who is comfortably running Opera on a 75MHz Pentium from 1995. (RAM and HDD upgrades were performed years back using old spare parts.) With his cable modem connection it works just fine; there are not many web pages that display slower than they would on a brand new machine, since the server is the weak link in most cases. His setup works better than a new high speed connection system with IE and no popup filtering, and better than dialup which 60% of home users still use.

    And of course he does also read email and do IM chat, again without trouble. I think there's something to this idea that you hardly need any processor power for basic productivity programs.

  72. This sounds odd... by Anonymous Coward · · Score: 0
    None of my laptops are faster than 150 MHz. I'm typing this on a 150 MHz laptop with a WiFi card, using Linux with X11 through SSH. MPEG video is a bit jerky.

    Let's boast about how old and slow our equipment is.