Slashdot Mirror


Second-Gen DDR SDRAM On The Horizon

cplcap writes "This story in The Register picks up on Samsung's new DDR-II Chips, pushing DDR's speed up to 533 Mb/s and a 4.2GB/s memory bus. Prototype 512MB DIMMs are being produced, and IBM has developed a chipset to take advantage of the speed. There's a little more meat in Samsung's official press release."

145 comments

  1. the big question is... by Lumpy · · Score: 4, Informative


    Is it a whole new form factor so everyone had to redesign the motherboards and to force incompatability with older systems??

    This is important because industrial and corperate-mission-critical is older equipment. and an upgrade path for ram is still important.

    --
    Do not look at laser with remaining good eye.
    1. Re:the big question is... by signifying+nothing · · Score: 1

      Is the form factor that important if the memory bus speed is increasing? It's going to be incompatible anyway.

    2. Re:the big question is... by denisbergeron · · Score: 1

      > -Microsoft and the BSA, the BEST advocates to get companies to switch to Linux! Thanks Microsoft!

      Stop telling this, they can change the way they act !

      --
      Ceci n'est pas une Signature !
    3. Re:the big question is... by ChrisTower · · Score: 1

      As this memory will require a new chipset, it will be incompatible with older motherboards anyway.

    4. Re:the big question is... by ToLu+the+Happy+Furby · · Score: 5, Informative

      Is it a whole new form factor so everyone had to redesign the motherboards and to force incompatability with older systems??

      The answer is...yes and no. DDR-II does have a new form factor, with 232 pins, as compared to the 184 currently used in a DDR (I) DIMM. Similarly, a DDR (I) DIMM has a bit more pins than the 168 found in an SDRAM DIMM.

      However, this isn't such a big deal for the mobo makers; it's just a matter of putting on a different slot and different traces on the board. One of the things that has made the transition from SDRAM to DDR more "evolutionary" than a transition to (say) RDRAM would have been, is that the same chipset can control both SDRAM and DDR, because they use the same (or at least backwards-compatible) commands. It's not often mentioned on the hardware-enthusiast sites which are only interested in benchmarking the fastest stuff around, but just about every DDR chipset is also available with SDRAM. You need a different motherboard--because the slots are incompatible--but the cost to the mobo makers for offering both versions is pretty small.

      In a similar vein, the commands for DDR-II are a superset of the DDR-I command set, such that DDR-II chipsets should very easily be able to detect and use DDR-I as well, just like DDR-I chipsets currently use SDRAM as well. Furthermore there is talk (dunno if it will happen) of releasing DDR-I DIMMs in the 232-pin DDR-II form factor; that way, one could buy a motherboard and use either DDR-II or DDR-I in it, with no problems. Of course old sticks of DDR-I will not fit, and the new ones will not fit in current DDR motherboards.

      So, while such a scheme doesn't get rid of all the headaches of an incompatible upgrade path, it does address some, albeit more on the mobo producer end of things than on the IT inventory end of things. It is indeed a pain that, while SDRAM (and the SDRAM form factor) enjoyed around 4 years as the mainstream memory type, DDR-I will only be on top for 2 before DDR-II takes over. And DDR-II will be lucky to have 3 years before something pin-incompatible comes along to replace it.

      On the other hand, the SDRAM -> DDR transition probably would have happened a year earlier if Intel hadn't tried to transition to RDRAM instead. And, meanwhile, being stuck with SDRAM for 4 years meant DRAM bandwidth only doubled (and actual performance did less than that) over a period when CPU clock speeds increased by a factor of 5 or so. I think the DRAM industry wants to make speed increases more frequent than they were a few years ago, even if this means more inconvenience for corporate IT departments.

      This is important because industrial and corperate-mission-critical is older equipment. and an upgrade path for ram is still important.

      I'm not sure what you mean here. As far as the upgrade path for greater RAM capacity goes, standard SDRAM and DDR-I will still be made and sold for quite some time, even if they will eventually be more expensive than their newer and faster brethren. EDO RAM is still being made and sold today.

      If you mean an upgrade path for higher-performance, of course you can't just buy faster DRAM and expect it to speed up (or even work in) a system that was built to use a slower type. The system clock sets the DRAM speed, and unless the system has been validated to run at the new DRAM speed, doing so amounts to overclocking. An performance upgrade path for RAM is always going to require purchasing at least a new CPU module and accompanying memory bus, if not a new machine.

    5. Re:the big question is... by Anonymous Coward · · Score: 0

      If you mean an upgrade path for higher-performance, of course you can't just buy faster DRAM and expect it to speed up (or even work in) a system that was built to use a slower type. The system clock sets the DRAM speed, and unless the system has been validated to run at the new DRAM speed, doing so amounts to overclocking. An performance upgrade path for RAM is always going to require purchasing at least a new CPU module and accompanying memory bus, if not a new machine.

      noo, but giving a machine a gigabyte of any ram is always faster than the paltry 128meg it had to live with from inception... Servers benifit the most (Hear that admins? if your servers are not at the motherboard maximum for ram then YOU ARENT DOING YOUR JOB!)

    6. Re:the big question is... by Ralph+Wiggam · · Score: 1

      "Hear that admins? if your servers are not at the motherboard maximum for ram then YOU ARENT DOING YOUR JOB!"

      So apparently your CFO has a giant jar of money on his desk next to the Jolly Ranchers.

      -B

    7. Re:the big question is... by Mr.+Biggles · · Score: 1

      Damnit, I got my new box TWO MONTHS AGO and already the DIMM slots on its mother board have been outdated by DDR and now DDR-II is coming. They need to start making DIMM slots have more pins then are being used at the time the motherboard(s) are manufactured so we can upgrade with the latest chips as they come out. Bleh, sometimes I almost hate technology.

    8. Re:the big question is... by JavaTenor · · Score: 1

      So, uh, why did you buy a box two months ago that doesn't use DDR? The stuff is pretty cheap.

    9. Re:the big question is... by ScHiZ0 · · Score: 1

      Hmm.. what we need is a modular mainboard with pluggable chipsets. And twice as many connectors per chip than currently in use.. naah, won't work I guess. Nice thought though..

  2. Wow by Anonymous Coward · · Score: 0

    I wish I had a job so I'd have money so I could buy this stuff.

  3. When will processors keep up? by gordonsch · · Score: 0, Flamebait

    Na, great... With the advent of even newer RAM on the horizon, it leaves me puzzled when processor development will close the gap - DDR333 didn't perform too well with nowadays' processors. Hammer anyone?

    --
    Gordon.
    1. Re:When will processors keep up? by Anonymous Coward · · Score: 1, Insightful

      Hahahhahahha!

      When will *processors* keep up with memory!

      Oh, you have me laughing.

      Memory technology is so far behind processor technology it ain't funny. Hence L1 and L2 caches, L3 caches are becoming necessary now as well.

    2. Re:When will processors keep up? by gordonsch · · Score: 1

      so did DDR333 put any _real_ speed increases into today's system?

      --
      Gordon.
    3. Re:When will processors keep up? by sacremon · · Score: 2

      Depends on what you do. Some applications are particularly memory intensive, like MPEG-4 encoding. The faster the memory, the better. Other apps are limited by the CPU, peripheral bus or graphics card.

      --
      If you can't beat them, embrace and extend them.
    4. Re:When will processors keep up? by gordonsch · · Score: 0

      well, most benchmarking tests i saw just basically concluded that with today's x86 CPUs (Athlon's 266FB, P4 I don't know) you basically don't get a real, noticeable boost in your daily work. So guess that was stuck in my head. :)

      --
      Gordon.
    5. Re:When will processors keep up? by Darren+Winsper · · Score: 1

      Actually, yes. The problem is the Athlon's FSB is 133MHz DDR aka 266MHz. If you overclock the FSB (Chipset proc rather than RAMchipset) to 166MHz DDR you do actually get a significant speed increase.

    6. Re:When will processors keep up? by sacremon · · Score: 2

      Key words there are 'daily work'. If that is using things like word processors, spreadsheets, web browsers and the like, then that is correct. If your daily work is encoding video or audio, making heavy use of Photoshop, Lightwave or Maya, then it makes a difference.

      --
      If you can't beat them, embrace and extend them.
    7. Re:When will processors keep up? by Anonymous Coward · · Score: 0

      i'm sure all of that can be made even more sluggish with enough bells and whistles.
      for instance, 100Hz smooth scroll at 1920x1440 32bpp takes 1,2GB/s. and it mainly slows things down..

  4. great news for Linux on x86 by tps12 · · Score: 0, Troll

    This strikes me as vital for the well-being of the Linux community and operating system.

    This removes the DDR bottleneck that has been holding Linux back since the days when the Linux VM overcame the shortcomings of the 486. For years, sysadmins "in the know" have passed over Linux on x86 in favor of the superior hardware of the Mac or Alpha machines. Likewise, the presence in Windows of well-known workarounds for the DDR bug has given Microshite an unfair edge. Kudos to Linus for not giving in to the hype!

    We will start to see Linux catching up on the desktop, in the home, and in the office. Even the much-ballyhooed server market? We'll see. Let's just say I'm optimistic. ;)

    --

    Karma: Good (despite my invention of the Karma: sig)
    1. Re:great news for Linux on x86 by Anonymous Coward · · Score: 0

      As much as I like the OS, I wouldn't call Macs "superior hardware". Superior for Photoshop and other Altivec-heavy programs maybe, but I really can't imagine too many sysadmins choosing Macs over Alphas or x86 servers.

    2. Re:great news for Linux on x86 by chill · · Score: 2

      That sounded like a Troll.

      Exactly what DDR bottleneck are you talking about? Specifically, where Windows has a workaround and Linux doesn't.

      Memory bandwidth has always been a bottleneck on systems, and it probably always will. However, this is a hardware issue and not an OS one, as far as I understand it.

      Finally, an admin "in the know" that chose a Mac server was probably on drugs. PPC hardware is very nice, but the extra cost -- not to mention the skills needed to deal with the lack of server software... a questionable choice for any serious environment.

      --
      Learning HOW to think is more important than learning WHAT to think.
    3. Re:great news for Linux on x86 by jo42 · · Score: 1

      You really should stop hoping that better hardware will fix the boogered Linux VM [software]. Then again, if you knew any better, you would be using FreeBSD if the bee in your bonnet is VM implementation.

    4. Re:great news for Linux on x86 by Anonymous Coward · · Score: 0
    5. Re:great news for Linux on x86 by Anonymous Coward · · Score: 0
  5. Excellent! by IIRCAFAIKIANAL · · Score: 0, Offtopic

    Maybe when this comes out (with the Itanium II) I will be able to get more than 5 fps in Morrowind.

    How they're going to port that to the XBox is beyond me...

    --
    Robots are everywhere, and they eat old people's medicine for fuel.
  6. IBM .. not so surprising. by lionchild · · Score: 1

    It seems not so surprising that IBM would flock to new and "exciting" technologies and improvements like this one. One can only wish that such forward thinking would shake-down through the rest of their organization.

    The geeks in the back rooms, and the engineers in the streets certainly see the benefits from this new technology. Perhaps someday the slimmer, sleeker, more lithe and less middle-management IBM will show itself and we'll see this sort of stuff rolling downhill more quickly.

    In the past, IBM has been near the forefront of going after new improvements. They sometimes just can't market their way out of a wet paper bag. Often sad, but true.

    --
    Awk! Pieces of eight. Pieces of eight. Pieces of seven... ERROR: General Protection Fault. [Paroty Error.]
  7. Everyone say "YAY!" by mrgrey · · Score: 0

    To the dropping prices of RAM.

    Joy to the advent of newer technology and lowering prices.

    --
    -Tolerate my intolerance
  8. On the horizon? by delphin42 · · Score: 2, Insightful

    It is nice to know what's coming, but Q3 2003 is a long ways away, and the modules being ready doesn't necessarily mean there will be a chipset ready that supports them. I'm still waiting for P4 motherboards to support 333Mhz DDR. Tom's has a review of the VIA P4X333 here, but we haven't seen any motherboards with this chipset yet. The VIA KT333 chipset currently has around 16 Athlon motherboards shipping with 333Mhz DDR support.

    --
    -- Adam
    1. Re:On the horizon? by sacremon · · Score: 2
      I'm still waiting for P4 motherboards to support 333Mhz DDR.


      There are plenty of them, based on the SIS645DX chipset. I've got a ASUS P4S533 that supports it just fine, and can use DDR400 (though there is no ratified spec for it) as well.

      --
      If you can't beat them, embrace and extend them.
    2. Re:On the horizon? by Tackhead · · Score: 1
      > > I'm still waiting for P4 motherboards to support 333Mhz DDR.
      >
      >There are plenty of them, based on the SIS645DX chipset. I've got a ASUS P4S533 that supports it just fine, and can use DDR400 (though there is no ratified spec for it) as well.

      Wow, great timing... I'm looking at building a few boxen based on this mobo with a 1.6A, and for my own box, playing with FSB overclocks (133=533 sounds easy) versus running the RAM asynchronously.

      (If I need USB2.0 I can just use a card - I think Via's P4X333 chipset will be strong, but why wait another couple of months just to get USB 2.0 onboard. SiS645DX rocks.)

      So anyways - on to my question - when you say DDR400 on the P4S533, do you have a stick of DDR333 / CAS2.5 running as DDR400 / CAS3.0, and how does your bandwidth compare? (Or are you able to run it at CAS2.0 at 333, 2.5 at 400?)

      Any hints/tips appreciated. Thanx.

    3. Re:On the horizon? by sacremon · · Score: 1

      I'm using a stick of Corsair PC3200, which is DDR400 (or so claims Corsair). The P4S533 allows for async PCI:RAM, including a 4:6 when at 133MHz FSB or higher. That gives 200MHz when the FSB is 133MHz. I'm presently running a 1.6A at 141MHz FSB (2.256GMhz) and running the RAM at 211MHz. My Sandra memory scores beat 100MHz PC800 RDRAM by about 600MB/sec.

      --
      If you can't beat them, embrace and extend them.
    4. Re:On the horizon? by jefp · · Score: 1

      Also the i845G and P4X333 chipsets. Check the ACME Boardfinder.

    5. Re:On the horizon? by Tackhead · · Score: 1
      Sweet, sweet, sweet ;-)

      Thanks, dude!

  9. Innovation vs Litigation by dlur · · Score: 0, Offtopic

    It's good to see a few companies in the memory market actually coming out with better and exciting products as opposed to Rambus who likes to litigate its way into the market.

    --
    Duris MUD - The best pkill MUD. Ever.
    1. Re:Innovation vs Litigation by SamBeckett · · Score: 0

      It's good to see a few posters in the slashdot community coming out with better and exciting products as opposed to dlur who likes to rehash old topics in hope for karma.

  10. meanwhile, Rambus is hard at work by Anonymous Coward · · Score: 0, Funny
    their dedicated staff of 60 lawyers, 80 marketers, 50 managers and 2 engineers (working double as administrators and POC's for sales) are hard at work inventing the next... greatest... fantabulous... PATENT!

    Yes siree folks, step right up and be amazed at their patenting of the ability to dynamically store linear memory through a Gated (TM) process that can be recalled on the fly and changed without requiring manual realignment or core mounting.

  11. Wow What a long atricle by KingKire64 · · Score: 0, Offtopic

    Wow what a long article.next time think of the routers and just list the entire 2 paragraphs on /.

    --
    "All I can tell the "lesser of two evils" folks is that if they keep voting for evil, they'll keep getting evil."-Lp.org
  12. geez... by echosa · · Score: 3, Interesting

    something tells me that the "computer age" is getting a bit unbalanced... we're nowhere NEAR reaching the hardware limits that we already have (home useage speaking at least) and we're already surpassing whats more than enough? sounds a bit unneccesary, at least for the moment...

    1. Re:geez... by Anonymous Coward · · Score: 1

      You are wrong, echosa. I use every cycle of power on my system with a recording studio, and I will never NOT have a need for more power.

  13. wow by __aahlyu4518 · · Score: 0, Offtopic

    I wonder what this will do to the write-time on my 1.44 floppies...

  14. Any news on their 210Ghz transistor? by kfsone · · Score: 1

    Since the slashdot article about IBM 210Ghz transistors I've not seen any further mention of these super-transistors or the possibility of building chipsets from the technology... And yes, I mean 210Ghz not 210Mhz.

    --
    -- A change is as good as a reboot.
    1. Re:Any news on their 210Ghz transistor? by RevRigel · · Score: 3, Interesting

      210GHz is the unity gain bandwidth of that transistor. That means that when switching at 210GHz, it only puts out as much as you put in (in layman's terms). In terms of chip production, that means you can only have a fanout of one. Therefore, it's impossible to construct basic circuit elements at that speed. Once you throw in a requirement for a fanout of say, 10, you've thrown 10 gate capacitances in parallel with that transistor, which is going to knock its bandwidth down quite a bit. To what, I don't know, but it wouldn't surprise me if it was by at least an order of magnitude.

  15. Clever Marketing Scheme by goldspider · · Score: 3, Insightful
    How many people besides myself have noticed that there are hardly any backward-compatible hardware technology breakthroughs?

    I understand that there are physical limitations well beyond my comprehension that are factors in all of this, but it seems that any time one of these improvements comes out, be it RAM or CPUs or any number of other upgrades, a new chipset has to be developed to support it?

    I'll tell you why: because marketers understand that some people (many of which frequent this site) will pay plenty extra to have the latest technology, no matter what.

    I, for one, am sick of it. For once I'd like to be able to upgrade my CPU or RAM without having to buy a new motherboard and re-install my entire OS.

    Sorry for the rant, but I think the fact that every incremental hardware update requires a new chipset is noteworthy.

    --
    "Ask not what your country can do for you." --John F. Kennedy
    1. Re:Clever Marketing Scheme by Anonymous Coward · · Score: 0

      How many people besides myself have noticed that there are hardly any backward-compatible hardware technology breakthroughs?

      I have. And so has this one guy I spoke to last week at the supermarket.

    2. Re:Clever Marketing Scheme by panurge · · Score: 1

      Well, of course. Processor gets faster, RAM gets faster, bits in between have to get faster too. You can't run an F1 car on a dirt track, you know.

      --
      Panurge has posted for the last time. Thanks for the positive moderations.
    3. Re:Clever Marketing Scheme by KingKire64 · · Score: 1

      Gotta love amd. For the most part AMD trys to avoid this. Now when it comes to ram changes they have no control. But i like how that Just because AMD comes out with a signaicantly fast CPU it doesnt mean you have to switch MOBOs. With Intel you pretty much have to buy a new MOBO with every new CPU.

      --
      "All I can tell the "lesser of two evils" folks is that if they keep voting for evil, they'll keep getting evil."-Lp.org
    4. Re:Clever Marketing Scheme by Yet+Another+Smith · · Score: 3, Insightful

      Simple. Next time you put together a computer, buy a chipset for DDR-II, but only put pc2100 memory in. Then, six months later, buy screaming fast DDR-II memory. Sure it'll cost you more in the long run, but you'll have upgraded your RAM successfully. Or you could do like everybody else and buy more RAM rather than faster to make your upgrade.

      Of course, if you had one of the early AMD t-bird chips, you could buy an XP and run it on the same motherboard, so CPUs generally are upgradeable within the same form-factor. Same is true for a Duron to XP upgrade.

      If you're having tp re-install your OS for a CPU or RAM upgrade, you've got bigger problems.

      --
      if ($it != $onething) {$it = $another;}
    5. Re:Clever Marketing Scheme by Anonymous Coward · · Score: 0

      What do you think a gravel trap is?

      Is that like a bunker in golf? Do F1 have to change tyres to get out of the "gravel trap" as well?

    6. Re:Clever Marketing Scheme by goldspider · · Score: 1
      "If you're having tp re-install your OS for a CPU or RAM upgrade, you've got bigger problems."

      My point was that every time I've upgraded my CPU or RAM, I've had to buy a new motherboard as well. Hence the OS re-install.

      --
      "Ask not what your country can do for you." --John F. Kennedy
    7. Re:Clever Marketing Scheme by Anonymous Coward · · Score: 0

      I have, and my co-worker has as well.

    8. Re:Clever Marketing Scheme by Loligo · · Score: 1

      >I've had to buy a new motherboard as well. Hence
      >the OS re-install.

      What OS are you running that can't handle a motherboard change?

      Even my last Win98 system survived three motherboard without a reinstall... along with four CPU any number of video/sound/network card changes.

      What x86 OS *can't* handle that?

      -l

    9. Re:Clever Marketing Scheme by Anonymous Coward · · Score: 0
      I've reinstalled the OS (win2k) as a precautionary measure, really. Back in the day, I've had win95 (I believe) have a really hard time handling a new motherboard (with the old board's drivers and other differences).

      Perhaps that's different now, but I've always done a re-install as a habit to reduce the likelihood of conflicts. Maybe paranoid, but that's how I've gotten the most trouble-free upgrades.

    10. Re:Clever Marketing Scheme by Alan+Partridge · · Score: 0, Offtopic

      what's golf? is it that electric karting world championship that I saw on Eurosport the other day?

      --
      That was classic intercourse!
    11. Re:Clever Marketing Scheme by DrSkwid · · Score: 2

      My first reaction was "so what". I perceive a value to buying a new mobo when I buy a CPU. Pennies per part matter. I think I'd rather pay when I buy the next generation than future proof this generation for the added cost.
      My experience has been one of losing money in this way before on hardware. *Something* seems to obselete it no matter how manufacturers try to sell me futureproofed parts.

      Also one loses because they break. So it might take hardware improvements for three years but it's only got 1 year warranty anyway.

      --
      There are places where the networks are not touching,and there are places where they are-Boeing's Lori Gunter
    12. Re:Clever Marketing Scheme by Anonymous Coward · · Score: 0

      [Hear the black helicoptors?]
      Look at the changes in AMD motherboards as an example. Start with slot 1. It sucked and everyone hated it, so they went to socket a. From socket A (@ 200 mhz), any Athlon from, what, 400 mhz or so up until 1.2 ghz or so would go into an old motherboard. Too many waitstates were being introduced with the high end processors, so they went to DDR ram. So 1 motherboard change in, oh, 6 years? That isn't too horribly bad.

      Truth be told, by the time you are ready for a processor upgrade, there is probably a lot of stuff on your motherboard that you want to change, too. USB2.0, ATA100, AGP4X, etc. I don't think that it is a conspiracy as much as just common sense. How can you design a motherboard that will we so flexible that people 5 years from now will still want it, yet meet the price and size requirements that everyone has?

      Reinstalling your OS is a sign of a crappy OS. That, you can change. :-)

    13. Re:Clever Marketing Scheme by Yet+Another+Smith · · Score: 2

      Well, I've had to replace a bad mobo (with a different model mobo, but same CPU and RAM) on a machine that was dualbooting WinME and Linux. ME continued working fine (well, by ME standards, meaning it still only crashes once or twice a day) and Linux actually got more stable.

      Just make sure to keep drivers and so forth current.

      --
      if ($it != $onething) {$it = $another;}
    14. Re:Clever Marketing Scheme by Junks+Jerzey · · Score: 2

      Simple. Next time you put together a computer, buy a chipset for DDR-II, but only put pc2100 memory in. Then, six months later, buy screaming fast DDR-II memory. Sure it'll cost you more in the long run, but you'll have upgraded your RAM successfully. Or you could do like everybody else and buy more RAM rather than faster to make your upgrade.

      And then some new memory system will be announced that needs a new motherboard anyway.

      It's time the myth of the upgradable PC was put to rest.

    15. Re:Clever Marketing Scheme by drinkypoo · · Score: 1
      The problem is that no one wants to pay for tomorrow's technology today. People design hardware for lowest cost, and that means restrictive designs that we'll outgrow.

      But really, why complain? The fact that you have to upgrade your motherboard and memory, and probably your CPU all at once is nothing compared to the bad old days when all computers were proprietary. Of course, they were simpler and thus more hackable, but you couldn't just upgrade your motherboard. Now there are even ATX PPC boards - You can change your architecture without swapping (many) of your peripherals.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    16. Re:Clever Marketing Scheme by Tackhead · · Score: 3, Insightful
      > My point was that every time I've upgraded my CPU or RAM, I've had to buy a new motherboard as well. Hence the OS re-install.

      Depends on the upgrade.

      As a lark, when I moved from a Pentium I (430TX chipset) to the 440BX-based system (new mobo, Celeron CPU, new chipset, new video card, new sound card, new RAM), I tried transferring (after Ghosting :) a Win9x system to it. After several reboots and requests for the install CD, it actually ran.

      (Then, of course, I wiped it and reinstalled from scratch to be sure I had a decent config and drivers, but it's theoretically possible. I was amazed it worked at all.)

      That said, I chose the 440BX because it had headroom for growth. That lowly Celeron-366 (66 FSB oc'ed to 100 for 550 MHz) is now running a Celeron 800 at over 1 GHz (FSB at 124.) It could probably run at an FSB of 133, except that I've got mismatched sticks of PC133.

      Am I getting as much out of that PIII-1G on a 440BX chipset as I could? Of course not. My 5400 RPM drives are still running ATA-66. It's still SDRAM. It's still the same PCI frequency.

      But the upgrade was $50 for the CPU, gave me another two years out of the system, and (most importantly) required no time-consuming OS or driver changes, be it Win9x, 2000, or Linux.

      I think we might be at a similar point with the P4 Northwoods. Buy a cheap Northwood 1.6A now, and a mobo with a chipset (SiS 645DX or Via P4X333) with some FSB headroom. Throw some fast DDR-I into it.

      Two years down the road, I think you'll probably be able to plunk in another "$50 CPU and $20 stick of RAM" behind the OS's back, giving you decent performance for another year.

      There are no guarantees, of course, but by paying a $50 premium for quality parts today, you can often get better than 50/50 odds of saving $500+ two years from now. That's a good risk, IMNSHO.

    17. Re:Clever Marketing Scheme by Anonymous Coward · · Score: 0

      Oh I'm sorry, I didn't realise you were an Indy Car fan. If I had know that, I would have put it in less complicated terms for you. /s/gravel trap/gravel surfaced run off/g/

    18. Re:Clever Marketing Scheme by ealar+dlanvuli · · Score: 1

      I upgrade my PC regularly..

      The trick is to wait 2-3 years then upgrade the 'core' components all at once, it's a ton cheaper than buying a new system, and you end up with top of the line stuff.

      Of course, you can't stay at the very top of every component at all times, but considering a standard mobo/ram/cpu has been ~300 for quite a while, it's not to horrible.

      --
      I live in a giant bucket.
  16. Getting old... by Little+Dave · · Score: 3, Funny

    Hell, it makes you feel old when 512Mb is being bandied around as the standard memory size. I remember getting all excited about a 512k(!!) trapdoor expansion for my Amiga, for which I paid 100 quid for.

    Oh yeah, and this whole website was fields back then... far as the eye could see. ;)

    1. Re:Getting old... by Skater · · Score: 1

      My favorite minor upgrade: buying an extra 128k to max out my IBM clone at 640k! It came in individual chips, too, no easy-to-plug in card!

      :)

    2. Re:Getting old... by gosand · · Score: 2
      Hell, it makes you feel old when 512Mb is being bandied around as the standard memory size.

      I hear you. I am sure there are those that have many more stories, but I remember shelling out over 2 grand for my 386DX-33 with 2 MB of RAM and 80MB hard drive. I now have more than 3x the amount of space in my RAM (256M) than I used to have in my hard drive. I must be sleeping - when did 512M become the standard memory size? Crap, I don't even have DDR memory. I am running just a piddly AMD Athlon 900 SLOT processor. I remember when the "internet" was Gopher and FTP. Hey you kids, get off my lawn!! :-)

      --

      My beliefs do not require that you agree with them.

    3. Re:Getting old... by Little+Dave · · Score: 1

      Yeah, the more I think about it, the more things like that come back to me and the more factors of a thousand crop up to haunt me. Example: 250 quid for a 120Mb hard drive in 1994. Compared to an 80Gb hard drive for 90 quid in 2002.

      And I'm still running at about 10% free space at any one time!

    4. Re:Getting old... by haa...jesus+christ · · Score: 0

      I think I can top that. $3k+ for a tricked out PC jr. in 1986. Of course I had 2 floppy drives and 640k of ram, so I was sufficiently badass, which justified the cost.

    5. Re:Getting old... by Explo · · Score: 2

      Hell, it makes you feel old when 512Mb is being bandied around as the standard memory size. I remember getting all excited about a 512k(!!) trapdoor expansion for my Amiga, for which I paid 100 quid for.


      I remember buying 3 kilobyte memory expansion cartridge with some new BASIC commands (the Super Expander) for VIC-20. I've forgotten the price, though. Anyway, it was nice to have more than 3584 bytes for BASIC programs available ;) (and some seriously nice graphics commands to improve the rather lacking CBM Basic V2.0). Funny, it doesn't feel like almost 20 years have passed since that; I still have that machine and the cartridge around, although I haven't switched it on for a long time to see if it still works.

      --
      Everyone who makes generalizations should be shot.
    6. Re:Getting old... by Analog+Squirrel · · Score: 1
      > I remember when the "internet" was Gopher and FTP. Hey you kids, get off my lawn!! :-)

      Don't forget about archie! google - pffft! :-)

      --
      I'd rather be flying
    7. Re:Getting old... by slashhot · · Score: 0

      What about those 8kB memory expansions for the Sinclair ZX81?

    8. Re:Getting old... by slashhot · · Score: 0

      Hell, I remember using a (dead tree) book, the Internet Yellow Pages, to find interesting ftp sites!!!

    9. Re:Getting old... by Anonymous Coward · · Score: 0

      Well, 512Mb isn't much, just 64MB. 64MB is pretty much past nowadays.

  17. Not Moores law by plarsen · · Score: 1

    You could be sure to say that the Memory development line isn't exactly following Moores law. But that's okay tough, since that wasn't Moores intension.

  18. Generic Memory Company Plan by ackthpt · · Score: 1
    * TOP SECRET * Invest heavily into materials research License applicable intellectual property Re-tool or build new fab Produce more memory than market needs in effort to crowd out competitors When all competitors do same thing complain for years how memory market not profitable and any-minute-now prices will have to go up Continue to overproduce and cut prices Repeat for each advance in memory technology
    --

    A feeling of having made the same mistake before: Deja Foobar
  19. Importance by coryboehne · · Score: 2, Insightful

    The importance of faster, cheaper RAM is obvious, however I do find it hard to get excited about a technology that will at best be in new systems in about a year, probably later. RAM speeds have skyrocketed, but unfortunately bus speeds have'nt, unless you're an overclocking guru this RAM just won't mean much to overall performance gains - just yet. But all the same, every step forward is a great step.

  20. IBM PPCs by Yet+Another+Smith · · Score: 2

    What with IBM making the G-4s for Mac, and making this chipset, d'you think they could finally bring Macs out of the PC100 world, and get a memory pipeline worth having?

    --
    if ($it != $onething) {$it = $another;}
  21. Um by denjin · · Score: 1

    First, they only make G3s for Apple currently. Also, Macs use PC133, and the newest server line uses DDR. They do need to work on the processor side though, supposedly the CPU itself can't interface with DDR, so a lot of the bandwidth goes unused.

    1. Re:Um by Alan+Partridge · · Score: 1

      partially true, those news Macs with DDR can't actually manage DDR from the CPU to the main mem, only from the "northbridge" to the main mem. Should be addressed when Apple moves to the MPC 7470 CPU (currently using MPC 7455). You're right though, IBM doesn't make G4s, although the "Sahara" G3 apparently DOES support DDR memory bus.

      --
      That was classic intercourse!
  22. A few facts by Anonymous Coward · · Score: 5, Informative
    Intro: I am D. C. Sessions, and I'm the chair of JC-16 (one of the committees which participates in the DDR standard). Here are a few facts:

    The two big reasons for the generational change are

    • Voltage change: DDR II is going to 1.8 volts to allow thinner gate oxides and denser, faster devices.
    • Internal timing. First-generation DDR has some architectural timing issues which make it impossible to go much beyond 333 in volume production.

    Yes, this makes for backward-compatibility problems.

    Yes, the Committee (JC-42.3) put a huge amount of work into making DDR-II as backward-compatible as possible

    Yes, we're starting work on DDR-III. You'll have to wait until 2006 or so.

    Target speeds for DDR-II were set at 600 MT/s for fully-loaded systems and 800 MT/s for embedded stuff like graphics.

    The signal-integrity issues for DDR-II are ugly, but we met the margin specs with lots of conservativism thrown in, so once we get hands-on time with systems you'll probably see the numbers exceeded just as the original DDR targets were.

    Flame away. You can get more info at JEDEC or Advanced Memory International.

    1. Re:A few facts by Zathrus · · Score: 2

      What exactly is MT/s as you refer to it? It's apparantly Mega data transfers/sec, but I haven't found anything that relates this to more common measurements such as MB/s or similar. (My guess - what it sounds like, with overall bandwidth being MT/s * bus width)

      Apparantly current DDR is running 200-400 MT/s (although the Micron page that had this information was rather odd in and of itself, with higher CAS times giving a higher MT/s), so this is either a significant upgrade (300%) or moderate (50%) if those numbers are right.

    2. Re:A few facts by Anonymous Coward · · Score: 0
      Yes, MegaTransfers/sec -- we coined the term because "MHz" doesn't work for DDR (or worse yet AGP 4x, 8x, etc) systems.

      The Micron data may be effective transfers in system applications rather than peak burst rate. I'd ask Micron next week, except I'll be skipping this meeting for personal reasons.

    3. Re:A few facts by Zathrus · · Score: 0, Redundant

      I can understand the issue of MHz vs systems that do multiple transfers per clock cycle (it's rather similar to the old bps vs baud difference for modems, where 9600 bps modems ran at 2400 baud using a Grey map to transmit 4 bits of data per cycle). Given that, MT/s should be equivalent to 2*MHz for DDR since there are two transfers per cycle.

      If so, then I'm missing something... since 333 MHz DDR I would have 666 MT/s by that definition, which is already higher than the spec'd maximum you list for DDR II.

      Clarification would be welcome.

    4. Re:A few facts by Anonymous Coward · · Score: 0

      DDR-333 is actually 166 MHz clock frequency, with two data transfers per clock cycle. I can't help the fact that people incorrectly refer to it as "333 MHz" -- that's the reason why we're trying to get away from the "MHz" business in the first place.

    5. Re:A few facts by Zathrus · · Score: 0, Redundant

      Doh. I'm half asleep today. Bonk.

      And yes, I just made a wonderful example of myself for why MHz is a bad thing here.

      Thanks for the clarification.

  23. 533Mb/s?? by Anonymous Coward · · Score: 0

    Is 533Mb/s right? For some reason that sounds a bit slow. Hell, my Ethernet card can pump out data almost as fast as that. If we assume that this DDR-II is running at 266MHz, then that means that it can only transfer TWO BITS per clock cycle?

    1. Re:533Mb/s?? by cyr · · Score: 1

      Probably 533Mb/s per data pin at 266MHz.

      That gives us 533*64/8 = 4.2GB/s for a 64bit bus.

    2. Re:533Mb/s?? by cmdr_beeftaco · · Score: 1

      i wish i had your network card...

  24. Actual clock speed and bandwidth specs by wpmegee · · Score: 1

    The actual clock speed is 200mhz and 266 mhz ddr for 400 (PC 3200, @ 3.2 gb/s), and 533 (PC4300 @ 4.3 gb/s), respectively. TheInquirer points this out, along with some more specs. Also, way back on May 2, JEDEC approved the standard.

  25. MOBO switch killing OS by Guppie · · Score: 1

    Well, I've managed to break both win98 and win2000 by switching motherboards. (Crashing all the time, finding lots of new devices, messing up IRQs, etc.)

    I think most other OSes handle that stuff better...

  26. IBM Chipset for which CPU? by ayden · · Score: 4, Interesting

    The article says that IBM made a chipset to take advantage the new memory speed, but what CPU does the chipset support? Athlon? P4? G4/G5? Anyone? Bueller? Bueller? Frye?

    --
    "I'm The Bounty Bear. I will find him anywhere. I'm searching."
  27. fucking marketting! by Cyno · · Score: 3, Insightful

    Gah! I fucking hate marketting! Why can't they just call it QDR, because that's what it is. Quad Data Rate fucking DIMMs. God damn it, motherfucking, sun of a bitch!

    1. Re:fucking marketting! by Anonymous Coward · · Score: 0

      i concur!

    2. Re:fucking marketting! by Anonymous Coward · · Score: 1, Insightful

      I believe the Double Data Rate term just refers to the fact that it is clocked on the rising and falling edges. Since those are the only two edges you can have, you can't very well have Quad Data Rate :)

    3. Re:fucking marketting! by addaon · · Score: 2

      Actually you can. You can clock on rising and falling edge, and both 'flat points' of the clock. I've seen this used in some circumstances, and it basically does give you quad pumped... no idea if that's what they're actually using here, though.

      --

      I've had this sig for three days.
    4. Re:fucking marketting! by Cynikal · · Score: 1

      because the average consumer is becomming confused with what is better/newer than what..
      if they keep changing the name of the ram, people wont know what to buy. by calling it ddr2, the consumer knows its the "sequel" to ddr, and if their motherboard supports it, they can then have an easier time deciding what ram they want...

    5. Re:fucking marketting! by fini · · Score: 1

      Why can't they just call it QDR

      'Cause there's already something called QDR. See QDR consortium. It's a high speed SRAM with separate input and output data I/O buffers, and 2 tranfers in (write) and 2 transfers out (read) per clock cycle, hence 4 transfers per cycle total. It's fairly popular for packet buffers in routers and switches alike.

      --
      SNS Not Sig
    6. Re:fucking marketting! by Cyno · · Score: 1

      Yeah, its kinda like one.e.and.a.two.e.and.a.three.e.and.a and so one. Some nice jazzy tempo for yer computing needs.

    7. Re:fucking marketting! by Anonymous Coward · · Score: 0


      So the full abbreviation would be QDRF DIMM? :P

  28. EXA Anyone? by OS24Ever · · Score: 3, Interesting

    Have you not seen the new intel servers IBM is releasing like the x360 and x440?

    Need more PCI? Add a drawer of 12 and plug in a cable. Need more processors? Buy another four way and plug them together, you have an eight way.

    Hot swap a failed memory dimm lately? You can in a x440.

    There are a lot of cool tech coming from IBM in the xSeries servers. There are only so many marketing guys out there

    But it sure is easy to bash IBM, so people do. They are changing. You think the layoffs of the last year or two are getting rid of the good people and not the middle management?

    --

    As a rock-in-roll Physicist once said, No matter where you go, there you are.

    1. Re:EXA Anyone? by lionchild · · Score: 1

      Well, being an ex-IBMer, I have a little room to talk about them. I like -alot- of things they do. But, as stated, their biggest problem is they need better marketers. OS/2 would still be competitive today, I suspect, had IBM been able to market it properly.

      --
      Awk! Pieces of eight. Pieces of eight. Pieces of seven... ERROR: General Protection Fault. [Paroty Error.]
    2. Re:EXA Anyone? by DragonWyatt · · Score: 2

      Sun has had this for awhile. Well, it's not as easy as cabling up boxes- but the architecture is similar, if not better.

      Check out the Ultra Port Architecture. Basically a meta-bus that you can put CPUs, memory, and other buses (PCI, SBUS, etc) on.

      --
      Don't sweat the petty things. But do pet the sweaty things.
    3. Re:EXA Anyone? by OS24Ever · · Score: 2

      True, and so has IBM in their AIX pSeries / RS6000 series.

      The xSeries however is Intel architecture. In that sense it's brand new cutting edge for that architecture.

      --

      As a rock-in-roll Physicist once said, No matter where you go, there you are.

    4. Re:EXA Anyone? by Noehre · · Score: 1

      PCI expansion is hardly revolutionary.

      Being a bus architecture, you can add additional PCI slot fairly easily. It just happens that it isn't very common in the commodity PC market because your standard PC case only has room for 7 expansion slots.

      In 1U rackmount servers PCI expansion cards for horizontal (to the motherboard) are common.

      LSI makes a highish-end 64-bit/66mhz PCI expander that I believe had 3 64-bit/66mhz slots on it.

  29. SDRAM - DDR - DDR-II transitions by dpilot · · Score: 3, Interesting

    I suspect that there were really two factors at work in the short DDR-I lifetime.

    First, Intel muddied the waters with the big exclusive Rambus push. While there was DDR work going on prior to the Rambus push, there was some very real contention in carrying both programs through development. This doesn't even mention quite a bit of "wait and back the winner," at many levels of the industry.I suspect that the success of the Athlon competing with PIII had almost as much to do with DDR success as Rambus prices.

    Second, there were very real signal integrity issues that had been skirted for quite some time, and really came to the fore with DDR. That took some time, but more thought has been applied forward to DDR-II, so it shouldn't be as painful.

    --
    The living have better things to do than to continue hating the dead.
  30. You must LOVE WindowsME by Marx_Mrvelous · · Score: 2

    Since it keeps all that backwards compatibility.
    On a serious note, keeping backwards compatibility both stifles development and raises cost. I don't complain that new computers are cheaper and faster than they ever have been.

    --

    Moderation: Put your hand inside the puppet head!
    1. Re:You must LOVE WindowsME by goldspider · · Score: 1
      "I don't complain that new computers are cheaper and faster than they ever have been.
      "


      That may be true, but I'd venture a guess that most people interested in this site don't upgrade in whole-computer increments.

      Perhaps, though, doing so is the best way to keep upgrade costs down.

      --
      "Ask not what your country can do for you." --John F. Kennedy
    2. Re:You must LOVE WindowsME by Marx_Mrvelous · · Score: 2

      I do know what you mean, of course, that upgrading one thing means upgrading a bunch. Personally I think they've done a pretty good job providing previous-generation support in motherboards (there were a ton of boards out there that supported both DDR and SDRAM, there were boards that supported SDRAM and EDO, EDO and FPM, etc). CPUs is another matter, of course, but you can use same board for anything from a duron 600MHz to a 1.8GHz Athlon MP. What *I* want to know is why do they still have two serial ports on most computers? I haven't used one in years.

      --

      Moderation: Put your hand inside the puppet head!
  31. servers and multiservice machines by Anonymous Coward · · Score: 0

    will see the benefit. I agree that the average home user will not really gain any true benefit, but the 'gotta have the newest most expensive gadget' folks will help drive the price down for everyone else.

  32. who modded this down, it is funny by Anonymous Coward · · Score: 0

    more text here

  33. who cares, they look pretty by Anonymous Coward · · Score: 0

    I'll take 'artiness' over usability any day

  34. Re:-1, Lifeless Loser by Anonymous Coward · · Score: 0

    Please moderate the previous puny post as such.

  35. Re:the big question is... "ALL IN ONE" MEMORY by geekster_2000 · · Score: 1

    3D Volume Holographics Optical Storage NanoTechnology wants to replace all memory devices with one storage device to handle all
    system memory requirements replacing DDR, SRAM,DRAM, MRAM, FRAM, CD, DVD, TAPE, HARD DRIVES, OVONIC, etc.

    www.colossalstorage.net

  36. Memory Pipelines by hotsauce · · Score: 2

    The Xserve has a DDR bus.

    The G4 will remain at 133 or 166 MHz because all effort is going into the G5's pipe.

  37. They claimed 100Ghz chips within 2 years... by kfsone · · Score: 1

    The story on the IBM site linked from the slashdot story claimed 100Ghz chips within two years (although we're talking comms chips) "IBM expects the new transistor will result in communications chips at speeds of 100 GigaHertz (GHz) within two years -- five times faster and four years sooner than recently-announced competitive approaches." So naturally I was curious what that might mean in terms of regular chips. Oliver

    --
    -- A change is as good as a reboot.
  38. Re:IBM Chipset for which CPU? (None) by qnonsense · · Score: 1
    • ...what CPU does the chipset support...
    None as far as I could tell. From the Samsung press release it looks as if the chipset IBM developed isn't a "chipset" as you're using the term. You're thinking Northbridge (or MCH in Intelspeak), i.e. a "chipset" that controls your CPU, memory, AGP, IDE, PCI, (and in combo with a Southbridge, or ICH in Intelspeak) USB, Parallel, Serial, ADB, ISA, IrDA, Audio, SmartCard, or whatever.

    The IBM-developed DDR-II chipset in question here is simply a memory controller, i.e. a small (but important) part of the Northbridge in what you're calling a chipset.
    --
    There comes a time in every man's life when he must say, "No mother! I do not want any more Jell-O!"
  39. Re:IBM Chipset for which CPU? (None) by ayden · · Score: 2

    I had a high school English teacher who once said, "Brilliant people make complex things simple."

    Thank you for the clarification. Brief, to the point; the perfect response.

    --
    "I'm The Bounty Bear. I will find him anywhere. I'm searching."
  40. gigabit ethernet cards are growing common by Anonymous Coward · · Score: 0

    And cheap, too! Apple is shipping with gigabit Ethernet standard on many of its models even.

  41. Dance Dance Revolution?! by Anonymous Coward · · Score: 0

    I don't understand what this has to do with Dance Dance Revloution!

  42. Because it's not QDR. by jefp · · Score: 1

    The data lines are still clocked at DDR, but there are twice as many of them.

  43. Motherboard makers might just skip it. by jefp · · Score: 2, Informative

    DDR-II is basically equivalent to on-chip interleaving - the data path is clocked the same but twice as wide. Well, board makers are now doing motherboard-side DDR interleaving themselves - see recent boards based on the ServerWorks GC-LE or Intel E7500 chipsets. Some manufacturers might just decide not to bother with DDR-II.

  44. what is up with Moderators today? by Anonymous Coward · · Score: 0

    I am seeing very good questions on a number of threads modded down, while absolute crap is elevated. If you don't agree with something someone says, that is not the reason to mod them down... same with modding up for agreeing.

  45. test by Cmdr+Taco+posted · · Score: 1

    test

  46. Re:the big question is... "ALL IN ONE" MEMORY by Anonymous Coward · · Score: 0

    Buttcunt crapflooder! Snort a Jew, you asstard tulipmonger! Suck a duck and choke on anuslicking cocksnot in reverse, you monkeyfuck assclown.

  47. WOW by Anonymous Coward · · Score: 0

    Its really great that you can transfer your entire memory contents in less that 8 seconds with a 4.2GB/s transfer speed :D