Become a fan of Slashdot on Facebook

 



Forgot your password?
typodupeerror
Check out the new SourceForge HTML5 internet speed test! No Flash necessary and runs on all devices. ×

4x4 Chips, Opening AMD's Architecture 229

Nom du Keyboard writes "Once upon a time open slots in a PC that anyone could build a card for were a good idea. PCs with them sold better than PCs without them. Now AMD is proposing another new socket that will be open for plugging in of 3rd party co-processors directly on the processor bus." They've also announced a 4x4 chipset, meant to counter Intel's Core 2 Duo chips. From the article: "Socket 4x4 will have a more immediately impact. Set for a release in the latter half of this year, it essentially lets you combine two dual-core Athlon 64 X2 or Athlon 64 FX chips to create a quad-core desktop PC now ... AMD made the point that Socket 4x4 also provides a more flexible upgrade path for a single motherboard system by letting you start with one chip and add another later on. AMD didn't talk pricing, but you can bet neither the Socket 4x4 motherboards, nor systems that use it to include two dual-core CPUs will be cheap."
This discussion has been archived. No new comments can be posted.

4x4 Chips, Opening AMD's Architecture

Comments Filter:
  • 4x4 chips! (Score:5, Funny)

    by suv4x4 ( 956391 ) on Thursday June 01, 2006 @04:38PM (#15448956)
    If they waste more electricity, are more noisy and increase the likelyhood for fatal accidents, count me in!
  • 4x4? (Score:4, Insightful)

    by Anonymous Coward on Thursday June 01, 2006 @04:39PM (#15448965)
    If you're combining two dual core chips, wouldn't that be 2x2? Or even 2x4 (or 4x2), but 4x4? That makes no sense. Looks like they're using the Chewbaca marketing technique.
    • Re:4x4? (Score:3, Interesting)

      by JDevers ( 83155 )
      4 CPU cores x 4 GPU cores

      These systems are designed to handle the dual SLI systems the GFX companies are starting to push.

    • Re:4x4? (Score:4, Funny)

      by purpledinoz ( 573045 ) on Thursday June 01, 2006 @04:46PM (#15449013)
      I think AMD is banking on the average person's inability to multiply 2 single digit numbers.
    • Re:4x4? (Score:3, Informative)

      by jonnythan ( 79727 )
      A 4x4 truck doesn't have 16 wheels.
    • by Surt ( 22457 )
      No, it's 4 cores and 4 gpus if you read their presentation slides (2xdual core procs, 2x dual gpu video boards).
  • Guns racks? (Score:5, Funny)

    by crotherm ( 160925 ) on Thursday June 01, 2006 @04:40PM (#15448977) Journal


    While these come with the gun racks standard?

  • by GillBates0 ( 664202 ) on Thursday June 01, 2006 @04:41PM (#15448979) Homepage Journal
    When using your AMD(TM) quad-core desktop computer at the campgrounds, always practice safety. Surround your quad-core computer with rocks to keep the fire from spreading. Be sure when you're done with your quad-core computer to put it out with a bucket of water and make sure it has stopped smoking before you leave the area.

    Remember what Smokey the Bear says. Only you can prevent your AMD(TM) quad-core desktop computer from starting a forest fire.

  • by Frightening ( 976489 ) on Thursday June 01, 2006 @04:41PM (#15448982) Homepage
    ..with jet propulsion.

    • I had a vision of a JATO unit strapped to DELL in a flashback to a Darwin Award Winner. I think I have been on Slashdot and the net too long. UGGGHHHH.
  • Sounds neat (Score:4, Interesting)

    by drewzhrodague ( 606182 ) <drew@@@zhrodague...net> on Thursday June 01, 2006 @04:42PM (#15448987) Homepage Journal
    As a sysadmin, this sounds neat -- but I haven't seen any computing environments that need that kind of horsepower yet. But, I can't wait to crank-up my distributed.net [distributed.net] ranking.

    At my last contract, we used IBM Bladecenters -- Linux in a dev/QA environment, and they had prolly the largest load-generator farm I've ever seen. It wasn't the CPUs that were maxed, tho -- just the network.
    • As somebody who does scientific computing (molecular dynamics), this sounds terrific. Four cores on the same board means really low communication latency, cheaply. This will reduce by a factor of four the number of expensive low-latency network interconnects needed to build a cluster of a given size.
      • and don't forget graphics rendering (eg for movies).

        There again, will this supplant normal quad-processor motherboards? And will they gain quad 4x4 sockets for 16 CPU systems??? :-)
      • I don't see what the fuss is about; 2-socket motherboards have been available for years and most scientific clusters already use them.

        This will reduce by a factor of four the number of expensive low-latency network interconnects needed to build a cluster of a given size.

        Not if you want to maintain constant bytes/flop.
        • What does "bytes/flop" mean?
          • Network interface throughput (in bytes/s) divided by floating-point operations per second; this represents the compute/communication balance that tends to be inherent in scientific cluster applications. So if you double the number of processors but keep the same number of network interfaces, your bytes/flop is 2X worse, which may limit application performance.
            • By that logic a cluster of 4 separate machines, each with one CPU, is better than one machine with 4 cores on one mainboard (all other things being equal of course). That does not make sense to me. Am I missing something?
    • Re:Sounds neat (Score:5, Insightful)

      by vertinox ( 846076 ) on Thursday June 01, 2006 @05:16PM (#15449193)
      As a sysadmin, this sounds neat -- but I haven't seen any computing environments that need that kind of horsepower yet.

      I take it you don't do any scientific calculations or physics modeling at your place of work.

      And I assume that you don't do 3d animation or video editing either?

      Or mabye mass amounts of OCR, Photoshop, or anything else that puts CPU usage at 100%

      Sure 90% of the computer market doesn't need this, but the other 10% is willing to shell out the big bucks to be the early adopters. Eventually this will be passed down to the rest of the 90% when the next big thing comes along.

      Oh and don't forget the gamers...
      • I don't think _most_ server farms really require all that much CPU (much less floating point.. that's why Sun actually has a market with their T1000 and T2000 chips, but I digress). IO is usually the bigger bottleneck, be it memory, disk, or network.

        Me, I'll take a 2 CPU/core server with 32 GB of memory over a "4x4" CPU server with say only 4 GB of memory any day.

        • Me, I'll take a 2 CPU/core server with 32 GB of memory over a "4x4" CPU server with say only 4 GB of memory any day.
          Unlike Intel, AMD has dual-core chips with decent performance/watt that actually support 64 bit. In other words, why would you assume this "4x4" thing limits you to 4 GB of memory?
    • by Sloppy ( 14984 ) on Thursday June 01, 2006 @05:40PM (#15449332) Homepage Journal
      but I haven't seen any computing environments that need that kind of horsepower yet.
      That's why I run Gentoo -- my machine spends so much time running gcc that I can always justify an upgrade without worrying about pragmatic concerns. ;-)
      • I hear you there, buddy. When you are installing X and your WM (or have to recompile everything after a major GCC upgrade) the more cores the merrier. I have an X2 4200+ and it is fast- but it's more fast in it only takes me 12 hours to recompile everything instead of 2-3 days on my old P4 2.2A machine. I'd have gotten an Opteron DP board and two 265s or 270s, but I'd have spent more just on the CPUs and board than I spent on my whole machine, $530 20" LCD included :(

        Something like this would have been a go
    • Heh, in most companies a sysadmin doesn't deal with people who really use their computers. Show me a computer built in the next 5 years and I'll max out the processor (as could most graphics people), whether it's rendering 3D content (which is kinda cheating 'cause the processor goes straight to 100% anyway), or trying to scrub through 1080p video in a video editor.

    • This isn't a need, it's a want, and I really WANT a 4x4.
  • Quad machines... (Score:4, Interesting)

    by Space cowboy ( 13680 ) * on Thursday June 01, 2006 @04:42PM (#15448990) Journal
    I thought the current dual-socket motherboards (eg this board [newegg.com]) could already accept dual-core Athlon (well, Opteron) chips (eg: the 270 series [newegg.com]) to make a quad-core machine ?

    Actually if this isn't the case, I'll be very grateful if someone could tell me, because I was thinking of ordering the above for a replacement webserver...

    Simon
     
    • Re:Quad machines... (Score:4, Informative)

      by Wesley Felter ( 138342 ) <wesley@felter.org> on Thursday June 01, 2006 @04:47PM (#15449025) Homepage
      I thought the current dual-socket motherboards (eg this board) could already accept dual-core Athlon (well, Opteron) chips (eg: the 270 series) to make a quad-core machine ?

      They can; 4x4 appears to be a new marketing label for the same thing. (Just as "Athlon" and "Opteron" are the same chip already.)
      • Re:Quad machines... (Score:4, Informative)

        by Jeff DeMaagd ( 2015 ) on Thursday June 01, 2006 @05:29PM (#15449275) Homepage Journal
        Just as "Athlon" and "Opteron" are the same chip already.

        Has AMD started enabling multiple hypertransport links in the Athlon chips? Opterons have two or three hypertransport links, Athlons only have one link active. Yes, it is artificial, but that makes sure the people that are likely to need it are going to pay for the feature. The multiple links are needed to chain or mesh multiple CPUs together. Maybe the "4x4" chipset is another crosspoint switch to get around the limit of the single link, though it might add latency by adding another hop or two.
        • Has AMD started enabling multiple hypertransport links in the Athlon chips?

          That's what they just announced. What AMD has crippled, they can uncripple whenever they feel like...
        • Re:Quad machines... (Score:3, Informative)

          by tomstdenis ( 446163 )
          Um to be more correct all K8 processors have THREE HT links. The difference is whether they can act as coherent links. A 2xx series processor will have one link between processors and at least one to the northbridge I/O controller.

          Tom
    • I thought the current dual-socket motherboards (eg this board) could already accept dual-core Athlon (well, Opteron) chips (eg: the 270 series) to make a quad-core machine ?

      Yes. The new board appears to be more consumer-level and hopefully less expensive.

      What I am really hoping for is the vague "other processors" note - perhaps this is also meant as a responce to Cell and the other socket could be populated with a DSP chip. That would be fun !

    • "quad core" means in one processor package.

      You can currently have upto eight dual cores on one network. There are products that extend this with cHT enabled switches so you can go pretty high in the # of nodes.

      You can't MP a Athlon64/FX setup because the memory is local to the processor [e.g. not the northbridge] and there are NO cHT links.

      Tom
    • I believe the idea is a more compact two-socket interface. Almost all of the existing two socket boards are extended-ATX, and will not fit in consumer-friendly mini-tower.
      • There are a lot of regular ATX-format DP boards. I have built computers with them, and they do fit in a regular mid-tower ATX case. Granted, it may be a pretty tight fit dependent on the board layout, size of the GPU (if present) HDDs and optical drives, but they do fit.
    • Re:Quad machines... (Score:3, Informative)

      by Surt ( 22457 )
      I believe what they're going to be offering is dual socket motherboards that take athlon rather than opteron pinouts.
    • I've currently got two boxes in a rack here at the office.. an HP DL 580 and an HP DL 585. Both have four dual core CPUs (580 has 4 DC Xeon's, 585 has 4 DC Opteron's) for a grand total of 8 procs per box. So yes, both AMD and Intel have this technology already... only thing different here seams to be marketing it to a home desktop environment instead of a server environment.
    • Re:Quad machines... (Score:3, Interesting)

      by Amouth ( 879122 )
      We have had this ability in highend servers for a long while (the ability to add diffrent types of chips and 3rd party stuff) it is known as a backplane

      the problem is that they are not like AMD's HyperTransport bus (which makes this really neat) - but wouldn't it be better all around if we moved towards more backplane styles for higher end stuff?

      the highest spec backplane i remember was a 64bit 66Mhz PCI bus.. what if we where to move that to PCIe with a massive amount of Lanes.. or have AMD open up their
    • Re:Quad machines... (Score:2, Informative)

      by 5pp000 ( 873881 )
      I have a Tyan Thunder K8SD Pro (S2882-D) set up with dual Opteron 275 CPUs, running Linux. Works fine. I would expect other Tyan motherboards to work as well.

      You will need a pretty recent version of Linux. I am running SuSE Linux Enterprise Server (SLES) 9 Update 2, except that I've upgraded the kernel to a 2.6.14 from kernel.org. My suggestion: go with the latest Red Hat Enterprise, or wait for SLES 10, due out any week now.

  • Dual processor (not dual core) systems have been the domain of server chips like the Opteron and Xeon, ever since Intel split the Xeon off from the PIII line. The motherboards for them (not to mention the processors themselves) are very expensive... this is good news for enthusiasts.

    Will AMD hurt itself by undercutting Opteron sales?

    Will Intel follow suit with its consumer chips?
  • by bunbuntheminilop ( 935594 ) on Thursday June 01, 2006 @04:44PM (#15449005)
    As I just noticed last night that the newer kernels support CPU hotplugging.
  • There is no FSB and the memory is LOCAL to the processor. How would this maintain coherency? The Athlon64 processors also don't allow cHT. Not that they don't physically have support for it, just it's been disabled.

    Given where I work, and that I've never heard of this before today... I suspect it's a hoax.

    The only way this would work is if the OS was aware of it and manually routed data from one node to another (e.g. like a northbridge DMA device you can pipe info to).

    Tom
    • Re:Cache coherency? (Score:3, Informative)

      by Visaris ( 553352 )
      There is no FSB and the memory is LOCAL to the processor. How would this maintain coherency? The Athlon64 processors also don't allow cHT. Not that they don't physically have support for it, just it's been disabled.

      Given where I work, and that I've never heard of this before today... I suspect it's a hoax.

      The only way this would work is if the OS was aware of it and manually routed data from one node to another (e.g. like a northbridge DMA device you can pipe info to).

      AMD's own slides from the 200
  • by Kesch ( 943326 ) on Thursday June 01, 2006 @04:51PM (#15449048)
    Even though every uber-gamer is gonna need a 4x4 for bragging rights and IPE(Imaginary Penis Enlargement), it won't be that much of an upgrade for hardcore gaming until more games break out of the single-threaded event loop. Multiple processors only work on multiple threads.

    I hear rumors that people use processing power for other things, but I think those are just myths. (Actually I just started to work for a high-performance computing group and they'll probably be excited by the new AMD offerings)
  • Yeah, but .... (Score:5, Insightful)

    by texaport ( 600120 ) on Thursday June 01, 2006 @04:53PM (#15449064)
    open for plugging in of 3rd party co-processors directly on the processor bus.

    AMD won't happen to produce any of these "3rd party co-processors" will they?

    I haven't been this excited since Intel started selling 386SX chips that allowed us
    to buy Cyrix (or Intel) math coprocessors for twice what a non-crippled DX cost!

    • The 80386 microprocessor never shipped with an in-built maths co-processor in either the SX or DX models. The difference between the SX and the DX was that the SX had a 16bit external data bus and can address a maximum of 16MB of physical memory (much like the 80286). The DX had 32bit external data bus and could address 4GB of physical memory.

      In a way, the 80386SX was to a 80386DX in the same way that an 8088 was to an 8086.

      The i486 was the first to have an integrated maths co-processor and early i486sx was
    • Re:Yeah, but .... (Score:3, Interesting)

      by Eric Smith ( 4379 ) *

      AMD won't happen to produce any of these "3rd party co-processors" will they?

      No, by definition. If AMD produced them, they wouldn't be "3rd party".

      It seems unlikely that AMD would try to get into the coprocessor market. Unless they find an extremely compelling coprocessor idea, they'll make more money using their wafer starts for more Athlon, Opteron, Sempron, and Turion processors than they would by devoting some of those wafer starts to coprocessors.

      The example of a security coprocessor is quest

  • English motherfucker! Do you speak it?
  • Opening up calculator, typing "4x4" computer says 4 (cores). Oops.
  • Now maybe there can be at last a truly powerful seti accelerator [slashdot.org]!
  • Poor Article (Score:3, Insightful)

    by clump ( 60191 ) on Thursday June 01, 2006 @05:03PM (#15449123)
    This article lacked any real substance and was as vague as possible.
    It also unveiled its new Socket 4x4 motherboard interface, which will let enthusiasts put two dual-core CPUs on a single motherboard.

    What does that mean? A motherboard with 2 processor slots? A motherboard that accepts two dual-core processors? We've had both, and for a while.

    I wish online editors wouldn't publish meaningless articles like this, and I wish sites wouldn't link to them.
    • It's 2 processor slots on the motherboard. What's interesting about the announcement is that apparently AMD is sneaking dual-processor capable athlons (not opterons) out the door.
    • Re:Poor Article (Score:5, Informative)

      by hattig ( 47930 ) on Thursday June 01, 2006 @05:18PM (#15449214) Journal
      It's not a new socket, it's two Socket AM2s next to each other which accept standard AM2 processors such as the X2, which have a coherent HT link enabled on them for this use.

      It's consumer version of a dual-processor Opteron motherboard, with a specific socket layout and memory system that's more directed at consumers. AMD will support this in 2007 with 4x4+ (2 quad-core processors on AM2) and in 2008 with 4x4++, whatever that may be.

      These motherboards will also support two x16 PCIe graphics card slots, which if you configured using quad-SLI gives you the other 4. 4 CPU cores, 4 GPU cores.

      It's mostly marketing to keep the high end benchmarks in AMD's hands, and thus the kudos, and then further sales.

      Quite clear really, although I'm confused as to why AMD didn't go the MCM route on a single socket, like the Pentium D and the upcoming Kentsfield processors from Intel.
  • ...this is going to end up just like every other off-the-wall motherboard/CPU/video card/etc' feature: way too expensive for anybody to care about. Remember the mobo a while back that would take either an AMD or an Intel CPU? It was basically two mainboards on the same PCB and it costed about as much.

    This also looks quite a bit like SLI/Crossfire in that it's marketed as "add on more stuff later to boost performance and save money in the long run." It looks nice on paper, but in practice, it's pretty
  • by Deliveranc3 ( 629997 ) <deliverance.level4@org> on Thursday June 01, 2006 @05:42PM (#15449344) Journal
    I am not a business major, but I was an AMD stock holder from when it was trading at $7.55 to $40.

    AMD has been jacking up their prices which we have assumed is simply a response to their higher quality and increased market share but it has done something interesting. AMD is now selling the majority of high end desktop and workstation cpus but they have low marketshare in high end servers and low end desktops.

    It would be easy to claim that these are new strategies implemented by Ruiz their new CEO however they would imply a more stock holder less comsumer driven business and AMD's poor marketing (low marketing budget?) and the $100 laptop project seem to rule out this possibility.

    If we look back over the history of AMD it becomes interesting to look at chips like the Athlon MP which went through severe price reductions immediately prior to the release of the Opteron.

    Implementing dual cpu chipsets on the desktop is likely a strategie implemented imediately before moving their low end to dual core and their high end to a new cpu architecture.

    Amd will likely try to match Intel's price and consumer points, low end desktop (with dual core if my predictions about their consumer centric and engineering company bias are correct), high end desktop (catering to the SLI crowd and consolodating on the likely long term presence of socket AM2 (or subsequent sockets, AMD's 754 for an example of a short term socket), workstation (likely with the same socket but with quad core cpus), low end server (Opteron or replacement) and some kind of new high end chip.

    The prediction about a new high end chip is based on reduced gap between the current opteron line and the 4x4 system layout.

    All of this is very predictive, but based on my studies of AMD's engineering, ethics, and sales history.
    • AMD has been jacking up their prices

      No, AMD almost always reduces their prices, just as Intel does. Isn't competition great?

      Perhaps what you meant was that the stock market has been raising AMD's share price. That's a different thing entirely. AMD doesn't directly control its share price; that is affected by the market's perception on how well AMD is performing financially, whether they meet their projections and the analysts' forecasts, how their business is perceived to compare with Intel's, and

  • you can bet neither the Socket 4x4 motherboards, nor systems that use it to include two dual-core CPUs will be cheap.

    I remember when people said that about the 80386. They were great for servers, but way too expensive for your own desktop. (Maybe that why I still don't have a 386 on my desktop!)

    Today's expensive stuff is tomorrow's obsolete dinosaur. What I'm getting at is this: you can bet it will be cheap. It's just a question of when.

    • Well, two chip packages will always be more expensive than one. Any PIII could easily be put into a dual-processor system, but the fraction of SMP users was always very low. A normal P4 can't do SMP on its own, Intel chose to make that a differentiator for Xeon. The same thing basically applies to SLI for video -- the affordable way to get 4 cores will not be some "4x4" scheme, but rather just the K8L, in a single package. Likewise, the mainstream users will generally just get a more powerful single video c
  • If a coprocessor that can do the same kind of mass calculation that a DSP or a GPU can do is incorporated into an architecture, I wonder if even more speedup can be had for all kinds of tasks in general.
  • for server and desktop before AMD...
  • ... drool over Boxx's APEXX 8 machine [boxxtech.com]. It's 8 dual core AMDs with up to 128 gigs of ram. Got one at the office. We can't wait to try our app on it. :)
  • The heyday AMD has been having with Intel and their nutbust architecture is coming to an end, mid-July. Picture this, Intel is going to blow out the price floor on AMD and offer better performance, clock per clock, in addition to outclocking the K8 by a healthy margin (~20%). the T6600, an low-end chip is proving to outperform the FX-62 (AMD's bad dog) in pretty much every category worth noting, has full support for X86-64, and has a lower TDP. Comparing price is a joke, the T6600 is going to retail for
    • You're overstating your case. Intel currently has no answer to HT, and that's necesary for both multi-cpu and multi-core chips. AMD will continue to firmly trounce Intel midrange server segment, which is hurting them where it counts indeed, and the cause for things like Dell's recent uptake of AMD. As well as Googles.

      C//
    • The latency of HT sucks compared to what? The shared crap bus Intel STILL uses for the Xeon? Or compared to uber expensive offboard transports that are still many times slower? Core is good no doubt, but the recent ramp up in feature count and speed means that the new top of the line Core 2 Duo Extreme is going to use about the same amount of power as AMD's top of the line chips, which is pretty bad considering how trim the Pentium M line was.

If in any problem you find yourself doing an immense amount of work, the answer can be obtained by simple inspection.

Working...