Slashdot Mirror


AMD Bumps Up Socket AM2 Launch Date

Thrill-Ki1l writes "According to DailyTech AMD has moved up the launch date for their new socket AM2 processors. The manufacturers of the new AM2 chipsets and motherboards have their hardware ready to ship early so AMD decided to launch the chips 2 weeks early. The new launch date is May 23rd."

234 comments

  1. condolences by caffeinemessiah · · Score: 2, Insightful

    to everyone who just dropped a ton of cash building a brand new athlon x2 socket 939 systems...my condolences. at least this will bring the price of the higher-end athlon x2s down for the rest of us...yay!

    --
    An old-timer with old-timey ideas.
    1. Re:condolences by mrchaotica · · Score: 2, Insightful

      You would hope anyone building a system would have done their research and would have known that new chips were coming.

      --

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

    2. Re:condolences by Bin+Naden · · Score: 2, Interesting

      I didn't get screwed: I bought the cheapest CPU with a socket 939 motherboard and will buy a better CPU once the prices go down much like 754 cpu went down once 939 came out.

      --
      There should be a "-1:Groupthink"
    3. Re:condolences by ePhil_One · · Score: 5, Funny
      You would hope anyone building a system would have done their research and would have known that new chips were coming.

      Really, the jokes on the people who by this new socket. I hear that eventually it well be replaced with something even newer! I'm waiting until 2019, when there will be no more computer upgrades (society will collapse July 17th, 2019, ending all new product development short of the flint arrowhead)

      --
      You are in a maze of twisted little posts, all alike.
    4. Re:condolences by Grey_14 · · Score: 1

      New chips are ALWAY'S coming, why worry? By time this really affects prices, anyone currently currently running a top of the line system will probably be wanting to upgrade again anyway's,

    5. Re:condolences by Bob_Robertson · · Score: 4, Insightful

      Actually, the release of new hardware should drop the price of dual and quad 939 motherboards to buyable levels, as well as the dual core 939 CPUs.

      It's not like the 939 performance has dropped, only that the bleeding edge has cut another swath. Let them go, and enjoy the savings!

      Bob-

      --
      The Ludwig von Mises Institute. The reasoning individuals economics
    6. Re:condolences by bersl2 · · Score: 2, Interesting

      How about those of us who dropped not so much cash on such a system?

      As long as I catch DDR1 prices at its lowest point (to reach 2GiB RAM total), my Opteron 165 @ 2.49 GHz system should cut it for a while.

    7. Re:condolences by Anonymous Coward · · Score: 0

      Cudos to the guy with the patent on the flint arrowhead then...

    8. Re:condolences by mrchaotica · · Score: 2, Informative

      Well, when you're this close to the launch of the new socket you might as well wait in the hopes that you'll be able to upgrade the CPU or motherboard separately once over its lifetime, if you so choose.

      --

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

    9. Re:condolences by toddestan · · Score: 3, Insightful

      Actually, I feel sorry for the people who built 754 systems back in the day. It seemed that AMD moved onto Socket 939 pretty quickly after that one.

      Though I really feel for anyone who has a Socket 423 Pentium IV system. Very short lived standard (1.3-2.0Ghz), expensive rambus memory, 100Mhz bus ("quad pumped" to 400Mhz), and really odd CPU coolers that screw into the motherboard that are virtually impossible to get replacements for.

    10. Re:condolences by Barny · · Score: 1

      I am assumeing you mean 940 sockets, 939 does not support multi sockets.

      --
      ...
      /me sighs
    11. Re:condolences by Entropius · · Score: 1

      I think I've got some prior art on that that I found lying in a cotton field.

    12. Re:condolences by caspper69 · · Score: 1, Insightful

      Exactly. I once held off on buying a dual-cpu motherboard because I didn't think the (south)chipset was up to snuff. How stupid. Here was a motherboard with 3 PCI-X(66) and 1 PCI-X(133) (in addition to two PCI32 slots and two PCIe x16 slots). I was upset because the USB host controller only supported USB1.1. Completely neglecting the fact that I could buy a trivially inexpensive add-in card and get the same functionality with minimal effort. People always look to the latest and greatest, but fail to ask one simple question: "What is it buying ME?"

      If it's not a huge increase in speed, then you have to understand that legacy platforms will continue to be supported for a good deal of time into the future. Never wait. Who cares? I know there are individual (and technologically sound) reasons why you would, but reviews have stated for ages that AM2 doesn't deliver any boost, and until DDR2-800 is available may not offer any tangible benefit whatsoever.

      So what's wrong with buying a nice dual or (drool) quad core desktop with socket 940 processors? You can (at this very instant) buy a quad core with dual x16 SLI and all the integrated platform goodies for about $400. If you wait until AM2 feeds down the pipe, it'll drop by 30%. My questions is this: if this lower priced platform still allows expandability with the peripherals you desire, and still supports (into the forseeable future) any new processor revisions, then what's the problem??

      There isn't one. Take care (power) bargain shoppers!

    13. Re:condolences by TubeSteak · · Score: 5, Funny
      I'm waiting until 2019, when there will be no more computer upgrades (society will collapse July 17th, 2019, ending all new product development short of the flint arrowhead)
      You know that very few people use the Mayan calendar anymore?

      It was the flint arrowheads that gave you away.
      --
      [Fuck Beta]
      o0t!
    14. Re:condolences by kg4czo · · Score: 1

      July 17th, 2019? Damn, my hatchday is the 18th. Couldn't they wait until the 19th? Why they gotta be hatin'?!?!

    15. Re:condolences by Aardpig · · Score: 1

      Actually, I feel sorry for the people who built 754 systems back in the day. It seemed that AMD moved onto Socket 939 pretty quickly after that one.

      Amen to that. I'm stuck with two S754 systems. I sooooo wish I'd paid a few extra dollars to get 939....

      --
      Tubal-Cain smokes the white owl.
    16. Re:condolences by zmilo · · Score: 0

      Ah...but not true. How do you account for the jump from T-100 to T-1000, then? :D

    17. Re:condolences by Lord+Kano · · Score: 1, Funny

      That would really suck because it's the day before my birthday.

      Do you know the time? If it's going to be 00:00 GMT then I'm fucked.

      LK

      --
      "Hi. This is my friend, Jack Shit, and you don't know him." - Lord Kano
    18. Re:condolences by whereiseljefe · · Score: 1

      Mayan prophecy is Dec. 21st, 2012 I believe....

      Searching teh googly eyes and I can't seem to see where "July 17th, 2019" comes from...

      --
      http://www.andrewsmcmeel.com/godsdebris/
    19. Re:condolences by PayPaI · · Score: 2, Informative

      According to the article S754 is going to actually outlast S939.
      AMD's Socket 754 to Outlast Socket 939

    20. Re:condolences by buswolley · · Score: 3, Insightful
      I just built an AMD 64 3800+ X2. I researched for quite a while, and was completly aware of the new socket. This does not bother me.

      1)I can't really imagine anytime soon when I will need more power than I have with this system.

      2) The price was good.

      3)You can overclock the shit out of them.

      4)I can scan for viruses, rip a cd, and play a top end game concurrently without a glitch or slow down.

      5)It is a stable mature technology(socket 939). I previously made the mistake of purchasing the first edition of a new intel socket, and regretted it for years.

      Let the new sockets, chips and boards work out their chinks before you buy, I say.

      --

      A Good Troll is better than a Bad Human.

    21. Re:condolences by Firehed · · Score: 1

      Considering that AM2 currently offers zero performance increase over s939 chips (in effect, it's simply moving the platform to DDR2 now rather than waiting for AMD's Conroe-equivalent), the possibility to upgrade would be nice. However seeing that you can still buy Socket A chips, I wouldn't worry about the availability of this-gen parts for quite some time, especially considering how widely successful s939 is among enthusiasts.

      --
      How are sites slashdotted when nobody reads TFAs?
    22. Re:condolences by Anonymous Coward · · Score: 0

      940?

    23. Re:condolences by spectrumCoder · · Score: 1

      Sure, the upgrade path of socket 939 may be limited, but reports suggest (http://www.anandtech.com/cpuchipsets/showdoc.aspx ?i=2741) that performance of AM2 and S939 CPUs will be very similar. Assuming that the new range of processors for socket AM2 is priced higher than the current Socket 939 range, those buying a Socket 939 x2 now will actually get a better price-to-performance deal than if they waited for an AM2, albeit at the expense of limited futureproofing.

    24. Re:condolences by Anonymous Coward · · Score: 0

      I lost track of sockets at the Athlon Thunderbird Socket A. I sort of woke up to boggle and laugh at the whole Socket 940/939 thing and then went back to sleep.

    25. Re:condolences by Anonymous Coward · · Score: 0

      It's not a big deal, because AM2 is actually a bit slower than 939 anyway (thanks to higher latency DDR2). So Im happy as hell with my X2 4800+ and 3GB of DDr1 with Nforce4 chipset and 2TB of disk space and Geforce 7800 GTX and will be for quite some time to come.

    26. Re:condolences by HuguesT · · Score: 1

      Don't feel sorry for me, there is no point.

      I bought a S754 system almost 2y ago. You can still buy new processors for my very own mobo today, great ones too, in the form of the latest and greatest Turion processors. A year later I bought the almost exact same system for my parents.

      Do you know any current mobo for which you think you'll be able to buy a compatible CPU in 2 year's time ?

      Also it was incredibly cheap, the CPU works with passive solid-state cooling and is still running like a champ. It was thus because AMD was pushing 939 instead, but I couldn't see the benefits at the time, and still don't except perhaps for PCIe, which I have no use for right now. At any rate I couldn't have bought AMD + PCIe then, and 939 was much more expensive, it was really an easy decision.

    27. Re:condolences by buswolley · · Score: 0, Redundant

      I mean you can overclock it.. I haven't yet, and it still performs as I described. Man I'm so glad to be off that old RAMBUS mojo.

      --

      A Good Troll is better than a Bad Human.

    28. Re:condolences by Nutria · · Score: 2, Funny

      So Im happy as hell with my X2 4800+ and 3GB of DDr1 with Nforce4 chipset and 2TB of disk space and Geforce 7800 GTX and will be for quite some time to come.

      Geez, how could you not be happy with that system? Must be kinda noisy, though.

      --
      "I don't know, therefore Aliens" Wafflebox1
    29. Re:condolences by tlynch001 · · Score: 2, Funny
      I can scan for viruses, rip a cd, and play a top end game concurrently without a glitch or slow down

      If you ran linux you wouldn't have to worry about the virus scanner.

      I guess you would'nt have to worry about the game either...

    30. Re:condolences by maxwell+demon · · Score: 1

      Let's see ... 2019-07-17
      take digit sums -> 12,7,8
      multiply -> 672
      subtract digit sum of year -> 666
      Ok, now we know what will happen on that date! :-)

      --
      The Tao of math: The numbers you can count are not the real numbers.
    31. Re:condolences by Anonymous Coward · · Score: 0

      Why?

      I have a S754 system and it seems to me the biggest factor limiting upgrades is that it still uses AGP. Unless you bought (relatively) recently, 939 had the same problem.

    32. Re:condolences by GoatMonkey2112 · · Score: 1

      Why does it matter to most people? How many people *REALLY* upgrade just the CPU? It usually doesn't make much sense to do it anymore. And after that what are you supposed to do with the old CPU? Sell it on ebay for $25? Doesn't seem to be worth the effort of doing it.

      I'm not saying that I won't wait personally, but if you didn't and just bought a 939 board recently, it doesn't stop being good as soon as AM2 exists. Ooooh, somebody else waited an extra 3 months to buy and got a system that is 2% faster (maybe), it's the end of the world.

    33. Re:condolences by buswolley · · Score: 1

      I run both.

      --

      A Good Troll is better than a Bad Human.

    34. Re:condolences by MarkVVV · · Score: 1

      You can't scan for viruses and play a "top end game" at the same time (you can, but loading would be very slow), since the former is not cpu dependant, it's I/O intensive.

    35. Re:condolences by COMON$ · · Score: 1

      I thought the Mayan calendar ended in 2033...maybe that is the maori, either case that is the day of the end of human history which the only thing to survive will be spambots.

      --
      CS: It is all sink or swim...oh and did I mention there are sharks in that water?
    36. Re:condolences by Gr8Apes · · Score: 1

      Sure you can - depends upon your I/O subsystem. IDE/SATA isn't the be-all end-all of I/O you know, SCSI/SCSI RAID will actually allow for multiple operations simultaneously (although the new SATA with queuing I haven't checked out yet, if it truly works as advertised, the old standard SCSI might finally have met its match. SAS, however, will still smoke full SATA/SATA II).

      --
      The cesspool just got a check and balance.
    37. Re:condolences by Deliveranc3 · · Score: 1

      Most system builders knew what they were getting with the 754...

      Socket A had dual channel memory and the biggest problem with 754 was no support for Dual Channel, people knew what they were getting into.

      Aside from memory bandwidth 754 is still a great platform with both AGP and Pci-E boards available and EXTREMElY affordable, the 3700+ for s754 has very very good performance for it's price, s754 would eventually have been able to encorperate dual channel memory if AMD had gotten the support from the chipset manufacturers.

      Actually AM2 is probably the most abortive socket so far, unless the DDR manufacturers REALLY improve DDR2 it could be another example of Intels RDRam fiasco...

      939 will be the base for AMD's budget processors of the future and is probably going to be the best deal for a while.

    38. Re:condolences by WuphonsReach · · Score: 1

      to everyone who just dropped a ton of cash building a brand new athlon x2 socket 939 systems...my condolences. at least this will bring the price of the higher-end athlon x2s down for the rest of us...yay!

      Frankly, it doesn't matter. I can count on one hand the number of people that I know who have upgraded CPUs instead of replacing the entire MB/CPU/RAM as a bundle. And the majority of those had more money then sense and were simply trying to stay on the bleeding edge. Unless you cheap out on the CPU at the very start of a socket's life-cycle, it's very rare that you can get enough of an upgrade out of a CPU to make the CPU-swap worth it.

      (However, the dual-core CPUs do upset that calculation a bit. But that's only worthwhile if you're moving from a single-core CPU to a dual-core CPU.)

      Plus, newer motherboards typically have better features (USB v2 vs 1.1, Gigabit LAN vs 100Mbit, PCIe vs PCI, SATA vs PATA, FSB speeds, memory bandwidth). So if you really want to get the most performance gain out of a new CPU, it's best to put it in a newer motherboard.

      --
      Wolde you bothe eate your cake, and have your cake?
    39. Re:condolences by arodland · · Score: 1

      Apparently you don't understand the meaning of "I/O bound". Okay, you have SCSI. We'll say that through some amazing physics this allows you to read twice as much data from disk per unit time than the rest of us. Your virus scan task will happily take all of it, leaving pretty much exactly the same amount of "whatever's left" for loading Halo maps. Allowing multiple requests in flight doesn't help latency that much when the real issue has a lot more to do with the time it takes heads to fly across a platter.

    40. Re:condolences by tomstdenis · · Score: 1

      Socket A most certainly did not have dual channel memory.

      Socket A didn't even have a memory controller. The Northbridge may have but the FSB was still a single pipe.

      Athlon-MP systems [at least dual] had their own pipes to the northbridge.

      This is why Intel has their 800Mhz FSB. The northbridge is dual-channel [or interleaved] and it feeds the cpu as fast as possible.

      Tom

      --
      Someday, I'll have a real sig.
    41. Re:condolences by Gr8Apes · · Score: 1

      Apparently you don't understand I/O bottlenecks, how disk access works, and what the differences are between IDE/ATA/SATA(non-queuing) collectively referred to as IDE henceforth, and SCSI systems.

      On the IDE front, when you load a file, you load the entire file. If it's a 10MB file, you load all 10MB. Thread priority is irrelevant. Hence, your anti-virus software appears to be hogging the drive while it's reading it. (I should note this depends upon how the software accesses the file. It's also possible to only read in segments of a large file, thus allowing other processes access to the disk in-between requests for segments, I would hope most AV software uses this approach)

      On the SCSI front, if a process starts loading a file, you can request multiple other files from the same drive while AV requested file loads. The large file load only has bandwidth impact on I/O, which if the thread is low-priority will allow the higher priority game thread(s) 100% access.

      Then you get to the point of RAID, and true theoretical bus bandwidths. But that's another story. Ever wonder why all enterprise servers use SCSI? (We're not talking about the cheap webservers, but real servers). It's because IDE as a whole sucks rocks in the performance world with multiple access.

      Now as for being I/O bound: generally this means you've saturated the platter to internal buffer limits of the drive, which is much lower than bus bandwidths or the burst speeds listed on drives (eg, ATA100 or ATA133). On carefully designed RAID systems, you can actually exceed bus limitations, and reach the theoretical bandwidth of the PCI bus you're on (a maximum of 512MB/s on a 64bit 66MHz PCI bus). A 2 or 3 channel SCSI controller can get you there with 4-5 disks per channel, but there are other bottlenecks.

      Lastly: to allow yourself to speed up disk access in general, buy a second disk and place it on a different channel than your system disk. Use this disk for games only. Remove it from AV scans, and you'll be able to run both with 0 impact.

      --
      The cesspool just got a check and balance.
    42. Re:condolences by default+luser · · Score: 1

      Exactly. These days, there is no such thing as future-proofing.

      Take the Athlon / Athlon 64 line, for instance. In the past, we've seen nice upgrades in bus speed (100, 133, 166, 200), and if you invested in a motherboard with faster bus speed support, and good enough ram, you could upgrade for cheap.

      Socket 939, with the introduction of the X2 processor, also offered an opportunity for a (relatively) cheap upgrade from single core.

      But where does that leave us now?

      Over the past two years, AMD has gained only 800 MHz at the top-end, and this is all thanks to the tweaked 130nm, and later, the tweaked 90nm process. It sounds like a lot, but percentage-wise, it has not been impressive. Only the introduction of dual-cores has kept performance improvements in line with market demand.

      Slow performance gains means one of two things: expand to quad-core processors, or redesign for better Instruction Per Clock (IPC) rates.

      So what happens when we go quad-core? Not so much. Most multithreaded applications are designed to take best advantage of dual-core processors. Beyond that, there are only so many people who do constant hardcore multi-tasking, and even then you run into I/O limitations hindering multi-tasking gains. Also, unless AMD finds a way to magically pump up the HT bus and improve the performance of their dual-channel DDR2 controllers, the 4 cores will be data-starved. Quad-core is only going to find a foothold in servers, and ONLY if AMD releases better performing memory and HT busses.

      So what does that leave us? Like Intel's Conroe, AMD will have to redesign the Athlon 64 for greater IPC, and like Intel, AMD will have to prioritize process improvements. Neither of these seem to be happening, so the future of "upgrades" on the AM2 platform is pretty bleak.

      Me, I just bought a 3800+ X2 plus 2GB ram. The prices I've seen for AM2 X2s are exactly the same as those for Socket 939, and DDR 2GB is not any more expensive than performance DDR2 (ie, DDR2 800). I'll get more out of overclocking the 3800+ than I ever would purchasing an upgrade in the future.

      Even if I didn't overclock, the performance gains of upgrading to a 2.6, 2.8 or maybe 3.0 GHz X2 a year or two down the road aren't exactly impressive.

      --

      Man is the animal that laughs.
      And occasionally whores for Karma.

    43. Re:condolences by God'sDuck · · Score: 1

      prior art? clearly you mean preemptive patent infringement.

    44. Re:condolences by drinkypoo · · Score: 2

      I have a hard time feeling bad for people who went to systems supporting RAMBUS. People who don't know shit about computers wouldn't know - but they should be asking someone who does know about 'em what they ought to buy, and anyone who makes an unresearched purchase can just fuck off. Including me, when I do something that dumb.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    45. Re:condolences by Anonymous Coward · · Score: 0
      On the IDE front, when you load a file, you load the entire file. If it's a 10MB file, you load all 10MB.


      Huh? Is this a stupid OS's decision? Because IDE is just a communication bus and protocol.

      The issue is that modern disk drives present a false geometry when queried, meaning software running outside the drive unit itself cannot guarantee accurate guesses about the layout of the disk, and therefore cannot accurately optimize the order of accesses.

      Without command queueing requests as issued by the software (and controller) are handled and answered in lock-step. With CQ requests are issued and answers may return out of order. If requests go out A, B, C, D but the physical data for C will spin under a drive head before any of the others, that operation will be done before A, B or D. TCQ and NCQ have differences with respect to out-of-order acknowledgments and head-of-line blocking; the former can require in-order operations and supports different priority levels.

      Low-level drivers may take the presence of CQ into account, particularly with respect to TCQ's in-order operations (for things like soft dependencies), however this is neither universal nor necessary. CQ simply allows the drive to reorder instructions based on unexposed knowledge of device internals much as OoO reordering in hardware like modern x86 CPUs.

      Drivers deal in blocks -- file systems deal in files. The file system layer requests a series of blocks in some order from the driver, which in turn order-optimizes the requests and feeds them to the controller (and then to the drive). Multiplexing is done at the file system layer in all modern OSes. So two concurrent accesses to different files will result in the driver layer being asked for blocks in an interleaved fashion. CQ in the target drive can reduce the amount of time it takes to serve these blocks across the bus; it does not enable the initial concurrency.

      SCSI's advantages over IDE are mostly that the disks spin faster and controllers are not limited to a primary and secondary device, and the electrical properties of parallel SCSI busses are more stable than parallel IDE busses.

    46. Re:condolences by Anonymous Coward · · Score: 0
      Let the new sockets, chips and boards work out their chinks before you buy, I say.

      What do Chinese people have to do with this?

    47. Re:condolences by buswolley · · Score: 1
      oK i MADE IT UP.

      But I can play a game, while playing mp3s and, download Linux, while masturbating.

      --

      A Good Troll is better than a Bad Human.

    48. Re:condolences by Lord+Flipper · · Score: 1
      prior art? clearly you mean preemptive patent infringement.

      Ha ha ha, and here I am with no mod points, wouldn't you know. Apparently the topic is too serious for the sense-of-humor squad.

    49. Re:condolences by Anonymous Coward · · Score: 0

      Until now, AM2 processors seems to be just as fast (maybe a bit faster) than the S939 processors. However, the DDR memory is phasing out, and DDR2 memory is about as cheap as DDR. All good for a new computer or a mainboard plus processor upgrade.
        Again, moving all processors to a single socket is good - you reduce the production diversification for your partners (mainboard manufacturers)

    50. Re:condolences by Gr8Apes · · Score: 1

      I agree with what you've said. However, here's the real deal on Windows, and you can verify this yourself if you have a single IDE drive and Windows. (I'm not sure whether this is MS's IDE driver, or the actual HD hardware, although I suspect it is the HD hardware, for reasons that follow)

      If you have an Exchange server and outlook, email yourself a nice large file, perhaps a 10MB JPG. Now open that JPG from the server. Note that you are pretty much hamstring until the file is downloaded locally and opened. This is especially effective if you throttle your connection speed to really show off the locking effect.

      second test: Get a nice video image (for DVDs) and have that image located on your HD. Using DVD Shrink, open the image/files. Now try to open anything (app, doc, generic file).

      On 3 different systems, these actions all have resulted in action 1 completing before action 2 even appeared to start.

      Now try these on a SCSI system. You're no longer locked out. IIRC, effective CQ doesn't exist on IDE hardware. It's why SATA drives that actually support TCQ is such big news, and why SATA drives that support it are closer to SCSI than IDE drives in price (for similar drive specs, of course).

      Unfortunately, I have no Linux/Solaris comparisons, as those all run SCSI HDs.

      --
      The cesspool just got a check and balance.
    51. Re:condolences by Harik · · Score: 1
      On the IDE front, when you load a file, you load the entire file. If it's a 10MB file, you load all 10MB. Thread priority is irrelevant. Hence, your anti-virus software appears to be hogging the drive while it's reading it. (I should note this depends upon how the software accesses the file. It's also possible to only read in segments of a large file, thus allowing other processes access to the disk in-between requests for segments, I would hope most AV software uses this approach)

      On the SCSI front, if a process starts loading a file, you can request multiple other files from the same drive while AV requested file loads. The large file load only has bandwidth impact on I/O, which if the thread is low-priority will allow the higher priority game thread(s) 100% access.

      Were you just simplifying here, or do you not understand Queuing vs non-queueing systems? I would have ignored it except for the comment on AV software. _ALL_ software should request as much data as it needs as quickly as possible, and let the OS handle resource allocation. Your seperate drive comment is sometimes OK, but you have to remember to manually scan it from time to time. Even legit game CDs sometimes come with unexpected bonuses, and it's worse if you're getting games from slightly shady sources.

      All operating systems post DOS don't allow one process to request a 10-gb fileread and hard-lock the disk for the next hour. NCQ gets around the fact that nothing but the drive really understands the physical geometry of data, and requests things in such a way that the head sits idle due to rotational latency. If you submit the request to the drive NCQ it can internally re-order the reads to return the entirety of your request in the shortest time.

      Isn't PCI-X 133mhz 64bit now? Takes quite a lot of I/O to saturate that bus.

      And Linux is finally supporting SATA NCQ, thank god.

    52. Re:condolences by Gr8Apes · · Score: 1

      Check your hardware specs. NCQ is a new addition created for SATA drives. It is a less capable version of TCQ. TCQ currently exists on SCSI only. As far as I know, it was never actually implemented in IDE even though the original spec called for it. Hence, the ability to completely bork your system with a simple file request with IDE hardware.

      On a side note, you'd trust MS to properly deal with resource allocation? This would be the same company that had a single threaded GDI module in their supposedly multi-threaded OS for years?

      Lastly, in another post in this thread, I gave two simple test cases to try on your single drive IDE system. I guarantee you both will shed unwelcome light on the shortcomings of IDE and improperly written software, including MS software.

      --
      The cesspool just got a check and balance.
  2. summary by The_GURU_Stud · · Score: 5, Insightful

    what should also be on the summary is that it was bumped up to coincide with Intel's paper launch.

  3. w00t by GrumblyStuff · · Score: 0, Offtopic

    What else can we say?

  4. WD AMD by Anonymous Coward · · Score: 0

    Wow it's nice to see a launch date come forward for a change. Props to AMD. Those guys must really have a hand on their engineering. PS. I don't work for AMD.

  5. Is it really worth it? by Bin+Naden · · Score: 5, Insightful

    Is it really worth it to be an AMD processor with a DDR2 memory controller? Sure this meant a lot for the intel architecture but from what I understood the AMD architecture will not gain a lot from this memory speed increase. Also, the latency on the memory will likely also increase which might cancel all gains made from the increased speed. Therefore, I'm waiting and seeing before I get me one of those.

    --
    There should be a "-1:Groupthink"
    1. Re:Is it really worth it? by MBCook · · Score: 5, Interesting
      There was an article somewhere recently (Anandtech? Tom's Hardware?) checking performance of DDR2 versus DDR on the Opteron. They determined that DDR speeds below 533 (IIRC) would hurt the performance. At 533, it was about even. As the processor and or memory speeds up then you will see the benefit. This isn't strictly necessary right now. I think it was actually due to the latency issue that you mentioned that this was the case.

      I'd rather see FB-DIMMs, personally. But the move to DDR2 was going to happen at some point. Better now (when it's not necessary and people can still choose a great processor and DDR combo) then later (when DDR is more expensive and they were hurting for the change).

      I seem to remember that was going to be something else with this socket upgrade (in the form of processor features) that was more interesting or offered better performance increases than the memory change. I don't remember if it was SSE4 (is that out yet?), a better branch predictor, AMD's Vanderpool (can't remember the name), or what.

      --
      Comment forecast: Bits of genius surrounded by a sea of mediocrity.
    2. Re:Is it really worth it? by PsychicX · · Score: 4, Informative

      This article examines the question in depth. Hope that helps.

    3. Re:Is it really worth it? by Bin+Naden · · Score: 1

      OMG, 7% increase in performance! That means at least 2 extra frames per second on Oblivion!

      --
      There should be a "-1:Groupthink"
    4. Re:Is it really worth it? by Bin+Naden · · Score: 2, Funny

      I'd rather see FB-DIMMs

      A maximum of 192 GB of RAM... Is that enough for windows Vista?
      http://www.anandtech.com/cpuchipsets/showdoc.aspx? i=2741&p=9/

      --
      There should be a "-1:Groupthink"
    5. Re:Is it really worth it? by Anonymous Coward · · Score: 0

      I remember when it was Intel that was the worst culprit with changing sockets. The story back then was that it was to appease the motherboard manufacturers (ie. if you needed to upgrade your CPU by a significant amount, you usually had to upgrade the motherboard as well as the socket had been changed in the meantime). I wonder how much of that was true, and how much it is relevant to AMD now.

    6. Re:Is it really worth it? by tetromino · · Score: 1

      Is it really worth it to be an AMD processor with a DDR2 memory controller?

      Yes, if you care about the price of memory in your new machine. The price of DDR2 is generally expected to drop below DDR1 during this year, as manufacturers convert DDR1 production lines to DDR2. The performance won't change by more than a couple percent though (because the higher bandwidth of DDR2 is almost exactly cancelled out by its worse latency).

    7. Re:Is it really worth it? by DrMrLordX · · Score: 1

      That's only with expensive enthusiast DDR2. Common DDR2-533 can actually produce speeds slower than equivelant s939 parts. Sad huh?

    8. Re:Is it really worth it? by Doomstalk · · Score: 1

      Is it really worth it to be an AMD processor with a DDR2 memory controller?

      Well, it's certainly easier than my old dream of being an astronaut...

    9. Re:Is it really worth it? by hackwrench · · Score: 1

      "Expensive enthusiast" RAM is the common RAM of the future.

    10. Re:Is it really worth it? by ArbitraryConstant · · Score: 2, Informative

      "Sure this meant a lot for the intel architecture but from what I understood the AMD architecture will not gain a lot from this memory speed increase."

      Early indications are that Intel's architechtural improvements with Conroe will give them a significant edge over AM2 chips, even though AMD still has an on-die memory controller and Intel doesn't.

      "Also, the latency on the memory will likely also increase which might cancel all gains made from the increased speed."

      They'll be using 667 and 800 mhz clock speeds, so it won't be too bad, but the gains from the extra memory bandwidth aren't as big as one might expect. At least for AMD.

      "Therefore, I'm waiting and seeing before I get me one of those."

      Sound advice for any pre-launch situation. :)

      I'm going to take the wait-and-see approach as well, but so far looks like I'll be continuing my pattern. My last few computers have been Pentium II, Athlon, Pentium 4, and Athlon 64.

      Though I rarely get top-of-the-line chips, so if AMD cuts the prices for their high-end stuff when Intel has faster parts, that might make them preferable even if Intel holds the performance crown at the time.

      I mostly want dual cores and hardware-supported virtrualization so I can run OpenBSD under Xen. Both AM2 and Conroe will have that, so it's pretty much a question of who gives me the best performance.

      --
      I rarely criticize things I don't care about.
    11. Re:Is it really worth it? by interiot · · Score: 2, Informative

      Yeah, Pacifica (AMD's hardware virtualization support) is going to be available for the first time with AM2.

    12. Re:Is it really worth it? by agallagh42 · · Score: 1

      "OMG, 7% increase in performance! That means at least 2 extra frames per second on Oblivion!"

      I think there's something wrong with your math. 2 extra frames per second in Oblivion equals a 200% increase in performance:

      old fps = 1
      new fps = 3
      increase = 2

      2/1=200%

      --
      Carpe Cerevisi - Seize the Beer
    13. Re:Is it really worth it? by Barny · · Score: 1

      "I'd rather see FB-DIMM"

      FB-DIMM increases the latancy of ram, effectively adding multiple memory controlers off the die. So far as amd have been preaching (and done a good job of showing in practice with the a64 core) off die memory controlers are a bottleneck.

      --
      ...
      /me sighs
    14. Re:Is it really worth it? by Mr+Z · · Score: 1

      AMD integrated the memory controller onto the CPU. The downside of this is that whenever memory technology changes, the pinout must also change.

    15. Re:Is it really worth it? by Anonymous Coward · · Score: 0

      So few people upgrade their CPUs that that conspiracy theory is implausible. Intel's socket changes usually have legitimate reasons (faster bus, increased power, etc).

    16. Re:Is it really worth it? by Bin+Naden · · Score: 1

      new fps = 3

      Or 3 cps (crashes per second) in my case.

      --
      There should be a "-1:Groupthink"
    17. Re:Is it really worth it? by John+Jamieson · · Score: 1

      Early indications are that Intel's architechtural improvements with Conroe will give them a significant edge over AM2 chips, even though AMD still has an on-die memory controller and Intel doesn't.

      Actually, early indications seem to indicate that it stomps the Athlon when everything fits in the massive L1 Cache, but the "architechtural improvements" you talk about only bring it up to parity without the gigantic cache. (anyone can add cache, it is an expensive move that you only make if you really need the performance)

      That Anand "preview" was in a very controlled situation, we really need to read more than ONE article before we decide who is king, and that Conroe will be superior to AM2

    18. Re:Is it really worth it? by ArbitraryConstant · · Score: 1

      "Actually, early indications seem to indicate that it stomps the Athlon when everything fits in the massive L1 Cache, but the "architechtural improvements" you talk about only bring it up to parity without the gigantic cache. (anyone can add cache, it is an expensive move that you only make if you really need the performance)"

      Even if that's true, Intel usually holds a pretty big lead in moving to smaller processes, so bigger caches aren't likely to leave their arsenal.

      "we really need to read more than ONE article before we decide who is king, and that Conroe will be superior to AM2"

      Well, I certainly won't be making purchasing decisions until I read multiple reviews of shipping hardware. These are just early indications.

      --
      I rarely criticize things I don't care about.
    19. Re:Is it really worth it? by John+Jamieson · · Score: 1

      Yep, Intel is the Fab king, so if anyone can get away with a large cache it is them. At the same time, wafer size is money, and they are hurting on the profits (by analysts standards, not mine), so you know they would love to drop the cache sizes if they could get away with it. Also, they were claiming to be capacity constrained for the last half a year I believe. So much so, they were sending Motherboard OEM's to other chipset manafacturers because they couldn't produce in sufficent volumes.

      All this leaves me a bit confused, because it seems like they have a lot of low end cpu's floating around in the channel at firesale prices.(mind you these are small cache, small die) But maybe this is just an attempt to pull down AMD's Average Selling Prices (ASP) on the desktop at the expense of some of thier other business.

      All I know it that when Intel shows this great new Conroe, and the cache size on the initial units is 4MB, It makes me wonder if they even believe they have a superior product. If they believed that, they would have a 1 MB cache - take the profit and run. (we will see, maybe I am wrong)

    20. Re:Is it really worth it? by M0b1u5 · · Score: 1

      I agree: not worth throwing good money after bad once you have purchased a PC - with one noteable exception: It pays to jam as much RAM into it as you can, before retiring it.

      RAM prices are volatile enough, and crash a period after the market leader changes its memory type, such that it is dirt cheap to fill old boxes up with maximum RAM.

      It's teh cheapest upgrade, and conicidentally, also the most performance enhancing. Users really appreciate it, and it does extend the lifetime of the product again.

      However, replacing a CPU? The labour in swapping them makes it uneconomic in my view. I have certainly never upgraded a computer CPU and have built over 200 computers and owned 'em non-stop since 1977.

      It's just not worth it: kinda like putting $1000 tyres on a VW Beetle. The new CPU is invariably starved of data, and is significantly held back by the aged form factor.

      --
      How many escape pods are there? "NONE,SIR!" You counted them? "TWICE, SIR!"
    21. Re:Is it really worth it? by Lonewolf666 · · Score: 2, Insightful

      AFAIK DDR2 brings better throughput but at the expense of more latency. For the current AMD chips the overall result seems to be equal, but once you go to more cores I guess the throughput will become more important.
      A few months ago I've read a review of AMD Opteron vs. Intel Xeon dual cores. For one socket, both systems had similar memory bandwidth and while the AMD was faster, the difference was not dramatic. For two sockets (4 cores total), the Xeons still had to make do with the same memory bandwidth because they shared the memory interface, while the Opterons gained a second memory interface because each socket has its own memory controller. In the test results, the two-socket Opterons completely smoked the Xeons. Conclusion:
      When four processor cores have to share a memory interface, it better be a damned fast one.

      Now AMD has announced that they want to introduce four-core processors eventually. Hence the need for plenty of bandwidth.

      --
      C - the footgun of programming languages
    22. Re:Is it really worth it? by tomstdenis · · Score: 1

      The latency issue gets masked when you start talking DDR2-667 and DDR2-800. Anything less and you're right DDR1 is a winner.

      The trick to realize is the DDR1 spec can't [cheaply] clock over the 400 mark without resorting to people just over clocking their memory.

      That and DDR2 parts are expected to be cheaper to produce in volume quantities.

      Tom

      --
      Someday, I'll have a real sig.
    23. Re:Is it really worth it? by Anonymous Coward · · Score: 0

      Even Apple use DDR2-667. I don't see what is so 'enthusiast' about it. DDR2-800 is the current enthusiast speed, and probably only until next year when it enters the mainstream.

      From the more recent previews it seems that DDR2-533 will keep performance parity overall with S939 + DDR400, DDR2-667 will give a slight gain, and DDR2-800 will give a 2-6% gain. That's with a 1.8GHz processor too - you can expect slightly higher gains with a faster processor because it can make use of more bandwidth.

      AMD timed AM2 to coincide with the availability of fast-but-cheap DDR2, rather than switching too early to slow-and-expensive DDR2.

    24. Re:Is it really worth it? by hattig · · Score: 2, Interesting

      Just a FYI as you might be interested, Anandtech today did another Opteron vs. Xeon test, this time with 8 cores per machine, 4 sockets.

      The 2.6GHz Opterons stomped on the 3.0GHz Xeon MPs by around 30-40%.

      Article

      Woodcrest (Conroe based server part) will have the same bandwidth restrictions that hurt Xeon in the above test. Expect to see the usual suspects test four socket Woodcrest with cache intensive benchmarks.

      However they're not a large part of the market really.

    25. Re:Is it really worth it? by Lonewolf666 · · Score: 1

      Thanks for the link.
      What I expect to become common a few years from now are four-core processors. At this point, AMD will run into the same bandwidth restrictions because the four cores have to share one memory interface.
      So it is a good idea for AMD to make the switch, even if DDR2 has no big advantage yet. The time will come when it makes a difference.

      --
      C - the footgun of programming languages
    26. Re:Is it really worth it? by edxwelch · · Score: 1

      You're right, it's only a minor upgrade in terms of processing power.
      Looks like AMD has run out of ideas how to make the current archeticture more powerful - we won't see much performance increase with 65nm either - and now can only wait while Intel plays catch up.

    27. Re:Is it really worth it? by ArbitraryConstant · · Score: 1

      "All I know it that when Intel shows this great new Conroe, and the cache size on the initial units is 4MB, It makes me wonder if they even believe they have a superior product. If they believed that, they would have a 1 MB cache - take the profit and run. (we will see, maybe I am wrong)"

      I don't think huge caches like that would help all that much if they didn't have a good execution core to back it up. They didn't help Pentium 4s (well they did, but not enough).

      --
      I rarely criticize things I don't care about.
    28. Re:Is it really worth it? by John+Jamieson · · Score: 1

      No question, I think they finally have a good core. It seems that the wider execution path, and improved branch prediction make up for the lack of on die memory controller. That is a feat.

      The first tests that I have seen put it on an almost even footing with the A64 when the cache is not a factor. I cannot wait for more tests so we can see more details.

      You are right, even a nice cache could not save the netburst chips from Athlon 64 domination, but it sure did help save face anyway.

    29. Re:Is it really worth it? by ArbitraryConstant · · Score: 1

      "The first tests that I have seen put it on an almost even footing with the A64 when the cache is not a factor. I cannot wait for more tests so we can see more details."

      I don't think the results warrant that conclusion...

      Instead of being equal and having an edge due to the larger cache, I'd say the execution core is better than an Athlon64's, and this is most evident when the working set fits inside the cache. The fact that the cache is larger only helps matters.

      Athlon64s still have an edge in memory bandwidth and latency due to the on-die memory controller, but from what I've seen Conroe has a significant edge in integer performance, the FSB isn't that much of a disadvantage most of the time, and the floating point stuff is dramatically ahead of Athlon64s. In particular, SSE instructions now have a single-cycle latency.

      Either way, early benchmarks of Conroe, as limited as they are, are very impressive, while early benchmarks of AM2 chips don't show much improvement over existing stuff. This may change, and I won't be making any final determinations until I see multiple reviews of shipping hardware, but at the moment it looks like Intel will take back the lead.

      The one thing that I found impressive and surprising about the AM2 chips is the power usage. 65 watts for most of them, meaning they've matched Intel even though Intel has moved to 65 nm and AMD hasn't, and they even have a 35 watt desktop chip, which is almost in laptop territory. This is one area where I thought Intel would hold a considerable lead, and I am impressed that AMD has managed this.

      --
      I rarely criticize things I don't care about.
    30. Re:Is it really worth it? by drinkypoo · · Score: 1

      Personally I expect four-cores becoming common around the time of the next significant process shrink. These are big, complicated cores and both power requirements and die space requirements will be too demanding before that happens.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  6. Too many sockets!!! by Freaky+Spook · · Score: 3, Interesting

    Although I find AMD to be better chips, I still stay with intel because their chips are all on one socket.
    AMD at the moment offers no upgrade path because their Semprons & Athlons are different sockets, you can't turn a budget AMD box into something more powerfull without replacing the motherboard.

    Intel allow people to start with a Celeron and easily upgrade to a P4 or Pentium D if more CPU power is required, I find the upgrade option far better value.

    1. Re:Too many sockets!!! by Bin+Naden · · Score: 2, Informative

      The reason that AMD had to go this route is that the AMD architecture has the memory controller embedded in the CPU chip while the intel machines have the controller contained in the motherboard. This means that AMD have better overall memory performance, however, a change in memory technology forces them to redesign their CPU and use another socket for fear that consumers might put those new CPU's in older 939 motherboards and either fry them up or call for tech support too much.

      --
      There should be a "-1:Groupthink"
    2. Re:Too many sockets!!! by Z0mb1eman · · Score: 5, Insightful

      Y'know... I used to reason along the same lines. After 10 years of building/upgrading my own computer, however, I realized one thing:

      Not once has it made sense to upgrade the processor. Every time it would've provided only a small gain compared to the expense and hassle. I've upgraded the RAM, hard drives, and video card several times - but by the time I felt I needed a better processor, it made more sense to replace the entire motherboard and go with a new generation (or build a new box entirely).

      To each his own, of course. But in the future I'm going to worry about the upgrade paths a motherboard offers for the RAM, drives, or video - and not the CPU, because I know I'll never bother.

      Then again, so far I've mostly had AMD boxes, so maybe there is some truth to what you say. :)

      --
      ClutterMe.com - easiest site creation on the Net. Just click and type.
    3. Re:Too many sockets!!! by Anonymous Coward · · Score: 0
      you can't turn a budget AMD box into something more powerfull without replacing the motherboard.

      Yeah, but at least until recently the price difference between an AMD CPU and an equivalent performing Intel CPU has typically been more than the cost of a new motherboard.

    4. Re:Too many sockets!!! by PsychicX · · Score: 1

      Socket 754 has benn phased out. Semprons are now socket 939. I'm not clear on how AM2 affects this situation, though.

    5. Re:Too many sockets!!! by MBCook · · Score: 1
      The difference between socket 754 and 939 was quite legitmate. They needed the pins for the second memory channel. The difference between 939 and 940 was pointless and served to segment the market, much like Intel does between P4s and Xeons.

      I seem to remember that AM2 was going to be their new socket for everything for a while on. Both budget and performance processors are going to use it (I think).

      As another reply pointed out, this particular gripe only affects a tiny portion of the user base. I've been bitten by it (specifically Intel's socket->slot->socket->other socket game years ago). At least motherboards aren't generally $300-$400 like they used to be. Makes having to purchase a new one much easier to stomach.

      --
      Comment forecast: Bits of genius surrounded by a sea of mediocrity.
    6. Re:Too many sockets!!! by forkazoo · · Score: 5, Informative

      Personally, I feel AMD has been a bit more reasonable with sockets. Pentium 4's have at least 423, 478, 775, and Pentium M has 478 and 480. Socket A lasted a long time, overlapping with Socket 370, IIRC. Since then, we've had 754, 939, and now AM2. (I'm ignoring 940, but also ignoring the Xeon sockets...) Since AM2 isn't actually out yet, that's two sockets that have been released in the same time frame that Intel released five.

    7. Re:Too many sockets!!! by FFFish · · Score: 1

      I've always found myself upgrading the whole kit and kaboodle anyway... I suspect the people who piecemeal-upgrade their system are far in the minority.

      Most people haven't the knowledge to do it themselves, and a good number of us who do built it ourselves are too cheap to be continuously upgrading, so that by the time we spring for a worthwhile upgrade, we also need new slot styles, memory stick design, CPU, maybe even PS or HD.

      --

      --
      Don't like it? Respond with words, not karma.
    8. Re:Too many sockets!!! by Freaky+Spook · · Score: 1

      I was the same to until 7 months ago when one of my PC's died and I had to build a new box. The PC that was being replaced was only my home workstation used for just light work so I decided to put a basic processor as I didn't want to spend $300+ on a CPU that wouldn't be used, but still wanted an upgrade path just in case.

      Just recently for work I had to test some software that needed a beefier CPU but I didn't want to put it on my server, all I had to do was upgrade the Celeron to a Pentium D.

      If I had gone with the AMD route, I would have needed a new board & CPU instead of just the CPU, this instance it did save me some cash.

      Although I probably could have afforded the Pentium D 7 months ago, I didn't think i would need it if it was only going to be used for email and office.

    9. Re:Too many sockets!!! by Spokehedz · · Score: 4, Informative

      Err... the P4 Comes in two socket styles. The old mPGA and the new 755-socket-whatcha-ma-callit. So right away, your argument is null and void.

      The 'old' 468-pin is just that--the OLD socket. Meaning, it's a completely different chip altogether.

      AMD has had some issues with sockets lately, I will grant you that. But Intel has been behind the 8-ball for a while now. AMD is now the innovator, and they are just playing catchup.

    10. Re:Too many sockets!!! by (H)elix1 · · Score: 1

      The irony is the 754 will outlive the 939 since that is what the pin count the mobile CPU's use. Go figure. If things go like the last time, the AM2 and 939's will be priced about the same with a small performance lead for the latest greatest. As time goes on, the 5G+ whatever will be offered for the 939, but it will cost at least one limb more than the AM2 version.

    11. Re:Too many sockets!!! by Anonymous Coward · · Score: 1, Informative

      You're wrong. The P4 comes in several sockets, and to get dual-core you need a 3rd motherboard. The AMD 939 supported single and, later, dual-core, on the same socket. I'm not saying AMD don't have as many sockets but Intel don't make it easier.

    12. Re:Too many sockets!!! by stone2020 · · Score: 1, Insightful

      So you think you are going to be able to put a new Intel Conroe chip in your current motherboard? You hear that? That's Intel laughing all the way to the bank.

    13. Re:Too many sockets!!! by mrchaotica · · Score: 2, Informative
      Socket A lasted a long time, overlapping with Socket 370, IIRC.
      Nope -- you forgot Slot A. (I got bit by that one...)
      --

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

    14. Re:Too many sockets!!! by Anonymous Coward · · Score: 0

      The P4 series also had pre-Prescott 478, and post-Prescott 478 - those extra watts required some power circuitry changes which meant incompatibility. Additionally there is the socket 479 for the mobile processor junkies (P4M's count, don't they...)

    15. Re:Too many sockets!!! by DrMrLordX · · Score: 1

      That is factually incorrect. On a few OEMs have gotten s939 Semprons. AM2 will have Semprons as well which casts doubt upon s754's future, but s939 is definitely finished.

    16. Re:Too many sockets!!! by kgruscho · · Score: 1

      I almost agree with this, I have done well with buying a high end motherboard towards the end of the product cycle, and a midline price/performance point chip, then buy the top of line chip as it is phased out. I bought an ASUS A7V when it was fairly new with duron 700, then got an affordable 1600+ Athlon XP, later I bought an ASUS A7N8x-e deluxe, which I now run with a Barton XP-M 2800+ with 400FSB. It still holds its one with most of the single core systems out there.
      I was never at the bleeding age, but always doing relatively good for a desktop, non-games box. I do agree that CPU upgrades generally go hand and hand with mobo upgrades though, as you can tell by the fact I did 3 cpus and 2 mobos... and yes I know that those chips are not supported on those boards.

    17. Re:Too many sockets!!! by Doomstalk · · Score: 1

      One would argue that if you had gone with an AMD system, the processor would've been cheap enough for you to have just bought the better processor in the first place.

    18. Re:Too many sockets!!! by Gwwfps · · Score: 2, Informative

      Not to mention all the different chipsets for 775 that are not compatible with all 775 CPU's.

    19. Re:Too many sockets!!! by billcopc · · Score: 2, Insightful

      Amen! As a shop tech I hate Intel for NOT diversifying their sockets. For the most part, each chipset is tied to a specific series of processors. It doesn't matter that it fits in a socket 478, if the chipset doesn't like the CPU it's not gonna boot PERIOD. Instead we have to worry about families like Prescott, Northwood, Willamette.. or even worse their friggin product numbers that you have to break down to figure out the speed and features of the cpu. Try telling a relative on the phone to buy a Pentium 672.. much easier to say "Get an Athlon 4000!".

      Excluding old sketchy motherboards (ECS, Gigabyte), you can pretty much stick any Socket-A AMD on any board. Same thing with the 939, even the early boards will run fine with a screaming new dual-core.

      As for the upgrading issues, it's very rare that you'll swap just a CPU, unless you bought a crappy CPU to begin with. Most people who want to future-proof their PC will buy the best kit they can afford and make it last. They won't get a budget CPU that they know will be obsolete within a year or two. We're still in a young computing age where everything is in great flux. Perhaps in another decade or two, computers will have reached a point where things have stabilized and one set of mainboard, ram and power supply can last through several generations of processors. For now, that's just a penny pincher's absurd dream.

      --
      -Billco, Fnarg.com
    20. Re:Too many sockets!!! by JohnyDog · · Score: 1

      Don't give AMD too much credit though - there was also Socket 940 for server market, and now it will be Socket AM2 for desktop, Socket F for servers and Socket S1 for mobile.

      --
      People who like this sort of sig will find this the sort of sig they like.
    21. Re:Too many sockets!!! by MojoStan · · Score: 1
      Since AM2 isn't actually out yet, that's two sockets that have been released in the same time frame that Intel released five.
      I don't disagree with your point, but your arguments seem rigged to favor AMD. Why would you count Intel's mobile sockets (Pentium M) in your comparison? Very few people, even among Slashdot readers, upgrade their notebook CPUs. Why not include AMD's other budget desktop socket (Socket A), since it's in the same time frame?

      Also, the Pentium 4/D architecture (introduced April 2001) has been around longer than the Athlon 64/x2 architecture (September 2003). Yet you chose to include an Intel socket (423) that had been phased out by the time Athlon 64 was introduced.

      I think a fairer comparison would be the number of sockets for each CPU architecture, not just some arbitrary time frame. Pentium 4/D will have three sockets from April 2001 to Q3 2006: Socket 423, 478, and 775. Athlon 64 will also have at least three sockets from September 2003 until M2 is discontinued: Socket 754, 939, and M2.

      However, I don't disagree with what I think is your point because dual-core Athlon 64 CPUs worked with many existing Socket 939 motherboards, while Pentium D needed a new chipset when it was introduced. The early adopters who bought Sockets 423 (Intel) and 754 (AMD) got screwed, though.

      --
      TO START
      PRESS ANY KEY

      Where's the 'ANY' key? I see Esk, Kitarl, and Pig-Up...

    22. Re:Too many sockets!!! by drsmithy · · Score: 1
      Try telling a relative on the phone to buy a Pentium 672.. much easier to say "Get an Athlon 4000!".

      Yeah, I know what you mean. I always tell people to get a "Sigglewatter 2468" because it's just so much easier to say over the phone than "Bagglerister 42".

    23. Re:Too many sockets!!! by (negative+video) · · Score: 1
      As for the upgrading issues, it's very rare that you'll swap just a CPU, unless you bought a crappy CPU to begin with. Most people who want to future-proof their PC will buy the best kit they can afford and make it last. They won't get a budget CPU that they know will be obsolete within a year or two.
      I dunno. I bought a pair of Opteron 240s and a Tyan S2885 motherboard soon after they were released. It cost a pretty penny, and the performance is still good compared to what's on the market now. If I wait until Socket 940 is being phased out, I can pick up a pair of high-clocked dual cores for a couple of hundred bucks, and get a massive performance increase.

      CPU upgrading still makes sense if you plan it right.

    24. Re:Too many sockets!!! by Saeger · · Score: 2, Interesting
      Not once has it made sense to upgrade the processor.

      Usually you'd be right that it makes no sense to upgrade the CPU in leu of building a completely new system around it, HOWEVER one CPU upgrade that does make a significant difference for a lot of people these days is going from single to dual core -- if your motherboard supports it (via bios upgrade or not).

      I just upgraded from a uni AMD64 3000+ -- that I built with my MSI Neo4 Platinum system a little over a year ago -- to a dualcore AMD64 X2 3800+ (best bang/buck) and the difference in FEEL is night and day no thanks to the small GHz bump. This was the first time I've bothered to replace a CPU on the same motherboard in over 10years of building my own systems. socket 939 might be end of life, but a dualcore upgrade is a worthy exception.

      --
      Power to the Peaceful
    25. Re:Too many sockets!!! by (negative+video) · · Score: 1
      The difference between 939 and 940 was pointless and served to segment the market, much like Intel does between P4s and Xeons.
      No, there were very good reasons! Socket 940 sacrificed signal return pins (power and ground) for memory ECC pins. ECC made the memory vastly more reliable. However, losing the return pins hurt electrical signal integrity, requiring that higher-latency registered memory modules be used. The ECC capability made AMD a lot of sales in the finance, medical, and industrial markets, where failure is frowned upon. And unlike Intel, AMD charged a reasonable premium for ECC, making Socket 940 machines a slam dunk with the beancounters.

      Socket 939 sacrified ECC reliability for extra return pins. This helped signal integrity, which let them get away with cheaper, faster unbuffered memory modules. The speed and cheapness turned in l33t benchmarks and made AMD a lot of sales in the super-gamer market. Intel could only respond by releasing frying pan editions of their top processors.

      IMHO 939 versus 940 was good, solid engineering on AMD's part. Upper management didn't latch onto an idea (Rambus, clock speed, EPIC) and try to ram it down everyone's throat. Somebody knew how the technology works and guts and foresight to specialize just enough.

    26. Re:Too many sockets!!! by redleaf8 · · Score: 1
      You know... until this last upgrade I thought the same way.

      I used to have a Socket 478 motherboard with a P4 2.4GHZ CPU (Northwood) in it. Then I looked at the "Mother of All CPU Charts" (2004 & 2005) and saw how high a Northwood chip still is on those charts. Now I have a 3.4GHZ (Northwood) cpu in my motherboard.

      And so far my rough benchmark with DVD Shrink bears out those charts. Copying a DVD with all the quality settings checked used to take 2 and half hours. Now it takes a little less than an hour and a half.

      It's amazing for a cpu that's 4 or 5 years old to be as fast as stuff that's still being released. Processor speeds have really stalled in the last few years.

    27. Re:Too many sockets!!! by truesaer · · Score: 1

      These new processors are for servers anyway, so its not worth worrying about the socket. The 939 pin socket was released in 2003, so by the time AM2 is mainstream its going to have had a reasonable lifetime.

    28. Re:Too many sockets!!! by Anonymous Coward · · Score: 0

      There was I time it made sense for me to upgrade the processor only. And guess what ? It ironically was on the Socket 939. From Athlon64 3000+ to Athlon64 X2 4200+.

    29. Re:Too many sockets!!! by KowShak · · Score: 1

      Slot A was the equivilent to Slot 1, which isn't mentioned here.

      Often with Intel the older CPUs don't work in the newer motherboards even when the socket is the same, where as I can't recall that happening with any AMD motherboard I've ever had.

    30. Re:Too many sockets!!! by tolonuga · · Score: 1

      Every three years I look at all the latest shiny hardware and write down the nicest
      machine I can think off, totaly bleeding edge, highest capacity and everything,
      but still something I think that might work. Then I put that paper aside.

      6 months later those components are widely available at a reasonable price, drivers
      are stable and I can afford it, so I buy a new machine.

      Having a new additional machine allows me to slowly move over to it, then take the
      three old one once I no longer need it and reinstall it as server, so the 6 year old can slowly retire. Works fine for me, not much hardware trouble, and still reasonable costs.

    31. Re:Too many sockets!!! by tomstdenis · · Score: 2, Insightful

      I fell into this trap when I learned by new 915G ASUS board wouldn't handle an i820 smithfield core.

      Intel may use 775 for everything nowadays (except for Core Solo/Duo btw) but the required chipset changes. To be safe on the Intel camp today you need >=i945 northbridge. But that didn't help all the 915G users like me back in the day.

      Might be safe to point out that unlike Intel at least AMD has multiple vendors of chipsets. So while AMD is going through transitions (hint: So will Intel be when they realize that an FSB for memory is a dumb idea) you're not stuck on one vendor for getting the requisit parts.

      Tom

      --
      Someday, I'll have a real sig.
    32. Re:Too many sockets!!! by Anonymous Coward · · Score: 0

      You can get S939 Semprons, and upgrade them to S939 Athlon X2s. AM2 will be for all desktop processors. I do agree that AMD made things confusing because they didn't see dual-channel memory being such a big thing on the desktop, hence they designed S754 for the desktop, and S940 for the workstation/server, then had to hack in S939 for desktop use.

      Intel motherboards may use the same socket for consumer desktop processors, but they keep changing the voltage requirements. Sometimes a BIOS fix will be all you need, other times a new motherboard.

      Intel's ludicrous power consumption on their Netburst line of processors is enough to put any sane informed person off that solution. Conroe will change that of course, but Conroe requires different voltage requirements, and thus won't work on existing i975 chipset based motherboards anyway.

    33. Re:Too many sockets!!! by Anonymous Coward · · Score: 0

      Intel has had an even WORSE record for staying with a socket. The only reason you are currently lucky is because the old P3 arch has been resurrected because the P4 is such a cow.

      Socket A (apart from the MOTHERBOARD manufacturer who refuses to update the BIOS) went from 500MHz to the just defunct Sempron 2800+. How many years is that?

    34. Re:Too many sockets!!! by evilviper · · Score: 1
      Why would you count Intel's mobile sockets (Pentium M) in your comparison? Very few people, even among Slashdot readers, upgrade their notebook CPUs.

      Because a good number of people want to use "mobile" processors in their desktops. Either for overclocking, or for low-power computers. Both particularly popular among Slashdot readers.

      It wasn't uncommon with Socket A, and is much more common now with Socket 754.
      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    35. Re:Too many sockets!!! by Noehre · · Score: 1

      Its almost as if you didn't even read the parent...

    36. Re:Too many sockets!!! by Anonymous Coward · · Score: 0

      excellent point. i've been done the same path. custom pc's built by me for years and i've upgraded everything except processor every time. by the time i'm complaining about the processor in even a Pentium system, i'm scrapping the whole thing and starting fresh. VGA, RAM and Harddrives are 90% of upgrades.

    37. Re:Too many sockets!!! by ryran · · Score: 1

      DUDE. do you know how cheaply you can get new motherboards if you want to upgrade a crap computer? fo'real.

    38. Re:Too many sockets!!! by drinkypoo · · Score: 1

      You went from one core to two. The bump in clock speed means jack diddly compared to that.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    39. Re:Too many sockets!!! by drinkypoo · · Score: 1

      While you have a point, there are socket to slot adapters for both slot 1 and slot A. The socket a => slot a adapters died out pretty quick AFAIK, because no one needed 'em, and because the older boards/BIOS/chipsets wouldn't run the newer and more interesting processors anyway, even if you could come up with an adapter card.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    40. Re:Too many sockets!!! by billcopc · · Score: 1

      Sure you can do that, along with everyone else who thinks like you. Right now I'm getting tons of requests for late Athlon XP and Sempron chips, for those who are trying to upgrade their aging Socket-A rigs. The zinger is that a brand new Athlon XP 3200, *IF* you can find them, sells for 140$. A brand new Athlon64 3500 costs the same thing. I think I'd take the 64 over the XP myself, so what if I have to get a new board ? They're cheap now, and I can sell the old board to the same bunch of tinkerers. Heck, most of my leftovers are too high-end for the used market, they're living in the past!

      The real kicker won't be the next socket transition. Just wait until Vista ships, or whatever sensational software lands and urges all these peons to upgrade. That's when you'll see chaos in the upgrade market.

      --
      -Billco, Fnarg.com
    41. Re:Too many sockets!!! by Saeger · · Score: 1

      You don't think I know that? That's what I meant by "no thanks to the bump in GHz". i.e. the clockspeed isn't to thank; the 2nd core is.

      --
      Power to the Peaceful
  7. Gorram It! by Null+Nihils · · Score: 1

    I remember reading that "Socket 939 will be around for a long time, its planned for it to last longer than Socket A." So I built a S939 rig and thought I was being cleverly future-proof. And now they're phasing it out? Not to mention, I got my current motherboard just before PCI-Express came out. I had a helluva time upgrading my video card while being forced to stick with AGP.

    You can't win when it comes to computer hardware. Hopefully, in a few months, I'll still be able to stick an older (much lower-priced) dual-core in my S939 motherboard and have a bit more power. However, so much for a box that was more upgradeable than not.

    1. Re:Gorram It! by Anonymous Coward · · Score: 0

      "And now they're phasing it out?"

      errr... where did u read that? they will continue to devolope cores for the 939, well into the 3-ghz quad-cpu range.

      well i have no idea really that is just a guess ;P

    2. Re:Gorram It! by Anonymous Coward · · Score: 0

      Yeah, that's more or less what everyone seemed to be saying for a while. According to them, s754 was like world's stupidest thing to buy. Dead end, don't bother! Like s939 was gonna last for the next 25 years or something...

      I still have 2 of my systems that are on good old socket A/462, an Athlon XP 2600+ and a 3000+ (also have 2 Intel systems, and a s754 one). Both have nice motherboards with everything one really needs (SATA RAID, 4 DIMM slots each filled with 512MB PC3200 sticks, USB2 & FW, SPDIF, etc). So I haven't even bothered upgrading them as I didn't really see 939 being that much of an upgrade (64 bit extensions are rather useless until the software gets there). It just wouldn't have offered a lot more performance (unless you shelled out lotsa $ on a bleeding edge CPU and nice new board) - not enough to warrant spending that much.

      And now, they're retiring it before I even bought one... And all that for a very minor speed increase (not much benefit from DDR2 AFAIK, like 10% tops). I generally prefer AMD CPUs (netburst is like the worst thing evar), I just might be buying a Conroe - especially since they're supposed to be a lot more affordable than the top AMD chips (like 500$ for a Conroe that'll be significantly faster than AMD's fastest X2 chip that costs 1000$)

      AMD truly had better CPUs than Intel during the P4 timeframe, but it better get its act together than make something new that can keep up with the Conroe. Intel has some new great stuff coming up too (new cores, new CSI bus, 45nm transition, etc)

      Right now I don't even know why one would want to buy one of those new AM2 chips.

    3. Re:Gorram It! by Neo-Rio-101 · · Score: 1

      Nothing is future-proof. The only thing consistant in the universe is change.

      Even if they never needed to change socket types, eventually they'd do so just so you have to buy a whole new mobo. If this wasn't a marketing conspiracy - CPU technological advancement has not really slowed down enough to warrant that we stop making faster chips and more complicated machines.

      --
      READY.
      PRINT ""+-0
    4. Re:Gorram It! by swv3752 · · Score: 1

      The increasing entropy levels are pretty consistent too.

      --
      Just a Tuna in the Sea of Life
  8. For those who don't know about it... by Spy+der+Mann · · Score: 3, Informative
  9. fake? by muszek · · Score: 5, Funny

    The story is fake. Nothing in our industry is released early.

    1. Re:fake? by Bin+Naden · · Score: 3, Insightful

      This is what we call a paper release as pioneered by IBM in the good old days. When the competitors threaten to release a better product then yours, you claim that you are developing an even better product than them in order to prevent consumers from switching to the competitor. The actual release date doesn't matter, all that matters is that consumers anticipate that you will have an awesome product coming along that they will want to save money for. And as IBM proved, you don't even have to release the product. You might just want to do this in order to cause your competitor financial hardships.

      --
      There should be a "-1:Groupthink"
    2. Re:fake? by dwater · · Score: 1

      It hasn't been released yet. There's still time for it's new release date to be put back to it's original one.

      --
      Max.
    3. Re:fake? by RockWolf · · Score: 1

      Microsoft is a master of that particular art...

      --
      February 9th, 2009 8:55pm: Slashdot becomes self-aware.
  10. Re:Why bother? by Anonymous Coward · · Score: 1, Insightful

    I think I'm going to have to agree with that. From my first experiences with the Pentium M, even though I generally go with AMD for my systems, I really had to give them some large amount of credit for the Pentium M. So far its the last intel CPU I've used in anything that wasn't acquired by me for free. So I actually am almost excited about a wide-scale transition to that architecture for desktops. As much as they've shown they can compete very very well, AMD might be a little behind on this one.

  11. 939... by Hyter · · Score: 3, Funny

    and 939 was suppose to be "future proof."

    1. Re:939... by Bin+Naden · · Score: 3, Funny

      and 939 was suppose to be "future proof."

      And 64k was supposed to be more than anyone would ever need.

      --
      There should be a "-1:Groupthink"
    2. Re:939... by Bob+The+Cowboy · · Score: 1

      I know you were just being funny, but anyone who believes that anything in this (or any?) industry is "future-proof" should be forced to carry a sign that says "Looking for bridge real estate"

    3. Re:939... by updatelee · · Score: 1

      anyone that tells you that is full of shit.

      buy it for now, dont count on being able to upgrade it later.

    4. Re:939... by Anonymous Coward · · Score: 0
      I know you were just being funny, but anyone who believes that anything in this (or any?) industry is "future-proof" should be forced to carry a sign that says "Looking for bridge real estate"


      It also depends on what you're expecting of your computer. I bought a 3500+ almost a year after they first came out. The CPU had gone through a few revisions (Clawhammer, Venice, Whinchester.... I think), but it was still the 939 socket. 6 months later a friend was wanting to buy a PC and was thinking on a 3800+, because he didn't see the point of the dual cores. All CPUs so far were/are still using the 939 socket.

      Flash forward to today... my 3500+ still plays the games I want (mostly WoW, but there was also Doom, Quake4, Oblivion), and I have upgrades available should things actually start feeling slow.

      As far as I'm concerned, it was as good as futureproof gets in the world of computers. How long has it been available now, over 2 years? Buy the best CPU for it now (or wait until they're being phased out and are cheaper) and you get another year, maybe 2.

      -Steven
    5. Re:939... by tomstdenis · · Score: 1

      Hate to say it, but for the average desktop user (developer included) a 4800+ processor should be more than enough juice to last quite a long time. I mean at what point do you "really need" more than 2.4Ghz of dual-core goodness to write a Java applet or C program or whatever...

      So really, if you went out and got a decked out FX-60 or 4800+ based box today, it would still be useful 5 years from now. ...

      But if you really must be on the bleeding edge, yeah, I'd hold off for AM2 instead of buying 939.

      Tom

      --
      Someday, I'll have a real sig.
    6. Re:939... by rancher+dan+3 · · Score: 1

      "And 64k was supposed to be more than anyone would ever need." It was. On my IMSAI 8080 24K was more than enough to load 8K BASIC *and* StarTrek via paper tape reader. And we liked it.

    7. Re:939... by Anonymous Coward · · Score: 0

      My 1.6Ghz Duron is still useful today. And I anticipate it to still be as useful in a few years as it is today. I'd probably still be using my 500Mhz P3 if it hadn't blown up a few years ago. I only use/used my computer for music, email, web, word processing/spreadsheeting, python/web development, and watching occasional videos. All of which could be done with ease on even a 500Mhz P3, and effortlessly on a 1.6Ghz Duron. Two 2.4Ghz cores is extreme overkill for anything but the latest games and serious number crunching.

    8. Re:939... by tomstdenis · · Score: 1

      Valid points. Though I'd like to point out that the Athlon64s can all idle at 1Ghz when not in use.

      So the real reason for not getting a higher end 939 is simply cost. If what you have already works great.

      Keep in mind my 4800+ remark was for the peeps whining about future gaming. If all you need is a workstation than even a 3400+ [2.2Ghz 1MB L2 939] is more than enough for the forseeable future. Though, come on, everyone wants a 4800+ :-)

      Tom

      --
      Someday, I'll have a real sig.
  12. do they feel threatened by intel? by john_uy · · Score: 1

    i mean with the initial benchmarks out for their new architecture, i think amd maybe trying to reduce the advantage of intel by releasing some products early. :)

    i hope to get a processor wars soon (and hopefully, motherboard, chipset, memory, etc.) so everything will go faster and better while price drops. :)

    --
    Live your life each day as if it was your last.
  13. Save condolences for intel fanboys by Saven+Marek · · Score: 1, Flamebait

    I think you should save condolences for intel fanboys :>

    The last month has been unbearable with them conroe this and conroe that. And what did I say back when they were all waiting for their chips? I said intel you will have your ass handed to you on a platter before conroe is released.

    And thank you AMD this is exactly what you have done. All the intel hype was hoping conroe could beat AMD's old generation S939 chips and that's what they did, but that was a chip intel will release in 6 months beating a design more than a year old! of course that will happen.

    Now let's see if intel have the guts to compare conroe to socket AM2 so cavialerly? I doubt it I doubt it very much. You have too test current models against current models or you are just hyping thin air.

    Try better next time intel

    1. Re:Save condolences for intel fanboys by Anonymous Coward · · Score: 0

      yeah that 2-5% marketshare amd has sure is handing intels ass to it on a platter.

    2. Re:Save condolences for intel fanboys by DrMrLordX · · Score: 1

      AM2 has been shown to perform at the same speeds or slower than those of s939 using common DDR2-533. It takes enthusiast DDR2 to get better performance out of AM2. Socket AM2 is a joke. Conroe will murder it with glee, and this is coming from a long-time AMD buyer. Don't believe me? Check this out.

    3. Re:Save condolences for intel fanboys by tomstdenis · · Score: 1

      Comparing ENGINEERING SAMPLES of Conroe to RETAIL SAMPLES of Opteron is a bit misleading. You don't suppose AMD has newer parts of their sleeves as well?

      I'm sure my 2P 285 setup is faster than the Intel 80486 ... Just a wild guess.

      And even though MCW sports a better pipe [than Netburst] and more cache [than Opteron] it still has an FSB. That makes 2P and beyond still an AMD favourite.

      I mean it's really hard to describe the speed of a box where both processors have access to their own memory. Coupled with a NUMA aware OS like Linux and you can really get some speed going.

      Tom

      --
      Someday, I'll have a real sig.
    4. Re:Save condolences for intel fanboys by somersault · · Score: 1

      I don't think that's too good of a joke.. clock for clock the Pentium 3 performs faster than the P4 for example, but the P4 was designed to reach higher clockspeeds more easily. Since AM2 can use the higher clocked RAM, then in the end it comes out faster. There will of course be some things that they can improve on with time, I wouldnt think it's the indivual socket that's the problem so much as the early revisions of mobos that are running the chipset, and the early revisions of CPUs that are running in them. Do you expect a proven technology or a prototype to perform better? The prototype is designed to eventually go faster, but the old/proven technology has had a lot of time for engineers to design mobos that work well with the processors etc.

      Can't comment on how good Conroe will be compared with AM2, but even if it's slightly better I'd probably still buy AMD.. I like supporting the underdog, and also AMD just seem to have a better ethos about them :p I'm not about to let Intel get lazy again.

      --
      which is totally what she said
    5. Re:Save condolences for intel fanboys by Anonymous Coward · · Score: 0

      Are you a fucking moron or what? AMD has been killing Intel in retail stores. That means that more than 50% of retail computers sold have an AMD processor. Combine that with the fact that Dell has fallen recently, and AMD is only looking better and better.

  14. Way to go Apple! by supabeast! · · Score: 1

    I'm sure that announcements like this make Steve Jobs really happy that he went with AMD. 64-bit dual core? Hey, if intel can make it on time maybe Apple can launch those new desktops in August.

    1. Re:Way to go Apple! by goMac2500 · · Score: 1, Informative

      Except Intel is launching 64 bit Quad Core in August. Yep, Steve seems to be pretty happy.

    2. Re:Way to go Apple! by ClosedSource · · Score: 2, Interesting

      "It's pretty funny to see the UNIX-hating, Intel-hating Mac zealots of the world to have converted within a couple of years into pro-UNIX, pro-Intel zealots that talk like Apple invented UNIX and the x86."

      Are you sure its not just UNIX fans' imagination that Mac zealots have become pro-UNIX? It seems to me that Mac zealots like whatever Apple makes, they don't care much about the underlying technology as long as the user experience is good. I seriously doubt that long-time Mac users are getting excited about the OSX command line interface.

    3. Re:Way to go Apple! by Anonymous Coward · · Score: 0

      It's pretty funny to see the UNIX-hating, Intel-hating Mac zealots of the world to have converted within a couple of years into pro-UNIX, pro-Intel zealots that talk like Apple invented UNIX and the x86.

      How on earth do you know he was one?

    4. Re:Way to go Apple! by tomstdenis · · Score: 3, Informative

      No, Intel is releasing a dual-dual-core not a quad-core. It's going to be two separate dies on one chip.

      Intel still hasn't figured out the whole "let's go MP" part yet either. While they are doing things like L2 sharing to speed up proccesses in the same dual-core part (which is a mixed blessing though) they are still using the single-FSB to do MP.

      Tom

      --
      Someday, I'll have a real sig.
    5. Re:Way to go Apple! by lemon_dieter · · Score: 1

      TYAN manufactures server mobo's with 4 chipsets (socket 940) capable of dual-core. You can use Opteron's for a total of 8 cores. There is also an expansion available to add 4 more socket 940 chips, although I am not sure of Opteron's ability to assimilate 16 cores.
      notice the memory bus architecture on the boards. if money were no object.....

      http://www.tyan.com/products/html/thunderk8qw.html

      --
      Spending Resources on Defense leaves Less to defend.
    6. Re:Way to go Apple! by tomstdenis · · Score: 1

      *cough* *cough*.

      AMD processors limit the number of coherent HT links not the number of cores.

      So yes, 8P dual core would net you 16 cores and it does in fact work. Obviously your BIOS has to recognize it and have space to store the cpu structures of 16 cores.

      Keep in mind as far as memory controllers are concerned there is only one per processor not per core. IIRC it's attached to the first core [logical id 0] whereas the second core has a "dummy" memory controller [writes to the registers are ignored].

      Tom

      --
      Someday, I'll have a real sig.
    7. Re:Way to go Apple! by powerlord · · Score: 1

      "I seriously doubt that long-time Mac users are getting excited about the OSX command line interface."

      True, on the other hand I've met a lot of long-time Unix users that are getting excited about the OSX GUI and CLI, and quite a few that are switchign to Macs as a result.

      --
      This space for rent. All reasonable inquiries will be entertained at proprietors discretion.
    8. Re:Way to go Apple! by shutdown+-p+now · · Score: 1

      I have often seen sentiments such as "OSX lets you do most stuff in nice GUI, but you have the full power of command line when you need it". It certainly is a good argument.

    9. Re:Way to go Apple! by ClosedSource · · Score: 1

      I'm sure that some people feel that way, but hard-core Mac fans wouldn't know what the "full power of command line" means. Those that updated from DOS to a Mac did so to avoid the command line, powerful or not. I realize that the OSX command line is more powerful than DOS but the average DOS user never used DOS's most powerful capabilities anyway.

  15. Wow! by Crazyscottie · · Score: 0, Troll

    Changing launch dates for a major product? They must be copying Microsoft's marketing strategy for Vista!

    Oh, wait...

    --
    Just because it can't be explained doesn't mean it isn't true. Science fits into reality... not the other way around.
    1. Re:Wow! by Ajehals · · Score: 2, Insightful

      Yeah, cause Vistas coming early... No.. wait.. Sorry

    2. Re:Wow! by maelstrom · · Score: 0

      What the?

      --
      The more you know, the less you understand.
  16. Re:Why bother? by IlliniECE · · Score: 2, Informative

    Its not trolling. Its true. Intel proved this at IDF. Furthermore, AM2 really is all promise without delivery http://www.anandtech.com/cpuchipsets/showdoc.aspx? i=2741

  17. But how much more money will it cost? by layer3switch · · Score: 2

    I am not talking about superficial retail madeup price. By past pricing scheme with early release claim, the tendency normally bend toward higher price otherwise cheaper with later release.

    I was looking forward to get it when it came out, but if higher price tag came along with it because of earlier release date, I would just wait.

    --
    "Don't let fools fool you. They are the clever ones."
    1. Re:But how much more money will it cost? by Shazow · · Score: 1

      I don't see why the price would be more expensive when released early versus when it would have been released normally. Usually prices start off at some point, and decrease proportionally to the time since release (by which I actually mean proportionally to the number of sales).

      It's not like they're giving a limited amount of people a "special preview". They shifted the release date earlier.

      If anything, now you wont have to wait as long for prices to drop. Since it'll be out earlier, the prices will drop earlier, by the above logic.

      - shazow

  18. Early Release? by insane_machine · · Score: 0

    Now there is something that doesn't often.

  19. It's been ready for a while by Anonymous Coward · · Score: 0

    I thought the AM2 boards were being intentionally held back anyway. They'd delayed the release to wait for DDR2 modules to get cheaper, but I guess they decided they've waited long enough. The AM2 certainly won't be future proof, but when they bring out their first 65nm chips it'll be for the AM2 as well, so the boards aren't just for the DDR2, they oughta be current (at least for processors) for 18 to 24 months. If I sound like I know what I'm talking about in any of this, please disregard, it's all from stuff I'd read online in the last while since I'm thinking about building a new computer.

  20. What's the point? by frieko · · Score: 1

    I have an idea, pick the processor you actually want and don't worry about upgrades! In my experience if it's time for a new processor, it's time for a new machine. Mem/hd/gpu make good upgrades but who wants to put a new hotness AMD X4 FX-80 into a slow-ass mobo.

  21. AMD's AM2 processor seems to be DRM-free by UseFree.org · · Score: 5, Interesting

    Hastening the launch date by a couple of weeks isn't too significant, but AMD certainly deserves to be congratulated for (apparently) leaving DRM out of their AM2 microprocessors. In contrast, Intel has succumbed to RIAA/MPAA pressure and betrayed their customers by stuffing Treacherous Computing down their throats.

    I'm also happy to see that AMD has not put DRM into its AMD Live! technology, which competes with Intel's DRM-ridden Viiv. I'm sure AMD is taking a lot of heat from the entertainment cartel for not handcuffing users, and I hope they'll continue to keep their products DRM-free.

    And let's not forget that AMD has been supportive of LinuxBIOS by actively ensuring that their motherboards can run it.

    --
    Get computers and accessories from Linux-friendly manufacturers
    1. Re:AMD's AM2 processor seems to be DRM-free by heinousjay · · Score: 4, Funny

      So tantalizingly close to on-topic. Excellent zealotry, A+.

      --
      Slashdot - where whining about luck is the new way to make the world you want.
    2. Re:AMD's AM2 processor seems to be DRM-free by somersault · · Score: 1

      Thankfully even the government purports to discourage monopolies.. so hopefully there will always be an option that doesn't include DRM - unless the public doesn't know any better (which it doesn't really.. :/ witness the success of iTunes). It's pretty stupid trying to incorporate DRM (of the type that you use to block audio/video content, which seems to be what most people are bothered about), into a chip design though, it should be something handled by the OS. As long as they dont lock down x86 to running Windows exclusively, then there will always be a choice.

      --
      which is totally what she said
    3. Re:AMD's AM2 processor seems to be DRM-free by Anonymous Coward · · Score: 0

      AMD has had support for Trechernous computing for a while now. All socket 754 and higher processors have unique Serial numbers, (of course every Intel CPU since the pentium III has had unique serial numbers in chip) which with trecherous computing software can 'lock on' it's 'software serial code' to a 'cpu serial number' and use the internet to decide if the software has the right to run or not*.

      it is true that Intel is paving the way with newer, more invasive on chipset DRM that could concievable be used to prevent 'linux' from installing but the past has shown that AMD is generally just a 'few years late' to the DRM party.

      *= this all has to be supported by the Host OS, such as Windows XP or Windows Vista, in the case of XP the application itself must be special coded, with vista, microsoft will be providing a pre-coded framework for drm implementation.

  22. What about power use? by Entropius · · Score: 2, Insightful

    I've heard power consumption cited as one advantage of DDR-2 over DDR. On laptops that idle around a dozen watts, even a few hundred milliwatts in the memory subsystem can be a signficant change.

  23. That old link? by John+Jamieson · · Score: 3, Interesting

    Fine, and I can show you an article that says the 65nm Athlons will clock 40% faster, and the conroe is actually slower if you don't fit in the 4Meg L1 cache. (anyone can add cache)

    Why don't we wait 6 months and then start trash talking, when we have actual products.

    One of two things has happened
    1. AMD has become complacent and has no strategy of really updating a now old product this year. In this scenario they were lulled asleep.
    2. Intel has stunk so bad that AMD has been holding some cards close to the chest because it did not need to play them.

    No staged demo by either AMD or Intel will give us the answer, but we will know in 6-8 months.

    1. Re:That old link? by fitten · · Score: 1

      Fine, and I can show you an article that says the 65nm Athlons will clock 40% faster,

      If you do, I'll show you a site that you shouldn't be reading anymore as it is worthless.

      anyone can add cache

      And yet not everyone does... :rolleyes:

      Why don't we wait 6 months and then start trash talking, when we have actual products.

      By all accounts, it will be sooner than 6 months.

      - AMD may have some cards to play yet, but it isn't very vocal about them, which is contrary to what it's done in the past when it had something new.

      - AM2 is either slower or marginally (usually within stastical noise) faster than the current S939 parts - and only when you use expensive high end DDR2-800 memory, we've already seen those benchmarks from numerous sites.

      - K8L is targeting FPU performance for some unknown reason, presumably to duke it out with Itanium which has a tiny share of the market - the HPC centers.

      - Conroe is targeting integer performance which is the mainstay of the vast majority of applications and Woodcrest is the server version of that where integer again rules the roost for the vast majority of applications/services (web server, database server, just about any other service you want to talk about, java/.NET languages, etc.).

      - Rumors are that within a year (maybe a little longer but in that time frame) AM2 will be replaced with AM3 which is for DDR3. Any CPU you purchase for AM2 will not work with AM3 just like S939 doesn't work with AM2. The joys of the IMC... upgrade the memory type and you have to buy a new CPU. Until AMD clarifies this (which it won't because it would be disasterous for AM2 if there will be an AM3 soon), there is certainly good reason to NOT buy AM2.

      This all adds up to my not purchasing any new hardware until Conroe comes out. I imagine many others are like me. While this is pretty much "not good" for Intel or AMD, it's going to mean that AM2 is a flop from the start as only fanbois will buy into that technology path blindly (and given the questions about AM2, there are certainly some big blind spots). This is coming from someone who has four Athlon64s and three AthlonXPs sitting in my computer room. I'm not a fanboi. I buy what is the best for the money when I buy. Right now, I'm thinking that's going to be Conroe (and I imagine there are plenty of folks like me).

    2. Re:That old link? by John+Jamieson · · Score: 1

      And yet not everyone does... :rolleyes:

      Granted, but it is VERY easy to do, and it is the first thing you do when you are behind and are willing to trade profit for getting a faster product out the door. AMD has not needed to use sparse fabrication resources on this, as they have had a commanding lead. I imagine if they become concered about the FX series not dominating, they will produce some large cache chips. With fab 36? having more wafer starts, larger wafers, and some being on a smaller process and having Chartered fab some as well, I can see AMD FINALLY being able to throw wafer space at cache.

      It is nice to see Intel finally competing with competent designs, but most of the recent "noise" about Conroe seems more like Intel marketing then educated and objective excitement.

      I guess I am not a fanboi either as I have both AMD and INTC PC's at home. But I admit, since the demise of the P3, I have tried to avoid buying INTC as needlessly burning electricity goes against my grain(my home fileserver runs nicely on a passively cooled P2).

    3. Re:That old link? by fitten · · Score: 1

      Granted, but it is VERY easy to do, and it is the first thing you do when you are behind and are willing to trade profit for getting a faster product out the door

      It is easy to do from a CADD standpoint, yes. However, it doesn't come without its own issues... for example the biggest one is a hit on latency. Larger caches tend to be slower (for a number of reasons). You have to be willing to pay the price(s) to grow the cache(s). Perhaps it isn't a big deal to the K8 core to take another clock cycle hit on the L2. However, AMD's cache architecture (exclusive L1/L2) is a little more complicated in the first place but yields a larger effective cache size (the size is L1 + L2 where the more 'normal' L1/L2 design - inclusive - isn't).

      I'm not sure the 'noise' about Conroe is entirely marketing. The previews done by a number of sites, even though they were orchestrated/presented by Intel, were fairly believable. 20% speedup is fairly large since we haven't seen that large of a jump in years (if you look at those previews, 20% was the average, there were some near 0% in there but there were also some near 50%).

  24. Why, exactly? by Weaselmancer · · Score: 3, Insightful

    You would hope anyone building a system would have done their research and would have known that new chips were coming.

    Putting aside that new chips are always coming up, why would this matter?

    Only reason I can think of is that you're suggesting that you might want to put a faster cpu in later on. Is that it? If so...is that a really common thing to do? Because it seems kinda....well, dumb to me. You unplug your existing cpu and stick it in a box. Then buy another one that's only a few percent faster. Then unplug that 3 months later...and stick it in a box. Seems like a waste of money to me.

    Every time I've done an upgrade, it's been a whole system upgrade. And then, I only do it every 5 years or so. Is there really a need to stay on the bleeding edge all the time that I'm missing?

    --
    Weaselmancer
    rediculous.
    1. Re:Why, exactly? by mrchaotica · · Score: 1

      If you start with the slowest CPU in a given socket, you can eventually get something like a 50% improvement with a new chip in the same socket.

      --

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

    2. Re:Why, exactly? by Znork · · Score: 3, Insightful

      "Then buy another one that's only a few percent faster."

      As far as I can tell, AM2 will be a merge of the desktop sockets, which means you'll eventually have a fairly large range of performances.

      If AM2 reclaims the same kind of staying power that socket A had, this also means you get the capacity to do cascade upgrades once you have a few systems. Stick a new CPU in your desktop? You dont stick the old one in a box, you move it to the server, which gets faster... and your old server CPU can be moved to the media frontend, which also gets faster... etc.

      "Every time I've done an upgrade, it's been a whole system upgrade. And then, I only do it every 5 years or so. Is there really a need to stay on the bleeding edge all the time that I'm missing?"

      Mmm, if that's how you do it, you probably wont benefit, no. In fact, it's far better to _never_ stay on the bleeding edge; bleeding edgers always get hosed by the price/performance ratio, and someone spending half of what you spend every 2.5 years will probably have a higher average performance over time on his systems, and twice as many systems. And again, once you reach the number of systems and component standardization needed for rolling upgrades, that's when you really start getting the payoff...

    3. Re:Why, exactly? by ponos · · Score: 1
      Only reason I can think of is that you're suggesting that you might want to put a faster cpu in later on. Is that it? If so...is that a really common thing to do? Because it seems kinda....well, dumb to me. You unplug your existing cpu and stick it in a box. Then buy another one that's only a few percent faster. Then unplug that 3 months later...and stick it in a box. Seems like a waste of money to me.
      Well, it depends on how and when you upgrade. Consider Socket 939 for example. You can buy a base system with a Sempron 2600+ (60$??) or a high end dual core Athlon FX60 (1000$??). The second processor is more than twice as fast than the Sempron. Even if it doesn't make any sense to upgrade right now, you can evetually find a new faster processor 12 or 18 months later at a reasonable cost. Most importantly, you can eventually get a used FX60 two years later from a friend or in ebay.

      As an example, a friend of mine started with a cheap socket A Athlon 1800+, later he bought a new 2500+ (reasonably priced) and now he got a used Athlon 3200+ from ebay (40$, I think). Unfortunately, he has reached the top of the line for socket A and cannot do any future upgrades.

      The end results is: if you PLAN to upgrade frequently you buy a 150-200$ processor every year then go for the fastest you can get on ebay for a low price. If you don't plan to upgrade, just buy a ~300-350$ processor upfront and forget about it. People that like messing with computers may choose the first path, most people would prefer the second path.

      P.

    4. Re:Why, exactly? by imboboage0 · · Score: 2, Informative
      Is there really a need to stay on the bleeding edge all the time that I'm missing?
      [sarcasm]But what about your SETI scores?!?!? And PCMark! Those are my life! You're such a n00b![sarcasm]

      I kinda like my 939. if i wanna upgrade from 3000+ to 4800+, i can. that's a huge improvement still available.
      --
      Honesty may be the best policy, but by process of elimination, dishonesty is the second best policy.
    5. Re:Why, exactly? by moro_666 · · Score: 1

      you will hardly get a 50% gain of overall performance gain :(

      the motherboard and disk access will still be slow as hell. but sometimes even a 10% gain in the right place makes you feel a lot better ;) /* when are we going to get non spinning storage that beats the %^* out of scsi ? */

      --

      I'd tell you the chances of this story being a dupe, but you wouldn't like it.
    6. Re:Why, exactly? by sleepy+eyes · · Score: 1

      Amen to that brother, My xp3000+ just went to my daughter's pc when I got the opteron. A cheap 206 dollar opteron. That's faster than any stock AMD on the market. But I guess you could OC the FX's a little higher than the Opty, but for 600 to 800 dollars more? Also, remember the theme, rolling upgrades, the 3rd tier pentium 233 goes in the kitchen to be a dedicated surfing rig. And for pesky guest who never touch my computer. It works and you don't have to buy the latest and greatest, but the 5 years between pentium 233 and xp3000 seem to be upped to two years but at least half the price, the xp cost 2500 back in May of 04 and the opty was only 1200 with a couple of aftermarket cooling devices.

  25. Aye Lads... by Anonymous Coward · · Score: 0, Offtopic

    ...this is Earthday weekend. A little introspection and reflection is in order.

    Perhaps it is time to look at this utterly ridiculous SUV model of computing. Because that is what it is for the most part. Building chips and mobos and computers takes WAY more energy and natural resources than it costs to run them. People look at CPU per watt, but that is a tiny part of the story, the true energy hog nature of these gadgets goes into the unrelentless manufacture of billions of them. Is it *really* necessary to upgrade constantly? Or is this putting the pressure on "the other guy" to do their bit and sort of ignoring our bits...? Perhaps a smidgen of "well, MY reason is so important and blah blah blah I am exempt, I simply MUST have the latest every six months because..."

        I call hypocritical BS on any such claims.

      It takes tons of pollution-TONS-to produce a new computer, and no telling how much energy if you follow it all the way back to mining and manufacture and shipping, etc. Beaucoup lots.. then disposal time, where it gets worse....

      Maybe we should just kick back and force the manufacturers to release less often and spend their time designing better, designs good for longer than a few months by NOT paying for the latest and greatest until such a time as at least a few years are past? Just maybe?

    1. Re:Aye Lads... by Lucractius · · Score: 1

      which is why i fully suport Sun and their new T1000 aimed at minimising these issues... primarily with their rather fantastic power per watt figures and being very small machines. low power/highly compact/very efficient machines well worth considering :) *wants one for his next apache & mysql box*

      --
      XML - A clever joke would be here if /. didn't mangle tag brackets.
  26. Memory Capacity? by Bill+Dimm · · Score: 3, Interesting

    I may buy/build a workstation soon that will need the capability of holding a large amount of RAM (say 32GB - calculations requiring a lot of memory but not a huge amount of CPU) at some point down the road (I can probably put off fully populating the memory for a while). I came across this post, which seems to say that motherboards for DDR2 will allow more DIMMs (16 2GB sticks is a lot cheaper than 8 4GB sticks right now, at least for DDR). It is talking about DDR2 with Opterons. Is there a launch date for DDR2 on Opteron? Is the capacity actually greater with DDR2? Is DDR likely to become scarce down the road, causing DDR2 to be a cheaper option for future expansion? Any opinions are appreciated (I haven't had an excuse to buy hardware in a long time, so I haven't kept up on such things).

    Sidenote: Yes, I am aware of the iWill DK88 (16 DIMMs DDR) - anybody have any experience with it (especially with Linux)?

    1. Re:Memory Capacity? by Anonymous Coward · · Score: 0, Funny

      Is (it (((possible) to use)) a few (more parentheses)) in your posts) ... it (((really))) adds to the clarity?

    2. Re:Memory Capacity? by wild_berry · · Score: 1

      AM2 uses DDR2 memory. It is expected to become cheaper and more available than DDR when most companies move their production to make it. I don't want to fob you off with a cheap RTFM, but there is no easy alternative to reading what Tom's Hardware / AnandTech / Ars Technica have to say about the matter.

  27. 1 word by 1310nm · · Score: 0, Flamebait

    Conroe

  28. Re:Why bother? by 10Ghz · · Score: 1

    The point of AM2 is to ensure smooth transition to dual and quad-core CPU's. Having four cores struggling for the bandwidth 128bit DDR400 provides is.... not nice. Each of those cores would have half as much bandwidth as the original S754 A64's did! Having them struggle over 128bit 800Mhz DDR2 is a lot more feasible. Add to that some L3-cache (on future moidels) to mask the higher latency, and you are all set.

    --
    Lesbian Nazi Hookers Abducted by UFOs and Forced Into Weight Loss Programs - -all next week on Town Talk.
  29. Re:Too many sockets!!! - parent is a troll by Anonymous Coward · · Score: 0

    Ok Who modded parent up as "Interesting".

    This should be modded down as "I am talking out my a55".
    Ever since the P2 days Intel has been KING of the incompatible sockets. AMD was steller up until the Athlon 64, but even now has not quite kept up with the frequent INTC changes.

  30. Re:Why bother? by IlliniECE · · Score: 1

    All this is very much true. However, it hardly seems worth it for AMD to be so competitive with the product's release date. Currently I'm using the dreaded 939, and frankly, I drag my feet at the thought of upgrading like that. Either way, it will be interesting to see where future architectures do go with respect to L3 Cache. It requires a bit of tinkering, as increased L3 introduces significant latency (a vexing issue in the Itanium architecture).

  31. Seconded! by zippthorne · · Score: 1

    I always end up buying a new mobo regardless of socket too, because the old mobo can't support the speed of the new cpu I want when I'm ready to buy anyway.

    --
    Can you be Even More Awesome?!
  32. Energy Bill? by sam0737 · · Score: 1

    DDR2 ram works at lower voltage, I wonder would that save some energy, even if it's by a small amount?

  33. AMD socking it to Intel by mikesd81 · · Score: 2, Interesting

    It sure looks like AMD is socking it to Intel with the lawsuit and now this release.

    It doesn't help either that HP/Intel's Itaniums aren't taking off and the AMD Opterons are doing well. Plus, as others have mentioned, AMD seems to backing Linux pretty tough. And I was looking @ alot of embedded devices and I see more AMD based ones than Intel.

    It's interesting how far AMD has come in the last 10+ years.

    --
    That which does not kill me only postpones the inevitable.
  34. Le Yawn by Groo+Wanderer · · Score: 1

    http://www.theinquirer.net/?article=31096

    Old news. Old old new.

                -Charlie

    1. Re:Le Yawn by Anonymous Coward · · Score: 0

      I don't know what is worse, old news, or the same tired reaction to posting old news?

      -
      "If you have nothing good to say, then post it on Slashdot."

    2. Re:Le Yawn by b0wl0fud0n · · Score: 1

      I don't know what is worse, old news, or the same tired reaction to posting old news, or the same tired reaction to the same tired reaction to posting old news?

      uh oh...infinite loop...must break...

    3. Re:Le Yawn by chawly · · Score: 1

      One man's old news is quite new to his neighbour. I appreciated the article for what it was to me - NEWS. I must be slow - you guys are always posturing and being bored and ahead of me. I feel depressed suddenly ! I've got to work and I'm sure to miss up-to-the-minute NEWS again. But I'll read it here tomorrow and find out how many people read it while I was at work - a bonus !"

      --
      How many beans make five, anyhow ? ... Charles Walmsley
  35. Upgrade Horror by unity100 · · Score: 1

    Its 'new breakthrough' time in the hardware industry again and time for a new 'upgrade chain horror' episode. I have a wonderfully performing amd 2500 + barton 333, asus nvidia nforce 2 motherboard, 512 kingston 400 ddr ram, asus fx 5200 magic (! it performs quite well with this setup) a seagate ide 7200 barracuda 60 gig hd, a sb live (6 years old and performs very well) machine running as a game machine. I was able to play most of the recent power-demanding game titles quite easy, lowering the settings in a few only - like star wars galaxies, x2 the threat etc. However now the situation is that, if i want to upgrade ANY of the components in this box, im going to have to do a full upgrade. see : If i want to change the graphics card, the pci-e thing is up, to hold for a few years i have to buy a pci-e supporting mobo. And that means a new cpu too, and vice versa - if i want to change the cpu, i have to get a new mobo, and will have to get a pci-e graphics card to fit in it. As the way things are going most mobos ship with serial ata support, so i have to change the hard disk too, if i do not choose to pick a 'supports both formats' mobo. And even in that case there is no guarantee that it will hold for 1-2 years, as the cpu market is moving to double core cpus now, 64 bit thing is already up and so on and such. Its the geek's ultimate horror - total upgrade time !

    1. Re:Upgrade Horror by tomstdenis · · Score: 1

      Long story short.

      1. You don't have to upgrade
      2. PCIe better than AGP
      3. DDR2 [will be] better than DDR1
      4. See point #1.

      Tom

      --
      Someday, I'll have a real sig.
    2. Re:Upgrade Horror by Anonymous Coward · · Score: 0

      I'm in the same situation, but I found that there are actually motherboards that support both PCI-E and AGP, so initially I only need to replace the CPU and motherboard. The motherboard I'm planning on buying is the ASRock 939Dual-SATA2 motherboard: http://www.asrock.com/product/939Dual-SATA2.htm

    3. Re:Upgrade Horror by unity100 · · Score: 1

      Well as a matter of fact i cant be sure ; RDRAM was told to be better than ddr, however due to market being unwilling to pay big bucks on rdram sticks ddr stuck out. What if i get a pci-e card&mobo and in 1 years time become stuck with non-upgradable stuff ?

    4. Re:Upgrade Horror by tomstdenis · · Score: 2, Insightful

      I don't get this argument.

      First off, the only way DDR2 will suck is if they never hit 800Mhz speeds. Since there is a lot of pressure on this I'm sure the memory manufacturers will keep at it.

      Second, PCI-E replaces AGP [which was around for a long time]. PCI-E is the new standard for a lot of high bandwidth parts including things like network controllers. So while I can imagine in 5 years time we will start hearing about a new bus coming out, PCI-E will still be around. Christ we still have PCI on motherboards and that was introduced in the early 90s [I recall 486 boards with ISA/VLB/PCI slots!!!].

      Third, don't be a fool. Buy what you *need* not what you think will be patchable.

      If you really need two cores with a decent cache get a 4400+, 4800+ or FX-60. Those parts are pretty darn fast. I mean I know people who STILL use P3-MP setups running at 550Mhz today... I'm sure a dual-core 2.2Ghz part will be fast enough to compile or run desktop apps for years to come.

      Just buying AM2 because "it's new" is stupid, unless that is, you're a developer who wants to support all new platforms.

      The trick though is to figure out what you actually need in terms of computing power and topology and buy to that. Otherwise, you'll just waste your money buying stuff you can't use wishing you had something else.

      Tom

      --
      Someday, I'll have a real sig.
    5. Re:Upgrade Horror by unity100 · · Score: 1

      Well as a matter of fact the other pc is for gaming/general purposes. you know that games are generally very demanding on resources, especially graphics. I have been told that if i wasnt on amd 2500+ barton 333 and nvidia nforce2, i would have been needy of upgrade a long time ago. thus what i want to do is to pick something that will take me 2-3 years in comfort, like the last config did.

    6. Re:Upgrade Horror by tomstdenis · · Score: 1

      So long story short you're gullible.

      Oh ok.

      Well just FYI, you can play most of the latest fancy games on 754-pin Semprons so long as you have plenty'o'ram and a decent GPU.

      Besides, do you need to play the latest and greatest FPS-clone at 1600x1200x75fps to have a good time? People like you, will never be happy. So long as you keep buying AMD parts though I'm happy. :-)

      I'm telling you straight up, if you're this worried go get yourself the following.

      1. FX-60 processor
      2. 2GiB of the fastest lowest latency memory you can find [4x512MiB at CL2 will do @PC3200]
      3. A GeForce 7800GT
      4. Good ventilation

      That should be quite capable of playing games for the next half decade at least.

      Tom

      Tom

      --
      Someday, I'll have a real sig.
    7. Re:Upgrade Horror by unity100 · · Score: 1

      Besides, do you need to play the latest and greatest FPS-clone at 1600x1200x75fps to have a good time? People like you, will never be happy.

      You see, as a matter of fact i believe that 800x600 resolution to play games is quite enough, 1024x768 is the climax. Maybe this is why i was able to happily play on for this long with the setup i have.

      I just want to make the optimal choice. Had it been 1.5 years earlier, it was simple - there werent too much technology around. Now there is a transition, and it makes things harder.

      I always seek to be able to upgrade my cpu/graphics card/ram for one more time on any motherboard i buy before i have to change the mobo too.

    8. Re:Upgrade Horror by tomstdenis · · Score: 1

      These comments come up whenever anyone releases a new chip...

      How is this any different than Socket 3, 4, 5, 6, 7, Super 7, etc...

      The world won't come to an end.

      The trick as I said [and you ignored] is buy what you need now. Don't buy the cheap shit and hope to upgrade. So save up a grand or two and buy a decent box that will live a while.

      If you're planning on buying the cheapest 939 now and save up for a faster on then you're wasting a lot of money.

      Tom

      --
      Someday, I'll have a real sig.
    9. Re:Upgrade Horror by ChaoticCoyote · · Score: 1

      Count me in the "upgrade horror" crowd.

      I have a wonderful dual-CPU Opteron box based on a Tyan Thunder K8W (@885) motherboard. When I bought it in mid-2004, it was leading edge. New, less than two years later, I've had a nightmare upgrading the AGP graphics. I found a nice nVidia 7800GS the works beuatifully in Linux, only to discover that it won't run my Windows games due to a flaw in the AMD 8151 AGP-to-PCI driver. AMD shows no sign of fixing the problem (they claim it is obsolete tech), so I bought and installed an ATI X1x00 card, which works great in Windows, but crashes X in Linux when using DRI.

      In Cyberpace, no one can hear you scream.

      Meanwhile, I'm upgrading my 1985 Ford F-150 pickup to use biodiesel and alcohol. I can upgrade a 20-yo truck, but not a 2-yo computer.

  36. When you need 234235GB of ram... by Anonymous Coward · · Score: 0

    .. there is only one solution ... Sun to the rescue....

  37. Cost benefits by Shivetya · · Score: 1

    There is a cost benefit for AMD by going with DDR2. As Intel has been on DDR2 for some time and will be so for quite some time it will benefit by reducing system costs.

    --
    * Winners compare their achievements to their goals, losers compare theirs to that of others.
  38. Re:Too many sockets!!! (BAD MODS) by evilviper · · Score: 1
    BAD MODS, NO COOKIE!

    I still stay with intel because their chips are all on one socket.

    Complete, 100% Bullshit. "Insert Forkazoo's post here"

    Semprons & Athlons are different sockets, you can't turn a budget AMD box into something more powerfull without replacing the motherboard.

    Unequivocally WRONG. Entirely ignorant Intel fanboyism.

    There are socket 754 Sempron 64s, Athlon 64s, Mobile Athlon 64s, and Turion 64s.

    Besides, with Socket 939 CPUs starting at $300 or so, the motherboard is only 1/3rd the cost, so NOBODY is going to be upgrading their CPU... Everyone will be buying a new motherboard for a few bucks, and have two high-end systems, instead of one.

    I really hope the AM2s push prices down across-the-board. I'd really love to see dual-channel, ECC systems becoming reasonably-priced for home PCs.
    --
    Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
  39. We have some here at our org.... by porkThreeWays · · Score: 1

    We have about 7 of those sitting in a cabinet here. They are pretty nice machines as basic web surfers, but at the same time useless. They have 64mb of ram and 1.5 ghz cpu's. We tried to find out how much ram upgrades for them would be. Most places don't sell it, and the few that still do... well... be prepared to pay more for your ram than a new computer costs.

    I remember the whole rambus debacle. Intel pushed it as the next big thing in memory. That is when I built my first AMD based system. I saw no future in rambus and its price was outrageous. It was a HUGE deal when they finally bit the bullet and started producing ddr based machines.

    --
    If an officer ever threatens to taze you, say you have a pacemaker.
  40. Different Strengths by Anonymous Coward · · Score: 0

    AMD's 64-bit x86 product is essentially a superior CPU design manufactured on mediocre silicon. Intel's 64-bit x86 product is essentially a mediocre CPU design manufactured on superior silicon. The good news is that both companies have significant room to improve.

  41. Apple! by Anonymous Coward · · Score: 0

    Yeah, but Apple uses Intel so Intel rules and AMD drools.

  42. Upgrade the CPU without getting a new Mobo? by Anonymous Coward · · Score: 0

    I know its possible, but I've never heard of anyone actually doing this. Sure being able to swap out the chip for a newer one once the prices drop is a great feature. I actually got an Athlon64 board with X2 support in case I ever felt the urge to upgrade. Frankly I'm very happy with my Athlon 64 3000+. The amount of power I have with my system is more than enough. Short of the CPU dying without the mobo going as well (highly unlikely). I don't really see myself ponying up the cash for an X2 chip without building an entirely new system. Why would I let a perfectly good Athlon 64 3000+ chip go to waste? The mobo its on only supports the low end X2's anyway. Its a compelling illusion and a good marketing ploy that the average uber-geek will upgrade the CPU, without getting a new mobo. But for an extra $50 when I get that new X2, I can also get a new mobo with faster buses, the true bottleneck, and unlock the full potential of whatever new CPU I buy.

    You can take this with a grain of salt since I saw no reason to upgrade from a P3 450 until last year, mostly because the RAM is starting to die on that 7 yr old system.

  43. Indeed by DrYak · · Score: 1
    We'll say that through some amazing physics this allows you to read twice as much data from disk per unit time than the rest of us.


    It's called 15krpm. Standart in most server-class SCSI disc. Twice the speed of regular 7.2k rpm SATA/IDE discs (except a few 10k rpm).
    That and a shorter seek time.
    Also Tagged Command Queuing is widely available since almost ten years, where only latest SATA have the slightly less advanced Natural Command Queueing.

    Your virus scan task will happily take all of it, leaving pretty much exactly the same amount of "whatever's left" for loading Halo maps.


    (Note: that I have more experience running linux than windows. So maybe if Windows is way more crappy than I think, the following reasoning is wrong)

    No. Usually not take all of it. Normally when you have 2 same-priority application competing for ressources, both of them should share the ressource in same part, so in theory both should get 50% of bandwith.
    Practically both will get less than 50% because the disc will loose some time jumping between the two regions from which it is reading.
    SCSI being designed with servers in mind is likely to response better to concurrent disc usage because of the reasons cited abovve (TCQ and lower seek time).

    There *is some* reason for the higher price tag you pay for SCSI discs.

    (Now add a decent OS like some Unix with a good read-ahead strategy and that can efficiently use most of the GIGs of ram as cache, and the whole thing flies.)

    And also note that initially, the first poster gave it as an exemple of processor speed : there's still plenty of free CPU cycles to both run a game, and scan data for viruses at wichever rate it comes out of the disk. Even with scanner maxing out disc bandwith left from the burning process, the CPU is fast enough to play a game on to of that.

    (Also, aren't on-demand scan in Windows supposed to run at a lower priority than regular apps ?)
    --
    "Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
  44. At least the hard drive can be kept by Nazmun · · Score: 1

    Most of the motherboards i've looked at support both pata and sata drives.

    --
    Hmmm... Pie...
  45. time to buy chips by Magius_AR · · Score: 1

    It's actually fast approaching the time to buy chips...

    Due to Intel losing market share to AMD in the most recent announcements, the prevailing market opinion is that Intel is going to engage in a price war with AMD in the upcoming months. That means lower prices across the board.

    Couple that with the fact that Intel's newer generation chips are beating the pants off AMD...methinks I'll be picking up a new Intel chip shortly.

    Oh, the other thing to note is that Intel's inventory totals are climbing...that means they're going to be offloading the older chips at a substantial discount to clear out the building inventory. So it's win-win for the consumer, whether you want a bargain chip or a new chip. I highly suggest buying Intel chips at the current stage in the market.

  46. Coincidence? by glitch0 · · Score: 1

    Whoa! That's the last day of school for me!

    --
    -Glitch "We all know Linux is great...it does infinite loops in 5 seconds." - Linus Torvalds
  47. Re:condolences. & Patents. by 2005g · · Score: 1

    Ah-ha. Flint arrowhead. I'll have a patent on that real soon now. Step 1. Profit.