Slashdot Mirror


Intel Core 2 Extreme QX6700 Quad-Core Benchmarks

Slimpickin writes "Intel gave access to quad-core Kentsfield-based systems to select members of the press at IDF. The embargo has been lifted on a preview of performance numbers with the new 2.66GHz Core 2 Extreme QX6700 processor. HotHardware showcases Intel quad-core performance from a few different angles, from digital video processing and encoding, to 3D modeling and rendering, along with a few of the more standard benchmarks. the new Intel quad-core puts up performance numbers, depending on the application, at nearly double the performance of a 2.93GHz Core 2 Duo processor based system. Core 2 Quad will also drop right into existing motherboards that are compatible with the Core 2 processor line."

162 comments

  1. Already tested: Two Quad-Cores in a Mac Pro, makin by chriss · · Score: 5, Informative

    A few weeks ago Anandtech already tried to plug two 2.4 GHz Quad-Core Clovertons (Xeons) samples into the new Mac Pro featuring two LGA-771 sockets. Worked like a charm, a nice eight core machine. And since dual socket motherboards are quite expensive, the Mac Pro might even be a cheap version.

  2. Well, All I have to say is... by HuckleCom · · Score: 4, Funny

    Quake 3 Voice: QUAD DAMAGE!

    1. Re:Well, All I have to say is... by NerveGas · · Score: 1

      Does that mean that you really only get three cores?

      (Q3's "quad damage" really only tripled the damage, if I recall.)

      --
      Oh, you're not stuck, you're just unable to let go of the onion rings.
  3. Summary for the lazy: by Ant+P. · · Score: 1

    No surprises, about 80% more speed for multithreaded programs.

    1. Re:Summary for the lazy: by Anonymous Coward · · Score: 0, Insightful

      With one really big exception: memory intensive processes. It looks like the shared l2 cache (amoung other things) is starting to hurt performance. Though this was expected, I am curious to see what the first AMD x4 will show.

    2. Re:Summary for the lazy: by Anonymous Coward · · Score: 0, Informative

      exactly. i've heard the amd quadcore will excel in memory management and cache efficiency.

  4. Should have wait... by Dunge · · Score: 0

    Why did everyone told me to rush on Core2 Duo when it got released saying it's the perfect time buying CPU..... now quad core get released a few months after.

    1. Re:Should have wait... by EatHam · · Score: 3, Funny

      Well, for sure now is the time to buy a quad core. I doubt there will be any new chips released for the next several years at least.

    2. Re:Should have wait... by mnmn · · Score: 1

      I was thinking of starting a company that LEASES computers, and you can swap your parts for new ones. It wont be cheap, but you'll always have the almost-latest parts.

      Next to it will be a shop selling computers with slightly used parts.

      (3) profit!!!

      --
      "Give orange me give eat orange me eat orange give me eat orange give me you." -Nim Chimpsky
    3. Re:Should have wait... by gbulmash · · Score: 2, Informative

      Why did everyone told me to rush on Core2 Duo when it got released saying it's the perfect time buying CPU..... now quad core get released a few months after.

      I'm reminded of a cartoon I saw years back, where a computer salesman is showing a customer a selection of computers: "Here we have the ones that will be obsolete in 6 months, and over here are the ones that will be obsolete in 9 months."

      Thing is, that though Intel is releasing a consumer grade quad soon, they're only releasing the "Extreme" version, which will be their highest-priced CPU. You won't see reasonably priced quads for 4-6 months after the Extreme version hits the supply chain. Unless you're doing hardcore 3d or video, a moderately-priced Core 2 Duo *should* be good enough to handle most of your tasks for the next 2-3 years before you start feeling the irresistable upgrade itch.

      - Greg

    4. Re:Should have wait... by Anonymous Coward · · Score: 0

      How I long for the good ole days of Motorola & the G4!

  5. Intel FSB vs. AMD Hypertransport? by ricky-road-flats · · Score: 3, Interesting
    If the Intel Core 2 Duos are good (generally agreed I think) , and this chip - their first quad-core - is looking so good, at what point will the apparent advantage of the AMD platform (no FSB, just Hypertransport links) kick in? If not at four cores, at eight? 16? More to the point, before Intel gets round to releasing CSI?

    I know on the face of it this chip is a kludge (two dual-cores connected to one FSB in a single-socket package, as opposed to AMD's forthcoming 'true' quad-core CPU), but if it performs well, so what?

    1. Re:Intel FSB vs. AMD Hypertransport? by mnmn · · Score: 1

      That will depend probably on the type of app. One with smaller tasks depending on each other, probably at 4 cores AMD will look good, else with linux kernel compilations where gcc takes its sweet time with each module, Intel will be better for now.

      I just wonder if in place of the fat L2/L3 cache multimedia extensions, x64 and legacy components, if we just get MORE cores it will be better. The Ultrasparc T1 has good performance figures with oracle and the Cell sounds like a workhorse enough for IBM to release blades for it. What if we just get an x86 system with nothing above MMX, 512kb L2 shared and 16 cores? On a laptop you could disable cores for efficiency or go full blast with 16 processes running on their own cores (Basic WinXP alone has like 32 running processes so it'll still be slow).

      --
      "Give orange me give eat orange me eat orange give me eat orange give me you." -Nim Chimpsky
    2. Re:Intel FSB vs. AMD Hypertransport? by jiushao · · Score: 4, Interesting

      It can equally well be argued that AMD's solution is a "kludge". Intel has four processors arranged in two pairs, within each pair the processors are connected by shared L2 cache, but the pairs are connected by the FSB. AMD on the other hand have all four processors communicating over HyperTransport links. Shared L2 is clearly better than HyperTransport links, and the HyperTransport links are better than Intel's current FSB.

      The physical packaging simply doesn't tell much about the quality of the interconnect. Sure it is harder to make a truly great interconnect with separate packages, but looking directly at the interconnect tells the much more accurate story.

      Either way, it is not an all that great suprise that the dual-FSB design of modern Intel platforms manages four cores decently, but yes, AMD probably still has a clear edge on 8 core systems.

    3. Re:Intel FSB vs. AMD Hypertransport? by ricky-road-flats · · Score: 1
      Good call, and it'll be interesting to see how it pans out. The Ultrasparc T1 did have it's weaknesses (anything single-threaded, anything involving floating point maths or anything involving multimedia/vector calculations), but is very good at other things (like the Orcale example you gave).

      I think with modern Desktop OSes there's just too much FP and SSE(1,2,3) going on now and soon (OS X now, Vista soon) for lots of simple cores to be much use in PCs. Geeks running Gentoo would disagree, I'm sure. Thinking about it, I wonder if Gentoo is actually useable in a reasonable amount of time on a Ultrasparc T1?

      I think the market will diverge - there'll be the few-but-complex core chips for desktops and workstations, like Core 2 Duo/Quad, Athlon 64 X2/K8L, and similar chips will be in many servers - but some like database and email servers, the many-but-simple core chips will become more useful and more widespread.

      Bring it on! It's the most interesting the CPU market has been for years!

    4. Re:Intel FSB vs. AMD Hypertransport? by chriss · · Score: 1

      The chip is not a kludge. It may seem that the right way would have been to build the four cores into one die instead of two, but according to some information Intel accidently slipped during the IDF (in German) due to the yield they get for Core2 chips the price for a monolithic 4-core die would be $36,13 compared to $29,37 for two 2-core dies. So this might simply be driven by economic reasons, till the process and the yield.

    5. Re:Intel FSB vs. AMD Hypertransport? by Anonymous Coward · · Score: 2, Informative

      Calling Hypertransport a "kludge" is a stretch. The advantage of Hypertransport with multi-core comes into play regarding access to main memory. All processors can access main memory simultaneously, with theoretical bandwidth actually scaling with the number of processors, rather than being divided among them. It really is better than the FSB, but AMD needs to get kicking with 65 nm and below.

    6. Re:Intel FSB vs. AMD Hypertransport? by drinkypoo · · Score: 1
      I just wonder if in place of the fat L2/L3 cache multimedia extensions, x64 and legacy components, if we just get MORE cores it will be better.

      For servers? Sure. For desktops? Probably not. Server tasks are typically (though not always) more parallelizable. doesn't mean the desktop Apps can't be made more parallel, but it's harder and it will take longer. Then again, maybe all these multicores coming out will lead to motivation to develop new tools to make threading easier.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    7. Re:Intel FSB vs. AMD Hypertransport? by Joe+The+Dragon · · Score: 1

      AMD quad-core chip will have shared L3
      also lack of quality of the interconnect for intel means that you will like not see a duel cpu system with out a non intel chip set. And the nforce pro chip sets have sli with 2 full x16 slots and left over lanes for x4 slots while most intel ones don't even have 1 x16 slot at full speed.
      some have do have x16 and a x4

      look at
      http://www.tyan.com/products/html/xeon.html
      then look at
      http://www.tyan.com/products/html/opteron.html

      also look at
      http://www.supermicro.com/products/motherboard/Xeo n1333/?chp=5000X

      http://www.supermicro.com/Aplus/motherboard/Optero n2000/

    8. Re:Intel FSB vs. AMD Hypertransport? by Jeff+DeMaagd · · Score: 1

      duel cpu

      Are you ASKING the chips to fight? Sheesh.

    9. Re:Intel FSB vs. AMD Hypertransport? by The+Warlock · · Score: 1

      Who cares about SLI on a dual-CPU system? I dunno about you, but where I come from, dual-socket systems are for doing Serious Buisness, not for playing fucking video games. If you want to play games, there's a $400 machine right over there that should be a good deal cheaper.

      --
      I've upped my standards, so up yours.
    10. Re:Intel FSB vs. AMD Hypertransport? by jiushao · · Score: 2, Informative

      Calling either solution a "kludge" is of course wrong. However, just running everything across HyperTransport is an obviously worse approach for core-to-core communication than shared L2. The trick about sharing cache though is that it stops making sense to talk about the cores "sharing access to main memory", since any memory fetches go into the shared cache. Plus that Intel isn't stupid, their current platform has two separate front-side buses, so there is quite a bit of bandwidth to work with.

      On the other hand it is of course also true that the HyperTransport approach is perfectly symmetrical and scales to almost any number of processors, so AMD has a good hold on the 8 core and above market.

    11. Re:Intel FSB vs. AMD Hypertransport? by jiushao · · Score: 1

      Yeah, K8L will get interesting of course, I don't expect things to stay the same. I just wanted to point out that it is not quite correct to accuse Intel of not having "proper" quad-core when the interconnect is in some ways superior to the way AMD currently does multi-core.

    12. Re:Intel FSB vs. AMD Hypertransport? by cptgrudge · · Score: 1

      I care. Computers can be used for different things. I don't want to have a dedicated computer for gaming, a dedicated computer for coding, and a dedicated computer for graphics/video. If one computer can adequately perform to my satisfaction in all these facets, what's the problem? As long as unacceptable sacrifices are not being made to accomodate multiple uses, I'm fine with it.

      At a previous job, I had a nice dual Xeon machine. It took whatever I could throw at it. It had a "professional" graphics card in it. It was great. It also played UT2004 great. What's the issue?

      --
      Qualitas edurus commercium, nullus penitus net rimor, nullus deus beneficium
    13. Re:Intel FSB vs. AMD Hypertransport? by The+Warlock · · Score: 1

      The issue is g-grandparent poster is saying Xeon is infereor to Opteron because some Opteron motherboards can do SLI, where Xeon motherboards are "stuck" with "only" one graphics card (the horror!), when in reality that's a non-issue, not least of which because while two quad-core processors can be cost-justified under certain circumstances, two graphics cards really can't be.

      --
      I've upped my standards, so up yours.
    14. Re:Intel FSB vs. AMD Hypertransport? by Jedi+Alec · · Score: 1

      duel cpu

      Are you ASKING the chips to fight? Sheesh.


      And today's weather report: excellent race conditions. Gentlemen, start your engines!

      --

      People replying to my sig annoy me. That's why I change it all the time.
    15. Re:Intel FSB vs. AMD Hypertransport? by Saint+V+Flux · · Score: 0

      "However, just running everything across HyperTransport is an obviously worse approach for core-to-core communication than shared L2."

      I know that AMD is still using HyperTransport 2.0, but it's only logical that in the very near future they'll switch to HyperTransport 3.0. With a bandwidth of 41.6 GB/s, I think that will bring transfer time down to essentially nil.

    16. Re:Intel FSB vs. AMD Hypertransport? by jiushao · · Score: 0, Troll

      The Core 2 Duo, clocked to 3GHz, has a L2 cache bandwidth of 96 gigabytes per second. Not to mention latency, HyperTransport has a latency on the level of a 100-200 nanoseconds, compared to the 14 cycle latency of the Core 2 Duo L2. This works out to a 23-46 times higher latency for HyperTransport. I would expect a more modern version of HyperTransport to bring this number down quite a bit, but still, it is probably safe to assume that HyperTransport will for the forseeable future have a latency well over ten times higher than a shared cache solution.

    17. Re:Intel FSB vs. AMD Hypertransport? by Jherek+Carnelian · · Score: 2, Insightful

      However, just running everything across HyperTransport is an obviously worse approach for core-to-core communication than shared L2.

      The real question is how important is core-to-core communication versus core-to-memory for "regular" workloads?

      My gut says that for consumer-level workloads, memory is more important than inter-core communication because most consumer-level parallel processing is of the "embarassingly parallel" type - specifically codec processing - video, audio and "photoshop plugin" types.

      My imagination may be lacking, but I can't think of any consumer-level compute-intensive workloads that are also fine-grained enough where inter-core communication is critical. Perhaps some of the distributed-processing/seti-at-home type jobs could make use of fine-grained parallelism within each "chunk" of processing, I don't know.

      So, it is entirely possible that the downsides of shared-cache, like bus contention and false cache-line sharing, could be a hindrence in comparison to the sort-of "shared-nothing" approach that AMD has taken with their designs.

    18. Re:Intel FSB vs. AMD Hypertransport? by Joe+The+Dragon · · Score: 1

      people who want to use quadroplex, 2 Quadro cards, a video card and other pci-e based cards and more.

    19. Re:Intel FSB vs. AMD Hypertransport? by jiushao · · Score: 1

      That does not change the fact that shared cache is a strictly good thing though. There are many other advantages. Sharing cache means more cache overall (since no data needs to be duplicated when both processors need it, a huge saving for common workloads), and more cache means a lot less memory accesses. Shared cache also means that such common data only needs to be read from memory once, where the reads would need to be duplicated when cache is not shared.

      On the other hand, the only thing I replied to was that Intel has a great approach to doing multi-core, no matter how "kludgy" some people claim it is. The inter-core interconnect is overall pretty damn good. The total system bandwidth is a very separate issue. AMD has a better solution for that at the moment, but it is not due to some kind of trade-off, they would be better off with shared cache and HyperTransport.

      As it happens Intel is not doing all that badly there either, the FSB design is kind of old, but it always was a great piece of engineering. They have cranked up the speed nicely and have two separate buses in the current platform, so properly feeding a quad-core does not seem like it should be an all that tricky obstacle to overcome. It is still a problem that Intel needs to solve sooner or later, but it is not currently a disaster in any way.

    20. Re:Intel FSB vs. AMD Hypertransport? by jiushao · · Score: 1

      AMD has a better solution for that at the moment, but it is not due to some kind of trade-off, they would be better off with shared cache and HyperTransport.

      Oh, and one more thing: As has already been pointed out, this is indeed what will happen with the K8L.

    21. Re:Intel FSB vs. AMD Hypertransport? by Kyro · · Score: 1

      Except K8L is going to have 2MB+ of shared L3 cache...

      --
      save the GNUs!
    22. Re:Intel FSB vs. AMD Hypertransport? by Anonymous Coward · · Score: 0

      But pipelining is exactly where you want fast channels between your processing units, and most video (still or motion) processing is done with stages assembled into a pipeline, with each stage bashing the bits that were bashed by the previous stage, and so forth.

      For video processing the "embarassing parallelism" comes from being able to parcel out seconds or minutes worth of source to different processors. Those work units are still usually going to be processed in a pipelined fashion.

      The parallel subunit approach requires more bandwidth to move multiple parts of the source bits to the processor simultaneously, or you are at a disadvantage compared to a faster single pipeline with results shuffled from one stage to another extremely quickly.

      Importantly, the approaches can be combined, which is why render farms are popular with people doing huge amounts of video processing.

    23. Re:Intel FSB vs. AMD Hypertransport? by Anonymous Coward · · Score: 0

      Sharing cache means more cache overall (since no data needs to be duplicated when both processors need it, a huge saving for common workloads), and more cache means a lot less memory accesses.

      I think you've just ignored everything the poster said - that the common case for desktop use doesn't need to share data and that shared cache has costs that are effectively the result of each core stepping on the other core's memory accesses - false cache-line sharing, bus contention and stuff he didn't mention like the fact that the bigger a single cache, the slower it is to access.

      Really, the only time that a single unified cache is better - other than for inter-cpu communications - is when one cpu is idle and the other cpu can use the entire cache, effectively doubling the size of the cache for one cpu at the cost of idling the other cpu. In other-words, single-threaded applications with large memory footprints (FFTs?).

      Which is better - a 4MB cache that takes 8 cycles to access, or a 2MB cache that takes 6 cycles? The answer is, it depends on the software - if your working set fits in 2MB, then that 25% speed-up is huge. If it is too big to fit in even the 4MB then it doesn't matter so much either.

      To categorically state that "shared cache is strictly a good thing" is at best an over-simplification and in many cases simply false.

    24. Re:Intel FSB vs. AMD Hypertransport? by prencher · · Score: 0

      Why is the parent marked troll exactly?

    25. Re:Intel FSB vs. AMD Hypertransport? by jiushao · · Score: 1

      I think you've just ignored everything the poster said - that the common case for desktop use doesn't need to share data and that shared cache has costs that are effectively the result of each core stepping on the other core's memory accesses - false cache-line sharing, bus contention and stuff he didn't mention like the fact that the bigger a single cache, the slower it is to access.

      I didn't read the poster that way at all, and if that is what the poster meant to say I simply disagree. I read his post as an argument that actual inter-core communication (as in, one core really reading another cores writes to continue computation) is not a great bottleneck, but saying that data (pristine from memory) is seldom shared between cores is really way off. Running several completely independent applications does happen of course, but as the number of cores increases one really has to expect that either an application with several threads or possibly several instances of the same application is involved.

      Also, of course the claim "shared cache is strictly a good thing" if the question is "do you want shared cache or 10X faster cache". That is not the question in practice however, the Conroe L2 has a 14 cycle latency, compared to the K8's 12 cycle latency. A latency increase of 16.6% for a chip that, on its very first revision, clocks 12.7% higher, not at all a bad scenario.

      The associativity argument is real of course, but it is not nearly as problematic as it is sometimes made out to be, with 16-way associativity on L2 it seems extremely unlikely that any real issues will arise from this. If anything 16-way associativity still appears to be a bit overkill.

      In the end, of course "shared cache is a strictly good thing" is a simplification, but in the same way that "more cache is a good thing" is a simplification. It is not nearly as unreasonable as you make it out to be to expect an implementation to have a near-zero performance impact for a single-thread only using half the cache. As it happens, the Conroe really does a really nice job of that as well.

    26. Re:Intel FSB vs. AMD Hypertransport? by hamanu · · Score: 1

      ummm, because in dual core AMD chips the two cores talk over the SRQ, not over hypertransport links? How dumb do you think AMD is?

      --
      every _exit() is the same, but every clone() is different.
    27. Re:Intel FSB vs. AMD Hypertransport? by snuf23 · · Score: 1

      "two quad-core processors can be cost-justified under certain circumstances, two graphics cards really can't be."

      I think there are folks in the video game and computer animation industries (TV and film) who would disagree with you.

      --
      Sometimes my arms bend back.
  6. How about quad memory capacity? by Travoltus · · Score: 1

    I'd hate to use a quad core system on just 2gb RAM - that's an average of 512mb for use per core.

    --
    --- Grow a pair, liberals... stop letting the Republicans bully you!
    1. Re:How about quad memory capacity? by gbulmash · · Score: 1

      I'd hate to use a quad core system on just 2gb RAM - that's an average of 512mb for use per core.

      But Windows XP is supposed to run just fine on a system with 512mb (ducks, runs for cover).

      Seriously, though, AFAIK, the cores don't balkanize the RAM, staking out a 1/cores share and then fencing it off to prevent incursion by other cores, shouting MINE like a 2 year old on steroids. I believe they were taught how to share before Intel sent them off into the big bad world.

      - Greg

    2. Re:How about quad memory capacity? by Travoltus · · Score: 2, Interesting

      That's what I meant by average... I know cpu's don't "demand" memory, but having enough memory for each CPU is a good idea.

      The apps I run at home (video conversion, maybe a VMWare instance) would each use very close to 512mb apiece. I might even run Oblivion in one cpu while turning a DVD converter loose on another process; AFAIK Oblivion will grab whatever it can, so 1gb for that cpu isn't unfeasible.

      I can imagine other, more memory intensive apps trying to run in tandem and running into problems if you have under 2gb for four cores, if you're using all four cores to the max.

      --
      --- Grow a pair, liberals... stop letting the Republicans bully you!
    3. Re:How about quad memory capacity? by portmapper · · Score: 1

      > I'd hate to use a quad core system on just 2gb RAM - that's an average of 512mb for use per core.

      Just because you add more cores does not imply that your favorite application will use much
      more RAM.

    4. Re:How about quad memory capacity? by Anonymous Coward · · Score: 0
      I'd hate to use a quad core system on just 2gb RAM - that's an average of 512mb for use per core.

      I'm reading this on an old Gateway with a 266Mhz processor and 128mb of RAM. I'd shout "whippersnapper", but I'm out of breath after putting my 15" CRT out with my cane.

    5. Re:How about quad memory capacity? by Travoltus · · Score: 1

      yeah but the point of using 4 cores is to -use- a ton of your favorite apps all at once. one single core can chew up 2 gigs (the ssytem spec inthe article) plus virtual ram, too, or one gig and 2-3 times that in virtual ram.
      lots of people will find 4 cores to be very freeing and decide to use even more apps at once than what they used to. that 2 gigs of ram will become very crowded. that's why lots of motherboards have a capacity of greater than 2 gigs of ram capacity.

      --
      --- Grow a pair, liberals... stop letting the Republicans bully you!
    6. Re:How about quad memory capacity? by Procyon101 · · Score: 1

      Well yes, *IF* you plan on doing 4 times as much with the quad core than with a single core, then you should have 4 times the ram. However, most people are looking to do what they are already doing, just faster, in which case adding more proc power to their existing ram footprint will speed them up.

    7. Re:How about quad memory capacity? by Movi · · Score: 1

      > But Windows XP is supposed to run just fine on a system with 512mb (ducks, runs for cover).

      Sir, I've been running XP on 128MB for YEARS, and it was a-ok if i knew not to run mozilla (no firefox yet at that time) with 50 tabs, Photoshop and at the same time. As time passed i upgraded to 256 then 512, then 1GB as i have it now.The 512 -> 1GB upgrade was _only_ for Oblivion.

      Sure with 128MB, some swapping occured. But saying that 512 is not enough for XP is a blatant lie.

    8. Re:How about quad memory capacity? by portmapper · · Score: 1

      If you need more RAM, then you buy more RAM, not a quad core CPU.

    9. Re:How about quad memory capacity? by Anonymous Coward · · Score: 0

      No way! The Gateway G6-266M? 'cause I'm typing THIS on the same machine (With more RAM added), on Linux (Debian with a Fluxbox DE). Of course, the keyboard is attached to a Pentium 4 1.8 Ghz with 1 GB of RAM, Windows XP, and keyboard sharing via synergy2, but hey. (Multiple desktops with multiple machines powering them. Makes life easy!)

    10. Re:How about quad memory capacity? by Anonymous Coward · · Score: 0

      As a good anonymous coward, let me admit that I'm pretending to be my Dad, on my Dad's machine, with his likely reaction, because it popped into my head and made me laugh. But yes. It even came in a black and white cow box (which I was obsessed with at the time.) I connected him to the net with it for the first time a month or so ago (imagine that - not a single web update). He is still too frightened of hackers to read slashdot. :lol:

    11. Re:How about quad memory capacity? by Doctor+Memory · · Score: 3, Insightful
      Oblivion will grab whatever it can, so 1gb for that cpu isn't unfeasible
      Do you know that your Oblivion process will stay on whatever core it starts on? If it's any kind of a useful application, it's going to have to do I/O sometime, and at that point will give up the CPU. Once the I/O completes, it'll be placed on the run queue and should be picked up by the next available processor. It shouldn't matter how many processors you have, any program that takes a given amount of memory to do a given amount of work will take up that much memory. If you're planning on running more programs to take advantage of your additional CPU power then yes, you'll want more memory. But if all you want to do is execute your current software and workloads faster (assuming they run faster on a multicore system), then you won't need any more memory.

      I can imagine other, more memory intensive apps trying to run in tandem
      You've got a better imagination than I do, then. I can't see applications forking off copies of themselves and jockeying for position! If you meant "I can see running other, more memory-intensive apps in tandem" then duh, you'll use more memory. Exactly the same as you would on a single-core system. If you've got an app that scales well, it'll still take the same amount of memory no matter how hard it's exercising however many CPUs. Input set sizes are pretty much fixed, whether they're hard-coded or dynamically configured based on system size: your app will allocate the same amount of memory either because it always grabs 32M or because it always grabs 1/16th of total system memory. Number of CPUs has nothing to do with it. Unless there's some software that allocates one thread per CPU, and allocates some fixed buffer size per thread, which now that I mention it actually sounds reasonable for some classes of software, but I've never heard of it actually being done.
      --
      Just junk food for thought...
  7. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by gbulmash · · Score: 1

    Not to be a spoilsport, but if you do drop in a couple of clovertowns, you'll void your warranty. I've had a lot of Mac-owner friends tell me it's a bad idea.

    Me, I might try it anyway, but if I do, I definitely won't shell out $249 for an AppleCare warranty I'll be voiding soon after purchase.

  8. embargo by xsarpedonx · · Score: 1

    You keep using that word. I do not think it means what you think it means.

    1. Re:embargo by mph · · Score: 1
      You keep using that word. I do not think it means what you think it means.
      Tell it to Jane Austen.
    2. Re:embargo by Anonymous Coward · · Score: 0
      I do not think it means what you think it means.

      Perhaps not, but it does mean what he thinks it means.

    3. Re:embargo by TMarvelous · · Score: 1

      Embargo is a common term in the media industry for holding back stories. Often information is distributed in advance witha request that the reporting entities respect an embargo until a certain time. In the US, NBC enforces an embargo on highlights of the olympics until after the event airs on the West Coast, even if it happened live 12 hours earlier.

      --
      http://www.worldsoccerbars.com
    4. Re:embargo by Overly+Critical+Guy · · Score: 1

      Why do I keep seeing this phrase online? I don't get the joke. Is it from some lame movie or something?

      --
      "Sufferin' succotash."
    5. Re:embargo by alexander+m · · Score: 1

      it's paraphrasing a genuinely amusing moment in the film "The Princess Bride", when one of the characters keeps saying "inconceivable" as The Man in Black continues to follow them through in a seemingly impossible fashion. one of the others turns to him in puzzlement/exasperation and says exactly that: "you keep using that word. i do not think it means what you think it means"

      and, yes, like most situational gags it completely loses its appeal when written down ;-)

      the film itself actually won a "Best Screenplay" award from Writers Guild of America and, if i remember correctly, it also won the Toronto International Film Festival "People's Choice Award". and an Oscar and a Grammy for something a bit random to do with the music i think. was all around 1988

    6. Re:embargo by Skevin · · Score: 1

      > You keep using that word. I do not think it means what you think it means.

      We Americans are not so unworldly as to not know the meaning of "embargo". Hmph.

      It's buttered snails, often served in French restaurants.

      --
      "Twice half-assed makes an ass whole." --Solomon K. Chang
    7. Re:embargo by nuzak · · Score: 1

      > "you keep using that word. i do not think it means what you think it means"

      It is of course much funnier with the distinctive expressive talents of Wallace Shawn and Mandy Patinkin. When said aloud, you really have to adopt a muddled spanish accent to get it right.

      That movie is right up there with Monty Python and the Holy Grail in terms of belonging to the collective unconscious of geekdom.

      --
      Done with slashdot, done with nerds, getting a life.
    8. Re:embargo by julesh · · Score: 1
      Hmm?

      embargo /embaargo/

            noun (pl. embargoes) 1 an official ban, especially on trade or other commercial activity with a particular country. 2 historical an order of a state forbidding foreign ships to enter, or any ships to leave, its ports.

            verb (embargoes, embargoed) impose an embargo on.


      Meaning 1, not in the "especially" sense, (i.e. "an official ban") seems to fit.
  9. Time to refine operating systems... by b0r1s · · Score: 4, Interesting

    For years, most operating systems have been designed for 2-4 processors, with some handling more, and others doing better with less (I'm sorry, FreeBSD fans, I use it myself, but let's be honest, SMP was horrible until 5-REL, and it still isn't up there with Linux and *ugh* Microsoft).

    With 4 core out this year, and 80 cores out in 5 years, it's time to rethink multiprocessor operating systems. There needs to be a significant change in the locking and threading metaphors, because 4 and 8 way will be obsolete by this time next year.

    --
    Mooniacs for iOS and Android
    1. Re:Time to refine operating systems... by Anonymous Coward · · Score: 0

      Might I suggest something else, that already runs on > 100 processors?

    2. Re:Time to refine operating systems... by mnmn · · Score: 1

      Operating systems are fine. They just take processes and share them across cores.

      Its the threads libraries and programming style of larger apps that matter. Say you have a basic Linux system with 4 cores. It will reasonably distribute processes across all 4. The problem is when a single process with multiple short-lived threads takes all the CPU power. Like games. Thats where funky compiler directives will be witnessed.

      --
      "Give orange me give eat orange me eat orange give me eat orange give me you." -Nim Chimpsky
    3. Re:Time to refine operating systems... by MSFanBoi2 · · Score: 1

      Microsoft's performance with multicore systems is quite good with Windows Server 2003 and up. I don't know why you say it "isn't there".

      When running apps suchs as SQL and Exchange moving from dual to quad systems can net improvements close to 100% depending on the query sizes.

      Its not really till you make the move from 8 way systems and up that you see a much more marked decrease in the increase.

    4. Re:Time to refine operating systems... by cyber-vandal · · Score: 1

      So why does an app or a library have to care how many CPUs or cores the PC has? Surely that's the job of the OS?

    5. Re:Time to refine operating systems... by Eccles · · Score: 1

      How would you rate Mac OS X on its multiprocessor handling?

      Obviously, you still need the apps to support it too.

      --
      Ooh, a sarcasm detector. Oh, that's a real useful invention.
    6. Re:Time to refine operating systems... by Jeff+DeMaagd · · Score: 4, Informative

      So why does an app or a library have to care how many CPUs or cores the PC has? Surely that's the job of the OS?

      Yes and no. Programs can split the hard work across several threads and all of those threads will be managed by the task scheduler regardless of how many cores there are. The hard part is making an algorithm that can split the heavy processing work to multiple threads, that threading has to be programmed. If the program has all the hard work in one thread, then it's not going to use more than 100% of one CPU, 50% each of two CPUs, etc.

    7. Re:Time to refine operating systems... by Lost+Race · · Score: 1
      ... 4 and 8 way will be obsolete by this time next year.
      By "obsolete" you mean "just starting to become mainstream", right?
    8. Re:Time to refine operating systems... by Klintus+Fang · · Score: 1

      I don't know what Intel was thinking with that recent "80 core" announcement. Nobody is going to have 80 general purpose cores in a package in 5 years. Looks like that 80 core announement was talking more about having 80 specialized floating point engines rather 80 general purpose processors and that they were really talking about very specialized niche markets at best rather than general purpose machines. That said Intel was happy to have it misconstrued as the latter by the public and press.

      But that aside, core counts are going to surpass 4 and likely go out to 8 or even 16 in the next 5 years for the desktop machines. And you are right. It's not clear what the average user is going to be able to do with so many cores. Out to 2 and 4, its probably easy enough for a decent OS to find work for the extra cores to do even if the individual applications are not multi-threaded, but beyond that?? Be interesting to see what happens.

      --
      In a minute there is time For decisions and revisions which a minute will reverse. -T.S. Eliot
    9. Re:Time to refine operating systems... by Anonymous Coward · · Score: 0

      Quite bad, and even their single processor kernel performance is atrocious. Solaris, Linux, FreeBSD, and even Windows are far superior to Darwin. Apple is either incapable, unwilling, or both when it comes to making Darwin a competitive Unix platform. Based it on Mach, it is really no wonder that they can't keep up.

      Creating an OS which scales well is a seriously non-trivial problem. It would be best, if they simply chose to leverage one of the several freely available systems. That way, they could concentrate on the GUI, and have also have a solid Unix base. As it is, the future does not look so promising.

    10. Re:Time to refine operating systems... by Jherek+Carnelian · · Score: 1

      So why does an app or a library have to care how many CPUs or cores the PC has? Surely that's the job of the OS?

      The OS does not know what kind of interdependecies there are between threads and or even different processes. One of the most common performance issues is where thread-A needs to communicate with thread-B, but B is sleeping so A sits and waits for B to wake up (be scheduled) and respond. By that time, A may have been put to sleep (by the scheduler) so that when B finally responds, A isn't there to act on the response for another XX milliseconds. You get a bunch of those round-trips in your code and pretty soon it is running dog slow even though the system is close to 100% idle.

      One way to fix that is with gang scheduling but that requires the app to tell the OS enough information about itself so that that the OS can "do the right" thing and schedule all the interdependent threads simultaneously.

    11. Re:Time to refine operating systems... by Elladan · · Score: 2, Informative

      To elaborate:

      Usually, if an application can split its work up into 2 threads, it can split its work up onto n threads (if it's well designed). This isn't
      always the case, but it tends to be. The hard part is breaking an algorithm up into pieces, usually not the number of pieces in particular.

      So, for example, it could spread its work over 100 threads on a 1-CPU machine. This would be an inefficient use of threads, if they're all doing work. Usually 1 or 2 threads is ideal for a 1-core machine.

      Similarly, it could spread over 2 threads on a 4-core machine. This would also be inefficient, since 2 of the cores would be idle.

      So, ideally, the program usually should have some way of asking the OS, "how many threads should I run for best efficiency?" In general, the question it really asks is, "how many execution cores are there?" and then it just uses that, or multiplies by 2, or something.

      So, the application needs to know how many cores there are as part of its auto-configuration, for performance. Often apps don't auto-configure this sensibly, and just spawn a fixed number. This isn't ideal, since it requires the user to twiddle something for no particular reason.

    12. Re:Time to refine operating systems... by jhackworth · · Score: 1

      probably not necessary. Sure, some will replumb their synchronization mechanisms, but in the interim there's a lot of advantage to be gained just by making some minor tweaks and recompiling. OpenMP is a good way to do this, but another approach is add a 2nd tier scheduler. The OS scheduler could be used to manage an a lower tier scheduler which simply breaks work into parallelizable units and schedules threads and processes to do this work. The lower tier scheduler can hand off processes to the OS scheduler to manage and the OS scheduler can manage multiple lower tier schedulers. This may seem like additional overhead, but it would save time and money while we all learn the new paradigms and programming languages required to take advantage of 80 cores.

    13. Re:Time to refine operating systems... by owlstead · · Score: 1

      If you don't use threads you won't get additional speed. If you would be able to automatically run a single thread on multiple cores at the same time, please give me a call. And even if an application does use multiple threads, it's easy to mess things up (try any multi-threading resource out there and see how easy *that* is).

    14. Re:Time to refine operating systems... by Jeremi · · Score: 1
      but B is sleeping so A sits and waits for B to wake up (be scheduled) and respond. By that time, A may have been put to sleep (by the scheduler) so that when B finally responds, A isn't there to act on the response for another XX milliseconds.


      You seem to be implying that threads can't be woken up except at scheduler quantum boundaries. That would be horribly inefficient, so it's a good thing it isn't true... any decent/modern OS can wake up a thread immediately at any time. So even if thread A was put to sleep, the OS can (and usually does) wake it up again immediately when thread B sends it a message (assuming thread B's priority is less than or equal to A's, or that thread B goes to sleep itself after sending the message). There is overhead to this -- the CPU has to save and restore register state on each context switch -- but that overhead is on the order of microseconds, not milliseconds.


      Note: all of the above is null and void if your program is using polling loops as part of its communications method. But your program is doing that, then you need to be taken out and shot anyway :^)

      --


      I don't care if it's 90,000 hectares. That lake was not my doing.
    15. Re:Time to refine operating systems... by Tibor+the+Hun · · Score: 1

      No, he probably meant gone, as in P3 or G3 CPUs that are obsolete nowdays. I mean who uses those CPUs any more, right? Maybe cavemen, with their obsolete hammers.

      --
      If you don't know what AltaVista is (was), get off my lawn.
    16. Re:Time to refine operating systems... by Jeremi · · Score: 1
      How would you rate Mac OS X on its multiprocessor handling?


      I believe it's pretty good, and getting better.


      Obviously, you still need the apps to support it too.


      Not necessarily... one trick Apple is doing is to hide the multithreading code inside its higher level libraries. As a hypothetical example, say you have a single-threaded application that calls RenderCool3DScene() in Apple's Cool3DGraphics library: on a single CPU machine, the scene will be rendered in normal way, but on a multi-CPU machine, Apple's code might get clever and spawn two threads internally: one to render the top half of the scene, and one to render the bottom half. Your app is still single-threaded, but it will now run faster because RenderCool3DScene() returns more quickly on the multicore Mac.

      --


      I don't care if it's 90,000 hectares. That lake was not my doing.
    17. Re: Time to refine operating systems... by Anonymous Coward · · Score: 0

      "For years, most operating systems have been designed for 2-4 processors, with some handling more [redhat.com],...".

      I am reminded of the Dilbert cartoon with the Unix guru.

      "Here's a nickel kid, get yourself a better computer."

      No offense, kid, but I was on an 8 processor computer back in '89. You are too busy being all smart and shit and talking like you have a clue to actually find anything out.

    18. Re:Time to refine operating systems... by drsmithy · · Score: 1
      How would you rate Mac OS X on its multiprocessor handling?

      Average. Probably at about the same level NT 4.0 and Linux 2.2 were in their day.

      OTOH, with the read availability of multiprocessor machines today, it will (and has) likely improve a lot quicker than they did. I would expect it to be comparable to Windows and Linux at either the next major release, or the one after that.

  10. Proofreading... by x_solidus_x · · Score: 1

    Did anyone else notice that the 2nd graph on page 3 and the graphs on page 4 don't match the results under them.

    The graphs show the Dual Core out-performing the Quad, but the descriptions indicate how much faster the Quad is.

    Sigh.. oh well. Moving on..

    1. Re:Proofreading... by InsaneGeek · · Score: 1

      Maybe you might want to proofread again:

      The quad-core Core 2 Extreme QX6700 is only showing about a 14% performance advantage over the dual core X6800 chip in the base CPU test module . We should note that an Athlon 64 FX-62 dual core processor scores around 5700 in the PCMark05 CPU test module.

      The overall score actually shows the QX6700 slightly slower than the dual core Core 2 chip.

    2. Re:Proofreading... by miller701 · · Score: 1

      Isn't that a per processor score?

    3. Re:Proofreading... by x_solidus_x · · Score: 1
      That's the first page.. look at the last two pages: e.g.,
      Again, the 2.66GHz quad-core Core 2 Extreme QX6700 shows itself to significantly faster than the 2.93GHz
      while the graph shows the Dual Core receiving a score of 80 to the Quad's 49. Their labels are flipped.
    4. Re:Proofreading... by Anonymous Coward · · Score: 0

      Unfortunately you're confused. The graphs show the quad core decidedly faster. Read the graph titles, shorter bars are faster on the 3ds test. In the case of the graph on page three, those are times to complete. In other words 49 seconds versus 80 for the dual core. In PovRay it's pixels per second so longer bars are faster.

      read it again

    5. Re:Proofreading... by tetigistus · · Score: 1

      I think you missed the part at the top of the image that states "Lower Scores = Better Performance."

  11. Before the naysayers come out by Kelz · · Score: 2, Insightful

    I seem to remember a particular article in which everyone seemed to decry the chip before it came out, citing "wait for the independant reviews". True, do that, but this time maybe people will think of Intel with a little more credibility? But then again, this is slashdot!

    1. Re:Before the naysayers come out by evilviper · · Score: 1
      True, do that, but this time maybe people will think of Intel with a little more credibility? But then again, this is slashdot!

      Oh yeah, a real hotbed of hate for Intel, this is...

      Give me a break. AMD, to this day, gets unfairly poor treatment on /. with myths of chip shortages, poor performance, heat problems, crappy motherboards, etc. These myths have been in decline in recent years, but they still persist, even though AMD has been slaughtering Intel until VERY recently.

      And your post is even a good example of the anti-AMD sentiment still prevalent. As if the instant Intel FINALLY comes out with something competitive, their reputation should be wiped clean, even though it took AMD years of utterly beating Intel to establish such a position.

      --
      Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
  12. Sure .. by b0r1s · · Score: 1

    And Sun is great for servers, engineers, and high end graphic designers / 3D rendering labs / etc.

    As long as you don't mean to suggest it for an office or home use, unless you can also suggest a meaningful Windows / Office / Exchange replacement that won't require retraining a few million people.

    --
    Mooniacs for iOS and Android
    1. Re:Sure .. by edmudama · · Score: 1

      I spun up a debian etch snapshot in a VM this morning and Evolution was connected to my corporate exchange server just a few minutes later. OpenOffice runs as well, just fine.

      I assume those'll run nearly as well on Solaris as well as Linux, being open source.

      --
      More data, damnit!
    2. Re:Sure .. by The+Warlock · · Score: 2, Insightful

      If an employee isn't smart enough to manage the differences between MS Word and OOo Writer by himself, show him the fucking door, because he's clearly so goddamn stupid he'll generate problems in other areas. Seriously.

      --
      I've upped my standards, so up yours.
  13. ExtremeTech has more benchmarks by mikemuch · · Score: 0

    ahref=http://www.extremetech.com/article2/0,1697,2 021888,00.asprel=url2html-4007http://www.extremete ch.com/article2/0,1697,2021888,00.asp>

    1. Re:ExtremeTech has more benchmarks by mikemuch · · Score: 4, Informative

      Well that linking format didnt' work: http://www.extremetech.com/article2/0,1697,2021888 ,00.asp

    2. Re:ExtremeTech has more benchmarks by e03179 · · Score: 1
      --
      -516
    3. Re:ExtremeTech has more benchmarks by Anonymous Coward · · Score: 0
      Well that linking format didnt' work


      Was the preview button broken too?

  14. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by Eccles · · Score: 1

    Any chance one would fit in an iMac or a Mac Mini?

    --
    Ooh, a sarcasm detector. Oh, that's a real useful invention.
  15. Quad Core Gaming by Psiven · · Score: 2, Interesting

    Currently the only game in the near future that will take advantage of multithreading is Crysis, shortly followed thereafter by HL2:EP2. In the case of Crysis, lead designer Cevat Yerli is quoted as saying that they are "scaling the individual modules, like animation, physics and parts of the graphics with the cpu, depending how many threads the hardware has to offer" (incrysis.com). But he has also stated that the game will get a 10-15% boost per thread in a 64bit environment compared to 32bit. If this is true, then what are the implications on performance when operated in AMD's upcoming 4x4 processer?

    The AMD 4x4 is pure 64bit, so does this mean that when compared to Kentsfield, a quad 32bit processor, Crysis would behave 40-60% (4x10% or 4x15%) faster?

    1. Re:Quad Core Gaming by neilyos · · Score: 2, Informative

      FYI, Kentsfield has 64 bit instructions, and therefore is 64 bit capable. Please stop spouting this "AMD is the only pure 64 bit processor" garbage.

    2. Re:Quad Core Gaming by Psiven · · Score: 1

      It was a legitimate question. It would be more helpful to explain why Kentsfield would be comparabe to Kentsfield in Crysis than huffing off. I was merely curious to know if this would have an impact in the case of a game made 64 bit compatible, not spamming FUD.

    3. Re:Quad Core Gaming by DragonWriter · · Score: 1
      Currently the only game in the near future that will take advantage of multithreading is Crysis
      I thought I remembered seeing that, among current games (not near future) Civ 4 was multi-threaded, though it may use some lightweight thread library rather than system threads, in which case it wouldn't necessarily get any advantage from multicore/multiprocessor systems.
    4. Re:Quad Core Gaming by Psiven · · Score: 1

      I looked around and I guess I spoke too soon. GalCiv uses multithreading for the AI appartently. Quake3 had multi processor support as well, don't know if it did any good though.

    5. Re:Quad Core Gaming by Anonymous Coward · · Score: 0

      Kentsfield is not a 32-bit processor.

    6. Re:Quad Core Gaming by snuf23 · · Score: 1

      The latest Quake 4 patch is multithreaded and benchmarks show a huge improvement with MP enabled.

      --
      Sometimes my arms bend back.
  16. Speaking of thread happy OS's, how about good ol' BeOS? It was designed from the ground up to be run with multiple processors and the more the better.

    Should dig that one back up und update the old batmobile.

  17. My favorite application will by benhocking · · Score: 2, Interesting

    If I add more cores, it's so I can simulate bigger neural networks in close to real time. Depending on my level-of-detail, 10,000 neurons take anywhere from 250-750 MB. In order to run 100,000 neurons I need dozens of CPUs (currently done via Beowulf clusters), and each CPU needs a lot of RAM. (Up to about 100k neurons, synapses scale roughly as n^2, not n - at least in our model of the hippocampus.)

    --
    Ben Hocking
    Need a professional organizer?
    1. Re:My favorite application will by portmapper · · Score: 1
      You have a CPU bound process that you split over several cores/CPUs since a single CPU is not fast enough for you, but this comes at a cost as you know: syncronization overhead and complexity of algorithms. Your special application may be able to split all this work over many cores/CPUs (even over network), but the majority of applications will not be able to do this.

      I'm pretty sure that many will be greatly disappointed that their quad core CPU will not be four times as fast as a singe core one, far from it (in general).

  18. dual-proc systems by Anonymous Coward · · Score: 0

    It's always advisable to run similar processors on dual-proc motherboards. It's immediately obvious why this is necessary for speed. But, is this rule of thumb true for the number of cores? Say I wanted to cheap out, buying a dual socket board and a Core Duo now, and then as the quad-core Core processors, drop one into the remaining slot? 6 cores?

    1. Re:dual-proc systems by neilyos · · Score: 1

      no regular Core 2 Duo (or quad for that matter) is dual-socket capable. You would need the server version (Xeon) to be able to do that. But you do pose an interesting theory.

    2. Re:dual-proc systems by Procyon101 · · Score: 1

      I wouldn't. You will likely run into issues getting it to work, as I doubt Intel has prepared their chip for such a scenario.

    3. Re:dual-proc systems by Klintus+Fang · · Score: 1

      It's more likely a question of whether or not the OS and chipset can handle it. The cores in one socket very likely do not care in the least how many cores might be running on the other. Only the OS and chipset should need to know about that. I'd research it before trying though...

      --
      In a minute there is time For decisions and revisions which a minute will reverse. -T.S. Eliot
  19. Names by jeffy210 · · Score: 2, Insightful

    2.66GHz Core 2 Extreme QX6700??

    So now, now only have they gone back to pointing out the clock speed, they add the NVidia product name at the end? Surely there's got to be a simpler way to do this, without even taking into account AMD. I mean you have:

    - Dual Processor Pentium
    - Dual Core Pentium D
    - Core 2 Solo
    - Core 2 Duo
    - Core 2 Quad
    - Dual Processor Core 2 Quad

    Seriously, that's some major word jumble and you haven't even specified anything like clock speed (I know it's not all about clock speed, but uniform naming to differentiate would help).

    --
    ------
    "And may your days be long upon the earth."
    1. Re:Names by Bacon+Bits · · Score: 1

      Uh... I hate to point this out, but AMD did it first. 2000+... 2500+... 3000+... 4000+....

      I mean, does Intel Core 2 Extreme QX6700 really roll of the tounge so much worse than AMD Athlon 64 3200+ socket 939 (which, if you remember, is important since socket 754s also had a 3200+)?

      --
      The road to tyranny has always been paved with claims of necessity.
    2. Re:Names by jeffy210 · · Score: 1

      Hence why I said "without even taking into account AMD.", They're just as bad at it. And they've been pulling an Intel quite recently too. Really clockspeed + codename should be well enough. If you want to know more about the specific chip, look up the code name info. Keep the marketdroids out of it (You know it wasn't a tech who came up with Core 2 Duo)

      --
      ------
      "And may your days be long upon the earth."
  20. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by Jeff+DeMaagd · · Score: 1

    You don't void your warranty for upgrading a Mac or any other computer. Your "friends" are wrong about this, at least in the US, because it would violate the Magnuson-Moss Warranty Act.

    The only way you void your warranty is if in upgrading your computer, you damage it or the parts you add damage the computer. Any damage you do is not covered, but anything else should still be covered.

  21. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by Jeff+DeMaagd · · Score: 1

    No. There probably won't be a quad core chip that will go in an existing iMac or Mac mini because the sockets are different, and future quad core notebook CPUs will use a different socket for faster FSB.

  22. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by Jeff+DeMaagd · · Score: 1

    There's one addendum I should make - Apple's warranty won't cover the parts that weren't bought through Apple.

    But what I'm really saying is that you don't automatically void your warranty if you upgrade your computer.

  23. The question I have been wondering.... by enc0der · · Score: 1

    Is if you need to replace them in pairs in a dual socket machine. I am about to purchase a MacPro and wonder if down the line, cost being the prohibitive part of the plan, if I could just upgrade one of the processors and then have 6 cores instead of 4. I use Digital Performer, and the more cores the better :)

    1. Re:The question I have been wondering.... by Movi · · Score: 1

      I would believe that having a non-parity CPU setup is impossible, because of potential timing issues. But i may be wrong.

    2. Re:The question I have been wondering.... by enc0der · · Score: 1

      I might be confused at what timing issues you are talking about? I don't see how having 6 cores is any different than 8 in terms of timing. It's still two separate chips. Mostly my question derives from some of the other architectures as well, that have 3 cores, and even Intel's mention of 80 (or whatever the number was). Is the portion of the architecture that handles the thread distribution that robust? (Of course, if you mean chip speed, and bus speed, I am assuming that they would have to match before it could work)

    3. Re:The question I have been wondering.... by Klintus+Fang · · Score: 1

      yeah. there might be reasons such a setup would not work, but it wouldn't be timing issues. there are no timing issues to consider between separate chips that are plugging into separate sockets. as I said elsewhere, the question of whether it is doable will likely come down to whether the chipset and/or OS are able to comprehend such an asymmetric configuration. and I don't know if they do.

      --
      In a minute there is time For decisions and revisions which a minute will reverse. -T.S. Eliot
    4. Re:The question I have been wondering.... by FuturePastNow · · Score: 1

      As odd as it sounds...that may actually work. I'd suggest reading this: http://www.tomshardware.com/2005/11/28/are_three_c ores_better_than_two/index.html

      That's a dual-core Opteron and a single-core Opteron in a tri-core system. Highly unstable, but very close to working, and the cores in the processors they used weren't even identical.

      A Core 2 Duo 2.66GHz and a Core 2 Quadro 2.66GHz would have six identical cores, with the exact same clock speed, bus speed, and instruction set. I'd really like to see some hardware review site try this.

      --
      Give a man fire, and you warm him for the night. Set a man on fire, and you warm him for the rest of his life.
    5. Re:The question I have been wondering.... by FuturePastNow · · Score: 1

      I was just thinking... in the article I linked, they had BIOS-related problems running non-identical processors. Given its lack of a BIOS, a Mac Pro may very well be the only way to run a six core configuration (on the other hand, EFI might react badly. The only way to know is to try).

      --
      Give a man fire, and you warm him for the night. Set a man on fire, and you warm him for the rest of his life.
  24. Learn to read maybe. by Anonymous Coward · · Score: 0

    He said freebsd isn't as good as linux and windows. He's wrong, freebsd is just as good as linux and windows, and none of the above are as good as solaris, but none the less, he said nothing bad about windows at all.

  25. Still no good motherboards. by Kenja · · Score: 1

    The Core series chips has the same problem I have with just about every CPU from AMD or Intel. No good motherboards. It seems you cant get a motherboard with basic features such as 133mhz PCI-X and without such crap as onboard audio and RAID without going to the Xeon or Opteron lines.

    --

    "Have you ever thought about just turning off the TV, sitting down with your kids, and hitting them?"
    1. Re:Still no good motherboards. by dwlovell · · Score: 1

      The ASUS P5WDG2-WS has two PCI-X slots and uses the 975X chipset that is supposed to work with Core 2 Duo, but the board was released just prior to the Core 2 release and it does not look like they are going to update the BIOS to support Core 2. I dont see anything else in the lineup with PCI-X.

      But PCI-X is a dying standard that is getting replaced by PCI-E x8 and x16 slots. (PCI-E x8 is 2GB/s while PCI-X is only 1.06 GB/s)

      There are more and more RAID and other controllers being produced for PCIe, so hopefully there wont be an issue in the near future.

      Besides, if you want the performance of a PCI-X slot, what is wrong with buying a Xeon Woodcrest (ie: Xeon 51xx) board? Woodcrest is based on the same Core 2 architecture, but has twice the cache and support multi-socket configurations. So you can get a Xeon Woodcrest system that has two Xeon 51xx processors for a total of 4 cores. When the quad-core Xeons are released, you will have 8 cores in one system.

      Take a look at the Dell Precision 690 for an example of a current system using the new Woodcrest Xeons.

      -David

    2. Re:Still no good motherboards. by zardie · · Score: 1

      The Pro version of that ASUS board DOES support the Core 2 Duo and presumably, the quad core chips as well.

  26. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by HTH+NE1 · · Score: 1

    The only way you void your warranty is if in upgrading your computer, you damage it or the parts you add damage the computer. Any damage you do is not covered, but anything else should still be covered.

    And so the warranter will declare the damage was caused by the non-factory parts you added and not investigate further.

    What I want to know is if the two firmware updates Apple pushed to fix Boot Camp problems also blocked this type of upgrade, like they did to the Blue & White G3s to prevent their easy upgrade to a G4.

    --
    Oh, say does that Star-Spangled Banner entwine / The myrtle of Venus with Bacchus's vine?
  27. double the performance ? by poormanjoe · · Score: 1

    Has it been 18 months already? Or are cpu's following the trends of storage?

    --
    I want to be retired when I grow up.
    1. Re:double the performance ? by The+Warlock · · Score: 1

      It's just Intel catching up from the Pentium 4 era, where it took a hell of a lot longer than 18 months.

      --
      I've upped my standards, so up yours.
  28. Synchronization overhead for us is less than 1% by benhocking · · Score: 1

    We did a lot of analysis on the speedup conferred by parallelizing our code. Interestingly enough, for a long while it was actually super-linear! I.e., quadrupling the number of CPU's cut the time to less than 1/4th of the original time. This was explained by the effects of having a larger total cache size.

    Nevertheless, sure, many applications will not benefit from parallelization as much as ours. Neural networks are naturally parallelizable.

    --
    Ben Hocking
    Need a professional organizer?
    1. Re:Synchronization overhead for us is less than 1% by fitten · · Score: 1

      Yup, there are cases where you can get superlinear speedup for exactly that reason. If you have data that can be split evenly among all cores (with little communication and little sharing), eventually you can add enough cores (and cache) to hold all the data in cache memory across all the cores.

      "Embarassingly Parallel" are the types of applications that are trivially parallelizable... ray tracing and many other video effects are also of this category, which is why video cards get faster and faster (look at the number of raster/pixel units and how each generation of video card has more and more).

  29. Did Intel learn *anything* from Java2? by Kostya · · Score: 4, Insightful

    What the hell is with this Core2 Quad crap? It should be Core2 and Core4. You would have thought Intel would have learned from the nightmare Sun/Java went through with the whole "Java2 1.4" branding nightmare. Sun finally wized up and started calling everything Java 4, Java 5, and Java 6. Why would Intel start such a fiasco?

    I get that they are trying to say "Hey look, it is a totally different architecture!" But calling it Core2 isn't going to do that. People will just end up calling them Dual Core or Quad Core anyways, not Dual Core2 and Quad Core2. It's just going to detract from their branding, not help it.

    --
    "Doubt your doubts and believe your beliefs." -- Switchfoot, Ode to Chin
    1. Re:Did Intel learn *anything* from Java2? by DragonWriter · · Score: 1
      What the hell is with this Core2 Quad crap? It should be Core2 and Core4. You would have thought Intel would have learned from the nightmare Sun/Java went through with the whole "Java2 1.4" branding nightmare. Sun finally wized up and started calling everything Java 4, Java 5, and Java 6.


      Actually, up through Java 2 Standard Edition 1.4, they used "Java 2 Standard Edition 1.x". I'm pretty sure there was and is no "Java 4" product.

      The next product version is "Java 5", for which the runtime and development kits are JDK 1.5.x and JRE 1.5.x. I'm not sure if its clear yet what the Mustang (for which the JDK is 1.6, judging from the current beta release) or Dolphin (presumably JDK 1.7) product versions will be, though "Java 6" and "Java 7" are natural guesses.
    2. Re:Did Intel learn *anything* from Java2? by nuzak · · Score: 2, Insightful

      > What the hell is with this Core2 Quad crap? It should be Core2 and Core4.

      Core 2 is the second iteration of the "Core" line. There is Core 2 Solo and Core 2 Duo. It's the new "Pentium", stick with a single brand and append numbers to it. It doesn't help that there's *also* pentium-branded chips still being made.

      I agree though, it's still a mess. I'm pretty experienced, and I get confused by it. Quick, which is newer, a Foofra QXV5024351GL or a Wibble RG188716912B?

      --
      Done with slashdot, done with nerds, getting a life.
    3. Re:Did Intel learn *anything* from Java2? by Kostya · · Score: 1

      Ok, maybe they never called Java2 1.4 Java 4, but that's my point: with Java2 1.5, they officially changed this approach. There will never be anything called "1.6" when it is released (well, maybe somewhere buried in the code or in some arcane property)--it will be called Java 6. It's not a guess that they will be Java 6 or Java 7--that's the new naming scheme.

      Which is what I was trying to get at--naming something FooBar2 3.4 is absolutely crazy from a branding and public relations perspective. Sure, it all makes sense from a code/product version number thing. But that stuff should be internal. And the fact that Intel isn't getting that is just weird to me--they made tons of money off of Pentium branding. How could they have thought Core 2 Duo was a good thing? Even something lame like CoreExtreme would have been better than the confusion that is going to come from Core 2 branding.

      I have always felt Sun made a mistake calling Java 1.2 Java2/Java 1.2. They should have just called it Java 2.0. Sure, it was very similar, but it's not like code for 1.1 or 1.2 was easily interchangable. Then they could have had Java 1.3 be Java 2.1 and Java 1.4 be Java 2.2--because that's what they were like. Anything Java 1.2.x or greater was mostly compatible (save for library calls). But the differences between 1.1-1.2 and differences between 1.2-1.3-1.4 aren't even the same kind of differences.

      Which means Java 5 would have been Java 3.0--and let's face it, with generics and autoboxing, it merits a new major revision number to communicate severe incompabilities.

      Anyways, as a Java programmer who always wondered what Sun was thinking with their whole Java2 campaign, I'm just flabbergasted that Intel would fall in the same trap.

      --
      "Doubt your doubts and believe your beliefs." -- Switchfoot, Ode to Chin
    4. Re:Did Intel learn *anything* from Java2? by DragonWriter · · Score: 1
      Anyways, as a Java programmer who always wondered what Sun was thinking with their whole Java2 campaign, I'm just flabbergasted that Intel would fall in the same trap.


      Intel has different historical problems that they are responding to, particularly, the inability to trademark a number, and the fact that their competitors (including AMD, Cyrix, and others) copied Intel's non-trademarkable numbers to sell competing processors, which is why, starting from the Pentium, Intel hasn't used numbers as the main identifier for their major processor products, but instead has gone with word soup, which is eminently defensible as trademark. Its also why AMD, likewise, hasn't used numbers as its main label since then (initially, because they couldn't copy intel any more, and later because they were the leader and didn't want to be copied.)

      Its not really the same thing as Java versioning thing at all, I'd say.

    5. Re:Did Intel learn *anything* from Java2? by Kostya · · Score: 1
      Intel has different historical problems that they are responding to, particularly, the inability to trademark a number, ... Its not really the same thing as Java versioning thing at all, I'd say.

      I assume you are referring to the inability to trademark 386, 486, etc. But I don't see how that problem has to do with them coming up with the brilliant brandname "Core 2". And don't dismiss branding as an issue--the Core 2 line could be the biggest thing to happend to Intel since the original Pentium.

      So the issue is one of branding (at least that is what I have always been referring to). Core 2 Solo and Core 2 Duo is just a mess from a branding perspective--never mind when you start to really lay on the numbers (like they did in the article). And it is this "two numbers that refer to two different things" branding issue I was referring to from the very beginning. Sun found that Java2 1.X was confusing people instead of getting them on the band wagon. I suspect that Intel will discover the same thing with "Core 2 [CORE_NUMBER]". Hell, most people didn't even know there was an original "Core" platform. So what does branding everything with Core 2 get them if 90% of the consumer market never heard of "Core 1" to begin with?

      --
      "Doubt your doubts and believe your beliefs." -- Switchfoot, Ode to Chin
    6. Re:Did Intel learn *anything* from Java2? by DragonWriter · · Score: 1
      I assume you are referring to the inability to trademark 386, 486, etc. But I don't see how that problem has to do with them coming up with the brilliant brandname "Core 2". And don't dismiss branding as an issue--the Core 2 line could be the biggest thing to happend to Intel since the original Pentium.


      I'm not dismissing branding. OTOH, its not much different for the Core than what they've did with the Pentium series, except that there are modifiers up and down the line, rather than just at certain places: Instead of "Pentium III" or "Pentium IV" as both the "base model" and the generic name for the class, with things like "Xeon" modifying it for certain versions, their is a clear distinction of the processor class ("Core", "Core 2") and the more specific processor designation within the class ("Solo", "Duo", "Quad", "Extreme")—now, admittedly, there are important distinctions within those groups, too, that you don't get to without the model numbers.

      Core 2 Solo and Core 2 Duo is just a mess from a branding perspective--never mind when you start to really lay on the numbers (like they did in the article). And it is this "two numbers that refer to two different things" branding issue I was referring to from the very beginning.


      Solo/Duo/Quad/Extreme are words, not numbers, even if they (except Extreme) may evoke numbers.

      I suspect that Intel will discover the same thing with "Core 2 [CORE_NUMBER]".


      Intel isn't using "Core 2 [CORE_NUMBER]". "Solo", "Duo", and "Quad" suggest numbers, and "Extreme" is not related to a number at all.
    7. Re:Did Intel learn *anything* from Java2? by edbob · · Score: 1

      I never really thought about it until now. It is certainly a different naming convention than what exists for the Pentium. I think part of the reason may be that the Pentium 4 name has been used for so long and for a number of different processor families. I really don't know what would have been so wrong with calling it Pentium 5 or maybe getting away from the Pentium moniker altogether and calling it Sexium. I also wonder if Ma and Pa will be wondering why the new Core 2 processors have a lower clock speed (and in their mind lower performance) than their old Pentium 4 system. Don't laugh, I've already seen it. Intel trained their customers only too well to associate clock speed with performance.

    8. Re:Did Intel learn *anything* from Java2? by Anonymous Coward · · Score: 0

      The first Core processors were released in January in both single core (Core Solo) and dual core (Core Duo) versions. The Core 2 processors are very different from those first Core processors and thus the number. By your logic the first single core would have been Core 1 (Core Solo) and then Core 2 (Core Duo). This is where we hit a snag. Does Core 2 Duo become Core 2.1 or Core 2 Again? What happens when they release Core 2 Solo processors? Then the Core 1.1s would be better than the Core 2.0s which would really confuse everything. Perhaps you should just relax, take a deep breath and think this one through.

    9. Re:Did Intel learn *anything* from Java2? by istewart · · Score: 1

      They are saving Core 4 for the eventual return of NetBurst.

    10. Re:Did Intel learn *anything* from Java2? by Emetophobe · · Score: 1

      Originally there was the Core Duo (codename Yonah), then there was the Core 2 Duo (codename Conroe). The 2 is not a representation of the number of cores, the 2 represents the updated intel core architecture, hense Core 2. Intel decided to use "Duo" to represent dual core.

    11. Re:Did Intel learn *anything* from Java2? by julesh · · Score: 1

      Ok, maybe they never called Java2 1.4 Java 4, but that's my point: with Java2 1.5, they officially changed this approach.

      And you think calling it "Java 2 Platform Standard Edition 5.0" is any better?

    12. Re:Did Intel learn *anything* from Java2? by eMbry00s · · Score: 1
      I agree though, it's still a mess. I'm pretty experienced, and I get confused by it. Quick, which is newer, a Foofra QXV5024351GL or a Wibble RG188716912B?
      Urg, I hate that. All the audio software companies do it, which makes it really hard to have a look at their site to check which of their umpteen products fit you the best.
  30. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by Psiven · · Score: 1

    DIdn't Jobs update the Mac mini line with Core 2 Duos? If so, than new minis would be compatible with Kentsfield.

  31. 64-bit benchmarking? by AaronW · · Score: 1

    Why is it that nobody seems to benchmark these chips in 64-bit mode? All the benchmarks seem to be 32-bit only.

    --
    This post is encrypted twice with ROT-13. Documenting or attempting to crack this encryption is illegal.
    1. Re:64-bit benchmarking? by smash · · Score: 1

      Maybe because very few people run a 64 bit O/S, and even fewer run 64bit ready software?

      --
      I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
  32. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by nuzak · · Score: 2, Insightful

    You don't void your warranty for upgrading a Mac or any other computer. Your "friends" are wrong about this, at least in the US, because it would violate the Magnuson-Moss Warranty Act.

    My interpretation of Magnuson-Moss is that it prohibits bundling, like say, Apple requiring you purchase Apple-branded CPU's to upgrade. Pulling out your own CPU is probably still a warranty killer. They just can't automatically call it void if the problem is obviously unrelated and a defect in the merchandise, like oh, the paint starts yellowing after you open it up (that's about the only thing I can think of that's TOTALLY implausible to connect to a cause of opening up the case).

    However, I bet you anything Apple's warranty says Limited Warranty. At that point they're largely off the hook. State laws may still apply.

    --
    Done with slashdot, done with nerds, getting a life.
  33. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by Anonymous Coward · · Score: 0

    No. The Mac mini uses Core Duo. Only the iMac currently uses Core 2 Duo.

  34. It's not Core 2. It's Core 2 Duo by WoTG · · Score: 2, Insightful

    But yeah, it's got to be one of the stupidest naming schemes from a major vendor of anything that I've seen in a long time. I was looking forward to a Pentium V. Sure it would have seemed a bit redundant, but so is the Core 2 Duo chip that's in the new laptop I've been eyeing...

  35. Who gets them in volume first? by Andy_R · · Score: 1

    It will be interesting to see how long it takes Apple to ship 8-core machines (or in intel speak, twin core 2 quad machines... what were they thinking?). Steve Jobs drives a hard bargain, and I wouldn't mind betting that in return for handing Intel his 8% of the computer market, and ruling out AMD chis for the forseeable future, he extracted something pretty special from Intel. I wonder if Apple has 'first dibs' on these, especially given that OSX's multithreading might well be more flattering to the chips than Windows.

    --
    A pizza of radius z and thickness a has a volume of pi z z a
  36. Stop! My sides are hurting! by Anonymous Coward · · Score: 0

    Steve Jobs drives a hard bargain, and I wouldn't mind betting that in return for handing Intel his 8% of the computer market ...

    8%? Bwahahahahahahaha!!!!!! ... especially given that OSX's multithreading might well be more flattering to the chips than Windows.

    OSX? Good multithreading?? LOLOLOLOL!!!!! With crufty Mach underneath, it's easily the worst of all the "PC" operating systems (Win, Linux, BSD, etc).

    Seriously, you're giving me a headache from laughing so hard.

  37. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by FuturePastNow · · Score: 1

    Swapping one component for another component that is designed to be a replacement for it cannot violate a warranty. It's just like replacing Apple's SATA drive with one from Best Buy. Now, if you damage the computer in any way during the upgrade process, you're SOL.

    --
    Give a man fire, and you warm him for the night. Set a man on fire, and you warm him for the rest of his life.
  38. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by FuturePastNow · · Score: 1

    The iMac and Mac mini use the mobile variant of Intel's processors. They are not compatible with the desktop processors.

    Although the mobile Core 2 Duo and the desktop Core 2 Duo are identical in most ways, the do not use the same socket.

    --
    Give a man fire, and you warm him for the night. Set a man on fire, and you warm him for the rest of his life.
  39. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by Jeff+DeMaagd · · Score: 1

    The mini uses the Yonah chip, with a notebook chip socket. It will work with early Merom chips. There will be no Kentsfield counterpart that uses that socket.

  40. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by Ed+Avis · · Score: 1

    If you replace the processors in a Mac Pro with quad-core ones, what do you do with the old processors? It seems wasteful just to sell them as secondhand on Ebay, shouldn't Apple buy them back or something?

    --
    -- Ed Avis ed@membled.com
  41. 80 cores out in 5 years by dp_wiz · · Score: 0

    That would be nice moment for GNU/HURD to start World Domination.

  42. Have We (Core2Duo Buyers) Been Had? by Anonymous Coward · · Score: 0

    Does this mean that Core2Duo is the new "Celeron" compared to Core2Quad "Pentium"?

  43. 1066MHz FSB? by julesh · · Score: 1

    The CPU will clock at 2.66GHz with a 1066MHz effective FSB

    I'm sure earlier articles were saying it would have a 1333MHz FSB. Has the spec been dropped for some reason, or is it just early models that will have this limitation?

  44. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by gbulmash · · Score: 1

    If you replace the processors in a Mac Pro with quad-core ones, what do you do with the old processors? It seems wasteful just to sell them as secondhand on Ebay, shouldn't Apple buy them back or something?

    Nah, you just buy a 1U case, dual woodcrest mobo, and build yourself a *buhlazing* little server. Rent a partial rack somewhere, plug in a 10 Mbps line, and serve up a million pageviews a day without breaking a sweat.

    - Greg

  45. Re:Already tested: Two Quad-Cores in a Mac Pro, ma by SP33doh · · Score: 1

    I voided my windows XP product key by upgrading my computer.