Catch up on stories from the past week (and beyond) at the Slashdot story archive

 


Forgot your password?
Close
typodupeerror
×
Intel Technology

New Pentium 5 Details - 5-7ghz? 408

Posted by CmdrTaco from the redundant-naming-schemes dept.
zymano writes "This article gives some details on Pentium 5. It will have 64 bit extensions and maybe a 4000 mhz frontside bus. Quote from the article,'The Pentium V is likely to fly along at between 5GHz to 7GHz, have 2MB plus of level two cache, be built on a 90 nanometer process, and have a stackable design. '"
This discussion has been archived. No new comments can be posted.

New Pentium 5 Details - 5-7ghz? More

New Pentium 5 Details - 5-7ghz?

Comments Filter:

  • The next chip called Nehalem (Score:5, Funny)

    by drkich ( 305460 ) * <dkichline.gmail@com> on Sunday September 28, 2003 @11:59AM (#7077651) Homepage
    Is it me or would you pronounce that "Nail 'em"? A dig at AMD perhaps?

  • Sadly (Score:3, Interesting)

    by Oculus Habent ( 562837 ) * <oculus.habent@gm ... Nom minus author> on Sunday September 28, 2003 @12:00PM (#7077663) Journal
    The fifth fifth processor.

    64-bit extensions? In the same way AltiVec was 128-bit extensions?

    The 4GHz bus does sound good, thought.

    • Real 64 Bit extensions (Score:5, Informative)

      by EDA Wizard ( 2225 ) on Sunday September 28, 2003 @12:16PM (#7077781)
      P-V should have 64bit extensions for both pointers and basic math.

      64bit pointers and basic math on those pointers, are really what people desire so that more than 4GB can be trivially addressed in a single process's virtual memory space. Think about people who want to manipulate a video file that is larger than 4GB.

      AltiVEC **128 bit** is just wide data manipulation and is of no use for those that require large memory footprints. It has the same 32 bit address lines and pointers at a 60MHz Pentium I.

      That being said, P-V should also have more than the current 36 bit of physical address lines. I'm guessing they will have 40 usable bits or so of the address bus to physically address memory.

      So if you want to put in more than 4GB of RAM you can. But if you don't, 64 bits will be useful to address more than 4GB of a video file sitting in virtual memory.
      • What the hell are you talking about? Altivec has nothing to do with the chip's word-length. It's the SIMD piece.

        The G3 and G4 are 32bit chips, the G4 has Altivec. The G5 is a 64bit chip and has Altivec.

    • Re:Sadly (Score:2, Funny)

      by Anime_Fan ( 636798 )
      The 4GHz bus does sound good, thought.

      It's Intel, more likely to be 20x200 MHz...

  • Yes but ... (Score:5, Funny)

    by maroberts ( 15852 ) on Sunday September 28, 2003 @12:01PM (#7077666) Homepage Journal
    ... will it be able to do Math correctly?

  • Other Issues (Score:5, Funny)

    by Absurd Being ( 632190 ) on Sunday September 28, 2003 @12:01PM (#7077667) Journal
    'The Pentium V is likely to fly along at between 5GHz to 7GHz, have 2MB plus of level two cache, be built on a 90 nanometer process, and have a stackable design. ' And raise the temperature of the room it's in by 50 Celsius.
    • I'm wondering what type of PSU they're hooking this thing up to as well. I mean, at that speed and probably power consumption, we'll be seeing a whole new line of PSU's just to power the thing (not to mention needing a new video card to take advantage of it).

      Wonder if I'll have to unplug my stove in order to allow my PC access to the ol' 220V, or perhaps I'll just ask my landlord for access to the MAINS.

      Either way... I have this picture of the lights in my apartment dimming and my power meter suddenly s
    • The Pentium V is likely to fly along at between 5GHz to 7GHz, have 2MB plus of level two cache, be built on a 90 nanometer process, and have a stackable design. ' And raise the temperature of the room it's in by 50 Celsius.

      From an inside source.

      "Yes the new pentiums heat will rise exponetially with the number of cycles. So we've added special bios to control the useage of excess CPU cycles, and allow the users to decide whether or not to run their chips full out. If this protection system fails and the

  • Article Text (Score:4, Informative)

    by ChozCunningham ( 698051 ) <slashdot.org@cho ... minus herbivore> on Sunday September 28, 2003 @12:04PM (#7077683) Homepage
    DETAILS HAVE EMERGED of the future design of Intel's Tejas/Pentium V processor, and of how the chip firm will present it to the world.

    The chip will sample internally at Intel in January 2004 and will take between four to six months to get to market. The Pentium 6 will follow a very similar schedule.

    The Pentium V is likely to fly along at between 5GHz to 7GHz, have 2MB plus of level two cache, be built on a 90 nanometer process, and have a stackable design.

    The processor we believe, sits in the LGA 775 pin socket, and above it is a very thin heatsink. But, according to sources close to the firm's plans, another permeable heatsink can sit between this and another microprocessor module, giving a stackable design.

    The final design of this arrangement is not set in stone.

    According to this source, and the details have not been confirmed, a module sitting on top could provide 64-bit extensions.

    And the source claimed, Microsoft is ready to launch a version of Windows called Elements with 64-bit extensions.

    The idea seems to be that people can buy a 32-bit module, and then add in the 64-bit processor.

    There are three samples of an arrangement of the Pentium V here in Taiwan this week, with a very thin processor and lots of wires and patches stuck on it, just to show proof of concept.

    The Pentium V could have a front side bus speed of as much as 4000MHz, the source claimed, although this may be reserved for the next chip along, the Nehalem.

    • Re:Article Text (Score:3, Insightful)

      by gl4ss ( 559668 )
      heheh, details indeed!

      only thing certain is that it is just marketing at this point.

      on a sidenote.. no fucking way for a modular system(add in 64bit shit ala math co-processor), not anymore. there's just no point in selling so expensive ships for consumer use that there would be much point in such. and also it does sound like it would be quite awful design too that way(being '64bit' extensions which could be just about anything!)..

      also the timing schedule mentioned somewhere seems a LITTLE opti
  • .. That article sounds a bit too good to be true, I'd like to see their sources. Some of those figures seem to be plucked from thin air.
    They would need some serious cooling going on at those speeds ...

    Anyhow Imagine a Beowulf Cluster of these ..

  • are you serious? (Score:5, Funny)

    by tomstdenis ( 446163 ) <tomstdenis@gma[ ]com ['il.' in gap]> on Sunday September 28, 2003 @12:05PM (#7077689) Homepage
    This article is all speculation...

    Ok here, um the next AMD processors will be faster than before, have more cache, maybe some new instructions [doworkNow! then doworkNow! (ext)].

    I must be an AMD insider now, l33t l33t !

    Tom

    • It isn't funny, it's insightful! They are talking about P5 and P6! With a 4Ghz front side bus! And it only needs a little heatsink! And at the bottom, under related links, they have stuff about the Pentium 8! And it's the Inquirer!

      Besides, everybody knows that the new AMD will run at 10Thz, with a 1Thz FSB! And its new 3dTomorrow SIMD extentions actually see through time and execute on data that is yet to be! It will be prerendering Doom 5 scenes before you are even decide which game to play! Wh

  • Stackable Design Flaw (Score:5, Insightful)

    by QuantumFTL ( 197300 ) * on Sunday September 28, 2003 @12:05PM (#7077690)
    Stackable designs sound really cool in the sense that you can cut latency between processors (for things like cache coherence) to rediculously small levels, but what about cooling? Cooling ability is roughly proportional to surface area, and two stacked chips will make twice as much heat but have almost the same surface area as only one (as two sides cancel out). This has to be a problem.

    No this is not a troll. I honestly wonder how they expect to accomplish this.

    Anyone know?

    Cheers,
    Justin
    • Those were my first thoughts too.

    • Re:Stackable Design Flaw (Score:5, Informative)

      by SeanTobin ( 138474 ) * <byrdhuntr AT hotmail DOT com> on Sunday September 28, 2003 @12:23PM (#7077836)
      Cooling ability is roughly proportional to surface area, and two stacked chips will make twice as much heat but have almost the same surface area as only one (as two sides cancel out). This has to be a problem.
      From the article:
      The processor we believe, sits in the LGA 775 pin socket, and above it is a very thin heatsink. But, according to sources close to the firm's plans, another permeable heatsink can sit between this and another microprocessor module, giving a stackable design.
      There will be a heatsink inbetween the stacked processors, although it would be more properly named a heat spreader. They just call it permeable because it will have holes drilled into it so pins can attach to the lower processor.

      • Re:Stackable Design Flaw (Score:4, Informative)

        by QuantumFTL ( 197300 ) * on Sunday September 28, 2003 @12:32PM (#7077900)
        The processor we believe, sits in the LGA 775 pin socket, and above it is a very thin heatsink. But, according to sources close to the firm's plans, another permeable heatsink can sit between this and another microprocessor module, giving a stackable design.

        Yes, I saw that in the article, and it's pretty much the only way you *can* do it, to have something separating the chips. The question is, how can they get this to work? I mean, there's limits to how fast heat can be spread away by something like this (based on the heat conduction coefficient of the material you are using) and the latency between chips increases linearly as you increase the thickness of the separator... We can barely keep faster chips right now cool with enormous heatsinks... this seems far more ambitious.

        Also remember ohmic heating is proportional to the square of the clock speed (yes, it goes down by a factor as you get the components smaller, but you see where this is heading). IT will be a long while till Intel chips don't put out a ton of heat (when they start using something like spintronics or photonics). There's simply too much current to dissapate.

        Cheers,
        Justin

        • We can barely keep faster chips right now cool with enormous heatsinks... this seems far more ambitious.

          The problem here is that you are absolutely wrong... (nothing personal)

          We haven't come anywhere close to the limits of traditional cooling... There are just such high temperatures in current systems, because OEMs are trying to save $1 on every unit. It's a ridiculous situation, but I can tell you, from first-hand experience, that buying relative inexpensive heatsinks/fans, you can get incredible impro

        • Re:Stackable Design Flaw (Score:3, Informative)

          by mczak ( 575986 )

          Also remember ohmic heating is proportional to the square of the clock speed

          This is not true. Power dissipation is linear to clock speed - it is square to the voltage .
          And, in fact, that's not the whole story either. Today, current leakage is a very serious issue (I haven't seen concrete numbers for 90nm process technology, but the leakage gets larger the smaller process technology you use, and the power dissipation due to leakage gets comparable to the power dissipation due to the transistor switching),

    • > Anyone know?

      I guess it is not like they want to sell you processors, which you can stack as you like, but for them to make multi-core chips cheaper.

      I assume they do it in the same way they do it with the Pentium4 or Athlon-64. Heat-spreaders. They can increase almost arbitrarily the area of the chip (but not the die).

    • Re:Stackable Design Flaw (Score:3, Interesting)

      by Lumpy ( 12016 )
      Ever heard of heat pipes?

      simple copper plate between the 2 processors with heat pipes emerging to channel the heat out to a radiating surface.

      really simple actually.

      I just hope they stop their current trend of raping their customers when they want to have SMP.

      no a Xeon is not worth the price... Give me Pentium 4 chips that can do SMP (only fricking 2 way is fine!) AMD can do it... and do it well with their MP's why cant intel?
      • Heat pipes aren't a panacea. They are reasonably efficient at moving heat, and that is all. Putting a flat copper block with a couple of heatpipes (which will be problematic if, say, the mobo is placed horizontally) will not make the heat magically vanish. Hell, just to make the heatpipes work you need a reasonable difference in temperatures at the evaporating and condensing ends- and that will be pretty hard to achieve, considering the scale of things.
        Current chips generally require all sorts of nasty sup

  • So when will they change product names/lines (Score:3, Interesting)

    by quantax ( 12175 ) on Sunday September 28, 2003 @12:06PM (#7077697) Homepage
    Intel is up to Pentium 5 now, my question is when will they drop the 'Pentium n' line and go with something new. By the same token, Apple as well is up to 5 with their G-line. After a while, it gets a little rediculous and reduntant, so companies come up with a new product line (Geforce FX, kinda hybrid cause nvidia didnt want to loose the geforce recognized name). I have to say that I prefer AMD's system more with the lettered naming system, XP, MP, etc since atleast its different. So how far do you think pentium will rise to? I have a hard time saying 'Pentium 7'...
    • The numbers are used to show which chip is better instantly, without all the other numbers like Ghz or FSB. For example, most people will understand right away that the Pentium 5 is faster than the Pentium 4 simply based on the number, but and average user isn't going to know whether it's the XP or MP that's the better chip from AMD.
    • Apple's G nomenclature refers to the generation of the PowerPC architecture. Whenever they feel a PowerPC design has advanced significantly enough, it becomes the Gn processor.

    • K9 (Score:3, Funny)

      by Bowling Moses ( 591924 )
      When AMD's K6 came out following up on the massive name recognition of the K5 I was really looking forward to eventually being able to buy a K9. Think about the possible slogan: "Introducing the AMD K9. No fancy names, no gimmicks, just pure processing power that dogs the competition." Then when the K9 got older people would say "K9? Man, that slow-ass chip's a dog!" Yup, I was looking forward to both. AMD could have even made that robot dog thing from Dr. Who the mascot. But then AMD blew their cha

  • Yes but.. (Score:5, Funny)

    by MongooseCN ( 139203 ) on Sunday September 28, 2003 @12:06PM (#7077698) Homepage
    I still prefer AMD chips for some reason [theinquirer.net].

  • The new processor will go from 5-7 GHz... (Score:5, Funny)

    by NorthWoodsman ( 606357 ) on Sunday September 28, 2003 @12:07PM (#7077712) Homepage
    but will actually perform the same as a 2.5 GHz Athlon
    • Perhaps internally Intel half the clock rate, hence allowing current 2.5 Ghz chips to be instantly converted into 5 Ghz ones.

      James
    • 5-7 is -2 .. so i guess it will be slightly slower than a 2.5GHz Ahtlon, and running backwards. Sounds like a nice challange for the gcc people..
    • ...but if you looked at Anandtech and read how fast the current Pentium IV (not EE) would have to run compared to the Athlon 64 FX in the areas where it really excels, it's not that far from the truth. Of course, Intel is improving their architechture (FSB, HT, cache size +++) also, so it won't actually come to that. But I suspect the difference in clockspeed for same performance might increase.

      The reason? Intel has sold the GHz (aka the MHz) myth so well, they need to increase clockspeed in order to make

  • Wintel boo. (Score:3, Interesting)

    by ChozCunningham ( 698051 ) <slashdot.org@cho ... minus herbivore> on Sunday September 28, 2003 @12:08PM (#7077713) Homepage
    Proccessor. Add-on? OS. Add-on? This sounds like a clever attempt to creat a support nightmare for anybody developing for the pentium pentium. Oh well.

  • Worthless story. (Score:5, Insightful)

    by maeka ( 518272 ) on Sunday September 28, 2003 @12:08PM (#7077719) Journal
    The article doesn't say the processor will have 64-bit extensions. The article doesn't say anything.
    Some quotes:
    "The Pentium V is likely..."
    "The processor we believe..."
    "The final design of this arrangement is not set in stone."
    "...details have not been confirmed,..."
    "... the source claimed..."
    "The Pentium V could have..."
    "...although this may be reserved for the next chip along, the Nehalem"

    This isn't news, this is BS speculation.

  • Yeah but will it actually feel faster? (Score:5, Interesting)

    by localman ( 111171 ) on Sunday September 28, 2003 @12:10PM (#7077729) Homepage
    I swear that the PIV 2.4 Ghz machines I've used are no faster that some of the P III 1 Ghz boxes I've used. We upgraded all our development boxes at work this way and there was hardly any notable improvement... yes, the memory is tricked out so we're not having swapping issues. But you run apache, mysql, and X on one of them and it just doesn't seem like an improvement.

    Are they doing a direct trade off where they ramp up the clockspeed and break the instructions down so that less is getting done per clock or something?

    Cheers.

    • Re:Yeah but will it actually feel faster? (Score:4, Informative)

      by halo1982 ( 679554 ) * on Sunday September 28, 2003 @12:19PM (#7077807) Homepage Journal
      Are they doing a direct trade off where they ramp up the clockspeed and break the instructions down so that less is getting done per clock or something?

      Yes, thats exactly what they are doing. The P4 pipeline is 20 stages, and the P3s is something like 10. The longer pipeline helps them to ramp up speed, but at the cost of efficiency. Wheeeee.

    • I've noticed the same, and I speculate it's because our hard drive tech is still in the stone age, relatively. Your typical cheap IDE drive hasn't sped up at nearly the same rate as processor/memory/bus tech has, and let's face it - 90% of what you do on a computer in a typical day requires some level of drive (or net) access.

      The true test of speed improvement is when you're doing something very CPU intensive that can entirely fit in memory - otherwise almost all of your time is spent waiting for the dri

      • And CPU's are so blazingly fast (and have been for the past couple years) that it's rare to find an application where that's the case.

        Try emulating something using protected mode memory with DOSbox.

      • Re:Yeah but will it actually feel faster? (Score:5, Informative)

        by ericman31 ( 596268 ) on Sunday September 28, 2003 @02:12PM (#7078641) Journal

        I can't speak for SCSI, Firewire, SIDE, or any other drive techs 'cause I'm a cheap S.O.B. and won't pay the big bucks for them.

        We moved an application from 2 UltraSPARC III 750 MHz CPU's to 6 UltraSPARC III Cu 900 MHz CPU's and saw very little improvement in performance. Then we moved the disk for the application from 9 internal drives to 20 external SCSI over FC drives, and voila our IO wait dropped from 60% or so to 10% +/-. Our query response times dropped by a factor of three or more. Faster, and even more, CPU's are not the answer to data intensive problems, I/O is. Slower (clock speed wise) 64bit CPU's, with better efficiency, more memory addressing, etc. are the norm in the data center for just this reason. IF you can take advantage of your L1/L2 cache then faster clock speed on the CPU will improve performance. The reason most Intel PC's benchmark better than an older box is because the disk, memory and video sub-systems have improved, not because the CPU is making a huge difference.

        As proof, search SPEC's benchmark results [spec.org] using Dell and then Sun as your search criteria. Notice the following:

        • A Dell PE2550 with a PIII 1.13 GHz CPU has a CINT baseline of 561.
        • A Dell PE2650 with a Xeon 3.06 GHz CPU has a CINT baseline of 1014
        • A Sun 280R with an US III 1.2 Ghz CPU has a CINT baseline of 637

        Theoretically the PE2650 should outperform the PE2550 and 280R by about 3 times, all other factors being equal (i.e. same benchmark). The SPEC benchmark does its absolute best to eliminate I/O systems and network interfaces as a factor, so if we are just talking CPU, cache and memory, the Xeon should have had a CINT baseline of about 1600 or so.

        Things get even worse when you start looking at the SMP capabilities and scalability. In a truly linearly scalable SMP system you should be able to go from 1 CPU to 2 CPU's and have the benchmark double. Even the best SMP systems (Sun UltraSPARC and IBM Power) can't quite achieve that. But Itanium really has trouble. Search on Dell and look at the CINT and CFP rates benchmarks. Look at 1, 2 and 4 CPU scores for the Dell 7150.

        Bottom line? If you are doing heavy lifting on a server, go SMP with 64bit RISC, or, in some cases, use a cluster of 2 CPU x86 servers. If you are a PC user, you are unlikely to see a significant performance increase with new Intel CPU's unless you upgrade the whole system, not just the CPU.

        This whole thing of adding clock cycles and deepening the pipeline is not working out well.

    • What are your apache bench figures before and after?

      e.g. ab -n 300 -c 10 "http://127.0.0.1/mydynamichtmlurl/"

      static html (direct to index)
      ab -n 1000 -c 50 "http://127.0.0.1/index.html"
      static html non direct to index page.
      ab -n 1000 -c 50 "http://127.0.0.1/"
    • The CPU can compute, but it is still dependent on the rest of the system. I believe that chipset is more important to system responsiveness than CPU, although I really don't have objective proof for this, and sometimes benchmarks can't show the extents of these differences as they aren't measuring system latency but rather system speed. That said, the relative latency within a P4 is higher but when clock speed is factored in it should still be a lot faster on throughput, and in my tests it is.

      I can't com

    • It will with multimedia and games (Score:4, Insightful)

      by StandardCell ( 589682 ) on Sunday September 28, 2003 @01:24PM (#7078304)
      If you look at media benchmarks, encoding requires a lot of processing power. So, while ripping your DVD may not take any more time on your P3-1GHz versus your P4-2.4GHz, converting it to DivX MPEG-4 for your media jukebox will take significantly longer on the P3 than the P4. In fact, decoding H.264 video and WMP9 High Definition supposedly requires 3GHz (or the equivalent in AMD doublespeak) processors. Add to that the fact that you may want to do more than one thing at once (i.e. encode video in the background and play back another), and you will quickly run into a hard wall. Check out this link [tomshardware.com] for a very nice roundup of how older processors fare against newer processors. A simple DV-to-MPEG2 conversion takes approximately twice as long on a P3-1GHz than it does on a P4-2.4GHz. That's a lot of time when you have a couple of hours of video to encode. Audio and image manipulation applications, video editing and the like will also benefit in similar ways.

      Games, it goes without saying, scale in a similar way [tomshardware.com] and a similar doubling of performance.

      The caveat: for many business applications, you will hardly notice a difference. A faster I/O subsystem and more RAM, as you mention, will pay much larger dividends for these users than any processor upgrade will. In fact, this post is being written up on my trusty P2-400MHz all-SCSI box and it's still going strong, though it's getting a bit long in the tooth.

  • Electro-Magnetic Headache. (Score:3, Interesting)

    by s/nemisis ( 7175 ) on Sunday September 28, 2003 @12:10PM (#7077730) Journal
    Running at 5-7GHz is absolutely retarded for a processor to do. If you look at the way that every single "wire" in the professor acts, they all must be treated like transmission lines. just sitting there and doing thost calculations to find out how much power is being delivered would be the most bit*h/bullsh*t job every. A processor running that fast would probably lend its self to using onboard optical systems (waveguides) and running parts that way so as not to have to deal with running copper or Al and doing all of the insane calculations associated with that.

    Oh and by the way, i'm running a PIII750 and the only things i would upgrade to are Apple and a 64bit processor. I'm not going to upgrade for a long time.

    • Re:Electro-Magnetic Headache. (Score:4, Interesting)

      by lcde ( 575627 ) on Sunday September 28, 2003 @01:07PM (#7078172) Homepage
      I agree. The numbers are impressive but is this going to be like the CDRW wars where you can get 52x but cd's explode at 50something. It is kind of getting rediculous.

      The traces do act like a waveguide with no sides. Just a top and bottom to propagate the wave. The problem is fringing effects. That is why its such an accomplishment when they move the spacing closer and closer.

      I've noticed that the only time i see significant improvement of a processor is when the cache is larger or bus speed is faster.

      Maybe Intel should look into creating a 4Ghz processor with 4Ghz bus and a ton of cache. Because you could do calculations at 7Ghz but if you can only move data at 4Ghz... your only running at 4.

      Correct me if im wrong.
      • The traces do act like a waveguide with no sides. Just a top and bottom to propagate the wave. The problem is fringing effects. That is why its such an accomplishment when they move the spacing closer and closer.

        Give yourself a pat on the back...you're obviously a real geek and clearly understand the issues raised by the parent poster a hell of a lot better than the other clueless idiots (geek wanabes...they should be ashamed!) that have responded so far. You've also answered a question that I've often w

  • Let me know... (Score:2, Insightful)

    by Black Parrot ( 19622 )

    ...when I can walk in my local shop and pick one up for $100.

  • Yeah but... (Score:3, Funny)

    by RinzeWind ( 413873 ) <chema AT rinzewind DOT org> on Sunday September 28, 2003 @12:11PM (#7077743) Homepage
    The Pentium V is likely to fly along at between 5GHz to 7GHz, have 2MB plus of level two cache, be built on a 90 nanometer process, and have a stackable design.

    Will it make coffee?

  • "Pentium Five" -- isn't that redundant? (Score:3, Interesting)

    by aquarian ( 134728 ) on Sunday September 28, 2003 @12:13PM (#7077758)
    A "Pentium" ("penta"=5)came after a 486, which came after a 386, which came after a 286, which came after a plain old "86"... So this one is the "Five-five"... Such wit, those marketeers...
  • IF the artical is correct it almost seems to imply that the default CPU will be 32 bit then with some method of upgrading it to 64 bit with an addon. Surely it would just make sence to make the 64 bit run 32 bit code well ala the Opeteron

    Rus
  • Does this CPU will be compatible with today's x86 ? If yes, WHY NOT ditch the x86 design one for all ? It's getting old and patched to make it work. They should focus on a better designed chip for tomorrow's applications than optimize it for speed.

    My 0.02$
    • First there is Itanium with a new instruction set. Second compatibility. Who would buy the new CPU if there isn't any applications for it? Who would write apps if there are no CPU's to take advantage of the power?

    • You mean... (Score:3, Insightful)

      by Namarrgon ( 105036 )
      ...like the Itanium? <snicker>

      Face it - the only way we'll see the end of x86 is if someone builds a new, non-x86 chip that can still run all that existing x86 code at least as well as the best existing x86 processors. Otherwise it's just another niche architecture, and no-one's going to "upgrade" to it.

      Intel forgot that, or thought they could force it on people anyway. AMD remembered, but took the easy way out & just extended things. Similarly, IBM got it wrong with OS/2, and MS jumped straig

    • They did. It's called the Itanium. Look how well that's worked out.

      Even running it outside of a server, you have to have a special version of Windows, which doesn't have all of the features that the 32-bit Windows does (Windows for the Opteron line is supposed to fix this). It's hideously expensive, meaning fewer people adopted it, which meant that costs stayed high, so there was less encouragement for people to adopt it, even within the server/workstation market in which it was sold.

      AMD is going about

  • No point in a 5GHz processor (Score:5, Insightful)

    by Anonymous Coward on Sunday September 28, 2003 @12:14PM (#7077768)
    There's no point in raising the speed of the processor to 5GHz if the memory speed (esp. latency) can't keep pace.

    4GHz front-side bus? Yeah, right.
    • You can always get an idea of the front side bus speed when you know the cache size. If its got goo-gobs of cache, then the FSB speed is probably relatively slow.
    • Yes, but it's...

      "what the kids want."

      or...

      "If we don't make this, the customers might buy from AMD."

      or...

      "If we keep promising more speed than our copmpetitor, then they'll decide to wait until the next upgrade cycle before considering the other guy's product."

      Hell, I still cant figure out why I would need 2.4GHz on my desktop, but I guess I'm just not a "savy consumer".

  • Does it even make sense? (Score:3, Interesting)

    by vadim_t ( 324782 ) on Sunday September 28, 2003 @12:15PM (#7077778) Homepage
    I calculated a while ago that assuming that RAM was 5 cm away from the CPU, at 5 GHz a clock cycle would be lost on waiting for the signal to travel the 5 cm to the RAM and back.

    If the speed of light is not far from being a limit at this point, then clock speed improvements can't continue working for long.

    Besides, there's the question of whether it will "fly" or not. Clock speed doesn't measure performance. It especially says nothing of the performance of a new chip.
  • ... is that all the CPU's instructions will take between 100 & 500 clock cycles to execute...

  • I've had one for years. (Score:3, Funny)

    by Stonent1 ( 594886 ) <stonentNO@SPAMstonent.pointclark.net> on Sunday September 28, 2003 @12:22PM (#7077830) Journal
    I had a P5 back in 1996! And it could whip through Windows 95 like nobody's business.
  • I remember reading a while back, that if CPUs continue increasing GHz, at the same current rate, then at some point in time they would be generating as much heat as a small nuclear reactor.

    Asynchronous processors are meant to be able to provide extra processing power, without having to tie everything down to a clock cycle. The added benefit being that the information is only delivered when everything is ready.

    Does anyone know where we are with these chips, and how long before they find themselves in main
    • My understanding is that asynchronous processors require a lot of extra circuitry so that when the result is ready, the unit receiving the data recognizes it as complete. Imagine an asynchronous adder. It has to have inputs for two numbers and an out put for one. In an asynchronous design, it also has to have an output that indicates incomplete or complete, since you don't have a clock to tell you when the work is done. I've heard that adding that circuitry is non-trivial.

      On the other hand, I've also h
    • If it's the article I think, it's the same watts per square meter as a nuclear reactor - not the same thing at all. The point being that nuclear reactors run hot so as to produce steam, whereas the chip has to be cooled as close to ambient as possible, so it is relatively hard to do.

      But power transistors have been able to produce more W/M^2 than reactors for a long time. Sounds scary, but not really that bad.

  • The Story So Far... (Score:4, Funny)

    by PipianJ ( 574459 ) on Sunday September 28, 2003 @12:25PM (#7077855)
    Intel: "Oh my god this is so AWESOME because we have super high gigahertzian-ness and you dooooooooon't!"

    AMD: "Uh... We don't need GHz to keep up. That's what We have these new nifty + ratings eh?"

    Intel: "Uh... HYPER-THREADING! WE'RE AWESOME!"

    AMD: "And we have a better 64-bit processor than your dinky Itanium. It doesn't need to 'emulate'. What a bunch of idiots."

    Intel: "OMG OMG! WE HAVE ULTRA 1337 SPEED! I MEAN 5-7 GHZ AND 4 GHZ FSB! I MEAN AREN'T WE COOL! 64-BIT EXTENSIONS!"

    AMD: "... Shut up. Better yet, don't shut up. It's good for our business, because at least we're delivering."
  • I'll believe when I see it, as slow as MS has been to produce WinXP for x86-64, I doubt they'll produce a version for Intel's in less than a year. That and 5-7GHz!!! Defuinately remains to be seen.
  • Hahaha, does anyone thing this sounds like a leak from Intel in an attempt to dampen the tide of people eyeing the Atlon 64 FX? "Hey! Don't buy our competition's superior product. We'll have something that might be as good or better ready in.. er.. half a year! And we'll try to have it on the market in quantity... er... maybe in a year if everything goes perfect! What, things have never gone perfect? Sssssh.

    A bird in hand is worth two in bush. Intel, you will now pay for your complacency. You did not beli

  • Well this makes it obvious... (Score:3, Interesting)

    by dpilot ( 134227 ) on Sunday September 28, 2003 @01:11PM (#7078217) Homepage Journal
    that we should ignore all of those silly Opteron and Athlon 64 announcements in the past six months, because next year Intel will announce something that will blow them all away, and lead us all back to the One True Processor Roadmap.

    Does this qualify as a pre-announcement, that just happens to be overlapping a competitor's introduction? I seem to remember that several decades ago, another three-letter company got in a decade-long heap of trouble for just that type of behavior. (Amoung others, but then there are more stories of things Intel has done to keep AMD 'present, but weak.')

  • Big deal (Score:3, Insightful)

    by Robber Baron ( 112304 ) on Sunday September 28, 2003 @01:20PM (#7078272) Homepage
    ...likely to fly along at between 5GHz to 7GHz...

    . ...and Windows 2005 (Code named Canyonero) will still manage to slow it to a crawl!

    • Re:Big deal (Score:5, Funny)

      by drinkypoo ( 153816 ) <drink@hyperlogos.org> on Sunday September 28, 2003 @03:00PM (#7079019) Homepage Journal

      Can you name the OS with four wheel drive, smells like a steak and seats thirty-five..

      Canyonero! Canyonero!

      Well, it goes real slow with the Pentium down, It's the operating system endorsed by a clown!

      Canyonero! (Yah!) Canyonero!
      [Bill Gates:] Hey Hey

      The Linux Users' commission has ruled the Canyonero unsafe for WAN or LAN use.

      Canyonero!

      12 gigs long, 2 gigs wide,
      65 tons of Windows Pride!

      Canyonero! Canyonero!

      Top of the line in crash reports,
      Unexplained reboots are a matter of course!

      Canyonero! Canyonero! (Yah!)

      I ran out of creativity here.

  • stop the FUD (Score:3, Interesting)

    by Bruha ( 412869 ) on Sunday September 28, 2003 @01:34PM (#7078383) Homepage Journal
    Just a scheme by Intel to keep those who are riding the fence on their side.

  • and yet. (Score:2, Insightful)

    by 2057 ( 600541 )
    5-7ghz and yet i still find no scenario to replace my pIII .5ghz. other than games but i dont game that much anyhoo
  • Get ready to hear about a lot more burnt penises [theregister.com]. Cause the faster the processors go, the hotter they're going to get.

  • It would have to be that fast (Score:3)

    by ruiner13 ( 527499 ) on Sunday September 28, 2003 @02:03PM (#7078571) Homepage
    Intel has built up the megahertz myth so much that most people who don't understand the work/clock cycle dynamics would need to see this type of 4-7GHz speed to even think about why they should upgrade to a next-generation Intel processor, even if it was only marginally faster computationally when compared to the P4. How much would you like to bet this "next-gen" processor has a 75-stage pipeline and a one-trillion transistor branch prediction unit to try to keep it working, not to mention the most-likely needed nuclear power plant water cooling tower that would have to be attached, or the 240V power outlet that would be needed. Yeesh.

  • Yeah Right (Score:4, Funny)

    by vandan ( 151516 ) on Sunday September 28, 2003 @05:37PM (#7080041) Homepage
    Well MY inside source tells me that Intel are ready to release the Pentium X, running at 50 Ghz and having a FSB of 25,000 Mhz.

    It has their patented uber-cool ultra-wizzer-extra-special 128-bit extensions, and it also has an expansion port that you can slap an extra processor on in case AMD releases a 256-bit processor in the meantime.

    This thing is going to scream, baby! It will plug into existing Slot-1 motherboards, and will be built on a 2 nanometer process.

    Microsoft are believed to already have a version of Windows running on the beast, with their new 'WTF That's Friggin Incredible Mate' extensions that go hand in hand with Intels 'Fuck Me If This Isn't A Faster Chip Than AMD Has' architecture.

    Wait a moment .......... yes, yes ........ THEY'RE ON SALE NOW!

  • Vapourware (Score:3, Insightful)

    by theolein ( 316044 ) on Sunday September 28, 2003 @10:21PM (#7081580) Journal
    Reading these amazing specs, with the attendant oohs and aahs and lots of ifs thrown in --"it seems, it could be" -- this gives me the feeling that it might just be vapourware, brought out at this time in the time honoured tradition of microsoft announcing products that do not even exist beyond specification form simply for the reason of cornering the market. AMD's Opteron and IBM's PPC 970 (G5 in Apple's Macs) are getting more press than the desasterous Itanium or even the Itanium2 for that matter.

    My feeling is that while Intel is probably less worried about the G5/PPC 970 as their marketshare is very small, but is more worried about the effect a successful Opteron could have on the market, on the one hand not needing special recoding for 64 bit apps (compatible to x86 32bit) and more importantly what the Opterons could do to the server market, causing companies to switch their 32 bit Xeon stuff to 64 bit Opteron with little effort and low price.

    I seriously doubt that all of a sudden next year, CPUs will be on the market running at 5 to 7 GHz without having serious cooling problems or running away from memory.

    So, in summary, I think it's Intel's marketing department in microsoft mode:Vapourware.

Slashdot Top Deals

The Tao is like a glob pattern: used but never used up. It is like the extern void: filled with infinite possibilities.

Close