Forgot your password?
typodupeerror
Intel

Intel to Release Pentium 1.13Ghz 123

Posted by CmdrTaco
from the arbitrary-numbers-with-extra-significance dept.
NoWhere Man writes "According to TechWeb, Intel officials have said that they plan to ship a 1.13-GHz Pentium III in limited production quantities on July 31 >(which also happens to be the anniversary of AMDZone). Interestingly enough, at the same time, the schedule for the Itanium, the companys first 64bit processor, seems to have slipped from the 3rd quarter of next year to the 4th quarter."
This discussion has been archived. No new comments can be posted.

Intel to Release Pentium 1.13Ghz

Comments Filter:
  • Anyone know what FSB they are running at? WHat kind of overclocking potential?
  • If the quantities are as limited at the rest of the Cu series, then you can expect Dell and Compaq to get the only case, and they'll probably have to share. Bring on the Athlon love, baby!
    --
  • by Chairboy (88841) on Wednesday July 19, 2000 @12:19PM (#919802) Homepage
    It seems clear that Intel is adopting the 'limited quantity' strategy as a tactic of exerting influence over the OEMs that recently complained about the Xeon incremental releases.

    Created a limited supply is a good way to create artificial demand and a means of initiating punitive action against the companies that were 'uppity' so recently.

    I suspect that if the whole Xeon controversy hadn't happened, this would just be another quiet incremental upgrade like before, but now.... it's an opportunity to put the OEMs in their place.
  • Nice, but my P3 450 is still even fast enough to easily run any games I throw at it... Does anyone need 1.13GHz? What are you going to do to use all that power?
  • It's not like it'll drive i/o pins at >1GHz.

    Intel's development path:

    1. increase clock frequency
    2. ratchet up CPU chip internal clock divider
    3. alert marketing division
  • by jmv (93421) on Wednesday July 19, 2000 @12:22PM (#919805) Homepage
    Is this going to be the same quantity as the P3 1 GHz. So far, it still isn't possible to get those. This seems more like "marketware" than anything useful.
  • What's the big deal? I'd rather have two 600mhz chips than OneBigOle 1.13Ghz chip. Nothing has scaled to this processing speed, save research stuff, so why waste the cash?

    Everyone I know who has a 1Ghz machine says they noticed no significant performance increase. Sure Apache compiled 4 seconds faster, but you're still using vi to edit the conf. The my dick is bigger than your dick argument is tiresome.
  • by LNO (180595) on Wednesday July 19, 2000 @12:24PM (#919807)
    ...but I won't be satisfied until they release the 1021Mhz processor, solely so I can shout:

    One point twenty one gigawatts! er, hertz!

  • by codehead (14804)
    I guess you'll be able to toast bread on that wafer. Can't wait to get my hands on one...
  • SETI@home. Duh.
  • 1.13 gigaHz?!!!!! 1.13 gigaHZ!!!!! Marty! nobody can generate that kind of speed! Why, they'd have to use......A Bolt of Lightning!
  • I think it's a different kind of strategy. The strategy is that they simply cannot produce even 1 GHz P3's, but they don't want to look like they're behind AMD in terms of clock speed.
  • I have this nasty feeling that the very term "GHz" is going to be used to goug the CPU market for some time to come.
  • That elusive Itanium slips back again...

    The 64 bit processor is the thorn in Intel's side... It is Intel's ball and chain... It is Intel's Microsoft... the list of metaphors goes on...

    Maybe Intel's persistent failures with Itanium will allow a new chip maker to take Intel's crown, like IBM, AMD, or MOT (maybe even DEC*, prolly not Transmeta tho :) anyway, the fresh air new leaders in this sector would bring would be Nice.

    *I know its Compaq now, I just didn't want to break with the three letter trend going there.

  • I don't believe that I could get my hands on a 1.0Ghz PIII, even if I wanted to.

    so, Intel is doing yet another paper launch.
    I guess that it is all about marketing, not about availability.

    Wouldn't it be cool if AMD beats them to the punch by a week, just like last time?
    ---
    Interested in the Colorado Lottery?
  • Frankly I'm not suprised Intel is doing this. After all, what sense would it make for them actually use any manufacturing capabilities that they might have to make the 1GHz CPU's available in some respectable quantities. I believe that Intel is running scared. AMD has them shaking, because the Athlon outperforms the PIII hands down. Intel continues to promise new technology, but when they actually produce something tangable (RAMBUS) it falls flat on its face. They are scrambling to introduce technology they don't have the bugs worked out of yet. And all because of the little company they've tried to bury under all the mud, FUD, and rigged benchmarks for all these years, AMD. Granted this is the first time AMD has out performed Intel, but it has made the giant nervous. And nervous giants tend to be clumsy. See any resemblence there?
  • Hopefully if the bar keeps getting raised on the high end, I'll actually be able to afford that 1Ghz Athlon I'm planning on sticking into my next computer early next year.

    Long live progress & competition!

  • You beat me to it, but I will say it anyway:

    NEWS FLASH! CPU Maker Announces Incremental Speed Increase; Chip Expected To Be Slightly Faster Than Previous Model

  • Intel removed the ability to overclock their newer faster, top-of-the line processors a while ago. There was even a few posts in on of the last over-clocking posts here.
  • by goten (36521) on Wednesday July 19, 2000 @12:39PM (#919819) Homepage
    I hope they actually sell both of the chips they manage to fab, and not keep one in house for testing.
  • When is the computer industry going to abandon this idea of a faster and faster single CPU in favor of slower but massively parallel CPUs. IMO, the latter would be able to accomplish far more. Yes, they're expensive, but that's only because there's little focus on them. Of course, programmers will have to get used to thinking differently for parallel programming. As it is, the few 2/4/8 way systems seemed to be being deliberatly kept expensive and off of the desks of us mere non-corporate peons. Linux already has SMP support, yes? Or are we all waiting for MS to "invent" SMP for (user grade) windows before we see the HW to support SMP get cheep?
  • At least there are ways to obtain those things when they are announced...unlike Apple's 500 Mhz G4 announcement a year ago which took almost 6 months to fulfill...
  • by Yhcrana (88366)
    Wow you are almost as bad as a microsoft zealot. Kinda makes me wonder if you also believe that the FBI isn't in the spying business or that Microsoft products are the best out there.

    :sigh:

  • by StevenMaurer (115071) on Wednesday July 19, 2000 @12:45PM (#919823) Homepage

    This is just marketing hype from Intel. Their 1GHz Pentium III is being outshipped by the 1GHz Athlon by a factor of 12 to 1. You can't even find a 1GHz Pentium listing on the Pricewatch CPU page [pricewatch.com], let alone compare prices.

    Given how much Intel has been suffering from their decision to go with Rambus (see this [tomshardware.com] article from Tom's Hardware), you can see why they feel the need to brag about something.

  • They won't beat them by a week, unless they release a 1.13ghz athalon in the next week...
  • ...but I won't be satisfied until they release the 1021Mhz processor, solely so I can shout: One point twenty one gigawatts! er, hertz!

    Trying to say this nicely [without flaming] but shouldn't that be 1210Mhz? Otherwise you'd be saying 1.021giga[hertz].. :)

    Back on topic, I think this sort of proves that Intel/AMD really rushed in the race to 1Ghz. They both released an obnoxious number of processors increasing in speed until they hit the mark, and since then we haven't heard much of anything from them. I hope they both have calmed down enough to make sure everything is properly tested [ie, delaying Itanium...WTG Intel!]. I don't know that there have been any bugs found yet in the 800Mhz-1Ghz chips, but I'm sure some will be found eventually.

    In the words of Miracle Max: "Never rush a miracle man...or you'll get a rotton miracle."
    -The Princess Bride...best movie ever :)

    Ender

  • Are they going to be collectables?
  • At least there are ways to obtain those things when they are announced...unlike Apple's 500 Mhz G4 announcement a year ago which took almost 6 months to fulfill...

    It would be fairer to scold Motorola for this - they botched the PowerPC production runs. Apple should have been more careful in not announcing systems until they were receiving a good supply from Mot, but at the end of the day Apple don't fab. PowerPC's themselves, Motorola and IBM do.

  • Ummm, I think you mean 1210Mhz.

  • CPUs are kind of like sports cars. You can't let the other geek down the street out clock you. Who needs a car that can go 180? Well, I guess I do, when my stock options come through anyway.
    Kate

  • ..have a /. story about every speed bump that Intel or AMD makes? Next thing you know, /. stories will all start running together because of redundanc... shit... too late.
  • I was looking at CompUSA's add, pentium 3s on one side athlons on the other. 733 MHz top p3s 1000 MHz top athlons Sure p3s are close to atlons at the same clock speed, but where are the 1 GHz p3s? (aside from their 'favorite' companies?) I see 1 GHz athlons. btw, when are the .18 micron copper alphas coming out? (supposedly 2.5 GHz+ ?)
  • This is not to mention that it seems all of the 1Ghz PIII's are going to mags to test against an K7 1Ghz, so it makes Intel look good.

    I personally have not seen seen any ads for a 1Ghz Computer that wasn't an AMD, even from Dell! Now, Intel wants to jump the gun and 'release' a procesor which it has no capability of producing. It is straight out lying to the public AND its investors.

    Give us a break.

  • by gorsh (75930) on Wednesday July 19, 2000 @12:54PM (#919833)
    Actually the article says that Intel won't start selling the chip until the fourth quarter of *this* year, with general availability for consumers coming sometime in 2001.
  • That's the idea :)
    ---
    Interested in the Colorado Lottery?
  • Actually Itanium has slipped from shipping the third quarter THIS year to the fourth quarter, THIS year. McKinley is the one supposedly set to ship in the second half of next year.
    Nuthin' like checkin' the facts every now and again.
  • All right people, this is the time to band together! It's not long until we'll go from this to our ultimate goal - 1.21 Gigawatts!
    Only then can we inadvertantly prevent our parents from getting together!
  • It would make the most sense if this cpu was @ 133 FSB (8.5x multiplier == 1.1305 Ghz).

    As mentioned in another reply, most recent intel CPU's are at least multiplier locked. You can usually still overclock by adjusting the FSB, but at 8.5x this gets very dangerous quickly.

    Example: for a 1.13 Ghz (133x8.5) processor, if you overclocked the bus up from 133 to 140 (a modest 5% move), the processor steps up to 1.19 Ghz. Since these cores are in limited quantity and nothing faster is made, it is probably a decent bet that either the processor or the integrated L2 would fail before you got to 1.2 Ghz.

  • They didn't remove the ability to overclock, they removed the ability to alter the clock-multiplier. Many people still overclock by modifying the FSB speed (and of course the core is the multiplier x the FSB).
  • A bit off topic of the original article, but right on for this comment, Apple today (hold on, keep reading! :) ) moved 2/3 of its desktop machines to dual processor boxes for this exact reason. They're having a terrible time getting IBM/Mot to product >500Mhz G4's, so they went with 2xG4s to up performance. No, 9.0.4 is not SMP, but OSX is, and so are the betas. So, if you want consumer level MP/SMP a a resonable price, just "Think Different" and they're here today.
    Hawks
    "Developers are the redheaded bastard step children of the computer world",
  • by Signail11 (123143) on Wednesday July 19, 2000 @01:09PM (#919840)
    Intel's moving back of the projected in-volume ship dates for the Itanium is far more important than the release, in limited OEM quantities no less, of an incremental increase in speed grade for the current generation x86 chips. Itanium, as the first line of IA-64 systems, represents the unveiling of a multi-billion dollar gamble by Intel (and its strategic, quasi-partner HP) in making inroads into the high end, 64-bit processor market. IA-64 is an elephantine archetecture; it includes everything including the kitchen sink, the waste disposal, the plumbing, and the hot water heater. It's such an unwieldy ISA for an idea that was supposed to simplify the processor by effectively exposing processor functional units to programmer visible namespace. And yet, Itanium has 10 pipeline stages (3 more than the Alpha 21264, I must add), is barely pushing 500 Mhz, and will probably be slower on a clock for clock basis than the current Alphas and PA-RISCs. I don't buy the ISA, the implementation of the ISA embodied in the Itanium, the projected performance of the Itanium (although I do have greater hopes for HP's Ft. Collins team in the McKinley...it would be hard to see how they could screw up as badly), and the market placement of the initial IA-64 processor line. All in all, I'm not exactly surprised at this delay.

    Maybe this means that Intel will have some sense and wait for HP's processor team to finish design so that they can fab the McKinley and avoid embarassment.
  • I just swapped my 450 for a 667 and the difference is VERY noticable across the board (not only due to the 48% clock increase but also the slightly improved core of the P-III over my old P-II). Q3 and derivatives (i.e. ST:Elite Forces) run smoother more consistently now and I'm running with a GeForce DDR card as well so the CPU should be even less of a factor.

    Falcon 4 finally runs somewhat acceptably. That was a game WAY ahead of its time.
  • by DigitalDreg (206095) on Wednesday July 19, 2000 @01:15PM (#919842)
    Too many people forget that all CPUs wait at the same speed. A 1Ghz anything is a waste considering the state of I/O and memory technology.

    This CPU is going to spend a lot of time waiting for memory, even with a generous cache. How many programmers design their data structures to be cache friendly?

    With all of the processing of multi-media data types (music, video, and pictures), there isn't a cache big enough to contain the data. Also, the temporal and spatial locality of these data types stink - you process a few pixels, and move on. You don't get to revisit a certain pixel very often. Yet it is wasting space in the cache.

    Intel and other manufactures would do much better to add some architectural improvements designed to help multi-media, which is much of what people do with these chips now. How about a section of "streaming cache" for data that will pass through, but only once? That way you don't have to fill the entire cache with useless bulk data.

    Or how about I/O model improvements - split the bulk data from the signal and control data so that the bulk data doesn't have to go through the memory hierarchy and the processor at all? If I'm playing a video file, why should the cache and processor be deluged with data being routed to the sound card and the video card? Put the signal and control data out of band from the bulk data so that the processor doesn't have to sift through the bulk data.
  • It's probably been delayed to give Microsoft time to finish porting Windows to it...

    hang on, I've just thought about that comment. It isn't really that funny.

  • Who needs a car that can go 180?

    Who needs a car that can go 180mph when you have a motorcycle that can go 190mph?

    ;-)

  • I can't recall too many performance increases smaller than this, percentage-wise. There were smaller increments between 60/66, 90/100, and 120/133, but I'm pretty sure that the faster models came out at the same time as the slower ones.

    A 11% increase doesn't sound that exciting to me. Then again, a 113MHz increase doesn't sound so bad.
  • by n0ano (148272) <n0ano@arrl.net> on Wednesday July 19, 2000 @01:37PM (#919846) Homepage
    How about a section of "streaming cache" for data that will pass through, but only once?

    Please RTFM, in this case the instruction set reference for the PIII. Part of the new Streaming Simd Extensions is a set of instructions that:

    1) Prefetch from memory to anywhere in the cache hierarchy.
    2) Write to memory, bypassing the cache hierarchy.

    Using these instructions I was able to write block bopy routines that achieved transfer rates of up to 600 MBytes/Sec. on a 500Mhz PIII. The same transfer using the GLIBC bcopy routine could get no more that 235 MBytes/Sec.

    --
    Don Dugger
    VA Linux Systems

  • Does absolutely everything have to do with Microsoft? Microsoft does not want to be solely dependent on Intel chips anymore than Intel wants to be tied to Microsoft operating systems.

    There are *many* problems with the IA-64 ISA and the specific Itanium implementation of it. I know someone working for HP (the organization that I work for purchases high performance supercomputers on pretty much a regular basis), who reliably states that the SpecFP performance of the Itanium is will be not at all competitive even with today's high end chips *even if it were at the same clock speed*, which it will not. They're barely pushing 700 Mhz even on small scale lots with a hell of a lot more QC than on any production fab.
  • by hattig (47930) on Wednesday July 19, 2000 @01:42PM (#919848) Journal
    Yes, they come with a certificate hand signed by the designers, and it is presented in a beautiful 22 carat gold edged package, with the item number on the back. This beautiful objet'd'art will set you back a mere months wages, and will look most beautiful when offset with an ATI Radeon or Geforce 2 DDR. Be sure to present it on an Intel approved Display Rack, Order Number: i820-NoDIMM, and to protect it even further from thieves and the like, please cover with a beige box.

    Unlike other 'pretenders', this is the real thing, and to prove it, you can purchase other pieces of art in the Intel Art Range, including the wondrous 256Mb RIMM, and the beautiful Itanium - purchases guaranteed to make your new PentiumIII glow in a different, rosy glow!

  • yeah, but staying in a car traveling at 180mph is much easier than staying on a motorcycle traveling at 180mph or 190 mph
  • by Signail11 (123143) on Wednesday July 19, 2000 @01:46PM (#919850)
    The Itanium has been tapped out; they're working primarily on QC/V and most importantly of all, ramping up clock speed and refining the fab masks. It's an astonishing complex design to verify, but regardless of my opinion of Intel's ISA design teams, their chip designers are among the best in the industry and their verification is equally good (even considering the F00F bug and the floating point SRT errata). Intel will not release a chip as important as the first member of the IA-64 ISA without ensuring that it is functions according to specifications for the especially critical reason that application programers will be using the Itanium to design the first generation of IA-64 compiled applications, applications whose reliability foremost and speed next will be critical to the acceptance of the IA-64 ISA as a force in the HPC market. They simply MUST get it right if they hope to follow their roadmap (Intel and HP have at least half a dozen IA-64 design teams working on the next generation chips) with any credibility. Itanium is basically do or die for Intel; McKinley will come at least half a year and by then the damage to IA-64's reputation may be too much to repair. You can always improve performance, but not if there are no applications for the ISA because no programmer or user wants to deal with processor bugs.
  • I was listening to most of the AMD conference call today, and they said that they would be releasing a 1.1 GHz chip this quarter (I'm guessing Tbird) with the Mustang (Server chip), Corvette, and Camaro (both notebook) coming in fourth quarter. Also, there will be faster speeds in the fourth quarter. I also think they mentioned something about the Sledgehammer (K8 - 64 bit) coming next year, but I'm not sure when. They also said that they will be moving toward DDR SDRAM, but that they had a Rambus license in case customers wanted a rambus support. There's probably some more things I missed (apart from all the financials).
  • by dark_panda (177006) on Wednesday July 19, 2000 @02:05PM (#919852)
    ... the REPENTium?

    J
  • it's nothing more than a FUD/vapor/pissing contest.

    if it ain't broke, then fix it 'till it is!
  • This CPU is going to spend a lot of time waiting for memory, even with a generous cache. How many programmers design their data structures to be cache friendly?

    Extra clocks never hurt anybody. It seems to me you're saying the ratio of cache load time to clock will be wasteful if you increase the clock too much. The new pIII's have full speed cache anyways and the load time is still getting lower. If you want more cache, get a xeon. These chips will still have uses.

    B1ood

  • Moto didn't botch the PowerPC production run.

    Bill Walker.

    if it ain't broke, then fix it 'till it is!
  • I was thinking more along the lines of using a small portion of the cache repeatedly, so as to not pollute vast portions of the cache.

    Does [1] fit the bill? Does "anywhere" mean to any level of the cache hierarchy, or does it give you a true way to limit cache pollution? Lots of architectures can do prefetches. I guess you'd have to work with a very small portion of the address range to keep from filling the whole cache.

    [2] Lots of architectures can turn caching off on a page by page basis. This is usable.

    I congratulate you on your tuning, but my point remains the same - this thing is hard to feed.

    Also, the value of pre-fetches diminishes as the latency to memory becomes greater. Quick example - if a cache miss results in a reference to main memory taking 100 to 150 cycles to complete. Do you know 100 cycles in advance what data you are going to touch? We are not far away from being in this predicament.

    These things need work.
  • by barleyguy (64202) on Wednesday July 19, 2000 @02:16PM (#919857)
    In order to piss vapor, it would have to be heavier than air. And compressed somehow...

    But anyhow, I agree with you. I'm not sure why they're doing a paper launch of the 1.13 Ghz when you can't even buy the 1 Ghz in the open market yet.

    In the weekly pricewatch comparison, the Athlon 1 Ghz has over 25 listings, and the PIII 1 Ghz has zero, zilch, aught, naught, cipher. None.

    The Thunderbird 1.1 Ghz will be out about August 15th, and will be shipping in quantity about that day. The Pentium III 1.13 Ghz will be "out" July 31st, but I doubt you'll see it in the open market (i.e. outside a Dell machine) before October.
  • If you won't be reaccessing the data, WTF do you want it polluting even a small part of the the cache hierarchy. The main memory bottleneck will always be present for 1) initial accesses and 2) accesses out of cache. The only solutions are 1) making the cache larger, 2) better algorithms and blocking, or 3) interleaved main memory.
  • I can also think of dual Celerons, dual Pentium 3s, and MP Xeons available today, with the first two at much lower prices than the Apple desktops (with comparable, if not greater performance). So what?
  • They are talking about putting a PLL (Phase Locked Loop) circuit in during marking, so the processor will only work at the proper FSB setting. Hasn't happened yet, but I expect it happen soon.
  • I'm assuming you copied all of that from a textbook... because I can't imagine some TrOlL having such knowledge. Amazing that I understood it all too...
  • by barleyguy (64202) on Wednesday July 19, 2000 @02:32PM (#919862)
    Actually, Compaq has been in the Athlon camp for their 1 Ghz machines lately. Dell is strictly Intel (and probably always will be, because of Intel advertising co-ops). Compaq, Gateway, and IBM are primarily AMD.
  • Intel has to one-up AMD to feed its ego and deliver what the market wants (by Intel's definition, "deliver" equals "announce"). If the market really demanded it, they would find a way to actually produce the chips they announce en masse (AMD can already do this). Why isn't there an antitrust suit against Intel yet?
  • Can you imagine if Intel had continued with their scheme of releaseing procs with half a bin more speed? How funny would a Pentium 1.066 GHz be?
  • I've been thinking the same thing. There is supposed to be a big AMD price break on September 20th. The 1000 should drop below $500, possibly the low $400 range. I think by January it should be in the $200 range. That's what you call cheap power.

    Don' cha love progress? (For pricing reasons at least.)
  • Well, they've already demo'ed 1.2 Ghz Athlons at room temperature, so you never know.
  • Can we stop the nimrod who say 1GHz is wasted because of limits in memory and I/O technology? The speed is only wasted IF you're doing certian types of tasks. In every other case, it is not.
    Places where proc speed is wasted:
    - Serving.
    - Databases.
    - Programming/Compiling.
    Places where it definately is NOT wasted.
    - Gaming.
    - 3D rendering.
    - Running high load apps like 3D Studio, Maya, and MS Outlook.
    - Running Win2K.
    - Scientific probs. where the data-sets are fairly small.
    - Image processing.

    In these types of tasks, I/O bandwidth is a non-issue, because if you're 3D renderer is swaping, you're wasted anyway. Machines for these tasks tend to have a load of RAM, thus disk I/O really isn't a factor. For stuff like games (and the little preview window in you're 3D app) the data sets are small, and the computations are large. Even a complex game like Quake3 rarely pushes over 200MB/sec of bandwidth to RAM. That's one reason why RDRAM is often useless, because apps rarely push even the 800MB/sec of SDRAM.
  • Great joke, except not. If I made the same comment of Netscape on Linux, I'm afraid I would have gotten quite a few remarks telling me where to put my CPU.
  • Why in God's name is Intel still releasing stuff in 33 MHz increments? Like some moron somewhere is really gonna pay a premium for a 1133 MHz chip as opposed to 1100 MHz.

    What'll happen is this: They'll release an 1100, an 1133, an 1150, an 1166, and a 1200 (eventually), which will just confuse the hell out of people and get more people to buy AMD stuff. At least AMD got smart and pledged to release in 100 MHz increments after 1 GHz.

    - A.P.
    --


    "One World, one Web, one Program" - Microsoft promotional ad

  • It is definately true in server market but I was under impression that desktop machines are generally better of with faster single processor. (where we stand now, most of desktop type software isn't even threaded ...)
  • If I'm playing a video file, why should the cache and processor be deluged with data being routed to the sound card and the video card?

    Subject says it all. Sure most video cards will do MPEG-2 in hardware nowadays; maybe you'd save something by getting the CPU out of the way there (although it's not actually in the way very much when you're just doing a memcpy of compressed data). But then here comes MPEG-4, and suddenly you need to do all that decoding work in software again. Which sucks if you're concerned about your SETI@Home performance, but it sure beats buying a new video card.
  • Jobs knew Mot still had problems with their 500Mhz chip and unable to mass produce it. It was Jobs' fault to jump to the gun with the announcement! It's Mot's fault for not producing a chip faster for a year since then, but certainly not their fault during the announcement last year.
  • Try using an AMD system. Maybe you hadn't noticed but compared to Intel's bus and memory structures AMD is actually advancing technology in these areas for x86.
  • That's actually 1210Mhz ... ;-)
  • Places where it definately is NOT wasted.
    - Gaming.


    Not quite. Games are more than happy with current CPUs. Anything over 800MHz or so is really useless. At resolutions 1024x768 and above, the FPS of a game is limited by the video card. Just check out the benchmarks. At high resolutions any reasonably fast CPU is able to saturate the video card with data. I especially like the benchmark where Celeron 667 is compared to 1GHz Pentium (see either Tomshardware, or Anandtech). The 1GHz beast easily smokes Celeron by like 40-50% at 640x480. But the FPS numbers quickly start to converge as the resolution is increased. At 1024x768 1GHz Pentium is only slightly ahead of the Celeron, and at higher resolutions, there is essentially no difference at all. (BTW, the video card was GeForce 2 GTS, the fastest at the time).

    As for running Win2k and Outlook... well, can't argue with that ;-)

    Even a complex game like Quake3 rarely pushes over 200MB/sec of bandwidth to RAM. That's one reason why RDRAM is often useless, because apps rarely push even the 800MB/sec of SDRAM.

    Agreed. While the higher bandwidth of RDRAM helps a little, the higher latency slows things down a lot. That's one of the reasons I hope Rambus will die a horrible death. The sooner the better.
    ___

  • Itanic.

    Has a nice ring to it.

    - A.P.
    --


    "One World, one Web, one Program" - Microsoft promotional ad

  • All the newest P3 chips use a 133 Mhz FSB so it can never be 'even' and come out at 1.1 Ghz.
  • What's the big deal? I'd rather have two 600mhz chips than OneBigOle 1.13Ghz chip. Nothing has scaled to this processing speed, save research stuff, so why waste the cash?

    So you have an SMP board. Why not get two 1.13 GHz chips (*drool* 2.26 GHz total) instead of two 600 MHz chips or one 1.13 GHz chip? As some earlier posts have stated, and as should already be obvious, there is no such thing as overkill when you are dealing with processor speed.


    =================================
  • Meaningless? I think you're going a little overboard. While it would be nice in the memory infrastructure and I/O subsystems could keep up, increasing the clock speed on today's systems does give a noticable performance increase and it is hardly meaningless.
  • Hi. I'm the nimrod. My name is Mike.

    My question was on how to feed this thing, both with memory and I/O. You can add RAM to eliminate disk I/O, but even the RAM is slow compared to the processor core.

    What does a Xeon have - 4MB of L2 cache running at processor core speed? What's that equivalent to - a 4 minute MP3 at a low bit rate? What about the player and the OS? It's getting kind of tight in the cache.

    On a big machine maybe I can have 8MB or 16MB of L2 cache. Ok, now that is enough to fit a good size scanned picture. That pales in comparison to the index of a good sized DB. If a server can have a main memory of 40GB or more, then what's a 16MB cache? A drop ...

    MS Outlook shouldn't need 1 Ghz processor. Win2K shouldn't either. Enough said.

    Scientific problems where the data sets are small. I can't think of any. Most problems worth solving have huge datasets.

    Image processing - a reasonable static image can overwhelm a modern cache easily. Video is even more rediculous. At least with scientific programming and image processing you can try to predict the data you'll need next and prefetch.

    This is like dropping a great engine in a crappy car. It will idle really nicely, but the suspension and the steering won't let you go fast around corners. I don't care what the redline of the engine is - I want to know how fast the vehicle goes. Processors are far ahead of memory and I/O technology - you'd have a much more useful system if this was balanced better.

    We're not even going to touch on how crappy the state of software is compared to the hardware ...
  • Maybe its Trollaxors english paper and he wants to get feedback on it.. its rather creative if thats true


    If you think education is expensive, try ignornace
  • what AMD really needs is SMP. godammit AMD when the hell are you going to release dual/quad CPU systems ? im tired of buying crummy P-iiis running at 650MHz for dual/quad processing.
  • You should take this to Illiad, I hear he's looking for bold new computer humor like this for User Friendly.
  • Just speculating...

    Intel, being a big, mature company, probably operates under a five year business plan and a more detailed two year business plan. It is in their best interest (as is true for all CPU makers) to feed the market with upgrades slowly, both to exploit the incremental upgrade frenzy and to keep from topping out where they don't have something new within easy reach that they can announce for next month to maintain the interest of the media and investors. The posited business plans would have been based on such a slow ramping system.

    Thus I speculate that their business plan called for shipping (say) 600 MHz last summer, 700 MHz over the fall/winter, 800 MHz in the late spring, etc., with 1G falling late this year or even early in '01.

    If they had honestly expected to see a 1G Athlon in quantity and problem free this spring, I'm sure they would have been working under a more agressive plan; per my first paragraph, such a plan would almost certainly have been feasible if it had been desirable.

    At any rate, they are now hustling to retool their plan (and factories) to an unwelcome reality.

    Notice also that the 1G Gold Rush has pretty much queered Moore's Law over the short run - I think we doubled peak speed in approximately one year. (Anyone remember when 500M first came out?) OTOH, I suspect that both Intel and AMD have "sprinted" to reach 1G ahead of schedule, so we will probably see sub-Moore advances from them for the next year or so.

    Presumably Intel's original business plan called for following the "every 18 months" variant of Moore's Law that has become familiar of late.

    --
  • Good point. I work with DSPs - who cares about the clock speed? It's all about throughput, babe - MIPS and BOPS. I like to see this 1.21 gigahert thingy's specs WRT these measurements.
  • Intel, being a big, mature company, probably operates under a five year business plan and a more detailed two year business plan. It is in their best interest (as is true for all CPU makers) to feed the market with upgrades slowly, both to exploit the incremental upgrade frenzy and to keep from topping out where they don't have something new within easy reach that they can announce for next month to maintain the interest of the media and investors.

    That is not true for all CPU makers. It is true for the speed and market leader. But if you are trailing the leader it is in your best intrest to skip ahead. If you are the speed leader it might make sense to move ahead faster if you are still not the market leader.

    It is obviously not a good idea to slowly ramp up if you are slower then the other guy, and have less market share.

    It also may not be true in a market with diffrent priorities. Would a 300Mhz StrongARM sell more units then a 200Mhz one? Probbably. But if they skip from 200Mhz to 600Mhz they might manage to make sales into markets that would have bought the TI integrated DSP and ARM7 (because the 600Mhz SA can jpeg compress as fast as the TI DSP and gobble digicam market share -- or at least that is my thery). Note for this example I'm assuming the faster SA doesn't suck much more power and lots of other stuff, but you get the point.

  • That would be 1210 hertz...
  • Hi. Read this: http://www.kuro5h in.org/?op=displaystory&sid=2000/7/18/122257/231 [kuro5hin.org]. Please don't b-slap me; this is important!

    --
  • Finally, Intel is breaking away from 33 mhz increments for its chips. It was ok when the 133 was followed by 166, with about a 20% mhz difference. But later we were seeing 833, 866, 900, etc., with differences of less than 4%. Factor in Amdahl's law, and that was a fairly useless distinction.
  • Most(if not all) PC system designes are based on the 40+ year old von Neumann architecture. This is high level enough to serve us as a guide. Sorta like "If you want to build a house you need a foundation walls and a roof". So as a basis it serves us well.

    The current Intel/AMD architectures are more specific than the von Neumann. They embody the actual physical motherboard design.

    The Intel/AMD architectures are based primarily on what we knew in the 70's and have been added to over the years. This can be shown as my (c) 198x Word Star will still run on my Win NT 4.x (*office*) PC and that this new 64 bit Intel chip wil support 16 bit apps.

    I agree that the principles of processing etc will always remain the same, but what if....

    We throw out that old Intel/AMD design and start afreash. New bus architecture, chip architecture, design for the future and with the user in mind. We saw what BeOS did when they started from scratch

    Anyway I put it to the /. masses that there is good reason to redesign with our original and newer (I don't remember user frendliness mentioned in von Neumann's paper) goals in mind, using technology that is available now.

    Your thoughts please(as if I have to ask for them)........
  • In the days that more and more are migrating to an OS that will run happily on a 486

    that's right...all those happy new linux users running KDE, GNOME, Netscape, GIMP, XMMS, BladeEnc, StarOffice...all on a 486!!! and they say it beats a 1GHz Athlon running Win2000!!! wow...those Linux programmers are smart guys. either that, or most linux zealots are full of shit about this whole "linux runs great on a 486" lie.

  • fart is denser than air, and compressed :-)
  • Yeah, right. That explains why Microsoft have dumped NT for Alpha, MIPS, PPC and whatever, and are back to square one.

    Looking at it from another perspective, you might come to the conclusion that Microsoft actively stays in the Intel camp.

    Intel does seem to try to spread outside of Microsoft, though...

  • Finally, Intel is breaking away from 33 mhz increments for its chips. It was ok when the 133 was followed by 166, with about a 20% mhz difference. But later we were seeing 833, 866, 900, etc., with differences of less than 4%. Factor in Amdahl's law, and that was a fairly useless distinction.

    Still useless, unfortunately, like saying that a Corvette with 400 horsepower is a big improvement over 350. The extra 50 HP is for bragging rights and faster times on the test track, for the handful of people who really care.

    Everyone is losing in these CPU speed pissing contests except Intel and AMD.
  • Hi. I'm the nimrod. My name is Mike.
    >>>>
    NimrodS, I meant to write nimrods.

    My question was on how to feed this thing, both with memory and I/O. You can add RAM to eliminate disk I/O, but even the RAM is slow compared to the processor core.
    >>>>
    You don't NEED to feed this thing. Some computations are simply NOT memory bound. Take Quake 3 for example. Few people will doubt that it is a VERY demanding application. However, it uses less than 25% of the available bandwidth of PC100 SDRAM.

    What does a Xeon have - 4MB of L2 cache running at processor core speed? What's that equivalent to - a 4 minute MP3 at a low bit rate? What about the player and the OS? It's getting kind of tight in the cache.
    >>>>>
    The Xeon is a server machine. Those use big caches because serving is a cache intensive task.
    You don't use a Xeon to play an MP3. But take MP3 decode for example. You read a chunk of data into the cache, then run the decode intructions. Those decode instructions take a lot longer than loading the data. MPEG compression is an even better example. Most MPEG algorithms use a 40 X 24 pixel block while doing motion estimation. That 40X24 pixel block easily fits into cache, and the instructions to process that block take a LOT longer than just reading that block.

    On a big machine maybe I can have 8MB or 16MB of L2 cache. Ok, now that is enough to fit a good size scanned picture. That pales in comparison to the index of a good sized DB. If a server can have a main memory of 40GB or more, then what's a 16MB cache? A drop ...
    >>>>>>>
    This isn't a database. I just said that databases don't need faster procs, but faster memory.

    MS Outlook shouldn't need 1 Ghz processor. Win2K shouldn't either. Enough said.
    >>>
    Agreed.

    Scientific problems where the data sets are small. I can't think of any. Most problems worth solving have huge datasets.
    >>>>
    I can imagine, though I can't think of one, admitadly, a scientific prob. with a small dataset. maybe tracking particle interactions or something.

    Image processing - a reasonable static image can overwhelm a modern cache easily. Video is even more rediculous. At least with scientific programming and image processing you can try to predict the data you'll need next and prefetch.
    >>>
    You don't have to load the whole image. Take many of the filters in Photoshop (like lighten or blur.) They load a chunk of the image (which fits into cache) into a matrix, then do a LOT of operations on that chunk. Memory bandwidth is not really important here.

    This is like dropping a great engine in a crappy car. It will idle really nicely, but the suspension and the steering won't let you go fast around corners. I don't care what the redline of the engine is - I want to know how fast the vehicle goes. Processors are far ahead of memory and I/O technology - you'd have a much more useful system if this was balanced better.
    >>>>>>>>>>>
    But what if you're drag racing?

    The point you don't seem to understand, is that a lot of apps simply don't NEED memory bandwidth. right now, my 3D renderer is starved for RAM, but the RAM is easily fast enough to support it. Or something like Quake or video compression/decompression, where many instructions are done on a small amount of data. When transforming a polygon, two matrixs are multiplied. Though it is just a loading of 20 numbers, it results in 16 multiplies (which take a lot longer than a load) and 12 adds. Or perspective division, which results in a (very slow) division instruction from loading only one vertex. Or in image or video (or even sound) processing, where many operations are applied to small chunks of data.
  • The reason why Quake doesn't look like Toy Story? You're CPU can't push nearly enough triangles. The GeForce can still razterize more triangles than you can throw at it. Resolution is a different issue entierly, since the load on the CPU doesn't change. The test you mention is invalid in this arguement because the fact that a GeForce isn't being maxed out at lower resolutions (ie. it gets faster from Celeron to PIII) means that the proc isn't giving the GeForce enough triangles to render. If you increased the proc speed to say 2 GHz, then the test would be faster still at lower resolutions. I know it's confusing. In the end, its a chain issue. The total speed is as weak as the weakest link. At 1024x768, above which the gains become smaller at this polygon size, the Geforce can still handle more polygons that the PIII 1GHz can feed it. Right now, the proc is the weakest link.) A more valid benchmark would be this. Use a high polycount scene and compare differnt procs. NVIDIA as already shown this. Scenes that bog down even on a 1GHz Pentium III, run fine on a GeForce2 because of the geometry acceleration. The key to making games look better is more triangles, and current CPUs can't nearly push the cards hard enough in that respect.
  • The 1GHz PIII was announced as a knee-jerk reaction to the Athlon announced only day(s?) before, and to no one's surpirse, there was a huge supply problem. To many people's surprise, AMD didn't have a huge problem with supply and has been the only contender in the x86 world selling actual GHz machines.

    Will we ever see this new PIII? I don't know. Chances are, it was just a smoke screen to keep their market value up while whispering about the slipping release date of their next processor.

    As we've seen from experience, Intel loves to throw out a few extra mHz (or a 100+ of them) and the market will buy them as they see their PC is now obsolete. Frankly? I have a 350 mHz K6/2 in my desktop and have no problem running most tasks.

    --

System checkpoint complete.

Working...