Follow Slashdot blog updates by subscribing to our blog RSS feed

 



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

Pentium III 1.13: Tops For Speed, 'F' For Price? 106

fjordboy writes: "CPUscorecard has some multiple reviews and benchmarks of recent CPUs. Somewhat surprisingly, the Pentium III 1.13 GHz processor tops the list, but only for speed. CPU Scorecard also gave the Pentium III an "F" when it came to pricing. Is the high price tag worth it for the top-notch speed? Click here to see how the Pentium III stacked up to the other CPU's."
This discussion has been archived. No new comments can be posted.

Pentium III 1.13 Tops For Speed, "F" For Price?

Comments Filter:
  • The program they make the speed tests with is Intel's iCOMP.

    Actually, as far as I can make out, they only used the iCOMP tests for Intel's processors. All other processors were converted from the manufactures benchmark to iCOMP compatible numbers using a "magic formula". The quote from their site is:

    The CPU Scorecard benchmarks are based upon Intel's iCOMP, a combined rating of integer, floating-point, internet (Java) and multimedia performance.

    Published CPU benchmark scores, including those listed below, are converted to the iCOMP scale using a unique and comprehensive, comparative statistical algorithm.

    Sounds like a recipe for biased, unreliable, PHB numbers to me. I'll make a note to avoid this site in the future.

  • So basically it points out that A) 1.13 Ghz is slightly faster than 1.1 Ghz. B) Because it's a new chip it costs much more than it's worth. In every case, a new processor has a high price tag that usally cuts the exisiting fastest processor in half. That's just the way it works. For that reason, I'll never buy the newest and fastest processor... the price isn't worth the slight performance edge. Go 2 or 3 steps down and you're looking at a fast processor at a decent price. This isn't news, it doesn't really matter, it just re-affirms my reason for not buying the latest and greatest chip.

    "You'll die up there son, just like I did!" - Abe Simpson
  • CPU Scorecard doesn't include Alpha or "other high-end SMP-capable processors" [cpuscorecard.com], so I wouldn't pay too much attention to whatever they happen to rank at the top of their little list.

  • in their chart they dont even have a price listed for the 1,13 gig intel. so how can they tell its the worst bang for the buck if they dont even know how much it costs??
  • the processor comparisons are interesting, so my wife's computer is only 2/3 as powerful as mine... cool

    seems much more than that but thats probably the windoze effect

  • Yep. BTW you forgot to mention the Java applet that crashed my Netscape browser...
  • Some subsystems of a core OS (or applications) aren't multithreaded and won't take advantage of a second (or third, or forth, etc) processor. In Windows 2000 for example (I know, BOOOOO!) the NTFS compression and EFS (Encrypting File System) subsystems are single threaded. If you are reading or writing a lot of compressed or encrypted data, you are MUCH better off having one fast processor versus two slower ones. I guess the lesson is to pick which setup is best for the job.

    ALG
  • They do. Because when the (theoretical) 1.26 GHz P3 arrives, that'll push down the cost of the 1.13 GHz model. Just as it's been for years. Of course, the absolute fastest processor is going to cost an arm and a leg. They always have. Their main purpose for us isn't to make us want to buy one, it's to push down the prices of all the previous chips.
  • I'd certify as crazy anyone who put out that kind of bucks today for something that'll cost half the price in six months. I took a quick look at CPU prices and you can get a PIII FCPGA 133mhz FSB cpu for under $220, who in the world needs more horsepower than that on their desktop. If I remember June 1999 we were buying a few PIII 500mhz cpu's for around $500 for some of the programming staff, now I don't think Intel even makes that speed anymore. All these cpu interations and the cost are just insane.
  • I think the simple reason that didn't get marked as "Flamebait" is that its a reasoned point of veiw, and is directed at the point of the article.

    This is the biggest problem I see with the moderating system here at the ol' Casa slashdot. people have been moderating stuff they don't agree with as flamebait.

    Folks, flamebait isn't something you disagree with. Things you disagree with are what drives a good discussion. Flamebait is something along the lines of "Apple/Linux/microsoft/ect. Sucks!" In this case, the poster had an opinion, expressed it, and was moderated accordingly.

    And just so I can actually have an opinon here thats actually germane to the main discussion, out of the last few systems I built, I have been happy to go with the less than cutting edge CPU. Until DDR chipsets get out, IMHO anything faster than a 900 is just chrome. nobody except freak gamers (And I count myself as one of those) and people doing multimedia production will need that kind of power. Just how fast do you need that kernel to compile anyway?

  • AMD is expected to cut their prices again later this month when they release the 1.2 GHz part. How does 250$ for a 1 GHz T-Bird sound against a non-available overpriced withdrawn 1.14 P3 sound? Intel has already had to take a price cut on their P4 line before they have released it. Jerry is finally putting the screws and fud to Andy instead of the other way around.
  • Male chauvanist.
  • Wow! Intel's top of the line processor is overpriced compared to other processors! The price/performance ratio has ALWAYS been better with the lower end processors-- go way way way back and look at the 486SX vs. DX machines from the early 90's-- same exact thing. DX's were a bit faster, and cost twice as much. As soon as pentium came around, the DX prices dropped like a rock. Yawn.
  • Warms my heart as a macuser since 1988... =)
  • And this has to be said.
    All you memory bus freaks get off of it.

    These procs aren't made for servers. If you put these procs in a server you are wasting your time (put slower procs and more memory and/or SMP) Otherwise, for games, 3D rendering, video editing, and 70% of the things that these procs are used for, CPU speed is still king. Example: QuakeIII uses about 200MB/sec of bus bandwidth. That's less than half the sustained (not theoretical) bandwidth of PC100 SDRAM. All the tests between PC100 and PC133 (or even PC66) show very little performance difference compared to bumping up the CPU speed a 100MHz or so. (Check www.sharkyextreme.com the Celeron vs. Duron tests)
  • 95% of all computing done on 100% of all computers purchased requires no more processing power than the Pentium 200. (and that is only because of bloatware- to actually get the work done, you can use a 486) there is a top 5% that actually use the computer, and of them only 25% of that 5% actually would use the processing power in a 1ghz processor. (and as posted above they would prefer multi-processor to the screamer)

    So Why? why are they busting their butts to get these processors to market? Does George Lucas need more processing power for the Star Wars episodes's rendering?? Maybe NASA is trying to do some astrominical trajectory calculations? weather modeling? a 250000 user SQL server? (only a moron would make one server do that.. use a farm)

    I'm betting that every one of you out there would have to really stretch to come up with a use that would require anything faster than a PIII 400 in your company/personal use. (AVID users dont count!)

    someone tell me - what the hell does 95% of the computer buyers need it for?
  • > On the fifth and final hand, though, the real advantage of the Alpha and US-III is their platforms, which give them much greater i/o throughput--often more important than CPU power for server applications anyways

    You also play down the FP performance, where the Alpha as is still kills the projected values for the (non-available) 1.5GHz P4. Intel's vaporware isn't even in the same league.

    --
  • It would only seem to be of value in those rare situations where the marginal gain in processing is so profitable or desirable that it outweighs the marginal costs -- but places like that probably already buy bigger machines than Intel boxes.
    I think it comes about when someone wants to scale something beyond its original capacity. Some program that is difficult to port to another operating system or architecture, is not multithreaded, and for the most part doesn't bottleneck in the OS (which probably is multithreaded).

    Fixing any of these problems is almost certain to cost much more than a really fast processor. OTOH, a really fast processor only gives you a tiny edge performance-wise over a pretty fast processor.
    --

  • The G4/500 stacked up pretty well. Not bad for a 10 month old CPU!
  • by Junks Jerzey ( 54586 ) on Monday October 09, 2000 @08:21AM (#721282)
    A 500 MHz G4 is twelve percent slower than a 1.1 GHz Pentium III? If that's true, then that's the real story here. Isn't this what everyone was trying to vehemently deny a while back, that a G4 is equal to a Pentium of double the clock speed?
  • They have already recalled this chip. Tom's hardware Guide [tomshardware.com] has had numerous articles on just how crapped up this chip actually is. He even has another hardware site to back him up; HardOCP. Maybe the Pentium III 1.13 Ghz can go that fast. Its possible...but the damned thing fails to work 20% of the time, do you want to spend the money to take that chance? Assuming you can actually get a hold of one? You'd have better luck getting someone to give you a porshe or something
  • I think you missing the point while Marketing is good and necessary for the Company trying to sell its products. To the purchaser its at best just an extra cost and at worst trickery or an attempt to rip them off. Do those da da a da notes Intel has paid millions upon millions of for in TV adverts, make the internet or quake run any faster. Have they make Intel and Intel share holder any money yes. Marketing is like a gun, fine and dandy if you the one thats holding it, but nasty if its pointed at you.
  • It was out, only to be withdrawn, have Intel released it again?

    I _really_ wouldn't bother with it anyway, it's
    nothing but an overclocked PIII 1GHz.
    Sure overclocking is actually how the *zillas often reach their speedratings, but the 1.13GHz P3, seems to be pushing it a bit too far.

    If it isn't out, I find it highly suspect, that anyone would include it in a review.

  • Learn how to use an apostrophe, you idiot.

    There's nothing wrong with my sentence. I'l rewrite it for you, slightly changed:

    Just because this is a very unfair comparison which neglects a very important good that Intel offers for its price:
    it is brand.
    "It" is an anaphoric pronoun which refers back to "a very important good ..." "It is" contracts to "it's". The colon separates a statement from it's elaboration.

    Who looks like an idiot, now?

  • then why bother spending such a high marketing expense which decreases the marginal revenue of the product?

    Because you need to inform the customer about your company. If you slip out of his consciousness, you're screwed.

    marketting hypes != quality of the product remember RDRAM?

    Yes. They didn't market it well. Whoever was responsible for that fiasco at the marketing dept. should be fired.

  • When you get a true blue, Intel Inside processor, you are assured of a) having received the best technology,

    That's debateable. For the longest time people bought IBM computers because of the brand, and the thought that they were the best around. Then people realized that they could get the same thing for much less by going with an 'off-brand' like Dell or Gateway.

    Of course, now Dell and Gateway are two of the major brands, and they put together the overpriced systems.

    b) that the company that sold your processor will be around for many years,

    An assumption, and given the tech field of the last couple of years, not necessarily a good one. Given the speed of the 'game' out there, it's possible for Intel to make a couple of bad decisions and be belly-up by this time next year. Now, do I think that this is likely? No. But it is possible.

    Of course, it's also possible for an AC to make a calm, rational post. Haven't seen one of those either...

    c) that your processor will be the standard (if the AMD offerings behave differently due to a design error, AMD is the one in the wrong, not the other way around!), that you can get the latest technology that everybody will cloning the earliest, and many such advantages.

    I've been using an AMD chip for over a year. The only times I've had any issues with my machine have been because Windows didn't like something.

    (Ok, I never really did understand why MM:VII wouldn't run from my C drive, but did run from my D drive...)

    Now, I realize that this isn't necessarily indicitive of AMD performance in general, but they do put out a comparative product at a more competitive price.

    The higher price also pays for the incredibly talented marketing crew that informs you of all these factors that g**k websites such as the one linked in this story neglect, so you have a chance of not getting screwed over in your choice by unreliable or incomplete data such as the cited in the linked article.

    I'd rather pay for tech people that marketing wankers any day... After all, anyone can do marketing.... All you need is a smoke machine, some mirrors, a pair of hip waders, and a shovel.

    Slashdot g**ks, however, seem to be massively oblivious to these factors, due to their ideological commitments, aversion to the science of marketing and irrational sympathy for the underdog.

    Hmmm... I can't tell if this is sarcasm, or you just being bitter about something.

    *shrug*

    NecroPuppy
    ---
    Godot called. He said he'd be late.
  • its when u really can appreciate a browser with image/ad filtering
  • What would be interesting is how it [the Intel CPU] compares with the CPUs that run inside most modern servers.

    The problem is that you are starting to compare systems, not just CPUs. Of course this is what you ultimately want to do, but unfortunately this is a little harder. There are many more variables to consider.

    Some old numbers are in the classic Unix-vs-NT [unix-vs-nt.org] article at unix-vs-nt.org [unix-vs-nt.org] where you have ByteMarks on I*86 and Sparc platforms using Linux and Solaris (about half way down the article).

    I don't know of any more recent benchmarks -- I guess there should be some web server statistics out there somewhere.

  • This is rubbish. How did they get iComp to run on a G4? What compiler did they use, what OS was it running on? At what angle was the playing field set? Don't get me wrong - I'm not a Mac-basher. But even I, an avid Apple fan, can see that this is a flawed comparison. I'm not saying the G4 is over- or under- rated here, just that it's got no credibility with no methodology published. I can't believe this made it onto the /. front page... What self-respecting *CPU* comparison site would refer to an entire machine as a CPU?
  • His point is valid. I've been running SMP configurations at home since '95, and I can say that without a doubt SMP is the best price/performance solution in contrast to the fastest uni-proc on the market. If you're running an OS which supports SMP (as does NT and Linux), it really doesn't make sense to buy top of the line, unless you're performing computationally intensive calculations which are memory bound. For desktop use cheap SMP really is a good deal.

    So, just what made you think his comment was flamebait? I didn't see a disparaging remark against any persons in his post.
  • Seriously though, it wasn't as bad in the good old days when the price premium was maybe 10% or so. These days, with all the money you save, you're much better of getting another 256Meg or RAM or something. Also, the Athlon prices really aren't bad at all. Something like $650 for the 1.1 GHz Athlon (on pricewatch) Score!
  • But you can't just buy a G4 like you can a PIII. You have to buy the $3500 system around it. Apple won't give you a choice.
  • Tbird still has better performance. At least for techies who know.
    • Tbird's (and Duron's) 200DDR bus *does* help memory access.
    • Tbird's FPU *is* much more powerful.
    • What Linux application actually uses SSE? (Which is the only reason any P3 vs Tbird benchmark *ever* shows a decisive victory for the P3.)
    More generic x86 and FPU power, a larger cache memory, and faster bus, are all things which to geeks (at least this one) totally outweigh a 1 or 2% performance margin on SSE-enhanced MS Windows applications, not to mention the hideous price differential. And finally, is the P3 1.13 even selling again, after having been recalled??? If it's selling again, can you actually FIND one on the street, or will it be another 3 months like it was with the 1.0G?? I mean wtf is the deal with writing this article??????
  • I decided to check out the "All CPS's Section" and scrolled down till I found my trusty AMD K6-2 and was surpised to find it "priced" at $530. Considering I bought my for $40 (cool looking fan included) it seemed a little over priced to me. Hey anyone want to buy it for say, $200 bucks? CPU Scorecard might want to try some sort of dynamic updating scheme. Then agin I appreciate what time they give.
  • by ToLu the Happy Furby ( 63586 ) on Monday October 09, 2000 @04:48AM (#721297)
    That's right, this site gives the impression
    that P3 1.13 Ghz is the fastest CPU in the industry.
    In fact, both Alpha and U-Sparc-III are TWICE faster.


    Well, no. By far the most credible cross-platform CPU benchmark is SPEC; if you had bothered to check the SPEC CPU2000 scores [spec.org] you would find that a 1GHz P3 is precisely as fast as a 900MHz US-III on SPECint2000_base (438) and only 30% slower in SPECfp2000_base (327 vs. 427). Assuming linear scaling (not generally a great idea but close enough in this case), a 1.13GHz P3 will be 13% faster than the USIII-900 in SPECint, and 16% slower in SPECfp. In other words, they will be essentially equal.

    Now, the Alpha actually is quite a bit faster than the P3, with SPECint/fp scores of 514/591 for an 833MHz chip. That makes it 17%/80% faster than our 1GHz P3, and an estimated 4%/60% faster than a 1.13GHz P3.

    Now, on the other hand, both the Alpha and the US-III systems tested cost many times more than the i840 1GHz P3 system; not only do the chips cost a good deal more, but they get the benefit of much faster (and more expensive) buses to memory, etc. This makes quite a difference even in the SPEC CPU tests, and if the chips could somehow be placed on equivalent platforms, the P3 would easily win SPECint outright, and might be rather competitive even on SPECfp. (In case you were wondering, the reason the P3 sucks at SPECfp is because it is saddled with the register-starved x87 floating-point implementation for backwards compatability reasons; the P4 will go quite a ways towards solving this problem--at least as far as newly compiled code goes--with its SSE2 instructions.)

    On the third hand, as has been pointed out, the 1.13 GHz P3 does not exist, and never did. (Intel "launched" what amounted to several engineering samples which turned out not to work properly anyways. Other than a couple dozen sent off to review sites and OEMs for validation, no 1.13 GHz P3's ever left the company.)

    On the fourth hand, a chip which does currently exist in much higher quantities, the 1.5 GHz P4, looks like it will quite forcefully take the SPECint crown away from Alpha, and depending on Intel's progress in optimizing their compilers for SSE2, might even take the SPECfp crown as well. We'll get to find out when it is officially released in about a month or so.

    On the fifth and final hand, though, the real advantage of the Alpha and US-III is their platforms, which give them much greater i/o throughput--often more important than CPU power for server applications anyways--and allow them to scale to configurations of 32 and 64 CPUs and beyond; Intel has a long way to go to compete on these measures.
  • Actually, I just checked the apple store and $3500 is for a dual processor 500 MHz G4. Given that, it should probably get twice the price/performance rating than the one it was given.

    Ma'at
  • I've done marketing. I was rather good at it.

    By your own "admission", eh? Sorry, you've revealed otherwise elsewhere in this thread.

    You assume I have some reason to lie to you. I don't. You aren't worth the effort.

    I also hated it. That's why I went back to programming and am now making less that I was before. But at least I'm doing something I like.

    You like it because of the feeling of superiority it brings you. "Anybody can do marketing, but nearly nobody can do programming, so I'm better than that."

    No... I never said anything about why I liked it. You're assuming again. It was just that I wasn't happy in marketing. I didn't have anything in common with my coworkers, I didn't like my boss, and the office had this ugly peach wallpaper. (Though that last was hardly the breaking point.)

    Not anybody can do marketing, period.

    Then please explain why business is where all the washouts from 'technical' majors end up? Most of them in marketing??

    Your characterization of the noble science of marketing as "90% basic math and bullshit skills" just shows you unability to grasp it.

    Ok, maybe not the standard defination of basic math, but my defination. I've taken high level Statistics courses, Numerical Linear Algebra, four semesters of Calculus (including Vector Calc), and Differential Equations. Anything below Diff. Eq. is basic math to me.

    And as far as marketing being a noble science, let us take that apart, shall we?

    'Noble' - can't say I usually consider any profession to be noble, with the possible exception of medical professionals or social workers.

    'Science' - Hmmm... Wait, let me check... Nope, none of the Business Majors on the local campus give a BS for their degrees, just BAs. That would be Bachelor of Arts, in case you missed it.

    Your preference for a programming job, and your dismissal of marketing as "trivial" just proves you have the Slashdot Syndrome (also known as the "IANAL but I can program, so here's some advice" syndrome).

    No... My preferance for a programming job over a marketing job merely shows that I prefer programming over marketing. My prefered job, Deep Space Explorer, doesn't exist yet.

    And I never refered to marketing as 'trivial', which your quotations would seem to indicate. This all started because I say I would rather have a tech person than a marketing person. And as you seem to be a marketing person, I now have another reason why.

    NecroPuppy -- Just another example of Slashdot Arrogance.
  • I haven't gone to the site, but if you say its better than pricewatch.com, then it must be REALLY terrible!

    shopper.com 0wnz j00! :)
  • The last line of his post was a flamebait.

    Maybe we live on separate planets, but from where I come from simply referencing a company's product and stating that it's good doesn't make for flamebait. He seems to like NT; that's his choice and it should be respected.

    But if you have a single CPU intensive process that can not be multi-threaded, then you are probably better off with the faster CPU.

    Yes. I made a similar point when I wrote:

    [...]"it really doesn't make sense to buy top of the line, unless you're performing computationally intensive calculations which are memory bound."

    So, we're on the same planet with regard to this issue. However, I've yet to find many desktop users (except in the scientific community) who need raw CPU horsepower and high memory bandwidth. Most users need multi-tasking stability and smooth responce under the load of many applications. SMP is perfect in this environment.
  • At least GWB is not a FUCKING LIAR like that Al "The Pompous Jackass" Gore. God I hate that faggotty bastard and his stiff posture. I hope him and his jew friend who hates computer games, loose this election bad!
  • by wmoyes ( 215662 ) on Monday October 09, 2000 @06:14AM (#721303)
    There is nothing surprising about Intel's fastest chip being a loser when it comes to price. Intel isn't dumb, this chip is targeted towards the people that will pay any price for that fastest machine on the block (at least fastest in their minds). Other companies do this as well. In the past hard drive manufactures did the same thing. The largest harddrives had a terrible cost per megabyte ratio.

    When buying new hardware you need to look at two price points and choose in the middle. There is the point when the price takes off to catch those who will pay through the nose to get the 'best' (only to realize in two months that something better came out), and the other price point is where they catch those who try to be cheap (yea, it's the cheapest, but for $5 more you can get something twice as big/fast). Those who go the cheap way get disappointed and lose money on upgrades.

    When I buy a new machine I mentally graph out cost vs. performance. Usually you will see a slow rise in price and performance takes off. Then it will level out somewhere in the middle and then about 2 generations from the top the price will skyrocket while the performance just creeps along. I buy at the point just before where the price takes off. This way I get very good hardware that only a little behind the best, and it doesn't cost much more then the junk I would get if I was cheap. I can then use the money on peripherals (a good monitor is better than a 50 MHz jump any day).

    I have a second rule of computer buying: When you own a computer you need to put $XXX into it every year. The more you put into it the closer to cutting edge it will be. If you put $1000 into you machine every year you will have the best machine on the block. If you only put $50 or less into the machine you will be facing obsolesce. Custom PC's don't become obsolete, they only become obsolete through neglect. They are more like a car than a VCR.

    Yes, I know my two rules sound obvious to any geek, but there is wisdom in there. This is the same spiel I give to anybody who comes to me for advice in buying a computer.

  • because software gets more and more bloated adding features that may or may not be useful so ppl need more and more CPU grunt to get the same performance out
  • You also play down the FP performance, where the Alpha as is still kills the projected values for the (non-available) 1.5GHz P4. Intel's vaporware isn't even in the same league.

    False.

    Someone reported a slew of leaked benchmarks on a preproduction 1.4 GHz P4. While many of them were disappointing (more on this later), the SPEC scores reported were rather impressive. In particular, the SPECfp2000 score was 517 IIRC. That would put a 1.5 GHz P4 somewhere in the neighborhood of 550--not quite the 599 that Alpha can pull off, but certainly "in the same league", and certainly not "killed".

    But there's more. The actual SPECfp score of the P4 will be much higher, for two reasons:

    1) That preproduction 1.4 GHz P4 was almost certainly crippled in some way--i.e. one section of cache may be set to bypass, or several associativity ways turned off, or branch prediction could be turned off, or instruction paths could be routed very conservatively in microcode, or any number of dozens of things. This is almost always true of prerelease benchmarks of a new core; it happened before the Athlon release last year, and before the PPro release so long ago. Furthermore, there is good reason for prerelease chips to be crippled in this way--this is how engineers test finished cores to make sure they're ready for release. Essentially it's a lot like how coders test their code--turn something off and make sure everything works in the degenerate case; that way you not only know it will work in real operation, but if there is a bug you're much closer to isolating it. These settings are set in microcode and not changable by whichever two-bit employee at an OEM decides to leak benchmarks off a preproduction CPU sent there for validation (or whoever leaked the scores). Indeed, preventing accurate leaks is a reason to leave prerelease chips partially disabled like this.

    In particular, the resulting slew of benchmarks which came from this particular preproduction P4 showed several very odd results almost certain not to represent the true performance of the fully functioning chip. It's not that the chip did poorly across the board, but rather that a couple particular benchmarks which stress particular aspects of the chip happened to be stupendously bad, and other benchmarks were mainly impressive. Paul DeMone, an EE who writes some excellent technical articles at realworldtech.com and posts often in places like Ace's Hardware, says that in his opinion these particular scores come from a P4 which has had its L1 associativity-way-prediction turned off, thus effectively increasing the latency of the L1 from 2 to 5 or so cycles. (Of course, there's no proof that the P4 even does way-prediction; the idea that it does is simply Paul's conjecture to explain how Intel got an L1 to run with 2-cycle latency at 1.5 GHz (and greater) on a .18um process. You can read his article on this here [realworldtech.com].) I'm not knowledgeable enough to comment, but Paul knows what he's talking about.

    2) As I said in my original post (your accusation of "playing down fp performance" notwithstanding), the P4's SSE2 instruction set includes double-precision fp instructions for the first time. Thus we have an x86 chip which can finally run the double-precision operations necessary for SPECfp without relying on the horribly antiquated 8 register stack-based x87 fp implementation. While the 2-cycle latency L1 data cache will help the P4 run x87 code much faster, the reason all the major RISC chips have always creamed x86 chips in SPECfp is because they have sensible floating point implementations while the x86 chips are stuck with x87 for compatability reasons. But now that the P4 can use SSE2 instead of x87 instructions, it may have a real chance to compete or even win in SPECfp. We've already seen how the SPECfp performance of the leaked chip was remarkably better than that of a 1GHz P3 (517 vs. 327). What we don't know is if those numbers were made using a compiler which was fully optimized for SSE2. Indeed, it's likely that the SPECfp numbers which accompany the P4's release will later be improved upon by better SSE2 compilers.

    Furthermore, classification of the P4 as "vaporware" is utterly uncalled for. This is a chip that's remained remarkably on schedule, with the only official delay being one month for a chipset (not CPU) issue. Believe it or not, Willamette is a chip that wasn't supposed to even exist, because by now the P3 was supposed to be replaced by a 2nd-generation, consumer oriented IA-64 chip. (Now *that's* slipping on your schedule!) Plus, Intel has been intentionally downplaying the performance of the P4, which is the exact opposite of what one does with vaporware. While some (who are not knowledgeable enough to study the actual P4 design) have taken this to mean that the P4 will be a disappointing performer, it in fact suggests just the opposite. Intel is not afraid to exaggerate (lie about) the performance of its upcoming processors in order to scare off competition--witness Merced/Itanium. Likewise, Intel is known to downplay the performance of upcoming MPUs in order to surprise the market when the chip finally debuts--they did this, very effectively, with the PPro, which surprised everyone in taking the SPECint lead away from Alpha when it was introduced. Intel leaked that the PPro core was supposed to be a dog; instead it's been perhaps the most impressive core design in history.

    In any case, we may not have long to wait. While I'd bet we won't see any final SPEC numbers until the P4 release next month, Intel's presentation on the P4 at this week's MicroProcessor Forum is tomorrow. Will we see SPEC numbers? Who knows? But if we don't, it's likely only because Intel has a big surprise ready on Nov. 20.
  • You say that those that go on the cheap get bummed. only when they listen to un-knowing computer people. There are laws of computer buying yes... and they are as follows...

    Buy the best motherboard you can afford. The motherboard is your lifeline, if you get a great quality mobo, it will outperform the crap easily, and be upgraded in 4 months when the max speed processor it can take becomes the fodder.

    Buy the best video card you can afford. the bottle neck in computers are the video and hard drive. - with ultra66 as standard today (and you cant buy an non 66 hdd anymore) this is a non-issue. But buy a danmed fast video card, but not the best.

    Get a minimum of 128meg of sdram. windows is a resource hog, plain and simple... maybe someday someone will write an OS that isn't bloated into stupidity.

    finally, spend very little on the processor. The processor is the least important of the bunch, if your mobo can handle a 1Ghz get a 550mhz for dirt... BUT: get something with good FPU.

    I have at home a PII-233 that will kick the arse off of everyone I know's PIII-500-650Mhz machine. and I makes my brothers P-III 850 Coppermine look like a joke. My secret? Good video, good mobo(no integrated anything but the basics) a Real Creative labs Sounblaster (not a live! a awe64) etc..

    I can run Quake-III at 800x600 at great framerates, while the gateway cant even get close!

    cheap out on the processor - it's a piece of fodder anyways, and you can slap the next one in there for about $130.00

    The above way you can get a cheapo computer that will kick the butt off of anyone's supposed "power" machine. and upgrade at your liesure for peanuts.
  • Yep, it out beats a pentium 800Mhz and is equal to an Athon 1GHz, quite amazing. It shows what many people have been preaching for years, ia32 sucks, big time. But check out the typical desktop price: C$5,300 :-( . One has to wonder, is it the processor that's expensive, or the rest of the system?

    And where's the alphas and the sparcs?

  • oops, that of course should have been pentium III 800MHz :-)
  • by swb ( 14022 ) on Monday October 09, 2000 @02:54AM (#721309)
    I've never known it to make sense to pay top dollar for Intel's fastest CPU. From a value perspective it just doesn't make sense, especially with SMP boards so cheap. The CPUs one, two or even three steps down from top of the line running in pairs often deliver *better* performance than the top CPU and at a lower cost(YMMV, IANAL, etc etc). Even in single-CPU installations the price differences are so great and the performance advantages so minimal between Intel's #1 CPU and the lower-clocked family members that the marginal gain doesn't exceed the marginal cost.

    It would only seem to be of value in those rare situations where the marginal gain in processing is so profitable or desirable that it outweighs the marginal costs -- but places like that probably already buy bigger machines than Intel boxes.

    The thing is, its always been this way. I remember buying a P150 when P200 was out and the price difference was astronomical. To this day, when I use my P150 (running @ 166) I still don't feel the performance difference is substantial over a P200.

  • erm...I was just curious as how this got marked as redundant...he is the 3rd poster...and the first two don't have anything to do with that...Personally, I thought it was pretty interesting......but..then again..I just posted the story, I don't have any moderation paoints.


  • ... Duh!

    I'm also going to say something I swore I wouldn't: WTF is this doing on /. ????

    Cutting edge processors are always going to be far more money than their relative speed indicates - it's the premium you pay for getting the complete best-of-the-best. Given the CPU turnover these days, only those with more $$ than common sense would buy a top-speed chip (or, those with a hard performance-is-absolutely-priority-one requirement (though they should probably be looking at an Alpha or PowerPC chip instead of an x86 one)).

    Like I said before, this article doesn't add anything, so I'm reduced to complaining.

    Slow news Monday, eh folks? Hemos, go back to bed, and we'll wake you up if we need anything.

    -Erik

  • Yeah, cutting edge processors are always going to be far more expensive than their relative speed indicates, especially when they've been recalled (Pentium III: 1.13GHz).
  • making a better processor in terms of cost performance?

    Yep. That is, if they want to retain market share.

    Of course, this does make the 1-GHz and sub 1-GHz processors more affordable... In another couple of months, I may be able to afford one.

    NecroPuppy
    ---
    Godot called. He said he'd be late.
  • This is almost exactly what I tell people who are asking what to buy. Often, I'll even draw a simple graph for them showing some of the processor speeds and prices. In a reply, Lumpy pointed out the importance of a cutting edge motherboard, so other components can be upgraded. This is not a bad idea, considering that motherboards prices don't skyrocket at the high end quite like processors do.
  • The CPU, although the 'heart' of the computer, is nothing without the muscle.

    I for one, as a large corp IT purchaser, would rather have a dual-proc box:much cheaper, more power/price performance. When everything in the corporate market place must be carefully budgeted to provide bang for the buck, these CPU's just don't cut it.

    In a similar, take a look at these guys [microsoft.com], their SMP scaling is fantastic.
  • by Bob Ince ( 79199 ) <andNO@SPAMdoxdesk.com> on Monday October 09, 2000 @02:55AM (#721316) Homepage

    Since the Pentium !!! 1.13GHz has been withdrawn [slashdot.org], its price seems pretty irrelevant.

    The pricing of the Pentium 4 is much more interesting [theregister.co.uk]...
    --
    This comment was brought to you by And Clover.

  • CPUs at the top of the MHz range have been way too high in the $$s ever since 133MHz hit. This is not news. Go to pricewatch and pick one CPU type, and do a graph of $ vs MHz, and you will see, the fastest are always the worst bargin.

    Most people knew this trend when speeds were 1/10th of what they are now, but aparently /. considers it news now?

  • I strongly doubt that Intel put in code that favors Intel processors, since it would be hard to prove any such result is true. Even if the 1.13GHz does beat out the Athlon 1.1Ghz.

    And it wouldn't matter. Since the price is so far out of reason, any user with a bit of intelligence would do a bit more research than one site. 30Mhz (1.13Ghz - 1.1Ghz) isn't a huge difference.

    Right now, actual processing speed's value is decreasing. Only FSB speed, L1 and L2 cache size and speed are making huge differences.

    Note: Sadly, none of this matters to me, since I'm 16 and running an OLD PII 233Mhz with (GASP) ATI Rage Pro. Oh, and I have no money to upgrade. My best bet at better performance is PeoplePC. Sad, ain't it?

    The point of that rant was to NOT WORRY ABOUT 30Mhz, buy the best value (probably Athlon 1.1GHz, but don't take my word for it), and be glad you can!

  • I'd rather pay for tech people that marketing wankers any day... After all, anyone can do marketing.... All you need is a smoke machine, some mirrors, a pair of hip waders, and a shovel.

    Yet another case of Slashdot Arrogance, the belief that because one is good at computer, one is automatically smart enough to do anything else. You are obviously no good for marketing, or for law, for that matter.

  • I wonder: who, besided manufacturers, actually buys these "latest-and-greatest" processors when they first come out? For me, an announcement of a new Pentium or Athlon chip means one thing: time to see how much the price is dropping on last years (months?) models.

    The idea of paying $1000+ for a processor that is only marginally better than one $500 cheaper seems silly to me, despite cutting edge needs. Seriously: would you really gain that much more performance in buying a 1.13 ghz than an 866 or 933?
  • Yet another case of Slashdot Arrogance, the belief that because one is good at computer, one is automatically smart enough to do anything else. You are obviously no good for marketing, or for law, for that matter.

    Yet another case of Eladio arrogance. Or is that ignorance? With you it's so hard to tell. :)

    I've done marketing. I was rather good at it. I also hated it. That's why I went back to programming and am now making less that I was before. But at least I'm doing something I like. And I don't have an incipient ulcer anymore.

    90% of marketing is basic math skills and a good ability to bullshit. I have both. (As can be seen by my current karma rating.)

    And as for law, I never said I was good at law. I just happen to know some, know where to look up the rest, and have five or six people readily at hand to give actual professional opinions on it.

    NecroPuppy
    ---
    Godot called. He said he'd be late.
  • They should have a bar with price vs speed, that is where the 'grade' is made.
  • Every respectable hardware site has known and reported for a long time now that Intel's PIII 1.13 GHz chip was unreliable when it was out, impossible to get when it was out, and has since been withdrawn. Furthermore, this article doesn't make reference to the Athlon 1.1 GHz chip (out and and available in quantity). With the Athlon 1.2 coming within the month, this article is out of date. Lastly, all major hardware sites use a suite of benchmarks to compare chips in order to have a more fair comparison of x86 chip performance. Well, Intel's I-Comp is not an unbiased benchmark suite, and doesn't point out the Athlon's FPU strength. I-Comp also probably includes SSE instructions and not 3D-Now instructions. All of which makes this article irrelevent at any time, but absolutely irrelevant now.
  • Thinking about this at a slightly more elevated level... If your going to compare x86 compatible CPU's should you use a benchmarking program that actually uses x86 compatible code (how about a series of benchmarks test each level of x86?) and therefore runs on ANY 100% x86 processor... Put in some additional code which detects SSE / MMX/ 3D_Now / 3D_Now+ and run the appropriate code as required but make each block carry out a similar task... anyway just my 2c.
  • before a million other people waste bandwidth by asking the same question:

    The last line of his post was a flamebait.

    I responded seriously to the remainder of the post.

    Now can we get back on-topic?

    Your comments I can say that without a doubt SMP is the best price/performance solution in contrast to the fastest uni-proc on the market is BS. It really depends on the application. Honest. For general purpose use, e.g. running a workstation at home, you are absolutely right: SMP is an excellent solution, usually very cost-effective (by allowing you to use less than state-of-the-art processors) and is in fact what I use at home.

    But if you have a single CPU intensive process that can not be multi-threaded, then you are probably better off with the faster CPU.

    And even in a more generic situatuion, if the newer CPU has a bigger cache, you may -- again for some applications -- be better off with the single CPU and the bigger cache (basically if the bulk of your problem fits in the bigger cache but cannot be split in two parts that would fit in a two-way SMP's cache -- two CPUs are no competition against memory latency).

  • Why was this moderated down to redundant? I don't see a similar question being posted previously. Also, my comments were only slightly off-topic but was on-topic to its parent which was a valid post.

  • ...not including this one. Just shows how inflammatory Intel articles can be just by having the word "Intel."
  • Standards must have sunk for /. to have posted this. I mean, doesn't everyone know that the 1.13 GHz PIII was recalled before any consumer had a chance to even purchase it. Which makes me wonder how this website could even manage to benchmark it and get a price for it. It is not on the market. Intel said it would be back in a few months, but my guess would be that it will get dropped when the P4 comes out...so why bring attention to a website that is posting a bunch of garbage about processors...they did not site how they came across their ratings and they are reviewing non-existent processors. Seems like the person who decided this piece of "news" did not actually read what the "news" was.

    Nisi
    mayhem [mindlessmayhem.com]
  • >forcefully take the SPECint crown away from
    >Alpha, and depending on Intel's progress in
    >optimizing their compilers for SSE2, might even
    >take the SPECfp crown as well.

    Look at your history. Any time in the past 8 years that x86 has come close to Alpha, something happens where Alpha again leapfrogs in speed. That's not about to change. Not to mention that thru history, Alpha's available today are always compare with vaporware of tomorrow.

    I'd like to see a P4 using LESS power, as small a power supply, and in the form factors that Alpha can get in today. Not to mention price. It'll be interesting to see all the same people who bitch about Alpha not having this or or that or being too expensive when they see P4 systems at $4000 using non-standard power supplies and cases.

    The FUD is so thick, you can cut it with a knife.
  • by Anaxagoras ( 190565 ) on Monday October 09, 2000 @05:08AM (#721330)
    the speed of a chip in Mhz means nothing, when comparing two different types of chips. People are never going to realize this though, they have to start looking at mips and flops to get the low down on how the chip performs...
  • Clearly. And the $2500 price-tag for the PIII was for a complete system as well. My point was: why is the PIII rated the worse price/performance when the Mac system is more expensive than the PIII system?

    It would seem, using the criteria they are using, that the Mac would be the worse price/performance, not the PIII.

    If in fact they are using the "price per chip" (as opposed to price per system) in the analysis, why not list the chip prices?
  • Tiger Direct dumped my 650MHz Athalon and a motherboard for $200. Weeee! It runs Red Hat OK for me. Does CFD calcs at least 3 times faster than my 180 Media GX board. Mother board can be upped to 1GHz one day. I might just do that if the price is right, but I get the feeling I'll be better off just building a new machine when the time comes.
  • Context? Where's the context?

    People who post benchmarks without explanation of their particular yardstick ought to be flailed.


    --
    Chief Frog Inspector
  • 'performance-is-absolutely-priority-one requirement' people probably also have certain, ahm, software requirements to go with their need for speed requirement. Such as running a _particular_ piece of software on their blazing fast cpu.

    I myself am getting a little tired of people whining about how useless, overpriced, and power hungry the new Intel cpus are, and everyone should just ditch the crappy x86 architecture, and Alpha is just oh-so-cool and fast and efficient.

    OK, but does it run Windows? Can I play Diablo in my spare time? Run exchange? There are some practical reasons for the dominance and price point of x86 architecture.

    You can't separate need-extreme-speed people from have-lots-of-cash people. If you don't have the money there's no fast cpus for you I guess. Alpha or x86. And if you don't have lots of money what are you doing with all that data to analyze (oil&gas maybe)? And if you have lots of data (your research is not well funded?) maybe a (relatively) cheap off-the-shelf x86 is just the right fit for you.

  • I think I responded to the wrong person. I agree with you, that the G4 has a worse price/performance than the PIII. I was talking to the guy who said that the G4 chip was cheaper than the PIII.
  • someone tell me - what the hell does 95% of the computer buyers need it for?

    They don't. At least not yet. And the chip is not marketed to them anyways. People who are comparing a Celeron to a Duron and looking into an inegrated video/sound motherboard aren't even going to give this a secong look. They're irrelevant as far as this chip is concerned.

    Now, as even faster cpus come out and the price is pushed down there won't be an excuse for buying a And software makers will just assume everyone's running at least a P3 of some sort and that's what they will code for. CPUs just come preprogrammed for a 3-5 year obsolescence cycle.

  • (oops, submit and preview are WAY too close to each other)


    someone tell me - what the hell does 95% of the computer buyers need it for?


    They don't. At least not yet. And the chip is not marketed to them anyways. People who are comparing a Celeron to a Duron and looking into an inegrated video/sound motherboard aren't even going to give this a second look. They're irrelevant as far as this chip is concerned.


    Now, as even faster cpus come out and the price is pushed down there won't be an excuse for buying a <1000GHz cpu. And, here's the kicker, you won't be able to find one. Why are people not running on P200s, even though that's all they need? You can't buy one! If you could (second hand) they won't be in quantity (so no corporate purchasers), the chipset will be way outdated and you won't be able to use any new expansion cards.


    And software makers will just assume everyone's running at least a P3 of some sort and that's what they will code for. CPUs just come preprogrammed for a 3-5 year obsolescence cycle.

  • they gave it a "poor", not an "F"!!!
  • by kyz ( 225372 ) on Monday October 09, 2000 @02:59AM (#721339) Homepage
    The program they make the speed tests with is Intel's iCOMP [cpuscorecard.com]. Is it any wonder that Intel's CPUs come top?
  • But, ... people keep buying them. So is does belong on /.
  • I'll give you a reason. I do mpeg encoding all the time. I've got a Athlon 750 and can easily keep it busy for 6 to 8 hours at a time. I'd _love_ to have a faster processor.
  • The fastest CPU on the block is incredibly expensive, and you can get a system with 90% of the performance for most things at maybe 60% of the price. It has always been so, and will remain so.

    Unless you're so rich that throwing away $1000 matters nothing, don't buy the fastest CPU available for your desktop box. Spend your money on a better-quality digital video camera (if you're a video junkie), or a surround-sound speaker system (if you're a game junkie), or a 21-inch monitor. Better still, spend the money taking your partner on a holiday. Much more fun than 2 extra fps in Quake III :)

  • I live in Canada, I'd much rather buy a Cyrix. It's cheaper and it reduces heating costs...
  • I hate to flame, but that site was really agrivating. It took forever to load up all their flashing adverts, including a porn site like extra bubble, "support our advertisers", with, I shit you not, a picture of a TV broadcasting a pager! ARRRRRG! All of that may have been worth while if the information displayed was clear, but it was not. What exactly was that price comarision? A typical box price? What on earth did they use to compare the performance? Sorry, but I got tired of looking through all of that flashing junk.

    Sharky's extreem never looked better. Ars Technica, you are beautiful. Pricewatch, we love you.

    Poster recomends ignoring this link.

  • by Anonymous Coward
    According to the key to their color coding scheme, my dual 550s are on their last legs and are barely able to run "today's applications"... what a load. Also, I don't see how they can call an Athlon 1GHz only "fair" in terms of price vs. performance... goddamn! That chip is dirt cheap anymore. I immediately don't trust this site. The information they provide is clearly not for performance enthusiasts but rather for the Mr. Computer E. Literates out there. This is more of a guide to buying a PC from Circuit City than a comprehensive CPU price vs. performance comparison. Look elsewhere to find more objective information.
  • I would only trust an independent benchmark. From what I hear, the iComp is optimized for the P3 SSE instructions. If you check out Tom's hardware and and testing sites, you will see that the Athlon comes out on top. At any rate, it is a moot point because there are NO P3 1.13 out there anyway.
  • I've done marketing. I was rather good at it.

    By your own "admission", eh? Sorry, you've revealed otherwise elsewhere in this thread.

    I also hated it. That's why I went back to programming and am now making less that I was before. But at least I'm doing something I like.

    You like it because of the feeling of superiority it brings you. "Anybody can do marketing, but nearly nobody can do programming, so I'm better than that."

    Not anybody can do marketing, period. Your characterization of the noble science of marketing as "90% basic math and bullshit skills" just shows you unability to grasp it. Your preference for a programming job, and your dismissal of marketing as "trivial" just proves you have the Slashdot Syndrome (also known as the "IANAL but I can program, so here's some advice" syndrome).

  • by atrowe ( 209484 ) on Monday October 09, 2000 @03:09AM (#721348)
    "CPU Scorecard also gave the Pentium III an "F" when it came to pricing."

    It's always nice to see the chip at the top of the list doesn't work.

  • It need to be said again: CPU speed mathers but memory speed is much more important. I would be happy to see some major improvements in this area rather than the CPU area. The performance gain would be much more visible than pushing those CPU-s in 100Mhz increment higher.
    This field also shows similarities with the gaming field. More and more eye-candy but less playability/thinking/fun. It's boooooring.
    I'm stiking with Nethack on my good old p188 :)...

    Is it me or it seems that all this is happenig in order to bring the masses to the IT industry's products? But the good old feeling of using/coding that little 386s had gone.

    Something is wrong with the world...
  • by swb ( 14022 ) on Monday October 09, 2000 @03:58AM (#721350)
    Last I read, HL didn't directly support SMP.

    However, I run Win2k on a Tyan Tiger 100 with Dual 650e CPUs -- there is an added smoothness missing in single-CPU versions of this as the operating system is SMP enabled and multithreaded, so that "other" stuff running on your machine gets a chance to run, too -- a single runaway process doesn't freeze out the UI for instance.

    SMP's value grows with multithreaded or forking apps (like Apache) and as your process table grows -- you're able to keep more processes in an executing state than you could on a single CPU machine.

  • But you don't have a clue what you're talking about.

    Intel's technology is so very good that they had to recall the 1.13GHz PIII, because it quite simply didn't work.

    http://www.theregister.co.uk/content/archive/128 70.html

    AMD on the other hand are shipping 1.1GHz Athlons in quantity, and 1.2 GHz Real Soon Now.
    --
  • How this post got moderated up as "interesting" as opposed to "flamebait" is beyond me... But back on-topic:

    There is more to computing than CPU performance, but, conversely, it is a factor. It would be better, in a sense, to do benchmarks of the type: this configuration is better for playing Doom, this one for being a web server, this one for running Microsoft Office, etc.

    The problems are two-fold. First it is very hard to agree on an intersting application to benchmark against (and even if you do then to define it unambigously -- think of the IIS vs. Apache "benchmarks" out there). Second, there are just too many possible combinations in building and configuring a complete system. You would never get a comprehensive benchmark.

    So for the moment we only have component benchmarks. Yes, they are difficult: you actually have to apply some intelligence and knowledge to use them in a "real world" situation. That's why we get paid big bucks. The alternative is to find a vendor you trus and buy whatever they recommend.

  • That's right, this site gives the impression
    that P3 1.13 Ghz is the fastest CPU in the industry.
    In fact, both Alpha and U-Sparc-III are TWICE faster.
  • This is not exclusive to CPUs. You can apply this to quality and/or performance of pretty much anything. The best is always disproportionally higher, because you are paying off the R&D, production improvements, public relations and not just a little subsizing of the next thing in the pipe.

    There's nothing really to complain about, just pick what works for you and get off the fence.


    --
    Chief Frog Inspector
  • by ToLu the Happy Furby ( 63586 ) on Monday October 09, 2000 @07:12AM (#721355)
    Look at your history. Any time in the past 8 years that x86 has come close to Alpha, something happens where Alpha again leapfrogs in speed. That's not about to change.

    Look at your history. x86 actually did briefly leapfrog the Alpha in SPECint95 when the PPro was first released; Alpha took the crown back with the EV6. In any case, the PPro was Intel's only new core introduction of the past 8 years! Thus, judging from our exactly and precisely 1 datapoint, we can conclusively predict that the P4 will indeed take the SPEC crown away from Alpha for a short while.

    I mean, come on--this is engineering, not history. You're not going to get anywhere with a teleological theory of CPU performance over the last 8 years--that's just ridiculous. We don't need to guess or play "history" here; there is plenty of solid evidence about both Intel and Compaq's upcoming designs, how they will perform, and when and at what speeds they will be released. It is a known fact that the P4 is going to be released on November 20 at speeds of 1.4 and 1.5 GHz. It is also a known fact that the Alpha looks like it is stuck at 833 MHz until the release of the EV68 die shrink. It is moreover a known fact that the EV68 is behind schedule and that it will *not* be released before November 20.

    Next, we can look at the again well known design specs of the P4 and EV68. The initial EV68s are essentially just a process shrink of the EV67 from .25um to a hybrid .18/.25um process. The only change we can expect there is a higher clock speed--around 1 GHz by January. A full .18um EV68 will ship by maybe March or April; that ought to hit 1.2-1.3 GHz and might include an on-die L2. Still, we're safe assuming that the EV68 will scale linearly with clock speed at best, with perhaps a slight bump from the on-die L2 in March or April.

    The P4, on the other hand, is a completely new core, full of some really pretty impressive design features. From the point of view of SPEC, the most important are the 3.2GB/s FSB, trace cache, 2-cycle data L1, and larger reorder buffers. In addition, the half-clock-latency ADD will be a tremendous help for much of SPECint and the double-precision SSE2 instructions may allow the P4 to be the first x86 chip to compete or even win on SPECfp. (The much maligned 20-stage pipeline is largely compensated for by the improved larger branch predictors.) In other words, it is very likely that the P4 will achieve higher IPC on SPECint than did the P3. Oh, and it runs at 1.5 GHz.

    So, assuming that the P4 will have the same SPECint IPC as P3 (an assumption generous to your argument) and the EV68 the same as the EV67, Compaq would need to release a 1.066 GHz Alpha before the 1.5 GHz P4 (i.e. in a month). Assuming the more likely occurrence that the P4 achieves ~20% better IPC on SPECint, Compaq will need a 1.266 or 1.3 GHz Alpha to win. Very very doubtful. Looking ahead, it doesn't appear that the EV68 will be able to keep up with the P4 in ramping clock speeds over the next 18 months, either; while the lead will likely go back and forth, it will probably be Intel, not Compaq, with the SPECint lead the lion's share of the time. This is all up until the release of the EV8, which looks to kick some serious butt. Note that I'm not claiming the P4 is a better design than the EV6x, just that Intel has access to better fab process than Alpha.

    In any case, as you see, this is something that can be analyzed with known facts, engineering principles, and informed industry predictions, not with some blind appeal to (false) generalizations made over an entire 8 year period. In other words, "Alpha always wins SPEC" is not quite on a par with "never start a land war in Russia."

    I'd like to see a P4 using LESS power, as small a power supply, and in the form factors that Alpha can get in today. Not to mention price. It'll be interesting to see all the same people who bitch about Alpha not having this or or that or being too expensive when they see P4 systems at $4000 using non-standard power supplies and cases.

    LOL! The P4 *does* use less power than an Alpha; around 50W vs. an astounding 100W for an 833MHz EV67. And as for form factors, I truly have no idea what the hell you're talking about. Yes, the initial implementation of the P4 requires a somewhat ridiculous heatsink compared to the typical x86. That's alright, because the initial implementation of the P4 is being positioned essentially like the original PPro was. The P4 won't become Intel's mainstream chip until around 9 months from now, with the Northwood revision and die-shrink. Northwood, being made on a .13um process, will have much lower power, voltage and cooling requirements than Willamette. This sort of thing happens with every new Intel core: the first implementation is big, hot and power hungry and is aimed at a niche workstation market; then they do a die-shrink and move it into the mainstream. Thus the fact that P4 systems will cost around $2500 (*not* $4000) at introduction really doesn't mean anything. Even at $4000 they'd still be a full order of magnitude cheaper than an 833MHz Alpha system.

    You think the Alpha can beat the P4 in form factor?? Uh...which do you think is going to come out first, an EV68-based laptop or a P4-based laptop?? Or howabout this: an EV68-based tablet computer or one with a P4?? Sun can make a stab at offering embedded CPUs, but I've never heard of anyone even considering an embedded Alpha. Why?? Well...power and form factor constraints, obviously. This is absurd.

    The FUD is so thick, you can cut it with a knife.

    You can say that again. Luckily, come Nov. 20 the FUD will be cleared away, for better or for worse. Now, I'm not arguing that the P4 or even Foster (the "P4 Xeon") will be able to replace Alpha for most of its markets. But it looks as if after years of failing to take advantage of their one clear selling point--unambiguous SPEC superiority--the Alpha is going to lose even that. Here's hoping Compaq finally decides to pour the resources necessary into making this excellent architecture prosper as it deserves. But let's not pretend that Intel is standing still just because the Alpha has been.
  • Who cares if it's the fastest thing in the world? It's still unstable and still can't compile the linux kernel. Now normally, I don't think that linux benchmarks are the way to prove sxomething, but the fact is that it's not a stable chip. Besides, even if you can afford it, finding it will be a pain as well. Buy AMD, they won't crash on you.
  • I'm not sure why I'm responding to an offtopic AC with no reply e-mail address, but...
    The Cube is built on the same motherboard as every other Mac currently shipping. It uses the same video, sound, USB, firewire, etc. circutry, so Linux should work fine on it.
    It is true that the PowerBook w/ FireWire didn't boot Linux when it first came out, but that was (as far as I could tell by trying to install it on one) due to the trackpad not behaving like a generic mouse, and it was before the new motherboards were well supported.

    Fsck this hard drive! Although it probably won't work...
    foo = bar/*myPtr;
  • > If you check out Tom's hardware and and testing sites, you will see that the Athlon comes out on top. At any rate, it is a moot point because there are NO P3 1.13 out there anyway.

    Benchmarks are like complex numbers: they have a real part and an imaginary part.

    --
  • This is ssssaaaaadddddd....
    No offense, but this should be -1 offtopic -1 misinformative. The article compares several processors at various speeds using an Intel benchmark, and it's apparent that they perform differently. That's the point of this article. And the point of this post is?
    This post couldn't possibly be informative because the sole nugget of information is already prerequisite to understanding the article it's posted to in the first place.

    Not only that, but once the author Informed us that MHz mean nothing (which it doesn't), he laments that "they" won't know the real performance of various chips until they start looking at the "real" simple quantitative properties of processors (at least as he seems to be seeing it), the "mips and flops". I have news for you, Anaxagoras. There is no way to place a general performance score on any processor. How many FLOPS a processor can do makes no difference if you're using a word processor. The maximum number of instructions per second it can do can't be compared across processors that don't run the same ISA. And what's the representative program that says what instructions will determine the MIPS of the processor? Hence the science of benchmarking... but the author of the article used a benchmark!

    And what's more, this post is *not* in response to anything. I went and reloaded the thread at -1 and this remained, totally unsolicited.

    I'm sorry, I don't normally beat up on people like this. But it irks me when I see a comment with the length and value of a pedagogical sig get more moderation points than so many other people (e.g. moi) get for hard research, typing, and thought.

    Fsck this hard drive! Although it probably won't work...
    foo = bar/*myPtr;

  • But check out the typical desktop price: C$5,300

    Eh? The page I'm looking at says:

    "Typical desktop: C$3,800 (US$2,500)"

    http://www.cpuscorecard.com/top_cpus.htm#IP3-113 3

    Not that this number really makes sense, because you can't really buy a single-processor G4/500 machine anyway. Only the G4/400 comes in a single CPU flavor.

    - Scott

    ------
    Scott Stevenson
  • then why bother spending such a high marketing expense which decreases the marginal revenue of the product? marketting hypes != quality of the product remember RDRAM?
  • So Intel makes the most powerful Intel or Intel clone CPUs. What would be interesting is how it compares with the CPUs that run inside most modern servers. Is a 1.13Ghz Intel processor as fast as a 400MHz 64 Risc processor.

    Why the suprise that Intel, the company with the most money and who designs the basic platform, can be the fastest in their own backyard. If they were to challenge the server machines then it would become interesting.

Egotist: A person of low taste, more interested in himself than in me. -- Ambrose Bierce

Working...