Please create an account to participate in the Slashdot moderation system

 



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

K7 vs. Pentium III benchmarks 159

The Register has published some benchmarks which they got from an engineer who works at ACER. Personally I would not count on those numbers because: 1. the motherboard is just a sample and not a final product, and 2. The OS is Win2K Beta 3 WinHEC APR 99 release. What do you think?
This discussion has been archived. No new comments can be posted.

K7 vs. Pentium III benchmarks

Comments Filter:
  • by Anonymous Coward
    These "benchmarks" are fakes, and have already been discredited - they're from some spanner in university in Thailand, who claimed to work for acer.

    They're only being repeated in the register because the register has apparently got something against AMD (they're actually talking about suing AMD elsewhere on the site - just go to their front pages, and follow a few of their other AMD links)

    The register isn't usually a hugely reliable source anyway. Out of the UK sites, Need To Know is much better.


  • by Anonymous Coward
    For pity's sake, don'te tell me you actually believe these benchmarks ?
    DON'T believe The Register -
    a) it's never been particularly reliable

    b) these benchmarks are complete crap that a student in thailand just wrote off the top of his head ( he'd not an ACER employee, just goes aroung calling himself AcerManPS ) They're completely unreliable and unsubstantiated.

    c) the register are only printing it because they've been fighting with AMD lately -just check out their other AMD stories ( such as the one about the register suing AMD)



  • > WinBench99 Version 1.1 (5 times measure)
    > CPUMark99
    > - K7@600MHz 68.4 Mark
    > - Pentium III@600MHz 70.1 Mark

    > FPUWinMark (CPU Floating Point Performance does
    > - K7@600MHz 2,819 Mark
    > - Pentium III@600MHz 3,104 Mark

    (1 - 70.1/68.4) * 100 ~= 2.49%
    (1 - 3104/2819) * 100 ~= 10.1%

    2.49% It's a benchmark. Benchmarks don't measure
    real world performance. 2.49% difference is
    nothing.

    10.1% That is a little more, but once again, it
    is just a laboratory benchmark. Plus, the bus
    speed on the K6 is signicantly lower.
  • by Anonymous Coward
    All sites have problems, but TheRegister and BBC seem to not filter their news very well. Just a week or so ago TheRegister reported that Apple was switching to Intel chips. This has thoroughly been denied by all parties involved and confirmed by none. If I recall, the BBC also had a really fake story a while back, but I don't remember what it was.

    Lesson: Don't trust the Register unless you write for them.
  • by Anonymous Coward on Monday May 03, 1999 @08:13AM (#1906871)
    The K7 looks good, and I am sure it can get better than this. This is a chip at 600MHz with the cache running at 200MHz. AMD will want to separate the K7 into the low end like this and the high end with cache like this nice stuff mentioned on comp.arch last week [dejanews.com].

    Having said that, AMD has a real uphill struggle on it's hands. They are ramping up the K7 on their 0.25um process while Intel is just moving to its 0.18um process for the P-III and P-III Xeon. And it's not just any old 0.18um process, according to a Register article I can't find right now and another recent article on comp.arch [dejanews.com] it has a lot of stuff that makes it more like a 0.13um process in some ways.

    AMD really need to break into the high end on x86, otherwise Intel can keep killing them by pressing them into the sub-$100 space where they can't make any money. I wouldn't mind a K7-500 for under $100 though :-).

    I will never understand why Motorola doesn't buy up the x86 part of AMD. AMD is cheap right now, they have a very good x86 design in the K7 and Motorola has the fabs. Are Motorola just going to leave the x86 market to Intel? Are they going to keep betting on the PowerPC to take off? Again and again, AMD has had a good design only to be outspent and outmanaged on the fab front. Motorola has the fab experience, they just need something with a high profit margin to build in them. Take a look at the Intel bottom line, there's money to be made in that business.

    By the way: Interesting to see how crippled the x87 architecture really is. This is said to be a similar implementation technology to the Alpha 21264 (done by some of the same people if I recall correctly), yet the floating point performance of the 21264 in its current 600MHz 0.35um process totally smokes current high end x86s including, it seems, the K7 at 0.25um.

    Erik Corry, who can't remember his password

  • by Anonymous Coward on Monday May 03, 1999 @07:55AM (#1906872)
    This is a fake benchmark perpetrated by a guy who called himself AcermanPS. He lurks around at a Thai webboard called www.pantip.com at tech-exchange section.

    He claimed to be working for Acer in Singapore but his IP address comes from Kasetsart University in Bangkok, Thailand.

    He is the same guy who, a few months ago, claimed that he can overclock Celeron 300A to 600 MHz using only a fan. When pressed, for details, he defaulted with no proof whatsoever.
  • The P3 cache infrastructure looks much nicer. More associativity in the L1 cache (still small, however), and the L2 is at 1/3 chip speed. The latter might not be too bad, if I recall the instruction fetch was fairly pipelined and many outstanding memory fetches were allowed.

    I wonder if AMD is planning on moving the L2 on-chip and upping the L1L2 speed. That would be nice. DRAM sucks, it's way to slow.

    What I really want to know is where they got those G400's and when they will become available. And how well they work under X. :-)

  • Yeah, the K6-3 has on-chip L2.

    The main reason why the K6-[123] had poor FPU performance was that the FPU unit wasn't pipelined. So while if you had to do one FPU instruction every once in a while, it was pretty fast (faster than chugging through the entire Intel pipeline) if you had to do a bunch of FPU calculations, it started going really slow, as it could only work on one at a time. Now the K7 has multiple FPU pipelines, so a whole bunch of floating-point instructions can be going all at once. Which lets it keep up with the P-II/III.

    I'd like an alpha, except I hear Mozilla has big problems with the 64-bit architecture. That, and x86 chips are so darn cheap.

  • Really? A couple of months ago I was using mozilla on my friend's Alpha and it was pretty bad.

    Have things changed a lot since then?

  • by Scott Wunsch ( 417 ) on Monday May 03, 1999 @08:20AM (#1906876) Homepage
    Funny, my copy of that Win2k beta has a licence that says that it isn't allowed to be used for benchmarking or performance testing. I wonder if these guys read their licence...
  • It looks like they are _both_ bound by the constraints of the x86 architecture, and that's what this is all about. Why should that surprise anybody? I'd be more surprised if AMD was able to _significantly_ beat Intel designs. I'd also be surprised if Intel was able to _significantly_ beat AMD designs, or their own designs from last year.
    For crying out loud, haven't you PC guys been eating the same dog meat for ten years? Even if it's terrific don't you get a little sick of the lack of variety? Especially now that billions of dollars have been spent to work out _all_ the big wins in the designs so there is nothing left but piddly little gains at phenomenal cost.
    More than ever I'm happy I've been using PPC- now that's something I'd like to keep available, in all its 32 register, general purpose vector (128 bit) processing unit, 1 meg of cache glory. What do you think would happen if the industry put the same amount of energy behind that as it does behind x86? Yeah- it'd zip right past x86 and you'd be buying PII-like daughtercard things with _sixteen_ or _thirty-two_ PPCs all on the same die- and you'd have to run Linux (or Solaris or something) because NT or MacOS don't _scale_ to that extent yet!
    Instead most people want to eat the same dog food over and over, even when they have to _replace_ their RAM, their MB etc anyway (you'd think that would tip them off).
    Linux runs _quite_ nicely on PPC and you don't have to give money to Apple directly to do it- homebuild something, buy older powermacs used (top of the line ones from a couple years back) and get ones that can be upgraded to G3 simply and easily (i.e. most of them, by now). That or wait around forever for somebody to make PC PPC mobos while _you_ keep eating old dog food because you don't see anybody making new recipes, which they won't as long as you and everybody else are still gobbling up the old dog food as fast as they can make it.
    I hope PPC (or Alpha, or *fill in blank*) _does_ end up stomping all over x86. But if it does not, I don't regret for a second that I was willing to try it and see. I _like_ the way my PPCs work. I was able to get some frags on q3test against G3 guys and I only have a 200Mhz 604e on a slow bus! (unsupported, and running the Mesa libs) PPC is _so_ underestimated. (ok, end rant. phew.)
  • How does a processor make the Internet go faster? It makes all the cpu-intensive Java applets and VRML worlds that Intel pays sites to include go faster.

    Promoting poorly-designed sites with more fluff than content for their own financial well-being... .

    That AMD doesn't do that sort of thing (and doesn't have Intel's deceptive advertising) is among the reasons I favor them.
  • by gavinhall ( 33 )
    Posted by Perkolater:

    I'll believe it when I believe it. When I see some benchmarks on non-sample, commercially-available hardware, using an operating system that ISN'T vaporware, then I'll start paying attention. This is beyond FUD -- it's AGFUD. (AG meaning "Axe Grinding")
  • If you take a look at www.pricewatch.com, it can be seen that the K6-3 450 is indeed slightly higher priced than the PII and PIII at the same clock speed. However, if you compare the K6-2 at 450mhz, you'll see that the K6-2 is over $225 cheaper than either of those chips. The K6-3 at 450mhz is currently the fastest processor by AMD that is on that page, and if you look at the K6-3 at 400mhz rather than 450mhz, the price is $170 less. ($235 vs $405) Now, if you look at say a 500mhz PIII xeon with 1meg of cache, the chip costs $2067. If you go for the highest end K7 that comes out the first day it's out, you'll probably pay quite a bit, but the lower end of the K7 spectrum should bottom out rather nicely to match what else is out there after a week or two. As to the benchmark situation, I think enough other people have shown the architecture benefits of the K7 cpu over current offerings, and why this test logically doesn't make very much sense.
  • The die sizes I quoted are all for a .25u process. According to AMD, the K7 die is less than 100sqmm at 0.18u.

    I agree that the K6-III gets a real boost from its onchip L2, but remember that the K7 has 128Kb of L1, and this should be enough to compensate the "slow" half speed L2.

    For the FPU, you're right, I should not draw conclusions from the tech docs, but the K7's FPU is something AMD seems really proud of ...

    If theese numbers are true, I really wonder why AMD hired all theese Alpha designers, and what they've been doing for the past 2 years ...

    Oh, another "weird" thing is that the tested K7 is supposed to run its L2 at 1/3 core speed. I thought that AMD demonstrated both 500Mhz and 600Mhz K7s with half speed cache (but I may be wrong) ...
  • by six ( 1673 ) on Monday May 03, 1999 @08:16AM (#1906882) Homepage
    Yep ... I don't trust theese numbers for some obvious reasons ...

    Ok, so a K7 is slower at WinStone than a P3 at the same frequency ?? This would be VERY SURPRISING given that even the K6-III WS scores are significantly higher than a P3 at same clock speed. This would mean that the K7 is outperformed by a K6-III and I just can't belive this.

    Let's compare the CPUs die sizes also :

    K6-III : 91 sqmm
    Pee!!! : about 120 sqmm
    K7 : about 185 sqmm

    K6-III 91 sqmm includes 64Kb L1 and 256Kb L2, K7 just have 128Kb L1 on die ...

    So, if you got my point, the K7 is more than double the silicon size of the K6, so what do you think they put in ... Delay loops ??

    Another strange thing is that the K7 system uses and AMD chipset and DRDRAM. ALI is one of the supposed K7 chipset manufacturers ... For people who don't know, ALI stands for Acer Labs Inc. so why the hell an Acer engineer is not using an ALI based test system ??! Moreover, the AMD Irongate chipset is not supposed (but don't quote me on this) to support DRDRAM.

    The FPU numbers are quite funny too ... I read some K7 FPU tech docs (well, the few that are available), and there's absolutely no way that the K7 performs worse than a P3. K7 has 3 fully pipelined FP units, P3 has 2 semi-pipelined units, and P3 has more latency on FMUL, FDIV, etc ...

    I won't trust any benchmark numbers unless they come from a reliable source, and the register, obviously, is not one (but we already knew it :)
  • by RobKow ( 1787 ) on Monday May 03, 1999 @07:44AM (#1906883)
    Doesn't exactly look like responsible reporting to me. Upon a close inspection the system stats look hokey (Especially regarding RAM and HD). And if I understand correctly, ALi and VIA were to be creating the chipset. Additionally, according to AMD the backside L2 cache bus supposedly "scales past 1GHz," so I'd naturally assume that the L2 cache would be core speed, or at least 1/2 of it. And even the size (not to mention the Ultra3 speed) of the IBM hard disk looks fishy. What happened to 4.55, 9.1, 18.2, 36.4... From our favourite news source, even.
  • Why?

    To get its hand on a good x86 design

    Last year AMD had sale of something like 2.5 billion dollars. Last _quarter_, Motorola had sales of 7.2 billion. And Intel? 7.1 billion last quarter.

    Precisely. AMD is too small to be taking on Intel. Motorola could take the K7 design and run with it.

    The rumour mill has Compaq buying AMD. I think they need to be bought by someone who knows how to run a fab and who won't be in competition with AMD's customers.

    x86 is a dying technology

    Merced is rumoured to be a flop, McKinley is rumoured to be late, Alpha is still not taking off. Sure x86 is dying, but it has been for years and that hasn't stopped Intel making a fortune on it. Remember, Windows 2000 is either going to be W98/DOS-based or late or both, so where does that leave non-x86 designs for the mainstream? Some years off.

    The PowerPC 750 is a damn fine chip.

    I'm sure it is, and Motorola should keep building it, but its not where the volume is, and that's not going to change. And while they are doing OK, they don't have any sort of performance lead over the `dying' x86 chips: According to The CPU Info Centre [berkeley.edu] they get maximally 17.6 SPECint95s at 400MHz in Motorola's 0.22um process, while Intel is well into the twenties [spec.org] at 0.25um (I think).

  • What the heck is a 7th generation CPU?

    Are you counting back generations form the 8080?

    8080 -> 8086 -> 80186 -> 80286 -> 80386 -> 80486 -> Pentium -> Pentium Pro -> Pentium II -> Pentium III

    But even then before that was a 4040, or was it a 4004, I don't recall.
  • AFAIK even intel doesn't have a test implemenation, so i doubt any amd/via K7 chipset would.

    i think you should go back and read the article!

    i meant that it says both 133 and 200mhz as the fsb for the K7 system. which is not quite right: 200mhz ev6 bus is plausible. 133mhz SDRAM is plausible - but it says RDRAM@600Mhz!!

    would an acer engineer make those kind of mistakes? sounds like a kiddy who pulled jargon of various sites.
  • you can get 533MHz 21164a's for dirt cheap from samsung dealers. (eg ~$200).

    You can get a motherboard with onboard uw scsi, ethernet and 2MB L3 cache for the price of a high-end P11 board.

    That's 533MHz, 8+8KB L1 cache@cpu clock, 96KB L2 @cpu clock and 2MB L3 @66mhz - and beats the pants off *any* intel chip at floating point. All at the same price, maybe less, than the latest intel stuff.

    better still - it'll clock to 600, maybe even 667.
    anybody considering doing 3d rendering should get an alpha rather than intel.
  • depends where you are. I'm in Ireland and just a bought a Samsung 533MHz 21164a @ GBP £149 and a Samsung UX board @ GBP £452 from Compusys in the UK. I got a midi case, motherboard, cpu and 128mb of memory for a total of about GBP £890 ex VAT. which is pretty good. ($/£ = roughly 1.5).

    Have a look on www.alphalinux.org, there's links to vendors like dginc, who can probably put a nice system together for about $1500.
  • by Paul Jakma ( 2677 ) on Monday May 03, 1999 @07:23AM (#1906890) Homepage Journal
    This has already been discredited.

    Look at it: it talks about USB2.0 (not ratified).
    600MHz rdram doesn't exist.
    one minute it says 133mhz fsb, next it says 200mhz.

    it's a fake.
  • Just because USB 2.0 isn't ratified doesn't mean that can't possibly have test implementations of it.

    And there doesn't seem to be any sort of inconsistancy with the FSB rates. They're exactly what every media story has mentioned for the associated chips, 200mhz for the K7 and 133 for the PIII.

    Go back and reread the article.
  • I've got a Celeron 450a, which has 128K of full-speed L2 cache. It works very nicely. It's debatable which will give better performance, AMD's 128K of L1 and 512K L2 at FSB, or Intel's 32K of L1 and 256K of full-speed L2.

    Didn't K6-3 have on-chip L2? If they did it there, they'll likely do it to K7. IIRC, that was the move that made AMD start benching faster than PIII (but not Xeon) for non-FP stuff. A K6-3 would still make a bloody nice webserver, and K7 can do SMP, right?

    I'm impressed that (if the tests are true, no way of telling) AMD finally has a machine that appears to be able to keep up w/Intel in FP performance. 3DNow! aside (since it's only used in a few specific applications, and Intel has their own SSE), the old K6 core was pretty pathetic in the FP department, about 40% slower than an equivalently clocked PentiumMMX.

    But if K7 can keep up ... oooh ... 200mHz FSB ...

    I guess we're all being stupid. If we want fast computers we should abandon this 20 year old mickey mouse architecture and go buy Alphas. Mmmm, Alphas.
  • in these tests, just CPU FP and INT performance. So it probably doesn't matter, and I'm not surprised they give round numbers for the HD. The only important thing was that the systems be as close as possible to identical.

    Of course, I'd still like to verify this m'self. How about a K7, AMD? :)
  • But I disagree with some of your critiques:

    - Die size: this is an early K7 built on the .25u process, while the pIII is .18u, right?

    - The k6-3 has L2 on chip, a significant speed boost for non-FP stuff. I imagine AMD will hurry up and add this to the next run of K7's.

    - Don't draw any conclusions from white papers on FPU design. Benchmarks are benchmarks. I wouldn't trust anything written about those FPUs, there's just no way to tell what weird stuff will affect performance (e.g. PPro core is fast, but very easy to stall. Result --- some poorly-compiled programs get lousy performance)
  • They're only being repeated in the register because the register has apparently got something against AMD (they're actually talking about suing AMD elsewhere on the site - just go to their front pages, and follow a few of their other AMD links)

    Try reading the article you're recommending, Should The Register sue AMD? [theregister.co.uk] Despite the title that caused you to make an unwarranted leap to a foregone conclusion, they're NOT suing. The title is partly tongue in cheek, and partly asking for opinions from readers, but the key part of the article says "...So we're inclinded not to be litigious."

    An American lawyer is quoted in the article as offering to represent The Register, and recommended that they make certain demands before they offer to refrain from suing...but it's not the Register that said that.

    Yet another example of why you should read stories (and read them reasonably carefully) before jumping to conclusions.

    (But yes, it's obvious the benchmarks are fakes, as you say; as to the reliability of the Register, I don't know their track record overall, and I don't read them regularly, but I've noticed a number of articles over time that were in fact accurate and did seem to be the one of the first sources to break new news, so I wouldn't discount them out of hand, either.)

  • Why would I take a PIII anyway? As far as I'm concerned, AMD will always have my $ and I'll always have their product unless they start this processor serial number crap too. And then in that case I'll just start working from my 486. I can get parts for it really cheap, and noone cares what I run on it. :)
    -Philip
  • The PIII machine listed there purportedly has CPU speed L2 cache (600 MHz). But Xeons' smallest L2 setup is 256k, I thought. In any case, this PIII sounds like a next gen 'workstation' Xeon.

    Anyway if these are right (and, IMO, they're not) then everything you've been told about the FPU of the K7 is wrong. Right?

    The Register is not a good source for much. I am not familiar with the benchmark program, but believe time will show this to be baloney.

    -k
  • (fud disclaimer, i'm a diehard linux fan, but the following is just the truth, taken from what i've read from linus)

    that would be cool, until you hit 4, when linux's smp hits the wall, i haven't heard when linux is supposed to do 16 well, though i doubt i'll get that many processors any time soon...really, how many people do you know with 16way smp boards?
  • Maybe they make good motherboards, but that's it!!! Everything else they make "SUCKS ASS" - CD-ROM drives, complete systems, modems, etc. I think the motherboards are made my a separate division A-Open....
  • We should look at the results of a K6-3 first, it's CPUMark is higher than the P3 already. This is saying the K7 is slower than a K6, I don't think so. I've seen benchmarks that says a K6-3 450 beat the P3-500... (not in FPU though) ---With 3DNow enabled the Direct3D(I know I hate to use this comparison) benchmark was right on par with the P3 at the same clock speed. So it's basically impossible to say the K7 would be slower. Look in Maximum PC, April issue...
  • Though I highly doubt the credibility of these benchmarks, I wouldn't find them that far fetched either. Taking the naive attitude that AMD will build a supercomputer processor for cheaper than a Celeron is insane.

    If you take a look at chip pricing today. You will see that the AMD K6-III is currently more expensive than the PentiumII-450 (by about $39) and even the PentiumIII-450 (by about $25). What makes anyone think that when the K7 comes out it will be so much cheaper than Intel offerings. Companies are in business to make a profit. AMD is a company. Therefore, and this goes especially for AMD, getting profit it the bottom line. AMD has been losing money because of trying to sell their processors to cheap. A company can only do this for so long. When the Premium K7 comes out its also going to come out with a Premium price tag. Just like the Intel chips. So please, don't continue to think that the K7 will be a cheap chip. Performance has its price.

    Taking the also very naive idea that Intel cant build a better chip than AMD is also idiotic. While in my eyes the K7 currently appears to be a better processor than the CURRENT PentiumIIIs. What makes anyone think that Intel cant do better than them? When prototype samples of the K7 are out, who do you think some of the first people to have their hands on the specimens are? I guarantee you Intel techs are some of those people. Intel knows what AMD is up to long before you and I do. And is it really that far fetched that there could be a pro-Intel guy working for AMD? Or vice-versa? Welcome to corporate America where _Everyone_ has their price (Except Linus Torvalds apparently. :)

    We can crown a processor as king these days, but not for very long. And in all actuality its impossible to say who makes a better chip. AMD may bring out its K7, but in the fairly long time they have been designing this chip, who knows what Intel, Motorola, IBM and even 'lil Cyrix have come up with. One company may squeeze ahead for a while, but another one may squeeze by and take the lead from them. It will be interesting to see as the months (and years) go by who will come out on top. Who knows, maybe a few years from now we will all be running Linux on Cyrix chips. Hey, It could happen to Cyrix, did YOU think 3 years ago that AMD would pose such a threat to Intel's happy little camp?
  • ... when you consider that AMD usually/always price thier chips BELOW intels.
    Somone above did the math and found it was only 2% slower in one test, and 10% in the other. If AMD price their chip 25% less than intels, then with two CPU's of the same price, you still come out ahead, even with floating point (floating point performance is what has kept me with intel cpus up until now, so no I'm not an AMD zealot, just noting some math :)
  • This stuff happens way too often. Does anybody know if AMD has an e-mail address for reporting blatant FUD like this?
  • K6/3 had 256k on-chip L2; the K7 looks a larger chip (because of the 128k L1), and AMD have been having enough problems fabricating the K6/3 that I'm not surprised they're rolling out the K7 with FSB L2.
  • The i820 (board used in these benchmarks, codenamed Camino) can use either PC133 or RDRAM. Intel's intention was to use RDRAM all the way; despite something like $1 billion investment by Intel in RDRAM manufacturers, it's not yet available in sufficient quantities, so they're permitting PC133 as well.
  • Yes oh wizard of BS. Where do you get your benchmarks? This is all just hyped BS being spread around. So until a K7 is in your hands and you can play Q3 on it, shut up.
  • Oh calm down little kid. Getting all pissed off are you. And by the way its not a Xeon you TARD. It's a coppermine PIII. So before oyu start cussing your little head of, shut up. And it never said they were on the same Mobo and its not illegal on Win2k if microsoft gives you permision. Tard.
  • Do you consider your cdrom drive eating an AOL disk a problem ?

    If it were my cdrom, I would be proud of it :)

  • I dunno what's wrong with 6x100, but you know intel. Forcing a lot of people to upgrade motherboards (mine supports 133, many don't).
  • here's some info I found about the source of the data. It's copied from http://www.3dnow.net/

    It appears that more bits have been found out about the source of these "Acer" benchmarks. Found this posted on the forum: "This is a fake benchmark perpetrated by a guy who called himself AcermanPS. He lurks around at a Thai webboard called www.pantip.com at tech-exchange section. He claimed to be working for Acer in Singapore but his IP address comes from Kasetsart University in
    Bangkok, Thailand. He is the same guy who, a few months ago, claimed that he can overclock Celeron 300A to 600 MHz using only a fan. When pressed, for details, he defaulted with no proof whatsoever."

  • K7: 7th gen cpu, 200mhz, bus, 3 fpu units, huge pipeline, large L1
    PIII: ppro w/mmx w/sse and slower cache (6th gen)
    Even if the K7 sucked (probably won't) it would outperfrom the Pxxx at the same clock speed by at least 20%. The Register isn't exactly a reliable news source.
  • K6/3 had 256k on-chip L2; the K7 looks a larger chip (because of the 128k L1), and AMD have been having enough problems fabricating the K6/3 that I'm not surprised they're rolling out the K7 with FSB L2.


    If I recall the presentatino sheets correctly, the K7's L2 cache is a _backside_ cache and can be clocked at whatever speed they decide to ship it as. The front-side cache is an L3 cache.

  • AcerOpen Motherboards are fine components.

    Check Tom's hardware... he rates one of their boards as being the most stable socket 7 board out there [tomshardware.com]. I've personally purchased three dozen computers based on Acer AP53, AP58, and AX59Pro motheboards for my customers over the past two years, and I've had no complaints at all. Most of these systems run NT Workstation 24/7 and get rebooted once a week at the most.

    I ran Debian on a used AP53 with a Cyrix 166 and went two months without a reboot.

    Don't knock hardware you don't have any experience with. Acer makes fine stuff.

  • I agree.

    Motorola is in a very good position to buy AMD (which is in a very bad position). It makes a lot of sense for a variaty of reasons. also IBM should consider buying AMD.

    it's interesting that AMD's stock is so low that ARM has nearly the same market cap as AMD. this is funny since ARM has no FABs.

    come to think about the FABs that AMD have alone are worth more then their current market cap.
    --------------------------------
    check out my music [mp3.com] .
    you might actually like it.


  • This would mean that aside from FPU, the K7 is roughly the performance levels of a K6 with an improved FPU (which is enough to throw considerable doubt on on the numbers, but is tangentical to my point).

    This would mean that AMD has sacrificed more in the name of clockability that I had believed (recent reports from Sanders seem to indicate that MHz is king again and that's AMD's primary goal). In this case, AMD had best ramp the clock speeds up into the stratosphere quickly -- something they'll need to do even if the numbers are completely bogus.

    Another possibility: is this benchmark first and foremost a L2 cache speed test?


    SL
  • Anonymous Cowards shouldnt go around bashing AMD or the people that happen to like AMD. And they also shouldnt go around showing off their ignorance of a subject. AMD has been in the microprocessor game for years, and recently only have they begun to make moves to overtake Intel,s market share. While they know they may never fully replace intel in the market place their quality products for a much reduced price is something that will make them very competitive.
  • No I thought "coppermine" (0.18 micron P3 core) will have 256kb of on-die L2 cache? This looks like a next-gen P3 against a P7. I don't know if they'd get a P2 "deuteches" (current PIII core) going at 600mhz without serious cooling. Still, looks the hardware they have on those rigs does look a little sus'
  • It will trail the K7 by 3 months to market.

    The Coppermine is like the Celeron only with TWICE the L2 cache and the P3 instruction set (with SSE).

    I think AMD will do MUCH BETTER once SLDRAM is on the market (i.e. the latency of DRDRAM just sux!).

  • Here [supersite.net]'s one article (April 9, 1999) announcing the 700MHz spec. It exists, just not in desktop quantities; AFAIK, it's only just reaching the OEMs for server integration...

    Just so there's no confusion, Direct Rambus [rambus.com] DRAM (RDRAM) is a completely different memory architecture from the stuff in a regular PC. That's why the speeds are orders of magnitude faster
  • - Die size: this is an early K7 built on the .25u process, while the pIII is .18u, right?

    Yes, and no. I'm not too sure on the dates. At the moment (I think, unless this is a one off chip...which I'd doubt) the K7 is .25u, but will be .18u when AMD get their collective sh_t together.

  • Which part of the AMD-cpu is outperforming the Intel chip? I hope you are not talking about the integer unit cause that's the only thing that barely beats Intel's.
  • Well, I found these benchmarks a bit untrustworthy, so I decided to get my hands on a couple of test systems and do my own benchmarks. Here are the results:

    K7-600 vs PIII-600
    all peripherals identical

    RESULTS:
    rebrane niftymark 3000 (integer operation test, MMX register not included)
    - PIII: 3.6
    - K7: 1,953,234

    rebrane FPUmark 3000 (FPU operation test, 3DNOW register not included)
    - PIII: 0.5
    - K7: 5,230,193,294

    As you can see, these results clearly and conclusively show the superiority of the K7 over the Pentium III. I hope this puts an end to this Register nonsense once and for all!

    -- neil
  • ... but if the hard disk doesn't EXIST, then that's a fairly good barometer for whether or not the article is made up, obviously enough. -- neil
  • The last I heard the K7 was a very not cheap chip to produce and will most likely cost about the same as a comparable Intel chip
  • Thats a good call on the hard drives, I've been searching for a 10 gig scsi hard drive for a while now, need just a bit more than the 9 but not quite an 18, and no one makes them. Unless this is some new prototype there aren't any 10 gig scsi hard drives. Figures tho, since when has acer done anything good, much less reputable
  • From all I have read about the k7, architecturally there seems to be no good reason that its fpu would be slower than that of the Pentium III, ie, more parallel execution, more pipelining, and all the rest. Or the problem could be cropping up in the operating system, god knows microsoft plays enough tricks in its final releases, god only knows what they are up to in thier beta's.

    Either way, if these are true I am really dissapointed. I was planning on replacing this machine with a dual K7 system just about as soon as the chips and boards came out. Also if these are true it could spell the end to that small thorn in Intel's side known as AMD, and that would be a real shame. It might just be an american thing about rooting for the underdog, but damn if i didn't want the K7 to come out and just wipe the floor with intel and its crappy PIII adds. (how in god's name does your processor make the internet faster? someone want to explain that one to me?)
    If AMD goes down the only real competition I can see Intel meeting is the DEC Alpha.(sorry Compaq, in my heart it will always be a dec) Once everyone realizes that they are going to need to move everything to epic, both on the development side, porting to epic, and on the consumer side, buying all new apps, people might really consider the alpha because atleast in Linux as of now its distributions are stable, its compilers and libraries are getting more and more mature, and no matter what it will be more mature and more stable than merced, just because it will have been around a lot longer. But I digress.

    Someone please prove these benchmarks are crap...besides the fact that they came from acer :)
    I would hate to see AMD go down now, getting so close but not quite knocking intel down.
  • In any good experiment its always nice to see where you might have screwed the pooch.

    1. Win 2k beta 3? why in gods name would you try and pass any type of reputable benchmark off on an operating system that isn't done yet.

    2. Acer computers...need anyone say any more about that? :)

    3. Intel FUD, acer, being a crappy company that makes crappy computers is just fine with being used as a toy for Intel's PR department. The last time I checked I didn't know acer made anything with an AMD chip in it, but I could be very wrong, I've been building my own machines for a while and don't stop to look at the specs on acer's most recent POS at compusa or wherever they sell them.

    4. Timing, last I heard the K7 wasn't in final production yet so its also a beta chip.

    Beta OS, beta chip, crappy company, looks like a load of BS to me.
  • Cheap computers making more money is utter bullshit. Albeit I've only been in computer sales for about three years. Then again I'm only 20, but from what I've seen switching from one computer retail center (OD) to an actual computer company (Moocow!!!) I've seen a great difference. The moo at the moo company my average sale is close to 3000 dollars where at the other place it was around 1300. At the moo place I do about 500,000 dollars a month in sales. The other place only netted about 200,000. Good companies put out good computers that people buy **Repeatedly** Shit computer companies put out shit computers that some people get stuck with once in a lifetime. I.E Acer, Compaq, Packard Bell, HP, and I list so long I dare not go on. Trust me cheap computers only make money for a short period of time then they fizzle. If cheap computers were so great, then Compaq wouldn't be taking such a big push into the small to medium grade business level now would they!!!
  • the REGISTER. Plus, these tests conflict with all other test results I've seen, as well as Intel's take on the K7 (see various articles saying how AMD 'worries' Intel). There's another absurd article on the REGISTER mocking AMD. If they want to be Intel stooges, let them. Those of us with a clue will make an informed decision about what CPU we buy.
  • It never stops amazing me how many people step up to bat for AMD.

    Nothing against them, I wish them the best and I think competition is good but why should anyone believe that these benchmarks are incorrect? (why should they believe them?) The K7 has impressive sounding specs but I've never known a chip company to underestimate their product's performance. Intel has never exaclty sat on their butts while a competitors made something amazing either, it sounds like the K7 and the P3 are about the same, as I would expect it.

    I'm guessing that the K7 will perform on par with Intel's best and it's cost will also be on par with Intel's.

  • THe K6-3 is beating the PIII at what? NOPs?
  • What the heck is a 7th generation CPU?

    4040/4004 we will call 0th gen
    8080, 8086, 80186 are all 1st gen
    80286 is second gen
    80386 is 3rd gen
    80486 is 4th gen
    Pentium is 5th gen
    Pentium Pro is 6th gen
    Pentium II is 6th gen (PPro with slow cache and MMX)
    Pentium II Xeon is 6th gen (P2 with fast cache)
    Pentium III is 6th gen (P2 with SSE)
    Pentium III Xeon is 6th gen (P3 with fast cache)

    intel have not released a new architecture since the PPro god knows how long ago. The K7 is 7th gen.

    --
  • by Edd ( 24120 ) on Monday May 03, 1999 @09:28AM (#1906936) Homepage
    I found this on a messageboard, here [aceshardware.com] by General Lee D. Mented, it is pretty good:

    > I'm a hardware research engineer from Acer Inc. (Singapore)

    Do we have any proof of this? No.

    > K7 test machines CPU K7 600MHz (FSB 200MHz x 3.0) 600MHz 128KB L1 Cache
    > 2-way associative 200MHz 512KB L2 Cache 4-way associative EV6 BUS
    > Controller L2 Cache Speed 1/3 FSB

    Everyone on this message board has mentioned this part spec dozens of times, this could easily be expected.

    >RAM TI Direct RDRAM 256MB at 600MHz

    I believe Intel RDRAM spec is twin concurrent 16bit busses at 800mhz, not 600mhz. This would support the claims of 3.2GB/sec and multiples thereof with interleaving. Also, Sony has speced their PSX2 as having an 800mhz RDRAM bus. Nintendo RDRAM runs at 433mhz. I don't know of anyone making 600mhz rdram because nobody apparently intends to use it. I believe this is fake.

    VGA
    > Matrox Millennium G400MAX 32MB SGRAM 360MHz RAMDAC Resolution 1600x1200 32
    > Bpp 85Hz

    The card's been announced, everyone who read the press release saw it and full specs.

    > Harddisk IBM Ultra3 SCSI 6ms 10.0 GB

    Nobody makes a SCSI HD in 10.0GB. They're all multiples of 2.255GB. 4.55, 9.1, 18.2, 36.4 are all currently shipping capacities. I don't believe IBM has shown a U3W prototype yet, only Quantum has that I'm aware of. Also, there is no controller listed in this spec, and I haven't yet seen any manufacturer talking about and upcoming U3W controller for anytime this year. Not believable.

    > Mainboard AMD Sample Chipset
    > Northbridge AMD Irongate AGP4X SouthBridge AMD Cobra ATA66 USB 2.0

    Chip names but no numbers. I believe the names were on AMD presentations or discussed at comp shows or shown on roadmaps. We obviously expect AGP 4x. Intel has not even finalized the USB 2.0 spec yet, so support for this in an already existing chipset is nonsense.

    > OS-Windows 2000 Beta 3 WinHEC April 99 Release

    Nobody in their right mind would run benchmark comparisons on a beta OS.

    > P-III test machines CPU Pentium III Coppermine 600MHz (FSB 133MHzx4.5)
    > 600MHz 32KB L1 Cache 4-way associative 600MHz 256KB L2 Cache on-die 4-way
    > associative

    We all expect this part eventually. Nothing new in the specs for it.

    > Mainboard Intel Sample Chipset Northbridge
    > FW82820 AGP4X Southbridge FW82801AA ATA66 USB 2.0

    Chip numbers for this can probably be easily extrapolated from current intel partnumbers. We've been hearing for weeks about delays in the "intel 820" chipset. We know it will support agp4x and ata66 (not that anyone cares about ata66). I'm very confident it will NOT support USB 2.0 as intel has announced that will be coming up for early 2000.

    > WinBench99 Version 1.1 ( 5 times measure ) CPUMark99 (CPU Integer
    > Performance Not include MMX register) - K7@600MHz 68.4 Mark - Pentium
    > III@600MHz 70.1 Mark

    This is quite likely made up. The scores on the PIII which could be considered a "known" are way off from projections from standard clocks and results from overclocked systems. Sorry, this is most likely numbers drawn out of a hat and adjusted to make the K7 look bad.

    > FPUWinMark( CPU Floating Point Performance Not Include
    > MMX,SSE,3DNow!,FSTORE Extendtion register ) - K7@600MHz 2,819 Mark -
    > Pentium III@600MHz 3,104 Mark

    Again, probably random numbers.

    Now I have to ask, how many people on here would not know where to find the press releases, product roadmaps, and rumored info to construct this kind of sham? The accuracy of the description is the only thing that makes it believable to any of us. The more you actually know about this upcoming hardware, the easier it is to fake, because you can get the audience's confidence with known facts and then slip the lies in at the end.

    --

  • Actually 256k full speed on-chip cache is exactly the specs that have been floating around for Intel's .18 micron Coppermine PIII core.
  • how in god's name does your processor make the internet faster? someone want to explain that one to me?

    I think it has the ability to suck harder on your phone line than most other processors can.
  • Did the sock monkey commercial creep-out anyone else? I was having flashbacks to "Poltergeist".

    Yes, give this one some time. I think we'll see these figures become more realistic. I don't think AMD will disappoint us on price, either.

    Another ß Windows 2K? Hmm. We're not even internally supporting Office 2K until June, which is ready to ship AFIAK.
  • I say take your idea a bit further. Disregard benchmarks altogether. Very rarely have I seen a benchmark that comes close to actual production performance. Is the K7 faster than the PIII? I dunno. Wait until it comes out and evaluate it yourself.
  • Acer isn't exactly known to be a trustworthy company. A while back they had a class action lawsuit filed against them for using old/used hardware in their new computers. Though my old acer is still running alright. So who knows.
  • I've been wanting Alpha for a long time. If anyone reading this knows of a particular supplier that has deals on just the MB + CPU, please let me know
    a while back I got a quote fo $1,400 for PC164UX2 and 533CPU, but There is some way to get this for 5-600 ill do do it.
  • The generally accepted x86 Intel CPU generations are:

    1st Gen: 8086/8088/80186/80188
    2nd Gen: 80286
    3rd Gen: 80386[DX|SX]
    4th Gen: 80486[DX|SX|DX2|DX4]
    5th Gen: Pentium / Pentium MMX
    6th Gen: Pentium Pro / Pentium II / Pentium III

    Note that the Pentium Pro thru the Pentium III all share the same basic core, with the PII adding MMX and the PIII adding SIMD instructions to it.
    Calling the K7 a seventh generation CPU would mean that it has a new basic microarchitecture after that of the PPro (which it does)

  • AMD already has knocked Intel down. Their products may be somewhat slower than Intel's, but that does not make them a failure. They have successfully pushed Intel to lowering prices and making newer and better products. Without this competition Intel would be charging more for slower CPU's. Whether AMD topples Intel or not is pointless, simply replacing one (possibly evil) empire with another one accomplishes nothing. By having a good competitive balance as we have now the consumers are the real winners. AMD needs to start making money, so this competitive process can continue, rather than destroy Intel.
  • mozilla works fine on mine... netscape on the other hand...
  • IBM has fabs and engineers to make Intel and Motorola drool. IBM has come in already and helped out AMD on their .25 fab and even talked about buying the company at one point. This is exactly what I think IBM will do if AMD gets into too much trouble. If IBM took the K7 design and let their engineers loose on it and converted it to their .18u copper process, Intel would be dead in the water.
  • i'm certainly no benchmark guru -- but if the goal here is to test the motherboards, why the heck do they need all this other completely cutting edge hardware in them [g400 graphics accelerator, USB2.0, SCSI 3]?

    Sounds more like an Acer engineer fell asleep at his keyboard and had some kind of hardware-based wetdream.

    TravelMate indeed!
  • The 133mhz fsb is listed on the PIII while the 200 mhz is listed under the K7. I'm not sure whether 133 is correct for the PIII, but the numbers are for separate processors.
  • How is that? Hell the K6-3's are selling for a higher price than the P3's at the same clock speed? Not to mention you need to get a new motherboard and RAM to support the K7 where as I can upgrade my Intel CPU by taking out the old one and popping in the new one.
  • Sorry , that last comment was mine , not Anon Cow
    forgot to login .
    squireson
  • Do you need to have a new motherboard to use an Alpha chip ? Do you need a new motherboard to get the advantages of a motherboard ? Where can I go to learn more about this ?
  • nice!
    looks like you've got even more proof than that other guy... hehehe

  • My IBM deskstar is advertised to have 10.1 GB.
  • I thought that the P-III ran on a 100 Mhz bus. This test was done with a 133 Mhz bus... Hmm that would seem like an overclocked P-III isn't much better than a standard K-7. I would like to look on Intel's website to see if the 600 Mhz P-III will be run at that bus speed, but their site sucks so much ass, that it is hard to find info on P-II, let alone the P-III. If it is supposed to be on a 100 Mhz bus the test would only be fair if it was against 266 Mhz bus on the K-7.

    P.S. I wonder if AMD will put fun little IDs in their chips like Intel.
  • Well. Isn't this interesting. An anonymous poster, *claiming* to work for Acer, *claiming* to have access to a K7 chip and the kinds of hardware that he writes about *claims* to have benchmarks claiming the Pentium III will outperform the K7.

    Well isn't this just *nice*. All scientific and wonderful. There's a problem, though, scientific studies are built on their ability to be *reproduced*. These results are not reproducable. No one has these systems. Furthermore the author has denied us even the oppertunity to contact him in order to find out what conditions the tests were undertaken as.

    People, think back a week ago to the Mindspring-Microsoft scandal. That was a well-published, well-documented study claiming that Microsoft was better than Linux. And you know something? It was hogwash. All of it.

    Benchmarks can just be affected *to* many ways for me to have much faith in well-documented tests. I *certainly* am not going to take the word of an anonymous test, no matter what he's waving about. Sorry, but I'll wait for the first real tests and take this as FUD.

    --Virtual Adept
  • Correct?
    I too have a 10.1 GB _IDE_ Deskstar by IBM.
    They never said there were no hard drives that were 10 GB. They said no _SCSI_ hard drives at 10GB:

    Harddisk IBM Ultra3 SCSI 6ms 10.0 GB

    And yours isn't an Ultra3 SCSI is it?
    :-)
    If it is, let me know where you got it so I can get one.

    ~unyun~
  • Xeons are so pricey, because everyone knows that the K6 FPU is pretty weak compared to the PPro-PIII. Intel knows this, and hundreds of IT professionals know this. And so you pay for it. I know alot of people who say that you shouldn't build a server on anything but an Intel processor (if your looking at the x86 architechture anyways). That might change with the K7, but until final silicon can be tested, Intel remains on top for now.
  • Why? Last year AMD had sale of something like 2.5 billion dollars. Last _quarter_, Motorola had sales of 7.2 billion. And Intel? 7.1 billion last quarter.

    x86 is a dying technology. Compaq knows it. Sun knows it. Motorola knows it. SGI should have known it.

    Why should Motorola purchase AMD and saddle itself with a potential liability. Don't get me wrong, I really like AMD. I own 2 AMD boxes myself. But I think it would be a mistake for Motorola to enter this market. The PowerPC 750 is a damn fine chip. With LinuxPPC picking up speed and OpenStep 5.3 (err....MacOS X Server) running on the PPC750, I think Motorola is making the right decision in bidding their time.

    Anytime you hear the Motorola is dropping the PowerPC, you can be sure that it is Intel FUD, pure and simple. Don't forget that Motorola virtually owns the embedded market and is making buckets of money that way.

He who has but four and spends five has no need for a wallet.

Working...