Please create an account to participate in the Slashdot moderation system


Forgot your password?

AMD Athlon (K7) Ships 208

Sir-Techlot writes "AMDs wed site has a page saying that the Athlon will be shipping today (6/23/99). Tells a bit of info we already know also. "
This discussion has been archived. No new comments can be posted.

AMD Athlon (K7) Ships

Comments Filter:
  • by Anonymous Coward
    Does anyone know what companies (Asus, Tyan, maybe) are producing Athlon compatible motherboards?

    Anyone know when the chips and boards will be available?

  • by Anonymous Coward
    I have not seen anything on their site, will it be possible (and when) to use Athlon in laptops? It seems to me that in this area (in which Intel is goind to make a big stress), AMD is lagging behind. Real competion in mobile CPU market (and falling prices!) is what I really want to see!

  • by Anonymous Coward
    Perhaps they think it is like the Alpha, which was manufactured by the Digital Equipment Corporation. That would make it the DEC-athlon!
    Okay, I should go to sleep now.
  • by Anonymous Coward
    The new Alphas and the AMD K7 share a bus format now, so that they can use the same motherboards. The new interface is called Slot-B. API is hoping that the K7's will sell well enough to drive the prices of the motherboards down, giving Alpha a cheap motherboard to provide their processor on (the lack of which has hurt them in the past), while AMD gets multiprocessor capability out of it, the lack of which has hurt *them* in the past. Intel owns the SMP protocol used in other x86 motherboards, and AMD could not use it in their processors. AMD defined its own multiprocessor specification, but they never convinced any motherboard manufacturer to build a motherboard to that specification. So while AMD processors were technicially capable of SMP, they were effectively confined to the single-processor (ie, low-end) market. But now they have an SMP specification *not* owned by Intel which motherboard manufacturers *are* willing to produce. So if the new systems sell well, both companies win.
    It was frustrating to see 533MHz 21164PC processors for $499, massively overpowering the most powerful x86 processors at the time, and for so much cheaper, but being stuck with the cheapest Alpha motherboard being the $300 164SX. The extra price of the motherboard ate up the price:performance benefit of going Alpha. If the low-end models of the Slot-B motherboards go for $100, and the new shrunk 21164PC (the low die area, low cost version of the previous generation Alpha) sells for $180 at 800MHz as it is rumored, then API will have all the ingredients for a completely hot shit $600 consumer PC.
    -- Guges --
  • by Anonymous Coward
    If you can get a DUAL 500 MHz for the same price ? I wonder if these are as overclockable as Celerons... 500->600 is only a 20% increase in clock frequency a lot less than 300->450 for the Celerons, which was a 50% increase.

    If the FPU is faster for DSP, graphics and games than Intel's I'll buy it, otherwise not. I'm tired of everyone saying how their processor beats Intel, I'm not going to buy it before some objective proof. Cyrix was always faster than Intel... Quake sucked on my Cx-PR150+, and it was fine on a P120.
  • Don't get me wrong, the K7 (Athlon) sounds like an incredible chip and is sure to make AMD some money, but is it enough to save the company? If you read AMD's press release today you know that they have larger than expected loses(200 million), so they need this chip be their cash cow. The problem is that they destroyed the market that they are shooting for with the K7(Computers between $1,299 & $2,599 USD) by selling those damned K6. The K6 (all the other low end chips) created a huge sub $1000 computer market. Why is the average consumer going to spend $2,000 for a machine when they(in their eyes) can get a compuer that does the same for under $600 from eMachines? They need to make a ton of money with this chip and I don't think the market is really there. They tried using the Christensen effect to beat Intel and it bit them in the ass. And I think Intel is looking more into the future by developing the advanced 0.13 micron technology and 300mm waffers(This will give them a cost saving of 30% alone). In the long term (3-5) Intel will win because AMD is spending all their resources (and then some) to beat Intel in the near term with their K7. Just my .02 cents. :)

  • by Anonymous Coward
    So does anyone know if anyone is paying attention to this on the Linux kernel development to get support for SMP working with the EV6 multiprocessor technologies? As I understand it, on the Intel architecture, only Intel's MP spec is supported. Does the Alpha port support this MP spec and would it be easy to port over to Intel arch?
  • by Anonymous Coward
    The answer's probably more complex than you'd like. For integer/pointer operations, the K7's supposed to be faster than the PIII at same clock rate. For floating-point it's supposed to be a little worse. On the *other* hand, the K7 will use PC133 SDRAMs and a 200MHz L3 cache, while the PIII will remain with the 100MHz memory bus for a while yet, and the K7 uses a memory bus twice as wide (128 bits) as the PIII's, *and* the K7 has larger caches and a larger TLB on top of it. So if you're looking at the system as a whole, the K7-based *systems* should outperform PIII-based *systems* hands-down. Even floatingpoint-intensive algorithms bang on the memory bus, and any weakness in the K7's floating point unit will be more than offset by the lower memory latency and higher memory bandwidth.
    -- Guges --
  • by Anonymous Coward on Thursday June 24, 1999 @02:34AM (#1835849)
    Err...a damned good one.

    First off, there's the 128k of L1 (4x that of every Intel P6, including the Xeon).

    But, of course, what you're implying here is that the K7 can't run with the Xeon because the Xeon has up to 2MB of L2-cache--very important for, well, server type stuff (big databases, etc.)--and, most ominously, it runs at the same speed as the CPU (for comparison, the PII/PIII has 512k running at half speed; the Celeron has only 128k but it's full speed...and they're about as fast at equal clock speeds, depending on what you're running).

    Well, the K7's that shipped today only have 512k of L2, and that only at half clock speed...

    However, AMD plans on shipping K7's with both half and full speed L2-caches, ranging in size from the aforementioned 512k all the way up to an absopositively humongous 8MB.


    Of course, it's gonna cost AMD a chunk of change to fab a chip with 8MB of full-speed L2-cache ( Wow ), but if you think they're gonna be tacking on the same exorbitant markups that Intel sticks on the Xeon (a PIII Xeon w/2MB L2 is $3400 at pricewatch)...well, I sorta doubt it.

    But, you may stammer, the Xeon is better for SMP?

    Hardly. The Xeon, while technically capable of up to 8-way SMP, only sells in 1, 2, and 4-way configurations so far (I think). 8-way K7's should be up and selling quite soon, and I've heard talk of a 16-way chipset. Oh, and if you're wondering why no one's bothered to make an 8-way Xeon box, it's because the communication between the chips in a multichip Xeon server has to go through the 100Mhz system bus; not only is 100Mhz not so fast, but adding chips means less bus bandwidth for everything else. Long story short, you don't get anywhere near linear performance gains by adding Xeons, and in fact an 8-way box might not be any faster than a 4-way. Luckily, the K7 fixes that little problem by providing a dedicated path for the chips to communicate to each other.

    So unless AMD has problems fabbing such massive caches, it looks as though the Xeon's in a bit of trouble...
  • i heard they were going to release SMP later? but when? :-)
    i ll be forced to go with intel for this summer! =(

  • HAHAHAHA...that was pretty funny.
  • Everything I'd read about the K7 was that it was designed from the ground up as a high clock rate chip. At first I thought this was pure marketing bunk...that all fast chips were "designed for high clock rates". More reading revealed I wasn't totally right. Basically, the chip was built to be more forgiving to higher clock rates, with higher cache latencies and the like. Sorry for my vagueness, but apparently the K6 was designed with minimum cache latency, making it do a lot per clock cycle, but at the same time making it very unforgiving to slight manufacturing defects and high speeds. So it looks like the K7 should be pretty o/c'able. Also dont forget that the later .25 um chips should be more oc'able, as they refine the fab process, and of course they should go through the roof when both of amd's fabs go .18u.
  • AMD supported OpenPIC with their K5 (as well as Cyrix with every 6x86 and M2 chip made), but dropped it in K6 for lack of mobo support. I'd imagine that the K7 uses OpenPIC as the multiprocessor protocol. AFAIK, OpenPIC has no limit on processors, or maybe it's 255. Anyway, the limit's more than you'll ever fit into a standard box. Of course that's the standard, and making an 8+ processor machine work may never be feasible.

    Another thing: the openPIC standard defined that the architecture had 255 IRQ's! Granted, they're not such a big deal today due to PCI and USB (heh), but back then (1994-1995), we were all fighting with ISA cards and conflicts. And a heavily loaded PC would run out of IRQ's damn fast.
  • you have to cool to be able to overclock or else the heat will crash it. FWIW one of the guys from Kyrotech died a few days later from alcohol poisoning due to overcelebration, which is a real bummer -- he will be missed
  • when the k6-3s were being announced i often could find mail order houses selling them for 30% less than the price given by AMD. i'm not all too sure how true this will hold with a high end chip like the k7(why a fakey name?).
  • all amd makes is the chip and a chipset, what you need to do is drop an email to your favorite motherboard maker letting them know your concern.
  • by vipw ( 228 )
    they would probably know
  • If AMD fails, let's look at the alternatives we'll have left, besides Intel:

    * Alphas - a viable alternative, and what my next investment will be if the K7....err.. Athlon doesn't work out.

    * Cyrix/IBM - low-end, nothing new from them.

    * IDT (Winchip) - low-end, nothing new.

    * Transmeta - nothing released yet.

    * Sun/HP/others - too expensive

    * PowerPC - requires purchase of an entire (usually mac) computer. Or is there a motherboard and CPU I can get separately?

    I do not 'hate' Intel (My current CPU is an Intel P200MMX), but an Intel only future for the majority of us is NOT rosy in my eyes.
  • With all of the pre-release (disappointing) K7 benchmarks floating out there I can hardly wait to get my hands on a K7 to test it thoroughly... AMD, are you listening?

    From the information released so far about its internal architecture it should be a scorcher, but only extensive testing will tell the real story.
  • Well, SMP motherboards tend to be noticably more expensive than UP boards. Many programs don't make good use of the second (third, fourth, etc...) processor. Some people will buy the 600 just to have the latest and greatest. And, of course, most people run Win9x "for the games", and it just doesn't support SMP.

    If I can find a reasonably priced dual board, that 500x2 option sounds real nice for a Linux box, though...

    And all the reliable speculation (as opposed to the "D00D! INT3L R00lZ AMD'Z A$$" stuff (and the converse)) I've seen indicates that this chip is going to be the "fastest x86 ever" that they bill it as...

    And, yeah, the Cyrices had their problems. My 6x86M2-233 will run neck-in-neck with a Celeron 333a doing kernel compiles (though some of that's probably just faster disks and stuff in the Cyrix box), but it gets its butt kicked at Quake and the like. Cyrix's FPU has always sucked big-time. They made a bet that office applications were going to be more important than games in the future, and they lost. They are good machines for a programmer who spends more time compiling than fragging, though.

    Another thing to keep in mind when comparing clock speeds is that the Cyrices are not clocked as fast as the number stamped on them seems to indicate... my "233" is a 200MHz processor, and your "150+" was, I believe, a 120MHz chip, so comparing a 150+ to a 120 is a fair comparison... comparing it to a 150MHz Pentium isn't, really. And there's no way to really compare on price... the most expensive Cyrices are so much cheaper than the cheapest Intels...
  • Posted by 2B||!2B:

    You're absolutely right!!! It's just like when Microsoft put a (paltry) sum into Apple to keep it alive.

    The company I'm surprised hasn't gotten into this deeper is IBM. They have both the capability and the deep pockets to compete head-to-head with Intel if they want to. It could still happen.
  • Posted by 2B||!2B:

    Athlon sounds like either a tennis shoe or an anti-fungus foot powder. But we forgive them if it rocks!
  • Posted by Lord Kano-The Gangster Of Love:

    Actually, licensing had nothing to do with it. AMD has an agreement with Intel not to use the "same technology" for a certain number of years.

    What I am hoping is that the K7 has some type of key or can on the outside of the cartridge so that a MB maker can design a MB that can recognize the difference between a K7 and a P2/3 and automatically switch it's voltage, et al.

  • Ok, I have couple little tidbits to share. First of all, those prices are really closer to what us resellers will be getting them at. Expect $25-50 more from a legit store. You can also exspect that price or probably less from the stores on pricewatch, because they are stolen or not manafactured of they dont deliver. I am not going to tell you where to buy your chips, but just look at the places on pricewatch. A 15 day warrantee? That is obviously not an authorized chip, all AMD chips come with a 3year manafactures warantee, same with Intel. Its no wonder they are cheaper then what us legit resellers can get from our distributors. So when you go out to buy your next chip think about whether you want to save a couple bucks or spend a little more to get a high quality and warenteed product.

    Also, comparing K7's to P3's is not realistic. The real comparison is closer to Xeons to K7. And the K7 is faster then any current Intel chip. The pricing is also cheap, considering that it was rumored to cost as much as Xeons do, in the thousands. So be happy.

    Anyway, thats all. Good Day.
  • The K7 is an x86 chip. As such, it is 32 bit.
    It has nothing in common with an alpha chip
    except the motherboard it uses. A sparc or
    ppc kernel would do you as much good on a K7
    as an alpha kernel would (i.e. none).
  • Begin Transmission: Stop waiting for the K7... stop.

    Find Motherboards now! stop.

    Over and out

  • by substrate ( 2628 ) on Wednesday June 23, 1999 @05:57PM (#1835869)
    If I ever quit my present job and work on microprocessor circuits I'll do my best to kill names like Pentium or Celeron or Athlon and stuff. They all sound either very similar or just aren't very beefy sounding. They sound like they're picked by focus groups. I hate focus groups.

    Instead I'll pick names that are more in your face, much like 60's and 70's sports cars. These chips are powerful and they suck up as much power as old sports cars suck up gas. They deserve names with guts. Names like the Vindicator, maybe with performance specs right in the title, the way sports cars used to proudly display their number of cylinders and engine displacement. The Vindicator 128 1 gig.

    Forget dancing femme-boys in gold lame bunny suits, open up a early 70's Popular Mechanics sometime. Thats how advertising should be. Scantily clad girls draped across the vehicle. Chips are small, there won't be any draping across them. Maybe a gorgeous blonde in a string bikini. The camera pans in to her feet and slowly makes its way up her body. Caressing every last inch of her perfect legs and thighs. Just above the bikini line is the chip. Slowly the camera zooms and focuses in on the chip and its name. The Vindicator 128 1 gig. Fade out. No text, no boring announcers. Maybe the wa-wa guitar track from a porno flick. The viewer knows if he buys one of these babies he's getting some!

    Ah well, maybe not. The management didn't think adding tesla coils, jacobs ladders and a full height lava lamp to our big servers was a good idea. Even after I explained the concept of retro-computing.

  • From my mail to AMD:

    Just a quick note on the new name for the K7 processor -- Ugh! One of the many things I liked about AMD was the focus on giving better performance at less cost. Part of this was the avoidance of silly marketing techniques such as the use of a semi-random conglomeration of masculine phonemes as a product name. By choosing "Athlon" you have clearly identified your product as a Pentium-Merced-Celeron knockoff. (Besides, why would you want a name that has connotations of scrawny marathon runners?) The notion that it's easier to differentiate the "Athlon" processor generation from the "K6" as opposed to "K7" from "K6" is pure goofiness. I hope that you continue to use "K7" (at least as a subtitle) in your marketing and sales, and I look forward to the K8.

    I'll buy one (esp at those great prices!), but I don't think I'll be putting an "Athlon Inside" sticker on my case anytime soon...
  • I don't understand why everyone is so excited. We already have Alphas that are far faster than this, and have better price/performance in the high end. x86 is outdated, outmoded, and deserves to die. Why not use something better? Alphas are cost-effective and fast. There are also fast Sparcs, but they're more expensive so I can understand the resistance there.
  • I am not surprised that AMD decided not to sell this chip as the "K7". Why? Simple: they think that they really have something on their hands this time around. They want a trademarkable name to prevent anyone from trying to make "knock-off" K7's! This is exactly the reason that Intel called the 586 the "Pentium" -- so that AMD and Cyrix couldn't sell their designs with the same name. Intel tried to trademark "586", but the courts said that it was too generic to own. I expect that "K7" is no different.

    So AMD now thinks that, with this chip, they can crawl out from under Intel, and become a dominant player. So dominant, that they fear AMD clones.

    What happens when the clones get cloned?
    --Lenny (who likes AMD)
  • So the K7 is faster then the Xeon at SPECint, and much faster for SPECfp. When multi-processor chipsets come out it will in all likelyhood be far faster then the MP Xeon (thanks to DECs point to point "bus" design). The K7 can eventually beat the Xeon's L2 cache size and match the speed (note that the SPEC numbers are better with a worse L2 cache, I assume due to the far better L1 cache, and a more agressave OOO engine).

    So far things are better for AMD then I recall them ever being. However each time AMD had a CPU that could threaten Intel they have had problems making enough of them. Will things really be better this time?

    From reading AMDs press release there are a few clues. They will not be selling their CPUs at a fixed discount from the similar Intel ones. They listed a bunch of reasons, but I susspect a big one is they will adjust price to reflect yeild. They also keep talking about the K7 gunning for the high-end market (after all the K6 will not be discontinued for quite some time!). The profit per chip is far higher there, fewer chips will have to be sold to earn the big bucks.

    The downside of corse is many K7 systems won't be signifigantly cheeper then the Intel Xenon systems (or so I assume). We may even see the MP K7 systems costing more then the Xenon, after all it will in all likelyhood be a much faster beast.

    The upside is Intel may be forced to cut Xenon prices, and in any even when Intel starts beating the K7 there will be more price cuts (and AMD's new fab plant may help them manage volume shipments for once)

  • The K7 is nothing for the $2500-systems, its for BIG $x0.000-systems. It for places, where money doesn`t count. A single high-end-K7 will cost several thousand dollars alone.
  • This probably refers to the use of processor cartridges, like the Pentium II and III have. Meanwhile, Intel is moving its processors back to sockets...
  • This has nothing to do with ATX. I have an ATX power supply with a mains power socket for the monitor.
  • intel also has to make money and they're not doing it with the celerons. They make money off the xeons and now that's where AMD is heading
  • > A 15 day warrantee? That is obviously not an
    > authorized chip, all AMD chips come with a 3year > manafactures warantee, same with Intel. Its no
    > wonder they are cheaper then what us legit
    > resellers can get from our distributors.

    Huh? The 15 and 30 day warranties are for OEM chips bought in bulk from chip brokers. The idea is that AMD (or Intel, or Samsung, whoever) will sell you a chip with no packaging, very little warranty, and no support for a discounted rate. The 3 year warranty is for AMD boxed retail only. There is a 1 year warranty for end-users who buy direct from AMD, and a 30 day OEM.

    This is standard practice in the wholesale computer parts business. And it is perfectly legit. You just have to buy in bulk and have the right suppliers, not Ingram Micro..


  • This doesn't make any sense to me. If you lower the resistance in the chip, it still has to change states based on the clock signal. Just because the chip is more efficient doesn't mean that an instruction that executes in three clocks is going to start executing in two. You still have to run the chip at the faster speed, which is essentially "overclocking" (since the chip isn't specified to run at that speed).
  • They were just thinking ahead. If this chip was the K7, the next one would be the K8. And what about the chip after that? It would have to be called the K9. Insert your own joke here.
  • Well, they need a name so they can put a trademark on it. If you notice, every time AMD says Athlon, they put TM all over the place. Plus they wanted to make this CPU sound different. Call it what you want, but Athlon should be fine.
  • Well, Cyrotek demoed a 1GHz k7 a month or 2 ago. IIRC it was just done by cooling the chip, no actual overclocking needed. I beleve that the way the K7's are made, simply cooling them down speeds them up. At the time, people thought that they had done it by using a K7/700. so overclocking a 500 to a 600 isn't all that impresive if you can do a 700 -> 1000. Mmmm 1Ghz.
  • Why stop there... according to the FAQ, 4 and 8 processor systems are in the work, and they didn't say it has a max of 8, they hinted that it may be able to handle more... SMP is not dependent on the CPU, it is in the chipset. But then I guess, even though PIII's are capable of two CPU's by their pinouts, higher Pentium processor machines are also being designed from chipset support... So I guess not much has changed. I just expect that the K7 will have better SMP support and a better design based on the bus architecture, but I guess I will have to wait for these MB's to develop... :/ Damn it, I thought I had a really good point to make, but I seem to be countering my good arguments... Don't you hate it when you argue with yourself and lose.


    Time flies like an arrow;
  • No, they're actually talking about cache prefetch instructions, also known as streaming memory instructions. When you know that you need something from main memory in about 30 or 40 cycles, you prefetch it, which means that when you get to the part where you need the data, you don't stall those big pipelines. I don't think AMD is trying to claim that the K7^H^H Athlon makes the internet come alive like Intel claims ... it's just some new instructions that help to mask main memory latency. Nice stuff, Intel has it in SSE, which may be the reason for the reference to the Intel marketing campaign. And yes, AMD's marketing department needs help.
  • I'm just hoping that you were ... ummm, being humourous in the above post. (It's hard to tell sometimes around here.) In case you weren't:

    1) The K6-3 is approximately equivalent to a same-clock *Xeon* on 32-bit integer code. Floating-point? Not a chance, but what does a file server care about floating point?

    2) I've *easily* run 30 people off of a K6-266 running Linux/Samba. The machine didn't even really get warm, much less break a sweat. Load average was about 0.1 most days, and while these weren't software developers, they weren't watching their screensavers all day, either. Anything over 200Mhz for a fileserver is a genuine waste unless you have a serious disk subsystem and a well-built high-speed network.

    So, either I need to get a sense of humor or you need to get a clue. :)
  • The word is that the chip only goes to OEMs for a while -- you'll have to buy a whole computer with an Athlon inside for the near future. Those whole systems start shipping in August (?), and it'll be some time after that before the CPUs and motherboards make it to the retail channel. Sorry -- I wish they were here sooner, too.
  • The simple answer: K7 (Athlon). Far and away.

    The real figures are about 12% faster in SpecInt95, and about 50% faster in SpecFP95. That's comparing a P3-550 versus an Athlon-550. For the P3 Xeon-550, the Athlon beats it by about 5% in integer, and 40% in floating point.

    If you want the full Athlon story, go to JC's page []. More Athlon info than you ever wanted to know, including the above spec numbers and where they were obtained.
  • The K7 is a home user and server chip. Basicially the home user chip will have the lowest amount of cache and speed of the cache. The server chips will have a few megs of cache at faster speeds. Similar to Intel's strategy witht he Xeon and PII.

  • Oh come on! ATX cases are great . . . . And it's not like they're all that expensive. You can get fairly nice mid towers in the $30 range.
  • I've been looking on both Anandtech and Tom's Hardware for any article relating to the K7 being compatible with alpha boards and vice versa. Is this just rumors or is it true? Any articles relating to this? I know that they share the same bus, but as far as I know alphas arn't slots but socket chips (but I could be wrong).

  • The management didn't think adding tesla coils, jacobs ladders and a full height lava lamp to our big servers was a good idea. Even after I explained the concept of retro-computing.

    Jacob's ladder? Is that the "bzzzt" thing?

    Mmmm. Now that's a real computer. Where can I buy one? Does it also come with programming that goes wrong so it falls in love with its creator and tries to take over the world?
    Consciousness is not what it thinks it is
    Thought exists only as an abstraction

  • As far as I'm aware, it should already be fairly close, as EV6 was originally used for Alphas - and the Linux kernel supports Alpha SMP.

    Of course, the chipset is different, so it might take a little while to get a working kernel, but don't be surprised if it's available before you actually see an K7 SMP system.

  • If so, tell me please, where exactly Linux is so eager to use FP?

    The GIMPS [] (Great Internet Mersenne Prime Search) software will stress the FPU and main memory bus. It was very carefully coded in assembler by George Woltman to run at high speed on a Intel CPU. It is an excellent stress/reliability test. If anything is flakey/marginal on your system, you will usually find out about it very quickly.

  • Oh yeah? What sort of cache does the K7 have?

    (There's a reason that the old Pro-200s can out benchmark a standard Pentium III. Of course, it depends if you are running Quake or databases)

  • IBM's attempt to take on Microsoft - OS/2

    IBM's attempt to take on Intel - PowerPersonal/PReP.

    'Nuff Said.


  • Everyone seems to be speculating that K7 motherboards will accept Alphas without much problem. But there's actually a big problem - the Alpha uses a completely different BIOS/Firmware than a standard x86. (Doesn't the Alpha firmware have an 8086 emulator built-in in order to initialize ISA cards?)

    I don't know what the cost or technical difficulties of a duel/swappable BIOS would be, but imagine that there's enough trouble there so that a you-pick Alpha/K7 board is not going to become a commodity item.

    During the Phoenix-is-putting-ads-in-the-boot-sequence discussion, a guy from Dell's BIoS division posted, and his point was that creating a BIOS for a specific board is not an easy task. Considering that Alpha is essentially a workstation/server OS, the market could and probably will continue to bear the extra couple hundred bucks.

  • I guess my point was not that it was difficult/impossible, just unlikely in the low-end motherboard market.

    Merged firmware would be great though - I would love an x86 PC with a real boot firmware setup. Once you start adding lots of controllers and drives, the over-extended PC BIOS starts showing it's age.


  • I'm not stammering - I was just pointing out that Xeon (big L2) verus K7 (small L2) is an illegitmate comparision, because folks usually pay the big bucks for Xeons to get the big L2.

    A K7 will a large L2 and SMP support is certainly welcome here. Those Xeons are too damn expensive.
  • I don't think consumers are getting the point. Each piece of equipment only holds the value of it's usability. I specifically love Linux for it's ability to breathe new life into older equipment. I've also got an AMD-K6-2 350 running linux, and i am very impressed. If AMD can beat Intel's performance pound-for-pound for a FRACTION of the price...well, nuff said.

    Oh yeah...when's the last time you rebooted? :)

  • does anyone know where i can get some info on optimizing for this processor? also, i'd like to know what these new integer instructions are in 3DNow.
  • Intel has been leadin the chip industry for too much time to just disappear.
  • You as a "technical" person should know that the K7 doesnt USE 200mhz RAM. The system bus runs at 100mhz, but the chip itself runs it's own mini-bus at 200mhz. This results in a much faster pipelining and betting communication with the memory bus than traditional architectures. Similar to the Kensington Quickchips that have their own on-chip multipliers and such so you can stick a 300mhz chip into a 66mhz motherboard with a 3.5 multiplier and still end up with 300mhz. If you compare these to the G3/G4 and Alpha's you're going to be sorely disappointed. G3's and Alphas are both RISC and the Alpha is a full 64bit chip, so it's naturally goingto perform tasks faster than an x86 chip. In most environments the bottom line IS the price tag, get a clue. It's all about price tag whenever you're buying for your company and even for your home computers unless you're one of those "independantly wealthy" people. Real technical users get paid to make logical descisions which will benefit their employer or themselves to the fullest, not to rant because they found a keybaord on their desk.
  • Geez, I'm sick of all this bitching about the K7's release schedule. Dammit people, they are in competition with one of the biggest microprocessor production companies on this planet, they manufacture several lines of chips in a single fabrication facility, not to mention trying to build a new processor from scratch and not just improving parts of an existing model. They have a hard road ahead of them, they are building their second factory right now, releasing a brand new processor, and facing the brunt of market fluctuations. I think they are doing very well in the face of adversity.

    It also pisses me off when I see posts that are so anti-intel that they are nearly bursting with energy to rant. The next time you want to rant about Intel, count to ten, turn your computer off, and walk away. Who cares if Intel makes their chips expensive, don't buy them, you have that ability. Stop being anti-everything monkeys, it just makes you closed minded. Intel has advantages and so does AMD, use whatever works best for your situation or your checkbook. Making up your mind to like one company or one product makes you overlook anything produced by another company, even if it is a better product. Think before you rant.

  • the EV6 is a point to point bus, unlike the bus used by intel. this means that while the processor can run at 200MHz, the ram is not required to, so the only thing that matters is what speed of ram the bios supports (eg. 100 or 133 or whatever). this also affects things like the pci and agp bus too: they are independent from the FSB, and run at whatever speed the chipset allows.

    someone correct me if i'm wrong about anything.
  • Well, jeez... I REALLY, REALLY want one of these to replace my aging P-II 333. I wonder if my boss would buy me one? [Tongue heavily in cheek, as I work for Intel.]
    On a [slightly] more serious note: What does this say for Intel that the K7... er... Athlon, is supposedly (can't wait for real world benchmarks) faster than an equal megahertz Pentium 3, that it's available in higher megahertz, and it's cheaper (at higher megahertz) than the Pentium 3? Hmmm... Maybe I should change employers to AMD?
  • Anyone have any idea on whether AMD and Alpha might merge the way PA-RISC and IA did? Would this be technologically and economically feasible/practical? The use of a motherboard standard between the two is interesting.

  • I doubt AMD is going to be able to borrow Intel's specs for the new 64-bit architecture soon, at any rate.

  • It has to do with AMD competing with Intel for the high-end x86 market. In the near future, this would include a 64-bit chip.

  • That's what I'm talking about. the IA-64 will be Intel's next-gen of high-performance chips. It only seems logical that AMD would want to do the same thing.

  • The company also says it is confident that it has an outstanding product lineup for the second half of 1999, including a new series of chipsets designed to capitalize on the power of the new Intel Pentium III line of products.

    Don't you mean "the Company"? Am I correct in guessing that this AC works for Intel?

    You sound like a marketroid even when you appear to be trying not to. ugh...Salescritters.


  • ??? Pricewatch has the P-III 550 at $702 (limit one per customer) and the 500 at $442. As someone already mentioned, there isn't a P-III 600 yet.


  • Assuming the entire chip operates synchronously (meaning every circuit depends entirely on the clock), you would be correct. But I've always had the notion that asynchronous circuit design, even with its major pitfalls, has the potential to work slightly faster than synchronous circuits. If AMD has been able to harness asynchronous circuits at extremely high speed then it would make perfect sense that the processor would operate faster internally. The external bus speed, however, would remain unchanged.
  • What does the Alpha have to do with any of Intel's internal specs?
  • You can also exspect that price or probably less from the stores on pricewatch, because they are stolen or not manafactured of they dont deliver. I am not going to tell you where to buy your chips, but just look at the places on pricewatch. A 15 day warrantee? That is obviously not an authorized chip, all AMD chips come with a 3year manafactures warantee, same with Intel

    Well, a 3 year warranty if you buy a *retail* version, not an OEM version. With a retail version, it's a boxed set, with fan, IIRC. OEM, you get the chip on a piece of foam to protect the pins. Nothing else. That's why it's so cheap. And it's not grey market, or stolen. It's perfectly legit.
  • The new Alphas and the AMD K7 share a bus format now, so that they can use the same motherboards. The new interface is called Slot-B.

    No, no, no. The K7 is going to be using a new interface called Slot A. You won't be able to interchange a K7 and an Alpha. Besides, like it's been said, these are two separate architectures: Alpha (RISC-based, 64 bit) vs. x86 (CISC-based, 32 bit). Not gonna be interchangable.
  • I'm gonna go out on a limb here, but I think that it wouldn't be terribly hard to do a dual-arch boot prom w/an x86 bios emulater.
    All you would have to do is put the x86 bootstrap code at the correct address (ffffh:0000h (or ffff0h linear), I believe), then have the Alpha bootstrap code at another address (prolly down low, below 2000h linear). they already are going to make boot prom's for both arch's for each high-end board (that's most of the point behind k7 using ev6, and alpha going to slot-B), so why not just put in a hack to make both work?
    As far as the firmware, I don't know. AFAIK, they are going to merge the two, such that they only need one set for both cpu's. Of course, that's pure rumor on my part, so...

    Anyone who would know want to blow some holes in this one?

    -- ioctl()
  • In every aspect of speed, the answer is the K7. I haven't found this out first hand yet, but I think it's safe to say this as of right now.
  • by nd ( 20186 ) <nacase AT gmail DOT com> on Wednesday June 23, 1999 @03:35PM (#1835921) Homepage
    Check out the prices, they aren't half bad.

    600mhz - $699
    550mhz - $479
    500mhz - $324

    Also, from browsing the AMD website, I came across this K7 FAQ []. It's actually pretty interesting and gives some new information.
  • Great to see that some people still have faith in the little guy!

    GO GO GADGET K7 chip!
  • as far as i know, my pII-300 compiles 2.2.4 in 150 seconds (although the configuration is rather simplistic). no compile ever took longer than three minutes. i would assume K6-III 500 would do it in less than half as long. after all it is 2/3 faster and interger operations are actually faster on AMD's. Slightly but the difference is there.

    can't wait for k7!

  • More like 500 $500, 600 non-existent. Considering that K7s kill the PIII at the same clock speed, they're practically giving these things away. Really, the K7 is priced absurdly low.
  • First of all, it's Kryotech (OK, minor detail. But seeing "Cyrotek" really, really bugged me.). Second of all, it's not because of "the way the K7's are made", it's because of the way any piece of silicon is made. We are talking about extreme cooling, not just lowering the temp by a couple degrees. The Kryotech system cools the K7 to -40 degrees C, which is enough to actually lower the electrical resistance. This is not the same thing as overclocking. Overclockers stick big heat sinks on their processors to combat the extra heat produced by the overclocked chip. Kryotech lowers the resistance within the processor to allow it to run at a higher speed with no side effects. This might sound like a technicality, but it isn't. The practical difference is that overclocked systems suffer from electromigration (the process in which an overclocked processor slowly decays, leading to premature failures) even if they are properly cooled, while the Kryotech system does not. It is every bit as stable as the processor it was based on, if not more so (afterall, -40 degrees is overkill for simply removing heat).
  • I heard that the initial motherboard maker will be Asus, Gigabyte, MSI, FIC, and Biostar. Of course, others will start making them later on. And the K7 is compatable with newer Alpha motherboards, if you have a lot of money burning a hole in your pocket.
  • Check out the Athlon logo. There is the number 7 hidden in it. Seems like an AMD artist wanted to send a message.
  • by Upsilon ( 21920 ) on Wednesday June 23, 1999 @05:37PM (#1835928)
    Actually, that huge loss wasn't due so much to lowered revenues as it was due to them spending so much money preparing for the K7. And that loss does not even take into account the fact that they sold their Vantis division for $500 million.

    Sure, it looks bad right now. But Q3 will show a huge change. They will go from a $60 ASP to charging $500 and more for their processors. Now, if they were able to make a profit with an ASP below $100 (which they did for the last couple quarters of 98), think about what they can do with that kind of ASP. Also, their Dresden facility is nearly complete (should be online this year, but I don't know if it will be in Q3 or Q4), so they will finally be able to acheive some real volumes. Their .18 process in on schedule, and the K7 is really getting some promising press. Even Dell will be making K7 systems. In case you don't know, Dell is currently the only one of the top 10 PC manufacturers that doesn't use AMD chips in at least some of their systems.

    Sure, there is less demand for high-end systems. But there is certainly still enough demand to sustain a company. Especially since AMD is so much smaller than intel, they can sell everything they make to this market. And the K7 is really a bargain anyway. I don't think lack of demand will be a problem for the K7 at all.


  • What 64-bit x86 chip are you talking about? IA64 (the Intel/HP design for Merced and Mckinley) is NOTHING like x86. And, as far as I know, Willamette will still be a 32-bit chip -- just faster. It will probably also be the end of the x86 line...thank god!
  • Think about it: Intel has already had a few run-ins with feds because they appear to be monopolistic. If AMD starts to REALLY get in trouble, the feds will probably make Intel give up some of their .13 micron technology so prevent Intel and HP from owning the market.

    Also, I seriouly doubt that AMD is unaware of the their predicament. That hefty lost figure probably includes a substantial amount of research on next-next generation technologies. Sure, AMD doesn't have a lot of money to work with, but their investors are probably much more willing to pay out their asses to make AMD profitably *eventually* rather than take a big loss because of myopia.

    Besides, Intel should be the least of AMDs worries. With companies like Rise and Transmeta focusing a LOT of effort on nextGen chips, they'd better find a market soon. Oh, and if you think Torvalds is Transmeta's star, you should take notice of who else they're hiring -- they seem to be plucking the most promising post-docs from the best universities faster than you can say "DAMN!"

  • I was talking about stability of the whole architecture (CPU + Motherboard/chipset + Video card combination) FOR 3D Gaming. All I was saying was this new untested combo might not perform at its best during the first 8 omnths or so, because there is lots of work that has to be done on chipset side and drivers side to make this work well for 3D gaming (K6-2 optimized RivaTNT video drivers shipped only a month ago, although the card existed for a while already), heck even the software developers might have to do K7 specific tweaks to for better performance, better compilers, etc ..
  • If you play games a lot, don't buy K7 now.. Why?
    Because there is no a tested motherboard and chipset for it, you are not guaranteed that your prefered 3D video card will work without crashes.

    Don't get me wrong. I talk from experience. When the first super 7 (socket) motherboards appeared they were as unstable as hell at doing 3D stuff. They supported AGP but once you pushed them hard the system would just freeze or your game would not run. It took about a year of waiting until decent Super 7 motherboards apperared that would actually work with AGP 3D accellerators without your game/system freezing. Even right now, Super7 motherboards still have issues with my latest and fastest 3D cards. Even at faster CPU clocks speeds
    AMD would systems would get lower fps than Celeron systems while both using the same TNT video card.

    But if you don't play a lot I guess it is a nice number cruncher for server or compiling kernels...
  • The K7 is finally out. This is great news. I was going to buy a K6-3 but decieded to wait for the K7 because it was so close.

    But the question now is: When do we see good motherboards with decent chipsets? Until then, the CPU is pretty much worthless to me.

    Any thoughts?

  • I read that the chips rated at higher clock speeds come from the better part of the silicon wafers (the middle I think). But there is no difference in cost for the manufacturing, so such a dramatic price increase really isn't justified.
  • Yeah, but let's keep one thing in mind: where does that high-end system demand come from? That's right: corporations. Big ones. We're talking Fortune 500 here. And who do you think corporations are going to trust with their mission-critical IT needs? AMD? It's sad, but AMD has NO presence in the corporate world and coming out with the Athlon isn't going to suddenly , magically make them the right choice for high-performance computing in your CIO's eyes. As a system administrator I've borne witness to the results of the reprehensible testing/burn practices AMD uses just to get as much out the door as possible. Believe it or not, but CIO's know about this as well. Plus there's the PHB "big name" factor--"AMD? Who's that? Just buy the Intel chips!". Yeah, I'm sure Intel probably knows that the K7's a better than anything they've got performance-wise, but if I were them I wouldn't worry since AMD has never been able to produce reliably at large quantities and they don't advertise worth sh*t. But I guess we'll see one way or the other, right?
  • wouldn't that be i786?
  • I hate to burst your bubble, but those prices are for a lot of 1000. Individual processors will be pricier than that.
  • The Athlon won't be in notebooks untill the begining of next year...or so I have heard.
  • So they are planing on Q3 roll out. Well, 7 more days and Q3 will be here. But, Q3 also lasts 3 months >:(

    Anyone have a guess when the home tweaker can get one? I love to get one just to play with it.

    "It is dangerous to be right when the government is wrong." - Voltaire

  • But AMD hasn't got any Athlon tech docs up yet. When they do show up, they'll probably be here [].

    BTW: Looks like Athlon will just have the standard 3DNow! instruction set. No "Athlon New Instructions" ;) So check out the 3DNow! manual [] while you're waiting for the Athlon docs.

  • its x86.. i mean linux may not be totally optimized for the 3 fp units, but it'll still run
  • AMD's FAQ says:

    The AMD Athlon processor is a totally new architecture and system platform demanding a new set of thermal and electrical specifications and enclosure requirements to match its leading-edge performance capabilities.

    Does this mean that standard cases won't provide enough cooling? Or does "enclosure" mean something else?


    Ok. I'm better now. I've heard that there will be some delay on the dual K7, I guess I'll just have to wait to get me a Dual-Athlon...or, should that be a Bi-Athlon?

    Can they hook it directly into my brain like Intel did with Homer Simpson? I'd like that!

  • Definitely an x86 class machine. Because of this I doubt it would work in an alpha motherboard especially since it is using a "Slot A" format for the processor. (Aren't Alpha's still traditional chips?) EV6 is refering to the bus protocol that the processor uses; the rest of the motherboard probably still has to look like an x86 motherboard.
    (I'm not entirely sure about this, so someone please correct me if you know for sure that it will run on an alpha motherboard, but looking at the differences between the architectures it would seem unlikely that it would just work.)

The party adjourned to a hot tub, yes. Fully clothed, I might add. -- IBM employee, testifying in California State Supreme Court