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


Forgot your password?

AMD Thunderbird And Duron Set For June Launch 158

Chris Tom writes: "Mark Hachman has an article up on EBNS discussing the AMD Thunderbird and Duron. Topics include release date, die size, performance, and positioning against Intel's CPU offerings. The Thunderbird and Duron will both include on-die L2 cache. "
This discussion has been archived. No new comments can be posted.

AMD Thunderbird and Duron Set For June Launch

Comments Filter:
  • Can anyone with inside information explain to me the reasoning behind the Duron's cache setup? It just seems that having an L2 cache smaller than the L1 cache wouldn't increase performance much over L1 with no L2 cache, while it does increase die size. Is there a reason why 64/64/64 was chosen over 64/64/0 or 32/32/128?
  • That would kick ass. Too bad it is so expensive right now. Hopefully, if there is enough demand for it, Compaq would be able to drop the price on it.
  • That's because he's writing the games in quickbasic
  • Because mostly what it demonstrates is the benefit of the MicroQuill heap. ;-)
  • Compared to the Celeron which has 128K of L2. But half of it is just the same stuff that's in L1. So basically its 64K of L1, and 64K of L2. The Duron has 128K of exclusive L1 cache, and 64K of exclusive L2. Almost like 192K of L1. Mmmm.
  • Dell's argument about the supply chain is laughable at this point. Over the past year we've had i820 delays, i820 bugs, i820 bugs again causing a recall, processor delays (although generally speaking not critical ones), and processor shortages from Intel. From AMD we've had... a lot of CPU's! ;-) Admittedly their Irongate Chipset has been far from ideal, but once you throw VIA into the mix, things look a lot better.

    Seriously, AMD's record over the past decade hasn't been great, but over the last year it appears to be much better than Intel's. If supply was really the issue I'd think at this point Dell would have taken the initiative and dabbled a bit with AMD (nobody says you have to commit your entire product line to AMD chips).
  • by Anonymous Coward
    Your problem was you bought a gateway
  • Not to mention they are selling the decrepit 66Mhz bus. Obviously to avoid competing with their own products. Hmph.

    Go AMD, Fight, Win.

    I don't think AMD is our savior from Intel, but they will at least light the fire under the microprocessor industry to get their asses in gear and get us the good stuff, instead of slowly dribbling out technology to keep us paying the big bucks for each new piddly advance.

    I want 1.5Ghz processors, with 256K of L1 cache, 512K of exclusive L2 cache, 200 Mhz DDR system buses, with stable chipsets, and I WANT THEM NOW.

  • To keep the Celeron out of the P3's territory.

    Plain and simple.
  • It sickens me how many times this joke was made in this and the last Duron article threads.

    And yet, it's still funny. I laughed.
  • Oh, you mean like WinStar []? Who the fuck are they?

    Their name implies that they have something to do with Windows (or a minivan), they use a logo image reminiscent of a Macintosh Meta key, and they had an ad that looked like a Dodge commercial... I'm not sure if any of those things are nearly as bad as the term they are so proud to have coined: "e.conomy"...


  • "Make the internet come alive."

    From an Intel commercial. How amusingly.. er, amusing.
  • Aw lay off. If we wanted serious, we'd go to Tom's or Ars. This is just too good an opportunity to poke fun.

    Heh, I said poke.

  • At that point AMD Mustang will be out

    What is this? Is that the real name of the chip? It sounds like AMD has some special relationship with Ford...

    -- Dr. Eldarion --
    It's not what it is, it's something else.
  • by Signal 11 ( 7608 ) on Friday May 19, 2000 @09:51AM (#1060671)
    Personally, I think AMD is leaving out a critical piece of information - silicon is running out of time. Various experts agree that within a decade, silicon will reach the end of its usable lifespan - we can only go so small. This is why I think AMD has secretly started moving to Latex based CPUs. I mean, think about it - it's available at lower cost than silicon, and for wearable computers it is simply great. I mean, imagine how many gigabites per second this thing can achieve. What's even better, nobody will squabble about the die size of the newer latex-based CPUs - afterall, size matters. In addition, this may finally solve the issue of unsafe hex which has caused numerous virus outbreaks across the country - an estimated $10 billion in damage.

    AMD is keeping the wraps on this new processor for a reason, and I bet this is it.

  • Thanks for the insightful information! (^_^)

    At least now I know there will be Socket A motherboards available when the "Thunderbird" Athlon ships in June. I didn't want a repeat of last August when CPU's were easy to come by but motherboards were hard to come by.
  • IMHO, AMD is doing a remarkable job at keeping on top of Intel. Except for one thing. You (not that I know of anyways) Cant do SMP with Athlons. But you can with P3's and P2's etc... Right now Im running a Dual p3 550E System. And I do alot of computational junk (what i really mean is I do alot of compiling and MP3 Encoding at the same time) And Im willing to bet My System will make the Athlon 1ghz look like Eniac at those tasks. However Games would be really really sweet.
    Im not aware of how A 1ghz Athlon stands up to Intel based systems but Id be interested to see how they handle against SMP based machines (By the way the p3 550E set up cost me about 500 Dollars, A 1ghz Athlon is around 800 for hte chip... ANd I belive that price is a little low.)
    If anyone knows of anhthing that pertains to this chime on in.
  • First, Intel with its bizarre names: Pentium. Celeron. Now AMD with Althon and Duron? What's next?

    The AMD Enduron? Or perhaps the AMD Marathlon?

    The Intel Vegetron?
    The Intel SafeSexium?

    The mind boggles.
  • I'm sure that if the Allies could have bombed Germany with 'vettes they would have ;)

    (it would certainly _look_ neat)
  • "The Thetans are attacking! Quick, Dr. Org, activate the Elron(tm)* processors!"

    (Elron(TM) processors no longer available on E-Bay.)
  • Actually, it's quite the opposite. I pick what processor I want, and what price I want to pay for it, and then I wait for it to hit that price.

    I usually buy processors at around $150.00. It's a little high compared to the low end, but it's still high enough that I can feel close to the bleeding edge.
  • Speaking of Corel Office 2000, there are two HUGE patches on the internet that make it run very well. One is about 50 meg, the other one I think is 62 meg. It has some major bugs that are fixed with these patches.
  • I got those. Thanks to the big one, Quattro pro will now open, though not if you have Eudora open at the same time. Celeron 466, 128MB RAM. That app just doesn't play nice with others.

    You Know You've Been Watching Too Much Ranma 1/2 When...
  • Okay...well...come over to engineering sometime and ask one of us if we think AMD is stable... You might be surprised (from your comment) about what you'll find out. We haven't had an quarterly meeting yet where someone has said lets talk about AMD.... and stability hasn't been the deterring factor for a while.

  • After the Thunderbird, it's only logical that AMD will announce the "Ripple Chip"
  • by paitre ( 32242 ) on Friday May 19, 2000 @09:56AM (#1060682) Journal
    Keep in mind that the ondie L2 is -exclusive-, meanign that the data in it will -not- be the same data that is in the L1 (and possibly the L3).
    This increases performance because it gives almost the same performance as having 192K of L1.

    Pretty damn neat.
  • Intel will now say:

    "Only a real prick uses Duron"

  • Actually Elron is a pretty cool name. Reminds me of Elrond from Lord of the Rings.

  • Do you know someone manufacturing one of these?

    I could really use an ATA/66 transporter room controller card with 128MB of DDR Molecular Pattern Buffers. I'm planning on building a low-middle end intergalatic starship on a budget.

    Or do I need to buy a special motherboard?

  • I think there's a couple of things going here:
    • every little bit counts anyway
    • more associativity - think of L2 as being a way to extend the low associativity of L1
  • I'll second that. I checked the specs and they say ATLEAST a 250w power supply. I bought a 300w and have had little difficulty with the GeForce card. Now, it DOES randomly crash sometimes, but I believe this is due to my overclocking the board - it is perfectly stable at it's "normal" 700 rating. So all this means is the card is running near or at its limit.. which I already knew.
  • Will this really be competitive with Celeron and will the Durons be as finicky with memory as Athons???
  • The Duron is likely to take over from the celeron, but it would be so much better if they worked in SMP. I know AMD is working on a SMP chipset, but I hope they don't do an Intel and only make later steppings SMP compliant.

    On another point the L2 cache on the Duron seems a little small and I'm concerned it will impact performance. It's not like AMD to make a mistake, but I guess we won't know until some benchmarks appear for the final silicon

    My Webcam []
  • Have we been under a false impression that Athlons need special memory? Many companies advertise athlon compatible memory; if this is a false issue I'm sure it's hurt AMD's sales.
  • You can add the fact that his website is nonexistant! Guess what - it's not just down, it's a vailable for registration []! He is SO a sham!
  • AMD has shown consistent leadership recently. And continues to do so!
    hopefully they will keep up the good work...and maybe learn some lessons from transmeta?

    Anyhow, they have done a good job of keeping intel from dominating the market, which is good for everyone!

  • I have 3 computers connected to one keyboars and monitor through the special switch (Belkin OmniCube 4-port, model F1D094). It is not inexpensive at about $180 plus cables, but I save on monitors, space and convenience.

    As for the older computers, they still can run SETI@HOME ;-)
  • I hope to hell they rename it something else at launch: it sounds like a variant of Teflon, or maybe its the material from which they make Durex condoms....

    You'd think marketroids who get paid to come up with names would do better than this!

  • The article commented that AMD has supieror production yields.... which puzzles me. I know Dell (gee wonder why I know) is iffy about using AMD procs because of supply problems. It'd be nice to see AMD push stuff out the door so larger OEMs can begin to really consider them for servers and higher end markets. Even if their procs are faster,better, etc than Intel.... overall Intel can provide more quanitity to a company that demands high supply. If AMD is sitting around going "well, we're a little low" that'll drive the OEM's prices up (unexpectatly)...

  • I wasn't aware of any memory problems with Athlons.

    I don't think there that many differences between the Duron and the Athlon, so I imagine that any problems you're having with an Athlon is still going to exist under a Duron.

    Devil Ducky
  • There will -not- be slotA Durons.
    There -will- be slotA TBirds.

  • Well, with Athlon, you have a superior chip (than the P3) at a lesser price. What more can you ask?

    The Duron will be a major improvement over K6-2 though.
  • AMD had a lot of trouble with yields earlier, in pre-Athlon era. For the last year or so, however, they have no trouble supplying their cpu's on time and in volume. Intel, on the other hand, was having problems supplying Coppermines recently. Just look at the availability of higher speed parts from both companies this winter/spring.
    DELL is the only big OEM company that isn't shipping Athlon systems. They almost did it once but then backed off. Rumors are that Intel was very "persuasive" in helping them back off.
    The only real problem with Athlon is chipset. Incompatibility problems are more frequent with Athlon motherboards then with ones based on Intel's own chipsets, although the situation is much better now then it was 6 months ago. Still, Intel has the edge there - and in SSE vs 3DNow! support -, although their own 820/840 is nothing but disaster. But with Thunderbirds/Durons, new chipset from AMD is coming so the situation might change.
  • So what would a two-proccessor machine be? A Duron Duron?
  • AMD Moron [] processor as well...
  • > DELL is the only big OEM company that isn't shipping Athlon systems. They almost did it once but then backed off. Rumors are that Intel was very "persuasive" in helping them back off.

    And perhaps only as a coincidence, Dell seems to be Microsoft's staunchest supporter among the OEMs as well. Texas was one of an original 25 states joining the DoJ in its suit, and rumor holds it that it was Dell that convinced Texas to drop out.

  • You know... it just occured to me... OEM vendors typically market their AMD systems has "lost cost alternatives." Why? Why not market an Athlon into a high end server market... Use AMD not because its cheaper but because its a faster, and a better value. I wonder if people tend to view the lower price of an AMD system to mean that its of lesser quaility....

  • AMD is not guilty of multiplier locking. You can adjust the multiplier on current Athlon's with the use of a Gold Fingers device.
  • I wouldn't think so, unless it's higher quality, and it may do just the opposite, boosting sales for those companies that make RAM, as there are those who will do anything to get an Athlon, and will therefore think they need new RAM, so they go out and buy the 'Athlon compatible' kind, which will be marked at a higher price, of course
  • What happened to VIA's Celeron competitor? I wanted to buy two of those and MP those things.
  • People think they bought a Ford Mustang when they really bought a Dodge Neon.

    Aw, you should have said they thought they bought a Ford Thunderbird... keep it along the same lines as the article ;)

    -- Dr. Eldarion --
    It's not what it is, it's something else.
  • The Ford Mustang line works just a as well. Mustang is the codename for AMDs next core after thunderbird. Check for details and rumors on, plus all the Mustang v Willameters guessing and flamage.
  • How do you mean "it's a piece of shit" exactly?

    I don't know how I can get much clearer than that. Unless you're so stupid as to take it literally, and you really think the chip is made out of manure or something. Maybe you don't realize that "IT" means "DURON." I dunno.


    It is slow.
    It is difficult to write to.
    It isn't compatable with jack shit.
    It is inconsistant.


    If you want the technical details this isn't the time or the place. Despite what your self esteem might think, /. isn't exactly a technical forum. Go elsewhere if you really want me to tell you how this chip works. Doink.

  • Well this time last year AMD had productions problems, for the same reason Intel Coppermines have problems the processors core was being pushed to MHz levels the design couldn't handle. I think Dells main problem is AMDs size. With the Autstin Fab running flat out AMD can ship 6-6.5 million chips a quarter, say 20% of the market, Desden can current do a couple million probably 6 million by years end. So even if AMD processors are a quarter of the price and twice as fasters as Intels, the Box makers will still be shifting intel chips because they aren't enough AMDs chips to go round. Expect Athlons to go out in ugly boxes with no adverts to the clued up. While the less clever follow adverts and prettier but slower intel boxes until such time as Intel catches up, cuts prices, or AMD can deliever more chips.
  • Imagine a .....
  • Well Abit KA7 and the Asus K7V are reported to work with all T-Birds. I believe only the deasden copper based T-Birds will have a problems with KX133 motherbirds. Besides KX266 and/or 760, with DDR and ATA-100 will be great reasons to change your motherboard too.
  • I tell you what, though: I've dealt with a lot of computer manufacturers, and IMHO, Dell's support easily blows away everyone else. Granted, they are probably on average the most expensive of the Big Name companies, but I'll gladly spend a little more on the front end if it get's me superior service down the road.

    Still, I wouldn't mind seeing some AMD's in Dell systems, and I don't see why it hasn't happened yet. I don't think Intel's in any position to say to Dell, "Stick with our chips or we'll pull them all" like they used to back in the day.
  • I can see the future news releases now...

    Today Intel, in response to the strategic alliance of AMD and Ford, is planning to team up with Chevrolet.

    Intel's plans for the future include a chip named the Intel Camaro, which is going to be a direct competitor to the AMD Mustang.

    -- Dr. Eldarion --
    It's not what it is, it's something else.
  • by WombatControl ( 74685 ) on Friday May 19, 2000 @10:06AM (#1060715)
    Duron is kinda interesting... sounds vaguely like a Klingon name... "Duron will destroy its enemies on the field of silicon battle and drink their blood! Qapla'!"

    Then again, that's not the worst naming gaffe that could be made. I will *never* forgive Intel for not naming the Pentium II the Sexium. Even worse is them not then calling the Pentium III the Septium. That way if something went wrong in the manufacturing process it could have been the Deviated Septium. *rimshot*

    In all seriousness, the Duron should have enough of a price/performance ration to seriously give Intel some competition. The next computer I plan to be will be a Duron box, and I suspect I'm not alone on that one.
  • by SpinyNorman ( 33776 ) on Friday May 19, 2000 @10:07AM (#1060716)
    Of the top 10 PC manufacturs, 9 use AMD parts (incl. Compaq, Gateway, IBM, HP...), with Dell being the only hold out.

    Guaranteed volume may be a factor of why Dell hasn't yet adopted AMD parts, but another major reason is that it would jeapordize Dell's special relationship with Intel.

    Still, performace and price are likely to force Dell to use AMD processors this year in order to remain competetive. Thunderbird is likely to be around 10% faster than PIII at the same clock speed, but will in fact also be available at much higher clock speeds than PIII.

    Ignoring Dell's limited edition 1GHz PIII made possible by their Intel relationship (1GHz PIII won't be in volume production until Q4), the fastest PIII currently available is the 866MHz.

    1GHz Thunderbird vs 866MHz PIII is a big performance gain for Dell to expect it's customers to give up. The latest Computer Shopper is even advertizing the as yet unannounced 1.1GHz Thunderbird, which may be a surprise announcent at the launch on June 5th.

    Intel are not going to be able to match Thunderbird clock speed or performance until Willamette is launched towards the end of this year. At that point AMD Mustang will be out, and may well again be the faster processor (no benchmarks for either Willamette or Mustang are available, but AMD technology roadmap indicate they are about a year ahead of Intel in the move to .13 micron process technology - Mustang may well be a ".15" .18/.13 micron process hybrid).

  • How do you mean "it's a piece of shit" exactly?

    I thought this was basically a repackaged Athlon with a bit less onboard cache.

    I don't generally hear the Athlon described as a P.o.S., so I'm curious why Duron would be so much worse than say, a Celeron.

    The name sucks, but other that that all other reports have made this sound like a contender for the low / low-middle / middle-middle market. And since I am actively thinking about a machine that can actually play games ;) but don't need a dual gighertz athlon with transporter room, I'd like to hear more details before writing off these new AMDs. I've been pleased as punch with my salvaged AMD K6, and would like to keep supporting non-Intel chips unless driven otherwise by good reasons.

    Any insight?

  • Considering that:

    a) I've never heard of you,
    b) I've never heard of your company,
    c) I've never heard of any of your games,
    d) You offer no qualifying information on why you consider the chip to be "a piece of shit,"
    e) You offer no information on what you were trying to do with the chip, aside from the cryptic "Assembly" as the subject for your post, and
    f) You offer no evidence that you are qualified to speak on the issue, aside from merely being "lead programmer" (whatever that means),

    nothing you say will establish experience or credibility for you to speak on this issue. As a result, your opinions as expressed in your post are meaningless, and you appear to be using your title as "lead programmer" in a classic case of False Authority Syndrome.

    If you would like anybody for you to take you seriously, please provide pertinent information, observations, and data about your experiences with the chip.

  • So true -- if Dell was afraid of the "lunatic fringe", they wouldn't be selling Linux boxen... ;)

  • Celeron may be Similar to Pentium III at 466 and 533, but the slower 66 bus kills at faster MHz, Clock multipliers above 8 start to suck badly especial with a small cache. Duron stays on a 200MHz (100 DDR) bus and will slay celeron above 600. Expect Intel to push forward the celeron 100s quickly. In fact Intel with stupid not to but all the new coppermine celerons on 100 to begin with. It would be faster and wouldn't cost them a penny.
  • So far I've dealt with support from Dell, IBM, Compaq, Gateway, and Micron. The IBM guys are fucking geniuses with their product, though the hold times are occasionally long. At the other end of the spectrum, Gateway's people always seem on the virge of blurting "you want fries with that?", though I suspect this has something to do with the way Gateway tracks their equipment ("You can't get sound? What kind of card do you have?").

    Dell and Compaq were about the same, very professional. Micron's weird: not as sharp as IBM (no one is), but if they can't tell you how to fix it within about 10 minutes, they send a new one. I've gotten motherboards, RAM, monitors, even whole PCs replaced like next day without even asking.

    You Know You've Been Watching Too Much Ranma 1/2 When...
  • It'd be nice to see AMD push stuff out the door so larger OEMs can begin to really consider them for servers and higher end markets

    I thought that the reason no one is using AMD hardware in servers was because there were no MP motherboards that supported the Athlon.

    But I could be wrong...

  • Nah, just the result of bad puppet work. I couldn't get enough of the show as a kid, though. Oh well.

  • Good point. I hadn't thought of that. When I hear "special relationship," I think post-WWII Iandoli's supermarkets here in MA: they had an inside deal with ADM or something and they "passed the savings on to you."

    The high-end chip angle makes sense seeing how they've always maintained their reputation by buying at the top of the market. Still, the other day one of the statisticians asks for a new laptop and it's $1000 more than the best Thinkpads, which I like better anyway. I can see it if you're Fortune 500 or something, but we're non-profit and that just looks bad on paper.

    You Know You've Been Watching Too Much Ranma 1/2 When...
  • Dell's argument is BS; the VIA KX133 Athlon chipsets are more than stable enough. The real reason for Dell's reluctance to use AMD products is left as an exercise for the reader. *grin*
  • I'm sure if anyone implied that their special relationship benefits the customer. You're right, of course, I jumped to conclusions. I'm still suffering from sticker shock. I hope their advertising barrage goes very well.

    Personally, I could care less what kind of chip the machine runs if it's just a desktop. My users run the sort-of-finicky Corel Office 2000 app, and whoever makes a computer that can run it without crashing wins our vote.

    Honestly, though, I don't think HAL could run it.

    You Know You've Been Watching Too Much Ranma 1/2 When...
  • Well, ya got me there. Im just spectating. Oh know what they say about how one shouldn't assume. :)

  • the Intel 128 bit Unobtainium.
  • The institutions which recently did mass upgrades to Slot-A boards will have serious trust problems with AMD in the future.

    AMD: "Hey, we've got this great Athlon chip. It's better than a P3! You need this Slot-A motherboard to run it."
    Corp: "Okay, if it's so great, we'll take 1,000. You'll continue to support this Slot-A platform, won't you?"
    AMD: "Of course!"

    This happens more often than you think; there are tons of companies that upgraded to next-gen K6en instead of next-gen Pentia, for the simple reason that they could. The Pentia required motherboard upgrades, the K6en didn't. Any corp faced with this choice will go with the upgrade that gives comparable results and is roughly half the cost, and rightly so. Based on the positive experience they had with Socket 7, a lot of corps then went to Slot-A when upgrade time rolled around, assuming it'd continue to be AMD's platform of choice.
    Not so.

    If VIA/Cyrix are smart, they'll slap together a Slot-A processor to fill this gap.

  • I knew this dog when I was a kid. It would eat the little extra chunks of cement that is leftover after cement has been poured.

    Well...imagine hitting that sorta dog-pooh with your lawn mower. Took out my mom's Volvo Wagon window once. She was PIS*ED... dad and I named the dog Boron...

    Sorry for the off-topic...

  • What I would have liked to see is procs released like the Pentium Pro - no multiplier lock and no set bus frequency. You should be able to take a PIII from 100 MHz to 133 MHz without overclocking. Intel & AMD can sell their procs at a rated speed and make this info easily identifiable.

    Perhaps I shouldn't whine too much. After all, the shitty state of affairs is why I still run pentium pros.
  • Your problem wasn't from the hardware, it was from the manufacturer. I worked for Gateway for 2 years in the Service department and can tell you one thing DON'T BUY GATEWAY. Especially if you are a power user.

    I bought a Gateway as an employee and when I recieved it it instantly stopped working. I fiddled around and booted the hard drive in another machine and it turned out that they had loaded the wrong video driver for the card that I had and that video driver had somehow actually screwed up the original video card. This is my personal Gateway horror story and I can't tell you the number of screw ups I saw come through when I worked there.

    If you want a computer pre-built, go somewhere else. Gateway was always low quality, and in the time I was there I could actually tell that the quality was getting worse. I'm sure I will get flak for this if Gateway sees it, but what are they going to do, fire me?!? I quit there because of the mindset that Gateway is the one true way, and that Ted was GOD (the original founder). What a joke. And we laughed just as hard inside the company as people outside the company laugh, believe me.

    BTW, I quit there almost three years ago now, so this isn't just a quick "I'm going to get those bastards" type of post. Once I got out and started to see how real computer companies do things (Dell, Micron, Compaq, HP, ....) I realized that it was worse than I had thought. Just stay away from Gateway. Judge the Athlon on its own merits, not on Gateway's shoddy work.
  • > AMD has secretly started moving to Latex based CPUs.

    Not a secret anymore. They announced their new "cling-on" processors at Cannes yesterday, and had some of Victoria's Secret's models wear them to cover their naughtybits on the catwalk.

    Rumor has it that VS has put those particular processors up for auction on ebay, and will give the procedes to a charity for geeks that can't get a date.

  • by Wreck ( 12457 ) on Friday May 19, 2000 @10:15AM (#1060734) Homepage
    Anyone recall a year ago when the Athlon first came out? The benchmarks then all had athlon handily beating the PIIIs at the then-current top speeds of 600-650. And it was not small, particular: anywhere from 10 to 25% faster. The two processors both had 512K of L2 cache, not on-die so running at half of the CPU speed.

    Then Intel went to coppermine: 256K of L2 cache running full speed. This yielded about a 10% speedup: for instance see Tom's comparison here [].

    Meanwhile, though faster Athlons were released (at 700, 750 MHz), they had no faster L2 cache: they had to run at 40% or 33% of the core speed. The result? Coppermine beats Athlon, narrowly. You can see it happening in this graph [], if you imagine the blue line extending about straight (which is more-or-less what happened.) The two chips are quite comparable at the lower end, or maybe Athlon wins. But in the 1G processors, PIII is the winner (see this [], for instance).

    Now with Thunderbird, Athlon will again be more or less the same in L2 cache as PIII: 256K full speed on-die cache. So, we should expect the Thunderbird to kick PIII's butt, by about 10% or so plus the fact that it will actually be available.

    Duron should also beat celeron, though perhaps by a smaller margin.

  • For one, how can you have an opinion of the performance of the Duron chip, being that it's not yet availabe and you don't have an in your email address? :)

    The difference between Celerons and Pentium III's at the same speed is minimal, unless you work with data that's too large for the Celeron's cache but small enough to fit into the Pentium III's... That's probably a very small subset of the population... It's either small enough, or it isn't. If you're working with word documents, it will probably fit. If you're editing graphics or video, or if you're writing large programs, it probably won't.

    The reason that Celeron's at this point appear inferior to P-III's is simply that Intel refuses to let Celeron's be released at speeds that might compete with the Pentium family. The moment that Duron chips march into the Celeron's market, watch as Intel hurriedly rushes faster and faster chips out the door. Not saying that my fingers aren't crossed for the Duron to be successful. I just think it's inappropriate to make presumptions on non-shipping products based on information that the manufacturer supplies (and that holds true for everyone, Intel, Apple, Microsoft, Transemeta, etc...)
  • Window's new startup sound: "Anything can happen in the next 30 minutes!"

    AMD's Beofulf startup script: 5.... 4.... 3.... 2.... 1.... *sound of rocket taking off* Thunderbirds are go!

    AMD's next chips (the Stingray series) will cause office buildings to retract into the ground, whenever you run a difficult program.

    Reports that using the AMD Thunderbird causes you to walk in a strange, stiff-legged manner are denied, as are rumours that Brain has bought out Red Hat.

  • Nothing I've seen indicates that newer celerons and newer P3s perform the same for a given clock speed. This used to be the case. For example, I have a celeron 300a overclocked to 450. The performance is similar to P2 450 and a P3 450 (the older flavor of P3 that had 512k off-die cache) for most applications.

    The newer P3s have 256k on-die cache that makes the chip much faster than the old P3s. The newer celerons are the same, but with half of the L2 cache disabled. The benchmarks I've seen have shown the new celeron lagging considerably behind a new P3 with the same clock. I think the days of celerons offering the same performance as a P3 are over.

    Two notes: I'm basing this on my memory of reviews. If someone knows better please correct me (I know, I know, it's tough to find people willing to at Slashdot). Also I wonder if the celerons aren't slower than the P3s because the L2 cache's bandwidth is halved. I'm no expert, but memory systems can use interleaving similar to RAID striping on hard drives. Maybe when Intel chopped the L2 cache in half (really just a crippled coppermine P3) they halved bandwidth too.
  • It's just too bad that these processors will be made available in a socket interface instead of the slot interface all current Athlon motherboards are available as. It makes upgrading a bit more expensive, as a new motherboard is needed. Apparently, it's also not feasible to make "slotket" converters for the Athon / Duron / Thunderbird / Mustang / K7 / Whatever.

    "You can bypass the click-though licence agreement on Microsoft's PAC specification by opening the file with WinZip instead of running the file". There. Have you violated the DMCA today?

  • by MSG ( 12810 ) on Friday May 19, 2000 @12:34PM (#1060769)
    Some people are asking about SMP, and since I recently attended an AMD partners conference, I thought that I would share.

    First, the Duron and Thunderbird processors are going to integrate the L2 into the die. The AMD techs seemed excited about that since the Athlon is already outperforming the Coppermine. The move from the L2 on the module to L2 on the die should prove a massive boon to their already good performance. This also means that there is no longer a reason to use a slot. (With .25 micron process, you can't put the L2 on die, it'll produce too much heat. However, you can't access the L2 cache very quickly through a socket, there's too much resistance.) The Duron will use the new Socket A, and the Thunderbird will be available in both Socket A and Slot A configurations, so that all of the old motherboards aren't immediately obsoleted. Later processors will only be available in Socket A.

    Second, SMP is coming, but not in the Duron or Thunderbird. Mustang will bring us SMP later this year, in Socket A configuration. The point that AMD stressed is that Intel processors use a shared bus to the North Bridge, whereas their Athlons will each have their own bus to the North Bridge. This will provide the processors a whole lot more bandwidth to their memory and peripherals.
  • Theoretically, a dual Athlon MB could be made using the Tsunami chipset (Compaq's blindingly fast dual-processor chipset for the Alpha). Unfortunately, the chipset would then cost more than the two Athlons (about $1000), so I don't see this happening soon.

  • Yes, it will be competitive with the Celeron. Even though it does have less Level 2 cache, the effective 200mhz bus will make all the difference in the world -- Not to mention the Athlon core which is still far superior to the PPro core of the Celeron. The Celeron 2's had relatively dissapointing performance, and it's likely that Duron will perform much better and cost less.

    As for the memory, not much will change probably. Duron's will be using basically the same chipset for Socket A (KZ133 and AMD 750). There are several places to buy "Athlon-tested" memory though, so I don't really see why this is a problem.
  • Thunderbird? Duron? Athlon?

    They sound like secret weapons from a bad sci-fi movie...

  • by Shoeboy ( 16224 ) on Friday May 19, 2000 @09:44AM (#1060791) Homepage
    AMD practises safe computing
    Relax, you'll just feel a tiny prick
    Chimpzilla's new - ahem - entry level chip, Duron, would appear to share advanced technology with condom giant Durex, if the contraceptive company's website here is to be believed.

    The site states: "New technology has considerably improved the condom and enabled the production of far more sophisticated versions than our ancestors were used to. The latest development is DUREX Avanti made from a unique polyurethane material, DURON, which is twice as strong as latex enabling a thinner, more sensitive film."

    AMD would not confirm rumours that Duron would ship in packets of three rather than trays of ten, nor that the company was planning a 'Duron Inside' ad campaign. ®

    Looks like you'll need to lap that Duron processor as it may be ribbed for her pleasure.

    The chip may grow flaccid if not in use.

    Feel free to make your own juvenile jokes.

    (former microserf)
  • I know Dell (gee wonder why I know) is iffy about using AMD procs because of supply problems.

    I don't think Dell is worried about the supply of AMD chips - I think they're worried about their supply of Intel chips if they started using AMD chips too!
  • Is sadly going to be that you will need a special chipset - unlike Intel, where the same memory controller that does single processor work is used for SMP, the AMD memory controller for SMP will have to be a seperate SKU (because it needs an extra set of 90-odd pins to talk to the other CPU) - the upside to this is that it's likely to perform better, the downside is that because this chip will ONLY be used in Athlon SMP boards it's volume will be low and as a result its cost is likely to be much higher (unlike for example an Intel 440BX which is used in many many single CPU boards and a relatively small number of SMP boards).

    I currently buy SuperMicro P6DBEs (dual cpu 440BX boards) 10-20 at a time @~$160 a piece - I'd jump at the chance to be able to buy something similar that's Athlon based - but at a similar, or lower, all up (stuffed including CPUs) price - sadly I doubt this is going to happen any time soon

  • Dell's PCs are so goddamned expensive I don't see how their "special relationship" benefits anyone.

    Dell has a huge advertising co-op with Intel, so the special relationship mostly benefits Dell, by getting them millions of dollars of free advertising. Also, they got price protection on RDRAM, which allows them to peddle some of Intel's otherwise worthless 820 motherboards. Also, many of Dell's computers are Intel barebones systems.

    I'm sure if anyone implied that their special relationship benefits the customer. It definitely benefits Dell, though, which is why they will have a strong resistance to upsetting Intel, even if it hurts their profits.

    If Dell goes AMD, that will be a warning sign to Intel that they no longer dominate the market.
  • Thunderbird/Spitfire/Mustang etc are almost certainly internal names for the project - Athlon/Duron/Itanium etc are made up 'marketting' names chosen because they're words that (hopefully unless someone screwed up) haven't been used in the English language before - thus avoiding all sorts of potential trademark pitfalls
  • One might argue that not upgrading the board is healthy cost savings, but if you're upgrading a processor within a sufficiently short timespan as to not necessitate a new board technology, then money obviously isn't an issue.

    When you are upgrading often, money is MORE of an issue, because your annual cost can go way up by having to buy more parts. I actually have a socket 7 motherboard that is on its third processor. It's a FIC PA-2007, that I've had since 1997. They have bios patches to run anything up to a K6-III on it, as well as large hard drives.

    I have respect for a company when they still provide updates and support for legacy products, and allow upgrades for a long period of time. I'm hoping Socket A will stick around for a while, because I hate buying motherboards unnecessarily.
  • People think they bought a Ford Mustang when they really bought a Dodge Neon.

    I can tell you from personal experiance that Dodge Neons really suck.

    So Linus, what are we doing tonight?

  • Actually it's not availability, but rather "the lunatic fringe" as Michael Dell put it. Bah, whatever.

    The argument is the AMD chipsets aren't stable enough. But then we (I do tech support for Dell) use the 820 chipset, so...
  • We already know that the AMD Duron and the "Thunderbird" variant of the Athlon CPU will be great, if only because they are based on the modern Athlon CPU core with its 128 KB L1 cache and the all-new FPU unit.

    The big considerations in regards to these new CPU's are chipset support and motherboard availability. In regards to chipset support, will AMD finally make the 760 chipset avaiable? And when will VIA Technologies ship the Apollo KZ133 chipset, the one that will support the Socket A design natively? And how about availability of motherboards that use Socket A? Once the 760 and Apollo KZ133 chipset motherboards become widely available, then AMD will avoid the issue of plenty of CPUs but no motherboard situation that plagued initial Athlon shipments last summer.
  • For slot-A/socket-A mobo information, you can check ( points to the same page).

    The KZ133 has been sampling for a long time, and will be available in volume along with socket-A motherboards to coincide with the Duron/Thunderbord launch in early June. There are at least 3 socket-A motherboards that should be available at launch (the FIC mobo is already on - search for "Duron" or "Thunderbird").

    There will also initially be some slot-A Thunderbirds to ease the transition, and these will work with existing AMD 750 based slot-A motherboards, although don't expect to be able to buy a slot-A Thunderbird in retail - they are likely to only show up in OEM computers.

    The AMD 760 chipset is for DDR and will be available in Q3. There is also the 760-MP (aka 770) which will support 2-way SMP as well as DDR.

    There are also many other AMD chipsets coming, such as Micron's DDR/SMP ones, Via's KZ266 for DDR, ALI (Acer Labs) support, etc.
  • It's also worth noting that you must be over 18 and supply a credit card number to view the duron being inserted into amd's new socket architecture.

    I wonder if they make spermicidal thermal paste.

    (former microserf)
  • More:

    Durian: Incredibly smelly Indonesian fruit.
    Duroc: Castrated male pig.

    C'mon chip firms, enough with the cute names already. Us geeks liked numbers just fine, and they work fine for car marketdroids. Let's have the numbers back now, thanx...

  • kill ... Straker. Kill ... Straker! Kill Straker!! ;)

    And now, some text to evade the lameness filter. Bla, bla. Linux rules, Micro$oft s*cks, beowulf, smp, boy howdy I really love those chips with the funny names.

System checkpoint complete.