Follow Slashdot stories on Twitter


Forgot your password?

More on Athlon Overclocking 140

The Tech Report is running an article concerning Athlon overclocking. With the 1Ghz+ chips coming down the line apparently soon, will things need to change? Or will it be just a documentation change? The other change is the issue of moving to on-die L2 cache - how will that affect things?
This discussion has been archived. No new comments can be posted.

More on Athlon Overclocking

Comments Filter:
  • by Anonymous Coward
  • by Anonymous Coward
    Bullshit. I've seen blacks pull themselves out of the ghetto, and it's through hard work. Urban black pop culture spurns hard work and encourages the kind of moral degradation that is the cause of the black man's failure.

    Successful criminals are treated as heroes. Rap lyricism both documents and encourages this. Gangsters are "cool". Young black girls having babies love the idea and so do their friends. In "conservative" culture, teen pregnancy and a life of crime make one an outcast in most social circles. That's what keep little boys from dealing drugs and little girls from being careless whores.

    American blacks respond to racism with laziness . Whitey may have put you in the ghetto, but you're the one keeping yourself there.

    I say American blacks because blacks around the world are different. Blacks living in Europe, Asia, Africa, and everywhere else don't applaud the same kind of sick things that American blacks do.

    Killing a man for his shoes is wrong, little brother. Having a baby you can't support is wrong, little sister. Why didn't your parents teach you these things? Are you the child of a teen pregnancy yourself? Did you never know your father? For that matter, did you mother?

    Why do you value expensive clothes and gold chains more than your own existence? You spend your life consuming everything, giving nothing. You'll die and no one will remember you. You won't have left your mark on the world. An empty soul, a wasted life.

    The but the problems of modern America are not one of the black man alone. ALL races in all parts of the counrty are feeling the burn of moral degradation, and they love it.

    Morality does not mean xenophobia of homophobia. Morality means knowing the difference between what is right and wrong, encouraging what is right, and despising what is wrong.

    What the fuck is wrong with this country? Americans have short memories. We are a nation of selfish, evil people, children of the immigrants who made this country what it is. Ungrateful, dirty children. All we care about is money and sex and fame and pleasure. Fuck the world, we're America, dammit. We don't have to care. We can spend our lives wallowing in our own filth and nothing will stop us.

    Television evangelist: God will not let you into heaven for what you have done. You are a disgusting beggar in rich man's clothes. You beg on television for the money of others, feeding your "church" like a disgusting leech. You are not a good person. Joseph did not wear an Armani suit. Matthew's church didn't have air conditioning. You wallow in your wealth while fellow Americans die in the streets from cold and hunger. You want to make a difference? Go to the beggar. Give him one meal. But only one. Charity is overrated. Help him find a job. Help him with his alcohol problem. Let him know that he's a child of God just like you, and deserves the respect of his fellow man. Help him earn that respect.

    Politician: You disgust me. You do not serve the people. You only serve yourself. Your policies help no one. You only want them to appear as if they do. You sit in office and soak up the money and the fame and the life and then you retire. Poverty isn't fought with ten-year initiatives, argued over by rich, fat, white men who have never known true poverty and never will. You want to help? Help NOW.

    I could go on for days, but I won't. Stop electing bad people to run our government. Stop being so fucking LAZY. The reason this country worked in the first place was because people were INVOLVED IN THE GOVERNMENT. That means learning about the people who make the laws, and ACTUALLY VOTING. Don't think, "Oh, I'm just one person! My vote doesn't really count!" If every person who thought his vote didn't count actually went out and voted for CmdrTaco, he's be our next president! Don't you get it? It's like physics. The American population has gobs and gobs of potential energy that could be utilized. Get involved. It's your fucking country. You can make a difference if you get off your ass and try.

    I for one can't take it anymore. I'm fucking sick of living in a country of irresponsible citizens. Anyone in Canada or the UK looking for a roommate?

    Thank you. [mailto]

    Let's start praying for someone to save us and start saving ourselves. - KMFDM

  • by Anonymous Coward

    AMD, naturally, will never tell you of the risks you run in using their products, but you have a right to know.

    The L2 cache design is really still experimental. The old L1 architecture is proven, but it's just about tapped out performance-wise, so AMD is moving on. Sadly, they're releasing designs that are not yet "production-ready" in a few crucial respects. Under certain circumstances (multiplying > 1k x > 1k matrices of doubles, for example) the L2 design will "underclock", or in engineering idiom "sprag". "Spragging" means, in layman's terms, that a lot goes in and nothing comes out. This happens when fast swapping cuts in during cache defragmentation with a mod zero byte block size in the under-storage. The result can be as small as a die melt ("burnhole"), which will require you to replace the unit (yes, that's "small", relatively speaking) to an extremely fast and sudden heat buildup: The L2 cache warms up only slightly, but it happens to be very near the clock-monitor throwback module. Yes, you heard me. You don't want your clock-monitor throwback to be soaking up any joules from a sprag, believe me. If the "glow-up" is fast, it'll throw a burnhole in the substrate and that's all she wrote. An expensive hassle, but not a major tragedy. Unfortunately, slow glow-ups do happen from time to time (larger byte blocks in the under-storage can cause this) and in that case the substrate won't burn-through before the clock-monitor throwback gets hosed. When that happens, look out, you've got the thing spinning out of control. Have you seen those cryonic supercooling rigs for seriously overclocked chips? Do you have any idea how much heat they're soaking up with all that liquid nitrogen and so forth? A hell of a lot of heat. Your computer under your desk doesn't have any liquid nitrogen. Fry your clock-monitor throwback and you'll wish it did. Here at AMD (that's why I'm an AC, duh) we do keep liquid nitrogen in the lab when we work on this bug. That's how serious it is. A couple of engineers have been very seriously burned, one so badly that he's on permanent disability.

    Be safe, be careful, is all I'm saying. It's a rare, freak glitch, but it can happen, it has happened repeatedly in testing. And it can happen to you.

  • by Anonymous Coward on Saturday March 04, 2000 @07:41PM (#1225335)

    It's been covered up, obviously, with the connivance of the liberal media, but at least three moderate-to-severe head-explodings have been recorded in ordinary household usage of Athlons. Don't let this thing near your kids. It'll pop 'em like popcorn.
  • I actually do feel stupid; that story was never meant for the Slashdot front page. I meant to leave it as a joke to anyone going through the stories list tonight as a 'how long has it been since you've seen this' piece. :) Sorry for the mix-up. --Emmett
  • Again, it was a joke that was NEVER MEANT for the front page, but as something for the other staff members to see in the queue and laugh as a 'how many times have you seen this' joke between us. I'm really feeling very stupid about it; please be kind!


  • Hey there, Spanky!

    As I've explained, the story was never meant for the front page; I left it as an internal joke for the other staff going through the 'stories' list tonight. Unfortunately, I accidentally left it as 'Always Display,' and the rat-bastard thing displayed for like 10 minutes before I realized I had done something waaay wrong. :)

    So, before you attack my editorial integrity, get the facts first. Thanks!


  • Additionally increasing the clock gives the charge carriers less time to move, if it cant make a difference to the far side of the active region of the semiconductor, it isnt working. Increasing the voltage increases the electron drift velocity. Increase it too much and theres a chance of electrolysing your chip ;)

    You also dont want to reduce the temperature too far or kT will drop to below the bandgap, turning the semiconductor into an insulator.

    The best way of increasing speed is to reduce the size of the active layer, but soon we'll start getting quantum effects, which in current designs, are unwanted.
  • Wow, such an enlightening site. This stuff really needs to be reigned in quickly. People are dieing because if our lack of action.

    Their studies were very nice as well. The remind me of the UCB bit where they got signatures to stop Women's Suffrage.
  • by whoop ( 194 )
    The food one was very nice. You mustn't let these slip ups happen again. Get yourself a Tivo. That takes care of everything.
  • Not just that, but you know that smell that comes before a good rainstorm? That, my friend, is ozone. The government is letting millions of people breathe that stuff every day. With Spring coming upon us soon, I am fearing every second that goes by. Dear God let's hope someone takes action against this stuff.
  • Come now, it's a decent joke for geeks. Let the commie environmentalist liberals fall for it if they don't understand it. ;)
  • by whoop ( 194 ) on Saturday March 04, 2000 @08:21PM (#1225344) Homepage
    Boy lemme tell ya, if anyone is gonna spend the $1200 (or whatever) for a 1000 Mhz chip, and doesn't overclock it, they are downright fools. I mean, how can you look at yourself in your monitor's reflection every day with a measly 1000 Mhz machine? Sure you compile kernels in 5 seconds, but look at the guy down the road. He's running his at 1700 Mhz right now, pulling in about 738 fps in . Yeah, that's right, you non-overclockin weirdo, you.

    Ladies and gentlemen. Do not let this scenario happen to you. The next time you remortgage your home to buy a CPU, remember, overclock that puppy to heck. Thank you.

    This has been a paid advertisement from the Go Ahead and Fry that CPU Foundation.
  • here at AMD huh ?

    How about here at intel we cant fight with technology so we will try FUD, and lawyers.
  • Anyone know of a motherboard anywhere that supports two athlons, that was sposed to be a big technology benifit when they were introduces over pentium 3.
  • Uh, dont you think that companies would be smart enough to have shielding around the processor itself, rather than relying on the case? I think people think retards work in the R&D section of companies, they ARE aware of severe problems like THIS.

    Of course they are. They're engineers. And the instant the marketdroids realize they can drop costs and increase profits by forgoing the shielding they will do so. And if past experience is any guide, people will buy it even though it interferes with their tv, radio, and other computer equipment, and cooks their brains. These are peecee buyers we're talking about, not intelligent human beings. If they'll buy aol, they'll buy anything. Now we just need to find a way to sell them a "computer" that is actually just a metal case connected to the appropriate line voltage. Pfffzzzzt, no more peecee luser.

  • Yes, but what about when your L2 cache goes into mod zero byte block mode and slags the hell out of your cpu? That could easily lead to multi-megawatt emissions of head-exposion-causing microwave radiation madness! Write to your congressman/MP now, before it's too late! Think of the children!!!
  • by The Man ( 684 ) on Saturday March 04, 2000 @08:38PM (#1225349) Homepage
    You have missed the point. The objective of overclocking is not to obtain noticeable, or even measurable, speed increases in any task. It is to show how 31337 the 0v3rC10kk3r d00d!!!#!!@!!! is. You are correct, however, when you mention that A 1 GHz chip (or even a 800 MHz one) can, for most tasks, outpace any other componant of the system. This is why real workstations with "slow" 300-500MHz processors can easily outperform peecees with processors clocked twice as fast or faster. It's called balanced design, and has never made an appearance in the peecee world. The great irony is that peecee overclockers are trying to increase the speed of what is already the fastest component in their systems but refuse to spend one extra currency unit on improving the subsystems that are the slowest in the computing world. Instead, they should buy a chip 200-300 MHz behind the state of the "art" and spend the extra dosh on a better mainboard, i/o subsystem, and disks. It's amazing how much better performance such a system can deliver at a similar price point.

    rated speed to avoid single-bit errors and the like

    SBEs, eh? Well, that implies that you invested in ECC memory. Investing in higher quality components is highly unusual for an overclocker. I can assure you that most of them observe SBEs as a BSOD in their GameOS, because they spent all their cash on a higher-clocked processor and then bought Joe's Factory Thirds "PC92-1/2" Memory from the guy on the corner wearing a trench coat.

  • Fortunately for the engineers, there are FCC requirements for emissions and inteference, so they can tell the markedroids to shove it.
  • Microwaves are optimized to produce microwave radiation and use a wave guide to concentrate the energy in an enclosed space. Faraday cages are very good at blocking high frequency radiation so not much leaves the box.

    In CPU design, radiated power is minimized because it is required to get an FCC license of the device and because radiated power can cause interference within the box itself which is obviously a bad thing.

  • Well, you won't be seeing dual Athlons until a dual Athlon chipset and motherboard come out.

    But, according to this Anandtech article [] yhey will hopefully be available by the end of 2000.

  • Hell with that! *REAL* overclocking was desoldering one's 6809 CPU and replacing it with the 6309(?)!

    (actually, i may be blowing smoke here... i never did do this, but i *think* i recall seeing plans to...)

  • I'm sorry this has turned out to be a rant all, please forgive me. Theres nothing I get more passionate about then technology and the Average Joe who's going out to buy that top o the line CPU to run his wordpad. If it wasnt for Joe Average spending tons of cash buying the top of line CPUs, do you think these companies would have the money to develop better chips as quickly? Or the desire to? Just because you only drive 3 miles a day to work, and to church on sundays don't mean you shouldn't drive a BMW/Cadillac/(insert expensive car here) and look good doing it. I hate when elitist geeks spout superiority over your typical user. Get over yourself.
  • One difference between factory marked and overclocked chips is that the factory marked chips have been tested at their rated frequency by the manufacturer. This is an important difference for non-recreational users. A dealer or end user can not properly test an overclocked CPU. The manufacturer uses a very expensive chip test system with proprietary test vectors.
  • It does make sense for anyone, with the money, to buy at the top of the bell curve (750MHz PIII or Athlon) rather than several steps behind it (Celeron 333A, K-6 3D). In most cases the difference between the high end and low end is $1500 at most... In reality, for a machine that you expect to be functional for several years, that's not that much money.

    So long as deevelopers know that faster CPU's are on the way, they'll continue to write programs that sap just about every available resource from the machine... Intel's salivating at the prospect that one day Win NT/2000 will be dumbed down enough to run the worlds desktops.

    Windows is one example of code bloat... But there's also X, and especially the newer WM's, like Gnome and KDE... And as opensource developers try to match Microsofts applications in features, there's bound be more and more bloat on the way.

    Remember, 10 years ago, what was the norm? 16 Mhz? maybe 25? or even 40 MHz AMD 386's? But regardless, for most apps, those were probably good enough, too. The person that says that 750 MHz is good enough for everyone can almost be compared to Bill Gate's (though i'm not 100% possitive it's his quote) "640K ought to be enough for anyone"
  • Hold up a bit there!

    The real heyday of overclocking was the PC-AT, with the socketed crystal! No fancy-pants jumpers, DIP switches, BIOS settings, or anything!
  • by JamesKPolk ( 13313 ) on Saturday March 04, 2000 @08:02PM (#1225358) Homepage
    Which is better?

    Compile, test, debug
    Compile, test, debug


    Compile, check email, test, debug
    Compile, have lunch, test, debug

  • I'm not so concerned about 1GHz CPUs anymore. I want to see supporting subsystems match the processor's performance, specifically video and memory. It would be very interesting to have a 500MHz memory subsystem and a 1GHz 256bit 3D video subsystem. By way of example, I have recently been able to extend the gaming life of a number of older P/PII systems by giving them Voodoo3 3000 PCI cards. How much more performance could we all get from a bleeding-edge CPU if everything else is running just as fast?
  • Am I the only one thinking we'll be seeing the BiAthlon and TriAthlon just like the P2 and P3 came along?

    Possible, but personally I'm hoping they'll call the dual athlon a biathlon etc. Not much chance of a pentathlon that way though :-(
  • Hold up a bit there! The real heyday of overclocking was the PC-AT, with the socketed crystal! No fancy-pants jumpers, DIP switches, BIOS settings, or anything! *Sigh*. Nothing compares to the good old days of overclocking, when choosing the right lubricant for your abacus could mean the difference between getting a good deal on a camel and accidentally mortgaging your soul.

    I well remember cranking my Intel Abacusium IV to over 100 BOPS (bead operations per minute), my favourite FPA (first-person arithmetic) games ran lickety-split...

    Chris Morgan

  • According to this Electronics Weekly [] article, on non-graphics intensive applications like the LINPACK benchmark the Athlon 800 Mhz CPU performs twice as fast as a Pentium III 800Mhz. It goes on to mention that the Quake 3D test which is so widely used is in fact faulty. Underclocking both CPUs to 400Mhz (i.e. halving the speed) and using an nVidia GeForce caused the frame rate to drop by only 2 % at the highest resolution! There is some serious bottlenecks on the video card. Who needs a 1Ghz CPU then?!
  • Okay, I'll admit, it took me a good minute or two of reading the site to sit there and go, ummm... what the.. OH! HAHAHHAHAHHAHAAHHAA!

    What threw me off was the calling it hydroxylic acid or hydrogen hydroxide, until I realized that an hydroxide is an OH, so hydrogen hydroxide is HOH which is H2O. I also just realized that hydroxylic (HO, but that's a stretch of terminology) acid (H) is also H2O.

  • Hey, thanks dude.

  • BTW.. Dihydrogen Monoxide is a joke, but please don't ruin it, because it's funny as hell reading it and then when you finally realize what DHMO is.
  • Honestly how many of us are going to use a 1ghz processor for something other than RC5, Seti, and Quake 4? Thanks, but no thanks, i'll stick with my 266 and keep stacking on the ram and storage. I have yet to see a useful program that requires mor than a 266. Sure, maybe some new media device will come along soon, and it will be a must have, but right now I'm running netscape, mozilla, xchat, gaim, x, and enlightenment, and my processor is 97% idle.
  • Don't be stupid - they posted it under "It's Funny - Laugh", so they obviously knew it was a joke.


    "You can't shake the Devil's hand and say you're only kidding."

  • HAHAHAHAHAHAHAHAHAHAHAHAH I just read throught that site, OMG, that's almost too good to be true : ) I've got to link that site to some people I know......
  • I wonder if Nasa's Galileo [] is powered by AMD. If so, let's overclock that baby, because hey, when you crash a $1.5 billion probe into an ice-covered satellite, you're not gonna find a better way of cooling down an overclocked chip.

    It's just a small matter of it surviving impact. :)

    .sig Instructions
    step one: place .sig here
  • Slashdot will post any story as long as it sounds good. They will reject any story even if its really important if the person submitting it didn't make it sound good. so much for editors
  • ok where is your explanation.
    second of all slashdot will not post a story unless someone has written a submition that sounds really good. Stories will be submitted and rejected. A week later the same story will be submitted and made to sound remarkable. This story will get accepted even though its the same story.

    Looks like you are the moron who fucked up anyway.
    No need for excuses.
  • Then Kryotech can overclock and cool the NEW cpu! that's what's great about them, upgradability!
  • I have an athlon 750 with the asus k7m motherboard. Overclocking is as easy as going to bios and selecting what I want the FSB set at. I havn't messed with the multiplier (its a jumper) but by changing the bus I can get it pretty high, not sure exactly how high, but well over 800mhz. I was running it over clocked for a while, but got paranoid that it was causing problems. Maybe, may have been flukes.
  • Importance of the cache existing is one thing. However, if you're going to have cache on a gaming rig, faster is better than bigger. Look at the competition at Anandtech between dual Celerons and P3s in SMP Smackdown [] if you doubt that. :)


  • Sorry, this should have been with my first reply.

    When I said the cache was helping the P3 in comparitive benchmarks, I wasn't referring strictly to fp/gaming, but to benchmarks as a whole. On-die cache could make the Athlon bench faster all around, not just on some benchmarks.


  • This is not completely true. Yes, with sufficient cooling and added power, one can increase a processor's speed dramatically. However, this cannot be done to "almost any speed," because at a certain point, the signal strength becomes so great that the signal in one wire interferes with its neighbors, and that is a Bad Thing(TM). The maximum power is partly determined by architecture, and partly by die size. However, one can usually take a processor to half again its rated speed, even if it's not a Celeron, with sifficient cooling and provided it's not top of the line.


  • by Datafage ( 75835 ) on Saturday March 04, 2000 @07:03PM (#1225379) Homepage
    The move to on-die cache is what has me most interested. High-speed cache is what affects gaming most, not the actual size of the cache, and as we all know, gaming is what counts.:) For repetitive tasks, such as searching a database, a larger L2 cache is superior. For non-repetitive tasks, like drawing triangles, the faster cache will win out. Of course, if you can get both, like the Xeon or alleged Athlons with 8 Meg full-speed cache, life is good.

    Full-speed cache is the only thing letting aluminummines approach or outperform Athlons, just look at the graphs and you'll see that the P3s get closer and closer as the speed increases, and the Athlon's cache gets slower and slower by comparison. With full-speed cache, AMD will be in a very good position as far as benchmarks go. If you think the Athlon is a good performer now, just wait. :)

    Am I the only one thinking we'll be seeing the BiAthlon and TriAthlon just like the P2 and P3 came along?


  • Well, that's one view.

    The other view is that more and more mainboards are using DIP switches instead of jumpers, making it easier. And of course ABIT brought BIOS-level clock setting changes, which (IMHO better)companies like ASUS now include.

    I haven't had any athlon-overclocking experience, but I understand it is more difficult than changing a BIOS setting. ;-)
  • Power consumption of an Athlon and/or a PIII are on the order of 20-45 watts. No where near a kilowatt, but still considerably greater than milliwatts.
  • There is a lot more to it than just set-associativity vs direct-mapped. HP's PA-RISC line recently changed over from 4MB external direct-mapped caches (2MB instruction-cache and 2MB data-cache) on the PA-8200 to on-chip 4-way set-associative 1.5MB (0.5MB instruction-cache and 1MB data-cache) on the PA-8500.

    For some application code (specifically *our* custom floating-point intensive code) performance went in the toilet, in some cases the new chips are more than 50% slower than the old ones, despite a doubling of clock from 220MHz to 440MHz. Part of the problem is a poor (simplistic) cache-line replacement policy and the rest may be due to some chip-specific assumptions we made when developing on the PA-8000/PA-8200 that do not apply on the PA-8500.

    So, I agree with your ultimate point that "it's hard to make [accurate] generalizations," but I must extend it to all levels because *most* would say the PA-8500 is much better than the PA-8200, but for us it definitely ain't.
  • Instead, you'll need a device that sits between the chip and mobo

    Has it struck anyone else that this needn't be a separate device, but could be a part of the mobo. Overclocker friendly mobo makers (hello ABIT, are you listening?) could include the circuitry in the board, and configure it from the bios... now that's easy overclocking!

  • we have to assume that they are actually designed better.

    As far as I know, these are the same K75 core, 0.18 micron die chips.

    The difference is probably just in yield. When Kryotech released 1Ghz, there were to few chips capable of running at 1Ghz air-cooled. Now, the proccess has run longer, it is (probably) tuned somewhat, and AMD has had time to save the best chips for a while. Remember, neither Kryotech nor AMD need to sell huge quantities of the top chips... the prices are huge!

  • Ahem. CPUs are not cheap. :P My Athlon 750 cost me $550 when I bought it (would have paid $650 if I didn't have to wait for the next paycheck). Okay, I have to back up a little bit. High-performance CPUs are not cheap. The Athlon 650 actually costs less than the 600.

    As I understand it, AMD stopped making 600's and 650's sometime late last year, and to keep up with the demand that was still in place for the lower-clocked Athlons, they actually underclocked 700's and 750's to keep up.

    My very same CPU now costs about half as much as I paid for it with not even a month passed.

    And to the guy that said Athlons are hard difficult to overclock? That is shenanegans. AMD made a little connector on the top of their PCB that lets you slip on a little (tiny) overclocking device and go to town. You can use it with the cartrige installed, but what the hey. You need to take off the cartridge anyway if you want to use a "decent" heat sink. (I bought an Arctic Cirlce cooler)

  • by Sp@mMan ( 82919 ) on Saturday March 04, 2000 @07:23PM (#1225386)
    Also, metal cases for microwave shielding will cost money. What happens when people start skimping on

    the case, or putting the new 10000Ghz motherboards in their old plastic boxes

    Uh, dont you think that companies would be smart enough to have shielding around the processor itself, rather than relying on the case? I think people think retards work in the R&D section of companies, they ARE aware of severe problems like THIS.


  • No, actually, Intel has said for quite a while now that they would be releasing one gigahertz at the end of the first quarter. Although, as you said, this will only be in small quantities (which is in fact true). Don't expect these in stores until the end of the year.

    My whole feeling on the processor war, is that Intel/AMD could release the chips now, they just don't, to make their businesses thrive. Like, this way, you have to keep upgrading... and therefore they get more money. Well, I don't know about my reasoning, but I'm pretty sure that my hypothesis is true.
  • Am I the only one thinking we'll be seeing the BiAthlon and TriAthlon just like the P2 and P3 came along?
    ROFL , boy I like the sound of that. I'd wait until the Pentathlon comes along, 5k run, 5k bike ride, 5k swim, Overclock 5 cpus, lose 5 megs of ram.. Or however the hell it goes.
    All kidding aside though some of these people have brought up some very valid points.
    What about the microwave output on one of those new 1Ghz+ cpus? People worry about the radiation coming out of a little cellphone, and this is a bit worse then a cellphone.
    But for me at least, I just dont give a damn about the new cpus coming out OR how much I can overclock it to. Name 1 reason a non-technical user would have for a cpu running at 1Ghz? How bout 500Mhz for that matter? The only reason I could see for owning one is A.)Server B.)Graphic Intensive work and MAYBE C.)COmpiling large programs.
    Personally, I had my share of fun overclocking cpu's and trying to take the machine to the max. Now, I try to take the software to the max. I recently bought an Athlon 750, and dont plan on buying a new computer for quite awhile again. I was getting along fine before with my p200 as it was. The only reason I upgraded was Im rally getting into some C and VB stuff and wanted the programs to compile a tad faster. Alright, and because Q3 wasnt playing so hot on it either.

    The vast majority of end users out there dont need anything above a PII 300 with 64-96MB Ram. Thats it. FOr their AOL, their Outlook Express, their beloved solataire.
    I'm sorry this has turned out to be a rant all, please forgive me. Theres nothing I get more passionate about then technology and the Average Joe who's going out to buy that top o the line CPU to run his wordpad.

  • I heard from a very reliable source that a dual athlon enabled board is coming out later this month to mid April. Believe it was sposed to be AsusTek who is making it.

  • I especially liked the use of the phrase "moderate-to-severe head-explodings"

    Good job Mr. AC, I wish I had some mod points left!
  • are they essentially just overclocked versions of earlier chips?Well, since they will not be using any Kryo-cooling technique on the chips, we have to assume that they are actually designed better. Otherwise why would Kryotech bother working on their cooling technology to get it to work if air-cooling did the same. Now, they might be slightly more overclocked than currently (perhaps the 1Ghz is a 900 overclocked or something) but for that, we'll have to wait until the chips come out for some good analysis.
  • Dual Athlons [ BiAthlons =) ] won't be out for a while -- not until later this year (possibly until November, so the rumor goes). For once, I hope the rumor is false.
  • Complete bullshit. I don't think I could have loaded one up any fuller than this. Man, It must have taken a while to come up with all that crap. What did you eat? Let's just say that, if you really work for AMD, I hope you keep the toilets clean, cause only a janitorial worker could pull up all that B.S.

    OK, to set the record straight, the L2 cache is a proven mechanism for increasing the average access time for data in a computer system. On die L2 caches can be as simple as you like. The performance gain comes in the high bandwidth availability and the distance from the processor core. The only real problem with on die L2 caches is that they increase the size of the die, and the cost of the chip.

    If I were to believe that AMD had such problems, then it would NOT be in the design of the L2 cache, but rather the implementation. And I don't think you could implement such a simple device in such a poor manner. I could build an L2 cache with tinker toys that worked better than something that had these kinds of problems (problems which, by the way, CANNOT physically exist in the way they are described here).
  • yep, I think it's made up. Why? Cause I design caches. If you push too hard, things don't work. That doesn't make the tech bad, it makes your company stupid. If they have these problems, they are really trying to do something very very wrong. (like save too much money)...
  • Ok, so like let me overclock my 1GHz to what? 1.1?that's not really neat... the percentage gained in performance by overclocking goes down as the speed increases, because the relationships between die size, speed, and heat are exponential not linear... The faster things get, the harder it will be to overclock, at least without cooling... I see a nice future for kryotech...

    la la lalalala
  • i mean, to think that there might be an outside cause for their seemingly eternal place in the urinal of society.
    actually, i'm being sarcastic. you're a moron, and you seem to find pleasure preaching a holier-than-thou, more-deserving-than-thou, better-than-thou attitude. i know noone will read this, but i hope you do.

    i sincearly believe that, placed in the same situation, any individual would have the same 'chance' of getting out of a ghetto.... to think otherwise is to think in piss-headed social-darwinistic terms.
    i hope you understand what i'm saying.
  • The links don't work for me now even though they are the right address. They take you to the beginning of the story, just click forward four times.
  • I think you are overgeneralizing based on a few test cases. One thing to keep in mind is that saying a cache (or any kind of memory) runs at 300 Mhz does not fully (or even come close) to fully describing how fast the cache is in real life. Sdram and FPM memory both can run at 66 Mhz, yet Sdram has higher bandwidth and lower latency.

    One factor (for cache) is called set associativity. I'm not an engineer yet, and haven't studied this formally, so beware. Higher set associativity is better. Set associativity indicates that the cache can be used more effectively. You could have a smaller amount of cache, with a higher set associativity that would be as fast as a bigger cache with lower set associativity. This is running at the same speed.

    Also, retrieving each byte of data has a certain latency listed in clock cycles (at the frequency it runs at). This latency is as important as the actual MHz rating of the cache.

    I don't have the numbers on me, but I found a comparison between the latencies of the K6-3's, Celeron's, and Coppermine's. The Coppermines have a very fast cache, faster than the other two. Much lower latency than the K6-3, even though both look equal at first inspection.

    Basically what I'm saying is that it's hard to make generalizations about which case is better, other than to say this one processor is better than that another.
  • Thanks for the information. I didn't mean to imply that set associativity was the only factor, just that it was all that i knew of. Sounds like you are doing some neat stuff.
  • As many things as there are that I love about Slashdot, I really dislike it when stories just vanish, or something is changed *poof* without any record of it having been different.
  • Why do you care? Why are you so bitter about it? You don't like it. Don't buy it. Don't read about it. Don't care about it. You wish for an economic downturn so people will have less money? What a crock. Why wait so passively?maybe you could send some mail bombs to these assholes who aren't making the world into your utopia. Get a life.
  • by billybob jr ( 106396 ) on Saturday March 04, 2000 @07:39PM (#1225402)
    I would argue just the opposite. L2 cache is less important in games than other applications. Do you remember the first Celerons with no L2 cache on die or anywhere else?

    They benchmarked very poorly in the typical ZDnet benchmarks for Windows. They also performed pretty well in games such as Quake. Here are some benchmarks from Tom's Hardware:

    Office Performance Windows 98 []
    3D Gaming Performance []
    Notice the difference between a 300 Mhz Celeron with 128k L2 cache and one without.

    in Quake2:
    with L2 cache: 50 frames per second
    without L2 cache: 45 frames per second
    pentium 233mmx: 32 frames per second

    in Business Winstone:
    with L2 cache: 25
    without L2 cache: 19.3
    pentium 233 mmx: 19.5

    Granted this is only applicable for Quake2 (and the other quake engines more than likely), it still indicates at least one game doesn't depend very heavily on L2 cache. I think the generalization to be made is that L2 cache boosts integer performance moreso than floating point performance.

    Check out the Coppermine vs. Athlon benchmarks you were referring to. The ones I've seen indicate that the on die L2 cache helps the Coppermine catch up to the Athlon in integer performance, but not in floating point.
  • I heard that Samsung is helping AMD make the chipset and that it'll be available 2nd quarter 2000, they're working on it right now, and judging by their other releases, it'll probably be realeased earlier than sceduled =)
  • Both Intel and AMD had previously announced the 1 Ghz Pentium and Athlon for mid-2000. Did they speed up the assembly line? I think not. More likely these announcements are for small quantities. We won't see any real supply of these chips until July at the earliest, IMHO.

    Note: I could be wrong.

  • Yeah. There are CPU diagnostic programs for PCs, such as AMIDiag [], but few users have them.
  • Well, being a former overclocker myself, the hey-day(-5 points for spelling) seems to be over to me. No longer is overclocking simply a dip switch or jumper change. With these new cartridge-afied CPUs, you hafta break into the things, and maybe even de-solder and then re-solder those miniscule eyeball straining resistors. With chips running as fast as they are nowdays, I opine that a modern-day overclocker is significantly more bleeding-edge than those of yesteryear, like me. I do admit that I miss it...
  • Do believe his quote was "40k of RAM should be good enough for anybody. Anyways, the reason why KDE and GNOME are bloated is because they're concerned about features and usability first. A WM should be fast, yes, but it should be usable. Speed in KDE and GNOME is falling behind because there are more developers interested in features than speed developing for these WMs; take a look at E and tell me if that's not eyecandy. ;-) Welp, the speed comes next. that's the way the kernel's been for a while, and that's the way most stuff is as far as open source. Make it work first, then speed it up, as it's rarely finished being developed. Micro$oft has a similar idea, but it's more that optimization is last, so that they can make it usable first, and dumb it down a bit to run well on the faster desktops. I've been using my PII266 since the day Integrated Electronics (Intel...) put them in boxes for the public, and it's done well. E was really slow at 10, 12, 14, and it's speeding up a little at 16, because it's under constant development. it's fine for me w/ this box. Microsoft stops developing and only starts bugfixing after the release of their product. Most software companies are like this and Open Source is the exception, and that's why linux seems to get faster on my PII and P166 every time I upgrade stuff... I'm worried about M$, they're digging a big hole for themselves with overpricing... if they do fall they will slow processor and RAM sales dramatically as open source most likely will be the "NeXT Step" (pardon the pun). if your machine is too slow, optimize the source! or, wait for the next version to do it for you... I've seen it, too. 2.2.4 is WAAAY slower than 2.3.36 or 2.3.45...
  • by ArchieBunker ( 132337 ) on Saturday March 04, 2000 @07:55PM (#1225409) Homepage
    Water can boil at any RF frequency. When you radiate 1kw of power into a steel box its going to cook something. This has nothing to do with your computer. The cpu clock is running at 1Ghz, but at very minimal power, probably milliwatts. What takes so much current is the 40 million transistors on the cpu. If your athlon suddenly started radiating hundreds of watts of RF I would be worried.
  • because it's funny as hell reading it and then when you finally realize what DHMO is.

    If it takes you that long to determine what dihydrogen (two hydrogen) monoxide (one oxygen) is, you have greater issues to deal with.

  • Now I know you people want to overclock everything, but man, CPU's are CHEAP! Why even bother anymore? Now overclocking RAM is a different story... anyone have any luck running PC133 at 133 MHZ on a Microstar 6195 motherboard?
  • >> You are at least as stupid as they are. Overclocking a cpu is stupid. Overclocking memory, OTOH, is the most brain-dead, idiotic, deadass dumbshit thing you can possibly do. You are essentially saying "I WANT random crashes." I hope you all burn up your crappy hardware.

    I asked if anyone got PC133 ram to run at 133... Thats not overclocking you grumpy twit.
  • You're right. What's interesting to me is that while chip manufacturers (Intel in particular) have made it much harder to overclock their chips, other hardware producers, especially high-end graphics cards, often have clock control built into the Windows drivers.

    It's an interesting divergence of philosophy, and it'll be cool to see if AMD learns something from the positive reaction to this and offers something similar.

  • by Captn Pepe ( 139650 ) on Saturday March 04, 2000 @07:49PM (#1225414)

    The article brings up the fact that, with Socket A (as opposed to Slot A) chips coming sometime in the not-too-distant future, the whole goldfinger card issue will be more or less moot. Instead, you'll need a device that sits between the chip and mobo, or a "slotket" type device that plugs into an older, Slot A, board. There are, however, pins on the chip die designated for these sorts of things, so it shouldn't be too hard.

    I agree that the on-die cache is going to be the most important advance, performance-wise. The L2 cache was running at 1/2 clock, then got bumped down to 2/5 clock at around 700 MHz (due to problems with high-speed L2 cache chip suppliers, I believe). When this goes on-die, the cache will finally be able to run at the full clock frequency, which will make the difference between 800 MHz and 1 GHz look paltry by comparison.

    On the whole, though, we may be getting to the sorts of CPU speeds where overclocking no longer serves any useful purpose. A 1 GHz chip (or even a 800 MHz one) can, for most tasks, outpace any other componant of the system. So is overclocking my chip to 1.3 GHz going to make a major difference in my Q3 frame rates? Probably not. The graphics card (yes, even a modern 3D card) became the major bottleneck about 400 MHz ago. Sure, that might let me compile software faster, but in this case, I'm going to go with the rated speed to avoid single-bit errors and the like. Heck, with a chip that fast, I might even underclock a bit, just for the added stability.

  • by pjbrewer ( 140003 ) on Saturday March 04, 2000 @07:01PM (#1225415)
    Ok, so when do we start getting machines that can excite some mode of H2O?

    Most microwaves ovens operate above 2Ghz, but arent there some modes of water down around 1Ghz?

    Also, metal cases for microwave shielding will cost money. What happens when people start skimping on the case, or putting the new 10000Ghz motherboards in their old plastic boxes.

    Well, power and frequency are different things, I suppose. But one can still wish for a few exploding heads anyway....

  • Is there any difference between the new 1Ghz chip about to be released and the 800's overclocked to 1Ghz that are already avaliable at places like Kryotech []? Are the new retail chips actually designed better (ie smaller die, better cooling, new layout...), or are they essentially just overclocked versions of earlier chips?
  • I used to do work with autonomous robotics, using a motorola 68HC11. One day, I needed a pulse at a certain frequency, higher than that of my 8Mhz processor, and I didn't want to use an external capacitor. So, I overclocked it to 50Mhz, slapped on a heat sink and it promptly crashed after 30 seconds, never to get up again. There is a moral to this story, I just can't remember what it is.
  • I'd love a dual athlon. Tell me, your reliable source... can you tell anyone ELSE where to see such information to put mind mind at ease about the actual existance of such an awesome mobo?

    - Xobes
  • Good point. But I was emphasizing the difference between the prior Athlons and the newer ones. Still, you are correct.
  • by Pahan ( 151973 ) on Saturday March 04, 2000 @07:45PM (#1225420)
    AFAIK, you can run almost any CPU at almost any speed, assuming you can tweak the motherboard clock. However, running it at higher speeds reduces the clarity of the signal (the detectable difference between 0 and 1), and that can only be overcome by increasing the voltage. But more voltage means more heat and you will need more and more cooling to keep it from melting and otherwise becoming damaged. This is what Kryotech people do: cool the CPU, allowing them to maintain signal clarity at higher speed. However, it seems that these newer Athlons will be able to run at those speeds without needing the voltage increase or the extra cooling. On-die L2 cache is also good: placing it there will allow it to run at CPU speed (hopefully), and that would further improve the preformance. (Just look at what it did for the Intel Celeron.) Of course, Intel will try to match it, in speed, in price, and/or in PR. (Hopefully the first two, not the third.)

    I love competition!

  • I wanted a little more speed from my Columbia Data Products 50lb lugable, and swapped out the 8088 (@ 4.7mhz) for an NEC V20 (@ 8/10mhz?). It worked, and I was happy...for a week or so! (Yes, it's not overclocking...but a brain transplant. Cheap at the time too!)
  • This is an interesting question. If the new "rated at 1GHz" chips have a "better" design, than they can be pushed even farther by O/Cers. But there is the lurking possibility that the chip is the exact same as the 800MHz rated chip, just with an upped multiplier. Wow, what a sneaky way to make extra cash... why didn't Intel think of that?

    Oh... wait... nevermind.

    I am the Lord.

  • ...are incorrect. That would only be true if there was a maximum of five posts.

    You posted at #29. So at the time when you made your stupid comment, he was only off by ~3.4%.

    Judging by the subject matter and day of the week, I predict that this story will receive at least 150 posts before it is moved off the main page. If my prediction proves correct, than said troll will be less than 1% off his mark.

    Any statistician would commend an error rate so low, when applied to such an erratic and unpredictable subject as Slashdot Post-number Trolling. Let us have a round of cheers for our heroic AC, who showed remarkable courage in continuing to post in the face of such amazing odds. Huzzah! Huzzah! Long live the AC! Huzzah!

    I am the Lord.

  • I'm going to have to agree with you on this one. I hate to feed the conspiracy theorists, but we all know that MS and much of the PC industry is helping feed Intel with the MHz-hype. X (as in X windowing) is proof that a 300MHz CPU is still plenty fast for most PC users.

    I honestly have no idea how MS managed to create software so bloated and slow that a 300MHz seems too slow. The source of the problem IMHO is Windows' poor reclamation of memory. So the damn thing starts paging every two seconds, and IDE just can't keep up. So we throw more and more MHz at it, which appears to solve the problem, but it's just hiding it, really. And Intel gets rich off of Microsoft's poor OS design. We've all seen the situation when Windows runs out of resources, and you close all of your applications, and it *still* says it's low. What's up with that? How could they have released such buggy SHIT?

    Windows users: you don't need a 1GHz CPU. What you need is more RAM (128MB minimum) and some UltraSCSI disks. (Actually, what you *really* need is to switch to a a different OS. If you're not ready to try a free UNIX, try a Mac.)

    The one good side of the MHz-hype is that the so called "obsolete" chips are SOOOOOO cheap. You can slap together a 350MHz Linux box for a song. And 350MHz runs it just fine.

    I am the Lord.

  • This Intel vs. AMD 1GHz race is really marketing positioning, or "mine is bigger than yours". Both will allegedly announce 1GHz chips this month, within days of each other (AMD first?), but they will not be available until 3Q. Intel has problems shipping 733 and 750 PIII's, and the latest available _engineering samples_ are "only" 866 MHz. And they were weeked to work. The 933's are not available even as engineering samples. NO ONE has a 1GHz PIII, not Dell, not anyone else. Oh, sure, they are coming, but don't have someone charge your credit card this month for one. ;-)
  • >I can assure you that most of them observe SBEs as a BSOD in their GameOS, because they spent all their cash on a higher-clocked processor and then bought Joe's Factory Thirds "PC92-1/2" Memory from the guy on the corner wearing a trench coat.

    Wow, that guy seems much more trustworth than the people I usually buy memory from... :-)

    And besides, I have a PC-66 DIMM that lasted over a year at 100 Mhz ( :-P Mine is bigger than yours [jj]).

    And I'm about to get another 5400 RPM drive for my uberc00l Ultra66 which is now a Fasttrack controller.

    And lets not forget the extra cooling system - Nothing beats running your computer inside a refigerator for that ultimate speed.


    I figure there must be a limit to how far I can push my machine, that's why I've abstained from putting my computer in a fridge. Maybe sometime I'll have to try, though. I'm getting tired of only 1 hour uptimes... :-)
  • >Of course, the crux of the matter is that those systems won't run GameOS which all these wankers want so they can play their 31337 g4m3zzz!!!!@@!!$$!!!#!!!. Idiots.

    (I'll assume GameOS = Windows 98)

    Yeah, but there are a lot of people running GameOS. And it is hungry for more power, all the time. So don't expect there to be a mad rush for workstations anytime soon, unless all the GameOS games work with a real OS all of a sudden. I don't see that happening, so the push for more processor power to run those games will continue.

    Gamers don't care if it takes a few more seconds to load a Q3 level because their hard drive sucks. They care that the game runs fast. And that is it. Once it is loaded, as long as there is no swapping, 64 Mb RAM, and a 5400 RPM drive will do, as long as there is a fast 3D card and a fast processor under the hood.

    The fact is that the performance increases found by going to SCSI/etc... are wasted on most people. Games only want a fast processor and fast graphics board. Business apps run well on even slow systems (by today's standards, eg. 300 Mhz). So the market for SCSI, etc... is only of importance to people building servers. And while the server market is large, so is the game and business market.

    And let me tell you, there is a lot of purchasing power from the Gamers... So companies listen. Expect faster video and processors to keep on coming.

    Just my 2 cents...
  • >There is a moral to this story, I just can't remember what it is.

    The moral is: Always have spare parts handy.

To write good code is a worthy challenge, and a source of civilized delight. -- stolen and paraphrased from William Safire