Slashdot Mirror


Current Processors Tested With Linux

Happy-Jollies writes "The team at LinuxHardware.org have kept us up-to-date on the latest in processors for quite some time now and they're at it again. With the latest release of the Pentium 4 'Prescott,' many Linux users will be deciding where to spend their money. LinuxHardware.org's round-up takes a look at the Prescott, Northwood, Extreme Edition, and the AMD Athlon 64."

330 comments

  1. Why did they leave out ... by burgburgburg · · Score: 5, Interesting

    the G5? It can run linux too, you know.

    1. Re:Why did they leave out ... by falcon5768 · · Score: 2, Interesting

      my thought exactly... it might run OS X but if you really wanted to you cou.ld wipe the HD and run linux as well... no reason to leave it out of the comparison...

      --

      "Slashdot, where telling the truth is overrated but lying is insightful."

    2. Re:Why did they leave out ... by dreamchaser · · Score: 4, Insightful

      I agree in a sense, but for now most people who buy G5 machines will stick with OS X. Yes, I know IBM is making some G5 boxen too, but the ratio of those to G5 Macs sold will probably mirror the ratio of Macs compared to x86 stuff.

      Yes, the submission should probably read 'Current x86 Processors Tested with Linux', but in reality the vast majority of individual Linux boxen will be using x86 based hardware so I don't think it's that big of a deal.

    3. Re:Why did they leave out ... by Anonymous Coward · · Score: 1, Interesting

      > so I don't think it's that big of a deal.

      The thing is, if they're comparing CPUs for the power and speed and all, why not include the G5's... will the x86's get trounced by them or what? Are they AFRAID to include the G5's?

    4. Re:Why did they leave out ... by Anonymous Coward · · Score: 2, Insightful

      I looked on pricewatch but couldn't find any G5 CPU/Motherboard combos. Where can I buy them and how much are they? What power supply and form factor should my case have.

    5. Re:Why did they leave out ... by GOD_ALMIGHTY · · Score: 4, Informative

      That doesn't make sense. Yellow Dog is an Apple Authorized Reseller who will ship you a brand-spankin new G5 or XServe with Yellow Dog Linux running on it and under warranty from Apple.

      They really should have used a Yellow Dog box or named it an x86 shootout.

      --
      Arrogance is Confidence which lacks integrity. -- me
    6. Re:Why did they leave out ... by mangu · · Score: 1
      Are they AFRAID to include the G5's


      Perhaps Apple marketing paid them not to include the G5's. It would look bad for them if the x86's weren't trounced by the G5's.

    7. Re:Why did they leave out ... by Thud457 · · Score: 2, Interesting
      "G5... IBM"

      I never understood why IBM has stuck with the x86 PeeCees this long. Lord knows I'd like a nice IBM laptop with a Power PC in it. If they could do it for a comprable price.

      --

      the preceding comment is my own and in no way reflects the opinion of the Joint Chiefs of Staff

    8. Re:Why did they leave out ... by October_30th · · Score: 2, Informative

      Simple reason: MS Windows does not run on a PPC.

      --
      The owls are not what they seem
    9. Re:Why did they leave out ... by teh*fink · · Score: 2, Interesting

      also why did they leave out other (admittedly not) mainstream chips, such as via and trasmeta's offerings? i would much more interested to see linux's performance on these chips, frankly.

      --
      "I DARE you to make less sense!"
    10. Re:Why did they leave out ... by Frymaster · · Score: 1
      yes, but, the prerformance of yr linux-on-mac set up will depend a lot on the distro.

      note that almost all ppc binaries are just that... ppc binaries. no optimizations for g3 let alone g5. these binaries are designed run on a 601! so, if you want to get real performance out of yr linux-mac run something like gentoo...

    11. Re:Why did they leave out ... by bhtooefr · · Score: 2, Interesting

      They wanted high end chips like the Prescotts, Northwoods, and AMD64 chips. VIA and Transmeta aren't even close in clock speed OR IPC to either Intel or AMD. VIA is slow because they're running old fourth-generation (read: 486) architecture, with sixth-gen instructions (think Pentium III, actually). Transmeta is slow because they're emulating an x86 - they've probably got very high VLIW IPC, but their x86 IPC is what counts.

    12. Re:Why did they leave out ... by millahtime · · Score: 1

      Don't forget that the G5 and G4 processors are used for other things. Like mars rovers, and in many other military and applications like that. It is actually a very popular series of chip outside your basic pc market.

    13. Re:Why did they leave out ... by boaworm · · Score: 1

      I own a DP (1.8 Ghz) G5. I would be very interested in knowing how well it would run linux. I do love OS X, but it hurts my geek-karma not running linux on my "desktop".

      But I guess if i'd really want to know I could always try out, write myself an article and get slashdotted :)

      In that case, i'd try out Gentoo, perhaps Yellowdog, NetBSD (current has SMP support as far as i know), and benchmark that vs OS X. Perhaps someone out there already have done this, and could enlighten me ?

      --
      Probable impossibilities are to be preferred to improbable possibilities.
      Aristotele
    14. Re:Why did they leave out ... by spaceyhackerlady · · Score: 4, Interesting
      Yes, the submission should probably read 'Current x86 Processors Tested with Linux', but in reality the vast majority of individual Linux boxen will be using x86 based hardware so I don't think it's that big of a deal.

      Having just had my first experience running Linux on something other than an x86, I was curious too.

      You can blame it on this very forum - after reading the article I bought an Ultra 5 on EBay and loaded Debian on it last night. Installed most of the packages over my ADSL connection. Worked like a charm.

      ...laura

    15. Re:Why did they leave out ... by FuzzyBad-Mofo · · Score: 1

      I'm not seeing a downside here..

    16. Re:Why did they leave out ... by Frymaster · · Score: 3, Informative
      i've run both yellowdog 3.0 and gentoo on an ancient imac (rev a). when the hardware is that slow, you notice small speed gains more. while yellowdog is pretty snappy and has the ease-of-use advantage (anaconda, yum &c.), the gentoo was noticably faster.

      be warned - to get the boosts yr going to have to start at a low stage install and this results in a looong install time. on my imac it took (wait for it) a week to install. and updates take forever too. but, as long as you read up on your use flags and set them well you'll get a fast core system.

    17. Re:Why did they leave out ... by October_30th · · Score: 1
      One word: sales.

      You can't make a profit selling computers unless you can run Windows on the hardware.

      --
      The owls are not what they seem
    18. Re:Why did they leave out ... by FuzzyBad-Mofo · · Score: 1

      Really?

      Of course, if Apple was a startup today they probably wouldn't make it. Your point is valid, at least for now. But nothing can last forever, even Microsoft monopolies. :)

    19. Re:Why did they leave out ... by diablobynight · · Score: 1

      Many other millitary applications
      may I ask what other millitary applications? And be careful when you answer, you never know how much the person your speaking to, knows

      --
      Anonymous Cowards - Oh God, How I hate you
    20. Re:Why did they leave out ... by Thud457 · · Score: 1
      Yeah, but we're talking IBM here. A lot of their customers are vertically integrated. Who cares what it runs as long as it can be made to get the job done.

      errr, well you do have that whole "OS/2" thing. And I guess getting locked in by buying a custom enterprise system from IBM is just as bad as being indirectly locked into MicroSoft.

      --

      the preceding comment is my own and in no way reflects the opinion of the Joint Chiefs of Staff

    21. Re:Why did they leave out ... by Short+Circuit · · Score: 0

      Somehow I doubt G5s and G4s are used in military/space applications. Components for use in those areas have to be hardened against radiation and the elements pretty damn well. You don't normally see consumer-performance processers in such extreme environments. (Not saying it's impossible, though. I've seen some pretty damn tough x86 laptops.)

    22. Re:Why did they leave out ... by Dan+Ost · · Score: 1

      I believe the 2 NASA rovers on Mars are both using a PPC chip (G3?).

      --

      *sigh* back to work...
    23. Re:Why did they leave out ... by drew · · Score: 1

      well, if you look at their benchmarks, three of the six are based on programs that likely aren't available in source or non-x86 binary form. it would be kind of a lame benchmark if for half of their tests they said, "well we couldn't compare one of our processors in this category".

      of course, i may be wrong- it's possible that there is a ppc linux version of q3 or unreal tournament available, but i've never heard of them....

      --
      If I don't put anything here, will anyone recognize me anymore?
    24. Re:Why did they leave out ... by Anonymous Coward · · Score: 0

      I don't believe the G5 is a processor. I think Apple tends to call the IBM 970 a G5 sometimes, but that does not make it one.

    25. Re:Why did they leave out ... by platypus · · Score: 1

      Not that I concur with your parent post, but at least the 68020 is used" in military applications. Yes, I know, that's not the G4, but at least this is a chip which has been used in a Mac, and you sound as if you were interested in that stuff.

    26. Re:Why did they leave out ... by aastanna · · Score: 1

      Well...I could tell you...but then I'd have to shoot you.

    27. Re:Why did they leave out ... by Anonymous Coward · · Score: 0

      You can find them at http://store.apple.com/ , they and they start at about $1600, throwing in a whole rest-of-computer for free.

      Or did you for some reason want the "Current CPUS For People Who Dislike Supported Products" article?

    28. Re:Why did they leave out ... by Anonymous Coward · · Score: 0

      What if I already have everything else I need? $1600 seems a bit steep to test out a different processor.

    29. Re:Why did they leave out ... by MuParadigm · · Score: 1


      If you read the article, you'll notice that they used Gentoo for the testing, so, even with your analysis, there's no reason why they couldn't have done the PPC testing mentioned above.

      I'm not a Mac user or fanboy, but I would have liked seeing those results as well.

    30. Re:Why did they leave out ... by MuParadigm · · Score: 1


      Yeah, there were a lot of odd things about that test. The first thing I noticed were the higher end sound and video cards. They could obscure the difference between processors, or even create differences if data transfers from chip to daughtercard have a thunking overhead for the Athlon.

      Also, I thought the recommendations were a little off. Compared to what I saw in the tests, Intel (Northwood) would still be the better chip for most home users and gamers. I'm not sure why they chose the Athlon.

      Hell, you could get 2 of them and do SMP for less than the cost of single Intel EE, and the way the Athlon failed to adequately scale up to 1600x1200 resolution for UT 2003 was quite disappointing. Certainly not a chip I'd want to use for Doom 3 (only two months away!).

      Anyway, I think the AMD 64 bit technology is great, but these tests lead me to think it still needs a little work and tweaking.

    31. Re:Why did they leave out ... by diablobynight · · Score: 1
      I am USMC, and I don't recall seeing anything about G4s or G5s in any of our weapon specs. Not even in the new Anti Tank weapon.

      http://www.global-defence.com/2001/WSpart12.html

      --
      Anonymous Cowards - Oh God, How I hate you
    32. Re:Why did they leave out ... by millahtime · · Score: 1

      The space rovers use them and they have been hardened against radiation.

  2. Extra Transistors by swordboy · · Score: 5, Interesting

    I know that this is a little off-topic, but does anyone know where the extra transistors in Prescott are coming from? There are 125 million in that baby. Even with alleged 64-bit extensions (hidden, at this point), SSE3, improved branch prediction and the extra large cache, there should be under 100 million, no?

    --

    Life is the leading cause of death in America.
    1. Re:Extra Transistors by paitre · · Score: 4, Informative

      Actually, there's some fairly hefty core changes involved in making the integer pipeline 31 stages instead of 20. Almost enough to account for most, if not all, of the additional transistors in this thing.
      I'd actually be suprised if the AMD64 extensions were in this chip...most of what I've been hearing/seeing has Tejas being the earliest we could see them.

    2. Re:Extra Transistors by ZuperDee · · Score: 1

      3 things I can think of:

      1) Extra pipeline stages (and all the baggage that entails)
      2) Extra L1 and L2 cache
      3) 64-bitness

    3. Re:Extra Transistors by philthedrill · · Score: 5, Informative

      Don't forget the extra pipe stages... those count for a lot. I can't say how many transistors, but it should make a dent in the numbers.

      A 1 MB L2 cache will be at least 50 million transistors, assuming 6T/bit (1024 * 1024 * 8 * 6), not including sense amps, decoders, tags, coherence, predecode bits, etc.

    4. Re:Extra Transistors by Anonymous Coward · · Score: 0

      does anyone know where the extra transistors in Prescott are coming from?

      I'm guessing the same place the rest of the chip is coming from. :o)

    5. Re:Extra Transistors by Anonymous Coward · · Score: 0

      isn't the entire north bridge on die? plus I heard they used a lot of alpha technology which means instead of having busses everywhere, they have N-N connections that's a lot of extra transistors

    6. Re:Extra Transistors by bhtooefr · · Score: 1

      That's the AMD64 - Prescott works with current P4 boards, which have a real northbridge.

    7. Re:Extra Transistors by Jeff+DeMaagd · · Score: 1

      Add about 13% more on the cache for the fact that most modern CPUs have ECC there. Intel had ECC on the cache there since late PII / early PIII. I know Athlon 64 has it but I don't know about Athlon.

    8. Re:Extra Transistors by pyrrhos · · Score: 2, Insightful

      Adding a number stages does not necesarily mean you are adding as much hardware (transistors). You can simply divide a stage into two by adding a few latches and nothing more. This can be done to increase the clock frequency.

      Example: you have a unit (say, multiplier) that has three stages, each of which can complete within 1 nsec. This means your clock can run at 1GHz (1/nsec). If you divide each of these stages in two then each of these new stages will complete in .5nsec which means you can run your clock at 2GHz. No extra functionality and no extra transistors, not counting just a few latches.

    9. Re:Extra Transistors by hottoh · · Score: 2, Informative

      This does not enumerate the transistors, but you have a nice picture. http://www.hothardware.com/reviews/images/Prescott 32_34ee/prescott_die_8in.jpg The additional cache and pipelines add many transistors.

    10. Re:Extra Transistors by Anonymous Coward · · Score: 0

      And of those 3, #2 probably accounts for 90% of the increase...

    11. Re:Extra Transistors by Loki_1929 · · Score: 1

      "Don't forget the extra pipe stages... those count for a lot. I can't say how many transistors, but it should make a dent in the numbers."

      We can also assume there's some form of speculative execution integrated into the CPU to bypass the latter stages of the extremely long pipeline where possible.

      --
      -- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
    12. Re:Extra Transistors by neurosis101 · · Score: 2, Informative
      Yeah, but we're talking about a P4 here.

      First of all, no latches... all these chips are clocked very tightly and timing propogation will get ruined by latches. They'll be flip flops or buffers.

      Secondly, its likely that they've subdivided their stages so small it will require extra logic to accomodate more stages. Keep in mind the typical computer example uses FIVE pipleline stages (from MIPS processors), and we're at THIRTY ONE.

      Most of these transistors I would bet are for upcoming SSE3 instructions that are not on and additional pipelining logic for branch prediction, and to allow more parallelism in between the stages, especially the fetching and decode stages. Will all the new trace and victim caches added, it will need more logic to check all the different caches.

    13. Re:Extra Transistors by Short+Circuit · · Score: 2, Informative

      You mean branch prediction? They did some serious improvements to Prescott's branch prediction in order to compensate for the performance losses that come from having such a long pipeline (or, rather, the performance losses that come from not keeping that pipeline full.).

    14. Re:Extra Transistors by Anonymous Coward · · Score: 0

      Predecode bits in data cache?

    15. Re:Extra Transistors by jimbo3123 · · Score: 1

      Sense Amps are only necessary to overcome the analog nature of DRAM. Your 6T SRAM cells require nothing of the sort.

      You do make a valid point that there is a lot of support hardware necessary for cache to work though.

      --
      There should be a moderation category "Dumbest Comment EVER"
    16. Re:Extra Transistors by Loki_1929 · · Score: 1

      "You mean branch prediction?"

      I'm referring to speculative execution in a more generalized way. That would include branch prediction, data prefetch, etc. What it may also include is an early termination, whereby under certain circumstances, you don't have to surf the entire pipeline to get a result. The Sparcs have done this since about '94 (simpledoc here). An Inquirer article hinted at the possibility of this being included in the Prescott chips, mentioning that this would explain why the incredibly long pipeline doesn't seem to have a hugely negative effect in many different benchmarks.

      --
      -- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
    17. Re:Extra Transistors by philthedrill · · Score: 1

      You're right about DRAM, but sense amps are used in microprocessor caches as well - not for functionality, but for speed. It'll be a lot faster to have sense amps and related circuitry pull a line to rail whenever it detects a change instead of waiting for the transistors in the bits drive the line.

  3. Linux becoming a lot more mainstream? by 192939495969798999 · · Score: 4, Insightful

    It seems that Linux is becoming substantially more mainstream, and quite quickly. I don't think the desktop war has really even started -- it won't start until that linux user base reaches a critical size, where managers, etc. start having linux at home and start to desire to be consistent at work too, and then have everyone convert. Still, articles like this seem to point to a more heterogeneous system environment in the near future.

    --
    stuff |
    1. Re:Linux becoming a lot more mainstream? by Anonymous Coward · · Score: 0

      What the hell are you talking about? What you say is pretty much common sense and has nothing to do with the article.

    2. Re:Linux becoming a lot more mainstream? by 192939495969798999 · · Score: 1

      Since your reply begins with an insult, I will assume that you didn't think out your response as well as I have mine. The fact that a test like this is being run by LinuxHardware.org and then picked up by slashdot shows an increase in the interest as to which machine would run Linux the fastest, therefore an increase in the consumer demand for such a test. If that alone is common sense to you, that's fine. There's no reason to insult me for my ignorance. My reply might provide some reinforcement to some people's beliefs, strengthening the linux community.

      --
      stuff |
    3. Re:Linux becoming a lot more mainstream? by Anonymous Coward · · Score: 1, Insightful

      you're getting info from a site called linuxhardware via slashdot and thus linux is becoming "substantially more mainstream'? when my local paper starts doing comparisons like they do for new cars, then I'll consider it mainstream.

    4. Re:Linux becoming a lot more mainstream? by corky842 · · Score: 0, Offtopic

      And you, sir, are a waste of my bandwidth.

    5. Re:Linux becoming a lot more mainstream? by 192939495969798999 · · Score: 1

      cars have been around for 100 years, while Linux has been around for a lot less -- plus, not everyone requires Linux to get to work in the morning.

      --
      stuff |
    6. Re:Linux becoming a lot more mainstream? by bhtooefr · · Score: 1

      When my local paper starts doing comparisons on PC hardware, then I'll consider computers mainstream.

    7. Re:Linux becoming a lot more mainstream? by Anonymous Coward · · Score: 0

      yours doesn't?

    8. Re:Linux becoming a lot more mainstream? by Anonymous Coward · · Score: 1, Interesting

      I think it's the wrong way round: don't start at the top, start at the bottom. Get the secretarys work with linux. Their bosses will (have to) follow. At least that's how MS won on our Campus.

    9. Re:Linux becoming a lot more mainstream? by diablobynight · · Score: 1

      Wait you think that because slashdot(linux fan boy homesite) picks up an article on linux being tested on different processors, means that linux is becoming more main stream.
      Just checking to make sure I heard you right, and that my brain didn't explode from the stupidity of the comment

      --
      Anonymous Cowards - Oh God, How I hate you
    10. Re:Linux becoming a lot more mainstream? by Anonymous Coward · · Score: 0

      I don't think the desktop war has really even started -- it won't start until that linux user base reaches a critical size, where managers, etc. start having linux at home and start to desire to be consistent at work too, and then have everyone convert.

      Linux won't reach the "mainstream" desktop until programmers and designers can all come to an agreement on 1 windows manager to use.

    11. Re:Linux becoming a lot more mainstream? by Anonymous Coward · · Score: 0

      What other operating system do you think a site like LinuxHardware.org would use to test processors? What other operating system would make it at all interesting to Slashdot readers (except maybe OS X which would be very interesting)? If this were a test run by PC World and mentioned in the New York Times then I would agree with you but saying that Linux acceptance on slashdot is at all indicative of acceptance by the general populace is not just ignornace. It is plain stupidity.

      Why can't you just admit that you are a karma whore. I read some of your other posts. They are the same, vague, generic, vapid posts that are guaranteed to get modded up. Your username and the fact that you sign with Sir Haxalot only reinforces the idea.

  4. Why use Intel anymore? by thebosz · · Score: 2, Interesting

    Seriously, why why anybody use Intel anymore? AMD kills them almost every single time. AND they're cheaper! (Note: I said *almost*)

    --
    The Kerr Divine: My wife's battle with a mysterious illness.
    1. Re:Why use Intel anymore? by Anonymous Coward · · Score: 2, Interesting

      Some people have this bizarre fetish over paying more for inferior hardware. I wish AMD would focus more on dual-processor stuff, though. It'd be nice to build a real dual AMD CPU machine for cheaper than a fake Hyperthreaded one.

    2. Re:Why use Intel anymore? by Krojack · · Score: 4, Informative


      I will always use AMD for my home PC mainly because of the price. IMHO Intel is over priced, you're paying for the name not the product/quality.

    3. Re:Why use Intel anymore? by RailGunner · · Score: 1
      I think it has to do with marketing - I'd suspect that a lot of people have never even heard of AMD - but have heard of Intel because of the stupid alien commercials (where an alien inserts a Pentium into some gel and checks out a chick in a bikini) and the old Blue Man Group commercials... that and the 4 note sounder..

      But what about AMD? I've personally never seen a commercial touting an Athlon from AMD. AMD should buy some commercial time and tout "Hey we kick Intel's ass AND we're cheaper! Join the revolution" or something similar.

      It's all about the name recognition (or lack thereof)...

    4. Re:Why use Intel anymore? by grahamlee · · Score: 1

      Then Linux users, who like me pride themselves on the openness of their software, should consider using open standards for their hardware. Such as SPARC, especially the scrummy 64-bit sparcv9. These things can scale up to a 64-CPU box; I'd like to see the Athlon manage that ;-)

    5. Re:Why use Intel anymore? by Dutch_Cap · · Score: 3, Insightful

      "AMD should buy some commercial time and tout "Hey we kick Intel's ass AND we're cheaper!""

      I think part of the reason AMD is cheaper is that they don't spend huge amounts on marketing.

    6. Re:Why use Intel anymore? by Anonymous Coward · · Score: 0

      What are you talking about?

    7. Re:Why use Intel anymore? by Tony+Hoyle · · Score: 1

      Have you not seen the 'Amd Me' adversts at train stations, bus stations, etc.? AMD have a very high advertising profile. Intel (at least in the UK) seem to have dropped off the planet since the dancing multi coloured chip-workers adverts. Also most of the cheap clone PCs that you get are AMD, because in that market price matters a lot.

    8. Re:Why use Intel anymore? by Anonymous Coward · · Score: 0

      Totally different in the US. AMD is almost nowhere to be seen, while Intel continues to crank out advertising. Plus they get computer vendors (Dell, etc) to advertise for them, too.

    9. Re:Why use Intel anymore? by ergo98 · · Score: 5, Informative

      Unfortunatly AMD not being 100% compatable with the standard causes problems.

      Good old FUD -- when Windows crashes on an Intel box, it's because of Microsoft. When Windows crashes on a AMD box, it's because the AMD "isn't 100% compatible". Uh huh. I'll buy either AMD or Intel without a hesitation (I'm not a fanboy) where one is the clear winner, but I still see FUD when someone spouts it.

      Here's a clue for you -- neither AMD or Intel are x86 processors, but rather both have a converter that converts x86 to their own internal microcode. The x86 standard that they're converting is EXTREMELY well known and standardized (I mean -- other people have to write the software that runs on it). AMD is 100% compatible with core x86.

      Intel also has much more R&D into making a chip that won't fry itself if it gets too hot. AMD? Naw, they'd rather make you buy a new chip than bother to make it prevent a problem before it occurs.

      Tom, is that you? Firstly, Intel and AMD chips are comparable in heat levels (actually the Prescott sets all new levels for heat generation, making Intel the clear winner in the egg cooker category), but secondly you are correct -- Intel has been more fervent in putting heat protection on their chips, though it is arguably over-engineering. It's like having guidewires "just in case" around all of your high rises. It's generally unnecessary as, apart from Tom's Hardware PR stunts, heatsinks don't fall off processors in regular use. My car doesn't have a special fuel purge if I decide to fill it full of ketchup.

    10. Re:Why use Intel anymore? by NoGuffCheck · · Score: 1

      If AMD took branding to mass media in a similar fashion to Intel, or at least in a way where they may be considered decent competition (ie TV adverts prime time) the price of your AMD chip would go through the roof to cover the costs. They may cost less, and chances are their cheaper too.

      --
      serenity now!
    11. Re:Why use Intel anymore? by John+the+Kiwi · · Score: 3, Interesting

      I've had problems with AMD cpu's and poorly made hardware, Mobo's especially. Of course way back in the day there were a lot of applications that simply would not work on AMD architecture - this goes back to Windows 9x but at times AMD cpus were more trouble than they were worth IMO and so I now stick with Intel as much as possible.

      I recently got a 2.8 P4 with HT, I found that with a $150 Mobo the price was very competitive with the latest AMD CPU/Mobo combinations. About the only benchmarks that AMD was beating the P4 with were in game playing. For things like video editing and database hosting then the P4 was beating the AMDs. But I really don't read too much into benchmarks anyway.

      AMD is definitely cheaper most of the time, but if you don't buy the latest generation of CPU, and lets face it cpu speed is really not a bottleneck anymore anyway. I found that replacing my old 40GB hard drive on my old 1.6 Ghz P4 with a 120GB WD with the 8MB cache increased my performance by at least 400% where memory caching is concerned.

      I'm also a great believer in getting what you paid for. I might pay a little more for my Intel cpu, but I know it will overclock further (should I ever require more cpu speed) and that it was designed to be on 24/7.

      There's my 2c

      John the Kiwi

    12. Re:Why use Intel anymore? by miodekk · · Score: 1
      I've always used AMD processors in my PCs.

      My first PC was 286. Bought in local store. After some time I've found out that the chip was from AMD. Next was 386sx. Again it was AMD, just by coincidence. After some time I've jumped to 486dx2. Of course by AMD.
      My first (and the last) Intel processor was Pentium (166MHz if I recall corectly). It worked for less then a month. One day it burnt. Literally, with smoke and everything. We couldn't get rid of that terrible smell for a week. After that I replaced it whit AMD K5. And I stayed with AMD. Currently I have Athlon XP.

      Probably I had very bad luck, but that Intel processor was the worst experience in my life...

      Regards

    13. Re:Why use Intel anymore? by Linus+Sixpack · · Score: 5, Insightful

      AMD only also is just brand blindness.

      I will always use the best priced solution. While I agree that right now that is AMD, Intel is welcome to tempt me -- I can be convinced.

    14. Re:Why use Intel anymore? by Afrosheen · · Score: 5, Insightful

      "My car doesn't have a special fuel purge if I decide to fill it full of kethup"

      That's not really a relevant analogy. Something more analogous would be 'my car won't explode if I don't put any coolant in the radiator'. Your car will show the temperature steadily increasing and it may well let you get it hot enough to start a fire or seize the engine. A Pentium engine OTOH would turn itself off after the temperature threshold reached a certain point, thereby saving itself.

      What Intel fanboys don't realize is that AMD left it up to the motherboard manufacturers to add proper thermistors beneath the ZIF socket where the cpu goes. While some believe it was irresponsible and some motherboard companies just forgot to add this altogether, most reputable companies have done it for awhile.

      You could take issue with the fact that any AMD chip will self-destruct with no heat sink or without adequate cooling, or you could figure you're a total moron for not putting coolant in your radiator and you reap what you sow. Many ways to look at this issue.

    15. Re:Why use Intel anymore? by __past__ · · Score: 1
      These things can scale up to a 64-CPU box
      Sun sells the Sun Fire 15k with up to 106 UltraSparcs, the FujitsuSiemens Primepower 2500 comes with up to 128 SPARC64 processors.
    16. Re:Why use Intel anymore? by Anonymous Coward · · Score: 0

      Haha, Intel vs. AMD pissing matches are useless anyways.

      Everyone knows Intel is better.

    17. Re:Why use Intel anymore? by jimmer63 · · Score: 1

      One of the major reasons is because of availability. I love AMD's. Their bang for the buck is unmatched. But the problem is that many vendors still do not offer AMD chips. We use a lot of Dell machines. Dell doesn't sell AMD. Dell has a great support network, drivers, etc etc so it outweighs some of the chip savings. Even our white box vendor is only using Intel chips to streamline deployment and warranty issues. I'm searching for a good vendor that sells AMD chips in my area. C'est la vie.

    18. Re:Why use Intel anymore? by Loki_1929 · · Score: 1

      " I've had problems with AMD cpu's and poorly made hardware, Mobo's especially."

      AMD makes motherboards? Also, what does the CPU have to do with the motherboard? Until the PII, Intel and AMD CPUs fit in the same boards. If the board was junk, an Intel chip isn't going to magically re-draw the traces, nor add extra layers to combat EMI.

      "Of course way back in the day there were a lot of applications that simply would not work on AMD architecture - this goes back to Windows 9x"

      Really? Which ones had problems specific to errors, bugs, or errata (to use Intel marketspeak) in the AMD CPUs? I can remember a few problems with Windows, mostly having to do with bugs in the Windows software that only showed up on AMD CPUs, as AMD wasn't privvy to the bugs ahead of time as was Intel. This goes to the relationship between Intel and Microsoft, in that they showed one another where things were screwed up so they could come up with a workaround. It had nothing to do with anything AMD was doing in the FAB.

      "About the only benchmarks that AMD was beating the P4 with were in game playing."

      AMD CPUs generally perform well in things like gaming and office-style applications. Content-creation and compression/encoding tend to like the long-pipeline/low-IPC/high clock frequency of the P4s.

      "I'm also a great believer in getting what you paid for. I might pay a little more for my Intel cpu, but I know it will overclock further"

      650MHz Durons usually overclocked to 900MHz+ with air cooling. I can't recall having ever seen anything else match that. High-end chips generally don't overclock well from either company.

      "and that it was designed to be on 24/7."

      On which planet does this make any sense? You appear to imply that AMD CPUs are somehow not designed to run all the time. Actually, neither company seems to say much at all about expected usage, though I've had and run both 24/7 for months on end without issue. If this is a slap at heat dissipation, then you might want to check Prescott's TDP of 103W, or perhaps the board specs released by Intel to board manufacturers telling them that boards designed to scale to the 3.7GHz Prescott must be able to handle as much as 137W TDP. Compare this to AMD's max of about 89W.

      If you'd really like to get into a discussion about CPU quality control, allow me to start you off with a little reading over here.

      --
      -- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
    19. Re:Why use Intel anymore? by confused+one · · Score: 1

      AMD's early attempts at Pentium compatibility did have some issues that caused software incompatibility. They've gotten a lot better since then. Any issues you hear of now are because of crappy chipsets or poor implementation by the Mobo manufacturer -- and it wouldn't matter what cpu was on the board, it just happened to be an AMD. I've run Cyrix and AMD chips in my home computers since day one (1991 for me) and I haven't had any problems in years. Mike the son of a Kiwi...

    20. Re:Why use Intel anymore? by vasah20 · · Score: 1

      > My car doesn't have a special fuel purge if I decide to fill it full of ketchup.

      You obviously need to get the 2004 model then.

    21. Re:Why use Intel anymore? by Anonymous Coward · · Score: 0

      I built a computer with an MSI 845 geml board and a 2.6ghz proc. Shipped it. It was back in the shop about a month later, problem? Keeps shutting down. The heatsink bracket was detached from the mainboard, just dangling. replaced the board because the bracket could not be securely replaced. Thank god it was an intel, or I'd be rma'ing a proc as well. It fell off in regular use

    22. Re:Why use Intel anymore? by Anonymous Coward · · Score: 0

      Yeah, Intel may win on the fastest chip in some benchmarks but AMD almost certainly wins the price/performance contest.

      If I could afford the best consumer chip on the market, maybe I'd use Intel. As it is, I have a budget which is (significantly) lower than the price of the fastest consumer chip on the market. I spend my money on the chip that gives me the best performance for the money.

    23. Re:Why use Intel anymore? by John+the+Kiwi · · Score: 1

      I think you're missing my point.

      In my experience I have had quality issues when buying cheap hardware. This includes AMD and various motherboards that AMD CPUs run on. People have been posting that AMD is better because of price, I am only stating that in my experience buying things just because they are cheap is not necessarily a good indicator of value.

      And am I intimating that AMD chips are not designed to run 24x7? Of course not, but if you're running poor hardware then it generally will not run as well or last as long as better built hardware.

      I make no claims to be a computer guru. I've been working with computers for over 10 years, I own 8 computers that run PPC, AMD and Intel CPU's. I think that qualifies for me to make informed personal obversations about my own experiences with computer hardware.

      Now, if you couldn't understand the context I was using before then you should be aware of it now. I'm sorry to have confused you, now that you understand where I am comig from I will once again summarize for you:

      In my experience I have found that Intel based computers work better and more reliably than similar AMD based systems. I would attribute a lot of this to the fact that AMD cpu's and hardware tend to be of lower quality than similar Intel based hardware because AMD systems generally appeal to the price minded buyer.

      Kind Regards
      John the Kiwi

    24. Re:Why use Intel anymore? by 4of12 · · Score: 2, Informative

      The "not 100% compatible" complaint is about ten years old.

      My experience, buying a 200 MHz K6 and an 800 MHz Duron, has been good with AMD chips.

      The price/performance ratio has always been more attractive for AMD relative to Intel.

      I will say that once I had a problem with a K6-III that would lock up after an hour or so - turned out the cheapo CPU cooling fan wasn't moving.

      AMD produces fine chips, but their reputation as a "budget" CPU means they get tied into other components of mediocre quality in order to keep the price in the basement. That helps sales at the low end, but actually hurts sales at the high end. MyCorp, like many, pretty much buys Intel only hardware, paying more than they need to for x86 instructions and for systems integration, just to keep the potential support hassles down to a minimum.

      If AMD made sure that a separate model line, such as the Opteron, were only used in MoBos and systems with high MTBF on all the parts they might have a better chance of getting more corporate business. But it will still take time to overcome the image of "CPU Backwards R Us".

      --
      "Provided by the management for your protection."
    25. Re:Why use Intel anymore? by dsci · · Score: 1

      That's not really a relevant analogy. Something more analogous would be 'my car won't explode if I don't put any coolant in the radiator'. Your car will show the temperature steadily increasing and it may well let you get it hot enough to start a fire or seize the engine. A Pentium engine OTOH would turn itself off after the temperature threshold reached a certain point, thereby saving itself.

      Actually, with no coolant in the radiator, the temp gauge WON'T move, since the sensor reads the temperature of the coolant. Your analogy is more like saying the thermal protection, whether on-chip or on-mainboard, didn't work. In either case, the chip's fried.

      --
      Computational Chemistry products and services.
    26. Re:Why use Intel anymore? by Loki_1929 · · Score: 1

      "Now, if you couldn't understand the context I was using before then you should be aware of it now. I'm sorry to have confused you, now that you understand where I am comig from I will once again summarize for you:
      In my experience I have found that Intel based computers work better and more reliably than similar AMD based systems. I would attribute a lot of this to the fact that AMD cpu's and hardware tend to be of lower quality than similar Intel based hardware because AMD systems generally appeal to the price minded buyer."


      The highlighted part is what I questioned. I understand and agree with the point that cheaper does not equal better, but I think the overall point that most people make is that it's just as fast or faster than a similarly-marketed Intel CPU and that's it's generally less expensive, while implying that quality remains the same.

      Your experience might include putting AMD CPUs on the cheapest hardware money can buy, but for the enthusiast who knows what mainboard, graphics card, etc to buy, this simply isn't the case. That you choose to stick an AMD CPU onto a cheap board with cheap parts says nothing of AMD's quality control. What it does say is that when you stick a CPU, regardless of its quality, onto the cheapest boards available, you're likely to have problems. Stick an Intel CPU on an el-cheapo ECS board and see what happens. I had about 7 or 8 PIII systems sold to a church built on ECS P6STM boards. I had made the mistake of giving them a try. Of those, 5 or 6 ended up needing the board replaced at least once, and 4 or 5 of those I ended up just putting in a Gigabyte board after multiple replacements. Haven't had a problem with them since (this was a few years ago). The ones that did work were running slower PIIIs. While the P6STM was supposed to run everything up to about 1GHz, they would be very unpredictable at any clock frequency above 800Mhz or so. Intel chips, cheap boards, problems. Now, I sell AMD based systems almost exclusively. I use nothing but Asus mainboards and quality power supplies and haven't had a single hardware problem with a new machine in the last couple of years.

      If you're going to knock AMD's CPU quality, please provide at least a shred of evidence to back up your claims. If you're simply trolling, I'll have to make a note to stop feeding you. If you want to get into a debate about quality control at microprocessor manufacturers, I suggest you take a look at the link I posted.

      Intel has had problems with nearly every CPU type sold since 1994 - this includes Itanium.

      --
      -- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
    27. Re:Why use Intel anymore? by Anonymous Coward · · Score: 0

      Do you know why they put the "Intel Inside" labels on everything?

      They are warning lables!

    28. Re:Why use Intel anymore? by Anonymous Coward · · Score: 0

      Yeah but you're just a poor yank student with no direction and/or prospects. I bet you're the kind
      of kid who hangs around shopping centres offering to take honest folk's trolley's back to the front onf the shop just so you can nick the quid that goes in them.

      wanker.

    29. Re:Why use Intel anymore? by Anonymous Coward · · Score: 0

      How does crap like this get modded up? The only insightful part of the comment is regarding strengths and weaknesses of Intel vs AMD, and about new Hard Drives increasing performance (especially the 8MB cache versions).. but this is true for all computers. But the only crap you can give AMD is maybe about the shitty Heatsink and Fans they used to provide with their CPUs. But as another poster stated, AMD Motherboards aren't made by AMD. And if you really want to check out an awesome AMD motherboard, look at the Asus A7N8X-DX (or the newer A7N8X-E if you want Gigabit Ethernet). I personally own 3 of them, and they work flawlessly - and can be overclocked very easily.

    30. Re:Why use Intel anymore? by zoloto · · Score: 1

      -----BEGIN PGP SIGNED MESSAGE-----
      Hash: SHA1

      Now I'm not an Intel fan boy, or AMD for that matter. I pick what
      works and here is a question for you:

      "Why use intel?" you say. My question to you is, why use AMD?

      In my experience with AMD vs INTEL would be the following.

      A fresh install of MS-Windows (The 98's, 2000 and XP) on an Intel
      board was as simple as it gets. Install the various drivers for
      your video, sound, network etc and you have a working box that
      doesn't have any problems. I never even needed to install any
      motherboard drivers (nor do i think there needs to be if it's
      engineered correctly, with the exception of onboard lan, audio,
      video) and it worked just fine.

      Now with the amd boards (and i've tried multiple boards with via,
      kt chipsets from ASUS, ABIT etc... and various mods or versions etc.)
      and a fresh install of the above mentioned windows versions, you
      almost always have to install the motherboard drivers. I say almost
      always b/c I haven't used all of the AMD mainboards - duh. But for
      some reason, the AMD boards have to have these drivers installed or
      your Windows system will bluescreen, freeze, or act odd (in a way
      other than how windows is supposed to, cliche aside).

      Maybe it's my personal experience, but being a third year CSE student
      and having taken numerous hardware courses, I most certianly will
      defend the argument that yours truely isn't to blame.

      This is why I chose Intel boards over AMD. It's not a price over
      performance issue, it's what works for me with a minimum of hassle
      and still performs as it's advertised and designed.

      -----BEGIN PGP SIGNATURE-----
      Version: GnuPG v1.2.1 (MingW32) - WinPT 0.7.96rc1

      iD8DBQFAIW/NLXRZNs3to5MRAvTeAJ9FNBpWElnq7Teno+PZ sH 6FDvIRdwCfcMbL
      7nPRfG0gPphWS7G8TevVpps=
      =so3l
      - ----END PGP SIGNATURE-----

    31. Re:Why use Intel anymore? by grahamlee · · Score: 1

      Erk, I was looking at the UltraSPARC IIIi :-)

    32. Re:Why use Intel anymore? by Afrosheen · · Score: 2

      It depends on where the coolant temperature sensor is located. I've had a car with a leaky heater core hose (under the hood) and the coolant system just emptied itself completely on a hot summer day. The gauge shot up.

      Experience counts in this one. :)

    33. Re:Why use Intel anymore? by dsci · · Score: 1

      Experience counts in this one. :)

      Good point. My experience was just the opposite! Had a water pump leak around shaft bearing, emptied the radiator. Sensor stayed low. Caught the problem only cuz I happened to see coolant dripping.

      --
      Computational Chemistry products and services.
    34. Re:Why use Intel anymore? by Anonymous Coward · · Score: 0

      Current AMD chips have internal thermistors. Doesn't really help much when you only half about 2s before the chip pops, tho...

    35. Re:Why use Intel anymore? by Hoser+McMoose · · Score: 1

      Erk, I was looking at something that us mere mortals could afford!

      Who cares if you can theoretically buy an E15K with 106 processors, that box costs over a 3 million dollars! Ok, it might be an option for some companies that REALLY need the high-end, but honestly, that's a different world altogether!

    36. Re:Why use Intel anymore? by Hoser+McMoose · · Score: 1

      Unfortunatly AMD not being 100% compatable with the standard causes problems

      Intel is not 100% Intel compatible either. Don't believe me? Go to their website and check their "Errata" sheets. These are lists of bugs in their processors where they do not conform to the x86 standard (which, in itself, is a bit of a moving target). AMD processors actually tend to have fewer errata than Intel processors, though I'll leave it as an excersice to the reader to decide if that's because AMD's processors are more Intel-compatible than Intel processors or simply if Intel documents their bugs better.

      There are some problems with AMD chips and certian hardware.

      There are also some problems iwth Intel chips and certain hardware, or more to the point, motherboards on which those chips sit. The chips themselves have dick-all to do with compatibility, it's all in the motherboards.

      Intel also has much more R&D into making a chip that won't fry itself if it gets too hot.

      Go back and watch that Tom's Hardware video again, but this time keep three things in mind:

      - Intel's thermal throttling reduces chip speed by 50-70%. If we assume that ALL the power consumption of a chip was dynamic power, that would translate in a fully throttled 2.0GHz P4 processor would be consuming about 20-30W of power. In reality, the power consumption would be a bit higher because leakage current is pretty constant regardless of clock speed.

      - That 20-30W processor ran without a heatsink, you try running a 20-30W processor without a heatsink and see how long it lasts

      - Their temperature measurments read a constant 29C throughout the tests, Intel's thermal trip doesn't kick in until somewhere in the 60-70 C range

      Long story short, the video is total bullshit. It was faked for the purpose of getting lots and lots of page hits (read: advertising revenue). A P4 will NOT run without a heatsink, thermal throttling or otherwise.

    37. Re:Why use Intel anymore? by grahamlee · · Score: 1

      Erk, I was thinking that if I wanted an affordable, open standards-based computer, I'd look for one of those instead! Oh wait, I already have three. Never mind. What you've done is to take an incidental point in the discussion way too seriously, as geeks are often wont to do. The thrust of my original post was this: intel proprietary, sparc not. Intel crummy hack to eight-bit washing machine controller, sparc not. Sparc win.

    38. Re:Why use Intel anymore? by Lord+Kano · · Score: 1

      Your car will show the temperature steadily increasing and it may well let you get it hot enough to start a fire or seize the engine.

      Not exactly. If there is no coolant, the coolant temperature sensor won't be able to accurately measure the temperature of the engine. It's very possible (depending on the type of car, even probable) that your car's gauges will under-report the temperature. If you're not careful, you might not notice the temp problem until after your engine siezes or you crack a piston.

      LK

      --
      "Hi. This is my friend, Jack Shit, and you don't know him." - Lord Kano
    39. Re:Why use Intel anymore? by Anonymous Coward · · Score: 0

      This coming from a recognised Z80 fan ;)

  5. nehalem by Coneasfast · · Score: 1

    there was a cpu called the nehalem. anyone know any information about that? was that a codename or something?

    --
    Marge, get me your address book, 4 beers, and my conversation hat.
    1. Re:nehalem by spiny · · Score: 1

      loads of info here.

      --

      Fry: heh, Yakov Smirnoff said it
      Leela: No he didn't.
    2. Re:nehalem by Anonymous Coward · · Score: 0

      Nehalem will be Intel's next processor after Tejas. Tejas is supposed to come around the end of the year, so Nehalem won't be here until late 2005 or 2006. IIRC, Nehalem is supposed to be on the 65nm process.

  6. still not biting by Chuck+Bucket · · Score: 4, Insightful

    I'm not biting, I'm looking at upgrading my 1.2 Gig AMD to some 2.something Gig P4 or AMD. Why not? They're cheap (under 400) plus they'll keep up for more time than you'd think. When will we really _need_ 64bits on the desktop? I don't see it for another 2 years.

    CB

    1. Re:still not biting by Anonymous Coward · · Score: 0

      Get an AMD Barton 2500 ( $100), some good PC3200 RAM, and OC that baby to a Barton 3200. Works great for me, and I didn't even need to up the cpu voltage.

    2. Re:still not biting by Patik · · Score: 4, Funny
      When will we really _need_ 64bits on the desktop? I don't see it for another 2 years.
      Shhh, don't give away our secret. Keep telling people they need it so they'll buy it now, then in two years they'll be stable and cheap.
    3. Re:still not biting by stratjakt · · Score: 3, Interesting

      64 bit workstations have been around forever. Does everyone forget the DEC Alphas?

      No, we don't need 64 bit on the desktop. We haven't for the last decade or so, and it won't have that big of an impact immediately.

      For gaming? What, you need 64bit color and 64bit sound? No, 24bit is already more colors than the eye can distinguish.. Even if you did, that's the realm of the GPU/APU. For writing emails?

      So what if you can linearly address 4TB? A 1 or 2 GB machine is top of the line these days so far as desktop boxes go. The barrier is mainly price, not the addressing capabilities of the CPU.

      Show me 512GB-1TB dimms and I'll show you a real good reason for a 64bit CPU on the desktop.

      In the backroom, big transactional servers and the like, there's more of a call for it. Maybe a lil boost to a high-end CAD machine.

      As far as all the kids running out to spend their allowance on AMD64 chips, that's just them trying to fit in and show how computer savvy they are.

      --
      I don't need no instructions to know how to rock!!!!
    4. Re:still not biting by Eyston · · Score: 1

      The Athlon64 isn't that pricey of a machine. The Athlon 64 3200+ comes in at about a 50-75 dollar premium over an Athlon XP 3200+. Pair that with a good motherboard and it is still at your 400 dollar mark.

      If you are worried about not needing 64bits, it doesn't really matter as the A64 is an all around much better 32-bit chip than A-XP.

      -Eyston

    5. Re:still not biting by maxwell+demon · · Score: 2, Interesting

      You don't just get a larger physical address space, but also a larger virtual address space. I can imagine this is much more of an advantage (think of memory mapped I/O of large files, or even such simple things like dynamically expanding arrays without copying because you can leave much virtual space between your allocations).

      --
      The Tao of math: The numbers you can count are not the real numbers.
    6. Re:still not biting by Zathrus · · Score: 5, Insightful

      Does everyone forget the DEC Alphas?

      Pretty much, yeah... unfortunate too, since they were such good chips.

      For gaming? What, you need 64bit color and 64bit sound?

      No, for content creation -- textures, maps, etc. You can't reasonably address >4GB with a 32-bit chip (yes, you can do it. No, it's not fast) and we're reapidly approaching that limit in content creation.

      And while 24-bits of color may be adequate, you need more precision than that when doing blends and other operations. Of course, those are largely done by the GPU nowadays, so that's a non-issue as far as the CPU is concerned.

      So what if you can linearly address 4TB? A 1 or 2 GB machine is top of the line these days so far as desktop boxes go. The barrier is mainly price, not the addressing capabilities of the CPU.

      Actually you can linearly address 256 TB with the current AMD64 chips (48-bit addressing) and 16 exabytes with true 64-bit addressing. That's quibbling though.

      The main advantage of a 64-bit CPU (or at least one with direct addressing of >32-bit) is that you can directly map permanent storage to memory. Right now trying to do that is a freaking nightmare and very expensive, since we've long outgrown 4GB of disk space.

      And, really, that's not even the main advantage of x86-64. The real advantage is compiling 32-bit code to be aware of x86-64's extra registers, which can lead to a considerable speed up with no other changes.

      As far as all the kids running out to spend their allowance on AMD64 chips, that's just them trying to fit in and show how computer savvy they are.

      Yeah, by and large. My next PC will probably be x86-64 based though. Why? Because it's not that expensive. You can get a Athlon64 3000+ for just over $200 now. That's only a little more than an AthlonXP 3200+ or a little less than a P4 3.0C. If you're looking in that price range, then why not go for it? You'll get roughly the same price/performance in 32-bit and be able to upgrade to 64-bit when the time comes. If you don't need that kind of performance, that's fine -- save your money. But otherwise it's kinda silly to ignore the potential advantages offered.

    7. Re:still not biting by jubei · · Score: 1
      they'll[2+GHz Cpus] keep up for more time than you'd think

      I bet your 1.2 ghz cpu will probably be fine for most desktop tasks for at least another 2 years. It seems to me that desktop apps are not tending to require more cpu nearly as fast as more memory and disk bandwidth.
    8. Re:still not biting by remmy1978 · · Score: 2, Informative
      No, we don't need 64 bit on the desktop. We haven't for the last decade or so, and it won't have that big of an impact immediately.

      For gaming? What, you need 64bit color and 64bit sound? No, 24bit is already more colors than the eye can distinguish.. Even if you did, that's the realm of the GPU/APU. For writing emails?

      One of the reasons to do use the new amd 64 bit chips is that since you'll have to recompile your software for it anyways to use the 64 bit mode efficiently, AMD has been kind enough to add some extra registers to the CPU. As the x86 has traditionally been a bit starved registerwise, this is a very nice addition and by itself can account for a 20 - 30% increase in speed. Compilers have more registers available to them which results in less 'slow' accesses of reading and writing to memory.
    9. Re:still not biting by Short+Circuit · · Score: 1

      mmm...it would be really nice if data structures in memory could be virtually contiguous, but physically fragmented. realloc could be so much faster... :)

    10. Re:still not biting by BillyBlaze · · Score: 1

      There is no problem that can't be solved with an additional level of indirection.

    11. Re:still not biting by Sique · · Score: 1

      You don't even need 32 bit on a desktop. All you need is a processor capable of calculating one bit at a time and the three instructions INC(rease register), DEC(rease register) and JIZ (Jump If Result is Zero). Such a computer is called Turing Complete and able to emulate the behaviour of all other computers.

      There are only few applications for the normal desktop user yet which need 64bit computing, because there were no 64bit computers on a normal user's desktop. Everything in need of the increased memory address space, memory bandwith and additional registers was released only for 64bit workstations and servers because it wasn't able to run reasonably on 32bit.

      But it doesn't mean that there are no applications for 64bit. And even though you may not use those applications in the next future doesn't mean other people won't use them too.

      Look at cars: There are people driving so carefully and only on dry roads that they never even trigger the Anti Lock System of the brakes. Shall car makers now stop putting Anti Lock in stock cars, because there may people out there not needing it? Most people out there driving alone in their cars. Why don't we see hundreds and thousands of single seated cars? Speed limit on roads in the U.S. is (with some exceptions) at 75mph. Why do virtually all cars sold in the U.S. far exceed those limits? You won't ever need the speed.

      It has to do with something called economics of scale. If you develop a product, you don't just consider the absolute average use. You look at the extremes, and if you can meet extreme specifications without increasing costs too much, you have a better platform, you can penetrate markets you won't reach with putting out products only for the average user.

      You can share your development costs to more potential buyers thus limit the price burden you have to put on each buyer. If development of a limited product for 100 people costs you $1mio, you have to charge each buyer $10,000 to get your money back. If development for an allpurpose product costs you $10mio, and you sell it to 1mio buyers, each one pays you $10 for development. And computers are the products with the widest possible range of uses since the wheel.

      Products need builtin reserves to meet future demands and be able to adapt to new uses. Otherwise you end up with hundreds of little platforms each designed for a small target group, expensive to maintain and barely manageable.

      If putting out a 64bit platform will cost you only a little more than designing the next 32bit platform, why maintain both a 32bit and a 64bit product line? You can use the 64bit technology for both, thus making the 32bit obsolete. You now cover a large range of uses from servers crunching through Terabytes of data down to cash registers summing up $7.99, $0.50 and $3.99 in a small gift shop with only a single technology. Every improvement at one end is available through your whole product line without additional cost. Even though the cash register at a little store will never encounter numbers outside the 0 - 1mio range, why make the additional effort to design a custom 20bit processor for cash registers, if a stock 32bit processor will do too? Why artificially limit your computer to 32bit registers, if 64bit registers are available at reasonable prices?

      --
      .sig: Sique *sigh*
    12. Re:still not biting by Bert64 · · Score: 1

      The extra registers have nothing to do with the fact the system is 64bit, the extra registers are an attempt to get around some major design flaws in the x86 architecture.. problems which other architectures simply don't have, thus you won't see such a performance increase on other architectures like sparc and mips (which btw went 64bit years ago)

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    13. Re:still not biting by Zathrus · · Score: 1

      The extra registers have nothing to do with the fact the system is 64bit

      Which has absolutely nothing to do with what I said.

      I stated that the advantage of x86-64 is the additional registers. I said nothing about other architectures.

  7. Let's check by mckwant · · Score: 3, Funny

    -sound of high powered, yet extremely fine lathe-

    one, two, three...

    I'll be back.

    --
    ceci n'est pas un sig.
    1. Re:Let's check by captain_craptacular · · Score: 2, Informative

      Do you know what a lathe? Maybe you're thinking of a planer, because I can think of no reason why spinning a processor at several thousand rpm's would help answer the question....

      A lathe spins an object about a point very fast allowing you to work it into a cylindrical shape.
      A planer shaves a layer off the top (or bottom) of an object allowing you to quickly work it down to a desired thickness...

      --
      They who would give up an essential liberty for temporary security, deserve neither liberty nor security
    2. Re:Let's check by etymxris · · Score: 1

      The lathe is funnier though.

    3. Re:Let's check by spagnitz · · Score: 0

      Actually you would use neither, a surface grinder can take off much finer incremements than a planer will ever be able to, even the least accurate surface grinders can remove .0002

  8. Apples compared to oranges. by stratjakt · · Score: 4, Insightful

    Decide what the requirements are for your system then choose appropriate hardware. Do you need 64 bit extensions? Do you need hyperthreading? Do you need instruction set X because it'll make your game run faster?

    I'm sick of hardware sites and the lame "X vs Y showdown" articles. They're utter bullcrap.

    --
    I don't need no instructions to know how to rock!!!!
    1. Re:Apples compared to oranges. by commodoresloat · · Score: 4, Funny

      Actually, the problem, as the first poster noted, was that they didn't test any Apples at all!

    2. Re:Apples compared to oranges. by queen+of+everything · · Score: 1

      But the problem is no one wants to have an adequate system...they want a super leet system. They want something to brag about, who cares if its over the top for what they use it for. I can't say I'm any different. I'm a sucker for the newest, coolest technology.

      Most (average, non-tech) people won't need to upgrade their processors, but its new so they think they should. They don't fully use the processors they have now. Email and Internet browsing can be done quite happily on a 100 mhz. Its not what you need, its what you "need"!

      --
      "Wisdom is not a product of schooling but of the life-long attempt to acquire it." -Albert Einstein
    3. Re:Apples compared to oranges. by Afrosheen · · Score: 1

      Internet browsing happily on a 100mhz machine? Yeah right. I guess you've never seen Flash, shockwave or java before at that speed. Regardless of your OS, if it's graphical it needs speed. I'd say a 450mhz machine is base for this day and age..unless pine and links are your cups of tea.

    4. Re:Apples compared to oranges. by Anonymous Coward · · Score: 0

      Apples to oranges? Is there any comparison (in your opinion) that could NOT be apples to oranges?

    5. Re:Apples compared to oranges. by Anonymous Coward · · Score: 0

      Eh, I don't think your post was very well thought out. No one "needs" hyperthreading, it's just one of many techniques to make things a little faster. That's like saying people should decide if they want out of order execution before deciding what to buy.

      The only possible requirement that would eliminate something would be x86-64, and that's a pretty unlikely requirement. More likely people want whatever runs their favorite applications fastest, which is what these benchmark face offs are for.

    6. Re:Apples compared to oranges. by Anonymous Coward · · Score: 0

      I guess you've never seen Flash, shockwave or java

      Are you saying you actually browse with these things turned ON?!?

      Feelings of pity nearly overwhelm me...

    7. Re:Apples compared to oranges. by bhtooefr · · Score: 1

      Actually, I think it's RAM and a good OS. Windows needs about 400MHz and 256MB of RAM to work well on the Internet. Me? I run a P233MMX with 96MB RAM on Linux, and it ran flash stuff FINE (pr0n mpegs don't do so well, but...)

    8. Re:Apples compared to oranges. by Afrosheen · · Score: 1

      I have a hard time believing that flash runs fine on that configuration. I have an athlon xp2100, 768mb of pc2700 running linux, and flash loses sync with audio CONSTANTLY. Then again, the flash plugin from macromedia is crap, so maybe that's the real issue.

    9. Re:Apples compared to oranges. by cyfer2000 · · Score: 1

      yeah, they tested orange and grape fruit, but where comes the sour lemon smell?

      --
      There is a spark in every single flame bait point.
  9. You know what they say by Anonymous Coward · · Score: 3, Funny

    Intel inside. Idiot outside.

    1. Re:You know what they say by no+longer+myself · · Score: 3, Funny

      Intel Inside <- It's a warning label.

  10. PPro 200 by hedley · · Score: 4, Interesting


    I run 2 PPro 200 boxen. They are up 24/7/365. I find that linux keeps it lean and the incentive to keep up with the Prescott's just isn't there for me. For a home server I would say keep it simple and reliable. If you want a work engine that will be used for large EDA jobs etc, then the cpu may get you somewhere (coupled with a good system mobo etc). For EDA jobs though we are starting to look at the future wrt 64bit Synopsis builds for the Opteron family.

    I am curious if home server users need all this power...

    Hedley

    1. Re:PPro 200 by Anonymous Coward · · Score: 0

      > I run 2 PPro 200 boxen ... For a home server I would say keep it simple and reliable.

      I'm sure they depend on repeat business from loyal customers like you. Problem-free == no future sales. Microsoft does it best - keep the bugs in so there is incentive to upgrade and use your monopoly to prevent people from switching to something more reliable. Perfect.

    2. Re:PPro 200 by stratjakt · · Score: 1

      There are those two or three who run linux desktops, I'm sure they could make use of it.

      Everytime there's a new processor on the market someone always says "noone needs this power". Frankly, I've never used a machine that I didn't wish was just a little bit faster.

      "2 minutes to compile?! I want it now"

      Whether the performance/price ratio is worth it is subjective. To me, 1000 bucks for 5%-10% better performance with the P4EE isn't worth it. To the "uberguru" type who's computer skill extends only to the ability to spend lots of money to impress other dolts with meaningless benchmark scores, it is. The markets there, why else jump on the hip-n-trendy bandwagon to market it as the "Extreme Edition"?

      --
      I don't need no instructions to know how to rock!!!!
    3. Re:PPro 200 by jidar · · Score: 1

      this should be modded "obvious" and "beside the point". We know what we can do on the low end, the the point of this article is figuring out the high end.

      --
      Sigs are awesome huh?
    4. Re:PPro 200 by Anonymous Coward · · Score: 0


      24/7/365

      24 hours a day, 7 days a week, 365 weeks a year?

    5. Re:PPro 200 by notbob · · Score: 0

      I got a quad ppro 200 ibm netfinity 7000 server for sale cheap if you're interested.

      1mb cache on each cpu, 1 gig of ram, raid 5 hard drives

    6. Re:PPro 200 by Anonymous Coward · · Score: 0

      No kidding.

      "I have a computer from 1995 and it works just fine for me!"

      WTF does that have to do with an article titled "Current Processors Tested With Linux?".

      He should save his comments for an article titled "Ask Slashdot, How Long Before I Can Label My Server an Antique?"

      Sheesh

    7. Re:PPro 200 by Just+Some+Guy · · Score: 1
      I run 2 PPro 200 boxen. They are up 24/7/365. I find that linux keeps it lean

      Sure does! And FreeBSD (my server OS of choice, but not by a huge margin) does also.

      However, even my home servers spend more time running applications than kernel code. I run a Zope webserver, LDAP, a decent-size IMAP setup, and a few other services that don't require huge amounts of horsepower averaged over time, but that really make use of a nice CPU over short bursts. I probably only serve 5000 to 10000 web hits per day, so I could technically get away with a system that could manage pushing out a page every 8 to 16 seconds, but site visitors would get horribly annoyed at the sluggishness of their session.

      That's why I have reasonably modern CPUs in my little home server. I don't do any video encoding or protein folding, but I want enough processing power to lower the latency of the services I host.

      --
      Dewey, what part of this looks like authorities should be involved?
    8. Re:PPro 200 by e40 · · Score: 1

      I completely agree. Unlike Windows, Linux doesn't need a faster processor to keep up with each new release.

      My main mail/gateway/firewall/webserver is a Dual Celeron 500 and I don't see any reason to upgrade the processors. It ran Red Hat 7.3 very well for years, and now runs SuSE 9.0 just fine.

      The only upgrades I've done were disk space related. The last one was a 3ware 7000-6 (IIRC) with 2 120GB Seagates for RAID 1.

    9. Re:PPro 200 by scotch · · Score: 1
      I'll give you $3 for it, plus shipping. Do you have a support contract option? Because I'd be willing to shell out another $1.37 for that. Let the bidding commence.

      --
      XML causes global warming.
    10. Re:PPro 200 by notbob · · Score: 0

      $225 + ship or pick it up, comes with 7 9gb ibm scsi drives, triple redundant power supplies, has the cool lcd on the front etc...

    11. Re:PPro 200 by pesc · · Score: 1

      I run 2 PPro 200 boxen. They are up 24/7/365.

      I see this idiom 24*7*365 from time to time and I always wonder: What happens after the seven years? Why seven?

      --

      )9TSS
  11. But if G5 boxes were shown to be ... by burgburgburg · · Score: 5, Insightful
    superior for running linux then the best and brightest in the x86 world (including on price) then perhaps more linux users would build their own with a different class of processor.

    But we won't know if we don't look.

    1. Re:But if G5 boxes were shown to be ... by Doc+Squidly · · Score: 2, Interesting

      I would like to see such a comparison. Its hard to get an even comparison with hardware running different OS's.
      Although I've got a feeling that the G5 would do ok but wouldn't end up on top.

      I'm not trolling but...

      Maximum PC magazine had a review/benchmark in their Jan '04 edition. Featuring an AMD 64 FX-51, P4-EE and a Dual, 2 Ghz G5. (unfortunately the article isn't available online)

      To summarize, the G5 finished last overall. The tests even included Photoshop (with filters provided by the folks at Mac Addict), Indesign and QuickTime.
      Maybe it was that even though the programs use where the similar, they were more optimized for x86 than Mac or didn't take advantage of multi-threading.
      I don't see how that if Dual CPU system with a faster SATA HD (the other two were running parallel ATA) couldn't beat a single CPU AMD or Pentium system, that it could be superior in more even comparison. (Same number of CPU's, same HD, same amount of RAM, etc)
      Then again we'll never know until we try.

      --
      I think I think, therefore I think I am.
    2. Re:But if G5 boxes were shown to be ... by Anonymous Coward · · Score: 0

      Was it the same as the PC World review?

    3. Re:But if G5 boxes were shown to be ... by boaworm · · Score: 1

      I don't see how that if Dual CPU system with a faster SATA HD (the other two were running parallel ATA) couldn't beat a single CPU AMD or Pentium system...

      Well, you said it yourself. I make small .avi's with my Digital Ixus 400 and compress them on my DP G5, and Quicktime isn't multithreaded. Heck, even iTunes importing MP3s from cd isnt multithreaded. As far as i've noticed, not much in OS X is actually MT at all. WindowServer (~X), Finder (GUI frontend), iApps etc. None of them are...

      --
      Probable impossibilities are to be preferred to improbable possibilities.
      Aristotele
    4. Re:But if G5 boxes were shown to be ... by diablobynight · · Score: 1
      so it sounds like you spent about 2000$ more than you needed to for the software you run. This is the inherent problem with multi proc machines. Most programs are designed to take advantage of it.

      I am disappointed to hear it though I assumed considering apple made the hardware and the software, they would have optimized the software for the dual proc.

      --
      Anonymous Cowards - Oh God, How I hate you
    5. Re:But if G5 boxes were shown to be ... by incom · · Score: 1

      Interesting, but are there any G5 mobo's for sale at low costs?

      --
      True genius is grasping a situation like a peice of fruit, and peircing it just right so that it drains dry.
    6. Re:But if G5 boxes were shown to be ... by boaworm · · Score: 1

      Yes. And it's all depending on how you see it. Even though a single app is not multithreaded doesn't mean i dont make use of both my CPUs. For instance, if i run Diablo II, the .app consumes 100% on one cpu, while the WindowServer consumes like 40 % on the other. That also leaves like 60% for all my other apps not to choke me while gaming.

      And it does not cost $2000 to upgrade ;-) I spent an additional $400 to go from

      Single 1.8, 256MB/80GB

      to

      Dual 1.8, 512MB/160GB

      That also includes a faster FSB (800->900, twice the amount of ram slots (from four to eight) etc. So it's actually a bargain :)

      --
      Probable impossibilities are to be preferred to improbable possibilities.
      Aristotele
    7. Re:But if G5 boxes were shown to be ... by diablobynight · · Score: 1

      sorry, i was implying the whole computer was a waste of money when you could have built a PC for half the cost, ran Linux or XP, and done everything you can do with your G5

      --
      Anonymous Cowards - Oh God, How I hate you
  12. Site's down by LittleLebowskiUrbanA · · Score: 1, Redundant

    Insert obligatory smartass comment about how they should be running their site on one of those high-end chips right now.

    1. Re:Site's down by Mysticalfruit · · Score: 1

      Well, their site is fine... the problem is that they've only got 1/3 of all the bandwidth of the internet and we control 1/5...

      --
      Yes Francis, the world has gone crazy.
    2. Re:Site's down by maxwell+demon · · Score: 1

      The new processor benchmark: How long can they stand slashdotting?

      --
      The Tao of math: The numbers you can count are not the real numbers.
    3. Re:Site's down by AceCaseOR · · Score: 1
      Um... you know that 1/5 is less than 1/3, right? If they had 1/3 of the bandwidth on the Internet and we controlled 1/5, thent hey wouldn't have to worry about being /.ed.

      And yes, I know that was a joke.

      --
      Zagreus sits inside your head, Zagreus lives among the dead, Zagreus sees you in your bed and eats you in your sleep.
    4. Re:Site's down by 74nova · · Score: 1

      i think maybe his point was that 1/5 is a significant portion of 1/3 of the whole. if we take up 1/5, that doesnt leave a lot of room for anybody else. i dunno, maybe he just got it backwards. not worht the effort i put into this post, probably.

      --
      use your turn signal! you people act like it's divulging information to the enemy
  13. Apparently Linuxhardware needs more hardware by Anonymous Coward · · Score: 0

    Maybe they can appropriate some of the hardware they tested to build a more robust web server.
    I can't read the f&#@(&$ article because the site is already non-responsive after fifteen comments.

  14. MMORPGs by Anonymous Coward · · Score: 0

    Remember this: 32-bit will be gone once gaming, and in particular massive multiplayer gaming demands 64-bit clients in order to keep up.

    It will take between 5 and 8 years.

    1. Re:MMORPGs by Anonymous Coward · · Score: 0

      Actually, I think that MMORPGs will benefit from infinite badwidth, zero latency, 100% reliable network connections much more than 64-bit clients, after that it'll be a GPU capable of driving a 200dpi 2-meter-diagonal roll-up display, and THEN you can sell me on a 64-bit CPU.

      I've looked in my case while playing MMORPGs. Generally the CPU leaves a sign up saying "Potty break: back in 5" while the network & graphics cards are churning out frames.

  15. Answer: Compilers by October_30th · · Score: 5, Insightful
    Where is the AMD's answer to Intel's compiler? Intel's Fortran and C/C++ compilers optimize floating point code so that it performs 20-30% better on your Intel CPU than the GCC produced code?

    That's why I still buy Intel.

    --
    The owls are not what they seem
    1. Re:Answer: Compilers by thebosz · · Score: 4, Insightful

      That's a good point. But for the average user AMD just always seems like a better choice from a cost/performance point of view.

      --
      The Kerr Divine: My wife's battle with a mysterious illness.
    2. Re:Answer: Compilers by October_30th · · Score: 1
      Indeed. No question about that. If you're not into heavy floating point computing AMD's the way to go.

      I wonder if AMD has any plans to rectify this problem. Multi-CPU Opterons combined with a native compiler support would just kick ass when it comes to crunching numbers.

      --
      The owls are not what they seem
    3. Re:Answer: Compilers by Anonymous Coward · · Score: 0

      I wonder if AMD has any plans to rectify this problem.

      I think AMD are funding SuSE to enhance GCC for x86_64 - but whether that's just for the basic port or the fine tuning too I'm not sure.

    4. Re:Answer: Compilers by PetiePooo · · Score: 2, Informative

      Where is the AMD's answer to Intel's compiler?

      I can't find the link, but I remember hearing once that code optimized for the Pentium actually had a larger speed improvement on the Athlon than it did on the Pentium. I don't recall which models were under test or what their clock speeds were, but it was a few years ago now. It wasn't publicized much, of course, because it bloodied Intel's nose..

      The point is that AMD CPUs perform optimized and unoptimized tasks more efficiently (wrt clock speed) than Intel CPUs. While Intel has focused on exceedingly high clockspeed (witness the 31 stage pipeline..) and compiler improvements (IA-64/VLIW anyone?), AMD has gone for parallelism and efficiency in utilization.

      AMD pioneered vector math with 3DNow (Correct me if I'm mistaken, but I'm pretty sure 3DNow predates MMX...) but, instead of Intel using AMD's technology, they developed MMX in response. I believe code optimized for either extension saw about the same improvement. However, as market leader, Intel led the market where they wanted. And since more developers coded for MMX than 3DNow, AMD added MMX. In doing so, AMD's chips started benefitting just as much or more from Intel's extensions.

      Historically, its been Intel introducing the extensions, and AMD quietly implementing them in response. The x86-64 extensions are shaping up to be the first example of an AMD-pioneered extension that Intel will implement!

      As for Intel vs. GCC compilers, GCC is a very flexible cross compiler that targets many different architectures. Intel's compilers are very architecture specific (hint: they target only Intel's architectures). Apples and oranges. Like Java and the CLR; their design goals are worlds apart.

    5. Re:Answer: Compilers by Cleveland+Steamer · · Score: 1
      Please see this article at The Inquirer: New Intel compiler gives AMD Athlon64 a boost

      A READER WRITES to bring our attention to latest issue of German magazine, c't.

      According to the magazine's own tests, a new Intel V8 compiler can give a boost to the performance of applications running on Intel platforms by between 5 and 10 per cent.

      The chipmaker may be miffed to learn, however, that its compiler can help boost the same apps by a similar margin on rival AMD's Athlon64 platform, when suitably tweaked.

      According to our correspondent, the compiler switch -QxN produces x86 code which runs only on P4 CPUs, not on AMD CPUs. However, the boffins at c't used the -QxN to produce code, patched out the CPU type inquiry and so managed to get the code to run on the Athlon64.

      As a result the chip notched up a record-breaking Spec score.

      According to the tests, under Windows, the P4 3200 gets a SPECint2000base value of 1286 while the Athlon64 3400+ scores 1404. Although, in SPECfp2000base, the P4 3200 scores 1257, against the Athlon64 3400+'s score of 1227.

      Hmmm.

      Here's a link to c't where you'll find no mention of these shenanigans whatsoever.

    6. Re:Answer: Compilers by pantherace · · Score: 1
      Historically, its been Intel introducing the extensions, and AMD quietly implementing them in response. The x86-64 extensions are shaping up to be the first example of an AMD-pioneered extension that Intel will implement!

      Great... Intels will finally have 3dnow! :)

    7. Re:Answer: Compilers by Glock27 · · Score: 2, Interesting
      Where is the AMD's answer to Intel's compiler?

      On the Portland Group's website. If you have the money, they're darn good compilers. Microway sells them as their preferred C/C++ suite, which says something... They support AMD64 too! :-)

      The only downside, for some, is that they're Linux-only.

      --
      Galileo: "The Earth revolves around the Sun!"
      Score: -1 100% Flamebait
    8. Re:Answer: Compilers by orbitalia · · Score: 1

      I think you will find them right here

    9. Re:Answer: Compilers by Yokaze · · Score: 1

      > patched out the CPU type inquiry and so managed to get the code to run on the Athlon64.

      To avoid accusations: As stated in the manual, the flag -QxN includes the check for the processor, the flag -QaxN does not. Otherwise the code is identical. And to free the c't from doubt of bad reporting, it is mentioned in the article. They mereley patched it to check that the performance is the same.

      --
      "Between strong and weak, between rich and poor [...], it is freedom which oppresses and the law which sets free"
    10. Re:Answer: Compilers by Anonymous Coward · · Score: 0

      Have you ever tried Intel's compiler on AMD ?
      It actually optimizes floating point intensive code better for Athlons than for Intel CPUs. And then there is GCC 3.4 coming, which seems to match and sometimes even exceed Intel (well, at least in my type of application, which is Monte Carlo simulations).

    11. Re:Answer: Compilers by Anonymous Coward · · Score: 0

      We use Java now. C and C++ have become irrelevant.

  16. Yet Another... by quandrum · · Score: 5, Interesting

    example of the megahertz myth. The chip with the largest cache won. Hands down, no contest.

    1. Re:Yet Another... by mrm677 · · Score: 4, Interesting

      example of the megahertz myth. The chip with the largest cache won. Hands down, no contest.

      Of course. Eliminating a cache miss is huge. Suppose that it takes 300 nanoseconds to get a word from memory.

      At 3GHz, that is 900 wasted cycles where each cycle could have potentially retired 3 instructions.

      At 6GHz, assuming your memory latency doesn't change, that is 1800 wasted cycles.

      It is well known that the memory latency is not keeping up with the clock cycle latency. This is why memory system design is becoming far more important the processor core design, and is also why Itanium SPEC numbers are so good.

    2. Re:Yet Another... by Loki_1929 · · Score: 2, Funny

      "The chip with the largest cache won. Hands down, no contest."

      You make it sound as though cache is the primary factor in CPU performance.

      That's... absurd.

      Also, the statement is non-sequitur. The Athlon64 3400+ has more L1+L2 cache than the P4 Prescott or the P4 3.2 Northwood, and I believe also the P4EE (Gallatin). The P4EE has 2MB of L3 cache. There was no discernable "winner". There were only a handfull of chips tested. The AthlonFX wasn't amoung them. There were only a handfull of benchmarks. This is an example of a very small sample of a very small sample using a very small sample. Thus, the margin of error for the overall results is so extreme as to virtually negate the purpose of testing in the first place.

      --
      -- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
    3. Re:Yet Another... by thelasttemptation · · Score: 1

      The P4EE has 2MB of L3 cache
      That's level 2 cache to the rest of us...

    4. Re:Yet Another... by Anonymous Coward · · Score: 0

      The megahertz myth is a stupid idea. To imply that megahertz has no bearing on performance is more ignorant than to imply that it is the sole determinant of performance. I don't understand why your post, which takes useful data than spins them to be more ignorant and misrepresentative, got modded informative.

    5. Re:Yet Another... by Anonymous Coward · · Score: 0

      Megahertz myth?
      Looking at any review site's benchmarks it seems going from Athlon64 3200+ to 3400+, with a 10% clock speed boost, the benchmark also goes up about 9%. Cutting bandwidth in *half*, from Athlon64FX51 to Athlon64 3400+, is almost no difference in performance, and cutting cache in half in Athlon64 3000+ is only a few percent loss.

      Even sites like anandtech proclaimed there was no reason to get an FX51 when the 3400+--at the same MHz---performs almost as well at half the cost.

      Clearly we're reaching a point where megahertz, more ALUs, more threading, matters a lot more than bandwidth. Why else would Intel, AMD, and IBM all talk about "hyperthreading" or multi-CPUs on a chip? We've over compensated for our bandwidth problems and need the MHz to back it up now.

    6. Re:Yet Another... by Loki_1929 · · Score: 1

      "That's level 2 cache to the rest of us..."

      I'm not entirely sure who "the rest of us" is, but unless Intel is making a special version of the CPU marketed just for me, it's Level 3 cache on all their P4EEs. The P4EE has 20K (8+12) L1, 512KB L2, and 2MB of L3. As I recall, the L3 mirrors what's in the L2, thus giving you an effective 1.5MB L3. The latency on that L3 cache is more than double the latency for the L2 (13.44ns vs 5.94ns), which still beats the hell out of the memory latency (about 64ns).

      --
      -- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
    7. Re:Yet Another... by Anonymous Coward · · Score: 0

      The chip (especially with hyperthreading) just doesnt sit idly by for those 900 cycles. The chip designers aren't retarded, you know...

    8. Re:Yet Another... by mrm677 · · Score: 1

      Without hyperthreading, the chip really does sit idle. An instruction window is only so big. You can tolerate an L1 miss, and an L2 miss if the L3 is on-chip, but going off-chip kills you. Your instruction window, typically less than a couple hundred entries, fills up and you are stalled by dependencies.

      Since Itanium is an in-order processor, it stalls period. And yet it performs pretty darn good. The reason is that superscaler out-of-order execution is becoming less useful with the increasing memory latency gap.

    9. Re:Yet Another... by Short+Circuit · · Score: 1

      (chuckle)

      Does anyone else remember the first celerons? When they got rid of the cache? (Then the later ones, when they started putting the cache on-die?)

    10. Re:Yet Another... by thelasttemptation · · Score: 1

      sorry, my mistake, I was basing my comment on a post in ace's hardware:
      http://www.aceshardware.com/forum?read= 105064614
      but I should have checked it out before I spouted, sorry.

    11. Re:Yet Another... by Loki_1929 · · Score: 1

      " sorry, my mistake, I was basing my comment on a post in ace's hardware:"

      Let it never be said that a comment in Ace's forums isn't worthy of citation. ;)

      I love Ace's, as it's one of the few places where the topics can go over my head from time to time.

      --
      -- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."
  17. Disappeared by slickjolly · · Score: 2, Informative

    Been 'Dotted already??? Jeez, that was fast.

    1. Re:Disappeared by Anonymous Coward · · Score: 0, Flamebait

      Of course it was fast: they're running linux! :)

    2. Re:Disappeared by dpilot · · Score: 1

      Where are the karma whores with mirror URLs, when we need them?

      --
      The living have better things to do than to continue hating the dead.
  18. practical review? by Anonymous Coward · · Score: 0

    Are the results of slashdot on linux-hardware going to be published?

    I'm looking forward for the slashmark-results!

  19. It gets better by florin · · Score: 4, Informative

    Don't let the fact that they proclaim the Athlon 64 to be the 'clear looser' in the SPECViewperf discipline because of the poor results in the DX-08 and DRV-09 tests fool you.

    Those scores are probably not representative of the true performance of the AMD processor but rather of the early stages of optimization of the Linux support for the Nvidia NForce 3-150 chipset. The very same weakness was observed in the past in other reviews that used Specviewperf on Windows platforms, such as this one from THG. Subsequent versions of the Nvidia drivers have since brought noticeable improvements.

    The AMD scores would likely have been much more competitive if a motherboard based on another Athlon 64 chipset like the VIA K8T800 would've been used for this review.

    1. Re:It gets better by Afrosheen · · Score: 1

      You know, that's exactly what I was thinking. The second I saw their motherboard of choice listed (the nforce3) I moved back a few inches. They just suck HARD under linux, and it's all because of nvidia's beta-quality nforce drivers.

      I would have picked a VIA chipset anyday for this test. Although VIA has had issues in the past under linux, these days it's better than the nforce, for maturity and stability if nothing else.

  20. Re:Extra Transistors (Its from the caches) by uarch · · Score: 1

    They doubled the size of both the L1 data-cache & L2 cache...

  21. Difference is in price & power consumption by Junks+Jerzey · · Score: 4, Informative

    "Prescott, Northwood, Extreme Edition, and the AMD Athlon 64."

    In all honesty--unless you absolutely need 8GB of memory--there's little difference between these processors in terms of performance. They're all more or less in the same ballpark. Sometimes faster, sometimes slower, depending on the benchmark. None of them is a huge breakout CPU performance-wise.

    Here's what's different:

    PRICE: There's a lot more than a few percent variation in price.

    WATTS: In exchange for your 5-15% speed boost, note that you're getting more than a 15% increase in power usage.

    1. Re:Difference is in price & power consumption by bhtooefr · · Score: 1

      AFAIK, A64 is the cheapest (except for possibly Northwood), and the coolest (ditto on Northwood).

  22. OC'ing AMD Bartons by Anonymous Coward · · Score: 0

    Maybe connecting and disconnecting miniscule jumpers under a microscope is not everyone's cup of tea...

    1. Re:OC'ing AMD Bartons by Anonymous Coward · · Score: 0

      All I did was go into the bios, and set the memory speed to 200. The 2500+ (11x166) became a 3200+ (11x200). That's it.

    2. Re:OC'ing AMD Bartons by Anonymous Coward · · Score: 0
      Then maybe you and other AMDers should inform the world that the bad old days of a microscope, dremel and graphite pen are over...

      Most people, myself included, still consider overclocking AMD CPUs as neurosurgery.

    3. Re:OC'ing AMD Bartons by Anonymous Coward · · Score: 0

      Up until a couple months ago, the CPU's weren't even multiplier locked anymore. You could do things like 12x200 to push them to even higher speeds.

  23. Crappy unformatted article text... by Westech · · Score: 1, Redundant

    Better than nothing until the ./ effect wears off:

    Intel's Prescott, Intel's Extreme Edition, and AMD's Athlon 64 3400+ posted by augustus on Monday February 02, @11:51AM from the CPU-Gods dept. Today Intel unveiled the next great chip in their line of Pentium 4 processors. This chip codenamed "Prescott" has been talked about for quite some time and we hope the chip lives up to the hype. With new features like an increased L2 cache and new instructions, the Prescott has the goods on paper. Along with this new processor, Intel also released a speed bump to their "Extreme Edition" line which brings the chip up to 3.4GHz. The Extreme Edition chips encompass the same features of their normal "Northwood" Pentium 4 cousins but also add an additional 2MB of L3 cache to the existing 512KB of L2. In this review we will introduce you to these new Intel processors and also bring in the Athlon 64 desktop processors now available at 3400+ model numbers. If your ready for a look into what AMD and Intel have in store for you today, read on. Intel's Chips First, we'll talk about Intel's Extreme Edition part. The Intel Pentium 4 Extreme Edition offers nothing fancy like new instructions or a new manufacturing process. Instead, Intel took the brute force approach on this CPU and simply added an additional 2MB of L3 cache. This wasn't even a processor redesign for Intel, they simply took their Xeon MP processor and repackaged it in a Socket 478 socket, compatible with today's 865/875 series motherboards. Many have said that this processor wasn't even planned but that Intel decided they needed an answer to AMD's Athlon 64 FX line. This wouldn't be confirmed by Intel, of course, but it's not like any processor company to spring random new products on the industry without a fair amount of hype. The Extreme Edition processor was launched at 3.2GHz and was extremely difficult to get. About the only way to find one initially was to buy a new system through a select few retailers. Not only were they hard to get but the price was prohibitive at around $1000 for the processor alone. The processor is available now through many more retailers but the price has wavered little. The 3.4GHz already seems like it will be a little easier to find than it's predecessor but expect to add at least $100+ for the extra 200MHz of the 3.4GHz model. The Prescott is an entirely different story from the Extreme Edition. The Prescott has been on Intel's road map for quite some time and was a necessary step in processor evolution. The biggest feature of the Prescott that you'll read about is the move to a 90nm manufacturing process from the previous 130nm process. As we've discussed in other articles about process shrinks, this allows for two things. First, it allows Intel to shrink die sizes, resulting in more CPUs per wafer (the base from which CPUs are carved). This will lower Intel's cost per chip. Second, it will allow for the processor to operate with less power consumption per transistor, due to the fact that the electrons will have to travel a shorter distance between transistors. Another change in this manufacturing process is the use if strained silicon which allows for an easier flow of electrons. The next big feature in this processor is the addition of 512KB more L2 cache bringing the total to 1MB. This increase in cache size is something that always seems to speed up the majority of applications. This allows for more of the application's code to fit into a extremely fast portion of memory sitting right next to the processor running at the full processor clock speed. While this seems like something relatively easy to add to a processor, it adds a great deal of transistors to the core which increases the cost of manufacturing. Finally, there are some architectural changes for the Pentium 4 that come with the Prescott. The first is that the pipeline has been extended and reorganized to make the processor more efficient. Along with this reorganization, the way memory is handled internally has been optimized

  24. Processor Last by Enonu · · Score: 5, Insightful

    For my day-to-day activities, I'm much more affected by the speed of my hard disk and the amount of memory I have installed. IMHO one should spend the minimum amount on a processor that they feel comfortable with, and then use the savings for the rest of the system.

    Buy brand name components, a decent 7200 or even 10K RPM hard disk, and a GIG of memory. Don't forget input and output either! A cheap monitor, keyboard, or mouse will ruin your experience. Don't skimp on where it counts so you can simply brag about having one processor vs. one that's slightly slower.

    1. Re:Processor Last by Just+Some+Guy · · Score: 1
      one should spend the minimum amount on a processor that they feel comfortable with

      I have a simple method for picking CPUs:

      1. Go to Pricewatch and find the lowest prices for each of the processors in the range I'm interested in that's from a store I recognize and have good dealings with.
      2. Make a mental graph of speed vs. price.
      3. The graph usually looks like a nearly-flat line at the low end, and a nearly vertical line at the high end. Imagine something like f(x) = x^4 for x in [0, 4]; where x 1, the line is steep.
      4. Buy the CPU whose price is at the cusp.

      "Ditto" for the rest of your comments about memory and drives. The local Office Max keeps running periodic sales of WD 120GB SE (8MB cache) drives for $59, so I upgrade the drive(s) in one of my systems every six months or so.

      --
      Dewey, what part of this looks like authorities should be involved?
    2. Re:Processor Last by Just+Some+Guy · · Score: 1
      Darn HTML comments. The end of step 3 is:
      where x < 1, the line is nearly level, and where x > 1, the line is steep.
      --
      Dewey, what part of this looks like authorities should be involved?
  25. brand blindness by dpilot · · Score: 1

    I'm mostly brand-blind, but...

    Any purchasing decision tie will go to the underdog. I might even de-optimize by a few percent in favor of the underdog, because competition benefits all of us, and therefore it's up to all of us to keep competition alive.

    But if the underdog is clearly inferior, they've lost my purchase.

    Another pet peeve, seen years back on Usenet, (paraphrased) "I like AMD and Cyrix in the market, because even though I'd never buy them, they keep pushing Intel on performance improvements."

    --
    The living have better things to do than to continue hating the dead.
    1. Re:brand blindness by Linus+Sixpack · · Score: 1

      I agree.

      For the record I think AMD has had the better value\performance point since the k5.

    2. Re:brand blindness by AhBeeDoi · · Score: 1

      Consumers could really benefit from a third significant processor designer. Cyrix was in the game for a while but their CPU's were not competitive performers but, in the end, they could only compete on price for low end machines. With only two major players from which to choose, I don't believe innovation will transcend revving up the clock speeds or adding more cache memory in a tit-for-tat race of incremental "improvements".

    3. Re:brand blindness by Linus+Sixpack · · Score: 1

      The problem is that without a portfolio of patents to buy your way into production there is a huge roadblock to new companies.

      In Video Cards the only reason why S3 or Matrox have any chance in the industry is that they have patents to bargain with.

  26. Is there a maxed memory test somewhere? by Linus+Sixpack · · Score: 2, Insightful

    The first market I can think of for these machines is the memory hungry. Mostly I'm thinking of databases seeking to be entirely in ram. I don't personally have any 8gb databases but I think they are more common than people think.

    I'd love to see a comparison, on linux, Solaris, even windows of Databases crunching big piles of data.

    LS

  27. Troll? by Anonymous Coward · · Score: 0

    What idiot modded this troll? Metamoderators, start your engines.

  28. Multimedia editing and encoding, that's what by StandardCell · · Score: 2, Informative

    Although the Athlon64/Opteron and AthlonXP processors either match or surpass the Pentium 4 line, the one application that the Pentium 4 processors still excel at is in multimedia editing and encoding. Most people don't look at Hyperthreading favorably, yet with Hyperthreading enabled you get an over 30% performance boost in DV25 to MPEG-2 transcoding for video with everything else equal. That's not to say that the Athlon64/Opterons are not useful, but this is one area where they still excel. Considering that transcoding is the major bottleneck for the folks who edit video and create DVDs, there is a good reason to go for a Pentium 4. 30% of your time on a 2 hour video is a lot of time lost if you're trying to crank out videos. Not to mention that most of Matrox's editing cards are almost always approved for Intel hardware to be stable but not for all AMD hardware, particularly motherboards.

    If, however, you're a gamer and aren't doing much media encoding or do it casually, then I would recommend an Athlon64.

    1. Re:Multimedia editing and encoding, that's what by jo_ham · · Score: 1

      Although if you're pro or semi-pro in the video production arena, Apple is almost too easy a choice.

      I've not edited on anything in the PC arena that touches the Mac - I've tried Avid, Premiere and a few "prosumer" packages.

      On the Mac side, Final Cut Pro is godlike - if only for the way it integrates so well into a whole workflow.

      Media 100i also demolished Avid in my opinion (although that was a closer call), although the latest offering from the Media 100 group runs on x86 (starting at $50,000 though, or something silly like that).

      I can get an Apple box up and running with FCP4 and associated apps for a fraction of that price, and still be cheaper than pretty much any serious PC contender.

  29. Warning - Somewhat Offtopic by karnal · · Score: 1

    I've been with AMD as long as I can remember, except for my first machine, and machines I've aquired for free.

    The only problems I've had with AMD:

    1. The Via Apollo chipset - in order to get win98 or later running, you had to install the motherboard drivers (I ran 95 at the time, and was trying to get 98 running, and couldn't for about a year, until I loaded the mobo drivers right after installing 98. Windows wouldn't see the ethernet card!)

    2. KT133 - I bought a KT133 Abit motherboard. That was a mistake -- I'll never trust Tom's Hardware again. Given, now the machine is rock solid, but for the year that I used it as my desktop, it was an endless loop of installing the new via drivers, as well as bios updates to get the thing halfway stable under stress.

    Granted, neither of these problems are necessarily with AMD in and of itself, mostly with VIA, but they were really supposed to be the leader... I have comfort nowadays that the boards I buy that support the Athlon XP (I own one kt400 and one nforce2 mobo) just "work". As well as have some good "tweaking" options.....

    --
    Karnal
  30. They Should Have Used by dcocos · · Score: 1

    some of the hardware they discussed to run their own site to keep up with the slashdotting.

  31. The IAs are roughly comparable timing wise... by Ayanami+Rei · · Score: 1

    so you just use ICC with SSE2 turned off. That seems to work just fine.

    --
    THIS THING CAN TURN ON A DIME, MACROSSZERO STYLE ALSO FUCK BETA, ~NYORON
    1. Re:The IAs are roughly comparable timing wise... by October_30th · · Score: 1
      Interesting.

      Got any benchmarks?

      --
      The owls are not what they seem
    2. Re:The IAs are roughly comparable timing wise... by Anonymous Coward · · Score: 0

      Yes. Check out the SPEC CPU2000 benchmarks.

      Athlon's are known for their great floating point performance. I'm not sure what the previous poster was talking about. The SPEC benchmarks prove it, as does the FEA code LS-DYNA which I run on both Athlon's and Xeons. Athlon MP 2600+ is as good as the 2.8 Xeons.

  32. Compare any to any by Anonymous Coward · · Score: 2, Interesting

    Oh goody, this gives me a chance to trot out one of my favourite rants.

    I really don't understand why more sites don't let you compare *any* part to any other, in a database approach, like StorageReview and some online stores. It is in fact relevant to do so for more than interest, you could for example find out if it is more cost effective to use 5 $100 chips or one $1000 chip. But sites do not support this, instead you have to piece it together yourself (if you're lucky and they're using consistent methodologies). It's not suprising on the candy sites like Anandtech or ExtremeTech where plainly they're just there to sell product, but on this type of site you might expect a little more.

    1. Re:Compare any to any by Mr.+Darl+McBride · · Score: 1
      The OS and applications aren't static targets. The version of Gentoo needed to test an AMD64 would have nothing to do with the version of Gentoo used to test the last 20 or so processors.

      If you want them to run the same tests over and over again with every hardware configuration with every new software release, I am sure the results would be interesting. However, this would take an order of magnitude more effort and the resulting gain in readership isn't likely to increase in proportion to that effort.

      If you want to simply use the old benchmarks and say there's a margin of error, go ahead. They already gave you the previous information. Spend ten minutes with gnumeric and the site search feature.

  33. BIOS - [Advanced] - FSB - 200MHz - F10 by Ayanami+Rei · · Score: 1

    durrrr.... that was hard....

    --
    THIS THING CAN TURN ON A DIME, MACROSSZERO STYLE ALSO FUCK BETA, ~NYORON
  34. No native AMD64 benches? by Magila · · Score: 4, Interesting

    They were running Gentoo yet they apparently didn't even attempt to get the Althon 64 running the AMD64 port. Both POVRay and Vorbis-tools are already marked stable on AMD64, would have at least made the comparison a lot more interesting.

  35. Intel and AMD64 by Short+Circuit · · Score: 2, Interesting

    I don't see AMD64 showing up in Intel's processor line for a long, long time. I expect they'll build their own set of 64-bit X86 instructions and specifications. After all, they didn't adopt 3dnow! or 3dnow!ext, did they?

    In fact, that's probably why Microsoft hasn't released a 'final' AMD64 port of their OS yet. They're expecting a split in the market, and they're not going to get caught in bed with the side that hasn't historically been dominant.

    1. Re:Intel and AMD64 by cens0r · · Score: 3, Interesting

      Actually microsoft has told intel they aren't going to support another version of windows. Intel has two choices, stick with Itanium or follow AMD's lead. It looks like Tejas is going to follow AMD. The reason Microsoft is going slow is simply because the OS isn't quite ready yet.

      --
      Jack Valenti and Orrin Hatch will be first up against the wall when the revolution comes.
    2. Re:Intel and AMD64 by Alizarin+Erythrosin · · Score: 1

      Quite right. As the parent pointed out, the OS isn't ready. The Itanic version didn't have DirectX or Windows Media Player. For a "consumer" OS built on x86-64, those technologies (DirectX anyways, I could care less about WMP) must be included. Couple that with 64-bit drivers that need to be developed by hardware makers, and it can explain the delays all by itself. Who'd want an OS that there are no drivers for?

      --
      There are only 10 kinds of people in this world... those who understand binary and those who don't
    3. Re:Intel and AMD64 by Anonymous Coward · · Score: 0

      Um, Itanium is strictly a server chip. It was NEVER intended to go in a "consumer" product, it isn't optimized for desktop or gaming tasks, and you would be severely retarded to try to do that. THATS why microsoft's IA-64 OS didn't have DirectX or WMP- there is absolutely ZERO need for either of those on a server.

      How many times do I have to say this?

    4. Re:Intel and AMD64 by Anonymous Coward · · Score: 1, Interesting

      Microsoft is going slow is simply because the OS isn't quite ready yet.

      Since when is not quite ready ever stopped Microsoft from releasing software?

      If Microsoft held back Windows until it was ready, we'd all be running Linux!

      I smell Microsoft stalling to protect their relationship with Intel. To not stall is to give AMD a time to establish itself in the 64bit desktop arena.

    5. Re:Intel and AMD64 by Anonymous Coward · · Score: 0

      If Microsoft held back Windows until it was ready, we'd all be running Linux!

      You must mean we as in the average Slashdot reader, because I used Windows95 (unfortunately) for a little while back when it was 'not ready', and eventually switched to Linux. Not that Linux was much better. I mean, it didn't have any application crashes. But it also didn't have any applications either, so that doesn't mean much. I later switched back to Windows when 2000 came out, so that I could actually use some real apps again.

  36. Perhaps the 'Nehemiah' ? by Space+cowboy · · Score: 1

    Which is currently only on Mini-ITX boards, it's an evolution from the Cyrix line of processors and isn't a great performer. Fine for low-CPU things or MPEG playback (it has hardware assist) but currently limited to ~1GHz, and even then performs more like an 800MHz P3.

    Lots of info at www.mini-itx.com

    Simon.

    --
    Physicists get Hadrons!
    1. Re:Perhaps the 'Nehemiah' ? by Rob+Simpson · · Score: 1
      Actually, it also comes in a socket 370 chip. (I got one from TigerDirect.ca for $50CA, but they don't sell them anymore.) It works well for a quiet, energy-efficient PC for internet use, old games, and mpeg4 playback, but nothing that requires serious performance.

      SiSoftware Sandra

      Processor Model : VIA Nehemiah Speed : 998MHz
      Performance Rating : PR898 (estimated)
      Type : Standard
      Multiplier : 15/2x
      Generation : G6
      Name : C5A (Ezra-T) C3/Eden 1000MHz+
      Revision/Stepping : 9 / 3 (0)
      Maximum Physical / Virtual Addressing : 32-bit / 32-bit

      Co-Processor (FPU)
      Type : Built-in
      Revision/Stepping : 9 / 3 (0)

      Processor Cache(s)
      Internal Data Cache : 64kB Synchronous Write-Back (4-way, 32 byte line size)
      Internal Instruction Cache : 64kB Synchronous
      Write-Back (4-way, 32 byte line size)

      Upgradeability
      Socket/Slot : Socket 370
      Upgrade Interface : ZIF Socket
      Supported Speed(s) : 998MHz+

      Environment Monitor 1
      Model : VIA 686PM ISA
      Version : 10.02
      Mainboard Specific Support : Yes

      Sensors
      CPU Temperature : 30.3C / 86.5F
      CPU Voltage : 1.45V

  37. Re:SO by Anonymous Coward · · Score: 0

    You're just pissed cos she won't put out for you.

  38. It was a metaphor, stupid.
    *ducks*

  39. None of these processors are running this site. by TheVidiot · · Score: 1

    Down.

  40. Answer 2: Heat by stacko · · Score: 1

    AMD chips run significantly hotter than Intel chips. I have a dual-AMD box that, to remain stable, moves enough air to make a helicopter jealous. As an added bonus, it acts as a heater for the entire room, while making enough noise to bug neighbors two or three blocks away. I run it as little as possible.

    By comparison, I have an Intel server that runs 24/7, is inaudible, and makes no difference in the ambient room temperature.

    It's worth the (mostly negligible) cost/performance difference for quiet/heat-free computing.

    1. Re:Answer 2: Heat by Anonymous Coward · · Score: 0

      Have you looked at the latest chips? The Intel chips run hotter than the AMD's. I've got an Athlon XP 3200+ that tops out, on the hottest days, at 49C. That's without any sort of fancy cooling, just a Vantec Aeroflow.

    2. Re:Answer 2: Heat by Anonymous Coward · · Score: 0

      Intel chips run hotter than AMD ones do? What are you comparing? An Intel 386 25 MHz vs. AMD 3200+?

      Intel chips are currently the hottest on the market. The AMD chip I'm using now (1700+, 1.47 GHz) seems fine. I've got it running with a heatsink and a Zalman fan set to the lowest setting and my chip's running at 34 degrees. Silent.

    3. Re:Answer 2: Heat by Znork · · Score: 1

      If heat is a significant issue for you, you might consider underclocking. It's an extrordinarily efficient way to reduce heat. Reduce bus speed and core voltage and you can chop heat output to a third for no more than 25% performance loss. Cutting an Athlon XP from 1400 MHz down to 1000MHz with core down to 1.15V and you should be able run it at 21W with only a fairly large heatsink.

    4. Re:Answer 2: Heat by Yokaze · · Score: 1

      > AMD chips run significantly hotter than Intel chips.

      AFAIK, this hasn't been true since the introduction of the Pentium 4. The Prescott has a TDP of 108W, Athlon 64 3400+ a TDP of 89W, the Northwood 3.2GHz has a TDP of 82W.

      Could it be possible that other factors are responsible for the difference of noise?

      --
      "Between strong and weak, between rich and poor [...], it is freedom which oppresses and the law which sets free"
    5. Re:Answer 2: Heat by stacko · · Score: 1

      It's true, the new Prescott chips take a huge step back in TDP, essentially giving up the ground they gained when they introduced the Northwood core. However, IIRC, the Williamette TDP was better than the AMD competition at the time, meaning the Northwood beat the pants of the comparable AMD chip, TDP-wise.

      I know for certain that it's the CPU fans that are responsible for the noise. The noise increased dramatically when I replaced the CPU fans, which I had to do to keep the thermal alarm on the motherboard from sounding after a couple hours of use. FWIW, the system in question is a dual AMD Athlon-MP running at 1.8.

    6. Re:Answer 2: Heat by Hoser+McMoose · · Score: 1

      Nope, Willamette chips ran REAL hot as well. The TDP of the 2.0GHz Willamate ranged from 72W to 76W depending on the stepping. The highest maximum power consumption of any AMD Athlon or AthlonXP processor at the time was 72W for the "Thunderbird" Athlon 1400MHz. More recently the "Barton" AthlonXP chips running at 3000+ and 3200+ model numbers have exceeded this slightly at about 75W and 77W max, but all previous AthlonXP chips had a TDP in the 50-70W range.

      Really the only times that Intel chips ran cooler than AMD chips were when their chip generations weren't all that comperable. For example, when the Athlon first started shipping, Intel was still shipping the Pentium 3. The Athlon consumed more power than the P3. However once Intel started shipping the P4 the two companies had similar power consumption. Then Intel started shipping the "Northwood" P4 build on a 130nm fab process, and it consumed less power than the AthlonXP that was still being built on a 180nm fab process. Once AMD switched to a 130nm fab process, they were back in the same ballpark and Intel's chips actually ended up consuming more power.

      The main reason why so many people found that Intel chips ran "cooler" is that the majority of P4 heatsinks were 80mm x 80mm heatsinks, while the majority of AthlonXP and AthlonMP heatsinks were 60mm x 60mm heatsinks (you can get a lot of bigger Athlon heatsinks now, but they were rare until a year or two ago). As such, not only did the P4 have more metal to stread the heat to, they also were able to use large and slower-spinning fans, while the smaller AthlonXP heatsinks needed fairly high-speed (read: noisy) fans to keep cool.

  41. Windows to Linux? by Kruncher · · Score: 1
    I am a long time user of Windows and I'm thinking about switching to Linux.
    Which one is the best?
    Where do I get it?

    - For some cool OpenSource programs check out: KruncherInc

    1. Re:Windows to Linux? by Anonymous Coward · · Score: 0

      Which one is the best?

      Linux 10.3

      Where do you get it?

      http://www.sco.com

    2. Re:Windows to Linux? by Anonymous Coward · · Score: 1, Interesting

      Mandrake IMHO. Download the ISO from http://mirrors.sunsite.dk/mandrake/iso/

    3. Re:Windows to Linux? by Anonymous Coward · · Score: 1, Interesting

      The short answer is 'depends'. Long answer follows.
      Ease of install goes to Mandrake. Best 'tuner-boy' seems to be Debian (if you want a steeper learning curve but lots of configurability). Suse has the best (IMO) 64-bit implementation. Red Hat WAS good, but they do not have a non-business release anymore. Since you are coming from Windows, Mandrake is probably your best bet. You could try their MandrakeMove product - no install, just Linux on a CD - if you wanted to kinda 'test drive'.

    4. Re:Windows to Linux? by Anonymous Coward · · Score: 0

      It depends a lot on taste, a lot on how much time you're prepared to spend messing around.

      I've opted for Red Hat's Fedora Core 1 because it provides a nice friendly experience for a Windows emmigrant (I did a cold-turkey swap of Windows 2000 Professional for Fedora Core 1 about 6 months ago and haven't looked back).

      But please take a look at the features of the main distros yourself and see what suits you.

  42. Re:WHAT MONEY?!? by heff · · Score: 1

    i think there are nicer ways to put it ..wait no you pretty much hit the nail on the head.. you're right.

    well said.

    --

    --

    |-_-| . o O ( bEef!)

  43. Re:Let's be honest with each other, Linux Sucks .. by Anonymous Coward · · Score: 0

    that was the worst fucking webcomic, no the worst fucking comic, paper or otherwise, that I have ever had the displeasure of reading in my entire life. you, sir, are an idiot.

  44. Re:Let's be honest with each other, Linux Sucks .. by Anonymous Coward · · Score: 0

    When I read your comic I couldn't believe it...worse than The Family Circle?? Worse than Rhymes With Orange?!??

    ...but then I clicked on the link for that turd of a comic and I'm going to have to agree with you. I still think User Friendly is worst comic of all time...but this comes very close...maybe even a tie.

  45. I don't see it - -ever by kfg · · Score: 1

    My desktop already does everything I want it too, and plenty fast enough as well. I've upgraded from my 486 laptop because it does everything I want it to, and plenty fast enough.

    For basic office funtions we've been fast enough for years. If someone offers to sell you a 64 bit word processor they're yanking your chain to yank your wallet and most likely delivering Byzantine crappy code.

    Yeah, the gamers will want it, but some of them spend several hundred a year on video cards. If I were doing rendering or confirming the solution to the four color theorem I'd want it. Real workstation stuff.

    But on the desktop? The only reason you'll need it in two years is because they've barfed up a 64 bit Office that won't run on a 32 bit machine and EOLed the 32 bit version, for no other reason than to make you buy it.

    In the meantime I note that the 2.0 kernel is still being maintained. That's nice, it's what I've got on my laptop.

    Runs emacs and Visicalc just fine.

    KFG

  46. Re:WHAT MONEY?!? by fzammett · · Score: 1

    Modded as FLAIMBAIT already?!?

    I guess I should add to my statement... "UNABLE TO TAKE AN F'ING JOKE!!"

    Does no one understand sarcasm and humor these days?? Even if the humor isn't very good, it's usually still identifiable to most of us.

    GET WITH THE PROGRAM!

    --
    If a pion (n-) collides with a proton in the woods & noone is there to hear it, does lamdba decay into the source pa
  47. Re:WHAT MONEY?!? by JM · · Score: 2, Insightful

    I didn't know if this should be modded as troll or as funny. But it's so far away from my reality that I couldn't help but reply.

    I'm 32 with short hair, don't drink Mountain Dew because here in Canada it doesn't have caffeine, I live with my girlfriend and 1 year old baby, and I write GPL/BSD code and get paid for it.

    But you got it right on the lack of sleep part.
    I think *this* is the lowest common denominator of Linux users ;-)

  48. Re:WHAT MONEY?!? by Anonymous Coward · · Score: 0

    troll!!

  49. Re:WHAT MONEY?!? by fzammett · · Score: 1

    Ogre!! With no name!

    --
    If a pion (n-) collides with a proton in the woods & noone is there to hear it, does lamdba decay into the source pa
  50. Distro places by Unreal7000 · · Score: 1

    linuxiso.org distrowatch.com

    --
    "If it has screws, it was meant to be taken apart."
  51. Linux Kernel 2.6 benchmarks by pcs305 · · Score: 1
    Infoworld did some benchmarks on the new 2.6 Kernel on the Xeon, Itanium2 and Opteron.

    It is a very interresting read. And a good one to pass on to the not-so-technically inclined. The reviewer had some problems with the new kernel but after posting to the LKML Linus and some other maintainers fixed the problems. (like to see Bill do this). Some of the performance improvements boggles the mind!

    The AMD Opteron kicked same serious butt in these benchmarks.

  52. Yes, but.... by Kjella · · Score: 2, Insightful

    I agree in a sense, but for now most people who buy G5 machines will stick with OS X.

    ...couldn't you say exactly the same about x86 machines and Windows? So I don't see what the argument is.

    Kjella

    --
    Live today, because you never know what tomorrow brings
    1. Re:Yes, but.... by Anonymous Coward · · Score: 0

      ...couldn't you say exactly the same about x86 machines and Windows? So I don't see what the argument is.

      Although there might be some people who buy a G5 to run Linux, it is a very small percentage compared to the people who buy x86 to run Linux. I mean, the people running this test could have ran their benchmarks on alot of systems, but they probably decided to stick with machines that people would be more inclined to use Linux with. Also the fact that the G5 is expensive as hell probably helped sway their decision.

    2. Re:Yes, but.... by zeroprime · · Score: 1

      Point is, you could build an x86 machine without windows. You can't say that about a G5.

      --
      Hey! come on! try dividing it by anything!
  53. Not a simple reason... by Anonymous Coward · · Score: 0

    Windows NT supported the PPC and IBM supported it.

  54. Re:WHAT MONEY?!? by fzammett · · Score: 1

    No caffeine in Mountain Dew in Canada you say?!?

    I KNEW I hated America Jr. for a good reason!!

    --
    If a pion (n-) collides with a proton in the woods & noone is there to hear it, does lamdba decay into the source pa
  55. Re:WHAT MONEY?!? by Anonymous Coward · · Score: 0

    don't drink Mountain Dew because here in Canada it doesn't have caffeine

    Might as well just change the name to "Urine".

  56. All the same... by Kjella · · Score: 2, Funny

    I suggest you try both methods, and report back to us. If you can find a significant difference in the results, do tell (read: nada in either case).

    Kjella

    --
    Live today, because you never know what tomorrow brings
  57. Still simple by October_30th · · Score: 1
    Ok, but W2K and WinXP don't.

    So?

    --
    The owls are not what they seem
  58. Re:WHAT MONEY?!? by DeltaSigma · · Score: 1

    *takes a sip of his mountain dew*

    We mod you down because we're hippies and your capitalist rants about money offend us.

  59. MMX came before 3DNow by Ikeya · · Score: 2, Informative

    As a side note, MMX.
    AMD licensed MMX and then added on top of it...
    This article provides background.

    --
    ---- Move SIG...For great justice!
    1. Re:MMX came before 3DNow by PetiePooo · · Score: 1

      My bad.. I thought I remembered the first chips with 3DNow not including MMX. Thanks for doing the research for me.. 8-)

  60. My God....why by Prince+Vegeta+SSJ4 · · Score: 1
    use the name yellow dog for the name of a company pushing Linux, we all know what happened to Old Yeller...

    I await my -5 Mod punishment

    1. Re:My God....why by itomato · · Score: 1

      However, think about geek culture's fondness for cyclic-redundancy, counter-common names, and hidden meanings, and Ol' Yeller may be an asset..

    2. Re:My God....why by Lord+Kano · · Score: 1

      we all know what happened to Old Yeller...

      No we don't. That movie is only three years younger than my mother.

      What happened? Did he get to do some steamy XXX scenes with Lassie? Or maybe a three-way with some rich bitch toy poodles?

      LK

      --
      "Hi. This is my friend, Jack Shit, and you don't know him." - Lord Kano
  61. Two Words... "motherboard Chipsets" by Anonymous Coward · · Score: 0

    Intel has the competition beat bloody
    for stable server boards.

    I'm an AMD lover and all my own machines are
    AMD, but if it's gotta work, the first
    time, and keep on working, without me having to
    travel 2K miles to fuck with it, I use Intel.

    1. Re:Two Words... "motherboard Chipsets" by Anonymous Coward · · Score: 0

      The nForce2 chipset works quite well on a number of boards.

    2. Re:Two Words... "motherboard Chipsets" by Hoser+McMoose · · Score: 1

      nForce2 chipsets don't support ECC, making thing pretty much useless for servers. Great desktop chipsets but still useless for servers.

      When it comes to servers using AMD processors, there is really only one chipset vendor: AMD. The AMD 760MPX chipset for their AthlonMP and the AMD 8000 series for their Athlon64 and Opteron line are the only real server chipsets for AMD processors.

      Now, one important change has occurred though: the Athlon64 has a built-in memory controller, and that memory controller supports ECC (and Chipkill and memory scrubbing and all those other nice high-reliability features). That means that no matter how bad VIA fucks up their chipset design, Athlon64 processors will STILL support ECC. It also means that boards using nVidia's nForce3 line of chipstes will support ECC as well, though not due to anything nVidia has done.

      I'm still not sure that this makes the boards entirely suitable for servers, but it's certainly a step in the right direction.

  62. Re:WHAT MONEY?!? by Anonymous Coward · · Score: 1, Funny

    I live with my girlfriend and 1 year old baby

    Sinner.

  63. Re:WHAT MONEY?!? by Halthar · · Score: 3, Funny

    They're all a bunch of 16-year olds with long hair

    Hey, I am 17, but I do have long hair.

    Mountain Dew can marks embedded in their chin

    Does Code Red still count as Mountain Dew?

    living at home with mommy and daddy

    Now this one is just plain wrong. It's a finished basement apartment. At least that is what Mommy calls it.

    no job

    Now, now, some of us mow lawns in the summer.

    never had a date

    Who needs a date? I saved up using my lawn job and got a RealDoll(TM)!

    eyes more bloodshot from lack of sleep than Robert Downey Jr. after a weekend binge

    Okie, so ya got me on this one.

    who enjoy puzzles based on multi-dimensional quantum chromodynamics

    I prefer building proteins with Legos, but to each their own.

    giving away all their hard work FOR FREE!

    I get 8 an hour for mowing lawns, wrong again.

    WHAT F'ING MONEY?!?

    Got me again, I spent all my mow money on the RealDoll(TM). She was worth it though.

    Note: The above is not an accurate representation of reality.

  64. Don't use percentage, or use it consistently! by axxackall · · Score: 4, Insightful
    but for now most people who buy G5 machines will stick with OS X.

    but for now most people who buy x86 machines will stick with Windows. so what?

    but in reality the vast majority of individual Linux boxen will be using x86 based hardware so I don't think it's that big of a deal.

    but in reality the vast majority of individual desktop boxen will be using Microsoft based software so I don't think it's that big of a deal to test with Linux anyway.

    Sarcasm apart, I think it's a very bad tradition to consider Linux only as for x86 platform. There are Linux users on other non-x86 platforms. Their percentage is most likely not less than the percentage of Linux/86 users among all x86 users. So, the logic of using any percentage here is basically corrupted.

    Linux is multiplatform system. Check the kernel source code for the list of all supported platforms. Kernel - because that wat makes it called Linux, the distributions are usually more platform specific. Also Linux is multi-purpose system - it can be used for servers, for embedded systems and for desktops. The list of oticable desktop systems on the market includes at least x86 and PPC platforms. Therefore considering Linux desktop as only Linux/x86 is not more fair than considering desktop OS only as Microsoft Windows.

    --

    Less is more !
  65. Article's author is creative, at least by ColonelPanic · · Score: 2, Funny

    I laughed for minutes when I read "Without further adieu" in the article. What a wonderful new way to announce I'm a total illiterate and blissfully unaware of it!

    --
    "Skill shows through where genius wears thin." -Wittgenstein || Religion: uniting aviation and architecture.
    1. Re:Article's author is creative, at least by Anonymous Coward · · Score: 0

      Would you like to elaborate on why he used that wrong?

    2. Re:Article's author is creative, at least by Anonymous Coward · · Score: 0

      Well, apparently so is the rest of the world. A quick google showed that about 10% of the amount of correctly spelled versions, are the incorrect adieu version. What is the world coming to, when I can correct native speakers, sheeez ;) Anyway, for those wondering, it's ado, not adieu. Adieu originates from french and is a farewell remark (as a native swedish person, I can say that it's exactly the same in swedish, adjo, since we just "stole" all the cool and hip words from french a couple of hundred years ago). However, ado means trouble or fuss. So, without further ado, I say adieu!

    3. Re:Article's author is creative, at least by Anonymous Coward · · Score: 0

      ADO, not adieu. You're the type that says "all intensive purposes" too, aren't you?

  66. Unfortunate name, Prescott by panurge · · Score: 1
    Slightly off-topic, but irresistible. Intel has fallen into the US-centric error of not checking brand names around the world. For those who don't know (probably most reasonably normal people) John Prescott is a British politician who is famous for being very overweight, loud, aggressive - and nobody seems to know exactly what it is he does. He's kind of like Dick Cheney only not at all like Dick Cheney, if you see what I mean.

    Since the Prescotts seem to have distinctly underwhelming performance, perhaps it isn't as inappropriate a name as it might be.

    --
    Panurge has posted for the last time. Thanks for the positive moderations.
    1. Re:Unfortunate name, Prescott by October_30th · · Score: 1
      aggressive... Since the Prescotts seem to have distinctly underwhelming performance

      "Intel Prescott - the level of performance that will punch you in the face!"

      --
      The owls are not what they seem
    2. Re:Unfortunate name, Prescott by mjake · · Score: 1

      I think you have fallen into the engineer-centric error of mixing up internal code names and marketing (brand) names. I don't think Intel marketing ever used Prescott or Northwood in their marketing. For the general public, they just slapped an "E" on the end of the Pentium 4 processor names for Prescott.

      Prescott was a name probably not decided by marketing, meant for internal Intel use. Since it wasn't intended for marketing or even public consumption they didn't care about checking it around the world.

    3. Re:Unfortunate name, Prescott by imsabbel · · Score: 1

      And in german prescott can be pronounced as "compacted excrements"

      --
      HI O WISE PRINCE. WHT TOOK U SO DAM LONG?
  67. Prescott, AZ by Anonymous Coward · · Score: 0

    To me, I think of Prescott, AZ. It's a small town a couple hours north of Phoenix, getting into the mountains, with real winter weather and lots of pine trees. It was Arizona's territorial capital, and was named after William Hickley Prescott. What does this mean for the processor? Not much... it's just a name.

  68. Server systems? by RAMMS+EIN · · Score: 1

    All those benchmarks are so x86-centric. It would be interesting to run benchmarks with Linux and some other OSes on other architectures as well. I am interested to see how other architectures compare to x86 on different fronts, and how well Linux runs on those archictectures compared to other OSes.

    --
    Please correct me if I got my facts wrong.
  69. Don't you mean by Cyno · · Score: 1

    Current Intel Processors Tested With Linux?

    Its nice they threw in an AMD for good measure, but Linux runs well on the AMD64, G5 and ia32, among many other things. So why not at least compare Apples to Intels?

  70. Selling? Me too! by __aafutm5472 · · Score: 1

    Hey, as long as we're selling old hardware, I have 5 Netframe 9800s. 1 has all four PPro 200s (1MB cache -- those chips will also work in the Micron W6-Li board), 2 have two CPUs, the other 2 are parts.

    C'mon, who doesn't want a big chassis with hot-swappable fans, hot-swappable PCI slots, hot-swappable 8 drive RAID arrays... ??

    Priced to sell!

    1. Re:Selling? Me too! by notbob · · Score: 0

      Bah my netfinity has all that too,they're good dependable boxen.

      Much more so then a lot of this new crap, my netfinity 7000 you could drop on a car from 100ft.... the car would need work to run again but the netfinity would be fine... use long cords and keep it running during it :)

    2. Re:Selling? Me too! by scotch · · Score: 2, Funny

      You said "boxen". I hereby lower my previous bid to $2.75.

      --
      XML causes global warming.
  71. 64-bit by noda132 · · Score: 3, Insightful

    I was excited to look at these benchmarks because I know that Linux does 64 bits and I really, really want to see what kind of difference there is before buying an Athlon64. But there is no 64-bit testing. What is the point of running on Linux if you don't take advantage of what Linux offers?

  72. Re:WHAT MONEY?!? by fzammett · · Score: 1

    Thank you! Someone with a damned sense of humor around here!!

    (Pretty good replies too by the way!)

    --
    If a pion (n-) collides with a proton in the woods & noone is there to hear it, does lamdba decay into the source pa
  73. The binaries work pretty good on Athlons, too. by emil · · Score: 1

    AMD seems to want to outsource compiler development. I've read recently on the Inquirer that Intel compilers produce very fast code on AMD. Some third parties are also releasing optimized AMD64 compilers, also.

  74. More than just price/performance... by Anonymous Coward · · Score: 0

    How about the fact that Intel has been bundling features in their CPUs that may have detrimental effects to users?

    Examples:
    1) The Pentium 3 GUID. Turned out there's a switch to turn it off, but the average user didn't know this, and IIRC, the switch was not originally made available through end user software.
    2) Integration of Wi-Fi in Centrino. Even in the absence of security/privacy issues, what effect does this have on the integrity of the CPU? I'm a fan of "add on what I want" vs. "everything jumbled together".
    3) Intel collaboration on the Palladium/TCPA effort.

  75. OT: your sig. by MrHanky · · Score: 2, Funny
    Support my campaign to add "Improbable" to the mod options in memoriam Douglas N Adams

    I support that. But should it be positive, negative, random or neutral?
    1. Re:OT: your sig. by schon · · Score: 1

      should it be positive, negative, random or neutral?

      Of course. :o)

  76. There should be no improvement to FP scores... by emil · · Score: 1

    The extra registers are all integer registers; the SIMD instructions and register count do not change between 32 and 64 bit modes.

    If the tests are truly FP-centric, this shouldn't make any difference.

    1. Re:There should be no improvement to FP scores... by Erich · · Score: 1
      The extra registers are all integer registers; the SIMD instructions and register count do not change between 32 and 64 bit modes.
      Actually, the SSE register file is doubled, also. The SSE/SSE2 register file is 16 128-bit registers in 64-bit mode.

      According to here at least.

      The x87 stack is unchanged, but you shouldn't be using that, anyway. The SSE/SSE2 instruction set is better. Yay, flat register file.

      --

      -- Erich

      Slashdot reader since 1997

  77. Re:WHAT MONEY?!? by ocooch · · Score: 1

    Right Wing?

  78. Kernel Compile times by Metuchen · · Score: 1

    You mean to tell me these things can compile the kernel in two minutes or less!?!? I guess it's time to upgrade!

    --
    # They who can give up essential liberty to obtain a little temporary safety, deserve neither liberty nor safety. --Fran
    1. Re:Kernel Compile times by npy · · Score: 1

      Not in 2 mins for me but 3 minutes for the 2.6.0 and it's modules :)

  79. Customer loyality by DigiShaman · · Score: 1

    It's all about customer loyality. And that often comes through satisfaction and trouble free hardware operation.

    I'm not saying AMD is any less better. But regardless of the industry "facts", if your comfortable with using a products...why change? For example, if you own a Honda Civic and the dealership treats you well then your next car might be another Honda.

    --
    Life is not for the lazy.
  80. Follow along here... by Anonymous Coward · · Score: 0

    Having Windows run on the PPC platform won't affect IBM's decision whether to support x86 or not _because_ Windows used to run on PPC and IBM still supported x86.

  81. CPU fans do fail by DigiShaman · · Score: 1

    CPU fans do fail. And if you have an AMD chip, chances are it's toast when the fan goes out. At least Intel P4s will throttle back to prevent overheadting. Not only that, but the PC will still RUN!!! Obviously not fast, but at least it won't crash instantly.

    By the way, I benchmarked a PC with 3DMark03 once when I forgot to connect the CPU fan. I didn't notice until after I went to put the cover back on. Thinking *OH SHIT* at the time, I went to grab the heatsink just to see how hot it got. Well thanks to my boner job, I burned my fingers and was given blisters. God damn, impressive that it still ran after that.

    --
    Life is not for the lazy.
  82. Re:WHAT MONEY?!? by Anonymous Coward · · Score: 0

    Troll.

    ...same difference.

  83. It's the same for AMD processors by nniillss · · Score: 1
    First of all, Intel compilers also optimize for AMD platforms. For my code (which over the time was ported to about 10 architectures including Cray Unicos, IBM AIX, Digital Unix, Fujitsu VPP, HP UX), Intel Fortran compilers improved the performance on AMD processors over gcc by up to 80%. With ifc 5.0 I had to choose the correct options manually (instruction set, cache size etc), with ifc 7.1 the default options were good enough. The same executable runs at nearly optimal speed on Pentium 4, Athlon MP 1.2 GHz and 2200+ and Opteron 244.

    Secondly, there are optimized precompiled libraries available for both Intel and AMD processors (AMD ACML, ATLAS, libgoto).

    Finally, dedicated compilers are available for AMD64 from Portland Group, NAG, Absoft, and Pathscale.

    What again was your point?

  84. SCO by NoxiousB · · Score: 1

    Better not let the SCO find out this is happening..........

  85. Re:to all you linux communist... FUCK OFF AND DIE by Anonymous Coward · · Score: 0

    i've been fucking off all day, but i'm still not dead. YOU FAIL IT!

  86. Here's MY advantage by MarcQuadra · · Score: 1

    I have a home server and workstation with high-clock chips in them, but I severly underclock the server (chip is 800Mhz, I run it at 300Mhz), and moderately underclock the workstation (1.8G - 1.4G). The energy savings are quite significant, as are the reduction in wear-and-tear caused by cooling. Less heat means less fans and airflow, less fans are cheaper to maintain, and less airflow means alot less case-cleaning.

    I also replaced my original-generation RADEON with a comparable modern RADEON chip (7500), basically the same chip, but manufactured on a newer process, so my video card needs no fan now. And my motherboard carries a KT600 chipset, but I run it at 266FSB instead of 400FSB and removed the chipset fan, it's cool to the touch.

    --
    "Sometimes, I think Trent just needs a cup of hot chocolate and a blankie." -Tori Amos on Nine Inch Nails
  87. Stupid conclusions. by Anonymous Coward · · Score: 0

    Finally, we're going to declare the Athlon 64 the best bang for the buck.

    Why? Performance was nearly identical to the vanilla Pentium 4 processors - within 10% in most cases - and it even *lost* in some of the benchmarks.

    The AMD is $400 - base Pentium 4 is $275. That's an extra ~10% performance (and sometimes less performance) for an additional $125. This is, by nobody's sane definition of the terms - "bang for the buck".

  88. Irony by pantherace · · Score: 1
    I suspect that the Athlon 64 "A64" is a much better 32-bit chip than an AXP (more commonly called an Alpha)

    Too bad Compaq & HP killed off the Alpha (the 364 is still a 264 (and was untill last year still kicking ass.) and scales better than almost anything) the 464 was to be the first new core, and was up to a 5X performance increase because of the 1st major addition to the alpha arch (Brief overview) It has been speculated that the reason HP doesn't release Alpha 364 scores, it that it doesn't want to embarass intel (& cause more ummm... stuff to fall on the pro IA-64 group of which HP is the only major OEM), which may or may not be true.

    Ode to Alpha

  89. I'd like to see more Linux based hardware reviews. by msimm · · Score: 1

    Knowing what we all do about the importance of driver software and kernel io/performance. How many of you have made 'educated' decisions about video card purchases based on performance reviews conducted on Windows based PC's? I mean drivers have a HUGE impact on how hardware performs and Linux drivers and Windows drivers aren't exactly the same (sometimes for better and sometime worse). We speculate a lot about better/more stable performance but haven't really got a good resource for basic reviews.

    Maybe I'm just idly wishing here, but as Linux gets closer and closer to the desktop these are the types of things we'll need to look at. My system feels a lot faster (games, mp3 encoding) then my work computer (Win98), but who really knows.

    --
    Quack, quack.
  90. Um...duh by msimm · · Score: 1

    Bragging rights.

    Cough.
    I mean database.

    --
    Quack, quack.
  91. Cyrix by dpilot · · Score: 1

    Actually, they are in a niche of the business. Cyrix IP was bought by Via, who has brought out a low power series of CPUs. They don't play in the sheer horsepower arena, but especially considering the way Intel positions Centrino, (perhaps protecting P4?) Via has the fanless market pretty much to itself.

    --
    The living have better things to do than to continue hating the dead.
  92. Why use VIA chipsets anymore? by Hoser+McMoose · · Score: 1

    I think the one thing to take from this is that VIA chipsets are just more trouble then they are worth. It doesn't much matter if it's a VIA chipset for an AMD processor or a VIA chipset for an Intel processor, they're all just trouble. Same goes for ALi chipsets.

    If you're going to use an Intel processor, get a board using a chipset from Intel or Serverworks/Broadcom. If you're going to use an AMD processor, get a board using a chipset from nVidia or AMD.

    SiS chipsets might be an option for either platform, but they're almost exclusively used on el-cheapo boards, most of which are very poorly built and cause their own sets of problems.

  93. worse, the lottery's transistor crashes by Anonymous Coward · · Score: 0
    THIRTY ONE STAGES, they are (2^5)-1 stages :P

    Many hundreds of millions of transistors are very bad for the health because the lottery's transistor can crash the CPU. open4free

  94. ifc on debian by Anonymous Coward · · Score: 0

    Hey anyone have luck getting the Intel Fortran compiler 8 working with Debian?

    I hear you need a 2.6 kernel with the libc6-i686 package but haven't managed it yet.. but I'd rather leave my calulations to something more stable.

    no joy so far getting ifc 7 going on a 2.4 kernel either.. (deb/testing)

    and I'll be damned if I'm going to install an end of life'd Redhat 9 ..

    cheers