Please create an account to participate in the Slashdot moderation system

 


Forgot your password?
Close
typodupeerror
×
News

AMD Introduces the Athlon XP 2200+ 304

Posted by chrisd from the that's-nacho-chip-it's-mine dept.
NevDull writes "AMD introduces the Thoroughbred core in the Athlon XP 2200+. Tom's Hardware Guide has a review of the new CPU based on the 0.13 micron core, and subsequently declares the current CPU war to have been won by Intel." Update: 06/10 12:48 GMT by T : DavoHH writes "To add to the list of reviews and benchmarks around the net for the new Athlon XP 2200+, HotHardware.com has one and also and also Anand's and AMDMB." Update: 06/10 13:45 GMT by T : One more: Johan contributes a link to an Ace's Hardware review which tries to answer the question "Does the 0.13 Athlon XP run well an on older motherboard, and does it provide good value as an upgrade?"
This discussion has been archived. No new comments can be posted.

AMD Introduces the Athlon XP 2200+ More

AMD Introduces the Athlon XP 2200+

Comments Filter:

  • They're flooding in (Score:5, Informative)

    by thegrommit ( 13025 ) on Monday June 10, 2002 @08:33AM (#3672126)
    Another report can be found at tech-report [tech-report.com].

    Personally, I'll just wait for the price cuts to take effect, then buy an XP.
    • Personally, I'll just wait for the price cuts to take effect, then buy an XP.

      I'm holding out for Hammer. My home system is a 1.0-GHz T-Bird...it still gets the job done. I figure that by the time Hammer is widely available, I'll have two years on my current system, which is reasonable. I have faster systems to play with at work in the meantime (like the dual 1.6-GHz Athlon MP goodness I'm typing on right now :-) ).

  • Yeah..but ? (Score:4, Funny)

    by cOdEgUru ( 181536 ) on Monday June 10, 2002 @08:35AM (#3672131) Homepage Journal
    This is a winning war for both Intel and AMD. The only ones who lose are us, standing in line forking over 180 bucks for the XP 2000+ and still ready to roll out whatsoever needed to get the new Thoroughbred because it can squeeze out couple of more 3DMark points.

    I would have posted more, but I need to run to the local computer shop to check whether they have arrived yet. :)

    • Funny but True (Score:2, Interesting)

      by green pizza ( 159161 )
      We often laugh about the upgrade craze, but I think we all feel the upgrade urge, especially when running games at high resolutions and also simply using several of the latest and greatest desktop apps and diversions. The slowest machine still in use in our home is my wife's ancient 1 GHz PIII overclocked to 1.33 GHz. A hellofa machine in it's day, but even with 512 MB of PC133, Internet Explorer will chug pretty hard when loading a page using one or more newer plugins. A fresh reinstall of XP and installation of the latest revs of her apps and plugins speeds things up a good deal, but still nowhere near as fast as our faster machines... and it just goes downhill from there with the 5 month cycle of "Windows Rot".

      And me... well, as I keep upgrading, I get spoiled and used to things happening faster and faster with each new machine. I'm sure someday I'll look back and laugh about the days when a kernel compile took more than a few seconds!
    • ready to roll out whatsoever needed to get the new Thoroughbred because it can squeeze out couple of more 3DMark points.

      Clearly, the Thoroughbred would be a more compelling upgrade with a bigger L2 cache and a faster FSB, but the die shrink is worth something: it's down about 10 W.

      Still, for a quiet system, I'd consider the 1 GHz C3 [tomshardware.com], which runs at a miserly 12 W.

    • Re:Yeah..but ? (Score:3, Insightful)

      by Com2Kid ( 142006 )
      This is a winning war for both Intel and AMD. The only ones who lose are us, standing in line forking over 180 bucks for the XP 2000+

      Depending on who you ask, from a few thousand to a few million years of technological development;

      for $180.

      Doesn't sound like a bad deal at all. : )

  • More reviews (Score:3, Informative)

    by Anonymous Coward on Monday June 10, 2002 @08:37AM (#3672144)



    review at Ace's hardware [aceshardware.com]


    Much info about upgrading older boards to the new AMD.

    At least here the reviewer make sure that both CPU work with the same memory.

    Tom's gives the P4 PC1066, while 95% of the P4 systems are sold with DDR.



    Review at Anandtech [anandtech.com]

    • Re:More reviews (Score:2, Insightful)

      by Anonymous Coward
      At least here the reviewer make sure that both CPU work with the same memory.
      Tom's gives the P4 PC1066, while 95% of the P4 systems are sold with DDR.

      I already see this in an automobile mag:
      In order to get a fair comparison, the Ferrari was equipped with a 1600cc VW engine.

      BTW, I think that 95% is more than a bit pessimistic. Somewhere between 50 and 75% maybe...

      • Wouldn't the thought then still stand that a majority of users are using DDR? Therefore wouldn't the comparison be slightly biased if the reviewer knows that the majority of people are using DDR and yet chooses otherwise for the competing test box?
    • Talking about cpu reviews, does anyone know if there is some hardware site that does reviews on Linux? While I don't usually bother to follow these hardware sites that closely anymore I think it would be interesting to see how these cpu:s compare under Linux. Say some benchmark like the linpack benchmark using generic compiler options usually found in binary packages and also effects of cpu-specific optimizations gcc can achieve. I read some time ago that gcc could optimize better for intel cpu:s than for athlons, is that still true? At least for me that would be more interesting to know than whatever >200 fps they can achieve in quake 3.
    • Tom's gives the P4 PC1066, while 95% of the P4 systems are sold with DDR.

      When you consider how Tom's was ripping Rambus (and rightly so) a year or so ago, this makes the choice to use RDRAM now somewhat suspect.

  • Won by Intel? (Score:2, Interesting)

    by Oculus Habent ( 562837 )

    Intel may have the higher MHz, and they may be leaving x86 behind soon, but I think that the Hammer series will really hurt Intel if they can't pull people away from x86.

    AMD seems to be betting on the difficulty that leaving x86 would cause for many companies, and I can't blame them.

    If we all go with Intel's new architecture, we'll soon be needing emulators to run programs from all the under-funded software companies.

    And if we lose x86, they'll have to just start calling it XFree. ;)

    • Re:Won by Intel? (Score:3, Insightful)

      by Zocalo ( 252965 )
      I don't know about that "Won by Intel" either, this battle maybe, but not the war as yet. The x86 market is at an interesting junction; Intel is backing the "migrate to 64 bit" horse while AMD is very much on the "make 32 bit faster" horse. We've been here before, when we all went from 16bit to 32bit CPUs, and sooner or later Intel's horse is going to win - it just depends on when Microsoft ships a 64 bit "desktop" version of Windows the consumers actually buy.

      In the mean time AMD and Intel are really talking about two completely different markets for their wares. Intel want to make a serious pile of money out of selling new (and hence overpriced) Itaniums for use in multi-way servers for bespoke applications where compatability is not such an issue. AMD on the otherhand looks to be targetting the consumer who wants to squeeze every last frame out of their Quake sessions and other (less important) "legacy" 32 bit code. Both companies will probably make a big pile of cash out of their respective sectors, so no problems there.

      In the long term though, unless AMD is going to make a seriously brave (or rash) departure from Intel compatability, ultimately they are always going to be playing catchup with Intel for compatability. There's a long history of that too, and in that context, I'm just amazed that AMD has lasted as long as they have when other ventures have long since come and gone - best of luck with giving us all a choice I say!

      • Re:Won by Intel? (Score:2, Interesting)

        by davros74 ( 194914 )
        AMD has to make a seriously brave (or rash) departure from Intel compatibility?

        Are you serious? The Hammer chips are AMD's decision on how to extend and improve the x86 platform. They cleaned up the instruction set, extended the number of registers, and made the registers truly general purpose. The x86-64 instruction set may be so popular that Intel has already licensed the x86-64 set from AMD. Ever heard of Yamhill?

        The way I see it is that many more companies are going to prefer the logical x86-64 route, rather than the very expensive IA64 route. There is just too much proprietary and legacy code out there to be able to just walk away from x86 altogether. Especially if AMD delivers on both speed and price as well (which they probably will).
        • "Are you serious?"

          What, about the way you completely changed the context of what I originally said, or that AMD has to abandon Intel compatability? ;)

          Assuming the latter, of course not; unless they have an absolutely bullet proof customer base and guaranteed application support it would clearly be commercial suicide. The point was, that until this unlikely day arrives, AMD will forever be having to add their take on what ever additions to the x86 Intel has success with, like a future revision of SSE perhaps.

      • We've been here before, when we all went from 16bit to 32bit CPUs, and sooner or later Intel's horse is going to win - it just depends on when Microsoft ships a 64 bit "desktop" version of Windows the consumers actually buy.

        IIRC, Microsoft has already committed [amd.com] to x86-64. Intel has also been said to have a skunkworks project [theregister.co.uk] to develop an x86-compatible 64-bit processor, though whether this would be compatible with Hammer is unknown.

    • Not quite yet (Score:3, Interesting)

      by RayChuang ( 10181 )
      If people think Intel has won the CPU war, they've kind of deluding themselves.

      Remember, the AthlonXP 2200+ is essentially a shrunk-down CPU core based on the current Palimino core design. That means it still has the same 256 KB of L2 cache. What happens when AMD's new Barton CPU core with the 512 KB L2 cache arrives later this year? I think AMD CPU performance will take a major jump once that happens, and will become competitive with the Intel Northwood-core Pentium 4's with their 512 KB L2 cache.

      Is it small wonder why Intel is spending large amounts of money to develop the Prescott core Pentium 4 on the 0.09-micron process and 1024 KB L2 cache? At 1024 KB L2 cache, that's reaching Xeon-class server CPU territory.

    • Re:Won by Intel? (Score:2, Insightful)

      by jtshaw ( 398319 )
      Not to take sides, because honestly, I really don't care... But Intel is hardly leaving the x86 behind.

      Intel's IA64 strategy is banking on a few things.

      One, that x86 doesn't have much need for 64bit support. They don't think much of our software would be benifited from a 64bit CPU right now, so they aren't going to give consumers a 64bit CPU to use yet. In general I agree with this, for now, it isn't like Microsoft Word would benifit all that much from being 64bit.

      Two, the people that do need the 64bit CPU will be in the price range of the current Itanium based computers. These people are those that do scientific calculations, intense server stuff... not Quake players.

      Three, they will have the IA64 technology optimized and proven in the future for when it is time to completely drop x86 from the planet, and the software houses will have a head start developing for it.

      Basically I think they are using todays Itaniums to get a head start on what they want to have 5 of 10 years up the road for main stream computers.

      Now this isn't to say I particularly like the IA64 architecture... but that is what Intel is doing.

      I guess what I am really trying to say is, don't count out the x86 CPU from Intel, they aren't through with them yet. I beleive they were aiming at 5~10Ghz with Pentium 4 like x86 designs... which is obviously way ahead of where they are now.

      I guess the real test will come when we see how much x86-64 software comes out. And what kind of performance increase comes with it over 32bit versions. Intel could easily have not extended there x86 to 64 bits just to try and bully the software industry into not shipping much 64bit x86 software thus negating any advantage AMD x86-64 might have over Intel x86-32.
    • Itanium, Intel's 64bit chip will not require an emulator to run 32bit code. It will just run at a performance hit. This is exactly what happened when NT4 came out and people complained about 16bit apps running slower on it.

      But rewriting all those apps for 64 bit will not happen overnight. That's why when I look at the options:

      A: Buying intel's 64bit chip and suffering until my apps are ported over to 64bit.

      -or

      B: Buying AMD's 64bit chip and running all my existing apps at roughly double(*) the performance
      (and when 64bit apps come out, they will SCREAM.)

      I tend to like AMD's plan. I think Intel is in serious trouble unless they either hurt their sales significantly before they can release the Hammer, or if AMD has major problems.

      *(current 800Mhz preview seemed to provide around 2x performance, final is expected to be 1.2Ghz).

  • What I'M waiting for is the Athlon XP 2800+, which will probably be the first AMD chip to run at 2200 MHz.

    • Re:Idiotic numbering scheme (Score:5, Insightful)

      by Tim C ( 15259 ) on Monday June 10, 2002 @08:54AM (#3672211)
      I'll bite.

      The numbering scheme currently used by AMD for their Athlon chips reflects the speed of the equivalently-performing Intel chip. ie the Athlon XP 2200+ performs at the same level as the P4 2.2GHz, despite running at a lower frequency.

      If AMD just quoted the raw GHz figures, everyone would assume that they are significantly slower than they actually are. They would also lose out on price comparisons - on dabs.com, the Athlon 1900+ is only about £8 cheaper than the P4 1.5GHz. The P4 1.9GHz, however, is almost £60 cheaper, a much larger difference (just over a third of the total price of the P4, in fact).

      (Note that I am in no way affiliated with dabs.com - they're just the first website I think of when looking at PC component prices.)

      Cheers,

      Tim
      • You're wrong about that. AMD made it quite clear when they introduced the PR figure that it related to the performance/Mhz of their previous generation Athlon (the Thunderbird) rather than any Intel CPU. Therefore an Athlon XP 2200 should perform equivalently to an Athlon T'Bird @ 2200Mhz - which would not have been possible seeing as the T'Bird 1400 cranked out even more heat than an XP 2100 (1733Mhz). It's still a dumb system, but at least it has a consistent INTERNAL logic.
      • There's one thing you will need to remember...
        Somebody called "Cyrix" used a comparative numbering scheme.
        I'd have more info, but it was so long ago.

  • I declare the current CPU war meaningless. (Score:5, Insightful)

    by Anonymous Coward on Monday June 10, 2002 @08:40AM (#3672154)
    My 1.1ghz processor is plenty fast enough for me, and will remain so for quite some time.

    In terms of tech nuts, AMD has a strong, strong following and lots of brand loyalty - as much, if not more, than Intel.

    In terms of people who shop at Staples/Best Buy/etc... They buy what's in the box and tend not to care what's inside. Last time I was at either of those stores, there were more AMD-based boxes on the shelves than ever before.

    If we're talking technology alone, it depends what facet you're looking at. Intel processors do better in some areas, AMD in others. With AMD, you always get more bang for your buck, so to speak, as well.

      • My 1.1ghz processor is plenty fast enough for me, and will remain so for quite some time.

      Good for you....but my experience is somewhat different. I have a 1.5Ghz p4, and I wish I had a faster one because processing large quantities of video is a lot of burden on the CPU.

      Even transfering video using IEEE1394 to the computer is such a delicate exercise, that I tend to avoid doing more than 30 minutes at a time. Of course I carefully close down all my programs before doing so, and even then it is a very unstable process. Last night I tried twice, and got dropped frames both times after 30 minutes or so.

      Premiere runs like a dog, too, unless you have a dual 2.0+ Ghz and 512 Mb of RAM.

      AMD's and Intel's fierce competition is driving the CPU market forward, so that consumers enjoy faster, better and cheaper CPU's all the time. To me, it is essential that they keep on going.

      • At some point though, the speed wars will be less relevant for us, the home market. THe relevance is shrinking. As soon as we can do everything and anything well on a CPU that works at given speeds, we will be at nirvana. Prices will drop and the higher speed processors, the ones that go beyond our needs, will only be meant for specialty use.

        Just like your need for a 1.5+ Ghz cpu is almost a specialty: video editing. There is a small community doing it, but not everyone is. :)

        -s
    • With AMD, you always get more bang for your buck, so to speak, as well.

      Not always. My experience is that AMD tends to run their processors a little closer to maximum spec than Intel. Therefore, you can often pick up a cheap Intel CPU and OC the hell out of it. While AMD procs are pretty much maxed out when they leave the factory. Of course, YMMV.
    • 1.1?!? HA! Lets see you just try and keep up with my 1.2 ghz processor!!

  • Moderation. (Score:3, Funny)

    by saintlupus ( 227599 ) on Monday June 10, 2002 @08:40AM (#3672155)
    declares the current CPU war to have been won by Intel.

    (-1, Ad-impression Seeking Flamebait)

    --saint
  • From Tom's Hardware
    Simultaneous to the launch of the new Athlon with the T-bred core, AMD has given the following guideline to the motherboard makers: starting June 10, all motherboards must have integrated thermal protection in order to receive certification from AMD. The costs per board for this thermal protection logic runs at approximately less than $1.

    Even though it's just $1 per board, that can really add up. I wonder how companies feel about being more or less pushed into this...

  • It's nice... (Score:3, Interesting)

    by eyegor ( 148503 ) on Monday June 10, 2002 @08:42AM (#3672161)
    to see that Intel has viable competition.

    In spite of AMD "losing" the so-called CPU wars, they're still a winner in my eyes.

    Geek life would be much different if we had only one viable CPU vendor (shades of Micro$oft, Batman!!!).

    I've been using AMD chips in my x86 boxes since early days of the K6-2 and I've been very satisfied. The only reason that CPU prices are anywhere CLOSE to reasonable is that Intel has real competition.

  • We are the winners (Score:3, Insightful)

    by delphi125 ( 544730 ) on Monday June 10, 2002 @08:45AM (#3672178)
    I managed to read this article at Toms just before it got posted here, and although the conclusion does state that the Athlon hasn't caught up with the P4 - and doesn't look like doing so either, I'm not sure if that should be considered a 'win' for Intel.

    You see, in the middle of the article there is a list of comparative prices ($ per chip when buying 1000). The prices for a xx00 P4 are almost exactly the same as for a xx00+ Athlon, except for the highest end chips ($600 for the P4 2500).

    So it seems as if Intel is finally challenged enough by AMD that they actually have to have the same prices for the same 'PR' in the mid-range. In my view that is a win for the consumer.

  • Anandtech has another review... (Score:4, Informative)

    by Jugalator ( 259273 ) on Monday June 10, 2002 @08:48AM (#3672186) Journal
    http://www.anandtech.com/cpu/showdoc.html?i=1635

    Their conclusion in short:

    Thoroughbred is more of an evolution to the Palomino core than a revolution. In other words, nothing new except minor speed increases to the end user. No special architecture changes, except decreased transistor amounts to allow higher clock frequencies and perhaps a bit lower prices as well.

    After attempting to overclock their Thoroughbred @ 1.8 GHz, they observed there was almost no overclocking potential at all, leading to some doubts to whether AMD will keep up with Intel that well until their Hammer processors is ready.

    So the Thoroughbred core seem to extend the Athlon XP lifetime with perhaps a few more 66 MHz jumps from the current 1.8 GHz, but will probably never get more than a 10-20% performance increase above the Athlon XP "Palomino" 2100+. From Anandtech's analysis, I'd think the best Thoroughbreds will end around a "2600+" performance rating.

  • Real MHZ (Score:2, Interesting)

    by Calomnious Awkward ( 459373 )
    Compackqard advertises with: " Compaq Pressario 6095EA met Intel ® Pentium ® 4 processor 2.2 GHz. Echte GHz voor echte snelheid "
    In english: " Compaq Pressario 6095EA with Intel ® Pentium ® 4 processor 2.2 GHz. Real GHz for real performance "
    See the Flashy pop up yourself [compaq.be]

    Guess they don't know about Tom's ?

    • Re:Real MHZ (Score:2, Insightful)

      by sheean.nl ( 565364 )
      should they be advertising with: "well, nobody of you will need that amount of GHz now, Pentium's sucks compared to AMD's... but what the heck, buy our stuff!).
  • From the article, in regards to the videos of the AMD procs overheating and catching fire without a heatsink:
    A few weeks later, at a meeting with a small number of select attendees, AMD presented a circuit logic, which immediately turns off the power supply when the die temperature overheats to about 85 degrees Celsius. To guarantee failsafe protection, the CPU temperature is monitored frequently, in very short time increments, by the thermal diode. This ensures that the power is switched off in a timely manner.
    Now, maybe this is just me, but is this really the right solution?? I personally don't think so. I mean, sure, it's much better than the processor catching on fire and melting onto your motherboard, but I still think the processor should instead slow down until it reaches a safe temperature. Hell, the Pentium IV does this, why don't the new AMD chips??

    If my heatsink fell off on a server, I would not want the system turning off, I would want it staying on. I mean, it won't do too much good being on in that state, but at least there is no data loss in that situation.

    Honestly, I think lack of core speed slowdown in the case of an overheat is the only thing keeping me from buying an AMD. I was really hoping their new chips would have that ability; I guess I'll have to keep waiting. If anyone knows if AMD is planning on implementing this, please let me know!

    • Re:Still wary of buying one though. (Score:5, Insightful)

      by Jucius Maximus ( 229128 ) on Monday June 10, 2002 @09:06AM (#3672259) Journal
      "Now, maybe this is just me, but is this really the right solution?? I personally don't think so. I mean, sure, it's much better than the processor catching on fire and melting onto your motherboard, but I still think the processor should instead slow down until it reaches a safe temperature. Hell, the Pentium IV does this, why don't the new AMD chips??"

      The 'throttling' solution has existed for some months now. In the BIOS (build 1007) of my Asus A7V133 motherboard I can select various actions for when the CPU temperature passes a (user-selectable) threshold: 1. Audio Alert on PC Speaker, 2. Do nothing, 3. Shut Down, 4. Throttle the CPU to a lower speed.

    • If my heatsink fell off on a server, I would not want the system turning off, I would want it staying on. I mean, it won't do too much good being on in that state, but at least there is no data loss in that situation.

      If a heatsink falls off the CPU, I would prefer my system to turn off the power as soon as possible. Know what a copper/aluminium piece can do to the many Amperes running in a mainboard? don't want to find out.

      And after all, those server cases (CPU temperature more than 85 degrees celsius, or CPU fan falling off) are extreme cases, which should never happen. If this happens, then something else want wrong. If you check larger servers, you'd find lots of fans, all being redundant, so even if 1 fan stops working, there's still plenty air being push-pulled through. If 2 fans stop, then the machine should do what it wants to do (slow down or turn off), as this is a very, very rare case.

    • "Now, maybe this is just me, but is this really the right solution?? I personally don't think so. I mean, sure, it's much better than the processor catching on fire and melting onto your motherboard, but I still think the processor should instead slow down until it reaches a safe temperature. Hell, the Pentium IV does this, why don't the new AMD chips??"

      Starting with the Athlon XP series, AMD's strategy to deal with extreme heat conditions is to simply have the information available but leave it up to the motherboard and ultimately the user to decide what action, if any, to take.

      The P4's thermal diode will automatically trigger some throttling if excess temperatures are generated. The Athlon XP's thermal diode will simply alert the motherboard as to what is going on so that some action will be taken. Ultimately, the Athlon XP can still have the same kind of protections as the P4 but the processing power and logic necessary is offloaded to the motherboard.

      Perhaps this is actually a cost-cutting measure and it is part of the reason why AMD chips on the whole seem to cost less than intel. Either way, if you want to build a good desktop around one of these chips, you will pay for good thermal protection in the CPU if you get intel or in the motherboard if you buy AMD.

  • I've not been following the speeds of chips for a while now, but I'm sure someone can tell me.

    Whats the fastest offering by Intel and AMD that is:

    1. Easily available
    2. Happily copes with *most* processor intensive applications
    3. Doesn't cost the earth
    Yes I know a lot of this is subjective, but I have a P2-400 at the moment and I'm thinking of boosting the speed a tad, but don't really know what my *realistic* options are. A processor running at 700 gigahertz is going to be nice but probably out of my range price-wise and more than likely won't be used to it's fullest.
    • AMD Duron 1.1GHz, $45
      AMD Duron 1.2GHz, $53
      AMD Duron 1.3GHz, $66
      AMD Athlon XP1700+, $99
      AMD Athlon XP1800+, $110
      AMD Athlon XP1900+, $137
      AMD Athlon XP2000+, $167
      AMD Athlon XP2200+ $241

      Next week Intel is expected to release a 1.8GHz Pentium 4 "Celeron" at around $103.

  • My current system that I run at home is between a 450 and a 233. Though this does not include the two system that I have both running dual 533. Considering where I was before, upgrading from an overdriven 486/pentium 83mhz to the current 450, that is a 542 percent increase in the clock rate. Ironically though, I aleady had 128MB in my old 83mhz and even my 450 only has 128mb... quite sad.

    The only justification that I will see in getting a new computer anytime soon is when I see some 3GHZ machines. (That is again about a 550 percent increase in clock rate).

    At the rate new chip designs are coming out, I think I will have more chips to choose from than underwear. I can keep waiting. :-)

  • AMD L1 cache is huge (Score:5, Interesting)

    by mrm677 ( 456727 ) on Monday June 10, 2002 @08:55AM (#3672216)
    Smaller memories are always faster (when comparing similar technologies). Registers, being the smallest memory, are the fastest. Followed by the L1, then L2, then main memory, and then disk.

    AMD's huge L1 cache probably contributes to the difficulty in ramping up the clock rate. An L1 cache must be able to respond to a data access within usually 1-2 clock cycles. Many computer architectects believe that the size of the L1 cache should be less than 10% the size of the on-chip L2 cache. AMD's chips have L1 caches on the order of 25% the size of the L2. Such a large L1 probably cannot keep up with increasing clock frequencies.

    Intel chips have very small L1 caches as compared with AMD. T
    • Intel chips have very small L1 caches as compared with AMD.

      Which is a tremendous problem, from a performance standpoint. Having hand-coded assembly for both processors (Intel and AMD), I know that seldom do these processors live up to their claims of being able to execute 2 instructions per clock cycle. Actual benchmarks that I've done indicate an instruction throughput of about 1 instruction every 2 clock cycles; coincidentally, the L2 cache runs at 1/2 processor clock speed. Which means, of course, that the processor is operating mostly out of the L2 cache because the majority of instructions are resulting in L1 cache misses. Thus, any increase in L1 cache size will have a large impact on actual system performance.Intel correctly recognizes that most PC buyers make decisions based on processor speed rather than actual system throughput, and this is why they can use smaller L1 caches - because the typical user will never notice the difference in actual performance. Fortunately, the result is that AMD has had to make up for the MHz gap with processors that perform better in actual computing situations, and a large L1 cache can work wonders for system throughput.

      • A large L1 cache certainly benefits the performance of AMD chips as long as it can keep up with the clock rate. My only point is that it also is likely a cause to why they can't ramp up their clock rate beyond 2.5 GHz

        Also look at the numbers of the Alpha, MIPS, IBM Power, and Sun Sparc processors. None of these chips has an L1 cache that is 25% of the total on-chip cache.

        Numbers speak for themselves. Intel leads the performance race.

        • In all but a handfull of synthetic benchmarks and a few "media" apps where SSE2 is used the top speed Athlons keep pace with the P4 when using similar memory technologies. Since the top of the line Athlon is less than 1/2 the cost of the top speed P4 I would say that for most of us AMD leads the performance race.(eg what is the most performance I can afford for X ammount of $).
          • You are referring to the Price/Performance ratio, which AMD probably does lead. You see, Price and Performance really are different things. And I mispoke: Intel leads the Performance race for microprocessors. For shared-memory computers, Cray probably leads the performance race. For other massively parallel computers, one of the ASCI supercomputers probably leads the race.
      • First off, it doesn't take much to achieve a 95% cache hit rate. Second, in order for the majority of instruction accesses to miss L2, you would have to have a very very small cache. I'm talking like 1KB small.

        What most non-programmers (and even some "hand-coders" like yourself) don't realize is that most software runs in loops. All you have to do is make your L1 cache big enough to hold a typical inner loop (less than 100 instructions) and you have yourself a 60-80% hit rate. Increase the size of the cache more, and you can enclose the typical outer loop and maybe a few often-called libraries, event handlers, or system calls. From then on, you run into severely diminishing returns. Increasing your cache beyond a hit rate of 95% to 100% (theoretically impossible of course) to compensate for a mere 2-cycle access L2 only buys you an additional ~5% of performance.

        Doesn't sound like much of a "tremendous problem" anymore, does it?

        From Intel's point of view, approximately 0% of the buyers out there care about the cache size. I'm sure Intel performs due diligence when modeling and selecting an appropriate cache size. When the diminishing returns set in, they know when to draw the line. I don't know about you, but I would prefer Intel spend an appropriate amount of resources on L1 cache and an appropriate amount on L2 cache, then spend the rest of their resources increasing the clock speed and validating the chip to make sure what I buy is bug-free. Surely Intel can better spend those resources on removing speed paths and reducing their cycle time. This has the potential to increase the performance well over the 5% needed to compensate for the additional L1 cache misses.

  • Yeah but.. (Score:3, Informative)

    by MagPulse ( 316 ) on Monday June 10, 2002 @09:06AM (#3672256)
    Intel P4 2.53Ghz: $535
    AMD Athlon XP 2200+: ~$250

    Intel price is from Pricewatch, AMD is a guess based on two sightings here [cbwnet.com] and here [myinfinity.com], and past release prices.

    • Re:Yeah but.. (Score:3, Informative)

      by hawkstone ( 233083 )
      That's nice. Compare the price of an AMD processor designed to compete with a 2.2 GHz (thus the name 2200+) with the price of a 2.53 GHz P4?

      How about:
      Intel P4B (533 FSB) 2.26 GHz: $262
      Intel P4 2.2 Ghz: $230
      AMD Athlon XP (your est) 2200+ : ~$250

      Price difference not quite so obvious now, is it?
    • That's exactly what makes declaring Intel the winner so stupid. Sure, they've got the better performing processor, but you'll pay for it if you want that slight advantage. AMD, IMHO, has won the value battle, and that's what matters. Its like declaring Ferrari the horsepower winner over Honda. Well duh, but how many Ferrari's do you see on the road vs. Hondas?

  • Intel is winning battles, but not yet the war (Score:5, Insightful)

    by EvilAlien ( 133134 ) on Monday June 10, 2002 @09:17AM (#3672302) Journal
    This is like announcing yet another minor version release in the Linux kernel.

    Both AMD and Intel regularly release new silicon rated at higher clock cycles. This isn't really that big of a deal. Tom's Hardware likes to make a statement rather than pull their punches, so it doesn't surprise me to see something meaningless like "Intel has won the CPU war". Many gamers now swear by AMD, and the damage to Intel's reputation will need to be repaired over time. Intel's deaper pockets may be churning out CPUs which are beating AMD's recent releases in Tom's comparisons [tomshardware.com], but the trust issue with consumers will lag behind the realities of comparitive performance, just as it used to in Intel's favor. AMD is winning the popular war even with their losses in specific battles.

    It may not matter if Intel can deal with heat more effectively [tomshardware.com] than AMD. The AMD CPUs are much cheaper and those with big concerns over heat will drop over $100 on a heatsink/fan.

    The CPU war isn't nearly over. Even if Intel continues to win these individual skirmishes, they will still have to demoralize AMD's faithful. Intel may have bigger "weapons", but AMD has something that Intel doesn't to the same extent: trust, loyalty, and support as an underdog.

  • when heat is important, this is a good chip (Score:3, Interesting)

    by dgym ( 584252 ) on Monday June 10, 2002 @09:18AM (#3672304)
    I spend more of my time trying to make my computers quiet than worrying about performance. To be able to upgrade from my 1GHz thunderbird to a 1700+ thoroughbred and see a 9% decrease in heat dissipation is good news.

    The only time I am soley conserned with performance is when upgrading my server, and for that I will be waiting for the hammers. A recent hammer review at THG showed an 800MHz hammer out-perform a 1600Mhz pentium 4, and that was just for 32 bit tasks.

    As soon as the hammer is available at a decent frequency (AMD might start with a ~1500 model) the race for performance will be on again, so for now I am not too surprised that AMD arn't doing that much to keep the XP on the bleeding edge (more cache will help, but it is hardly revolutionary).

    Right now VIA are winning more of my CPU money for their excellent C3, but that is purely a heat thing. Unfortunately they aren't suitable for my server or games box.

    Still, with all these companies comming to market with different viewpoints the choices have never been so good, I think these are interesting times for CPUs and as much as I like AMD, I am glad that neither they nor any other company is at the top for too long because complacency always puts a damper on things.
    • 5% less heat when changing the production process from 0,18 to 0,13 is IMHO a big disappointment.

      When AMD announced the new Mobile Athlons the new core seemed to be very promising. Core voltage down significantly, power consumption down significantly. Now the core voltage is just decreased by a mere 0,1 volt and power consumption down by less than 10%.

      Very frustrating! Especially when you know, that AMD ships 1,5 Volt-Athlons to NEC for Low-Noise-Office-PCs for Japan.

      AMD, LISTEN UP:

      Deliver those Low-Voltage-Athlons to all of us. If I could chose between an Athlon 1.8 Gig 1,75 Volt (60 watt) and an Athlon 1,7 Gig and 1,5 Volt (40 watt), I would definetly buy the the 1,5 Volt version. And I am sure, that I'm not the only one who would prefer a quiter PC for 5 % more performance.

      Bye egghat.
  • In my PC, I tend to upgrade at least one significant component every two or three months. What's interesting about the computer industry today is that often times, by the time I've done some research and talked with users of some new component, there's already a cheaper/better/faster replacement!

    Not that I'm complaing... it's just so different from the original Pentium days. Heck, that Pentium 60 lasted me for almost two years! My gosh how times have changed... my 1 GHz PIII was quite outdated just eight months after it was built... and ancient a few months after that. Today, overclocked, it's my wife's MSIE/Office box.

    What a crazy industry... I wonder where it's headed next?!
  • is that when I am ready to buy a 1.5ghz system, it will be dirt cheap. People are much better off putting the money into tons of memory, better monitor, bigger HD, printer, scanner, digital camera, web cam or any other media device. I'm still running 400 & 450mhz systems and they are fast enough thank you.

    Once CPU's passed 300mhz, I stopped looking at the number and more at the price. That's the only really important number to consumers now. Not counting hardcore gamers or people who need the fastest machines on earth. Now if only both of them would focus on lower heat, and quieter designs.

    Of course if I ever get back into gaming, I might change my story and lust for the fastest system. Then again, by that time, I won't need anything faster than a 2ghz anyways. Especially with the way the video card are improving these days, CPU ceases to be a major factor in gaming. I'm no expert, but I'm guessing improvements in bus and bandwidth will do more for realism in 3D than CPU clock speed.

  • AMD lost? (Score:3, Informative)

    by pdqlamb ( 10952 ) on Monday June 10, 2002 @09:54AM (#3672466)
    Gee, tell that to the simulation folks I work with! We've got a good half-dozen recent-vintage Linux servers also in use as desktops. At least once a week someone comes by to ask why my machine is running so slow. The answer is that I have a genuine Intel 2GHz processor. The "1.7+" and even "1.6+" AMD machines kick my Intel's butt. These AMDs have clock speeds at least 25% slower than my Intel's, but their throughput is 20-40% better. I never really believed in "clock equivalence" bullshit before, but I do now!
    • I have a genuine Intel 2GHz processor. The "1.7+" and even "1.6+" AMD machines kick my Intel's butt

      Tom's rhetoric is based on the impressive benchmarks of the Northwood (0.13u, 512 KB) Pentium 4 with a 533 MHz FSB and dual-channel Rambus 1066. I suspect that you have a Willamette (0.18u, 256 KB) Pentium 4 with a 400 MHz FSB and Rambus 800 or DDR.

      I agree that the rhetoric is exaggerated, but the Pentium 4's high-MHz design is starting to pay off. If AMD is to stay competitive, they'll have to look at a larger L2 cache and a faster FSB to match the DDR 166 and 200.

    • Re:AMD lost? (Score:3, Interesting)

      by UncleFluffy ( 164860 )

      It depends on what your simulation code is doing. (Surprise !)

      If you look at the SPEC CPU2000 [spec.org][1] scores for AMD vs. Intel you'll see that for, say, an XP2000 vs a 2G P4, the AMD is faster at integer work and the Intel is faster for floating point. Note though, that the Intel scores are with the Intel Reference Compiler, which will probably be generating SSE code. If you're running non-SSE code, then Intel stuff is considerably weaker for floating point work.

      The second thing to consider is how the pipeline length affects the execution of your code. The longer pipeline in the P4 means that, roughly speaking, the P4 is faster in a straight line, but Athlons corner better.

      For the simulation stuff I'm doing, which involves huge amounts of conditional integer and bit-twiddling operations and next-to-no floating point, I use a dual MP1800 box[2]. Getting the equivalent performance - for my code - would have cost a huge amount more with a P4-based solution and may not even be possible with the current P4 range.

      [1] If you're doing real computing rather than fragging folks, SPEC is probably a better place to get your information from than Tom's Hardware.

      [2] One SETI work unit every 80 minutes. Yummy.

      • You make a good point; a lot does depend on what your sim does. Interestingly enough, ours depend fairly heavily on floating-point calculations. Unlike some other sims I know of, there are a fair number of branches and conditionals. Looking at the code, I've always thought the floating-point had to be driving execution speed. But between the matrix and vector manipulations, I guess there's enough checks to slow it down.

        Of course, there's always the other possibility, that we lose lots of speed by not using the right compiler (tuned for things like SPECmarks).

      • The second thing to consider is how the pipeline length affects the execution of your code. The longer pipeline in the P4 means that, roughly speaking, the P4 is faster in a straight line, but Athlons corner better.

        That's one of the best examples for explaining pipeline (to non techies) I have ever heard.
  • This site is starting to look a bit sketchy in his reviews. On one of the benchmarks they note that P4 got beat so bad because there "may be compatibility problems with the P4", yet for every benchmark where the Athlon came in behind nearly every other P4 chip, they make no mention or comment to that effect, except something like "clearly the Athlon sucks for this program cause its outdated" etc...

    And who make Tom's the judge of the contest? Who gives a fuck who they "declare" the winner. I'll be the one to decide because in the end I decide with my Wallet. And my wallet likes AMD's chips cause they run nearly as fast with everything and cost 1/2 the price of Intel (at the highest speed). Duh... it's a no-brainer.

    <pun> Obey your wallet. Choose AMD =) </pun>

    • Toms is widely regarded, though not on Slashdot, as a tabloid. Read through some of their reviews with a critical eye and you'll see that they frequently make huge, blanket statements which seem to either have nothing to do with, or are least not be proven by their numbers. I find that Ace's Hardware, StorageReview.com, Ars Technica, and Anandtech (even though they use Windows servers) are far more objective and less full of BS.

Slashdot Top Deals

"The medium is the massage." -- Crazy Nigel

Close