Become a fan of Slashdot on Facebook

 


Forgot your password?
Close
typodupeerror
×
AMD

AMD Challenges P4 With 1.33Ghz 228

Posted by timothy from the yes-sir-it's-fast----it's-named-after-an-indian-legend! dept.
ravedaddy writes: "AMD is again upping the ante in the processor war with two new high-performance products: the Athlon 1.33GHz, designed to operate on the 133MHz DDR EV6 bus, and the Athlon 1.3GHz, which runs on the 100MHz DDR bus. There are a couple of reviews pitting the 1.33 Athlon versus the Pentium 4 1.3 and 1.5GHz at Sharky's and at Hardware Central." I'm still happy with last-year's Athlon -- does anyone harbor any lingering thoughts that AMD is a second-class citizen in the chipmaking world?
This discussion has been archived. No new comments can be posted.

AMD Challenges P4 With 1.33Ghz More

AMD Challenges P4 With 1.33Ghz

Comments Filter:

  • AMD is VERY GOOD, but.. (Score:1)

    by Anonymous Coward
    The problem is while it is a fince commmercial processor, it's major weakness is corporations. The reason companies such as the one I work for doesn't buy AMD chips (which I feel are far better for the price than Intel) is because the chips are not certified with certain corporate software packages, such as some CAD programs like PRO/E.

    If AMD would get such certifications, the business world would take AMD more seriously. And with corporate money comes money for advertising to make them even bigger in the private sector than they already are.
  • Who else can sell you a $40 CPU (Duron 600) that you can overclock to a gigahertz?

    - A.P.

    --
    * CmdrTaco is an idiot.

  • And the funny part is, they use Macs in their stage shows.

    Anyway, Intel can show us as many stupid-ass commercials as they want -- it doesn't matter when they're losing marketshare to AMD at an alarming rate. Intel recently issued profit warnings. AMD reported record profits last quarter. So go figure... maybe advertising isn't everything.

    - A.P.

    --
    * CmdrTaco is an idiot.

  • What would be an interesting review would be: Athlon 1333-DDR against a Celeron 450 (overclocked) against a K6-2-550.
    Or even more impressive: going from a 386-33 to a 486-66 (4x was nice:) to a dual celeron 300 (now 450:). That last jump just knocked my socks off. A 40+x speedup is just phenomenomly fast. Even after two years, I consider my box fast (though the G200 is sloing its slug heritage). Everything is relative. I still remember doing cpu intensive things on an 8M V20(?). Now? Well, SMP or nothing :)

    /me drools over the though of dual (or more:) 1.3G cpus.

    Bill - aka taniwha
    --

  • I'm trying to order a workstation. Once I found systems that have a 1.2G athlong and ddr ram, I couldn't find any with for DIMM slots! The closest I could find was 3, and only one of those, iirc. grr.
  • Try encoding an MPEG4 clip on that 800MHz CPU, then on the 1.33GHz CPU. Report back, and explain that you were wrong.
  • With this latest shot in the MHz war, I often find myself wondering if there's some other way to increase processing power other than cranking up the clock frequency. RISC systems offer reasonably comparable computing power for usually less than half the clock frequency of Intel/AMD chips (look at Sun's UltraSPARC chips now). Are there other ways of getting the same horsepower for lower speeds?

    It would seem off hand that an immediate benefit of this would be lower power requirements and significantly less cooling needs. OC'ers routinely chill their CPUs to get to even higher speeds, but at this rate how soon will it be before CPU chilling becomes standard or required?

    stop the madness!!!
    :)
  • don't forget Tom;s Hardware [tomshardware.com]

  • Huh? (Score:2)

    by roystgnr ( 4015 )
    I think that AMDZone and www.amd.com might just be a little bit biased, and I noticed Ace's Hardware spending half their time gloating over the performance they got by overclocking one of the new Athlons to 1.5 Ghz, and neglecting the fact that they managed to render it unstable at 1.533 Ghz.

    But what really gets me: you're claiming that Slashdot and Sharky Extreme are Intel biased sites? Are you daft? Did you actually read the linked review? From Sharky's conclusion:

    With this, their most recent unveiling, AMD has again leapfrogged Intel in all but one of our performance matrices, making the Athlon 1.33GHz the fastest processor we have tested.

    The biggest reason they can give *not* to buy this processor is that they're expecting faster (Palomino-based, possibly smaller process) chips from AMD shortly!
  • Or you could put a heatsync & fan on the thing for $10 and be done with it.

    Seriously, I'm sick of this type of AMD bashing. Yes if you run the chip w/o proper cooling it'll die, but on the other hand, if you run it /w proper cooling, it works great.

    Case in point. I built a system for a friend on a Duron 750. Got the generic $9 cooling fan solution and some thermal paste. Pasted it up good, put the heatsync & fan on, booted it up and all is fine. Even after running for hours doing 100% CPU load, it won't get hotter than about 100 degrees F ... that's pretty good if you ask me.

  • Yeah yeah. (Score:3)

    by Uruk ( 4907 ) on Thursday March 22, 2001 @10:29AM (#346649)
    OK great. A newer, faster processor.

    What I want to know is when we're going to get motherboards with IO buses and IO devices that can DEAL with a processor running this fast.

    Let's face it. You can attach a 40 million gallon per hour water pump to a straw. But that doesn't make it any better than a 30 million gallon per hour water pump because of other limiting factors.

  • The desktop Palamino has been delayed so AMD can redirect those Palamino chips to notebooks. AMD can't overhaul all their production lines at once y'know, and the Thunderbird is holding its own against the P4 just fine.

    Translation: there's big-time demand for Athlon notebooks, and I'm really, really glad I dumped my Intel stock several months ago ;-).

  • I do! (Score:1)

    by rho ( 6063 )
    does anyone harbor any lingering thoughts that AMD is a second-class citizen in the chipmaking world?

    AMD doesn't have the very cool Blue Man Group [blueman.com] shilling for 'em.
    "Beware by whom you are called sane."

  • Re:I do! (Score:1)

    by rho ( 6063 )

    Actually, I'd pay good money to see Bob Young dangled from a rope, splattered with paint and flung against a canvas.
    "Beware by whom you are called sane."

  • Re:I do! (Score:1)

    by rho ( 6063 )

    Nah. Bob Young might actually do it. Larry Ellison never would. (I have invested in Oracle).
    "Beware by whom you are called sane."

  • it's PROGRAM efficiency that's down.

    Which is fine with me. I can crank out Q&D VB apps in a couple of hours that would take a couple of days to write in C++. Most of these wouldn't get written if they took that long. So who cares if the VB message board app the secretary uses takes three times as long to update the screen as it would written in C++? On her 450MHz PIII, it's still under a second. And if the user can't tell the difference, what's more important -- your time, or the computer's time?
  • 800MHz processors are well under $100 now. Do you really expect them to get cheaper?!

    --
  • http://www.aniteccom.com/

    Canadian company. 800MHz Duron, C$105. About US$65. TBird @ C$175 = U$110.


    --

  • Fighting the brand name bozo's (Score:3)

    by ch-chuck ( 9622 ) on Thursday March 22, 2001 @11:08AM (#346657) Homepage
    The last 5 or 6 upgrds I've smuggled into here have all been very affordable 800Mhz T-birds - as long as I NEVER mention that they're NOT Intel the users are VERY happy and they don't start quaking with fear, uncertainty and doubt. Ditto with the Linux mail server. Guerrila IT works if you can expunge the mktng bozo's and all the hypnotized suits under their command.

  • Re:AMD is releasing a highly adaptable bus (Score:3)

    by Christopher Thomas ( 11717 ) on Thursday March 22, 2001 @11:36AM (#346658)
    Guess what? AMD is beating Intel there too. Intel is trying to bait users with more performance but added vendorlock. AMD convinced API, one of the leading Alpha system producers to use their bus. Why? Intel uses a 1-bit high frequency bus, AMD uses a slightly lower frequency variable width bus which gets you 8-bit,16-bit,32-bit, and I believe 64bit and 128-bit are possible with some tweaking.

    Um, you seem to be missing a few points:

    • RamBus is 16-bit, not 1-bit.
    • Intel chips are perfectly capable of using SDRAM. It's the motherboard chipset that decides which is used, not the CPU.
    • The limiting factor for total CPU-to-memory and -to-system bandwidth for both Intel and AMD chips is the front-side bus - its bandwidth, and protocol.


    The main thing that affects a system's I/O and memory performance is the motherboard architecture and memory architecture. Chip architecture is secondary.

    The main impact of chip architecture is, as mentioned, the communication point between the chip and the motherboard chipset. This has no relation to the RAM type.

    In summary, about two thirds of your post was based on incorrect information.

  • I still question your conclusions. (Score:4)

    by Christopher Thomas ( 11717 ) on Thursday March 22, 2001 @12:32PM (#346659)
    I wasn't talking about chip arch. I was speaking of motherboard arch. AMD is releasing a high speed main bus which is API compatible with PCI but blows Intel's 1-bit serial bus (Infiniband or something like that) out of the market.

    You are still ignoring several very important considerations.

    1. Infiniband motherboards do not presently exist. Claiming that AMD or DEC/Compaq's motherboard architectures blow them out of the water is very premature.
    2. You are blithely ignoring the serious problems involved in widening busses.

      It turns out that this is *extremely* difficult, especially at high speeds, and especially for synchronus busses. Your path lengths for all of the traces have to be the same, or very nearly the same. This is next to impossible to achieve for extremely wide busses. Thus, your claims of it being cheaply extensible should be taken with a large grain of salt. (You can make the bus wider by using more expensive motherboard construction, but this is - guess what - considerably more expensive).
    3. You provide no support for your claim that Infiniband's performance will be poor.

      It's an asynchronus serial bus. That removes two major design constraints (controlling the lengths of multiple lines, and keeping handshaking synchronus). I can believe that you could run something like this fast enough to make it competitive with existing busses (though I'd still want multiple channels in parallel in a real system). The fact that Intel is planning to use this at all suggests that bandwidth will be comparable to or better than what they're currently using.
    4. You're assuming a single channel. Any sane design that I can think of would use multiple channels in parallel to boost bandwidth (receiver logic has to be more complicated, to combine packets from two asynchronus data streams, but this isn't that difficult).


    Can you provide more support for your claims, so that I can see where your arguments are coming from?
  • May I join you in your dreamworld sometime?
    --
  • It's not the "general public" that Intel is worried about. It's all about risk-adverse IT managers who control large PC budgets. (And, yes, IT Managers are a huge marketing segment - watch the ads fly over Joe Sixpack's head during any TV sports event.) And it's worked in that corporate PC purchases are still primarily Intel, despite the clear price advantage of AMD.

    Trying to market a component brandname to people who buy low-end consumer systems is no-go. These people don't know the difference between Microsoft and Compaq, much less some thing inside the box.
    --
  • Or wasn't this announced a few weeks ago?

    The benchmarks are nice though

  • I doubt it. 8^)
  • Don't forget my fave, AnandTech [anandtech.com]. Lots of people like Tom's Hardware [tomshardware.com] as well.
  • You've GOT to be kidding me.

    I spent $900 to build TWO AMD-Duron 800's, with 128M, 20gig 7200RPM ATA-100 disks. Both of which I've O/C'ed to 1gig.

    Already had the monitors...and who the hell wants those POS printers and scanners they sell you anyway? My in-laws purchased a Gateway from the HSC, spent near $2k and the system I built for a quarter that price kicks it's ass.

    Can't win 'em all I guess.
  • does anyone harbor any lingering thoughts that AMD is a second-class citizen in the chipmaking world?

    I assume you're comparing them to Intel. I would offer that Intel is *also* a second-class citizen in the chipmaking world, given that their current batch of CPUs still boot into real mode.

    In any case, I don't think AMD is even close to the level of sophistication of Intel; anyone who does think so has a very narrow view of the industry. Sure, AMD makes a better x86 FPU than Intel, but they still haven't shipped a chipset to run dually athlons, and they don't do nearly as much experimental research - they're really just focused on imitating rather than innovating. Intel is about to (finally) roll out a completely new architechture with IA-64, while AMD is simply coming up with a 64-bit extension to the IA-32 architechture.

    I'm no Intel fan, and personally I think the Athlon is a better chip than the Pentium III/IV, but AMD is no Intel.

  • Wrong. As you can see, the processors are on the left (the other without a heatsink). Those fans are for something else (hd's etc.). I'd notice those CPU's don't have _any_ fans..
  • OnStar? Never heard of them. SAP?

    They run adds on TV all the time, actualy. Onstar and SAP anyway. I'm still not sure what exactly SAP does, though :P
  • ..meta-moderating is the jury duty of the /. community...


    And just like jury duty, you don't want anyone doing it who is too dumb to get out of it.

  • I have some friends that still think Intel is a safer way to go, despite the fact that I know a few friends with Athlon systems, and I've even built a Duron system for a friend who has not once complained about the setup.

    Now if only *I* could afford an Athlon...
  • I wonder if that'll change as soon as Compaq AMD-based servers start eating into their high end profits later this year...
  • Sure there are still plenty of Intel boxes at retail, but they're all low end = 1 GHz. AMD has all the high end. What a turnaround from a couple of years ago!!!!
  • You've got that backwards - AMD owns the desktop retail sector. Intel owns the server market and laptops.

    AMD's 760MP SMP chipset coupled with the incredible 1.5GHz AMD Palomino just shown at CeBIT are going to be used in servers from Compaq and apparently IBM also.

    AMD's Morgan (portable Palomino) comes out later this year.

    With Rambus rapidly going out of business and DDR P4 chipsets proliferating, Intel is in a world of hurt. Already their dismal selling (~1% of total PC sales) P4 is bested by the slower clocked AMD Athlon, and with P4 hobbled with DDR (it was designed for the huge memory bandwidth of RDRAM), the comparisons of P4 vs Athlon and Palomino just get more and more lopsided. Intel has dropped the ball.

  • What do people do to their AMD systems to make them unstable? My 1GHz Thunderbird has only been restarted a single time since the day I got it. And that was 17 days ago, during a power outage that lasted slightly longer than my UPS. I have had AMD systems for years and none of them had even the slightest hint of a problem with stability.

    Maybe I've just been lucky... ;-)
  • OnStar gets mentioned in a lot of car and car rental commercials...

    SAP has several wonderfully boring commercials, but they are fairly frequent.

    BASF... about three or four years now, the whole "We don't make the things you buy..." routine...

    All of these are featured prominently on CBS/NBC/ABC/ESPN/CNN and any other news related timeframe, or any type of show aimed more at adults than children (like "When MIR Attacks!!!" on Fox)...

    Of course, you'll never see these if all you watch is Cartoon Central for Anime or Cow and Chicken...
    --
  • I have an PC164-SX Board with a 533MHz 21164PC that I'm thinking of parting with...
    --
  • I'm more of a Dew/Alpha guy, rather than Jolt :)
    --
  • has amd actually made a reliable processor yet? it seems that everytime to release a processor they dont test them as thourghly as intel tests their pentium chips. if amd releases a bad processor they usually say 'oh well, lets see if we can fix that problem with the next batch'.

    Have a look at the Linux source code sometime...arch/i386/kernel/setup.c is particularly interesting as to whose bugs need to be worked around by the kernel. Looking at init_amd, one bug is attributed to B-stepping K6 processors, that comes into play in systems with more than 32MB RAM. (BTW, AMD used to replace those processors that were affected...I don't know if that program is still in effect.) By comparison, init_intel has workarounds for the F00F bug (non-root users could kill any Pentium or Pentium-MMX system) and the Pentium Pro's CPUID bug (it says it supports the SEP instruction when it really doesn't). There was also the problem with the 1.13-GHz Pentium III running so badly that it was recalled, plus the FDIV bug in the first Pentiums. Now try telling me that Intel makes a better/more reliable product than AMD.

    I'm on my fourth AMD processor now...started with a K6-200 and went through a K6-2-300 and K6-III-450 to arrive at the 1.0-GHz Athlon I'm using now. (The K6-III is still in use, only in my server now.) I've also built a few K6-2 and Duron systems for others, and the only problem that's ever popped up in any of them was an overheated SiS 530 (on the one time that I tried building a really cheap box) in one of the K6-2 boxen...fixed that by slapping a cooler on that chip, and in any case it wasn't a processor problem.

  • It's a sad but true fact of life that in the world of consumer goods, brand image is crucial to growing market share, because in fact most people do care about brand names. The way advertising drives demand, you at some point have to work at establishing brand consciousness in the public at large. Why do you think companies like OnStar, BASF, and SAP spend money advertising the way they do? They never sell directly to the end consumer, but they work at making their brands household words nonetheless.

    It's about creating a perception that you're the only game in town - that's why intel spends so much on their advertising - specifically to drown out AMD. AMD's best bet for wooing away Dell and the other business-machine providers (where the real money in PC sales comes from), is to get buyers asking Dell, "Why don't you sell AMD machines?" The best way to do that is through aggressive advertising. The fact that AMD has the superior product should only make that job easier.

  • Faster chips are great, but... (Score:3)

    by Dr.Evil ( 47264 ) on Thursday March 22, 2001 @10:32AM (#346683) Homepage

    What AMD really needs is mindshare. When was the last time you saw an AMD commercial on TV? Compare that with the Blue Man Group ads for the Pentium 4 that intel runs just about every hour on every channel. AMD can't get OEM agreements with the big PC manufacturers - did it ever occur to them that it might be because Joe Consumer doesn't ask Gateway or Compaq about the latest Athlon machines?

    OEMs are never going to worry about building AMD-based machines when there's no market demand. AMD has to make the public believe it's a serious competitor before the OEMs will believe it. I want very much to see AMD succeed and make the Athlon the top chip for x86 machines - but they have to know how to drive demand.

  • > I have to laugh when people (non-technical people) complain about how a computer is obsolete the day you buy it.

    Ditto. I just flashed the 0112 (beta) BIOS into my old TX-97 motherboard. My old P166MMX now supports 2.0V-2.2V CPUs. $30 for a K6-III at Fry's (which I originally bought for my I-opener!), and my old P166 box is now chugging along at 400 MHz with 256K on-die cache. If I overclock the PCI bus, I can take it to 500.

    For $30, I turn "that old computer I don't use anymore" into an all-in-one software-based DVD player, MP3 jukebox, and decent gaming box for the price of a pizza and a case of beer. (And I find a good use for the TV-out jack on the video card, which I never bothered to use, 'cuz hey, I can't play DVDs on a P166 ;-)

    > word processing, email, and browsing.

    In defence of your nontechnical friends, if they're "compulsive upgraders", their "old" computers probably have gotten slower, even if they're doing the same tasks. Netscape 3.0 to IE5.5? Word97 to Orifice2K? Win95 OSR2 to Win2000 or WinME? Yeah, if they've done these upgrades, their perfectly adequate P166 boxen probably are grinding under the strain, especially if they cheaped-out and got 32M of RAM.

    Computers don't get slower as time passes, but software does.

  • I don't know if I think of AMD as a second class CPU maker/distributor, but I still hold Intel in a higher regard simply because they tend to offer more in the way of innovation.

    Is it "innovation" or "let's add stuff to lock more people into our products!"?

    Take a look at Itanium (or their IA-64 instruction set) vs. AMD's Sledgehammer core-- IA-64 is just another operating environment, like Protected Mode was to Real Mode, except that IA-64 processors start out in IA-64 mode instead of having to switch modes after being reset. Sledgehammer, AFAIK, is just new instructions without a new operating mode. IA-64 introduces a HUGE number of general purpose CPU registers (no more EAX, EBX, ECX, EDX, EDI, ESI limitations!) while (from an admittedly brief review) AMD adds a total of 8 general purpose registers.

    So Intel has added as of yet unused and so far unnecessary registers to a new operating mode which can (will?) potentially lock consumers into their products as software gets written to take advantage of said (dubious and patented) innovations?

    While AMD has simply taken an existing operating mode, added a few general purpose and non-proprietary registers, and improved the overall design and performance of a tried-and-true architecture with known quantitative qualities?

    Do I need to bring up the higher monetary entry point in the marketplace for those "innovations"? Why pay extra for something that isn't fully utilized when I can purchase a similar product, which performs just as well (if not better) for much less?

    Somehow this doesn't seem to be "innovation" to me. It reminds me somewhat of how the Japanese do little that is truly "new" in the gestalt sense but instead rely on tweaking existing technologies to bring out their full potential. And last time I checked they 0wn3d many major markets which were invented and developed elsewhere (VCR anyone?) by approaching the market in such a manner.

    Of course, I'm probably just an idiot.

  • Why do you think companies like OnStar, BASF, and SAP spend money advertising the way they do?

    OnStar? Never heard of them. SAP? Never heard of them. BASF? Sure, about 20+ years ago, I had some of their open reel tapes. Now they are probably making cassettes.

    If these guys are spending money on PR, I don't think they are getting their money's worth! As far as I know, BASF probably stands for something like BayerischeAktiengesellschaftScheissFabrik...
    (I told you their PR isn't working...)
  • The standard Pentium III processors can only scale up to two processors, but then you are limited to the BX/GX chipset (aging, only officially supports 100Mhz FSB), the Via chipset (I'm still a little wary of it), or the i820/i840 (requires Rambus memory). The Xeon allows you to scale well above 2 processors, but then you have to pay through the nose for a decent motherboard and the processor.


    There's nothing wrong with the 440BX chipset, really. If you get a recent revision of the Asus or Tyan dual BX boards, you can support Coppermine CPUs all the way up to the 850E (depending on your BIOS, revision, etc). You don't get PC133 RAM or AGP4X, but who really cares? AGP4X is all about marketing, and PC100 memory on a BX will probably outperform PC133 memory on a VIA chipset. VIA chipsets suck royally.

    Not having a 133 MHz FSB is a bit of a drag, but I haven't had trouble supporting five Ultra2 Wide SCSI hard drives (four 7200 RPM and one 10K RPM), AGP 2X, and two 100Mb/s NICs on my 440BX. This is obviously a lot more than the typical load placed on a BX motherboard... or even a KT133A.

    The i840 isn't such a bad choice now that RAMBUS memory is so cheap. Cheap?! Yep. It's cheaper than DDR SDRAM in some cases. Check it out on pricewatch.com.

    What about the Serverworks HE and SL chipsets, if you don't like using PC100 or RAMBUS memory? You get dual or quad processor motherboards; 64 bit, 66 MHz PCI; multiple independant PCI busses; PC133 RAM; and some really awesome other stuff, all for around $300 or $1000 (dual P3 vs quad Xeon). Add another $100-$150 for integrated 64 bit Ultra160 SCSI. Wow.

    I dunno about you, but I'd get excited over a motherboard that cool for just $300. I paid $250 for my dual Asus P2B-D in October of 99. My KT133A board was about $125 a month ago. So, for just a little bit over the price of a dual BX or two KT133As, you can get a monster server board. Nice deal.

    Integrated 440GX, 450NX, and beyond can be prohibitively expensive. Try buying them from ebay cheap if you want a killer Xeon board from Intel. The 450NX supports four Xeons. Nice. Not cheap, though.

    You can also look at workstations/servers from Micron (they make their own cool chipsets). Some awesome stuff never makes it to the public, because of non-competition clauses Intel makes people (like Micron) sign.

    And, one last thing: don't ever trust marketing. Just because it's new doesn't mean it's better. Sometimes the best solution is older technology. It has proven reliability, lowered cost, *known* issues (rather than unknown issues), and more mature driver support.

    As an addendum to the one last thing: watch out for diminishing returns.

  • Re:AMD still isn't on TOP for ONE reason ... (Score:3)

    by questionlp ( 58365 ) on Thursday March 22, 2001 @10:59AM (#346695) Homepage
    Unfortunately, the current revision of the Pentium 4 processor and the i850 chipset only supports one processor. It's not until the new Pentium 4-based Xeon until we see 2+ processor based systems.

    The standard Pentium III processors can only scale up to two processors, but then you are limited to the BX/GX chipset (aging, only officially supports 100Mhz FSB), the Via chipset (I'm still a little wary of it), or the i820/i840 (requires Rambus memory). The Xeon allows you to scale well above 2 processors, but then you have to pay through the nose for a decent motherboard and the processor.

    I think AMD should take it's time to release the 760MP to make sure that performs like it is supposed to and it is stable enough to cram in 2x1.33Ghz processors. Since the current gen Athlons use the EV6 protocol, there are a lot more traces required to connect to the processors to the northbridge chip, but then you get two independent channels rather than a shared bus found on all Intel chipsets and processors. Even the first-gen Itanium will still run on a slightly tweaked version of AGTL+ (ie: shared bus).
  • Sure. Mathematical proofs are VERY biased to those who are verball oriented. I, for one, can easily get a concept if you put it into words, but big equations just fly over my head like so much wind. Besides, bias is built into the very fabric of perception. Name something that *isn't* biased.
  • Why do I see this every time a new procesor comes out. Not everyone runs a freaking web-server! Some things fit entirely into memory (especially with SDRAM so cheap!) and the faster processor scales performance quite linierly. Given that mature DDR-SDRAM and RDRAM chipsets are just around the corner, the I/O arguement really doesn't make sense for a lot of uses anymore. For example, I do 3D. I'd much rather have a 20% faster processor than a 200% faster PCI bus.
  • although this poster is largly incorrect, he has a point. AMD is releasing a product called LDT (or, sigh, HyperTransport... dumb names... Athlon my ass, it's a K7) which will offer a 6.4 GB/sec point-to-point bus. While Intel seems to have something similar in the pipeline, AMD's solution is much farther along.
  • From where? If the 3D model is bigger than RAM, its on the harddrive. If the harddrive transfers at 30MB/sec (at best) and PCI is 100MB/sec (optimal: 133MB/sec) then it does no good to speed up the PCI bus! PCI bus speeds used to matter, but unless you have an >4 drive U160 SCSI RAID array, it really doesn't any more, since the only thing on there is the hard drive and sound card.
  • I'm not sure what definition of "sold out" this is... but AMDZone is far more "sold out" than anandtech. It's got a freaking brand name in it's URL. What do you expect it to say "This chip sucks. It's too fast." These four sites are all also biased, just differently. Everythings biased. Thats one of those fundamental truths of life. People just tend to call "fair" whatever they see that is biased in a way that they find agreeable.

    Justin Dubs
  • ...imagine a Beowulf cluster of these.

    You may not notice a performance increase on your home PC, even in applications that squeeze every last cycle out of the CPU. However, you could certainly see a performance increase on, say, a 16-node Beowulf cluster of 1.33 GHz, versus the performance on a similar cluster of 1.2 GHz machines.

    ***

    "ALL YOUR CODE ARE BELONG TO US!" -- Jim Allchin
  • AMD is releasing the jacked up Athlons but delaying the Palomino's.
  • The ISA is a consumer issue not an Intel issue. Nobody gives a damn except consumers who already have old software.

    IDT Winchip uses a MIPS core with an x86 ISA. MIPS is one of the most cost-effective power-saving high-performance cores you can buy. If they would just advertise. I love AMD. It's great, but now that I've heard of IDT's use of MIPS I have to try it in an Amiga sometime. (yes you can use multiple CPUs at the same time with software running concurrently)

    AMD tried their 29K system with their own ISA. It smoked Intel's crap. Guess what? Nobody wanted it. Why? Software wouldn't run on it. The people holding the pursestrings as far as ISA is concerned are consumers not Intel.

    1st tier is as pointless as grains of film to a wedding photographer.

    No one cares about the ISA. It's purely a compatibility feature.

    You'll note Merced/Itanium was announced almost two years ago and still it hasn't hit the market. The ISA is a road block to the owner as well as the competition.
  • AMD doesn't have the very cool Blue Man Group shilling for 'em.

    Of course, Intel doesn't have the very cool Blue Man Group [google.com] using their products.

  • This is very clever on AMD's part. By moving the Athlon line to the 266 DDR EV6 bus, AMD now can increase overall system performance and finally take full advantage of PC133 SDRAM and PC2100 DDR, something which Intel has not as yet been able to do. AMD is also mimicking (almost mocking, in fact) Intel's now standard move of continuing to produce 200 MHz DDR processors in higher and higher speeds.

  • anyone harbor any lingering thoughts that AMD is a second-class citizen in the chipmaking world?

    Every company that I've worked for...least for desktops. they just choose intel by default since it is a safe, no-brainer and no one really cares all that much (me for example...Would I prefer an Athlon, yes. Would I fight purchasing to get one, no.)

    Until AMD can erode this mindset among those who purchase equipment for large companies, Intel will continue to be a class above the rest...no matter if their chips run faster or not.
  • The pics were also posted to the web very close to each other, time wise. About 1 minute difference. Here's the HEAD of each gif, note the dates. The space in the second HAD is a slash artifact.

    $ telnet www.mydesktop.com 80
    Trying 63.236.73.169...
    Connected to www.mydesktop.com.
    Escape character is '^]'.
    HEAD /graphics/screenshots/985242384image003.gif HTTP/1.1
    Host: www.mydesktop.com

    HTTP/1.1 200 OK
    Date: Fri, 23 Mar 2001 06:17:11 GMT
    Server: Apache/1.3.12 (Unix) AuthMySQL/2.20 PHP/4.0.2
    Last-Modified: Thu, 22 Mar 2001 06:26:24 GMT
    ETag: "c1c3c-2a6d-3ab99b10"
    Accept-Ranges: bytes
    Content-Length: 10861
    Content-Type: image/gif

    $ telnet www.sharkyextreme.com 80
    Trying 63.236.73.81...
    Connected to www.sharkyextreme.com.
    Escape character is '^]'.
    HEAD /hardware/reviews/cpu/thunderbird_1-33ghz/image003 .gif HTTP/1.1
    Host: www.sharkyextreme.com

    HTTP/1.1 200 OK
    Date: Fri, 23 Mar 2001 06:16:06 GMT
    Server: Apache/1.3.12 (Unix)
    Last-Modified: Fri, 23 Mar 2001 01:34:00 GMT
    ETag: "9bb42-2a6d-3abaa808"
    Accept-Ranges: bytes
    Content-Length: 10861
    Content-Type: image/gif
  • Actually I just noticed they are both in the 63.236.73.* subdomain. It's likely that there is some affiliation.
  • The chips are hot, but I have some problems with the rest of my system. For one it runs too hot and too noisy. My first Motherboard died, and I'm not getting the FPS on my GeForce that other Intel-based Motherboards are getting.

    I also wasted about 6 months trying to get my motherboard to run stably (until MS brought out a patch for AMD chiupsets...). Even thought this is not the chips problem etc. etc. I still wasted time, thus Intel would have been much cheaper in retrospect.

    Those are my gripes, and even though at heart I support AMD, I'll go for a P4 next. It's a better chip, even though most applications and benchmark programs don't reflect it yet.
    (See the FlaskMPEG benchmark for the optimised versions... both for Intel and AMD)
  • What can we be doing with all of this capacity to truly make our world better?

    How about these:

    • Distributed.net
    • Seti@Home

  • Second-class? (Score:4)

    by vex24 ( 126288 ) on Thursday March 22, 2001 @10:31AM (#346740) Homepage
    does anyone harbor any lingering thoughts that AMD is a second-class citizen in the chipmaking world?

    Dell, apparently... those jerks still won't sell me AMD powered boxes. :P

  • Windows crashes 33% faster on this one compared to a 1 GHz model
    --
  • The only problem with AMD is they still haven't delivered a working machine with more than one processor. Until they can give me a dual or quad processor system .. they're going to have to be TRUELY in second place ..

    Even if the 1.3G Athlon beats out a PIII or P4 system, if I get a PIII or P4 system with 4 or 8 processors in it, I'm sure that would kill an athlon system.

    Question: Do you think AMD is holding off on releasing the 760MP Chipset (the multiprocessor chipset) because they don't know if they'll be able to keep up with demands once people start buying two or four processors at a time?

  • wow! (Score:4)

    by shren ( 134692 ) on Thursday March 22, 2001 @10:33AM (#346747) Homepage Journal
    now software designers can release even sloppier, slower, uglier code and still have it work fast enough!
  • AMD put themselves in a good postion last year by (more or less)
    consistently delivering on product. It also helped that 2000
    seemed to be a year when it was Intel that was the one who could
    not seem to keep their overall quality going from Fab to retail space.
  • I haven't seen any indication that Intel is planning to use InfiniBand as their system bus. Even 12x InfiniBand (the fastest currently-specified version) is only 3 GB/s, while the P4 bus is 3.2 GB/s (granted, IB is not a bus; it's switched).

    However, I agree that LDT is likely to beat the pants off the P4 bus.
  • This is very true, I think that Joe Consumer, doesn't give a damn about brand of CPU. The big deal now is price. AMD has silenced a lot of vocal critics in the media with their quality. It used to be that every AMD review had a paragraph or two about their past quality issues. Even though those problems were isolated and way in the past you used to see those pot shots everywhere. Now AMD has proven themselves in the media and more importantly with their customers both OEM's and consumers alike. Now that the playing field has been leveled the only thing that matters is price.

  • You have got to be crazy!

    Of course its painful and in my opinion it should be. First of all, installing Oracle 8i on _any_ hardware with less tham 128mb is insane. Sure, you can use it as a simplistic test environment, but even in a development environment, especialy with the Java option, you've got to be nuts. The minimum size for the SGA with the Java option is around 58MB. That's more than half your physical memory gone, that leaves around 56M for Windows 2000, and anyone can tell you that Win2K Server is not a very happy camper at that low of memory. Throw, the very nice IDE, but resource hungry JDeveloper, and your machine must beg for mercy every time you start it up.

    The problem with your post is that two of the three pacages you talk about are server applications. Use WinNT Workstation, drop Oracle 8i, and install JDeveloper and that box will be fine. A P2-300 w/114MB is more than capable of being a desktop machine.

    BTW, I'm running Oracle 8i on a Dual Pentium II 233mhz with 256MB on Red Hat 6.2 and I would still only consider it a development machine. I wouldn't run a production environment on it without 512M.

  • Re:Practical spending. (Score:3)

    by Ian Wolf ( 171633 ) on Thursday March 22, 2001 @10:37AM (#346766) Homepage
    I agree with you completely, but I say push on boys and girls.

    As the people who have to have the fastest chips start to gobble these up the prices are going to to fall even further on their slower, but capable cousins and that is always good.

  • Re:wow! (Score:4)

    by Ian Wolf ( 171633 ) on Thursday March 22, 2001 @10:51AM (#346767) Homepage
    I laughed, but this isn't funny. It's all too true.

    I have to laugh when people (non-technical people) complain about how a computer is obsolete the day you buy it. To which I am always inclined to ask what they are doing with their computer that it can't keep up. The answers are almost always the same, word processing, email, and browsing. They simply think that becauses there is something faster out there that theirs is somehow obsolete.

    Hardware companies are building jets, and most software companies are simply building bigger biplanes with gold plated instruments, leather seats, and a teak prop.

  • Re:Faster chips are great, but... (Score:3)

    by jerkface ( 177812 ) on Thursday March 22, 2001 @10:38AM (#346769) Journal
    I disagree. AMD's success is a sign that people - whether or not they are clueless about microprocessors - care very little about brand names. (There are a few anti-intel fanatics who are the exception to this rule). Intel's attempts to pump up their brand name are obviously a failure with the general public. Most of the people who bought an AMD from Gateway or suchlike probably don't even know what AMD is. I'm glad AMD isn't wasting dumploads of money on establishing a brand name. Consumers see little reason to care.

    --

  • When was the last time you saw an AMD commercial on TV? Compare that with the Blue Man Group ads for the Pentium 4 that intel runs just about every hour on every channel.

    Perhaps if Intel spent as much money on R & D as they do on airwave saturation with the stupid chimes and the inanity of the Blue Man Group, AMD's taillights wouldn't be so far ahead of them.

  • I've seen a few AMD commercials, which is a few more than I expected considering their practically non-existant revenue compared to Intel.
    AMD made a profit of just under a billion last year (on revenue of around 4.5B), which is more than enough to pay for a few ads. Of course Intel made about 10 times that, but still AMD's revenue is hardly non-existant.

  • Plagiarism? (Score:3)

    by RedWizzard ( 192002 ) on Thursday March 22, 2001 @02:01PM (#346776)
    Why are those two articles using the same graphs?

    Take a look at this page [hardwarecentral.com] from the Hardware Central article by Vince Freeman. In particular check out this graph [mydesktop.com] (which is curiously not hosted on the Hardware Central website).

    Now look at the Sharky article [sharkyextreme.com] by Chris Angelini and Ben Hirsch. Compare their graph [sharkyextreme.com].

    The second pages of both articles are also very similar in structure, both discussing (in the same order) the fact that it's the same core, the cache, the bus, and then the chipsets. The comments are different though. Are these two sites getting the same person to do the benchmarking?

  • Comment removed based on user account deletion
  • Is it "innovation" or "let's add stuff to lock more people into our products!"?

    It's innovation-- take your own question and apply it back to the original x86 architecture. Was Intel locking anyone into their products then? The answer is yes, but as everyone here on /. is aware, emulation isn't illegal and nobodies stopping AMD from making their own compatible version of IA-64 (the specs are all out there for the taking, check out developer.intel.com [intel.com], and Intel will even ship, FOR FREE, IA-64 manuals to you that weigh in at over 1,000 pages!).

    So Intel has added as of yet unused and so far unnecessary registers to a new operating mode which can (will?) potentially lock consumers into their products as software gets written to take advantage of said (dubious and patented) innovations?

    Wrong. You clearly aren't an assembly language programmer-- the biggest problem with x86 CPU's is the LACK OF GENERAL PURPOSE REGISTERS. IA-64 addresses this problem using these methods--

    128 General Registers (64-bit)

    128 Floating-point Registers (82-bit)

    As you can see, compared to the number of registers available in the 386 through to the Pentium 4, this is a HUGE number. (FYI: The Pentium III has 4 32-bit general purpose registers, 6 if you count ESI and EDI, 7 if you can safely use EBP. There is also a similarly low number of FPU registers, again, Intel has addressed this with IA-64.) These registers would not go unused, and they are VERY necessary. The kind of optimizations this will open up are mind-boggling to an assembly programmer.

    While AMD has simply taken an existing operating mode, added a few general purpose and non-proprietary registers, and improved the overall design and performance of a tried-and-true architecture with known quantitative qualities?

    You're suggesting that Intel sticks with an admittedly broken and ancient architecture? Intel has stretched the x86 core as far as it's going to go, the only innovation that can occur now is with a changing of paradigms and a changing of actual instruction sequencing. IA-64 puts more of the burden on the compiler to figure out what code is trying to do, and puts less of the stress on the run-time architecture (not to belittle the IA-64's strong architecture, simply that it's taken a much more RISC approach than their x86 processors have).

    All of your points about cost of innovation and so on are moot-- it wouldn't be innovation if Intel stuck with the status quo. AMD isn't innovating, AMD is copying and now trying to extend x86 to last a little longer. Intel wants to ditch the x86 architecture but still leave a migration path for older users (hence the 'IA-64 is just another mode of the processor' trick-- code can switch at will from IA-64 mode to protected mode to real mode and back, and real mode/protected mode code can take advantage of IA-64 if the mode exists without using an IA-64 OS). In the end, one is innovation and one is just an attempt to keep the x86 around that much longer.

    I'm not anti-AMD, but to say that Intel isn't trying to innovate and is instead trying to force people to adopt some new hardware of theirs is just plain wrong. I don't think either company is trying to do that, or else we'd see a total dismissal of the x86 instruction sets-- but instead, we're seeing both AMD and Intel keep the x86 around in both their 64-bit implementations as legacy support.

  • Hardware companies are building jets, and most software companies are simply building bigger biplanes with gold plated instruments, leather seats, and a teak prop.

    I agree with you 100%-- but thankfully solutions are presenting themselves and eventually this will hopefully become a non-issue.

    As a software engineer though, I tend to try to optimize my code wherever possible, hence why I'm usually the only developer here that reads x86 instruction reference manuals, or pours over assembler code like it's not big deal.

    The thing is, most people just stick with what their compiler outputs and assume it's "good enough" and not worth optimizing-- never once bothering to throw their code under a profiler and see where the most CPU cycles are wasted. Merely doing that can lead to incredible speed increases, or atleast a better understanding of what code is eating up the most time. This can lead to more efficient re-writes, or better implementations. Here's my own personal example though--

    I was given the task of writing something simple-- a UTF-8 decoder that would translate UTF-8 encoded strings to normal 8-bit ASCII strings (unicode characters would be left encoded). This was for Win32, so I tried three things--

    MultiByteToWideChar (Win32 function)

    Pascal/Delphi translation using shl, etc.

    x86 assembler version (quickly, but carefully, written)

    As it turned out, my results went something like this-- the x86 assembler code performed the task 3x - 4x faster than MultiByteToWideChar. The x86 code performed 1.5x - 2x faster than the Delphi code I wrote. Clearly the short time I spent writing it in assembler paid off, and considering how often this code is called inside our code, it was well worth it. Besides this, calling MultiByteToWideChar yielded a unicode result, not an ASCII result, so there was also the issue of memory use and the fact that Delphi had to silently translate the unicode characters back to 8-bit ASCII.

    I think it's a good example of how developers can put the processor to use. People in IT, specifically developers and engineers, should quit dismissing x86 assembler as merely driver lore or as some black art. Sure, it's not as neatly portable as C or C++ or Java (although I argue that those aren't very portable as it is anyways), but with LITTLE work, most assembler functions (like the one I wrote for the task above) can be translated for use under any OS in almost any language that can link in external assembler code.

    My point? There's hope out there yet for less bloatware and more screamware. ;)

  • Well... (Score:4)

    by DarkEdgeX ( 212110 ) on Thursday March 22, 2001 @10:34AM (#346800) Journal

    I don't know if I think of AMD as a second class CPU maker/distributor, but I still hold Intel in a higher regard simply because they tend to offer more in the way of innovation.

    Take a look at Itanium (or their IA-64 instruction set) vs. AMD's Sledgehammer core-- IA-64 is just another operating environment, like Protected Mode was to Real Mode, except that IA-64 processors start out in IA-64 mode instead of having to switch modes after being reset. Sledgehammer, AFAIK, is just new instructions without a new operating mode. IA-64 introduces a HUGE number of general purpose CPU registers (no more EAX, EBX, ECX, EDX, EDI, ESI limitations!) while (from an admittedly brief review) AMD adds a total of 8 general purpose registers.

    AMD is definately a lot different from their start-up days, and it's nice to see them trying to innovate with technologies like 3DNow! (and even nicer to see adoption of their technology alongside Intel's own technology), but I still see some work to be done before they get the major acceptance Intel enjoys in the marketplace (and not the hobbyist).

    (Before anyone flames me, I know Gateway and other companies offer AMD processors in some of their offerings, but in general you still see a much larger number of Intel processors out in the retail sector vs. AMD processors.)

  • As *cool* as seti@home and distributed.net are, they don't count as making our world better. They are good things and cool things, but do not help make the computer a life-style quality multiplier.

    I can only think of trivial examples, like parsing, categorizing, and analyzing the music you listen to (songprinting, frequency of play, length of play, type of play) to help you find more music you like, and sharing this info with other machines to make music databases as easy to browse and search as the internet has made text databases browseable (if not easy).

    But what can a single 400MHz machine do to make the average household 10% happier?

    Geek dating! [bunnyhop.com]
  • Get a Mac tower. Heck, get a dual CPU 533MHz G4 with built in firewire, CD-RW, gigabit ethernet, and a GeForce3 ^^

    Geek dating! [bunnyhop.com]
  • What for?

    Here I have a 650MHz P3, there a 300MHz P2, at home a Celeron 450, and in my hand a 400MHz P3 laptop

    Most suck power being idle.

    What can we do (Open Source, PC industry, software industry) to make computers truly powerful, useful, productive! All these resources, Python, Perl, C/C++, CPUs, memory, storage, networking...

    What can we be doing with all of this capacity to truly make our world better?

    Geek dating! [bunnyhop.com]
  • Right about incremental performance boosts. Running UT I get 40fps on a K6-2 300 overclocked to 418 and a Geforce 256. A new system would be a 300% increase for me, but what's the increase on 1.2Ghz to 1.33Ghz, 9%. "Hi, would you like to upgrade 300% or 309%?" When I can see a tenfold improvement, it'll be time, just like upraging from my 486-33. Until then, I need the money for beer.
  • It's a moot point now. There is tons of stuff out to replace it. Got a Cue Cat(unmodified)? Got a Smart Card Reader? Got a new hard drive? Got a network card? Got Windows (any of the phone home^H^H^H^Hsubscription stuff)? Got MS Office? Got a Microsoft Optical Mouse? Any Matell Software? The CPUID is the least of your security holes.
  • Now, it's neat that AMD has just put out a top-of-the-line Athlon with DDR & 133MhzFSB support, but tell me fellas:

    Could any of you really tell the difference between this setup and a 1.2Ghz machine? I mean seriously, this isn't flamebait. Your app might open, what, 1/20th of a second faster, and you might bet 5 more FPS in Q3A.

    It almost seems like what's the point with these incremental releases.

  • Neither did Intel [apple.com], until the endorsement money started talking.

  • I have to agree. The AMD system I use at home is by far the most stable of my 3 main systems. The other 2 are both Intel (One Celeron, one Pentium) and both are more likely to freeze or choke.

    The question of course, is do you mark that up to the processor, the drivers, or the mo-bo? I am of course referring to all systems having the same OSs installed on them, with AMI BIOS.

    Have any of you used the BMRT (Blue Moon Rendering Tools, http://www.bmrt.org) on the Intel vs. the AMD? I don't have any systems that are speed comparable to run this test on. However, it's a great benchmarker.

    -WS
  • Well, I think that both companies would do much better if they could convince people like me why I should shell out more money to replace my perfectly usable P II 233. If it runs, it runs. I couldn't care less about how fast my CPU is.

  • Yeah I can tell the difference: it's in the price tag. These incremental releases keep the prices falling. To me, this release means that I am one step closer to getting the 800 Mhz processor I have my eyes on.

  • 2 worst reviews (Score:3)

    by ruiner5000 ( 241452 ) on Thursday March 22, 2001 @10:35AM (#346819) Homepage
    Wow, the two worst reviews from the Intel biased sites get posted. Surprise surprise. Here are a lot better reviews from sites that have not sold out.:)

    AMDZone [amdzone.com]
    Gamer's Depot [gamersdepot.com]
    Ace's Hardware [aceshardware.com]
    GotApex? [gotapex.com].

    And here is a presentation [amd.com] with benchmarks and a roadmap. Have fun. Don't let biased slashdot postings warp your mind!

  • Comment removed based on user account deletion
  • Comment removed based on user account deletion
  • Comment removed based on user account deletion

  • Re:SMP? FireWire? (Score:4)

    by Anoriymous Coward ( 257749 ) on Thursday March 22, 2001 @12:14PM (#346825) Journal
    Like those SMP Pentium IVs you see all over the place, right?

    I agree with you on the firewire, though.

    --
  • Until their mainboards support SMP, they will be second class.

    While we're on the topic, what's up with the lack of x86 mainboards with FireWire (IEEE 1394) support? I read a while back that the boardmakers aren't supporting 1394 because Microsoft doesn't want them too - because M$ doesn't control the standard.. but you'd think that would scare the Intel guys more than the AMD guys..

    How about it, VIA, can I get a MB with Firewire for my new camcorder? Or do I have to go Mac?

  • Mozilla (Score:2)

    by XBL ( 305578 )
    Maybe Mozilla will actually run fast on one of these :-)
  • Somehow I doubt it. The highest that a P4 has placed in the Sciencemark database [216.234.177.155] was a fairly far down the scale (26th place or some such) for a 1.7 Ghz oc'd P4 running 800 rambus. The higher places were all held by some variant of 1.2 T-birds. While I do admit that one or two of the higher places were by machines running more exotic cooling, the 1.2 tbird air-cooled and overclocked to 1.38 Hgz was still in the top 10. Given that this was a stock mobo, stock tbird, stock everything else, it sort of makes it a bit hard to justify a P4 at any price. Preliminary indications are that the long pipeline that Intel will allow you to scale up the clock, but will not provide faster execution in the commercial (rather than artificial) enviroment due to branch prediction problems.

  • Fa-a-a-st. (Score:4)

    by banuaba ( 308937 ) <drbork@ho t m a i l.com> on Thursday March 22, 2001 @10:37AM (#346835)
    Yeah, I got one of those bad boys. Overclocked it to just over 2ghz, I'm cooling it with liquid oxygen. I run at about 35 kelvin
    Had a little problem with open flames, tho. Foom! [purdue.edu] No more box.
    Course, I did manage to decapitate one of the blue men in the ensuing explosion. I made his little blue head into a hat for my dog.


    Brant

Slashdot Top Deals

"Virtual" means never knowing where your next byte is coming from.

Close