Intel Northwood CPU Review

gcshaw2nd writes: "Here it is, the first hands-on review I've seen of Intel's new Northwood chip, running at two gigahertz. It overclocks like a hog, easily to 2.5Ghz."

Comments

Clock Speed

[Anonymous Coward]

2.0 GHz (2000 MHz) Clock Speed

Well, its 2048, but who's counting?

Re:Clock Speed

[vipw]

umm, no it isn't. it is 100Mhz(+/- 1 Mhz) * 20. clock frequency isn't done by powers of 2.

Re:Clock Speed

[Steve Cowan]

2 GHz = 2000 MHz = 2000000 kHz = 2000000000 Hz. Metric. With bytes, however, 1 K = 1024 bytes, see below. 1 Mbyte = 1024*1024 bytes. 1 Gbyte = 1024*1024*1024 bytes. In metric we use a lowercase k to indicate 1000, the uppercase "K" was introduced in the seventies when RAM banks, which are addressable in binary, appeared. Thus 2^10=1024, which is close enough to a k that it's called a K.

Re:Clock Speed

[Howie]

= 2000000000 Hz. Metric.

and how much is that in imperial hertz? :)

Re:Clock Speed

[Anonymous Coward]

A Hz is a cycle/second, the closest imperial equivalent is RPM (revs per minute), so just divide by 60 (33.3MRPM). A mathemitician would use rads/sec, in which case multiply by 2pi (12.6 Grads/sec, I'm suprise the marketing people haven't caught this one yet).

Re:Clock Speed

[The Pi-Guy]

Err, that would be GiHz that's 2048, GHz is 2000. :) --pi

Re:Clock Speed

[SoupIsGoodFood_42]

= 2000000000 Hz. Metric.

and how much is that in imperial hertz? :)

1627545.12533 Gz (Gizyards)

1 Gz was how long it took King Arthur II to run around the table naked while being chased by dogs.

Re:Clock Speed

[Howie]

LOL :)
surely that would be 1627545 17/64 Gz though? :)

CPU Photos

[Anonymous Coward]

Does anyone else feel odd looking at photos of a CPU - like you're trying to look inside them - notice the number of ridges, trying to ascertain details that you can never get, like "what are you hiding - my precious?" and stuff?

Re:CPU Photos

[Monkey-Man]

No.

Re:CPU Photos

[Anonymous Coward]

Aw nuts
--Original poster.

And that's not all...

[Glonk]

Aside from the meager "5-10%" performance boost per clock that GamePC reports, the new PC1066 RDRAM and 533MHz FSB coming in a few months offers a "12%" performance boost per clock, when used with the original P4.

Northwood + 533MHz FSB/PC1066 RDRAM should be quite nifty.

The PC1066 benchmarks are here.

According to that chart there, PC1066 RDRAM actually has lower latency than PC133 SDRAM. I don't know how accurate that is, but it says PC1066 RDRAM takes 207 cycles for 128 bytes, and PC133 takes 229 cycles (PC800 took 270)?

Maybe I'm reading that wrong or don't know some specifics about RDRAM architecture, but that sounds nifty...

Re:And that's not all...

[hpa]

It's pretty silly comparing RDRAM to SDRAM. Compare it to DDR instead.

Re:And that's not all...

[Anonymous Coward]

Is DDR's latency significantly different from SDRAM? I thought SDRAM would have lower latency, if anything...

Re:And that's not all...

[SK-null]

I'm not sure but I think DDR-SDRAM should have half the latency as tradicional SDRAM.
They have more or less the same architecture but DDR-SDRAM tranfers two bits per cycle while SDRAM only tranfers one.
RDRAM also transfers two bits per cycle but has a completly diferent architecture.

Overclocking

[TheQuantumShift]

Is this needed? I mean seriously needed. I saw the benefits a few years ago in getting higher speeds out of celerons, but mother of god, are you seriously going to notice a difference overclocking chips that are already at 2000 or so Mhz? I'm not saying it's a bad idea, but why take life off your cpu(s) when you don't need to? I don't know about most people, but I can't afford a new $800 chip every 4 or 5 months. Hell, I still can't afford to upgrade from my dual pentium pro's...

Re:Overclocking

[TheQuantumShift]

Damn, it looks like I forgot the standard "Gee, can't wait to see a beowulf cluster of these running linux..."

Re:Overclocking

[BWJones]

When performing calculations that can take hours or days even, an increase in performance of even 10% can result in significant time/money savings. There are those mid level workstation users (like me) and high end users that can and do need every last bit of performance they can get. At this level, a few hundred $$'s every few months is nothing.

Hell, just the yearly support costs of a single SGI Octane are such that I could afford to purchase a new Macintosh G4 with a flat panel yearly for what it costs. So buying a new $800 chip twice a year does not even make me blink.

Re:Overclocking

[Anonymous Coward]

It makes a difference when you encode to/from DivX. And that's pretty much it, since computers used for actual heavy number-crunching purposes aren't made by intel.

Re:Overclocking

[ergo98]

What proof is there that overclocking lowers the life of the chip beyond its likely gross obsolescence anyways? I have a Celeron "450a" (300 overclocked 50%) that ran fabulously for a couple of years, including increasing the voltage 50%, and it's still working 100% as well as a test machine (despite the fact that the market value of the chip now is in the very low 2 digits).

Re:Overclocking

[adadun]

When performing calculations that can take hours or days even, an increase in performance of even 10% can result in significant time/money savings.

I was under the impression that an overclocked CPU usually ran rather flaky with spurious crashes and lockups. Do you really dare to run calculations that take days to complete on an overclocked processor?

Re:Overclocking

[TheLink]

huh? If you are really doing calculations that cost so much, I think you wouldn't want to overclock. Just buy the fastest, or if already at the fastest, hopefully you can do some parallel processing.

You won't save money by spending days to get the wrong answer :).

Only way is if you can certify and test the overclocked chips yourself thoroughly, however that would mean spending more money AND time. And when it comes to time, by the time you're done with those thorough tests, a faster chip may have come out :).

So it only makes sense in rare cases. Or for overclockers who don't care about correct results.

If 100% correct results don't matter, might as well ask an experienced person to guess :).

Re:Overclocking

[linzeal]

Burn in programs that can test the entire system for failure (processor errors to memory errors to etcetera) from overclocking are usually run on any machine before it is "blessed" for production work.

Re:Overclocking

[BWJones]

It depends upon how much you are pushing your hardware. If you have to resort to liquid cooling etc... you are either running Crays at the really high end (some Cray models are cooled internally by a fluorocarbon that actually bathes the CPU's and bus boards believe it or not) or pushing Intel/Motorola/AMD/IBM level stuff to levels I am not comfortable with. Modest overclocking/CPU upgrades can help considerably with reliable performance and no statistical data corruption depending upon the application.

For instance, I remember when I was an undergraduate, my stock Macintosh IIci would take three days to complete a series of calculations I was working on for a stroke study. Bumping up the performance just a bit by mild overclocking cut about 7 hours off of that calculation. I ran this machine overclocked by about 15% for almost five years after as an image capture/file serving machine before finally retiring it to a friends son. That kid used it for another two years before giving it to his sister who finally upgraded a couple of years ago. Last I heard it was still running in overclocked form as a web camera server in a biology lab.

Re:Overclocking

[BWJones]

See the above reply. As for purchasing the fastest, there are times when the fastest is considerably more expensive and performance approximations can be had by building/modifying lower end stuff. For instance, a SGI Octane runs anywhere from $35000-$50000. Going to the next level is considerably more expensive than that. There is some code that is only available for SGI and for that you run the SGI hardware. Other software can be run on cheaper hardware such as Macs or Intel/AMD. The performance of those boxes is typically lower than that of the SGI in some tasks, but can somtimes be overcome by mild overclocking.

Clustering is another potential solution, but one needs specialized code for most applications and benefits or solutions can often be very problem specific. Clustering code that is easy to use and adaptable to various problems could be incredibly useful here. See http://exodus.physics.ucla.edu/appleseed/appleseed .html for some easy to use clustering solutions on the MacOS. Low cost Linux clustering solutions are also available.

Re:Overclocking

[Anonymous Coward]

As near as I figure, most people that are running high end machines where every second counts, probobly aren't using pentium processors, but maybe I'm wrong.

As for everyone else and the consumers, this really seems like a waste, it's only 10% more, which you probobly won't see due to slow bus and of HD transfer rate. And since most consumer's computers are not optimized for optimum performance, the extra speed would probobly be lost in the OS. Besides, most of us never even use our processor to the max anyways.

Finaly, I don't see the bennifit of newer procesors when we haven't even taken out curent designs and pushed them as far as they will go.

Re:Overclocking

[WhiteKnight07]

If you need to perform those sort of complex calculations just buy a Tyran Thunder and drop in a pair of AthlonXP 1900+'s and go. Screw the P4, the Althlon is faster and cheaper. As for large compiles, thats mostly a factor of disk speed, go RAID or SCSI or preferably, both.

The jist of it is this: Intel has made a slightly faster P4, but the Athlon is still faster, so, who cares?

Re:Overclocking

[Alan Partridge]

why not just shell out $150 on an 1.33Ghz Athlon T'bird then? You'll get about 80% of the performance of the P4 in the article for about one sixth the cost. We got our 1900+ XP for less than 300...

Re:Overclocking

[Alan Partridge]

even a quad CPU Octane is feeble compared to the latest x86 and PPC chips when you're talking about raw number crunching. What the Octane has is BANDWIDTH, which makes it a great 3D or video workstation - take a look at the distributed.net client database for a look at where the various architectures are at now, you may be surprised at the astonishing speed of the G4 in RC5-64 or the sheer horsepower displayed by the Athlon in OGR.

Re:Overclocking

[Hoser McMoose]

The obvious answer is that people don't overclock because they need more CPU speed, they overclock because it makes them super-kewl with all their script-kiddie buddies! Or perhaps it makes their penis larger or some such thing. Some people overclock their systems for mostly the same reasons why a lot of people put special high-performance parts in their cars, not because it does anything really useful for them, but because it's a hobby.

Re:Overclocking

[SHiFTY1000]

In the 70s, guys "overclocked" their mustangs and camaros. Same thing, really... I still use my celeron 566 @ 850, saved me a fortune when it was new. Hopefully the new tualatin celerons with 256k cache are as good overclockers as this p4... What can i say, im a sucker for Intel.

Re:Overclocking

[BWJones]

even a quad CPU Octane is feeble compared to the latest x86 and PPC chips when you're talking about raw number crunching.

You mean simple iterative number crunching. In this case, it is true. For these tasks the dual 800 Mhz G4 running OSX is quite fast as is a dual P4 or single Athalon. However, when computing problems with significant matematical interdependancies that require more information to be driven through the pipline at once, the dual R12000's of the Octane @ 400 Mhz are damn hard to beat for a workstation.

Apple does not yet have the hardware (or software developers) to make me move completely over, but OSX is sure attractive. Hopefully the G5 will shake some things up.

Re:Overclocking

[IAmBlakeM]

It 100% depends on your setup and the level of intelligence of the overclocker.

If you take a bunch of cheap, bargain basement systems in cramped mini-towers with few or no case fans, then decide to run PC133 RAM at 150Mhz and run at 1Ghz system at 1.2Ghz, you will obviously freeze up.

When you get to nice systems, spacious and roomy cases, quality heatsinks and a case fan or two, you can easily run an Celeron 1.2Ghz Tuatulin 1200 at 1500, or in my case, you can run a 900 Athlon at 1.12Ghz and have your PC133 RAM running near PC2100 DDR speeds and see a 25% increase on your MIPS/MFLOPS for basically pennies on the dollar.

Buy a couple of steps below the current "top end" systems, spend $40 on a case fan or two and a decent heatsink and you'll be able to meet or beat the performance of those top end machines.

I'm not really sure why overclocking doesn't show itself more in the corporate enviroment. *shrug*

Re:Overclocking

[Anonymous Coward]

Er, not exactly the "same thing". The folks with the uhh, "overclocked" Mustangs and Cameros were getting laid by pretty young coeds, while you nerds with your overclocked CPU's will have to settled for the lovely coeds at http://thumbnow.com/

Re:Overclocking

[cowbutt]

When performing calculations that can take hours or days even, an increase in performance of even 10% can result in significant time/money savings. There are those mid level workstation users (like me) and high end users that can and do need every last bit of performance they can get. At this level, a few hundred $$'s every few months is nothing.

I agree with your VFM argument, but surely, if you're performing calculations that take hours or days (weather forecasts, biotech, scientific research, nuke simulation), they're likely to be important enough that you'd like to have confidence that they're actually correct, rather than save a few bucks/hours and run an overclocked system, right?

--

Re:Overclocking

[BiggyP]

most of these k1ddies get their little friends round to see their new overclocked hardware, and stare in disbelief as KDE locks up on Corel linux 1.1, and their windows ME partition gets eaten for no aparant reason leaving them with no hope of getting online to check their AOL account's email.

Re:Overclocking

[3rd_Floo]

Yo do mean that with the yearly support costs of that SGI Octane (or at least I know with ours) that you could buy 10 or 12 of thoes flat panel Mac's right?

Re:Overclocking

[Anonymous Coward]

Why the heck worry about the life of your CPU unless you burn it out before you plan on getting a new system, because even if you do burn it out in a year, you'll either be able to buy a newer, compatible, FASTER version or the replacement will be dirt-cheap.

Re:Overclocking

[systemBuilder]

Yes, if an engineer makes $50 an hour, if you can save the guy 6 hrs/yr over the course of a 3-year product cycle (0.3% of the year), you have paid for a $1000 chip. The economics are compelling.

Of course, once you install Windoze 2K01XP, you've blown all the savings that Intel sweated so hard to produce ...

Re:Overclocking

[AHumbleOpinion]

Burn in programs [demon.co.uk] that can test the entire system for failure (processor errors to memory errors to etcetera) from overclocking are usually run on any machine before it is "blessed" for production work.

Such programs are useful for the more severe overclocking induced errors but they miss the more subtle ones where the cpu simply gives a wrong answer. These subtle errors are sometimes dependent on particular code sequences or data patterns. These necessary condition vary and are unpredictable, they don't lend themselves to the testing you describe.

Re:Overclocking

[linzeal]

Actually some of them can check for single bit errors by executing a known set of instructions over and over and comparing the results.

Re:Overclocking

[AHumbleOpinion]

There is no "known set of instructions" to test against the more subtle end of the error spectrum. The instructions that fail and the required conditions (such as operands with particular bit patterns) can vary from one individual CPU to another. Beyond these errors there may be weaknesses that a particular design or stepping is vulnerable to. A "known" test may be useful for only these later cases.

What's the point?

[werve]

Does any one really notice the difference in speed between even 1.7GHz and the 2.0Ghz? I know it will scrape time from a kernel re-compile, but what non-IT consumers care about this? Especially considering you can get a dual 1.3 GHz celeron system for next to nothing.

I think Intel would make more money by even lowering prices even further and offering P4 SMP (non-Xeon) - they'd sell more chips... and make me happier ;-)

Re:What's the point?

[Anonymous Coward]

why would you even want a dual celeron system when you get a plain ol' 1.3 GHz celeron/duron for even less and most people will experience the same performance.

Re:What's the point?

[Anonymous Coward]

High-end improvements also upgrade the hz/$ for the low-end. This alone makes it worthwhile to the average consumer.

Re:What's the point?

[werve]

I agree! All I meant was that even techies (like me) can be satisfied quite cheaply with a dual celeron system. Mum and dad should be quite happy with a single 1.3GHz celeron.

Unless of course you are trying to get 400fps in Quake 5 - then you can justify the 6-way P4 system...

Re:What's the point?

[Steve Cowan]

The point? Hmm, leave it to an IT guy to think only IT guys have use for processor speed.

Some reasons for those extra 300 MHz: 3D rendering, MP*/QT encoding, video transition rendering, image manipulation (rotate a 20 meg image clockwise 1 degree anyone?), audio DSP, and making Windows not seem sluggish.

Re:What's the point?

[xted]

Taking a chip .3 ghz higher than its factory clock will show a difference in speed.. And there is a l33t factor involved in this. Its kind of like putting a $5000 stereo system in an $800 car. People like to get the most of their rigs.

Re:What's the point?

[mlk]

Mircosoft Windows XP?

Re:What's the point?

[Anonymous Coward]

Why would you even want a celeron?! eewwwwww....

Re:What's the point?

[zmooc]

You're absolutely right; nobody needs more than 640K RAM too....

The usage of computers changes along with the possibilities and there's still a lot that's not possible. Think about photo-realistic realtime interactive movies (have you seen the latest Chemical Brothers video-clip "Star Guitar"? THAT's what I want to do in realtime and interactively), multi-track samplers that can do a lot of effects without any latency, predicting the weather more exactly without the use of what we call supercomputers nowadays, SETI, simulations of large neural networks etc. etc. That's why we need the Hz's, not for the stuff we we're doing nowadays. As long as I cannot easily create my own Hollywood-production in 16384:1024 with 16-channel sound on my desktop, create the soundtrack for that with a software sampler with professional quality (latency) etc, we're not there yet.

Re:What's the point?

[FFFish]

We all want to do that. But the make-or-break point isn't going to come at the difference between 1.7 and 2.0GHz, or even 1Ghz and 2.5GHz.

IOW, spending twice as much isn't getting you twice the performance... and it's usually not even getting you a substantially appreciable difference in performance.

IMO, the bottleneck these days isn't so much with the CPU as the busses.

Re:What's the point?

[Anonymous Coward]

You can run Celeron II in dual?? got a link for that? last time I checked, Celeron II weren't SMP enabled... I'm still on a dual Celeron I overclocked to 550mhz

Re:What's the point?

[Glytch]

Actually, overclocking one of these babies is more like strapping a Saturn 5 onto the back of an Energia.

Re:What's the point?

[zmooc]

The Ghz-increase that we are seeing with CPU's now has indeed totally left the bus-, memory- and storage-speeds behind, but we'll still need to have fast CPU's. So indeed, at the moment there's not much use for such fast CPU's since the other components are just too slow, but they will catch up. What I was trying to say is that it's a bit narrowminded to say that we don't need such fast systems because the applications we use nowadays don't require them. I didn't mean to say that such speeds have any use for the `normal' user nowadays.

...and...I'm pretty sure there are numerous applications nowadays that DO benefit from such fast CPU's. For example lower latency in music-applications while being able to use a lot of effects [with changing parameters] in realtime at the same time. Such applications will benefit a lot more from fast CPU's than they benefit from faster memory...as long as there's enough cache.

Re:What's the point?

[werve]

Yeah, yeah... I understand all that - my point concerned the average consumer, not the geeks. I'm really just commenting that the speed at which processors are increasing in performance is outstripping the applications. Although Microsoft is working hard to slow things down (:-)) there isn't much justification for the increased speed.

I work for a company that does software development (Java, C++, VB etc) and we have PIII 933MHz PCs as standard - even though everyone here would love a 2GHz machine, there really isn't much commerial justification for spending the money.

Re:What's the point?

[not_cub]

Does any one really notice the difference in speed between even 1.7GHz and the 2.0Ghz? I know it will scrape time from a kernel re-compile, but what non-IT consumers care about this?
On the contrary. I think most non-IT consumers will care about it. When I walk into a consumer electronics store to buy, say, a stereo, all the components have little tags on them with meaningless quantifications like "frequency response: 20-25000hZ", "power output: 240W". These numbers are all meaningless. They will not have been measured in a meaningful way (most likely the power output is measured across a resistor than the speakers themselves). There is no mention of whether it sounds good qualitatively. Everything in the shop probably sounds terrible, compared to an audiophile hi-fi.

Similarly, your average punter in the shop on a Saturday to buy a computer because he read so much about the internet, or because he thinks he should get one for his kids, is going to look at the first number past the first bullet point on the thing and buy the one with the biggest number. This is why Intels policy of cranking up the number as high as possible with the P4, and not worrying about actually making it go faster, is such a good marketing move.

not_cub

Re:What's the point?

[tunah]

Especially considering you can get a dual 1.3 GHz celeron system for next to nothing.

Where from? I'll take 5!

Why do I live in NZ :(

Re:What's the point?

[archen]

Personally I really don't care about processor speed any more. My 1.4Ghz Athlon is plenty fast for me. But keep in mind that the processor does a lot more than it used to. Pop open my Pentium 133 and you find a LARGE card for just about everything. Nowdays you get these skimpy little cards that make the main CPU do everything for them.

But really, if someone gave me the option of a 10Ghz computer, or a computer with twice the bus speed/bandwidth - I'd take the better bus any day.

Re:What's the point?

[Anonymous Coward]

I don't think that was the point. Sure technology will advance, but I think the ones that really need it should be the ones paying for it, not those that think they need it because it's out and that they have to be the coolest geek on the block in getting it.

I think the point is that people get so starry-eyed by the "latest thing" be it a 10% CPU performance increase that they'd blow last week's pay check to be the coolest dork on the block or whatever just for quickly fading bragging rights. It's a lot like the people that would pay 2x the list price to get a new Thunderbird or VW New Beetle just to have one before anyone else.

Re:What's the point?

[Anonymous Coward]

The Celeron 500A and up don't do SMP. At all no matter how nicely you ask them to.

Re:What's the point?

[SHiFTY1000]

its progress!!! and just think about the low-end (celerons) that are going to be available soon... i hear the tualatins on the same 0.13 process are great overclockers, and finally have a 256k cache, meaning they are as fast as todays p3.

Re:What's the point?

[CTho9305]

True, but think about the cards that have grown and shrunk. Winmodems aren't especially much of an issue on a modern CPU. Any features for a sound card that may have at one point been hardware are also most likely simple.

However, the graphics card has drastically improved - from a mere framebuffer + ramdac to an actual processor, even a (somewhat) programmable one at that. The off-loading of graphics processing more than compensates for other cards moving to software.

Re:What's the point?

[Anonymous Coward]

What's the point? A single Athlon 900 will still perform up to the same standard, for about three quarters the price.

Re:What's the point?

[ajs]

The point? Hmm, leave it to an IT guy to think only IT guys have use for processor speed.

3D rendering, MP*/QT encoding, video transition rendering, image manipulation (rotate a 20 meg image clockwise 1 degree anyone?), audio DSP, and making Windows not seem sluggish

3D redering -- Speed comes from RAM, video hardware and bus speed, these days, not CPU speed.

Video -- Hardware video decoders are a must. Why would you want your CPU to grunt over decoding video?!

audio DSP -- Been done in commodity hardware since the early 90s....

Making windows seem ... not windows -- Been done by installing Linux since the mid 90s.

Re:What's the point?

[Anonymous Coward]

because you're a sheep rooting hippy my good man. a sheep rooting hippy.

Re:What's the point?

[FrostedChaos]

Why have a fast CPU? Well...

3D rendering speed depends on a lot of things, but CPU speed IS one of them.

He wasn't talking about "hardware video decoders for DVD." He was talking about encoding divX files... which is still done by CPUs these days.

Audio DSP... well, ok... that's not a problem.
Increasing the speed of windows... well, as long as you can run win2k/NT, you're all right. Anything less will crash every 3 hours (approx), and anything more is just a waste of money.

Believe me, in the future you will see applications come out that require fast processors. But it probably won't be as urgent to upgrade as it was in the 386 days.

Re:What's the point?

[Anonymous Coward]

Celerons above 533mhz have dual capcity disabled

Bah

[Anonymous Coward]

Story posted 2 minutes ago, server is hosed already.

Maybe they need to quit talking about the P4 and pop one in their server already?

Surest sign of obsolescence

[tunah]

Now I *know* my computer is obsolete: my CPU speed is just the difference between reccommended and possible clock speed settings on the new one.

Re:Surest sign of obsolescence

[Anonymous Coward]

I feel your pain: my primary computer's clock frequency is the difference between two official speed grades (Pentium Pro 200). Perhaps it's time to upgrade; it is starting to show its age after almost six years!

Re:Surest sign of obsolescence

[Anonymous Coward]

*Mine* is probably less than the difference between those two speeds for *your* chip.

What's the next thing below 'obsolete'?

Re:Surest sign of obsolescence

[bn557]

Paper Weight is commonly used. Target Practice is a good one also. I use mine as a space heater(a pentium 90, one of the ones that runs at around 800K)

Pat

Re:Surest sign of obsolescence

[TheLink]

Heh my p166 is running even slower than the bus speeds nowadays.

But I guess it's definitely worth considering an upgrade when a new cpu's frequency variations/fluctuations would be larger than my old cpu's clockspeed :).

e.g. Chips running at 40GHz plus minus 0.5%...

Re:Surest sign of obsolescence

[dynoman7]

mod this up, please...its funny (sad but funny ntl)

Re:Surest sign of obsolescence

[The Fred]

How about the fact that there are PDA's that have more raw processing power than your boxen?

Re:Surest sign of obsolescence

[Anonymous Coward]

When people use "boxen" they are trying to make a neat-/German-sounding plural of box (apparently "boxes" isn't good enough). Because the parent to your post is only talking about one computer, your "boxen" is completely unnecessary and stupid.

Uses RDRAM

[PoiBoy]

One major pitfall of the these new chips is that they use RDRAM, which is dramatically more expensive than plain-vanilla SDRAM. In fact, for the consumer market (including gamers without a ton of $$$), I think they've really got to start paying attention to memory prices--lots of RDRAM can blow the budget as fast as anything.

Re:Uses RDRAM

[Glonk]

That's not true, they use RDRAM or SDRAM or DDR SDRAM. In fact there's a brand new artice that benchmarks them all.

Take your pick of RAM (although RDRAM and DDR are the only real choices).

Re:Uses RDRAM

[Anonymous Pancake]

Actually rdram isn't that expensive anymore, and you shouldn't compare it to sdram.. sdram is obsolete. Ddr ram is the closest competitor, and it's price is now on the rise, and not that far off from rdram's price anymore. Lastly, p4 systems run best with rdram, even ddr speeds are not as good with it. So rdram is not that bad at all, besides the rambus' obviously screwing legal practices.

Re:Uses RDRAM

[aka-ed]

Ddr ram is the closest competitor, and it's price is now on the rise

That depends on the configuration. I've been watching the pc2100 512mb sticks go steadily down toward my price range, haven't seen a single uptick yet.

Re:Uses RDRAM

[llzackll]

Then you obviously haven't looked at the prices in the last week or so

Only 2.5 Ghz?

[Deltan]

Some people have had that little gem up to 3Ghz. Not exactly in English, but pictures say a thousand words.

Re:Only 2.5 Ghz?

[minusthink]

well I see the screenshots, but where are the shots of the processor melting into the pcb.

Re:Only 2.5 Ghz?

[archen]

They were afraid that if they took the fans off, that they couldn't run away fast enough.

Re:Only 2.5 Ghz?

[idealego]

And some people are calling it a big overclock. I still have a celeron 300 running at 504 in one of the systems here, that's a 68% increase. 2.2->2.5 is a mere 13.6% increase. I've heard of the 2.2's running at 2.8 which is still only a 27% increase.

2ghz != increased performance

[Horse Cock]

Really, does anybody really need a faster processor? They really should concentrate on increasing the size and speed of the data bus, rather than increasing the speed of the processor.

Re:2ghz != increased performance

[Glonk]

Yes, of course we need faster processors. Not only does it bring down the cost of the mainstream processors, but you always need more power. Always!

The big deal here isn't the 2GHz anyway. 2GHz has already been done, the big deal is the new core. The Northwood core is the first Pentium 4 chip to use copper interconnects instead of aluminum, it's much smaller (read: cheaper to make), it runs cooler (2.0GHz ran at 31C maximum temperature, overclocked to 2.5GHz it was 41C max temp). And it can clock much higher.

It's the new core that matters, not the speed (although Northwood is debuting at 2.2Ghz...)

Re:2ghz != increased performance

[jkc120]

Not to mention the increased 256k of L2 cache. That will help performance seemingly.

Re:2ghz != increased performance

[Inside_Joke]

With this new core, you can expect the Northwood to hit 3 GHZ before long. My guess would be Q1 '03.

And like what was just said. You ALWAYS need more power. If you think you have enough, you don't. If you think you've got a little too much, you don't have enough. If you think you've gone WAY overboard, you might have enough.

Have I mentioned that I want one?

Re:2ghz != increased performance

[kawaichan]

Also, it's based on the .13 micron process, 512k cache etc. not all that impressive, this should've been P4 right at the beginning.

Heheh

[Cave Dweller]

"It overclocks like a hog..."
LOL, I've never seen an overclocked animal :)

Re:Heheh

[dzym]

Maybe it's like what McDonald's do to their animals.

Re:Heheh

[Anonymous Coward]

Look for the hogs waving glowsticks.

Re:Heheh

[mlk]

Mix them with paper?

versus G4 1.6GHz

[Anonymous Coward]

I wonder how this will compare to the 1.6Ghz G4 Apple will announce tomorrow. The new G4 could do ~17MKeys/sec for rc5, but it seems distributed.net has disabled reports on that part of the stat engine since it was reported on http://www.insanely-great.com/ last night (which is now no longer reported there either).

Apple will also release a 1.0GHz G4 and a Quad G4 866MHz.

These could be Intel beaters (finally!)

Re:versus G4 1.6GHz

[Anonymous Coward]

when I see it i'll believe it. thats one HELL of a jump in clock speed

Re:versus G4 1.6GHz

[Anonymous Coward]

How is it that big? If the technology already exists, it's a matter of integrating it with the Macintosh style, RISC code and all that other jazz. Besides, the really problem with Mac processors comes from motorola not bumping up the speeds the way they should. IBM had much faster PPC processors than motorola, but since the main contract lies with motorola, the IBM ones were held back

Re:versus G4 1.6GHz

[Anonymous Coward]

this page lists a G4 at 1.6Ghz, but remember, this is user-entered data, there is no verification.

Re:versus G4 1.6GHz

[Hoser McMoose]

I'd bet just about any amount of money that this "1.6GHz G4" is really a dual-800MHz G4 that someone (totally incorrectly) assumed was the same thing as a 1.6GHz processor.

Like a what?

[Davorama]

I'm trying to get a visual around "overclocks like a hog" .... What's up with that?

Give it a week....

[happyhippy]

and a faster one will be out

Apples for

[el'gwato]

Apples for apples, I'm not going to throw away my Athlon!

printer-friendly article

[Anonymous Coward]

Here's a printer-friendly version of the article, which is easier on the viewer and the server.

Do they edit these things?

[Jennifer Ever]

Not to be too nit-picky, but if I have to read one more hardware review that sounds like it was scribbled on a napkin by a 9th grader with ADD while watching Moulin Rouge, I'm going to scream.

"While basically matching the Pentium 4 on a performance level, albeit not even close on a clock-to-clock level."

Well said! It's a good thing you know how to make bar graphs.

Re:Do they edit these things?

[Jennifer Ever]

How exactly is the quality of the review in question off-topic? Presumably, the benchmarks and whatnot are all valid, but for me, anyway, when there are some pretty obvious errors in the text of an article, demonstrating that it probably hasn't had any sort of review or gone through any sort of editor, it raises some questions about the integrity of that article as a whole. Who is writing this, and why isn't anyone else reviewing it? I'd rather not make hardware purchasing decisions on the advice of an unprofessional hack who has never heard of proof-reading.

what?

[bluenirve]

Here I am, just comming back from a week vacation, and they can make 2Ghz chips already? When I left, the best I could get was a 266Mhz!

Re:what?

[Anonymous Coward]

nice vacation! significatn chunk of my lifetime ;)

Re:what?

[ThatComputerGuy]

wtf, a week vacation? dude, I don't get it.

Even quicker than 3ghz !!

[sh0rtie]

now even quicker !! this page claims it has a world record

3023mhz !

Re:Even quicker than 3ghz !!

[ThatComputerGuy]

I dunno, the page that page links to now claims 3110MHz.

Of course, right above that image there's a link to supposedly 3150MHz.

Re:Even quicker than 3ghz !!

[Anonymous Coward]

According to the screen shot in that link they're not even using a Northwood. It listed the L2 cache as 256, and Northwood has a 512k L2.

Re:Even quicker than 3ghz !!

[theSprocket]

yeah, well i've got one that runs at 6.1 gig. Pictured here took me only about a minute to build the whole thing, in PhotoShop that is.

Thank heavens!

[Dog and Pony]

That it is possible to overclock... who could live with a bare 2GHz? Not that I would know, fastest I have accessible is 1GHz. :)

2 Ghz CPU or marketing BS ?

[J.D. Hogg]

Richard, Intel's VP of marketing : John, we need to produce higher gogohertz CPUs, other CPU manufacturers are creaming us right now.
John, Intel's VP of engineering : You mean "gigahertz" I 'spose : well, we can't, CPU core designs are reaching their limits. Technically, it's not very realistic you know.
Richard : Who's talking about technical stuffs here ? I mean, just crank up the gogohertz man, we need more hype fast.
John How about if we designed synchronous processors instead ? now *that* would be sexy.
Richard : You mean hotter than more gogohertz ?
John : Sure, it would impress the technical crowd, and we'd have a real actual breakthrough in CPU design in less than 5 year. That's pretty hot, I'd say.
Richard : Yeah, well, tech people are nice, but the Joe Sixpacks who walk into Fry's and buy a new PC, they want more gogohertz.
John : *sigh* Well, I guess we could double the clock and put a frequency divider inside the CPU ...

etc ...

Re:2 Ghz CPU or marketing BS ?

[willum448]

not to flame, but is Fry's really a Joe Sixpakish store, i've only been there once :( and it seammed to be a mostly techy crowd. Or mabye its cuse it was in the valley...

Re:2 Ghz CPU or marketing BS ?

[J.D. Hogg]

"not to flame, but is Fry's really a Joe Sixpakish store"

Well okay, CompUSA then :) You're right, I spoke too fast : Fry's is actually very nice and reasonably technical.

Re:2 Ghz CPU or marketing BS ?

[linzeal]

No people that go there only act technical. I was a saleperson there once a long time ago. Its like people going to any specialized store they like to pretend like they belong.

Re:2 Ghz CPU or marketing BS ?

[TheLink]

I dunno, I was at the women's underwear department the other day. I sure didn't bother pretending that I belonged :).

Re:2 Ghz CPU or marketing BS ?

[Anonymous Coward]

Try any of the non California stores. Such as the ones in Texas. Its more like a Walmart than a computer store. I hate listening to the mindless technobabble of the unknowing customers. "Yep, the more PCI slots you have, the more RDRAM you can slam in there!"

Duh!!

Re:2 Ghz CPU or marketing BS ?

[linzeal]

Yeah but if you go there you most usually say that you are buying it for your girlfriend not your mom or yourself ;) Of course in the last case you probably would belong there more than the other two ;)

Re:2 Ghz CPU or marketing BS ?

[aka-ed]

The real techies that do go to Fry's avoid the salespeople like the plague. Those guys will fight like sharks over a lousy 3% (or whatever) commision, and most are less knowledgeable than the customers (there are exceptions of course).

Re:2 Ghz CPU or marketing BS ?

[An Ominous Coward]

Intel's CEO has an engineering background, and he doesn't let marketing dictate technology. MHz certainly isn't the only issue with regards to performance, but neither is it a non-issue. The P4 is a very intesting chip due both to the technology that enables clockrate scaling and the technology that makes use of clockrate scaling.

Re:2 Ghz CPU or marketing BS ?

[caferace]

Whoa. Admitting that you were once a Frys "salesperson" on /. is pretty brave.

That being said, in 1979 I actually worked at a Radio Shack for a summer. Mmmmm. Batteries.

Re:2 Ghz CPU or marketing BS ?

[linzeal]

Well it was a summer job that paid for my first car. I felt pretty unwelcome and left for speaking out against sexual harrasement, my boss was soliciting sex from the cashiers for positions in the computer department. The place is run by coniving capitalist mormons, you have to watch out.

Re:2 Ghz CPU or marketing BS ?

[Anonymous Coward]

"coniving capitalist mormons"

Ah, did you mean morons?

Re:2 Ghz CPU or marketing BS ?

[yesthatguy]

Well, there is the whole polygamy thing in hitting on the cashiers. Maybe he's an outcast in Salt Lake City or something, and he really means Mormons.

NForce

[NitsujTPU]

Something tells me that the nVidia NForce chipset helped out in a few of those benchmarks. Still, the Athlon is quite impressive, and I have heard it will overclock all the way to 2.6 GHz.

Re:NForce

[talonyx]

Something tells me that the Nvidia Nforce chipset is not for Pentium 4 motherboards, but hey, it could be the voices in my head again.

Price vs Performance

[Alien54]

Normally I recommend to most people that they purchase one or two levels below the top level. I feel that paying maybe 50% to 100% more for maybe 5 or 10% performance increase is not really worth it, especially when waiting a few months will bring bring the processor within reasonable cost.

Otherwise I am spending thousands of extra dollars for the "blessing" of being on the bleeding edge.

I can see the need to shorten compile times, etc. especially for big projects. But otherwise I look at 'good enough"

Re:Price vs Performance

[RetroGeek]

I can see the need to shorten compile times, etc. especially for big projects.

Compiles of really large projects are disk I/O bound. A faster processor does not really give that much of a boost. Invest in a fast drive and fast controller. It will save more time.

Re:Price vs Performance

[Anonymous Coward]

You obviously have n't tried to compile mozilla then ? :)

Re:Price vs Performance

[Anonymous Coward]

"I feel that paying maybe 50% to 100% more"

But that is 50-100% more for the CPU, which is a fraction of the cost of an entire system.

Adding those few hundred bucks may, however, deprive you of the happiness having 768 MB in RAM.

Like a what?

[PeterP]

Are hogs known for their overclocking potential? Have I missed something?

YES WE NEED MORE CPU POWER

[ergo98]

Why is it that every story about ever increasing CPU speeds is met by about 50% postings claiming that such speed isn't necessary unless you "want 500 fps in Quake"? I've seen these sorts of posts since back in the BBS days when the new 486 came out, immediately to be met by 50 posts (usually by people who feel a need to justify whatever they own) claiming that "a 386/33 is more power than anyone needs anyways!". Bah.

There are countless benefits to the increased speed (and of course like always: Once you use a higher speed system for a while suddenly you notice, clear as a sunny day, that yes there IS a very noticable difference, and suddenly that previously adequate machine seems pokey), and if you don't realize what they are then continue using whatever it is you use, but save the "500 fps in Quake" rhetoric (here I am with what would have been a cutting edge machine one year ago and Operation Flashpoint runs with frame rates in the single digits, yet even still it isn't a fraction as complex of a "world" as it could be if more powerful systems were prevalent).

Re:YES WE NEED MORE CPU POWER

[archen]

True, but it also seems to me that processor speed is becomming more and more irrelevant. Sure it's faster, but can we even feed the thing anymore? We left the bus speed in the dust. RAM is slowly creaking along, and accessing the hard drive is an absolute catastropy in terms of performance. I'm sure the same people are bitching for the same reason that they've always been. But the way things are today; they're probably more right than they used to be.

Re:YES WE NEED MORE CPU POWER

[Jim Norton]

Well that depends on what you are doing, doesn't it?

If you are gaming, nobody is going to argue that a faster video card instead of a CPU upgrade is going to help you a lot more.

Re:YES WE NEED MORE CPU POWER

[ergo98]

Well my gaming comment was moreso directed to the flock of seagulls that likewise claim that a "GeForce 2 is more than anyone needs" (the exact same argument and technique as the CPU argument). Having said that: Games with greater AI and modelling of the real world (i.e. not a FPS where it's 96% graphics/4% computations), such as the example given (Operation Flashpoint), do beg for faster processors: In OpFlash the scope of a battle is heavily limited not by your video card, but rather by the CPU in your system. Falcon 4 from a couple of years ago simulated full-scale combat and as such still is begging for a faster processor on the fastest systems available.

2.5? Higher...

[Magus311X]

Try 2.8 GHz

Or why not 3.0!

-----

The CPU is only one contributor to performance

[DocSnyder]

When I bought my home workstation about three years ago, the CPU (K6-II/400) was one of the cheapest parts of it. What really made it powerful are the SCSI cache controller and a fast Seagate drive, as well as an adequate (for these days 128 MB were more than enough) amount of RAM. Of course it depends on what you do with your box, but to be honest, most of the time you're waiting for the harddisk, either for loading data or for swapping virtual memory.

Three years later, the only thing I added was some more RAM, with the rest of my workstation being the same. It is still very usable, and I rarely see the need for a more powerful CPU.

In contrast, my former office workstation was a P3-800 with 192 MB RAM (some of which to be "abused" for graphics), an IDE drive and a one-chip-does-everything Intel i810 on the mainboard. SETI was the only thing it could do faster. On pushing the IDE system or the network, sound playback got distorted, and the X server became quite unreactive, it even stalled for a few seconds. A compile run made it impossible to do anything different in parallel, so I would have needed two machines - one for compiling and one for the desktop.

AFAICT especially on Intel systems the trend goes towards integrated one-chip-does-everything systems like i810 and its successors, which can handle everything from graphics to sound to IDE to networking. Of course the Intel people want their customers to come back later, and save some money by using only one chip instead of several ones. Most users will think it's the CPU which is too slow... and buy a new 2 GHz monster with another i8xx-crippled mainboard.

Re:The CPU is only one contributor to performance

[Horse Cock]

Now, if you really wanted to get rid of that HD bottleneck, you could get a solid-state drive. I wish I had that kind of disposable income...

Re:The CPU is only one contributor to performance

[gpinzone]

You really don't need a solid state drive. Just give me a BIG RAM cache on the hard drives and it'll be almost as fast. I have a few 64MB PC66 SDRAM modules lying around. Might as well put them to some good use.

So what?

[JimE Griff]

I'm waiting until tomorrow. If Apple comes out with a g5 that's half what the hype of it is, all us guys with x86's is gonna look real stupid. Sorry to betray GOA (Grand Old Architecture), but I am interested in the best performance. I'm also interested in having money, so I run an Athlon.

Re:So what?

[Hoser McMoose]

If Apple's G4 had half of what the hype for it is, it would be twice as fast as it is now! Don't get me wrong, the G5 has some nice parts to it, but I don't expect it to be setting any records for raw speed by any stretch of the imagination. The raw computing power of the G4 is roughly comperable to an Athlon, clock for clock, and the G5 isn't likely to be any better (probably very slightly worse at equivalent clock speeds). Considering that it will only be coming in at ~1.5GHz by mid-year, that will put it as being about on-par with the slowest Celeron and Duron chips being sold at the time.

Steve Jobs does a great job of hype, and Mac OS X looks REAL nice, but really, when it comes to raw processing power, the G4 and G5 aren't the end-all be-all processors that many make them out to be. Anyone ever wondered why Apple/Motorola don't test these chips on ANY industry standard benchmarks, resorting only to some totally outdated "ByteMark" and the VERY easily manipulated Photoshop "benchmarks" (using the term loosely).

Re:Can you imagine...

[Codifex Maximus]

Why all they have to do is say that it's a PPC 2000+

Screw the MHZ hype.

[tcc]

Also To 2.8ghz

But now, a little rant...

Look at the next and last alpha that will come out, it will SMOKE at a fraction of the speed the P4 will be at the end of the year. That's what I call going out with a bang. It's a shame such a technology got obliterated in part because of Intel's markettign muscle, we're going to be set back for 2 years for them to catch up on this technology and performance (they've got some alpha people in their staff now that will teach them how to do more than overclocking and recycling like putting SMT on chips for example, that will be one great leap, it's in at least one of the northwood flavor I think).

Watch out for the Hammer when it will come out, it still going to beat intel's latest offering mhz per mhz in desktop performance (can't speak too fast about the server side though.)

Look at the PowerPC, as much as I hate apple's hyping to keep their blinded userbase into beleiving that they hold the only computer that should exist on the surface of the planet, the powerPC architechture has proven itself to beat the crap out of Intel mhz to mhz side to side (and no I am not talking about that "hey loading an image in photoshop on the mac is 2x faster than on a PC, but I won't mention that it's totally unrelated to the CPU and the mac is running on a SCSI cheetah while the PC was running a 5400 rpm 5 gig drive", I am talking about rendering on different crossplatform software like premiere, lightwave, maya, etc).

This goes without mentionning SUN or MIPS or any other cpus on the planet that has interresting technologies ASIDE FROM CLOCKSPEED.

So again, Screw the MHZ hype, I am a power user, I love doing 3d rendering, I administer a small renderfarm at work, I love raw power, anything that comes out and had a power factor gets my attention, it's nice to see stuff running fast, but I am not impressed at ALL with the MHZ hype. Especially for the PRICE you have to pay to cover all the media and marketting hype... Intel's Hype tax like I often call it. Also, what you see is the MHZ going skyrocket... How much do you thihnk they had to cut in the design so that it stays that stable at these speeds? why do you think the athlon4 can't run at 2.2ghz? design.. intel had to cut in some places so the cpu could be easily cranked up that much, they had to redesign part of it, and that's why you need SSE2 optimisation and the pipeline for standard FPU is so bad. It's not because Intel doesn't know how to design a FPU, it's because they HAD to cut on it...

My precision 530 workstation that runs dual 1.7ghz P4 for the price I payed, I find a dual AthlonXP or MP 1900+ far more impressive for 1/2 of the price. Heck, you want to be in the cool factor? get a Dell 8100 with DVD/CD-RW Geforce2Go 32megs and 1600x1200 15" LCD screen, now THAT'S a nice little piece of technology. And quake plays soooo smooth on it... I won't waste my personnal money or blast my budget for a chip that can generate small blackholes because of it's so great CLOCKSPEED. Gimme raw speed at a decent price. For the price you'd pay that northwood alone you could probably get 2 athlonXP and it's mainboard that beat the crap out of the P4 for the same price of the cpu alone.

enuff :)

Re:Screw the MHZ hype.

[Anonymous Coward]

You're claiming that a Sun CPU would be as fast as the one this article is about? lolz@ultrasparc

Re:Screw the MHZ hype.

[Anonymous Coward]

You compare MHz to MHz... why? Why not compare performance per dollar? I mean, I think my Amiga 500 still kicks butt with what it can do with 1MB RAM and a 68000.

If Athlons can beat Intel MHz for MHz when they're at 1.5 GHz and Intel's at 2.5 GHz... so what? AMD's certainly taken the heat crown away from Intel, and it looks like it's not changing hands anytime soon.

Get a grip. Real world buyers talk about price/performance not performance/MHz.

Re:Screw the MHZ hype.

[cgleba]

I by no means an expert in this area at all, but after hearing the death of the Alpha in favor of the Itanium and the fact that people buy P4s purely because "they have more megahertz" I bang my head on the desk asking why why why did I waste my life away taking Logic Design, Computer Architecture, Mircoprocessor Operations, etc in college.

I should haev taken a few marketing courses instead. They would have been more applicable to today's processor market and I could have gone to parties, drunk beer and relaxed instead of filling entire notebooks with K-maps :(.

Obligatory...

[gooberguy]

Could you imagine a beowulf cluster of these?

I really get tired of people who say that.

D/\ Gooberguy

Tests give the pentiums the benifit of the doubt

[masteroveride]

In the articles, the tester admits to having the SSE-2 patch installed on all the machines prior to the rendering test in Photoshop. Even with the advantage to the Pentiums, the athlons still beat them out. Not to mention that in the other benchmark tests (IE: quake 3) are specially optmized for the Pentium. I give credit to the review in the fact that they are giving the honest results, but this is far from impressive coming from intel. It certainly won't want to make me buy a much more expensive Intel based system over Athlon for a few FPS in quake.

-Lance

Audio and Video

[mt404]

I noticed a marked increase in the number of virtual insturments and plug-ins I can run on my digital audio workstation (DAW) at home and another identical set-up, ave for the increased chip speed, at a friends studio. I see a definite market for the increased chip speed amongst people using PCs for intensive video and audio work.

Re:Application for new goatse.cx guy

[Anonymous Coward]

Sign me up!!!! :) -jonkatz@slashdot.org

Computer Musician? heaps of point...

[netsrek]

Man, I get so sick of watching it nerds saying the only use for a faster processor is to 'scrape time from a kernel recompile'....

If you're like me, and you make music with computers, and try and do it entirely with real time apps such as Reaktor, Max/MSP, Supercollider, software synths in VST/Logic, faster processors make a big difference... as most people these days are limited purely by their processing power.

If someone gave me some mythical 10 Ghz machine, it would probably only take me a week or two to get used to that being the bottleneck....

*Cough Cough*

[NitsujTPU]

I'm not trying to crack on the benchmark, they made some very valid conclusions and of course very practical ones, but it's a mark of the chips, not the graphics architectures.

nforce is not graphics...

[rebelcool]

nforce has nothing to do with graphics (well, aside from its agp controller...). it's a motherboard chipset.

Re:nforce is not graphics...

[NitsujTPU]

Right. I KNOW. Darnit. That's not the damn point... Forget it.

Re:Can you imagine...

[Anonymous Coward]

Some people actualy buy computers for more than the Mhtz. OS X is one very kick ass OS to be using.

Intel competition

[Anonymous Coward]

1.2, 1.4, and 1.6 GHz PowerPC 8500 (aka G5). Showed earlier today at MacWorld conference.

So, was it worth the wait? The hype? Independent benchmarkers will report, extensively, in the following days.

He meant an overbored Harley hog

[Glasswire]

(as above)

Intel's worst nightmare

[Anonymous Coward]

All the comments here along the lines of, "Does anyone really need this much speed?" (which I agree with, BTW) point out the Big Ugly Problem facing Intel: The industry has hit a plateau in terms of demand for horsepower. In a very short time the PC industry has converted from a "build out" phase to a maintenance phase, and that's very, very bad news for all the CPU companies, particularly Intel.

Everyone loves to talk about how much longer we can push Moore's Law, but no one seems to want to address the real issue--how much longer will demand for ever-faster PC's be high enough to fuel the ever-more-expensive development of those new CPU's? I think we're about to find out that Moore's Law was subvervient to the law of supply and demand all along.

Intel's other big problem is the IA64 and its hideous architecture that puts an amazing burden on compiler writers. Even worse, it's more than a little reminiscient of the IAPX-432 fiasco from a bunch of years ago, the last time Intel tried to introduce a spiffy, all-new architecture...

Re:Can you imagine...

[gcshaw2nd]

Rumor has it that Steve is going to pull out the big switcheroo. We'll see tomorrow I guess, but the rumor is that Apple is moving to Intel chips!

P4 vs Athlon - they Recommend P4 for gamming?

[musicmaker]

Even though it lost every benchmark except the Quake III one, and the 3DMark by a mere 2%. The small fact that DDR SDRAM is barely half the price of P4 ram, and the entire system is not nearly as expensive. They still recommend it for gamming? This is unabashed Intel hype. Not to mention all that wonderfull waste in the third ALU, poor design, and abysmal FPU performance. The P4 is a joke. Look at the performance improvements made by AMD when they moved to 0.13 micron. They improved the prefetch and release a truley better CPU. 'Intel - we inch forward - leaps and bounds and we could hurt ourselves!' The P4 has nearly twice the memory bandwith, >20% higher clock speed and it's still loosing benchmarks! Pathetic - utterly Pathetic.

Sorry - but I'm not buying Intel anytime soon.

Re:P4 vs Athlon - they Recommend P4 for gamming?

[ThatComputerGuy]

Well said, I was wondering about the same goddamn thing. Too bad I have no mod points.

Re:P4 vs Athlon - they Recommend P4 for gamming?

[KjetilK]

I guess most people don't read the whole thing, and I only read the last page, but what they say there is pretty much that you'd be better of with an Athlon XP, though Northwood is a nice CPU too. That's what I get out of it anyway.... :-)

Re:P4 vs Athlon - they Recommend P4 for gamming?

[m_evanchik]

Yeah, but Intel runs cooler and consumes less power. The first is important if you are running a critical server in a remote location, and both matter when you need to put the chip into a laptop.

The Athlon is like a hotrod; great when it runs, but unreliable for the long haul.

Re:P4 vs Athlon - they Recommend P4 for gamming?

[musicmaker]

I have personaly deployed over 50 Athlons in a remote server environment. We had very few problems with them. They run software that runs at 100% CPU most of the time because it's intense number crunching stuff. That's why we picked Athlon, it was the best performance price point by a long long way. Rack mount with a 3U/4U chasis and all the trimmings for a song. Besides based on the price, we can afford to have a redundant node if one fails because we didn't have to pay top dollar for P4. These boxes run 24/7.

I would have like Alpha, but at 12k a box. And not 10x the performance, it just wan't sane

.

Nessesary? Or just fun?

[MoneyT]

Does anyone besides me find it slightly disturbing that we now judge processors not only by the clock speed but also now by how far we can overclock them? It used to be overclocking was a hardware hack that only hardcore geeks did, just for fun and to squeeze a bit more out of their system. Now it's almost become standard, I can't wait to see do-it-yourself-EZ-Overclocking-kit bundled with overclocking for dummies on the store shelves. That and I really don't think 2 Ghz, espesialy from intel *gag* is a very good performance boost, even if the tests (which sorry to say can never simulate real life usage) show 10% more speed (only noticable if you push your CPU to the limmit, which mst of us don't do anyways). I'd prefer to see our current processors pushed all the way to their max before they redesign the processor.

Re:Nessesary? Or just fun?

[An Ominous Coward]

Yeah, damn those worthless benchmarks. What does a Quake3 test tell me about real life useage such as playing Quake3.

Re:Nessesary? Or just fun?

[Spazntwich]

My GOD, do you know ANYTHING about overclocking? If so, why are you afraid of it? You seem to have taken the attitude of so many 'wannabe 1337s' that "overclocking doesn't give you any appreciable speed benefit, shortens the life of your CPU, and is very difficult".

That attitude is WRONG.

Overclocking can be as simple as flipping a jumper on your motherboard (Jumper? Motherboard? I've never heard of those!!!) and changing ONE setting in your BIOS. In my case, this yielded me a 33% speed increase of my processor, took me about 5 minutes, and was easier than figuring out how to install Linux for the first time.

It's amazing that so many of the people here who can hack around with nothing more than a command line and mock know nothing windows users are so ignorant and fearful of something as simple as overclocking.

Re:Nessesary? Or just fun?

[Graymalkin]

You means a do it yourself EZ overclocking kit like the Turbo button on old PC/AT systems? Overclocking is a hardware hack only geeks did? Everyone used to press than little Turbo button and got the tiny speed improvement. Besides you push your processor to the max everytime you fire up anything bought from the Games section of Best Buy or Circuit City. Like the other dude said, how is a Quake3 test not indicitive of playing Quake3 in normal usage? Shit man, every increase in processing power means that 19" or 21" monitor you shelled out big bucks for just became more useful since you can run games at the monitor's highest resolution and really have a awesome looking game running. If that 10% speed increase means I can run a game I like well at 1600x1200 resolution or it takes five minutes less to composite some video or means you can finally run MS Bob then it might be a worthwhile 10%.

Re:Nessesary? Or just fun?

[MoneyT]

Have you considered the fact that they probobly ran those tests on a clean system? I don't know about you, but most people I know, don't just have Quake 3 installed on their machine. They have many other little apps and extra files, all of which chew up this or that system resource. Background apps etc all affect the overall usage of the system. And since when did Quake 3 become the standard for computer usage?

Re:Nessesary? Or just fun?

[MoneyT]

I know overclocking is often as easy as pulling a jumper or two, but the point I was making is that it seems fairly rediculous to be rating processors based on how high you can overclock them. I bet if I tried, I could overclock a 1 ghz processor all the way up to 2, and it would last about 5 seconds before it burned out. The point is, we should be more concerned about how the other components of the processor are working and not how high can we get it to overclock.

Re:Nessesary? Or just fun?

[MoneyT]

And what happened to the turbo button? It went away cause everyone said, "why can't they just make processors that run at the speed the turbo button makes the current one run at?" The last time I used a game that pushed my processor to the max was when I was playing Deus Ex (a system intensive game, horibly so) and set off 250 mines at once. Every other time, the games rarely go above 85% processor usage. And with the size and types off chips apearing on graphics cards, I should hope that that card would handle the video, not my main processor, afterall, that was the point of providing seperate graphics and video chips.

Re:Can you imagine...

[Alan Partridge]

and how would that fit in with going boldy where no PC has gone before? Anyway, I use both PC and Mac workstations, and even our fastest PC (1600Mhz AthlonXP) only canes our fastest Mac (867Mhz MPC 7450) by around 10% on the kind of work we do, the G4s higher IPC and gert big Altivec units really get the Mac moving when exploited properly. Mind you, doing general purpose stuff like looking at Flash anims on a website, the Athlon seems to play 'em about twice as fast - so if you aren't actually WORKING the PC is the platform of choice...

More Info

[DeadBugs]

Here is a CNN Article about the chip.

my computer runs at 50MHz

[Anonymous Coward]

That's right, 50MHz. And it's fine more or less.
I want something faster, but I don't have the
money at the moment. Anyway it runs Linux so
really I don't need anything *much* faster.
Linux works great even on super-old computers.

Re:my computer runs at 50MHz

[Anonymous Coward]

Runs Linux? Do you speak 2.2.x and no X?

My 33MHz-16MB RAM cannot run X at an appreciable speed.

AMD marketing is right on

[Chazmati]

Well if I got anything out of reading the benchmarks, it's that AMD is dead on with their "Athlon XP 2000+" marketing game. I wasn't sure I liked the idea, after reading benchmarks where the 1.67 GHz AMD chip ran neck-and-neck with the 2.0 GHz Northwood, I have to concede that it seems accurate.

Bottom line? This might be healthy competition between AMD and Intel. Let's hope these two continue to push each other higher than they might climb on their own.

Re:AMD marketing is right on

[CTho9305]

Somewhere on AMD's site was a fairly detailed explanation of how they came up with the numbers - it was actually a fairly comprehensive test (lots of software), and I think they did a good job. It seems they gave Intel the benefit of the doubt though, as in most of their tests, the Athlons performed slightly faster than the P4 whose clock speed they were rated to match.

25% is dis-impressive overclock

[2ms]

I guess the reason this thing is on Slashdot is that somebody thought it was impressive that the thing overclocked .5Ghz. That's only a 25% overclock though!

Hell even my k6-3+ here with quiet Arcticooler is doing 50% overclock. It's common practice to take (as low as 600) Tbirds and overclock them well over a gig with smaller coolers than needed for PIV (that's, like, almost a 100% overclock).

It's amazing how effective Intel's trick of reducing work per cycle in order to create more cycles continues to be. It seems like with every stepping, there's another idiotic slashdot item where everyone's like "holy shit, remember when 1GHz seemed huge!!!! Imagine beowulf!!! AMD's fucked now!!! Until this PIV came along I wasn't sure that technology in general was progressing at all, however now that we have x GHz I am assured that technology is advancing more rapidly than ever before!!!!"

fastest vs 2nd fastest

[quarter]

interesting that they measure the fastest amd vs the 2nd fastest intel.

although, through extrapolation the amd would still be faster in most tests, i'm sure.

Re:fastest vs 2nd fastest

[Hoser McMoose]

To a certain extent you have a point that the 2.0GHz Northwood is not the fastest chip that Intel offers.

However, the other way to look at it is that they're comparing a $350 AMD processor to a $500 Intel processor, so one could say that the comparison is actually biased in the other direction as well.

Re:fastest vs 2nd fastest

[quarter]

first, according to cnet they are comparing a $339 part to a $364 part.

second, why make such a big deal to have all those charts and numbers that show how much faster the xp is, if they dont even use the fastest intel? why not run it against a celeron?

third, tom's review is out

WTF?

[Arjuna Theban]

From the article:

The Northwood Pentium 4 processor chips we have are off-the-shelf chips, the same as any consumer would buy. No specially picked chips or engineering samples here, folks!

From CNN: (front page)

SAN FRANCISCO, California (Reuters) -- Intel Corp. on Monday will unveil its fastest-ever microprocessor, a Pentium 4 chip that not only allows it to maintain its leadership over rival Advanced Micro Devices Inc., but also introduces what analysts said is a critical improvement in Intel's memory chip technology.

I'm pretty hungover from last night but I'm still pretty sure today is Sunday.

How can they get off-the-shelf chips for testing when they're not available to the consumers yet?

---

Re:WTF?

[Anonymous Coward]

becuase they have been shipping into the channel for weeks...

Re:WTF?

[Arjuna Theban]

What does shipping into the channel mean?

My point was that the only way they could be sure that they are testing a processor that is truly off-the-shelf/consumer product would be to actually go and grab it from a shelf themselves. It sounds to me like this was sent to them. Any hardware addressed specifically to a review site is destined to be tweaked, no matter where it came from.

---

Re:WTF?

[Anonymous Coward]

What does shipping into the channel mean?

Teachable moment here: when Intel launches a chip, they already have stock on hand, so you can go out and get one immediately. The "off the shelf" meant "off the stockroom shelf," not "off the retail shelf"--because the product hadn't launched yet, you couldn't go buy it. You know, like how Microsoft had that big gala bash when you could FINALLY buy Windows... 95, was it? At any rate, they had the product sitting and waiting until the official "go" date.

AMD, on the other hand, 'launches' a product about the time first silicon hits their debugging labs.

If you do the math...

[TexTex]

Steve's got a much better chance creating a faster computer... He needs to bump up the 667 processers to 1.3 mHz in order to double his speed. Intel needs to manage a 3.6 GHz machine right now in order to double their chip.

The higher and higher ye get, the less the percentages work. 2.0GHz??? That's a nice 11%... The 233 from the 200 was bigger than that!

Physical limits of chipmaking process

[SHiFTY1000]

How far is the 0.13um process away from the "wall" where you get funky quantum effects happening on a chip? What will happen when we reach there? Could a box with a quantum processor be dangerous to cats?

Re:Physical limits of chipmaking process

[Anonymous Coward]

They recived them directly from intel for testing and make free advertisments of intel iv processor?

Re:Can you imagine...

[athlon02]

It may be just be rumors right now, but very delicious ones :) ...

G5 = 64bit addressing PowerPC running about 1GHz to 1.6GHz = next Mac CPU (again, rumors, but still nice to dream)

And DDR333 in the next line of macs is probable from what I gather.

So until AMD brings out clawhammer and sledgehammer (of which I'm also waiting on) Macs may very well have some new advantages over PCs for a while.

I agree...

[athlon02]

... with those who say "who cares."

What I'd rather see is flash memory, magnetic RAM, and other non-volatile memories, become dirt cheap for a few GBs worth and with a data path of 128bits at least and preferably more. And of course a processor that had a 128bit or higher data path would be a good compliment to it too.

Sadly though, I know increases in technology are incremental so that these are only dreams right now.

Clock speed != Performance

[delta407]

Overclocking a 2.0 GHz CPU to 2.5 doesn't mean it will beat an AMD 1.7, it just means it pushes electricity through faster, generates more heat, and so forth. Case in point: if a single MOV operation takes fifty clock cycles (which it doesn't, anywhere, ever) and a MOV on a different CPU only takes one, guess which one will perform better (doing MOVs) at 50 times slower of a clock? Clock speed does not -- and cannot -- equal performance.

Wow. 533 MHz RAM... yummy. I wonder what AMD could do with that big of a pipe.

I just think it'll be kind of funny watching AMD's 2.0 GHz CPUs with 533 MHz RAM stack up to Intel in terms of performance.

Re:Clock speed != Performance

[VAXman]

Dude, if the MOV instruction is a load which doesn't hit cache, or a uncacheable store, it will take a heck of a lot more than 50 cycles to complete.

Re:Clock speed != Performance

[Anonymous Coward]

Example only...

Video processing is a CPU hog

[msobkow]

A number of people I work with have DV video cameras and are buying DVD-R/DVD+RW burners. I don't know of anything that consumes raw cycles like video processing. Even with clean source, it can take 4-5 hours to process a mere 25-30 minutes of video to MPEG2 if you want good video quality (and that's on an Athlon 1.4GHz!)

In the past 3 months, 4 of the 30 people in my work area have picked up DV cameras and looked at DVD burning their home vids. Every one of them has been greatly disappointed to find that they can't do it with their "old" 800MHz PIII boxen without leaving the job running over night.

So I guess the point is that you don't need much more power than currently available for raw compiles and such, but you can expect the upcoming flood of DVD burners and DV cameras to push a significant number of people to upgrade.

Re:Video processing is a CPU hog

[Anonymous Coward]

I've been playing around with video on a few 1+Ghz athlons and your not lying about the time it takes to render these things. A movie can take 2 to 3 days to render at 720x480. Most of my raw video files are mjpeg, taking up about 20-30GB for 90 mins, sometimes more depending on quality. But the end result is a 1GB file that is easily streamable over a 100Mbit net to play on your TV.

The main problems we have with this technology today are open and free video codecs of mpeg-4 quality. Hopefully that will be solved soon. But most quality analog sampling equipment is costly and macrovision protected. Preventing you from transferring your store bought movies to digital.

DVD recompression is an excellent way to get good quality with the finished product, but it can also be really tricky with the copy protection crap. Its best to just download free content via the web and store it to disk. For a forcast for the next few years I predict that both storage space and bandwidth with be in abundance.

Your attitude is dangerous

[Anonymous Coward]

Sure it is easy - but unless you do proper stress testing, it is possible you are running an unstable system. Even if it only makes one error per week, that could cost you data. Mission-critical systems should probably not be overclocked significatly.

My p200mmx doesn't do 233 with the stock heatsink. It seems to do 225, but I didn't bother testing (it is at 200, where it shoudl be, since it is purely a server).

My tbird 700 is at 750 (easy overclock) and after a few weeks of testing, I am sure it is stable.

Just make sure that before you recommend overclocking as "easy and safe" you give the full story - it is possible to damage your data, etc. The odds of killing the chip if you dont drastically raise the voltage are low though.

2.2 GHz CPU ???

[Zeinfeld]

Hmm, in the old days we used to use empty slots in a 19" rack to slide in a pizza to keep it warm...

With 2.2 GHz CPUs that all changes, every machine comes with a built in microwave.

Anyone know what effect the CPU has on 802.11b? Like might be tricky with both in the same box???

R.I.P. WIPO Troll -- we'll miss you, buddy!

[Anonymous Coward]

THE OFFICIAL TACO-SNOTTING FAQ By J. Wipo Troll, Esq., $Revision: 1.16 $

[This article attempts to document a vile, ungodly practice that runs rampant through the homosexual geek and hacker community, a practice known as Taco-snotting, or simply snotting. Taco-snotting is something that few geeks dare talk about in free or open conversation, but it is nonetheless a widely-practiced and dangerous form of homosexuality. If you or anyone you know has ever engaged in Taco-snotting, please get professional help before it is too late. ed.]

Why do I keep receiving emails from an individual calling himself CmdrTaco?

You have been receiving unsolicited mailings from a certain Robert CmdrTaco Malda, owner of the popular technology website slashdot.org. Actually, its not a very popular site in the common sense of the word; the site is rife with pimply, antisocial geeks and hackers, zit-faced nerds, communists, dirty GNU hippies, and other societal rejects and outcasts. Its also home to one of the worlds largest suspected pædophile rings, the infamous Slashdot crew.

Whenever Mr. Malda gets bored (and who wouldnt, running a site like Slashdot all day), he roams through the user database, penis in hand, looking for people who might enjoy engaging in homosexual activities with him. How he determines this is anyones guess; but if you have a homosexual-sounding nickname, or a nick with a letter of the English alphabet in it, youre a potential candidate.

This time, he found you. Lucky you.

Mr. Malda seems to be speaking in some sort of code. Do you know what it means?

CmdrTacos code language is relatively easy to decipher. This pervert prefers to speak in thinly-veiled sexual innuendo (yes, thats right: he wants you) to evade the watchful eye of Slashdots parent corporation, VA Software. Mr. Maldas Commander is, of course, his penis: a small, withered little thing that lives in his pants and only comes out in the presence of other male geeks or at the beck and call of Maldas own lubed-up right hand. His Taco bells are the shriveled testicles that droop beneath his Commander, and his Taco sauce is his thin, runny semen. It should be more than obvious to you now what he means if he asked you to ring his Taco bells or taste his gourmet Taco sauce.

I would also guess CmdrTaco asked you to engage in a practice known as Taco-snotting and, if he was in a particularly depraved mood at the time, a circle-snot.

Good Lord. And, yes, he did. What is Taco-snotting?

Taco-snotting is the term used by Robert Malda to refer to the depraved act of fellating another man (homo- or heterosexual; CmdrTaco is rumoured to prefer raping unwilling victims), then blowing the semen out his nose and back onto the face and body of his victim. Naturally, a long, bubbly stream of milky-white semen is left on CmdrTacos face, dribbling out of his nose and down his cheek: hence the term, Taco-snotting.

And if thats not bad enough

A circle-snot is a Taco-snotting circle-jerk, another practice common among the Slashdot crew. CmdrTaco, CowboiKneel, and Homos get together and snot each other with their gooey, sticky cum spooging their jizz-snot all over each others faces and pasty, white bodies, until theyre covered head to toe with their own and each others man juice. This vile, ungodly ritual can go on for hours. For the homosexual penetration that follows this lengthy foreplay, Roblowme is usually there to provide plenty of anal lubricant; he owns a limousine service and has ample supplies of motor oil and axle grease ready to go.

To complete this perverted orgy, fellow faggots Michael, Timothy, and Jamie will usually join in, dressed in tight leather mock-S.S. uniforms, jack boots, and leather gloves. The homosexual shenanigans that follow are nearly beyond description. The whole group begins to snot each others spunk and whip each others pudgy asses with riding crops and chains until their pale, white geek bodies are exhausted and soaked in stinking sweat from the hours of passionate, homosexual revelry.

Ewwwwww. So, can I stop receiving these emails?

Hopefully, but I wouldnt count on it.

To begin with, you most likely forgot to uncheck the Willing to Snot checkbox in your account preferences. CmdrTaco has probably already got the hots for your wad (do you have a homosexual-sounding nick?), and hes probably already been lurking outside your bathroom window for weeks with a camera, some tissues and lube, just waiting to pounce and declare you his new bitch. Theres no escaping a geek in heat (trust me), so its probably too late for you, but you can possibly rectify this situation. To remove yourself from CmdrTacos sights, log into your Slashdot account, go to your user page, click on Messages, and uncheck the box next to Willing to Snot. Maybe hell ignore you. Probably not.

I cant stop receiving these emails from CmdrTaco!?

If you indulge him in a Taco-snot or two, he might leave you alone. You might also want to look into mail filtering, restraining orders, or purchasing a heavy, blunt object capable of warding off rampaging homosexual geeks in heat. Trust me, when they charge oh, the humanity. If he gets you, and you let him Taco-snot all over you, you will most likely end up tied up in his basement to be used as his sex slave for the rest of your life (or until he accidentally drowns you in spunk in a circle-snot).

Have you ever been Taco-snotted?

Unfortunately, yes. I first met Mr. Malda at an Open Source Convention. He invited me back to his room for a game of Quake and some gourmet Tacos, but when I got there, the perverted geek jumped me and handcuffed me to his bed, stripping me. After taking his Commander out of his pants, Mr. Taco made me suck the withered thing six times, virtually nonstop. He then performed his vile Taco-snotting ritual on me three times over the next two hours, bringing me to orgasm after orgasm after sweaty, mind-numbing orgasm then he snotted my own thick, gooey jizz back onto my face out of his nostrils! He snotted me two more times, first into my mouth, then again on my exposed belly.

CmdrTaco invited several of his Open Source (or rather, Open Sauce man sauce) buddies over to continue their ungodly snotfest. European hacker and known überfaggot Linux Torvalds raped my ass with his monolithic kernel; his partner-in-crime Anal Cox used their network stack in a multitude of unspeakable ways on and in every orifice of my defenseless, tender, young body. Michael Sims was there in his leather Nazi uniform, caning my previously-virginal ass with a bamboo pole and ranting about all those Censorware freaks out to get him.

That is so disgusting! How did you finally escape?

After about 16 hours of countless unholy, homosexual atrocities perpetrated against my restrained body, they all finally went to sleep on top of me, sweat-soaked and exhausted. I was left there, completely covered in bubbly, translucent jizz-snot, chained to the bed, with half a dozen fat, pasty-white fags lying around and on top of me. Fortunately the spooge coating my flesh worked wonderfully as a lubricant I was able to squirm my way out of the handcuffs and slip out the back door (of the apartment, not their back doors). Im just glad I survived the awful ordeal. These sexually-repressed hackers had a lot of built-up spunk in their wads I couldve easily been drowned!

Thats horrible. Does Taco-snotting have anything to do with CmdrTacos special taco?

No, thats a different disgusting perversion CmdrTaco indulges himself in. Mr. Malda is usually not satisfied with merely snotting your own jizz back onto your face, he most often enjoys involving his own bodily fluids in his twisted games. WeatherTroll has spent some time trying to educate the Slashdot readership about this vile practice (emphasis added):

You may be wondering what CmdrTacos special taco is. You will be wishing that you hadnt been wondering after you finish reading this post. To make his special taco, CmdrTaco takes a taco shell and shits on it. He then adds lettuce, takes out his tiny withered dick (otherwise known as his Commander), puts his special taco sauce on it which means he jacks off on the taco, and adds a compound to make the person who eats the taco unconscious. Of course, the compound does not make the person unconscious until the taco is fully eaten. Thus CmdrTaco force-feeds the taco to the unsuspecting victim. After all, who would knowingly eat shit and CmdrTacos jizz?

After the victim is unconscious, he is held against his will and used for CmdrTacos nefarious homosexual purposes. This includes shoving taco shells up the victims ass, Taco-snotting, and getting Jon Katz involved. Trust me, you do not want Jon Katz anywhere near your unconscious body. Also, rumor has it CmdrTaco is looking for a new goatse.cx guy. Dont let it be you!

Different ungodly perversion, yet no less revolting. It should be clear to you now that Robert CmdrTaco Malda is a very, very sick individual, as are most of the Slashdot editors.

Does Jon Katz get involved in any of this? I thought he was a pædophile, not a homosexual.

Actually, Jon Katz is a homosexual pædophile. Hes also a coprophiliac, and, many suspect, a zoophile.

Mr. Katz is somewhat of a loner and doesnt involve himself in the circle-snots, but that doest mean hes any less of a freak than the rest of the Slashdot crew. Katz often engages in a game called juicy-douching with a harem of little-boy slaves that he has collected over the years: yet another vile practice which involves administering an enema to himself of the little boys urine (forced out of them with a pair of pincers), spooging the vile muck from his ass back into the enema bag, then dribbling and slathering the goo all over himself and the boys chained, naked bodies. If hes in the mood, he will sometimes skip refilling the enema bag from his distended anus and just squirt it from his ass onto the crying, terrified boys. Unwilling boys are further tortured with the pincers until they comply and allow Mr. Katz to juicy-douche them at will. A boy will usually last about two years before Mr. Katz either accidentally drowns them in diarrhea or kills them once they get too old, usually around 13 or 14.

Not content with being a pædophilic coprophile, Mr. Katz is also quite the zoophile. As if the sexual escapades with the helpless little boys arent enough, Jon usually enjoys his juicy-douches best when his penis is firmly planted in a female goats anus. He is also rumoured to get off on watching his little boys eat the goats small, bean-like turds, and he often kills his older boys by letting his goats trample them.

Are you getting hard writing this?

Why, yes. :) Join me in a WIPO-snot?

No, thanks. Im already CmdrTacos boi toi.

________________________________________

• The URL of this document is <http://slashdot.org/journal.pl? op=display &uid=267426 &id=2346>
• Previous revisions are publicly available at <http://slashdot.org/journal.pl? op=list &uid=308209>

$Id: tacosnotting.html,v 1.16 2001/12/28 21:20:03 wipo Exp $

Copyright © 2001 J. Wipo Troll, Esq. Verbatim crapflooding of this document is permitted in any medium, provided this copyright notice is preserved, and next time you take a dump, you think of the WIPO Troll and all hes done to make Slashdot a better place.

Yeah! Now I can play minesweeper @ lightspeed.

[superpulpsicle]

But it may still not carry enough horsepower to run my windows without crashing...

Well said!

[Dr. Spork]

Even when we know cheaper AMD chips do just about everything faster, we seem to instinctively drool when we hear about a clock frequency 20% higher than what we've seen before. It's like we're saying: "Clock speed isn't everything, but ...[drool]... isn't 2.5G a high number?"

Well, that's just stupid. We know better. AMD would benefit if they named their chips according to the flops they can do. Once we got used to how those numbers looked, our instinctive drooling at the latest chip innovation would at least better mirror the actual usefulness of the chips. It would also result in us scratching our heads about why Intel released the P4 in the first place.

More idiot Athlon fan boys...

[Anonymous Coward]

The Northwoods cost $365, iirc. Athlon XP 2000+ (which are about the same speed (and not in MHz, actual speed as tested by spec_2004 or Sandra or whatever they used)) cost about that much. Whoever modded this guy's ignorant rant up as insightful needs to be slapped.

Could a box with a quantum processor be dangerous-

[Anonymous Coward]

"Could a box with a quantum processor be dangerous to cats?"

If we're lucky...

Did Intel Kill Kenny, or something?

[Loki7154]

Maybe Intel gave a lot of you the bird personally, and if they did, I'm sorry, but as to the rest of the anti-intel crowd...

/Begin Rant

I'm sorry, but people time and time again keep naming the big price difference as a reason to buy AMD.

Here are a few facts to ponder: the 2.0A Northwood will be priced at around $360. The 2000+ Athlon will be priced at around $330. Yes, that's a huge price difference there. "Oh, but the (dirty) RAMBUS" you say. The price of a 256 meg stick of Corsair "Value Select" PC2100 DDR-DRAM PC2100 from www.memman.com is $98. The price of a 256 meg stick of Corsair "Value Select" 800mhz RDRAM is *gasp* $108. Assuming you want to outfit a rig with 512 megs of ram, that is a grand total of a $50 price difference. Maybe I'm just a little too loose with money, but on a $700+ purchase, I don't think $50 will make the ultimate decision. And I haven't even bothered to mention the fact that P4s can now use DDR...so what's the problem with price, again?

There seems to be a hatred of the P4 among some people. I really don't understand it. Yes, Intel made a tradeoff between per-clock power and ghz...but if they can make up for the difference with higher clock speed, so what? As I understand it, it's like the difference between buying a fast car that can't haul a lot of stuff and buying a van that can haul lots of stuff. Just so long as the fast car is able to go fast enough so it can make a few more trips (and thus transport the same amount) then it doesn't matter _how_ it got done. Also, continuing with the analogy, it seems the fast little car can go about 25% faster than its rated speed. According to most reviews, these overclock like a dream.

People who are against a product simply because it has the name "Intel" stamped on it are no better that IT departments that refuse to buy anything _not_ stamped with the Intel logo.

As is the mantra of capitalism, competition is good. However, for there to be competition, people can't just blindly stick to one brand. I'm not saying that the Northwoods are good enough to make someone switch, but they at least deserve a chance.

/End Rant.

Sorry all. I think it just needed to be said.

Re:Tests give the pentiums the benifit of the doub

[ThatComputerGuy]

And check out the quote from the conclusion:

"In reality, the Northwood Pentium 4 is an amazingly fast processor. It's safe to say that as of right now, the Northwood at 2.0 GHz is a faster gaming processor in comparison to the 1.67 GHz (2000+) Athlon XP."

Now, what makes them say that? In Q3A the Norhtwood usually leads, but in RTCW, which is using the Q3A engine, the XP's consistently lead.

WTF gives? Anyone got an answer?

what's in a name

[Anonymous Coward]

Why do they use the code name 'Northwood'. I am just wondering, because my last name is Northwood.

I wonder if this gives me a better opportunity to get that job I always wanted with Intel.

Cheers

Another Review

[m_evanchik]

Actually, Tom's Hardware has a review of the 2.2 GHz Northwood and they compare it to the Athlon XP2000+.

Looks like they just posted it.

Here's the link:
http://www.tomshardware.com/cpu/02q1/020107/inde x. html

Civilization will come to an end

[gelfling]

If I can't compile that horrendously large prog in 108 minutes instead of 120 minutes.

Toms hardware review of the 2.2ghz P4

[phaze3000]

Toms Hardware has just put their review of the 2.2ghz P4 up, and it seems it beats the Athlon XP '2000+'.

Personally I get the distinct impression Intel are just toying with AMD; they've already demonstrated the Northwood core at 3ghz, but if they were to release it right now they'd blow AMD away and loose their profit margins from 'early adopters'. It's in their interest to keep AMD going, in much the same way Microsoft kept Apple afloat. If there's a competitor then you can't be branded a monopoly.

At the moment though, I'll just have to get by with my 850mhz Celeron..

Re:Toms hardware review of the 2.2ghz P4

[Anonymous Coward]

Trust me if Intel could reliably produce 3GHz P4's today they would be doing so. Intel hates AMD and is and has been scaling as fast as they can to bury them. If anything they would release a expensive 3Ghz today and then scale down from there 2.9,2.8... etc like they did with the initial 1.7GHz model.

really depends on application

[john_uy]

many question the need for 2.2ghz. i do.

getting a faster cpu nowadays is just because you need it and not that you want it. a celeron 300 system can do most basic functions such as doing word processing, spreadsheet, e-mail, internet.

the only reason you would need to get a p4 2.2ghz is that if you will be rendering 3d images (and look at now lightwave 7 exploits p4 and beats the heck out of athlon), doing more multimedia work (which is the main thrust of intel), and games (yes this is most probably the 99% reason why more cpu/gpu is needed). other than that, it will be totally useless.

but i'm impressed with the performance (and engineering) of the pentium 4. you can now render through divx at realtime a dvd movie with audio. and if you can engineer a software to use sse2 and all the pipelines of p4, look at the performance gain of lightwave (which was totally reengineered from the start.) so i bet most applications use only less than 30% of the cpu at any given time. i bet if they would reprogram their work and use 100% better, it will be running all your system something like pentium 4 4ghz!

btw, a few days ago, i was running a celeron 300a cpu and it worked great for me (until i had to replace the worn out motherboard so i upgraded to p3 733 - not even a p4.)

Northwood CPUs

[13Echo]

These Northwood CPUs are nice, but can the marginally higher Quake III performance justify nearly twice the cost of an Athlon XP? I would probably just rather spend my money on a dual Athlon MP machine.

Besides... Quake III is optimized around Intel, as are all id games.

Yea Right

[Anonymous Coward]

I'm sure at your company you have a tech that goes around installing Alpha HSF's and overclocking your Compaq deskpros.

The only people who overclock are hobbyists perios.

we need a benchmark for response.

[leuk_he]

It has been said before: there are benchmarks and lies. What we need is a bench mark for system responsiviness. But i haven't seen this yet. But there are a few things that give you a clue we need a good test for this :

-There are lots of remarks the new linux kernel feels unresponsive, but in the benchmarks it test better than ever before. There is a low-latency patch that did not make it because there is not clear test this helps.
-I know a PC with 256 MB ram responds better than a pc with 128 MB ram from experience (i.e. MS word starts up faster) But in the test this not very visible.
-A stutter in the sound is written of to bad drivers, but is very annoying. Is there any test for this? (other then just listen to a mp3)

Re:we need a benchmark for response.

[Anonymous Coward]

A stutter in the sound *can* also be caused by a system by a system being unable to send sound samples to the sound card fast enough because it is too bogged down with other stuff. Not typically a problem anymore, but it can and does happen.

Overclocking - wrong answers to crashes

[AHumbleOpinion]

I was under the impression that an overclocked CPU usually ran rather flaky with spurious crashes and lockups

It's much worse than that. Every individual CPU reacts differently. The errors range from simple incorrect results to crashes. Remember the FDIV problem a few years ago where there were certain bit patterns that resulted in answers that were a little off? Well overclocking sometimes results in similar problems, except you don't know the conditions that will result in incorrect results.