Intel Pushes Pentium 4 Past 3 GHz

eh? by lordkuri · 2002-10-29 00:45 · Score: 5, Funny

Yahoo has the news about the new P4 who will run at nothing less than 3.06mhz.

umm... I've got an XT clone that's faster than that... wanna buy it for about $600?

(/sarcasm)

Re:eh? by MortisUmbra · 2002-10-29 00:56 · Score: 2, Funny

The evils of no proof-reading :) the greatest avance isn't 3.05mhz....

--

"The saddest words of mice and men, are not those which were, but should have been."
Re:eh? by Anonymous Coward · 2002-10-29 01:16 · Score: 2, Informative

Processors gain self consciousness at about 3 MHz, therefore we shall refer to them as "who", not "which".
Re:eh? by WhoolaHoop · 2002-10-29 01:23 · Score: 1

It's even slower than you probably thought.... a lower case m implies milli-hertz (mHz), not megahertz (MHz).

That is, 0.00306 Hz, about one clock cycle every 5 minutes!

Should run nice and cool though.
Re:eh? by SN74S181 · 2002-10-29 01:34 · Score: 1

It would be amazing, simply amazing, if the processor could run at 3.05 millihertz properly, without a static design and gargantuan power requirements. Because the dynamic registers would be DAMNED good at retaining charge at that refresh rate.
Re:eh? by hatchet · 2002-10-29 01:42 · Score: 1

And 'hz' doesn't imply as Hertz (Hz does) and it might mean horzogs. And maybe 3.06 milli horzgos is same as 3.06 mega hertz.

The point is... who cares what's written.. what matters is, that we understand what writter wanted to say.
Re:eh? by netsharc · 2002-10-29 02:12 · Score: 2

Hehehe, now The Taco has edited the article to say "GHz"... watch out buddy, he's on to you. :)

--
What time is it/will be over there? Check with my iPhone app!
Re:eh? by phagstrom · 2002-10-29 03:29 · Score: 1

Processors gain self consciousness at about 3 MHz, therefore we shall refer to them as "who", not "which".

"Sorry Dave. We can't have you telling people the truth. You'll have to be terminated..." ;-)
Re:eh? by Anonvmous+Coward · 2002-10-29 05:00 · Score: 2

"And 'hz' doesn't imply as Hertz (Hz does) and it might mean horzogs. And maybe 3.06 milli horzgos is same as 3.06 mega hertz."

Boy I bet you guys were a riot at the B5 vs. DS9 debates. Heh.
Re:eh? by trolleri · 2002-10-29 05:16 · Score: 1

> kdajad jnjfd erhwkuhwfdouf jdn jdflilwirfjwl
> frneli nmcslir hfd dj lsirj ifrnifler;o
> mfldeke kjfvn kk ijfveijf kj jdh ilsdijc
> jhdf ilfsijlice
no need to bring it up, we all know you're immature.
-
Re:eh? by RandyOo · 2002-10-29 11:25 · Score: 1

The point is... who cares what's written.. what matters is, that we understand what writter wanted to say.

Just curious... Does 'writter' rhyme with 'critter'?
Re:eh? by Ninja+Programmer · 2002-10-29 11:59 · Score: 1

Yes, but does your XT system have Netburst technology?

Great.... by MosesJones · 2002-10-29 00:45 · Score: 1, Troll

And yet while running enterprise class systems I can't find a system with too little power.

Lets face it servers are well beyond 95% of applications.

--
An Eye for an Eye will make the whole world blind - Gandhi

Re:Great.... by LookSharp · 2002-10-29 00:52 · Score: 4, Insightful

And yet while running enterprise class systems I can't find a system with too little power.

Well I have a citrix farm full of quad Xeons and 4 gigabytes of RAM, and we'd still love some more power, thanks. :)

Maybe you don't want 3.06 GHz for what you're working on, but our "Enterprise Class Systems" (Win2k application servers) can use all the CPU we can throw at them. Everyone has different needs, and for a lot of folks, faster processors are a good thing.

(I've seen this troll a few times over the last four or five AMD/Intel product announcements. And it's still getting modded up.)
Re:Great.... by GiorgioG · 2002-10-29 01:19 · Score: 2, Funny

Apparently you've never run tried to run IBM Websphere ;-)
Re:Great.... by sql*kitten · 2002-10-29 01:46 · Score: 5, Insightful

Maybe you don't want 3.06 GHz for what you're working on, but our "Enterprise Class Systems" (Win2k application servers) can use all the CPU we can throw at them. Everyone has different needs, and for a lot of folks, faster processors are a good thing.

Are they actually CPU bound, or are they slowed by memory access and bus bandwidth? Apart from certain numerical computations, I have rarely seen cases in which the CPU is really fully occupied, altho' the tools often report that it is. For example, tools will report if the CPU is idle waiting for a page fault to the swapfile, but not if it's waiting for data to get to or from main memory, it just looks like the CPU is occupied.

Knowing what I know of Citrix, it alone is far bigger than the L2, and that's before even considering the user applications. It requires the CPU to switch context heavily, and constantly flush and reload its L1/2/3 caches. After all, if you need 4G of RAM to run the applications you are using, and you have say an 8M cache, the CPU is going to be spending a lot of time managing its cache rather than doing useful work. Given that, it is bound by memory access, not raw CPU.

Manufacturers, driving by consumer marketing which believes that higher Mhz == better product, are optimizing in the wrong areas. If they want to talk numbers, they should be pushing fast memory and buses which are actually a useful measure of a machine's performance, not CPU Mhz which isn't.
Re:Great.... by ergo98 · 2002-10-29 03:20 · Score: 1

Manufacturers, driving by consumer marketing which believes that higher Mhz == better product, are optimizing in the wrong areas. If they want to talk numbers, they should be pushing fast memory and buses which are actually a useful measure of a machine's performance, not CPU Mhz which isn't.

So you're saying that they should be increasing memory bandwidth and bus speeds? What a clever idea. You should write a letter to them because clearly they just haven't caught on...oh wait, yes they have.

If they want to talk numbers, they should be pushing fast memory and buses which are actually a useful measure of a machine's performance, not CPU Mhz which isn't.

This is as much bullshit as claiming that only Mhz is a measure of a machine's performance. Obviously it's a combination of all of the systems in the machine, and the large CPU manufacturers aren't stupid (i.e. they want their machines to show up at the top of the benchmarks): As the need arises they increase bus and memory bandwidth accordingly, and for "cutting edge" needs they produce chips with huge L2 caches (though the cost/benefit is out of whack. A P2 2.4Ghz with 2MB of L2 would get trounced by a 2.6Mhz with 512MB of L2 cache, disputing your claims that CPU speed doesn't matter. Large cache chips only make sense if you can't get a faster CPU: In that case the only option they have is to increase the cache). A dual-channel RAMBUS solution isn't going to make a P4 1.4Ghz any faster than it would be with a single-channel: The CPU will never demand that memory bandwidth. Indeed, this was one of the original problems with RAMBUS: The extreme throughput it offered simply wasn't necessary for the early P4s, leading to a lot of the early naysaying about its usefulness. Of course we all know that it because the crucial point for P4 performance as the clock speed accelerated.

Sorry, but your post reeks of "armchair CPU designer" : It's all so clear and so obvious. I mean, it's not like Intel and AMD have a lot of extremely clever people who seek the best balance between all of the systems...is it?
Re:Great.... by sql*kitten · 2002-10-29 03:38 · Score: 5, Informative

Sorry, but your post reeks of "armchair CPU designer" : It's all so clear and so obvious. I mean, it's not like Intel and AMD have a lot of extremely clever people who seek the best balance between all of the systems...is it?

Yes, they are slowly improving, but modern PCs are still behind where workstations were years ago, and a modern Intel based server is well behind a SPARC based machine.

Intel and AMD will spend their money on whatever generates the most ROI. They have collectively spent literally billions of dollars convincing Joe Public that CPU Mhz is the best way to measure the speed of a system - they aren't going to throw that away. A competent manager with R&D dollars to spend will therefore spend them on increasing Mhz.

Oh, and your post reeks of being underexposed to any architecture other than x86.

though the cost/benefit is out of whack. A P2 2.4Ghz with 2MB of L2 would get trounced by a 2.6Mhz with 512MB of L2 cache, disputing your claims that CPU speed doesn't matter. Large cache chips only make sense if you can't get a faster CPU:

Yes, assuming the code to run is 512k in size. If the code is ~2M, so it fits into L2 on the slower processor, then it will have the advantage, because the faster one will have to waste cycles moving the cache back and forth to main memory. Cache size is related to CPU speed only in terms of memory bandwidth: if your CPU cannot get data from main memory fast enough to keep it occupied, then you need faster memory closer to the CPU, which is what a cache is. If you are context switching, then you will have to keep dumping the cache and reloading it, which puts larger caches at a disadvantage.

Ultimately, caches are a hack; an elastoplast solution to the fundamental problem, which is the mismatch between the rate at which a modern CPU can process data, and the rate at which memory can supply it. In an ideal system, there would be no CPU caches at all, because the CPU could get data from main memory fast enough to keep it fully occupied. Systems used to be built like this, before the current obsession with clock speeds.
Re:Great.... by LookSharp · 2002-10-29 03:50 · Score: 1

No, we just have several thousand remote users on 56k frame relay circuits who run their windows desktops and 4-10 different applications (depending on job functions) off of a Citrix farm.

Hope that answers your question. :) Also, yes RAM is your friend for multiple sessions!
Re:Great.... by ergo98 · 2002-10-29 03:52 · Score: 4, Insightful

Yes, they are slowly improving, but modern PCs are still behind where workstations were years ago, and a modern Intel based server is well behind a SPARC based machine.

The bus and memory bandwidth has improved pretty much in lockstep with the CPU computational ability. While it might be nice on paper to have 16GB of memory bandwidth, and it might look good on a ridiculously synthetic memory bandwidth benchmark, in practicality such a imbalance would be just a monstrous waste of money: Generally processors actually do something with the data that they're processing, so the two factors have to balance: You need a system design that can keep the processor satiated. In the Athlon world such a situation was demonstrated superbly recently with the ramping up of the memory subsystem speed, DDR ramping up from 266Mhz to 400Mhz...what improvement did it demonstrate? Virtually none. The processor simply had no real need for the additional memory bandwidth, though I'm sure it will as they come out with the next generation.

Intel and AMD will spend their money on whatever generates the most ROI. They have collectively spent literally billions of dollars convincing Joe Public that CPU Mhz is the best way to measure the speed of a system - they aren't going to throw that away. A competent manager with R&D dollars to spend will therefore spend them on increasing Mhz.

While I have spent considerable effort in the past disputing the Mhz-is-king myth (especially in regards to the P4 versus the Athlon), I think you're promoting just as false of an claim. CPU speed DOES matter. By your claims, shouldn't these benchmarks show no improvement as the CPU power ramps up, given your claims that it's starved for throughput?
Re:Great.... by Anonymous Coward · 2002-10-29 04:34 · Score: 1, Insightful

Yes, they are slowly improving, but modern PCs are still behind where workstations were years ago, and a modern Intel based server is well behind a SPARC based machine.

Are you kiddding me? You must work for Sun's PR machine.

Any modern PC versus a modern workstatation [including SUN] is a joke. Nearly every application runs significantly faster on a PC than a workstation [large CAD packages, image processing, databases, etc]. Yes, the workstations have larger L1/L2 caches and such, but the sheer speed of the core processors in the PCs overcome this limitation quickly as they are significantly faster than their workstation counterparts. Also, the memory architecture on the SUN's isn't some form of wizardary; rather, the latest SUN workstations use interleaved PC133 RAM [the expensive SUN OEM version of course though] - not exactly revolutionary.

Anyone with their choice of a PC 'workstation' running Win32/linux versus a IRIX/SUN workstation will choose the PC hands down if they have used both.
Re:Great.... by kasperd · 2002-10-29 04:50 · Score: 2

Ultimately, caches are a hack

Absolutely not. Making large memories matching the speed of the CPU is not feasible. If you want the speed of the memory to match the CPU speed, it has to be smaller. Since most modern systems uses paging/swapping, a smaller memory will cause more trashing on the disk and result in a slower system.

Instead of having to make one choice between speed and size, we have multiple levels of caches with different choices of speed and size. This actually gives a performance improvement. The remaining problem obviously is, that not all software was written with this in mind. Software actually written with the speed difference between L1 cache and swap file in mind can be 100 000 times faster than software not keeping this in mind.

However designing an algorithm for the number of different levels in a modern system is not feasible. There would be far too many parameters, and you couldn't optimize your algorithm for all of them. Instead what is needed in the future is cache oblivious algorithms, that will be efficient on one level without knowing the actual size of the cache and cachelines. The advantage is that since the efficiency is independend of the sizes, it will be efficient on all the levels at the same time. As data grows such an algorithm will become faster than any other algorithm.

The next step as cache oblivious algorithms are becoming more common is to design architectures with cache levels optimized for cache oblivious algorithms.

--

Do you care about the security of your wireless mouse?
Re:Great.... by dfeist · 2002-10-29 04:53 · Score: 1

Ultimately, caches are a hack; an elastoplast solution to the fundamental problem, which is the mismatch between the rate at which a modern CPU can process data, and the rate at which memory can supply it. In an ideal system, there would be no CPU caches at all, because the CPU could get data from main memory fast enough to keep it fully occupied. Systems used to be built like this, before the current obsession with clock speeds.
But it seems fast memory isn't cheap enough... Because of that, I think the cache solution is okay as long as you don't have large amounts of data needing only minimal processing...

--
Unix makes easy tasks hard and hard tasks possible. Windows makes easy tasks easy and hard tasks $29.95.
Re:Great.... by jumpingfred · 2002-10-29 04:54 · Score: 1

We have Sun workstations at work and PCs at work. For place and route of Xilinx FPGAs I have found that the PC just blow the suns away on speed. These generally take about 1 to 2 hours to run onthe PC and 3 to 6 on the Suns. I think the time has past where Suns out perform PCs.
Re:Great.... by pmz · 2002-10-29 05:01 · Score: 2

...our "Enterprise Class Systems" (Win2k application servers) can use all the CPU we can throw at them. Everyone has different needs, and for a lot of folks, faster processors are a good thing.

right click on desktop --> "Properties" --> "Effects" --> uncheck "Use transition effects"

That should make your XPerience a bit snappier.

Seriously, I suppose it really depends on site needs, but I still see whole offices run their e-mail on SPARCstations (less than 200MHz CPUs) and websites on Ultra Enterprise 250s (bleeding edge in 1997). And...they perform just fine.

A single server with Quad Xeons really should be sufficient for a company with many thousands of employees. Well, with Windows, perhaps a few hundred. Regardless, that's a hell of a lot of data-processing capability.

--
Healthcare article at Kuro5hin
Re:Great.... by pmz · 2002-10-29 05:17 · Score: 1

Anyone with their choice of a PC 'workstation' running Win32/linux versus a IRIX/SUN workstation will choose the PC hands down if they have used both.

I wouldn't. I guess that makes your "anyone" argument a bit off the mark.

Nearly every application runs significantly faster on a PC than a workstation [large CAD packages, image processing, databases, etc].

Not true (just as valid an argument as the one you just made).

What is your definition of "faster"? Intel workstations need to run at 2.8GHz+ to approach the computational throughput of a Sun Blade 2000 with 1GHz CPUs. And that is just for debatably-useful benchmark (SPECcpu2000). Considering that the Sun also comes with FibreChannel disks and doesn't use mere PC133 RAM, it will beat your PC in real-world usage--that's what Sun designs them to do. Sun workstations are also more reliable and easier to maintain (you would know if you worked with them).

--
Healthcare article at Kuro5hin
Re:Great.... by pmz · 2002-10-29 05:20 · Score: 1

You don't provide any real data (just run times). It is most likely that you are comparing apples (new PCs) to oranges (older Suns). You really don't provide anything meaningful in your post.

--
Healthcare article at Kuro5hin
Re:Great.... by pmz · 2002-10-29 05:50 · Score: 2

This is the int result...

Look at floating-point SMP throughput (the earlier post mentions things like engineering apps, etc.). That is where Sun systems shine. For integer stuff...well, if you are compiling a really large software application, that is important, but, otherwise, it isn't terribly relevant.

Sun systems are known for throughput, which is a better measure of work done. Quake FPS isn't terribly useful in the real world.

--
Healthcare article at Kuro5hin
Re:Great.... by op00to · 2002-10-29 05:57 · Score: 2, Interesting

"Yes, they are slowly improving, but modern PCs are still behind where workstations were years ago, and a modern Intel based server is well behind a SPARC based machine."

Not exactly true. I work as an Opens Systems Programmer at a major research university. I have a P2-333 and an Sun Ultra 1 on my desk. Which do you think is less painful to use? I'll give you a hint, it doesn't have a 64 bit processor on it. I'll tell you, I'd rather use my P2-333 to serve a website than the Ultra 1. So those sparcs you speak of are rarely as fast as the newer PC's in most everyday tasks.

That being said, it sure is cool to say that you're running sparc linux, and in the winter I'd rather have the sparc on my desk to keep me warm.
Re:Great.... by Ninja+Programmer · 2002-10-29 12:05 · Score: 1
- - Sorry, but your post reeks of "armchair CPU designer" : It's all so clear and so obvious. I mean, it's not like Intel and AMD have a lot of extremely clever people who seek the best balance between all of the systems...is it?
  Yes, they are slowly improving, but modern PCs are still behind where workstations were years ago, and a modern Intel based server is well behind a SPARC based machine.
*Ahem* You live in a dream world.
Re:Great.... by Halster · 2002-10-29 13:56 · Score: 2

And yet while running enterprise class systems...

I'm sick of running enterprise class systems. I never liked the damn LCARS system from the first time I used it.

I've had enough. I'm trading my Galaxy class for a Warbird! ;)

--

"How much truth can advertising buy?" - iNsuRge - AK47

A wish about hyperthreading... by httpamphibio.us · 2002-10-29 00:46 · Score: 2, Interesting

I just hope hyperthreading is the real deal, not a load of hyperhype.

--
sig.

Re:A wish about hyperthreading... by Webmonger · 2002-10-29 01:00 · Score: 5, Informative

Hyperthreading works well for certain types of software, and awful for others.

Here's an article from Ars Technica on HT/SMT.
Re:A wish about hyperthreading... by Jim+Norton · 2002-10-29 01:02 · Score: 4, Informative

A couple of sites have benchmarked Xeons with HT enabled already (Anandtech and Aces Hardware spring to mind.) It provides a boost in some applications but can actually decrease performance in others. It's rumored that Intel has improved their implementation of hyperthreading but I wouldn't expect the 20-25% performance gains in most applications.

--
-- Jim
Re:A wish about hyperthreading... by The+J+Kid · 2002-10-29 02:10 · Score: 2

I just hope hyperthreading is the real deal, not a load of hyperhype.

You just answerd yourself.
Hyperthreading is just for really dealing with the load.

--
Moderation: +4. Modded 70% Funny and 30% Overrated. 100% Saturated.
Re:A wish about hyperthreading... by EinarH · 2002-10-29 02:22 · Score: 2, Interesting

As the poster before me mentioned Anandtech did a test where they compared Athlon MP vs. Xeons. Both in single and dual setups. This test; Database Server CPU Comparison: Athlon MP vs. Hyper Threading Xeon cand be found here: http://www.anandtech.com/IT/showdoc.html?i=1606 Its actually one of the better tests that they have done. They use their own databases to test the performance; the webDB, the adDb and the forumDB. The smart thing about doing this is that the databases have diffrent characteristics: -the webDB: lots of selects(reads) -the adDB: some selects more stored procedures -the forumDB: selects,inserts and updates After reading this test in April, i wouldnt actually jump on to the conclusion that Hyertreading is a meaningfull "desktop- feature" if you look at price/performance. Actually, i think ist a bit overhyped. -

--
Melius mori in libertate quam vivere in servitute.
Re:A wish about hyperthreading... by BigFootApe · 2002-10-29 09:47 · Score: 1

The guys on the Beowulf mailing list dealt with this a while ago. The general consensus was HT would be effective in applications which have, for instance, threads which do I/O and others which do computation, as well as programs in which memory latency is an issue. Additionally, it was postulated that HT would enable simultaneous int and fp operations. Generally, they found compute bound problems received no benefit -- there is physically no significant mathematical capability added to Hyperthreading CPUs.

The thread begins here. There are some posts which aren't in the thread, but are relevant. Find them here

Units by Flamerule · 2002-10-29 00:47 · Score: 1, Redundant

.. the new P4 who will run at nothing less than 3.06mhz.

Wow... more than 3 millihertz! That is an achievement. It's almost 8000 times slower than my old 486SX.

Re:Units by 91degrees · 2002-10-29 00:52 · Score: 1

And I'll getting a chip to run with one clock pulse every 330 seconds is no easy task.
Re:Units by 91degrees · 2002-10-29 00:54 · Score: 1

A prize to whoever spots the missing word there.
Re:Units by sjoerd_visscher · 2002-10-29 01:01 · Score: 1

I think you mean 8 billion times slower.

A clock cycle takes 5.5 minutes.
If the answer is 42 then that's still an achievement...
Re:Units by 91degrees · 2002-10-29 01:34 · Score: 1

It's about as close to 3.06 milliHertz that I could get to in my head. I aplogise profusely for being about 0.97049% out. I'm sure it makes me look a complete idiot.

I shall restate. I'll bet getting a chip to run with one clock pulse every 326.7973856209150326797385620915 seconds is no easy task. Getting it to run with a clock pulse every 330 seconds is of course, trivial by comparison.
Re:Units by starfish23 · 2002-10-29 08:08 · Score: 1

bet? wager?
Re:Units by 91degrees · 2002-10-29 08:17 · Score: 1

Congratulations. I can only take your first answer, but that was correct. You win a +1 moderation next time I have mod points unless I forget.

3.06 MHz is over 3 times faster than a C64... by neonstz · 2002-10-29 00:49 · Score: 2, Funny

...but the C64 still got better sound.

Re:3.06 MHz is over 3 times faster than a C64... by Tune · 2002-10-29 01:05 · Score: 2, Insightful

> 3.06 MHz is over 3 times faster than a C64...
> ...but the C64 still got better sound.

I agree: despite al the claims about Moore's Law and technological advances, this proves that tripling the speed of a good ol' 6510 CPU has some disadvantages as well: Give a little to gain a little. 8-)

More seriously: graphics have improved since the early eighties, but what about gameplay? Isn't Mame the only thing that really justifies buy PC hardware now and then?

--
Money is the root of all evil (Send $30 for more info)
Re:3.06 MHz is over 3 times faster than a C64... by muyuubyou · 2002-10-29 01:11 · Score: 1

No it's not. The 6502 would be about 4X an equivalently clocked x86, mostly because it fetches memory in a single clock cycle. Add to that the fact of x86 software capable of running at that speeds since it's bloated as hell. Again, ppl believing Mghz = computing power.
Re:3.06 MHz is over 3 times faster than a C64... by Alan+Partridge · 2002-10-29 01:19 · Score: 1

Mghz?? What's that, Magnesium cycles?

--
That was classic intercourse!
Re:3.06 MHz is over 3 times faster than a C64... by Directrix1 · 2002-10-29 01:26 · Score: 1

Mghz = Magnesiums / second. duh!!

--
Occam's razor is the blind faith in the natural selection of least resistance and in universal oversimplification. -- EF
Re:3.06 MHz is over 3 times faster than a C64... by muyuubyou · 2002-10-29 01:28 · Score: 1

Nope Alan. Some ppl use Mg for Mega because there is another m for "milli". Yep, you have case-sensitiveness. But sometimes you don't.
Re:3.06 MHz is over 3 times faster than a C64... by 91degrees · 2002-10-29 01:43 · Score: 1

The 6502 has no pipelining, and is only an 8 bit chip. A single ADC instruction will therefore only add 2 8 bit numbers in 2-6 clock cycles. The Pentium series can handle operations that take an average of 0.5 cycles. These operaions will go up to 32 bits.

So, unless you're talking about an 8086/8, the x86 will probably still be faster at the same clock rate.
Re:3.06 MHz is over 3 times faster than a C64... by AndrewHowe · 2002-10-29 02:19 · Score: 2

Sorry, the 6502 was pipelined.
Re:3.06 MHz is over 3 times faster than a C64... by muyuubyou · 2002-10-30 03:42 · Score: 1

if you understood, 'ppl' is dumb proof enough to post here.
Re:3.06 MHz is over 3 times faster than a C64... by muyuubyou · 2002-10-30 03:57 · Score: 1

What's wrong with "square meters"? again, it's a typographic problem since m^2 isn't quite slick in block ASCII. No big deal, anyway. Next time I'll type Mhz and make everybody happy.

Hmmm... by llin · 2002-10-29 00:50 · Score: 5, Funny

the new P4 who will run at nothing less than 3.06mhz

Yeah, but what's its top speed?

Re:Hmmm... by Jenova · 2002-10-29 01:08 · Score: 5, Funny

>>Yeah, but what's its top speed?

I dunno, it depends of the person throwing the computer I guess?
Re:Hmmm... by catwh0re · 2002-10-29 02:37 · Score: 5, Insightful

the entire P4 design is what you call "long and narrow" with built ins to cope with things like the time it takes for a signal to cross the chip. Namely the P4 is soley designed to be able to be clocked to some very large numbers... I'd say expect P4's at 8GHz, they demo's 4GHz chips just before they were releasing 2GHz.
The true fact in the matter is that intel are going to rely almost entirely on the marketability of a big number with the P4, as it's handling is rather unimpressive when compared to such ordinary designs as those from AMD, which clock poorly, yet crunch happily.
I need not mention about G4's and other well designed chips as some GHz bunny is certain to point out that they are only at 1.25GHz at the moment.
Re:Hmmm... by Jonny+Balls · 2002-10-29 04:01 · Score: 2, Funny

And how likely is it CRASH after hitting THAT top speed? teehee ;)

--
--JonnyBlog
Re:Hmmm... by satterth · 2002-10-29 05:11 · Score: 1

African or European?

--
Being called a dork on Slashdot must be like being called the retard in special ed.
Re:Hmmm... by cheezedawg · 2002-10-29 05:13 · Score: 3, Insightful

The true fact in the matter is that intel are going to rely almost entirely on the marketability of a big number with the P4, as it's handling is rather unimpressive when compared to such ordinary designs as those from AMD, which clock poorly, yet crunch happily.

I disagree. Intel's strategy of designing for higher clock speeds has given them a much more scalable chip, and that is evidenced by Intel's ability to increase the clock speeds frequently while AMD is struggling. And if you look at the last Toms hardware review (its a couple of weeks old), the P4 2.8 GHz pretty much tied with the Athlon 2800 (they both won about 14 benchmark tests). But that is much less meaningful when you realize that Tom was testing an Intel chip that has been available for 2 months with an Athlon that won't be available until December. If you compare the 2.8 GHz P4 with the fastest available Athlon today, the P4 beats it in over 90% of the benchmarks (I'd imagine that a comparison between the 3.06 GHz HT chip and the Athlon 2800+ would be similar). So Intel's strategy is working for performance, and it is more marketable to boot.

And there is a lot of research right now about the optimal pipeline depth, and the conclusion was that the current pipelines are not deep enough. The optimal pipeline depth for the x86 architecture is around 40-50 stages.

http://systems.cs.colorado.edu/ISCA2002/FinalPaper s/hartsteina_optimum_pipeline_color.pdf
http://systems.cs.colorado.edu/ISCA2002/FinalPaper s/Deep%20Pipes.pdf

BTW- thanks to fobef for these links- I read them yesterday on /.

--
"The defense of freedom requires the advance of freedom" - George W Bush
Re:Hmmm... by Anonvmous+Coward · 2002-10-29 05:14 · Score: 2

"The true fact in the matter is that intel are going to rely almost entirely on the marketability of a big number with the P4, as it's handling is rather unimpressive when compared to such ordinary designs as those from AMD, which clock poorly, yet crunch happily."

Intel changed their architecture, they didn't just crank up the numbers. Now they're working with developers to take better use of it.

Case in point: Lightwave 7.5. 3D rendering app, needs to render as fast as possible. I did a benchmark yesterday comparing LW on an Athlon machine and a P4 machine. Guess what? MHZ to MHZ, the Athlon was maybe 1 or 2% faster than the P4. (And no, I was going by the actual mhz rating on the processor, not the inflated marketing number)

Intel worked with Newtek to P4 optimize LW. Seeing as how the Intel chips are the fastest on the market right now (mhz wise), wouldn't that imply that there's something to the P4 architecture?

In any event, if AMD has a trick up their sleeve, now'd be a good time to pull it. They're not so interesting in my eyes these days.
Re:Hmmm... by catwh0re · 2002-10-29 05:46 · Score: 1

The current AMD chip was not designed to be anything faster than around 2.5GHz, it's design has yielded it's maximum gains already(1.3 to 1.6 GHz ranges), all MHz increases now will not result in the large performance increases that we have seen in the past with the chip.
On the Intel side of things upping the clock speed in Pentiums isn't showing much performance increase either. What you've neglected to bring to light is that AMD are keeping competitive with comparitively 'slower' chip speeds. At fractions of the cost. AMD have a new chip in the works which will take over competition with the P4, from the now failing Athlon XP line. You also mentioned the Athlon 2800+ which I need not remind anyone is not clocked any where near the 2.8GHz Pentium 4 despite being almost identical performance.
Additionally there seems to be commentary about the P4 being a great performer, this is true, they all are. However when software is optimised for a certain chip (it's certain extra instructions) you will always find that it's apparent performance is considerably better than to those which are not optimised.(Apple users appreciate the G4 and well designed software for this exact same rule of design with Altivec.) However software can't reprogram itself to take advantage of the P4 multimedia extensions.
To use simple terms, the Athlon has a faster area to process ordinary unoptimised data. The P4 has a slower area to process ordinary unoptimised data, however this is compensated for with many chip-extensions that can make the chip process data in a more parallel fashion, and thus when software is optimised to take advantage of these extensions the net result is a faster chip. Don't optimise this data and you find yourself relying too heavily on this generic area and the chip will appear slower. This specifically accounted for why P4's appeared to be so slow when they were first introduced, when the reality was that there was no software optimised for them yet.
I hope this clears things up.
Re:Hmmm... by catwh0re · 2002-10-29 05:54 · Score: 2, Interesting

All that this shows is that you must fully optimise your software to the P4 extensions for it to match Athlon ratings in MHz to MHz. I wonder what would happen if it were optimised the the extensions found in the Athlon processor.
In any regard the argument still stands that present software can not reprogram itself to take advantage of the P4's extensions. It was smart of AMD to have a stronger floating point unit, when Intel decided it wanted to go technically superior in chip design.
Also it's a given that Intel changed the architecture, they had plenty of marketing to show that fact, it's trivial that this was the case, hence the whole discussion on the 'long and narrow' P4 design, and how this related to what a user (see top most thread) could expect the P4 to be maxing out at. I suggested 8GHz, however I would not be surprised in the least to find 15GHz Pentium chips eventually. (Remember once apon a time 1.036MHz were valid chip speeds.)
Re:Hmmm... by McCart42 · 2002-10-29 06:32 · Score: 2

AMD has been losing the speed war for several months now, but I think they have been winning the price war all along - comparable-speed Athlons have been much cheaper than their Pentium equivalents. As the sig says though, I could be wrong.

--
"I may be quite wrong." - Socrates
Re:Hmmm... by Anonvmous+Coward · 2002-10-29 06:34 · Score: 2

"In any regard the argument still stands that present software can not reprogram itself to take advantage of the P4's extensions. It was smart of AMD to have a stronger floating point unit, when Intel decided it wanted to go technically superior in chip design."

Oh I definitely agree with that. AMD made a wise move, and if they can make their 64-bit processors realistic then they'll always be a pain in Intel's side. Good for everybody. :)
Re:Hmmm... by cheezedawg · 2002-10-29 07:22 · Score: 2

AMD has been losing the speed war for several months now, but I think they have been winning the price war all along

Not really. In most cases, the Athlon model number is chosen to reflect which Pentium 4 speed it competes with. Therefore, the Athlon 2400+ on average performs about as well as the 2.4 GHz P4 in the benchmarks. If you look at the latest prices, the Athlon 2400 is $3 more than the P4 2.4 GHz.

A friend of mine recently built a new computer, and he was choosing between the P4 2.53 GHz and the fastest Athlon available (which did not perform as well as the P4). After adding the costs up for both systems, the P4 system about $10 more. I don't see that as a big win in the price war.

--
"The defense of freedom requires the advance of freedom" - George W Bush
Re:Hmmm... by cheezedawg · 2002-10-29 07:30 · Score: 2

I think you are missing the point. Intel is fully aware that the IPC of the P4 is less than the Athlon, but they are far enough ahead in the MHz that it more than makes up for this. That is the design philosophy of the P4. Intel is confident enough in this philosophy that they expect the P4 to have increased speed enough by the time Hammer is released (still another 6 months) that it will outperform Hammer. Only time will tell if this is true.

--
"The defense of freedom requires the advance of freedom" - George W Bush
Re:Hmmm... by McCart42 · 2002-10-29 08:20 · Score: 2

I don't usually use Pricewatch, because companies often list misleading low prices with expensive shipping, just to get lower in the guide and get more purchases (bait and switch). Anandtech's latest price guide shows a P4 2.53 GHz at $189, and the closest Athlon is a 2400+ at $194. So you're right, at the cutting edge. But for what I just bought, an Athlon 2000+ (1.67 GHz) for $95, a Pentium 4 would be foolish--it costs $160. Yeah, with the newest bleeding edge Athlons, AMD can't compete - like I said, they're not winning the speed war. But for the majority of their chips that have been out (anything 2200+ and older), the prices are much lower. That's why I said they were winning the price war. For those who are willing to pay $200+ for a chip, go Intel by all means.

--
"I may be quite wrong." - Socrates
Re:Hmmm... by pellaeon · 2002-10-29 08:20 · Score: 1

I seem to remember a leaked bench about a Hammer that ran at something like 800MHz but outperformed a 2+GHz P4. If that was true, and considering implications are that Hammer will debut at 2GHz or more, it will surely give P4 a run for Intel's money...

--
-- /bin/coffee missing. universe halted.

will be expensive by Graspee_Leemoor · 2002-10-29 00:52 · Score: 3, Insightful

It's interesting to see what the cutting edge is capable of, but you pay such a stupidly massive premium for the latest processor that only fools would use their own money to buy it.

In the UK you usually have the ultimate latest Intel at about 700 UKP- the sweet spot in the price/performance trade-off tends to be around the 200 UKP mark, which will probably be the 2.5Ghz by the time this 3Ghz one is out.

graspee

Re:will be expensive by MikeDX · 2002-10-29 00:57 · Score: 2, Informative

What's nice about that is that the new 1.7 P4's will easily overclock to 2.6Ghz+, so you are getting almost a Gig free for just knowing which switches to push.
Re:will be expensive by Alan+Partridge · 2002-10-29 01:22 · Score: 1

a free Gig you say? Who's playing, and which switches do I have to push?

--
That was classic intercourse!
Re:will be expensive by Craig+Davison · 2002-10-29 06:19 · Score: 1

For someone so pedantic lately, you sure do have a grammatically awkward sig:
I have won the essay writing competition, of that there is NO doubt - Alan Gordon Partridge
You mean: I have won the essay writing competition. Of that, there is NO doubt. - Alan Gordon Partridge. Your sig is a comma-splice.
Plus, what kind of douchebag quotes himself?

--
Hands in my pocket

what's my motivation by rob-fu · 2002-10-29 00:54 · Score: 4, Interesting

"You won't see a heck of a lot of difference in Word, but software like [Adobe Systems'] Photoshop or video-rendering software will benefit considerably," he said.

How can Word appear any faster at 3GHz? I would think that after 1.5GHz, improvement in performance would be hard to notice. Granted, it will be good for people who are still running those 200MHz clunkers but what's the incentive if you're already running in the GHz range?

Re:what's my motivation by AKnightCowboy · 2002-10-29 01:03 · Score: 3, Informative

How can Word appear any faster at 3GHz? ...
Granted, it will be good for people who are still running those 200MHz clunkers but what's the incentive if you're already running in the GHz range?

Unfortunately where I work the secretaries for division heads get these 3GHz machines and run Word on them while the scientists and technicians get to keep working on their Pentium 200MHz system. Maybe if they're lucky they get a hand-me-down from a secretary like a nice PIII-1GHz box. :-)
Re:what's my motivation by cybrthng · 2002-10-29 01:03 · Score: 5, Interesting

I think you over simply todays word & document processing.

For example, we use Microsoft word with built in excell spreadsheets and ODBC queries that update charts in real time from an Oracle database as well as include visio stencils and other good stuff. This is a 40+ meg file in raw format and a lowly 1.5ghz with 512 megs of ram takes time to re-draw. We daw a huge performance increase from 1.5ghz to 2.4 Maybe "hyper threading" will help out even more.

BTW, it is about the same performance under linux using staroffice or corel office. KDE Office is even slower, so i know its not just the tools :)

For people who *WORK* using there pc, you can never have "too much" power. Its like race cars, maximizing performance for the job at hand.
Re:what's my motivation by Anonymous Coward · 2002-10-29 01:06 · Score: 2, Insightful

Correct - Word, Excel, and general Windows GUI operations - or, if you prefer, OpenOffice, KDE etc - won't show any improvement, and indeed the benefit for these apps (in terms of what the end-user perceives) began to diminish once processors passed the 6-700MHz mark.
Where this kind of power shows, though, is in more intensive processing - as the article suggests, Photoshop, Cinema4D, and so on.

As for Hyperthreading / SMT technology - it absolutely does make a difference. I've been running an HT-enabled system (pre-release silicon) for some time, and there are specific usage models where it shines. Forget about single-threaded or single-tasking type environments - the user who loads Word, does some typing, then loads Photoshop, does some filtering, etc, isn't going to see any benefit at all from HTT. However, once you get into multi-tasking scenarios the story is very different. For example, run a series of Photoshop filters/macros whilst simultaneously virus-scanning the system; or, export a large Outlook folder to a .PST archive file whilst WinZIP-ing a large folder. All quite credible usage scenarios (who here can say, "that's preposterous! no-one would EVER want to do such a thing!"..?) and the difference between an HT- and non-HT-enabled system is dramatic - of the order of 20-30% time saved.
Re:what's my motivation by FeloniousPunk · 2002-10-29 01:14 · Score: 1

This is so common it makes me cry. In every office that significant fraction of humanity still operating at the instinctual level is well represented; pull them out of their suits and dresses and plop them into animal skins and you have cavepeople. Too many places I've worked did managers and their toadies grab the best machines out of a primal need for status and leave the people who actually need the good machines with the bottom of the heap.

--
I know this because Tyler knows this.
Re:what's my motivation by Alan+Partridge · 2002-10-29 01:27 · Score: 3, Interesting

tell me about it. Our RECEPTIONIST just got an 18.1 inch Sony flat panel (costing easily over £1000) while the graphics dept. are still using horrid 17inch no-name uncalibrated CRTs, the total value of ALL of which is less than the cost of the reception monitor...

--
That was classic intercourse!
Re:what's my motivation by Anonymous Coward · 2002-10-29 01:33 · Score: 2, Insightful

"You won't see a heck of a difference in Word..."

So why are you asking "How can Word appear any faster at 3GHz?" It won't, but Adobe Photoshop blah blah will use as much as you can give.....

Stu.
Don't mind me I drank too much at tonight uni function. tee hihee. :)
Re:what's my motivation by bjb · 2002-10-29 01:35 · Score: 5, Funny

How can Word appear any faster at 3GHz?

The speed is for Clippy, not YOU... he now is 3D ray-traced and has more artificial intelligence built in!
If it wasn't for the idea of WYSIWYG and fonts, I'd still be doing my word processing on AppleWorks for the Apple ][.

--
Never hit your grandmother with a shovel, for it leaves a bad impression on her mind...
Re:what's my motivation by dipipanone · 2002-10-29 01:38 · Score: 2, Interesting

I was in Government Office in Bristol a couple of weeks ago, and happened to notice that the receptionists were sitting on a couple of Herman Miller Aeron office chairs, nice things that cost around 700 UKP a pop.

When I went upstairs though, I noticed that all of the big knob senior civil servants were sitting on fifty pound clunkers from Staples or some such.

I thought the whole deal was quite heartening and very democratic, myself.
Re:what's my motivation by Alan+Partridge · 2002-10-29 01:46 · Score: 1

funnily enough, we ALL have Aeron chairs here as our old accountant had a friend in the furniture business and we got them for £300 each. They're pretty good chairs, to be sure, but I think the money could probably have been better spent nonetheless.

--
That was classic intercourse!
Re:what's my motivation by psavo · 2002-10-29 01:49 · Score: 2

How can Word appear any faster at 3GHz?

Well, it can't. I recently upgraded my machine from 200Ppro to 2x1800, and Word hasn't sped up a shit. It still pauses to think for some quarterseconds, not very long but very noticeable. So I think there's some other problems with word, it just doesn't seem to work correctly.
All the applications in Linux though have sped up tremendously. I knew that SMP evens the system load, but thought that there wasn't that many multithreaded applications, but the system just feels silken smooth (I first ran it with 1 processor, before modding XP's L5 bridge so they appear as MP).

--
fucktard is a tenderhearted description
Re:what's my motivation by zenyu · 2002-10-29 02:25 · Score: 3, Insightful

How can Word appear any faster at 3GHz?
Users do stupid things.
I've seen vector graphics with millions of lines inserted into word. Fine for a drawing package or desktop publishing app, but god awful slow in Word. Not really a fault of MS, it's these people should be using a desktop publishing application, Word is for wordprocessing.
Re:what's my motivation by gosand · 2002-10-29 02:34 · Score: 2

....."You won't see a heck of a lot of difference in Word, but software like [Adobe Systems'] Photoshop or video-rendering software will benefit considerably," he said.
How can Word appear any faster at 3GHz? I would think that after 1.5GHz, improvement in performance would be hard to notice. Granted, it will be good for people who are still running those 200MHz clunkers but what's the incentive if you're already running in the GHz range?
How can you quote something from the article and not even read it? It says you won't see much difference in Word, and you turn around and say "How will Word be faster?". Don't you even read what you cut and paste?
Strange days when people bitch about technology getting better.

--

My beliefs do not require that you agree with them.
Re:what's my motivation by Lumpy · 2002-10-29 03:10 · Score: 2

Ummm BULLCRAP...

Adobe premiere does NOT take advantage of a 3 GHZ processor.. espically when you are waiting for RAM and the Hard Drives in the first place.

A P-III 866 is plenty fast enough for Adobe Premiere and After effects.. jumping up to a 64Bit PCI bus a U160 scsi card and a Raid 5 array of U160 drives along with anything that has either lots of Rambus RAM or something faster will help. computing power is not needed in any of those apps. Hell the Latest AVID setups... the real ones not that AvidDV toy or that AvidExpress toy... still use older IBM P-III and P-4 machines.

--
Do not look at laser with remaining good eye.
Re:what's my motivation by Drakonian · 2002-10-29 03:15 · Score: 1

How can Word appear any faster at 3GHz? I would think that after 1.5GHz, improvement in performance would be hard to notice.
Well actually, you won't see a heck of a lot of difference in Word. Some software, like Photoshop or video-rendering software will benefit considerably.

--
Random is the New Order.
Re:what's my motivation by spike+hay · 2002-10-29 03:25 · Score: 2

The speed is for Clippy, not YOU... he now is 3D ray-traced and has more artificial intelligence built in!

I saw this poster (Microsoft-sponsored) in my CompTech room that detailed major advancemencements in computing in the last 100 years. In 1997, it said: "Microsoft introduces artificial intelligence into Microsoft Word." Heh.

Now they got the very, very annoying search dog in XP that I can't get rid of.

--
If you don't understand any of my sayings, come to me in private and I shall take you in my German mouth.
Re:what's my motivation by ChaosDiscord · 2002-10-29 03:42 · Score: 2

For example, we use Microsoft word with built in excell spreadsheets and ODBC queries that update charts in real time from an Oracle database as well as include visio stencils and other good stuff.

What exactly is it that you do that the above is considered valuable and a reasonable investment of your time? Most of the time when I hear examples of this sort, they're entirely contrived and don't occur in the real world. I'm interested in hearing about cases where the end result is valuable to the company, and the value exceeds the effort of the humans creating it.
I can certainly see embedding an Excel spreadsheet and some Visio diagrams into a Word document (here's the financial report with the "big picture" table embedded and some process flow diagrams). I'm less clear on the value of pulling real time updates into your document. If you're mixing text from Word, a spreadsheet, and diagrams, presumably you're creating a document for printing and distribution (or at least electronic distribution). Do you really want to distribute this document without being certain exactly what real-time changes made it in? If you really want real-time, what about the lack of real-time updates to your descriptive text in word and your diagrams?

--
Search 2010 Gen Con events
Re:what's my motivation by timeOday · 2002-10-29 03:49 · Score: 3, Insightful

Is your receptionist sitting out where people can see her/him? That's often why these things happen. The company is investing in its image.
Re:what's my motivation by MagPulse · 2002-10-29 03:49 · Score: 2, Insightful

Say what you will about .NET and Java, but there are hoardes of programmers waiting for the average PC to be fast enough to run managed code without breaking a sweat. When entry level computers are in the 2-3GHz range, managed applications will be very popular.

I also agree with the other poster about word processing being a much more complicated task today than you think.
Re:what's my motivation by crawling_chaos · 2002-10-29 04:00 · Score: 3, Informative

Now they got the very, very annoying search dog in XP that I can't get rid of.
Unless your system is locked down, click on "Change my preferences" in the Search Pane and choose "Without an animated character." I did that so long ago that I hardly remember that the dog was there in the first place.

--
You can only drink 30 or 40 glasses of beer a day, no matter how rich you are.
-- Colonel Adolphus Busch
Re:what's my motivation by Anonymous Coward · 2002-10-29 04:40 · Score: 1, Funny

For people who *WORK* using there pc
All that power in your office application suite, but no grammar checker for your web browser.
Re:what's my motivation by AftanGustur · 2002-10-29 04:53 · Score: 2

How can Word appear any faster at 3GHz? I would think that after 1.5GHz, improvement in performance would be hard to notice.
Two words: "Office XP"

--
echo '[q]sa[ln0=aln80~Psnlbx]16isb572CCB9AE9DB03273snlbxq' |dc
Re:what's my motivation by be-fan · 2002-10-29 05:16 · Score: 2

I'm sitting on a 2 GHz machine right now, and boy I wish I had a 3 GHz machine so I could run Konqueror faster! Hell, maybe if I had a 3 GHz machine, Konsole wouldn't take so freaking long (over half a second) to start up! Yes, my terminal app isn't fast enough! It used to be that Quake kept me buying faster hardware. Now, its KDE!

--
A deep unwavering belief is a sure sign you're missing something...
Re:what's my motivation by Sabalon · 2002-10-29 05:24 · Score: 2

True...typing "Dear John" won't happen any faster, but the system could be doing a lot of other things with the extra cpu time - faster speech recognition, reading your letter back to you as you type, rendering fonts better, etc...
Re:what's my motivation by pmz · 2002-10-29 05:27 · Score: 2

For example, we use Microsoft word with built in excell spreadsheets and ODBC queries that update charts in real time from an Oracle database as well as include visio stencils and other good stuff.

This is just a mistake. What's Microsoft's support lifecycle for Word, Excel, and Visio? Oracle shouldn't be a problem, but Microsoft just prefers to shove, shove, shove.

--
Healthcare article at Kuro5hin
Re:what's my motivation by thatguywhoiam · 2002-10-29 05:33 · Score: 2

Users do stupid things. Not really a fault of MS
Yeah, it is MS's fault. If their shitty program can't figure out that the user just wants to add some art, and make the appropriate conversions, then that is bad design.
Not trolling; just saying. I don't think it's unreasonable for the app to attempt to make the user's command feasible. If we're talking something like dropping a 40MB QuickTime onto Outlook, sure, you don't want to re-render to a smaller size... and the app should let you know what has happened.

--
If Jesus wants me it knows where to find me.
Re:what's my motivation by Milican · 2002-10-29 05:34 · Score: 2

Thats funny, because when I am doing video capture with codecs like DivX my processor just can't keep up. I guess the 100% CPU on my Athlon 1.4GHz is just a figment of my imagination.

JOhn

--
Campaign for Liberty
Re:what's my motivation by emarkp · 2002-10-29 05:40 · Score: 1

For people who *WORK* using there pc
Apparently, even with 1.5GHz and 512 MB RAM, the spell checker still doesn't work...
Re:what's my motivation by tres · 2002-10-29 08:02 · Score: 1

HA HA HA HA HA HA

My god, someone around your company must be big into S & M. I can't believe anyone trusts Word for anything more than memos & letters.

People who *WORK* with their pc know how to pick the right tool for the job.

Thanks, this will have me laughing all day.

--
Notes From Under *nix: blas.phemo.us
Re:what's my motivation by pellaeon · 2002-10-29 08:32 · Score: 1

Amen. Damn, I wish I had the money to buy all the researchers I support good machines!

Ah well, universities will never be rich enough for that (not the one *I* work at, anyway).

--
-- /bin/coffee missing. universe halted.
Re:what's my motivation by Alan+Partridge · 2002-10-29 09:02 · Score: 1

of course she is, but - IMHO - the image of our copany is better served by producing better quality work, and to do that we need to invest money strategically. I just think it's putting the cart before the horse (and I still haven't got over the #7500 they wasted on the plasma screen, either).

--
That was classic intercourse!
Re:what's my motivation by smallstepforman · 2002-10-29 09:54 · Score: 2

Hey, we must be collegues. OK, stand up and wave so that I may see you.

--
Revolution = Evolution
Re:what's my motivation by spike+hay · 2002-10-29 10:17 · Score: 2

Unless your system is locked down, click on "Change my preferences" in the Search Pane and choose "Without an animated character."

Thank you!

--
If you don't understand any of my sayings, come to me in private and I shall take you in my German mouth.
Re:what's my motivation by spike+hay · 2002-10-29 10:21 · Score: 2

I have two computers: Athlon XP 1600 running linux, and a 633 Celery running XP. I have photoshop installed in the older machine, and it works fine for my purposes. Unless you are a graphic designer, I can't really see the need for a 3 Ghz chip.

--
If you don't understand any of my sayings, come to me in private and I shall take you in my German mouth.
Re:what's my motivation by purrpurrpussy · 2002-10-29 11:41 · Score: 1

If it wasn't for fussy people insisting that I use Word to embelish everything to the Nth degree and have 8 different fonts on a simple memo I'd still be using microEmacs on a CLI with VT102.

I reckon I wrote better code faster using make, cl and microemacs on DOS than I do using Visual Studio on Windows too, but I think that may just be me getting old and stoopid!!

--
"None of this shit works" -W.Shatner
Re:what's my motivation by crawling_chaos · 2002-10-30 01:01 · Score: 1

No sweat.

--
You can only drink 30 or 40 glasses of beer a day, no matter how rich you are.
-- Colonel Adolphus Busch
Re:what's my motivation by Lumpy · 2002-10-30 01:13 · Score: 2

compressing to something that is of low quality does take lots of processing power. Most professional systems do not compress to such extremes as the resulting project is designed for airing on television and thus cannot use such low-quality codecs. DV is the current Codec standard used high bitrate high quality and needs GIGANTIC hard drive pipes and ram speed... cince it takes only a tiny processor to compress/decompress DV video or anything like MPEG2 it is not needed.

Plus what you are doing is massively different than video editing and rendering...

compressing to a codec and video editing are different. If you would like to learn more about video editing and other things that professionals do with their computers in the video arena you can do a search on google for adobe premiere and AVID.

besides, if you are doing anything other than playing around you get hardware that does it for you. My DV500 from pinnacle captures analog video and converts it into mpeg2 or even DV in the hardware with better quality than any software app can accomplish and I output through a professional Mpeg/DV decoder card when I'm not sending the video through the firewire direct to the deck.

I can do all this on a Pentium II-400 easily (that's exactly what the old AVID setup at work is). so processor is NOT an issue in video editing.

--
Do not look at laser with remaining good eye.

Re:I'm not impressed by Ctrl-Alt-Del · 2002-10-29 00:54 · Score: 1

Actually that's 3 milli-hertz, not 3 hertz. Therefore it's out by a factor of 10^12...

--
"Life is like a sewer - what you get out of it depends on what you put into it" - Tom Lehrer

Wow, hyperthreading. by puto · 2002-10-29 00:56 · Score: 3, Insightful

Disregarding all of the comments on the 3.06 typo. Geez, I remember the day when we use to comment on processors, peripherals, parts. Now the community is stuck on whining about typos. Read it, chuckle to self,move on.

Anyway they have ramped up the speed, and added something that could have always been, hyperthreading. Xeon has always had it. This is not progress, this is almost not worthy reporting.

Puto

--
The Revolution Will Not Be Televised

Re:Wow, hyperthreading. by Frodo2002 · 2002-10-29 01:43 · Score: 2, Insightful

Yes, mod me offtopic if you like. I think why people whine about the spelling errors is simply because /. is not a little news service for a bunch of computer geeks. Millions of people all over the world (90% of them smartarses like myself) read it and it seems really embarrassingly pathetic when the author and the editor do not know the difference between milli (m) and mega (M) and the fact that the P4 must be running at GigaHertz (GHz). Well... I am embarrassed for them.
Re:Wow, hyperthreading. by puto · 2002-10-29 01:56 · Score: 2

Man,

I know where you are coming from and if you look through my past posts you will note they are rife with grammatical and spelling errors. Sometimes I multitask and the least amount of attention is focused on what I am posting on slashdot. More content that checking my punctuation.

You are right though. It is embarassing to have our community display such glaring errors in a a public format.

I think the problem is that all the kiddies are just trying to get an article posted that they gleaned off of some other venue, and in their haste to submit before anyone, they type whatever they can, and submit without proofing. Did I mentions couples with the fact they have Slashdot open in a window at work that they keep minimizing when a supervisor walks by.

At least the editors should proof the articles for basic spelling and grammar, typos, especially when they are that small like the current topic. And if they are reading the comments they can go in and change it, fix it.

However, what is worse are the 1000 posts pointing it out. Like we do not all see it, like once was not enough.

I would rather see a reduction of the "hey your stupid comments" as well as some editorial proofing as well.

However, Slashdot is not run by language scholars.

We need to clean up the submissions and the comments.

Puto

--
The Revolution Will Not Be Televised
Re:Wow, hyperthreading. by tswinzig · 2002-10-29 02:21 · Score: 2

Disregarding all of the comments on the 3.06 typo.

Actually they got that part right.

Geez, I remember the day when we use to comment on processors, peripherals, parts. Now the community is stuck on whining about typos.

What exactly is there to talk about in yet another processor speed improvement story? Some people will say "who needs this much power?" Some people will respond and explain to these dolts who needs it. Others will make fun of the article submission. And then there are people who complain that the article was posted in the first place.

This is not progress, this is almost not worthy reporting.

See?

--

"And like that ... he's gone."

Bah by Brian+Stretch · 2002-10-29 00:57 · Score: 4, Informative

Or you can build a dual processor Athlon system for less money. No need for HypedThreading.

It has been reported on various sites that Athlon XP 2400+ chips (2GHz, new Thoroughbred Revision B core) are trivial to mod for dual CPU operation and easily overclock to 2.25GHz (150MHz FSB, aka 300MHz DDR, which is the most my ASUS A7M266-D will allow) with proper cooling (Thermalright SLK800 being my favorite). The chips are under $200 apiece. Imagine a Beowulf cluster of those...

Proper Athlon MP 2400+'s are due shortly I'd assume.

Re:Bah by hendridm · 2002-10-29 03:11 · Score: 4, Funny

> are trivial to mod for dual CPU operation and easily overclock to 2.25GHz

Some of us need reliability and warranty. I'm not going to throw an overclocked, modded AMD POS in the server farm at work. If I do, I'm going to make sure my resume is updated and my suit is free from little white fuzzies.

I'm gonna go overclock my laundry machine now and cook a pizza in self cleaning clean mode in my oven. Should be done by the time the laundry dings.
Re:Bah by drightler · 2002-10-29 03:37 · Score: 1

Really? AMD Athlon XP 2600+

--

blah blah blah....
drightler@technicalogic.com
Re:Bah by Brian+Stretch · 2002-10-29 04:34 · Score: 3, Interesting

Fine, read this and pick out a prebuilt Athlon MP 2200+ server for your server farm. It's STILL better/cheaper than buying a 3GHz P4.
Re:Bah by hendridm · 2002-10-29 04:40 · Score: 1

> It's STILL better/cheaper than buying a 3GHz P4.

Ok, I'll give you that one. Your solution is cheaper, and arguably better, that buying a 3GHz Intel chip (for now). I'd like to see an Athlon, however, beat an Pentium 4 running Rhambus on an Intel mainboard in stability tests, but I'm sure someone will post a comparison link any second now.

Then again, I work at Best Buy, so I probably don't know what I'm talking about :)
Re:Bah by Brian+Stretch · 2002-10-29 05:45 · Score: 2

I'd like to see an Athlon, however, beat an Pentium 4 running Rhambus on an Intel mainboard in stability tests

AMD systems are just as stable as Intel systems, the main variable being the competence of whoever built the system. If you don't use a decent power supply, don't install Windows service packs and semi-current drivers, etc, you'll have an unstable system, just like the garbage Dell Optiplexes we spent considerable time debugging here at work. High-volume websites have been using Athlon MP systems for quite some time now without trouble. My custom-built Athlon MP and XP systems have been solid as well.

And it's Rambus, not Rhambus.

Then again, I work at Best Buy, so I probably don't know what I'm talking about :)

Yup :-)

Yippie! by Anonymous Coward · 2002-10-29 00:59 · Score: 3, Funny

I'll be able to run Word really fast now.

Re:Yippie! by keller · 2002-10-29 01:20 · Score: 1

You will be able to speak really fast?

--
Enig? Det alt for hot det smor!
Re:Yippie! by dalamcd · 2002-10-29 04:05 · Score: 1

Really veteran Word users can curse it probably 3-4 times a second...
dalamcd

--
moer liek CELtroid prime!!@1!

Hyperthreading ... by RinkSpringer · 2002-10-29 00:59 · Score: 5, Interesting

Humm, this raises a point for me. Of course they claim it is faster, but when exactly ?

I mean, is it faster when doing stack swaps or when using TSS to multitask? *BSD uses the TSS to multitask, taking benefit of the i386's way to quickly swap registers and stack. Windows doesn't do this ...

So, from a pure technical point of view, how does it work? Did they just make TSS switches faster? Some OS-es benefit highly from that, but others, well, don't.

Re:Hyperthreading ... by Doctor+Faustus · 2002-10-29 01:26 · Score: 4, Interesting

Ignore Intel's "Hyperthreading" name. There was already an established name for the technique, Symetric Multi-Threading (SMT). The basic concept is that, since most of the CPU's pipeline is usually going to waste due to stalls, especially in a CPU with a pipeline as deep as a P4, the one physical CPU can pretend to be two CPU's. When instructions for one CPU stall, the pipeline can switch to instructions for the other.

This would have been a lot harder a few years ago, but most of the hard parts (like register renaming) had already been done to implement out-of-order execution.

As for what can benefit, it's pretty much anything that can benefit from dual CPU's.
Re:Hyperthreading ... by Webmonger · 2002-10-29 01:30 · Score: 2

Actually, they call it "hyperthreading" because there was already a more limited form called "superthreading".
Re:Hyperthreading ... by Ben+Hutchings · 2002-10-29 01:58 · Score: 2

So, from a pure technical point of view, how does it work?

The processor can appear as two logical processors and run two threads through the same core. RTFA for more information.
Re:Hyperthreading ... by hypersqurl · 2002-10-29 07:38 · Score: 2, Interesting

The Simultaneous Multithreading technology was coined as hyperthreading by Intel. It was originally developed at the University of Washington by one of my professors and some of her colleagues. Check out the SMT page for a brief overview of how it works and links to many technical papers describing it in more detail.
Re:Hyperthreading ... by Analog+Squirrel · 2002-10-29 07:54 · Score: 2, Interesting

If you want an extreme example of this concept, check out the Cray(formerly Tera) MTA system. It sports 128 threads per processor - that is, 128 complete sets of registers. The idea is to tolerate memory latency while still being able to keep your pipelines full. An intersting fact is that they use a flat memory architecture - no caches! The cost is they need a lot of bandwidth to keep data moving properly from memory to the registers...

--
I'd rather be flying

Incentive? by Gruneun · 2002-10-29 00:59 · Score: 5, Funny

Unreal Tournament 2003 just kicked my 1.0 GHz machine in the nuts and then made fun of me. If for no other reason, I'm glad to see this announcement, because I can expect a price drop on the 2.6 GHz and 2.8 GHz chips.

Re:Incentive? by Anonymous Coward · 2002-10-29 01:33 · Score: 1, Informative

The key to fast 3d is not how fast your procesor is, but how little it has to do. the better[1] your gfx card the less there is for the processor to do and the faster it will run. A better gfx card will almost always be a bigger win than a faster cpu for these types of games.

[1] better meaning one which implements in hardware more of the functionality used by the game.
Re:Incentive? by Toraz+Chryx · 2002-10-29 02:02 · Score: 2

Yes, but a 2.8Ghz P4 with a Radeon 9700 will outrun a P3-800 with a Radeon 9700.. all other things being equal.
Re:Incentive? by Zathrus · 2002-10-29 02:11 · Score: 2

Uh... turn off a lot of the crap man.

I'm running UT2k3 on an Athlon 750 with a GF2. I run at 800x600 with low qual textures/models and most options turned off. Yes, it's much more pretty on a fast system, but it certainly didn't "kick my [...] machine in the nuts".

Yes, I'm planning to upgrade, but I was pleasantly surprised at how well this 2.75 year old machine handled UT2k3.
Re:Incentive? by Gruneun · 2002-10-29 02:29 · Score: 2

I am running a GF2 at 800x600 with most of the stuff at "normal" settings. It runs fine. The first thing I tried were max settings, slowly moving backwards until the gameplay was acceptable. However, the beauty of the new game is in the texture/model quality and detail. Running at anything less than max settings is unacceptable and defeats the purpose of the new game.

After all, I'm sure the original Quake runs great on my machine and several slower processor-based iterations, but It's no longer the quality I demand from my games.
Re:Incentive? by Gruneun · 2002-10-29 02:37 · Score: 2

Unless your processor isn't pushing the graphics card to its limits. Honestly, do you think that there's anyone out there who doesn't know the benefits of 3D cards by now?
Re:Incentive? by spike+hay · 2002-10-29 03:20 · Score: 2

I tried to run UTk3 on my XP 1600 last night under 1200x1600. It raped my computer! ;-)

I'm hoping the Opteron actually comes out on schedule or else I might be forced to switch to the Dard Side. (Hey, I need to be able to run Doom 3 when it comes out.)

--
If you don't understand any of my sayings, come to me in private and I shall take you in my German mouth.
Re:Incentive? by Zathrus · 2002-10-29 04:30 · Score: 1

What FPS gamer want to run at 800x600 with the all of the options turned off?

Want? Nah. But the point is that it's capable of being played, and played well. It's freaking eye candy. Most of which is ignored if you're actually playing instead of standing around drooling.

Of course, who am I to say? After all, I'm only in the top 90%th percentile for UT2k3 CTF (currently in the top 100 weekly), and back when I played UT I ranked in the top 20 for Domination. Obviously I'm not an FPS gamer.

I love the anti-upgrade crowd on Slashdot

Wow you're an idiot. I even said that I was planning to upgrade - the OP, however, said that his computer couldn't play UT2k3. Eye candy has nothing to do with being able to play.

If you have to turn off everything why even bother playing the game

Because it's fun? Because I enjoy actually playing rather than staring? As many others have pointed out, it's about the game play stupid. Having to turn down the textures doesn't affect that in the least. Turning them up doesn't hurt either, as long as you have a system that can handle it.

If you want to be a gamer its costs money Period

Yes, but it doesn't mean that you have to upgrade every 6 months and waste tons of money in the process. Realistically, I should've upgraded 9 months ago. And I happily admit that my computer is at the bottom end of useful for game playing. All I objected to was the OP's statement that his computer couldn't play UT2k3.
Re:Incentive? by RabidOverYou · 2002-10-29 05:00 · Score: 1

> I'm only in the top 90%th percentile for UT2k3 CTF

Care to rethink that?
Re:Incentive? by Col.+Panic · 2002-10-29 05:29 · Score: 2

You don't need a 2.* chip to run UT2003. I just built a tower with Athlon XP 1700+, 512 MB DDR and 128 MB Radeon 8500 and turned on all the effects and set them to highest quality. Incidentally, when I turned on the last one to highest quality the program said, "Holy Shit!" :)

At 800x600 I thought I was going to convulse - the display was just too fast. 1024x768 is more playable (sane) but smooth and fast as hell. Amazing looking.
Re:Incentive? by RabidOverYou · 2002-10-29 06:59 · Score: 1

The "top 90%" includes 90% of the pool. He's saying he's better than 10% of them.

You don't say you're in the top 95% of your class, but rather the top 5%.

I'll admit, I can't really tell if he was saying he rocks or sucks at UT.

Hey, I'll give him points for spelling you're and it's correctly!
Re:Incentive? by Zathrus · 2002-10-29 07:12 · Score: 1

Er... oops.

In the top 10% that should be. Perhaps higher, but the UT2k3 stats page sucks so badly right now it's difficult to tell.

Of course, this is utterly meaningless in real life and to anyone that isn't a numbers weenie. And, trust me, there's a lot of people better than me at UT2k3. But I don't suck.
Re:Incentive? by pellaeon · 2002-10-29 08:24 · Score: 1

Well, that's probably because your gfx card couldn't figure out that weird 1200x1600 resolution then ;-)

--
-- /bin/coffee missing. universe halted.
Re:Incentive? by Gruneun · 2002-11-01 02:06 · Score: 2

You don't say you're in the top 95% of your class, but rather the top 5%.

Actually, he was correct in saying he was in the 90th percentile. A higher percentile indicates that if they were ranked into 100 groups, he would be in the 90th, with a higher number being better. The only error he made was using "top" which has no meaning in that context (or rather, is somewhat redundant).

From Webster's:

Main Entry: percentile
Pronunciation: p&r-'sen-"tIl
Function: noun
Date: 1885
: a value on a scale of one hundred that indicates the percent of a distribution that is equal to or below it [a score in the 95th percentile]
Re:Incentive? by spike+hay · 2002-11-01 08:30 · Score: 2

It like didn't completely get raped. But the framerate was really, really low.

--
If you don't understand any of my sayings, come to me in private and I shall take you in my German mouth.

Will this make my modem faster? by Anonymous Coward · 2002-10-29 01:04 · Score: 3, Funny

I have a 56k modem and the internet is soooo slow, will this make it faster? They said with the PIII it would but I didn't see much different.

Re:Will this make my modem faster? by keller · 2002-10-29 01:23 · Score: 1

Well never tried to change the chip in my modem, but i guess if you didn't notice any change when putting a P3 in, then it is probably not worth the money!
Get fiber and a flashlight, THAT will be quicker!

--
Enig? Det alt for hot det smor!
Re:Will this make my modem faster? by MikeFM · 2002-10-29 01:30 · Score: 2

Actually my parents have a P4 with a winmodem and it still sometimes losses connection if you have to many processes running (like 3 netscape windows, a text editor, and a bash window). Also when trying to connect the whole machine slows down a lot. I would have thought that by now winmodems could work half way decently but a cheap hardware modem still beats a winmodem hands down. Slap on a $30 external modem and everything works a lot better.

Not really an anti-Windows rant, more an anti-winmodem rant. :)

--
At what price learning? At what cost wisdom? The price is a man's peace of mind, and the cost is his life.

New Shuttle SB51G support hyperthreaded chips by mccalli · 2002-10-29 01:06 · Score: 5, Informative

Title says it all really.

I was torn between building another dual-CPU box (currently on twin 533Mhz Celerons with an ABit BP6 board), or going the small form-factor route. Now I can do both.

More at Shuttle's site.

Cheers,
Ian

Re:New Shuttle SB51G support hyperthreaded chips by Anonymous Coward · 2002-10-29 01:52 · Score: 3, Informative

If you are really used to using multi-processor enabled applications, especially graphics apps like Maya, Digital Fusion, etc, you will not like a hyperthreading machine. In our tests, Maya runs SLOWER as does Digital Fusion when hyperthreading is enabled.

Other things that runs slower (in general)

video encoding
audio encoding
quite a number of apps with real multi-threading built in.
Re:New Shuttle SB51G support hyperthreaded chips by mccalli · 2002-10-29 02:01 · Score: 2

you will not like a hyperthreading machine. In our tests...things that runs slower...video encoding, audio encoding, quite a number of apps with real multi-threading built in.
Hmm. Now that's seriously disappointing - video encoding is what I mainly had in mind. That and a tiny amount of Photoshop - I can live without dual-CPU for that though, as my Photoshop usage isn't that high.
There are other things I do with it - I run various virtual machines using Virtual PC for Windows, and I like the isolation that running on a dual-cpu gives me. Even if the virtual machine starts chewing its way through my CPU power, it generally only starts massacring one at once, thus leaving my native OS and GUI nice and responsive. I'd be looking for a hyperthreaded machine to give me the same advantage. Does that sound likely?
Cheers,
Ian
Re:New Shuttle SB51G support hyperthreaded chips by CustomDesigned · 2002-10-29 02:40 · Score: 1

Windows versions prior to XP limit you to one processor unless you paid extra for licenses. Whith hyperthreading enabled, you split your CPU into two logical processors. Windows 2000 (or whatever you have) uses only one processor - so you are effectively running on half a CPU.
Re:New Shuttle SB51G support hyperthreaded chips by Quarters · 2002-10-29 03:24 · Score: 3, Informative

Windows versions prior to XP limit you to one processor unless you paid extra for licenses.

Uh, no. Windows NT 4.0 (workstation) and 2K (workstation) support dual CPU out of the box. They have specific multi-CPU kernels that get installed (at OS install time) if the hardware reports dual CPUs.

You only ever pay extra on the server side if you want greater than 2-way.

An oldie but a goodie... by imag0 · 2002-10-29 01:06 · Score: 3, Funny

Knock Knock!
Who's there?
...
15 second wait...
...
Intel

Turbo? by suss · 2002-10-29 01:06 · Score: 4, Funny

Yahoo has the news about the new P4 who will run at nothing less than 3.06mhz.

Does it at least have a turbo switch?

Re:Turbo? by ShooterNeo · 2002-10-29 08:34 · Score: 2

Actually, a massively parallel processor running at 3 mhz or even slower would leave all known chips (including YOUR BRAIN) in the dust.

Hyperthreading by echophase · 2002-10-29 01:06 · Score: 4, Interesting

This will make things interesting for software licenses that charge per cpu.

for those of you who don't know, with hyperthreading, the system will appear to have two cpus. If you have a dual system with hyperthreading, then it will look like 4, and so on.

Re:Hyperthreading by Anonymous Coward · 2002-10-29 01:13 · Score: 1, Insightful

Just dealing with the Microsoft OSen:
This is not a problem for anyone running XP - both Home and Pro variants will only count PHYSICAL processors for licensing purposes. This means, interestingly, that with HT, you can have "dual processors" running on XP Home. And, of course, 4 processors (2 physical, but 4 "logical") on XP Pro.
Unfortunately, the Windows 2000 variants don't make that distinction. So it's easy to exceed the licensing CPU limit if running 2000.
However, all HT platforms - if properly designed, according to Intel specifications - have a BIOS switch or similar mechanism to disable the HT technology, in which case the processor reports as just a normal uniprocessor core. Users of "older" operating systems are encouraged to use this feature.
Re:Hyperthreading by gazbo · 2002-10-29 01:35 · Score: 1

No, hold on. Remember that the whole point of hyperthreading is to obviate as many pipeline bubbles as possible.
By running various different contexts within the same stages of the pipeline Intel have vastly reduced the problem of idle pipelines. By splitting the pipelines into multiple cores, not only will there be redundant cores, but there will be more bubbles in the pipelines of any active cores.
Re:Hyperthreading by e8johan · 2002-10-29 01:43 · Score: 3, Insightful

As long as there are enough processes both solutions will work well. If you run only one thread the multiple CPUs solution will have idle CPUs, while the hyperthreading solution will have bubbles.

Still, the multiple CPU solution will be vastly more scaleable and far less complex.

By changing the ISA of the CPUs, one can avoid lots of the bubbles (all if one is mean to the compiler). Just introduce branch delay slots and you lose a whole lot of bubbles and complexity. Just imagine how simple a CPU without branch prediction would be...
Re:Hyperthreading by leuk_he · 2002-10-29 02:29 · Score: 2

it is explained here at theinquererfor windows. Basically it mean if a applcation is licenced for a single processor it will use the first processor(even if i is a dual processor system.

There are no real problems if:
-You buy licences for real processors and the software does not check it.
-The software runs only on the number of (real)processors it is licences for: it just does not use the hyper threading. (This is the case for the current windows XP & windows 2000)

There is a problem
-The software aborts if it detects more (real) processors than it is licenced for.
I do no know such software. Or it is software that is tied so close to hareware it fails anyway if it is put on new hardware.

Note that you can still disable hyperthreading in the bios.
Re:Hyperthreading by zenyu · 2002-10-29 02:50 · Score: 2

By changing the ISA of the CPUs, one can avoid lots of the bubbles (all if one is mean to the compiler). Just introduce branch delay slots and you lose a whole lot of bubbles and complexity. It seems to me they are constantly trying to introduce simpler instruction sets. i860, i960, ia64 all tried to change the instruction set to make processors that waste less time on keeping the pipelines full. But developers keep rejecting them. They would probably have to have some kind of developer discount program to get programmers to play with them. If developers could get one for $200-500 they would probably get enough mindshare to make these work. I don't know why they haven't, Intel has sent me manuals for free that I would have gladly paid for, so I'm sure they've thought of it. AMD might succeed though, just eliminating older less used instructions so most things will run, then you can just buy one as your primary PC. If they also spend some money on funding optimization for gcc perhaps even releasing it under multiple licences so commercial compilers can use it, then they could slowly get rid of less efficient instructions but useful instrustions.
Re:Hyperthreading by zozzi · 2002-10-29 03:16 · Score: 1

This is why Itanium changes all that because the processor is explicitly told what it can execute in parallel and what not. So you could have this:
if (a=z) b=c+d; else b=f+g
and this would come something like:
cmp.eq p1,p2=r1,r2
(p1) add b=c+d
(p2) add b=f+g
In this case you can have multiple cpu's or multiple cores inside one cpu executing all statements at once (yes, ALL at once) and then when it gets the compare result it knows which result to keep (compare sets p1 to true and p2 to false or vice versa depending on the result).
This is much more fine grained so will give much better performance rather than fooling the OS that it's 2 processors and expect the programmer to think of ways to use "both". Hyperthreading IMHO is just a way to get back at AMD to dampen their marketing department, a sort-of "me-too" if you will.

--
---
Re:Hyperthreading by e8johan · 2002-10-29 03:31 · Score: 2

Ok, lets sort things out here.

Hyperthreading is when you take instructions from two threads and share the execution units between these threads to avoid idle parts of the CPU.

EPIC is an ISA that tells the CPU which instructions that are independent or not. EPIC may perhaps also allow solutions like the one you show.

As you probably wouldn't split an if-statement over several CPUs, I think that your example is irrelevant to this discussion. This kind of code would just add complexity and overhead.

As for fooling an OS into having two processors, I suggest actually using two processors, not faking them like in Hyperthreading.
Re:Hyperthreading by andrewgaul · 2002-10-29 04:10 · Score: 1

Just introduce branch delay slots and you lose a whole lot of bubbles and complexity. Just imagine how simple a CPU without branch prediction would be...

How many branch delay slots were you planning to add? The trend to lengthen the pipeline increases the slots you need to have; you might be able to fill 1 or 2 branch delay slots, but can you fill 5 or 10? Also, do you want to change your ISA every time you add pipeline stages? Branch delay slots are considered a design wart on modern processors (MIPS, SPARC, any others?).
I think you overestimate the cost of branch prediction. All modern processors have added branch prediction, including the ones with branch delay slots.
Re:Hyperthreading by Sargondai · 2002-10-29 04:34 · Score: 1

Right now, the two biggest concerns chip-makers have are power and die-size. With HyperThreading, Intel is able to garner about a 20-30% improvement (I've done a LOT of testing to back this up) of systems with multiple CPU-intensive threads running for only 15% additional die-size.

This also means an HT-enabled chip consumes much less power than a dual-core CPU.

The problem in current processors is that only about 30% of the execution units are actually being utilized due to lack of independent instructions. A dual-code chip would have this same problem. However, an HT chip can get up 50% usage... Again, this isn't a huge number, but for only 15% additional die-size, it's well worth it.
Re:Hyperthreading by BrookHarty · 2002-10-29 05:52 · Score: 2

If you run only one thread the multiple CPUs solution will have idle CPUs

You have more than 1 thread now. Your OS and your Application. You will see an improvement with hyperthreading, even on an average home computer.
Re:Hyperthreading by e8johan · 2002-10-29 19:10 · Score: 2

If you have many CPU cores, you don't need to have deep pipelines, as you will gain performance though parallel execution, instead of high clock frequency. A set of classic 5 stage RISC would probably do. I know that my ideas are far from mature yet, but I want to point out that there would be benefits from a complete restructuring of todays CPUs.
The 8086 (and thus the P4) was never intended for running multithreaded OSs, and todays caches have huge problems coping with multimedia (i.e. no temporal locality). The CS are must change into a more modern field, because with what we know today we could make so much more.
Re:Hyperthreading by pmz · 2002-10-30 02:35 · Score: 2

2) most computer systems today always runs multiple threads (i.e. utilization will be good).

It is true that pretty much all the modern operating systems support treads on multiple CPUs, but I have found that it doesn't guarantee good utilization. Most desktop applications are single-threaded effectively due to the user being single threaded. I saw this while working on a 2 CPU workstation: the second CPU was idle perhaps 90 to 95% of the time.

This would be different if a specific application were designed to automatically divide work among multiple CPUs, but those sorts of applications are not common outside of image/video editing, engineering, science, and mathematics. Perhaps games will take better advantage of multiple CPUs, but that is probably a little ways off. Servers, especially UNIX ones, will almost always find a second CPU useful, since servers are supposed to be multi-user multi-processing environments.

Multi-core architectures are naturally appropriate for servers, but I still think most desktop users are best served by one fast processor (even hyperthreading will be largely irrelevant).

--
Healthcare article at Kuro5hin
Re:Hyperthreading by e8johan · 2002-10-30 02:43 · Score: 2

Just use MOSIX to get it working. To quote the about "Just fork and forget..."

Update on the megahertz myth by Ed+Avis · 2002-10-29 01:08 · Score: 3, Interesting

Does this mean that AMD's scale for measuring the performace of its CPUs (the Athlon 2200+ runs at 2200 zlotniks) will no longer compare fairly against MHz for the P4? Perhaps a P4 will run about as fast as an Athlon of the same clock speed (if you could get Athlons clocked at 3GHz).

--
-- Ed Avis ed@membled.com

Re:Update on the megahertz myth by Glock27 · 2002-10-29 02:56 · Score: 2

Perhaps a P4 will run about as fast as an Athlon of the same clock speed (if you could get Athlons clocked at 3GHz).
Hyperthreading has produced spotty (and to my mind underwhelming) results so far.
The second revision of P4 chips has already shown, once again, that raw clock speed means nothing. The Alpha chips have made that clear for years. Itanium is now Intel's poster boy for the same issue. That is a conundrum Intel can't escape.
Opteron is very exciting. It is claimed that it will debut at around PR 3400+. AMD also recently released lab SPEC2000 scores for the 2 GHz. Opteron, at around 1200/1200 int/fp respectively. That should still beat a 3 GHz P4/Xeon nicely even with a boost from HT. We'll see how the Opteron does on things like SMP and SSE2, but so far so good...especially after the Cray contract to supply 10,000 for a supercomputer!

--
Galileo: "The Earth revolves around the Sun!"
Score: -1 100% Flamebait

it's pathetic really... by xirtam_work · 2002-10-29 01:09 · Score: 4, Insightful

the huge number of story errors that keep popping up. You'd think that the story editors would try to mantain some kind of quality control.

However, it's also possibly a ploy to keep people posting indigant comments about errors. 50% of posts on these kinds of stories seem to be pointing out these glaring errors. Like the recent story about PS2 games on an Xbox which was nothing to do with the Xbox at all.

Come on guys, wise up!

Re:it's pathetic really... by af_robot · 2002-10-29 02:52 · Score: 2

You'd think that the story editors would try to mantain some kind of quality control

I think they just need more quality mantainers, just like you :)

Hyperthreading by e8johan · 2002-10-29 01:14 · Score: 5, Insightful

Hyperthreading is a complex proof of the limitations of todays CPU architectures. I belive in a CPU architecture containing many small CPU cores on one chip, instead of just multiplying the issue and commit parts and sharing the execution units.
It would be more scaleable and easier to implement to use several complete CPUs. The biggest drawback (compared to hyperthreading) would of course be that in special situations some CPU cores would be idle, but this simply corresponds to pipe-line bubbles in the hyperthreaded case. This is easily compensated by two facts: 1) multiple CPUs can be made very scalable and 2) most computer systems today always runs multiple threads (i.e. utilization will be good).
Of course, for Intel to maintain their market lead, everything has to be compatible, so they'll have to pay, time after time, for the errors they made in the eighties (the 286 paging + the CISC ISA). By breaking Amdahl's law time after time (SSE, MMX, etc.) they have made an even more complex beast. The only area where they really excel is in the production processing. They can squeeze out high frequencies and pack the transistors tight. For that, I'll give 'em cred. For their CPU ISAs, I'll just laugh...

Maybe if you type really fast? by Cpt_Corelli · 2002-10-29 01:14 · Score: 1

Maybe if you type really fast?

Re:avance? by The+Whinger · 2002-10-29 01:18 · Score: 1

Not wanting to be pedantic ...but it is "advance" and "GHz".

If you are going to criticize make sure the criticism is accurate ;).

Re:Superfast! by Tune · 2002-10-29 01:18 · Score: 3, Funny

> FOR 1975!!!

Jump back in time... even further

Mhz = mega herz
mhz = milli herz

Imagine a computer that's triggered every 11 minutes... with hyperthreading!

Wow. It might have stunned Charles Babbage...

Whoopie. by Anonymous Coward · 2002-10-29 01:19 · Score: 2, Insightful

Great, so now we'll see nerds nitrogen-cooling these things to get an extra performance boost as well? What a waste of time.

This is all pointless. The entire pentium "architecture" (more like a shanty-town) needs to be dumped entirely. We NEED a clean start.

Even moreso, why is no one addressing the fundamental problem--that the PC is just horribly designed? There are better ways of doing things than just ramming everything through a single CPU. This is 2002--why are we not pursuing better computer design? The "PC" is the bottleneck for crying out loud. 10 years from now will we be reading about the new 10 Ghz PVII chip, still running in 30-year-old hardware? Wonder if I can still get a "Missing Basic ROM" error on my desktop machine...

Be, Inc. tried to redesign the "PC"...they had a very nice design, but they killed it before it's time. And how about Amiga...yeah everyone is sick of hearing about the Amiga but it WAS intelligently designed. Instead of shoving everything through the CPU the Amiga used coprocessors to deal with much of the stuff that bottlenecks PCs, leaving the CPU free for more important stuff. It was a great idea, and it actually WORKED.

I don't care who does it--I want to see a better machine being built. If done right, the Ghz of the CPU won't matter nearly as much.

Re:Whoopie. by nempo · 2002-10-29 01:34 · Score: 2, Insightful

With the early 486 cpu:s we had the extra fpu chip. Later, that was integrated into the main cpu.
The reason for integration was price, It's cheaper to produce one chip then two.
Today, we have spu:s (sound prossecing units), gpu:s (graphics prossecing utits) and so on.

You'r talking about redesigning the 'PC' when you actually mean 'redesigning the OS'.

--
--- No, english is not my mother tongue.
Re:Whoopie. by zmooc · 2002-10-29 02:00 · Score: 2

It's pointless indeed... regarding Wonder if I can still get a "Missing Basic ROM" error on my desktop machine...:
Find some DOS, type in the following: copy con myprog.com[enter][alt-205][alt-24][ctrl+z]myprog[e nter] and you will know:)
Disclaimer: no dos here.

--
0x or or snor perron?!
Re:Whoopie. by Xavier · 2002-10-29 02:02 · Score: 1

I think that Intel WANTS everything to be done by the processor, so that they can sell their more-and-more powerfull proc. This is surely a reason why USB ( intel specs ) trafic uses mostly central processor, and FireWire do not.
Re:Whoopie. by Martigan80 · 2002-10-29 02:06 · Score: 1

Well Commodore tried that but people wanted faster speeds. You can say advertisement killed the Amiga, but it was IBM/Intel/M$ that pushed the Hz wars.

Like you said about SPU and GPU's the C=64 had its own proc w/built in OS as well as the 1541 Disk Drive. The Amiga had the Agnus, Lisa, Paula chips. But the norm was one cpu...

Any how you are right, with the time we need to leave these 10+ year old cpu/databus/hd systems for new technology, you just have to convince the rest of the world to dump all of their systems just like the senate wants you to have DTV right now!

--
This SIG pulled due to lack of funding. (This damn war is costing too much!)
Re:Whoopie. by fitten · 2002-10-29 02:20 · Score: 1

a) Intel learned that the value of computers is in the software they run. Backwards compatibility is very important
b) I20
c) the key components behind the "PC" is cost. It is a cheap, simple design. There have been several alternatives in the past, none of which caught on -- MicroChannel, EISA, I20, etc. In each case, they were more expensive (sure, there is a cost of scale associated with them that they needed to overcome, but it is a tough one to beat) and people just didn't buy them because they were more expensive than the "regular PC".
Re:Whoopie. by Zathrus · 2002-10-29 02:32 · Score: 5, Insightful

Whoopie. Another EE student who has realized that the paper design of the PC architecture sucks wind and can't imagine that it works at all.

Don't worry folks. In a few years he'll graduate and get some real world experience. And then he'll probably realize that while the PC architecture does indeed suck on paper, in reality it's not all that bad. Could it be better? Sure. Should we throw the baby out with the bathwater? No way.

Compare the PC market to the rest of the computer market. Who's made more progress? Who has been rapidly pushing the niche markets into smaller and smaller niches as their "superior designs" find them running slower and more costly than the evil, horribly misdesigned PCs?

Coprocessors? Yeah... have you even bothered to look at a modern video card recently? The damn things are more complex and more powerful than the CPU. Modern audio boards are also powerful all by themselves. For the most part I/O is handled by separate chips as well.

The bus and memory interfaces on PCs could use some work. And that's happening, with 3GIO, PCI-X, and other buses being implemented in the next few years. There's some truely horrid cruft in the core too - the IRQs, DMA channels, etc. are still pretty godawful, but not nearly as godawful as they were back with the ISA bus. The issues haven't so much gone away as they've been hidden, but the performance limitations imposed really aren't all that absurd.

Design a better machine? Go for it. It'll die just like all the rest because while you may have a better electrical design, you've ignored the real world and the fact that people want to be able to make slow transitions from one architecture to another. Doing an all-at-once transition is not an option unless you control the entire market - which no PC manufacturer does (unlike Apple). Of course, the flip side of this is that the competition causes the current implementation to advance far more rapidly than would be otherwise possible. Which is why you can buy a $2000 PC that outperforms a $200,000 server.
Re:Whoopie. by leuk_he · 2002-10-29 02:36 · Score: 2

With the early 486 cpu's we had the extra fpu chip

In the 80486 it was already integrated. It was a seperate chip in the 80286 timeframe.

In the 80486 time there was a 486sx that was a 80486 with a fused FPU unit.

Dude, you are getting old!

But you are right, the parent poster does not properly makes a distinction between OS & hardware.
Re:Whoopie. by rugger · 2002-10-29 03:02 · Score: 1

As another point to the original poster,

After you have designed your nice, new architecture, and have everyone moved to it, whats to stop it becoming another crufty, crummy design after 10 years that people constantly want to brush aside because it doesn't fit with the mentality of the day.

By replacing the current x86 architecture with a cruft free and fully optimized system, at prices that people can afford, you probably wouldn't even get a 2x increase in speed. That is less than 2 years difference. Hardly worth throwing out all our software, which took many years to develop, just for that minor improvement.
Re:Whoopie. by master_p · 2002-10-29 05:53 · Score: 1

The coolest part of the Amiga was its DMA. The blitter, floppy disk and sound chip could work simultaneously with the main CPU. There are a lot of Amiga demos where the screen goes crazy filled with BOBs and sprites while the next part of the demo is loaded from the floppy.

Now, let's try a similar thing with the PC: do a file copy from a floppy to a hard disk and then try to move a window around (in Windows XP). Either the copy will stop or the window will not be dragged at all.

Another idea that has not caught on is the Transputer. Very cool chip, designed from the start to be used in parallel. You need more processing power ? you just added a couple of T32 chips and there you go! of course this was good for parallelized tasks only, but for me it was a damn good design.
Re:Whoopie. by Zathrus · 2002-10-29 08:40 · Score: 2

This is not a failure of the PC - it's a failure of the OS.

If XP still can't handle that it's rather sad. OS/2 could handle it over a decade ago. Linux should be capable of handling it as well.

Of course the floppy is pretty much a vestige of early PC days anyway. It's still needed for the rare occasions everything else goes haywire or some idiot manufacturer distributes drivers only on floppy (CD is cheaper you know), but that's it. I'm rather surprised more PC manufacturers haven't simply eliminated them as a standard component.

the new P4 *that* will run at 3.06 GHz by stud9920 · 2002-10-29 01:23 · Score: 1

about the new P4 who will run at nothing less than 3.06mhz

We know the submitter has no life. No one here does. Not even I. But does a P4 really need a *human* pronoun ?

Re:the new P4 *that* will run at 3.06 GHz by 1s44c · 2002-10-29 01:27 · Score: 1

3.06mhz

Wow! intel have finally made something thats 30 times slower than my firewall.

Well done Intel.
Re:the new P4 *that* will run at 3.06 GHz by distributed.karma · 2002-10-29 01:52 · Score: 2
Consider the following:
1. Information wants to be anthropomorphized.
2. The P4 runs at nothing less than 3.06millihertz. This does not conflict the fact that it actually runs at 3GHz. Think about it.
--
--
If you moderate this, then your children will be next.
Re:the new P4 *that* will run at 3.06 GHz by ralmin · 2002-10-29 06:02 · Score: 1

I seriously doubt that your firewall's CPU runs at 91.8 mHz, that is, it takes 10.9 seconds for each cycle.

--
Ralmin.

Genuine Question (Re:Turbo?) by keller · 2002-10-29 01:26 · Score: 1

I also used to have a PC with a turbo switch, but I never knew exactly what it did, can someone enlighten me please?

--

Enig? Det alt for hot det smor!

Re:Genuine Question (Re:Turbo?) by Zathrus · 2002-10-29 01:47 · Score: 4, Informative

It changed the CPU clock frequency - generally you left the switch on since that was the faster mode of operation. If you had an application/game/whatever that didn't handle the higher clock rate nicely (and a lot didn't) then you clicked the switch and the CPU core dropped from 10 MHz down to around 5.

They eventually became disused because instead of dropping down to 4.77 MHz (the orginal XT speed) they'd just drop some fraction of the regular CPU speed - down to maybe 7 or 8 MHz, which was way too fast still. Plus applications stopped doing stupid things like presuming the CPU frequency and using it for timing loops.
Re:Genuine Question (Re:Turbo?) by Alan+Partridge · 2002-10-29 02:23 · Score: 1

I had a 386DX (66!) with a turbo switch, as far as I knew, the turbo switch was there for reasons of compatibility with the XT standard, which specified a clock speed substantially lower than my roaring fast 386. Certainly, if you unclicked the turbo button the world went into reverse. Word Perfect and Flashback could be mightily slow with no turb-o.

--
That was classic intercourse!
Re:Genuine Question (Re:Turbo?) by archen · 2002-10-29 02:36 · Score: 1

Back then tech support was a breeze (under some circumstances).

User: Why is my computer running so slow?
Me: [hits the turbo button]
User: oh...
Re:Genuine Question (Re:Turbo?) by Waffle+Iron · 2002-10-29 03:01 · Score: 5, Informative

The real reason that hardware vendors were forced to put the turbo switch on PCs was because of the first outbreak of "digital rights management" technology.
Spreadsheets were the killer app that caused the PC to take off, and Lotus 123 came with a super-annoying floppy-based copy protection scheme. They intentionally misformatted the floppy, then the program verified that it was an original by doing low-level tricks with the floppy controller.
The most ridiculous and shortsighted part was that they used CPU-based timing loops to do the timing for their stupid floppy tricks. Of course, these were calibrated to the only CPU speed available at the time, 4.77MHz. As a consequence, if a PC was going to run Lotus 123, it needed to be able to slow down to the original 4.77MHz speed while it read the Lotus floppy. IIRC, Compaq had a nifty patent that automatically slowed the PC whenever the floppy controller was in use. Others had to make do with a manual switch.
The cost to society for this DRM fiasco, hundreds of millions of useless bezel switches, undoubtedly was far greater than any revenue that Lotus made by thwarting piracy. (In fact, their revenue from DRM might be negative, because they were eventually displaced by non copy-protected comptetiters.)

Hyperthread is useless for Win9x, WinNT, Win2000 by edxwelch · 2002-10-29 01:28 · Score: 1

According to this artical: http://www.theregister.co.uk/content/61/25774.html Hyperthreading needs OS support and only Windows XP and Linux provide that

Wow! Brilliant! Ace! by Rogerborg · 2002-10-29 01:28 · Score: 2, Funny

This will totally change my life! It's the announcement that I'd been waiting for! I must rush out and purchase ten thousand of these immediately, if not sooner! And so on!

</sarcasm>, wouldn't it be simpler for Slashdot to just link to every product announcement from a major hardware manufacturer rather than go through the farce of picking one of the dozens of frenzied (and typo'd) submissions from the "f1rz7 5Ubm1z10n, 5uX0rz!" brigade?

--
If you were blocking sigs, you wouldn't have to read this.

Re:avance? by Alan+Partridge · 2002-10-29 01:30 · Score: 1

surely that should be:-

a little editing of the stories wouldn't HURT

--
That was classic intercourse!

Hyperthreading? bah! by Jugalator · 2002-10-29 01:33 · Score: 4, Funny

I'm personally going to build an octathreading CPU by tricking the OS into thinking it's working with EIGHT processors! Wow, that should give me 8x the performance! Stupid Intel restricting themselves to faking just two processors.

--
Beware: In C++, your friends can see your privates!

Re:Hyperthreading? bah! by Jugalator · 2002-10-29 03:00 · Score: 2

Um, i'd mod you down for being an idiot

It's funny. Laugh. :-)

--
Beware: In C++, your friends can see your privates!
Re:Hyperthreading? bah! by Jugalator · 2002-10-29 07:18 · Score: 1

Have to agree with the other AC... you're fucking stupid...

So what should I do now? Sob at your sillyness? :-)

--
Beware: In C++, your friends can see your privates!

3.06mhz by stud9920 · 2002-10-29 01:33 · Score: 5, Funny

3.06milliHz ! Wow ! That means about ten clocks an hour ! With the super deep P4 pipeline (20 deep IIRC), it means it will push some 200 "single clock instruction" in just an hour. But beware of pipeline stalls. They better have a solid branch prediction algorithm.

big deal by g4dget · 2002-10-29 01:36 · Score: 2

Slashdotters did this a while ago :-)

something you don't see everyday by Anonymous Coward · 2002-10-29 01:40 · Score: 3, Funny

Yahoo has the news about the new P4 who will run at nothing less than 3.06mhz

There's only one explanation to 2 typographical errors in the post.. sex..

Rob posting articles to be posted automatically, Kathleen wants Rob.. if you know what I mean.. Rob tries to rush.. well.. you get the idea..

Re:something you don't see everyday by poot_rootbeer · 2002-10-29 05:23 · Score: 3, Funny

Then how do you explain the 3rd typo ("avance")??? ...HOO BOY!

Anyone notice this??? by FuzzyDaddy · 2002-10-29 01:45 · Score: 5, Interesting

The LaGrande initiative will coexist with existing security initiatives such as Microsoft's Palladium to create a more secure computing environment, Otellini said. It will secure the physical pathways that transport data on a computer's motherboard, and will be available for both servers and desktops. The technology will take until at least next year to come to market, however, probably with the next generation of Intel's desktop Pentium processors.

Securing the physical pathways that transpoty data on a computer's motherboard. This will sure help me against those tiny little hackers inside my computer stealing my data!

Oh wait, you mean this is to protect the data against me? Looks like we have about a year before this is built into the PC architecture. Plan your computer buying wisely.

Bastards.

--
It's not wasting time, I'm educating myself.

However... by MtViewGuy · 2002-10-29 01:48 · Score: 2

...Dual-CPU Athlon motherboards are not that easy to find in a retail store--you often have to purchase them mail order. :-(

Also, what end-user oriented software will take advantage of Intel's hyperthreading process right now? Will we have to wait for updates to CAD/CAM, drawing and image editing programs to use hyperthreading? And when will we see updates to multimedia programs such as Windows Media Player, RealOne, Quicktime, software DVD players, etc. that will take full advantage of hyperthreading? We might not see them until early 2003.

Re:However... by Alan+Partridge · 2002-10-29 02:48 · Score: 2, Informative

yeah, buying mail order's a real chore. I mean, apart from saving a ton of cash, you get a bigger choice too! What a drag.

--
That was classic intercourse!

Yet Another Link by Zech+Harvey · 2002-10-29 01:51 · Score: 1

With Bigger Shots! (Though, only in Japanese) http://www.elecom.co.jp/news/20021015/mapp/index.h tml

--
Zech Harvey, MCSE, MCDBA, CCNA

Scaling horizontally... by MosesJones · 2002-10-29 01:53 · Score: 5, Interesting

The advantage of Linux (and to a lesser extent W2K) and the low end Solaris, AIX servers is that for the first time it was sensible to scale horizontally, so rather than have 1 box that did everything ala a Mainframe you'd have 10 that shared the work, then you'd add 5 more. And because the real bottlenecks now are disk and other IO issues you start using things like EMC, Cached RAID disks and lots of other very expensive storage.

But if you are scaling an application horizontally the last thing these days is the processor speed, sure the heavy duty maths is still sitting on a mainframe, your ERP is still on an AS400, but that is more about reliability than power. Intel boxes fail, period, so having one box isn't a smart move, have 10 is a more sensible approach.

Dual NIC, external disk via fibre channel. That is where I'll spend the cash. The processor just needs to be fast enough, and I'd like there to be at least two in the box. 2 Boxes doing everything, federated systems.

If you lob everything on one box, then yes you need all the processor speed you can handle, you also need to think about what happens when the box fails.

If Intel announced that this new processor could degrade its performance when issues arose then I'd be interested. Overheating ? Turn off hyperthreading and drop the clock speed. Still got issues, move down to minimum speed and start a shutdown process.

I like servers that will run for 5-10 years with no down time. But with Intel/AMD boxen I'll stick with lobbing in lots on the basis that they'll fail.

--
An Eye for an Eye will make the whole world blind - Gandhi

Goodie! by Shome · 2002-10-29 01:54 · Score: 1

Now my Windows will boot faster... :-D

--

~Once you have your choices narrowed down, the rest will fall into place.

Meanwhile, in a systems context by panurge · 2002-10-29 01:56 · Score: 2, Insightful

I/O is still the bottleneck, be it to RAM, hard disk or whatever. I haven't got a single computer which at some time or another isn't sitting around waiting for the harddisk to stop reading or writing, or for data to flow through that sl-o-o-w 100baseT switch.

The fact is that for work a 700MHz PIII is usually fast enough given the rest of the system, as well as being reasonably cool and quiet.

So what is the point of this advert? Is it the result of a kind of desperation on the part of Intel? Marketing departments insisting on announcing ever smaller "feature creeps" in an effort to create a buying climate run the risk of the very buyer turnoff they want to avoid. It's like the old Indian auto industry, where the big new feature for each year was something like a differently shaped tail-light molding.

--
Panurge has posted for the last time. Thanks for the positive moderations.

From the seems-like-only-yesterday dept. by Evro · 2002-10-29 01:59 · Score: 1

Actually, it was just last month, not yesterday.

--
rooooar

Re:avance? by distributed.karma · 2002-10-29 02:00 · Score: 2

But it's true.. it really hertz to edit these CPU stories.

--

--
If you moderate this, then your children will be next.

missing word... by hummassa · 2002-10-29 02:02 · Score: 1

B?

--
It's better to be the foot on the boot than the face on the pavement. ~~ tkx Kadin2048

Re:The numbers are deceiving... by VAXman · 2002-10-29 02:06 · Score: 2

AMD doesn't have the equivalent of a 3GHz SMT CPU.

At what expense? by Alethes · 2002-10-29 02:06 · Score: 2, Interesting

What did Intel sacrifice to make the number of Ghz higher for the sake of marketing? Really, I'd like to know, because I've heard this is the case with previous Ghz barrier crossings, and I wonder how it affects the overall performance of the CPU, and the rest of the computer for that matter.

Re:where the fuck is AMD? by Alan+Partridge · 2002-10-29 02:09 · Score: 1

yeah, where the hell are they? They haven't announced a new CPU for almost a MONTH now!
You stupid fucker.

--
That was classic intercourse!

Speed of the CPU is good but... by Cheese+Cracker · 2002-10-29 02:14 · Score: 5, Insightful

Why not spend more R&D money in increasing the speed of the bus? It would give us way better performance.

Re:Speed of the CPU is good but... by brer_rabbit · 2002-10-29 05:25 · Score: 2

Why not spend more R&D money in increasing the speed of the bus? It would give us way better performance.
Bus? Hell, hard drives/drive speed has always been the weak point of the system.
Re:Speed of the CPU is good but... by Faizdog · 2002-10-29 16:48 · Score: 1

Also, Thanks to the One from the Matrix, we know that the speed of the bus can't be lower than 50 (insert unit of speed here) thus it can only go up.

--
-"Those who fought today will die tommorow."-

Awesome! by The+Evil+Couch · 2002-10-29 02:18 · Score: 1

now I can blue screen and reboot faster than ever!

--
The World's Worst Webcomic!

Re:BSD by markalanj · 2002-10-29 02:24 · Score: 1

Think again!

UT2003 is CPU limited currently. by raygundan · 2002-10-29 02:26 · Score: 4, Informative

Fooey. It has to do with *everything*. Yeah, your graphics card is sooper-fast. But what has to feed that card data? Your CPU. Your memory bus. Your AGP bus. UT2003 happens to be CPU-limited even with the latest-and-greatest video cards, all the way up to the fastest Athlon chips available.

Take a look at this UT2003 benchmark chart:

http://www.anandtech.com/showdoc.html?i=1650&p =3

You can see that the GeForce 4 Ti cards are ALL still getting faster the faster the CPU gets, right up to the bitter end.

That's not to say that a couple of years from now that 3D cards won't handle physics and AI onboard-- but they don't exist now, so it's hardly fair to say "A better gfx card will almost always be a bigger win than a faster CPU."

It depends on the game, and the newer they are, the more CPU they'll eat. (See Battlefield 1942)

In related news ... by Midnight+Thunder · 2002-10-29 02:31 · Score: 1

In related news Intel has now partnered with a major US energy company to use Pentium 4s in place of oil as a heat source.

--
Jumpstart the tartan drive.

So it is by 91degrees · 2002-10-29 02:41 · Score: 1

I stand corrected

My idea for a better PC by swb · 2002-10-29 02:46 · Score: 2

The high performance of CPUs makes me wonder why we couldn't do a more interesting type of a machine.

I'd have a case with a crosbar type bus. In this you'd add CPU cards that had memory and a single daughtercard slot. The daughtercards would be to add custom interface electronics for specialized tasks, but not actual processors, so a CPU card could be a video card, a SCSI card, NIC, etc.

One CPU card would be the "master" CPU card which ran the core of the OS kernel plus applications. The other cards would run applications or kernel modules specifc to their hardware daughtercards; network stacks, filesystems, display components (renderers, GUI).

Increase performance? Add a CPU module. The kernel or user tools could manage which cards ran which applications -- some apps could be dedicated to a specific CPU card, other apps could be "floated" to CPU cards based on available cycles.

I don't think this is such a terribly new idea -- its kind of the modularity that IBM 390 or other NUMA architectures do now, but condensed into a single box. Think of a blade server box, but with a switching bus and the ability to access other systems memory.

It would require an OS with a lot more modularity. I'm not sure what would happen to apps that wanted RAM beyond a single CPU card's RAM capabilities, or how fast or easy you could move an app and its memory space from one card to another. I'm also not entirely sure that even a P3 @ 3.xx GHz would be able to do the work of an NVidia GeForce, even if thats all it had to do, either.

But it would be an interesting way to make a highly scalable platform, and scalable both ways -- big and small. An OS written for such hardware could run on a single-card system (think of a laptop or even a palmtop as a single-card system), and multi-card systems could come in S, M, L, and XL sizes depending on cost and need, as well as eliminating the CPU/Memory/Bus bottlenecks.

Re:My idea for a better PC by default+luser · 2002-10-29 06:50 · Score: 1

Dy-4 with VxWorks on VME?

Hmmmmmm....

--
Man is the animal that laughs.
And occasionally whores for Karma.

Re:Superfast! by Fruit · 2002-10-29 02:47 · Score: 1

if you want to be anal about upper/lower case: it's "Hz", not "hz".

Overkill? by ruiner13 · 2002-10-29 02:54 · Score: 2, Insightful

Seriously, besides the 1% of the research/development population who may need this, doesn't anyone think this is going too far, to fast? My personal computer is a G4 450, and I have yet to find something that really taxes it. I've upgraded the VC, HDs and RAM, spent maybe $300 doing so (over 3 years) and I have no problems, and I'd say I utilize the computer's resources more than maybe 97% of the population does (I am a programmer/video editor). I don't see what the difference in being able to compile the latest release of Apache in 5 minutes instead of 6.5. The scary thing is, I know people who actually think that tweaking their Athlon XP 2200+'s to eek out another 150MHz or something by using a freakin' pencil is gonna get them somewhere.

I know that there are some of you on here that will flame me saying that you DO use that power. And that's fine, you are the 1% of the population I mentioned earlier. But to do it (like most of you would... admit it) just to get another 4fps in UT2003 or whatever, it's just sick. Yes, eventually I will buy a new computer, but only when my needs exceed the resources in my computer, which hasn't happend just yet (it's getting close though...). If any of you can actually tell the difference between this 3.06GHz P4 and the 2.5GHz P4 (without using a stopwatch that measures in the milliseconds) I have a bridge to sell you. Don't let Intel make you think that you need to buy a new computer right now. It may help the economy in the short term, but you will just be wasting precious electricity (in this case gobs of it) just to say you have the latest and greatest. It's becoming a disease!

--

today is spelling optional day.

Re:Overkill? by azadrozny · 2002-10-29 03:29 · Score: 1

You obviously have not seen the beta for the next version of Windows. It will bring that 3GHz P4 to its knees and beg for mercy! :)
Re:Overkill? by Junks+Jerzey · 2002-10-29 03:47 · Score: 5, Insightful

I know that there are some of you on here that will flame me saying that you DO use that power. And that's fine, you are the 1% of the population I mentioned earlier.

Everyone, of course, believes they're in that 1%.

I used to do commercial 3D video game development on a 450MHz P2. It was a bit slow when compiling, but acceptable otherwise. Then I upgraded to an 866MHz P3 and, even years later, it still feels like lightning. Compiles are quick. Everything is snappy. I've taken to writing tools in Perl and Lisp and Python, and they're snappy as well. I mean, geez, who would have thought ten years ago thay you'd ever be able write 3D geometry manipulation tools in Lisp and have no worries about performance?

Now, of course, you can buy a 2.5GHz P4 in an $800 PC. This is beyond ridiculous. Everything is three times faster than "beyond the point of caring"? I'm going to put C++ aside for almost everything, and just use whatever is the most abstract. Haskell? Yes, please.

Am I in the 1%? Certainly not.

It may help the economy in the short term, but you will just be wasting precious electricity (in this case gobs of it) just to say you have the latest and greatest. It's becoming a disease!

This bothers me, too. Yeah, people don't need all this performance, and that's okay. Who cares if your computer is too fast? But unfortunately you don't get all this performance for free. It's coming at the premature obsolescence of hardware and greatly increased power consumption. Hard drives and monitors are actually improving in this regard, especially with LCD monitors (awesome!). But now we have 70 watt processors and PCs that ship with five or more fans in them, and we're talking bottom end machines from Dell and Gateway here, not crazy high-end monsters. This is bad.

Enterprise Class? Call the engine room now! by El+Camino+SS · 2002-10-29 02:56 · Score: 2

Kirk: "Scotty? Why did we just pass our destination?"

Scotty: "Captain, ah gat ta have more time! The system, she just can't handle this light of a load! She's loading Bonzi Buddy and Clipit applications because she's bored and needs someone to talk to!"

XP? by Anonymous Coward · 2002-10-29 02:58 · Score: 1, Funny

Is this processor fast enough, that XP won't feel slow? I know that on 1.6GHz machines it feels like it needs a CPU twice as fast, which would be 3.2 GHz.

Re:XP? by Jedi+Alec · 2002-10-29 03:53 · Score: 1

This is obviously a troll, but I'll bite. XP runs fluently on my system. And that's a Duron 800 with 1 single SDRam 512 MB Dimm and a Geforce 2 MX. Now UT 2003, that's a whole different OS ;-)

--

People replying to my sig annoy me. That's why I change it all the time.

P4 at 3+GHz??? No thank you.. by Nonillion · 2002-10-29 03:18 · Score: 1

As I have stated in earlyer posts, I'm finished with Intel processors and comodity hardware in general. x86 has served me well through the years but trying to expand on it in it's current form has turned into a kludge. I'm moving on to someting else like Sun and/or Silicon Graphics hardware. Sure it's a lot more expensive but hell, 64 bit RISC processors and I/O bandwidth are the way to go. Besides, I can still run Linux on it :)

Mere mortals, I laugh at your 32 bit clunkers...

--
"I bow to no man" - Riddick

Who cares? by multiplexo · 2002-10-29 03:20 · Score: 2, Insightful

OK, if you're running a big Beowulf cluster and doing computational fluid dynamics or something similarly intensive this is great news, but for the rest of us who cares?The linux shop where I used to work, which was one of the largest commercial operations in the US if not the world, rarely had problems with being CPU bound on our HP Netservers, instead we found that we were memory bound, because the applications we developed in house were memory leaking death hogs or I/O bound because of the limitations of the PC architecture.

I recently purchased a laptop with a super duper 1.7Mhz Pentium 4 mobile processor. It's a nice box but it won't play GTA III worth a damn. Why? Well because the video hardware is crap. So I slapped together a cheap Athlon box, running at a lower clock speed but with a GeForce4 video card and all of a sudden I have high-res frame rates that leave my laptop in the dust. But both boxes have about the same performance for running Oracle.

If you think about it these chips are somewhat ridiculous. How many of them are going to be installed in motherboards that still have an IEEE 1284 parallel interface on them? How many of them will be installed in motherboards that still have PS/2 keyboard and mouse ports? How many of them will be installed on motherboards that have floppy controllers? You've got all of this insanely great hardware being strapped onto motherboards that are loaded down and dragged down with a bunch of legacy technology from the 1970s. I for one would be a little more excited if Intel were to dedicate itself to eliminating the cruft in the PC architecture. This would do a lot to improve performance and ease of use and would probably improve performance more than just slamming in a faster CPU every six months.

--
cheap labor conservatives - they want to keep you hungry enough to be thankful for minimum wage.

Prevailium. by newr00tic · 2002-10-29 03:27 · Score: 1

The LaGrande initiative will
coexist with

existing "security" initiatives such as

Microsoft's Palladium

to create a more secure computing environment, Otellini said. It will secure the physical pathways that transport data on a computer's motherboard, and will be available for both servers and desktops.

..and they had to mention the Palladium (in vain). In the future, we'll no doubt see technological improvements, only willing to improve the unimprovable (which is Palladium itself..). Who buys this kind of crap (mentally, not financially)?

--
A horse can't be sick, you know, even if he wants to.

Re:Hyperthread is useless for Win9x, WinNT, Win200 by matthew.thompson · 2002-10-29 03:27 · Score: 2

You mis-read the article - they dont say that ONLY XP and Linux support it only that XP definately supports is and Linux probably does.

Any operating system that supports SMP should work fine with this.

NT And 2K both support Hyperthreading for the simple fact that Intel designed it to look exactly like 2 processors per chip. I have a hyper threading dual processor box here running SQL server. It has 2 physical processors but Windows 2000 and even the Bios see them a 4!

M@t :o)

--
Matt Thompson - Actuality - Insert product here.

Progamming Revolution by KnowledgeFreak · 2002-10-29 03:32 · Score: 1

I keep seeing "funny" (more like redundant) comments on how this will not make everyday applications like MSWORD run any faster. Its odd though, i remember when CPU speed really started to pick up and thinking it would be great when all of my everyday actions on the computer are near instantanious. What i'm getting at is that, even w/ a four ghz CPU, WORD, and most things, still take time to load up. Is this a memory/hard drive issue? or is it just that our ability to make use of 4 ghz when programming software hasn't reached our ability to get that speed in hardware?

- Pete

This is no typo... by Loki_1929 · 2002-10-29 03:40 · Score: 2

"Yahoo has the news about the new P4 who will run at nothing less than 3.06mhz."

It's just the latest in a long-running battle between AMD and Intel. Judging by the speed on this thing, and assuming it might actually be able to run at say... 3GHz, we're looking at a chip that can run 1,052,688,062,745 (over a trillion) times it's rated clock speed with no additional cooling!

I may be an AMD fan, but holy shit, Intel. Bravo!

--
-- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."

Re:This is no typo... by ralmin · 2002-10-29 05:54 · Score: 1

Where did you get that figure 1,052,688,062,745 from? Ah, you've done:
(3 * 2^30) / (3.06 * 10^-3)
But GHz is not 2^30 Hz, it is 10^9 Hz! The correct answer is that 3 GHz is 980,392,156,863 times faster than 3.06 mHz.

(If for some WEIRD reason you did want to specify a unit of 2^30 Hz, you must write it as GiHz or gibihertz.)

"Does this mean... by Joey7F · 2002-10-29 03:43 · Score: 3, Funny

I can surf the web faster or no?"

(someone actually asked me this in talking about the 2.2p4)

--Joey

Re:"Does this mean... by larjon · 2002-10-29 06:37 · Score: 1

> (someone actually asked me this in talking about the 2.2p4)

ohh, I do hope your answer was "yes"! ;)

/ L-G

--
$> cd /pub
$> more beer

Re:see what i mean? by Loki_1929 · 2002-10-29 03:46 · Score: 2

" overclocking is pointless cos the speed increase you get isn't worth the effort and money."

Yes, because entering my BIOS at POST and upping the FSB by about 10MHz is so incredibly time-consuming and costly.

--
-- "Government is the great fiction through which everybody endeavors to live at the expense of everybody else."

Wanna make XP fast? by freeweed · 2002-10-29 04:05 · Score: 2

http://www.monroeworld.com/pchelp/xptweaks.php

I've done most of these tweaks on a group of brand new 1.2Ghz machines, and I'd say it easily makes XP perform twice as fast.

And an added bonus, you no longer have AOLdows on your desktop :)

--
Endless arguments over trivial contradictions in books written by ignorant savages to explain thunder in the dark.

Wrong! by Laura_007 · 2002-10-29 04:13 · Score: 1

Both Intel and AMD are CPUs for home users who don't need performance. Workstation processors, like the SPARC mentioned by my friend sql*kitten, have long known that real performance is obtained by putting even the weakest CPU with a fast I/O design. Indeed, I believe that even a 68040 with a very high scale transverse parallel memory design would give a mid to high end Pentium IV a run for its money. This link demonstrates the truth of this claim: Bandwidth is king.

The real improvements in the x86 world will come when they start quad-pumping and double-cheeling the memory system. Actually I believe that it'll be a great stride forward when they use the new lightpath memory architecture, removing the inherent speed limitations of tungsten interconnects used in modern systems. The elimination of filaments in the CPU core of the amatuer processors will be a good improvement as well.

Thank you for listening!

grrrlllpower

--
I am looking to accumulate friends. Please click on the circle and add me as a friend. Thanks!

Re:Wrong! by fudgefactor7 · 2002-10-29 05:30 · Score: 1

Too bad your link to micromac only talks about lowly Mac IIvi, Mac IIvx, Performa 600 and Centris 650 Macs and not about a SPARC which is what you were supposed to be talking up.

Ideally, architecture would have a really fast large amount of ram, a CPU capable of pulling from the ram at full speed, and a really fast output. Cache does get in the way a little, but not that much. Personally, I'd like to see 256MB of L1 cache, that would do then we wouldn't really need more ram except for heavy duty operations. But a CPU with that would be "prohibitively expensive." So the only way around that would be to eliminate the L1 and L2 cache entirely, but then you still need a fast CPU and I/O for that to overcome what you've lost in the exchange. In short, the argument "that real performance is obtained by putting even the weakest CPU with a fast I/O design" is slightly flawed. What is needed is really fast I/O and an equally fast CPU. Therein is the problem: CPU Ghz is important, the more the better.

The worst thing ... by vrai · 2002-10-29 04:23 · Score: 1

... is that I can order it over the web at work and have it delivered there the next day! Now I have to spend my lunchtimes in the pub with my mates and not wandering around dodgy computer outlets looking for the model I want, the horror!

The new Intel P4 3GHz (Corvair) by RobKow · 2002-10-29 04:30 · Score: 1

Unsafe at any speed! :)

Here is what you will see... by Raiford · 2002-10-29 06:04 · Score: 2

More software developers will take advantage of multi-threading. P4 users will run more of these apps. The hyperthreading technology which works well for one or two multithreaded apps will bottleneck trying to schedule too many threads. Result -> poorer perfomance than non-hyperthreading chip.

--
"player 4 hit player 1 with 0 stroms"

running quake 2 on BE by dextr0us · 2002-10-29 06:22 · Score: 1

wow, when i play quake 2 for BEos, i'll get the bestest performance around!!

GO TRULY MULTITHREADED OSes!!!

[/sarcasm]

--
"Martha Stewart can lick my Scrotum......do i have a scrotum?" -- Sharon Osbourne

Sorry (can't resist).... by King_TJ · 2002-10-29 07:53 · Score: 2

Maybe your real problem is the power-suckage of Citrix?

I'm sorry, but after doing some Citrix administration for a couple years - I'm convinced that the product is a solution to a problem that never really existed.

1. Their "reduced cost of ownership" is a blatant lie. Not only is Citrix ungodly expensive for licensing, but instead of having 30 or 40 users running a Win desktop happily on systems most firms already owned, they have to invest in monster servers to handle the load of serving all 30 or 40 of those desktops out. (Either served to the same, existing hardware that used to run the Win desktops anyway, or to overpriced "thin clients" which tend to break down as often (or more often) than the PCs they replaced.)

2. The "ease of administration" is questionable, at best. EG. I don't know many Citrix admins who found sharing multiple printers in the environment was "smooth sailing". I also don't really see the supposed advantage behind the "change it once on your server, and everyone gets the update!" concept. You can accomplish the same with a number of remote deployment tools for workstations (Enterprise edition of Norton Ghost, for example?). You also don't have to hassle with getting everyone logged out of a Citrix box to restart it after you make changes requiring a reboot. (I find it easier to schedule individual workstations to reboot at night or over people's lunch hour.)

Look, we all agreed that the mainframe/dumb terminal model was "outmoded" after the 60's and 70's. We embraced the personal computer, and eventually the usefulness of "peer to peer networking". Now, Citrix comes along and drags all the modern things back into the 60's and 70's -- yet this time, we're supposed to think it's "innovative"?

Re:Adam Smith baffled by chip market by BiOFH · 2002-10-29 07:57 · Score: 1

Dude, I worked there until recently. These guys are not sitting around throwing darts when they're gonna release a fatser chip, they're scrambling to squeeze speed out of their designs. We used to tape out a design once or twice a year at most. Now they're doing it as fast as they can and taping out shit all the time. Your categorising of the cycles as "slow" is ill informed and just plain wrong. If anything, the cycle is too fast.

Do you think they can rest on their laurels while AMD is nipping at their heels? The answer, I can assure you, is no. They are working full out and many of the people who work in the design departments and related are burning themselves out fast and furiously. And just because they get a prototype running faster than what's on the market doesn't mean the thing is ready to be released. That's where the RESEARCH in R&D comes from.

Intel, whether I like them or not, is killing themselves trying to get and keep ahead. I used to see it every day. I know these people and I know what they're going through. So...

___shut up___

--
- I am made of meat.

Re:Hyperthread is useless for Win9x, WinNT, Win200 by pellaeon · 2002-10-29 09:09 · Score: 1

Linux does support HT. I run a 2GHz Xeon box with HT as a firewall (on 2Gbit lines :) and it runs an smp kernel, using both cores just fine. Blistering fast machine it is, too! (Well, whaddaya expect, with 15000rpm SCSI disks, 2xGbit ethernet, etc, etc :)

--
-- /bin/coffee missing. universe halted.

Just my take... by Kjella · 2002-10-29 09:44 · Score: 2

But I believe the 700 UKP price tag is to make you believe 200 UKP is a reasonable price for a processor.

If they priced the latest and greatest "normally", your sweet spot would probably e somewhere else...

Kjella

--
Live today, because you never know what tomorrow brings

Re:Hyperthread is useless for Win9x, WinNT, Win200 by edxwelch · 2002-10-29 22:47 · Score: 1

You are more or less right, but under certain circumstances Windows 2000 server doesn't take advantage of the Hyperthreading. Read this: http://www.compaq.com/products/servers/technology/ hyper-threading.html "Windows.NET natively supports Hyper-Threading technology and is optimized to use with Hyper-Threading technology. Windows.NET is licensed by physical processor, but takes advantage of all logical processors and does not count logical processors against the license. For example, a 2P server with Intel Xeon(TM) processors running Windows.NET Server (2P support) will take advantage of four logical processors. Windows 2000 supports Hyper-Threading technology, but counts logical processors towards licensing. This means that the maximum number of logical processors available to the system is dependent upon the maximum number of physical processors that are supported by the operating system. For example, a 2P server running Windows 2000 Server (2P support) will only take advantage of two processors, even though 4 logical processors are available."

Since you were too lazy to look at other pages... by raygundan · 2002-11-03 08:42 · Score: 3, Informative

I went ahead and got you a link to another page in the SAME ARTICLE I linked that shows a chart of CPU usage with Radeon cards:

http://www.anandtech.com/showdoc.html?i=1650&p =6

Note that other pages in the article include the Kyro II, Matrox Parhelia, and the older GeForce 2 and 3 lines, as well as the GeForce 4. Keep in mind that the faster the card gets, the faster the CPU must be to keep it fed with data. You may not see CPU saturation with a slow card, because the card is maxed long before 100% CPU usage. In the Radeon chart, you can see that the faster the Radeon, the more CPU constrained it is. Just like with Nvidia.

The Radeon 9700 isn't there because it didn't exist when the article is written. It will be even more CPU constrained than the GF4.

I suspect you are a troll, but I'd hate to see the issue confused any further.

Last Post! by alpg · 2002-11-12 05:58 · Score: 1

All the big corporations depreciate their possessions, and you can, too,
provided you use them for business purposes. For example, if you subscribe
to the Wall Street Journal, a business-related newspaper, you can deduct the
cost of your house, because, in the words of U.S. Supreme Court Chief
Justice Warren Burger in a landmark 1979 tax decision: "Where else are you
going to read the paper? Outside? What if it rains?"
-- Dave Barry, "Sweating Out Taxes"

- this post brought to you by the Automated Last Post Generator...

Slashdot Mirror

Intel Pushes Pentium 4 Past 3 GHz

262 of 364 comments (clear)