Slashdot Mirror
Pentium IV Hits 2 Ghz
A number of people wrote in with the news that Intel released the 2 Ghz chip. The Tech-Report article points out a couple interesting meta-ideas - this is Intel's chance to retake the performance crown from AMD, as well as being one of those round numbers that makes people feel warm and fuzzy. I'm sure there's going to be gobs of benchmarks today - post 'em in the comments as you find 'em.
Here.
Basic conclusion: 2.0GHz P4 == 1.4GHz K7, but when the 2.2GHz P4.1 comes out in November it will take a clear lead.
Tarsnap: Online backups for the truly paranoid
I sure hope, for the sake of good ol' times, they'll be manufacturing a 4.77Ghz processor soon...
One thing that you don't see people talking about much is why all these Mhz matter. In other words, is there really a big difference between 1.9 and 2.0 on the software that people use today? And if not, how long will it take before there is a difference?
I am just remembering that back in the day, you could tell the difference between a 200 and a 233MMX relatively easily. Does that still hold true, say, when playing Counterstrike on a 1.8Ghz vs. a 2.0GHz?
_sig_ is away
...if each individual instruction takes up to three times as much cycles to execute. We've been having 667 Mhz Pentium III's for ages...
HardOCP
Source Mag
Cpu Review
Acid Hardware
--- Metamoderating abusive downgraders since my 300th post.
How in Bob's name are those "meta-ideas"?!
They are not ideas about ideas, they are simply ideas. Why do people feel the need to adorn their words with unnecessary cruft? I guess the old gearhead saying applys to prose as well: "If it don't go, chrome it".
<sigh>
This should be listed as a special case of Rule 17.
Most usability scientists agree that no one can distinguish much of a difference in PC performance 25% greater than the base value. When PC ran @ 200Mhz it was no big deal to squeeze ~50Mhzout of it since that was simply a quality control variable in the manufacturing cycle. Now with 1.4-1.9Ghz PCs you need to squeeze another ~350-500Mhz out of it before anyone notices so difference between old and improved performance. Just to keep pace with perceived performance you have to add nearly 500Mhz - that is, for lower values there is NO perceived benefit. Which translates into people willing to pay roughly ZERO for anything less than a 500Mhz improvemen. ZERO dollars for which
Intel may have invested billions of dollars to generate. You see it's kind of like boiling water. Nobody cares if it is difficult to raise the water temperature to 211 degrees - it's the 720x more energy required to raise the water that last degree. So it better be worth it to you to spend the energy doing it because investing only 600x more energy will not boil the water.
It's cool that Intel hit the 2GHz mark, but all that clock speed is really going to waste for the moment.
Right now, you should go for a Thunderbird (AMD Athlon). Later on a Palomino (AMD next-generation Athlon) or the upcoming Northwood (0.13 micron Intel P4) is a better option.
Am I just saying this? No, take a look at this.
.: Max Romantschuk
But:
(1) 1.4 GHz Athlon "MP" will still beat 2 GHz Pee-4;
(2) No upgrade for Pee-4 (423-pin Mobo soon to be out of date);
(3) Should have compared Pee-4 with 256 MB RDRAM vs. Athlons with at least 512 MB (or even 1 GB) DDR (on a same-cost basis)--the Athlons will smoke the Pee-4s, at whatever GHz;
etc.
AMD needs to start gettin the word out that numbers aren't the only thing that matters. On a side note, no one will ever have the crown permanantly. Intel may have it for now then the Palominos will hit 2GHz and then Intel will come out with something faster, then AMD, then Cyrix, then....wait a minute scratch the Cyrix comment.
I notice very little difference between my new GHZ machine and the 333 MHz machine it replaced. Compiles run faster, but I spend very little time compiling. I spend most of my time editing, and the processors have been able to keep up with my typing speed since the days of the 486-25. Web surfing? I/O bound. Video output? Also I/O bound. Most everything is I/O bound these days. Bus speed is more important than processor speed today. After all, when was the last time you saw anyone discussing spreadsheet recalculation performance?
Best Slashdot Co
I'm curious where power supply requirements are headed. A year or two ago, 230-250W was fine, now I'm seeing Intel and AMD demanding 400W. The HFCs that come with these things are now two or three times the size of the socket. With PCs outnumbering vehicles (saw that stat somewhere) I wonder how the power demands and the heat generated will effect global warming and such.
Sure, its probably not much more than a few light bulbs right now (in both aspects). But like I said, where is it headed.
Let's see, we have a Firingsquad review...
An AnandTech review.
And let's not forget ExtremeTech's review.
And finally Kyle and the gang at [H]ardOCP did a review.
Incidentally, [H] got their p4 to over 2.2ghz, but ran into heat issues at 2.3.
You're not doing your friends any favours by recommending they get low-end machines. What happens when they decide they want to run their new copies of Windows XP and Office XP with all the bells and whistles and voice recognition turned on? Or use that Firewire port for something and start messing around with some funky video effects processing? Or play the latest flight-sim or FPS at full-res and maximum reality and physics? A fast CPU isn't everything, obviously, but it's sure as hell not going to hurt.
Software almost never gets faster, and consumer-type applications, like games and multimedia are some of the biggest CPU/graphics hogs outside of 'professional' level computung. I always recommend to friends to get the fastest machine they can afford. It might seem like overkill now, but you can bet in 12 to 24 months it won't be looking like an extravagance. Not everyone wants to run vi to edit C source code and marvel at how small and lean they can get their Linux kernel down to...
Maybe when the 4 ghz chips are out, they'll have figured out how to lower the power requirement so that our computers don't sound like small jet turbines.
Intel can exhaust its resources too -- by making stupid mistakes (like its Rambus chipsets). Losing consumer confidence is a hard obstacle to overcome.
- Michael T. Babcock (Yes, I blog)
While astute computer users know that raw MHz does not automatically translate to application/game speed, not so in the case of the typical user.
When AMD broke ahead of Intel in the MHz race, their marketing department was quick capitalize on this with a media blitz that even included some TV commercials.
However, now that Intel once again taken the lead in the MHz race, astutely AMD has once again retreated its marketing tactics to the knowledgeable and computer savvy.
Every unbiased hardware review page has said pretty much the same thing, clock cycle for clock cycle the AMD is still faster. However, the average computer buyer is still tied down to the more is better idea.
And honestly, that is something that is hard to refute. More RAM is better, bigger HDs are better, bigger monitors/screens are better, faster modems are better...why don't CPU's follow the same rule?
The answer is a pretty complicated one and to explain that would require some basic knowledge that you just can't squeeze into a 30 second commercial. AMD has made noise about a marketing campaign that will educate the public, however so far it has been just that, noise.
Really, I know what I'm doing...Ohhhh, look at the shiny buttons!
it crashes windows in half the time as my 1Ghz. ?
Sit... Speak.... Shake.... Good Dog!
in video and pro-audio care a lot.
An extra chunk of processor cycles = more effects plugins, virtual instruments, etc. This is a big deal for folks with native studio setups.
You're not going to notice a difference in Word but I sure as HELL would notice a difference in Cubase.
http://www.mp3.com/vanderrohe
Let's see, do I buy a 2GHz uniprocessor P4 with its performence-killing 20 stage pipeline, miniscule 8K L1 cache, and high-latency/overpriced RDRAM, or do I buy a dual processor AthlonMP, 128K L1 cache, DDR SDRAM, and 64-bit PCI slots (Tyan Tiger MP) for LESS MONEY?
These days, Intel CPUs are for people who don't know any better (or are forced to buy Dell).
I use a PIII 500 at home. It is fast enough for everything I need to do, even on those occasions I need to run Windows.
Heck, I run Windows on a PII 333 and have no complaints. Very snappy. Hard drive speed is more of an issue than processor speed in a few cases, like when Internet Explorer starts up. And I should add that this machine gets used for intensive graphics design work and software development. Never has speed been any kind of hindrance.
Whenever comments like this are made, certain groups come out of the woodwork: "But I need to solve systems of fifty thousand equations!"; "But I need to use a high-end rendering package!"; "But I run a video processing business!" And those people are all in the tinities of minorities.
it is probably wisest to wait and see, of course, but you shouldn't have any trouble running 10.1 on a G3. right now 10.0.4's interface is equally slow on my G3 and my friends G4, and reports are that 10.1 is wickedly faster on all machines. Apple has been speeding up the code itself, and adding hardware video acceleration support, not just moving stuff to AltiVec (which is what could give the G4 its advantage).
sean
Actually, according to Firingsquad, if you're an unreal player, this tells us that the AMD 1.4ghz is STILL faster than the latest P4 offering! Aside from Quake, the P4 2ghz is only marginally faster. The 2.24ghz (OC'd) does take a bit more of a lead. So, for only $400 extra you can get 10% speed increase on a FEW programs!
There is no longer anything that can be done with computers that is nontrivial and clearly legal. -- Paul Phillips
Like IBM? They really dominate the entire personal computer market now, don't they? They were "the company with the most resources, experience, and capital" and had "secured the lead." I remember 15 or so years ago when trolls like you were proclaiming Compaq to have no chance of ever selling more PCs than IBM. I want an answer to that point! If the largest, richest, oldest company always wins, explain IBM's position in the PC industry today.
AMD already has a very large portion of the market share and their share is growing. They are not some no-name start-up company like Transmeta.
They're big enough to coast, and take a break sometimes. AMD needs every minute of developer time they can get just to keep up! Sooner or later, AMD just exhausts it's resources and slips back into the low-end slot, where it belongs. Also remember, intel can weather a lot more damage to their markets than AMD. AMD doesn't have much of a war chest.
What you are not realizing is that Intel has a lot more overhead than does AMD. Because of that, Intel has to sell their chips for more even if the chips cost the same to produce. AMD loves price wars. They can make a profit at a price point that's killing Intel.
As far as AMD's technical prowess, they have had far fewer failures than has Intel. You have not heard about AMD having to recall CPUs for floating point bugs, motherboard support chips for timing problems, and CPUs because they fail at their rated clock speed. Intel has had all of the aforementioned recalls in recent years. Add to that the Rambus fiasco that has driven up the price of P4 systems and Intel is not exactly a paragon of engineering talent.
I would think that the Slashdot community would be the one to harbor some bad vibes towards Intel for their involvement in the 4C project, or whatever the hell the copy-protected drive is/was. Maybe I'm just too political though, I dunno. Whenever I scrounge up enough money to replace the piece of junk I'm on now, there'll be as little M$ and Intel brand crap in it as possible. I know you're impressed but really that last sentence was included just so that I could plug responsibleshopper.org. It's not my site, but as the kids say, it's keen.
Intel had a great deal of lead because of their SMP capabilities. Thats no longer a problem with AMD and no longer a banefit of all the Intel processors. So I'd guess, put the money where the real benefit is and not just into sounding numbers.
If programs would be read like poetry, most programmers would be Vogons.
Nice post! You did forget to mention that a 1.4Ghz Athlon performs pretty darn close to if not as well as a 2.0Ghz P4. Faster clock speed does not mean sh!t. I want to know which one renders 3d faster, compiles kernals faster, and downloads pr0n faster, er- wait.. forget that last part...
What about running KDE at a useable speed?
> I'm not interested in games, and frankly can't
> imagine what I would use a 1Ghz cpu for, never
> mind 2Ghz.
That's a problem Microsoft is going to run into as well as Intel (and they know it.) 500MHz is more than enough for anything, including DVD software decoding, outside of 3D games.
You need no more computer? You need no more Intel or Windows more than 95.
I am for the complete Trantorization of Earth.
So what were they? What chips did AMD have to recall and for what reason? I'm not aware of any "huge reliability problems."
IBM never really made much of an effort in the PC market, since their core business has always been in big iron, a much more profitable market (ask compaq), than PCs.
Huh? By 1986, IBM estimates put their total PC sales at 7 million! IBM's Boca Raton PC division was a 565 acre campus housing nearly 10,000 IBM employees. For electricity, IBM arranged with Florida Power & Light to have a twin-unit substation built on the edge of the property, with ''double redundancy'' so that each unit would have to fail twice before there was a cut-off in electricity. IBM was not a company that dismissed PC sales as unimportant. For quite a few years, it was their bread and butter. The fact is that IBM fought as hard as they could to dominate the market and they failed, becoming a company that is a non-entity in the PC sales arena.
Didn't see these posted, so check these out:
;o)
SharkyExtreme, and pcmag.com.
Naturally, those seeking the zdnet advertising-big money-enhanced (tm) view should choose the latter, while those seeking that of an enthusiast should check out Sharky's.
-S
- - - - - - - -
Don't worry, being eaten by a crocodile is just like going to sleep in a giant blender.
If you can grab the edge from the competitors by using the extra 50W to grab an extra 100MHz out of the processor, you're going to flow as much juice through that processor as you can.
Look at the VIA C3 (aka the Cyrix III)...a 700MHz chip that takes so little voltage that you can almost run it without a heat sink (almost...which says quite a lot compared to these 5 lb. heat sinks on the P4). So? No one's buying it. Even if it had the biggest battleship of a FPU (though it doesn't), the fact that they're not running the processor fast enough to save energy is not going to sell the processor.
If someone could come up with a power transformer which charges 1000W into the computer case just so that you can get an extra 200-300MHz out of your processor, people would buy it.
AMD has been in business since 1969 and has introduced many CPUs, including proprietary ones like the AM29300 family. If they were "cloners", their chips would perform identically to the Intel chips that you claimed that they cloned. Instead, the current generation of AMD CPUs significantly outperforms the Intel CPUs at the same clock rate. They have more efficient floating point units (FPUs). They use a completely different electrical interface and pinout. They have additional instructions not present in the Intel chips:
21 original 3DNow! instructions
19 additional instructions for improved integer math for speech and video encoding
5 DSP instructions to improve soft modem, soft ADSL, and MP3 applications.
Sure, they support the basic x86 instruction set, but that does not make them "cloners." They would be hard-pressed to sell chips into the PC market that could not run normal PC software and operating systems.
It's a function of how many wafers you can bake within a given tolerance. The difference between 1.4Ghz and 2Ghz is a function of how many wafers you can make that don't melt when you push that many Watts through them as opposed to any material difference in the design of the chip. It's straight up manufacturing process quality control. Each stepping represents a higher yield way of making the same chips. When chips are rated at 1.4Ghz that represents a given economic value of making at least X chips that can pass that QA test. Certainly SOME of them can be made to go faster but not enough so that you wouldn't have to throw out most of the wafer sheet. When the process gets sufficiently better and the yield surpases Y number of chips that can survive a 2Ghz QA test then you have an officially branded 2Ghz chip.
Yes. $ for $ the AMD chips win. But you need a computer engineering degree to understand why. Consumers still measure Sony TV's horizontally to determine if they're 27 or 35 inches (try it! Sony makes them that way so they don't have to educate the public).
However, the 1.4 GHz Athlon with DDR SDRAM was about par on the benchmarks with the 1.7 GHz P4 with RDRAM.
1. You can't get 1.5 GHz Athlons yet, and the P4 has gone on to 1.8, 1.9, and 2.0 GHz.
2. Intel and VIA are releasing motherboards that will run DDR SDRAM, reducing memory cost significantly with an unknown but predicted to be very small performance hit vs. RDRAM.
Ergo, if you want the fastest commercial desktop, you buy the newest P4 platform. And the early adopters, speed queens, and obsolescence anxiety victims have always justified exhorbitant price differentials.
Businesswise, Intel made a bad, bad mistake putting all its chips in the Rambus basket. AMD was also able to leverage some serendipity when Digital went belly-up, leaving a lot of Alpha engineers with nowhere else they could stomach to go. But Intel has been through this before (remember the PowerPC? Apple, Motorola, and IBM combined are about 40x the size of AMD, and they couldn't take Intel...) and has already reposition itself.
Intel can be bloodied, but it's never been knocked down, much less knocked out.
Am I cheerleading? Maybe a little. I own a ton of INTC. But I have always known they make inferior products. 6502, m68k, Alpha, PowerPC, even Intel's own i960 line are superior products to any chip that eats x86 assembly. But if you get prejudiced on the characteristics of a product you will totally fail to understand the value of the company.
Intel will rule in the end. Start from that premise, and then try to prove otherwise to yourself.
--Blair
"It's not an 800 lb gorilla. It's an 800 lb gorilla with a PhD in process technology and 30 Superbowl rings."
but when the 2.2GHz P4.1 comes out in November it will take a clear lead.
That's getting pretty close to the magic 2.4 GHz number.
Computers might upset the global microwave oven infrastructure we've already established. Chaos will ensue, as networks of Amana RadarRanges and Panasonic Genius are disrupted. People might have to make a choice between counting with rocks or defrosting TV dinners over a campfire.
Even worse, there might actually be grounds for newbies calling the CD-ROM tray a "coffee warmer".
This will also be a new problem for overclockers who are managing to get processors up to the lofty 2.4 GHz range. RF heating of their water cooling systems will have to be addressed.
Welcome to a brave new world.
Fire and Meat. Yummy.
You can always find a particular benchmark that makes your desired result occur.
There are benchmarks where 1.2GHz Athlons and P4's beat 1.4GHz Athlons and 1.7GHz P4's.
A benchmark can't be biased. Either you run the piece of software faster or you don't. But selection of benchmarks can be biased. And other value-determining factors can get pulled into the evaluations that are supposed to be made solely on benchmarks.
If all you care about is Unreal Tournament, then you've found your answer. But using that to make an overgeneralized statement like "AMD has the better chip" means you're probably lying to everyone else.
--Blair
>Comparing desktop 1MHz P3 to 1MHz Athlon,...
1mhz? wow that's pretty speedy... you'd think the wattage would go down signifigantly a bit with that type of underclocking
*shrug*
e.
Build Your Own PVR/HTPC news, reviews, &
http://news.cnet.com/news/0-1003-200-6982283.html? tag=mn_hd
AMD to slash prices... you can get your cake and eat it too... er... nvr mind.
e.
Build Your Own PVR/HTPC news, reviews, &
Yeah, sales people are always trying to get people to spend less money ... on some planet that I've never visited.
Ben "You have your mind on computers, it seems."
Blair,
I didn't make any "overgeneralized" statement in my post - read it. I didn't write the subject's topic "RE: AMD has the better chip", just the "RE:" which refers that I am replying to that thread (read: your post has the same subject). First, try to understand my point. What I said was, in Unreal Tournament (not to mention Serious Sam, and 3DStudio MAX) the Athlon 1.4ghz is still faster. I didn't say, "because of the Unreal benchamarks AMD makes a better chip". Also, I said that aside from Quake, the P4 is only marginally faster. This is based on a whole gauntlet of benchmarks. Only on a few programs is the increase in speed significant (read: maybe noticeable). My point was, the chip still isn't faster at everything (see also: "mhz myth"), and where it is faster, it's not worth the $400.
There is no longer anything that can be done with computers that is nontrivial and clearly legal. -- Paul Phillips
Might "backfire" though... Boom Boom.
The NA 2.0L would (all other things being equal) be more reliable...
Okay, my bad, fair enough, looked like you were being bench-selective, I'll take your word that you weren't.
Is it worth the $400?
Not if you're an Unreal nut, no.
But over on Tom's Hardware, almost all the benchmarks other than UT go to the P4.
There's one from SiS about memory bandwidth that I don't trust that shows every P4 with nearly a 2X advantage on any Athlon, but there it is. Maybe it isolates the CPU and just demonstrates the point behind RDRAM (which is also getting cheaper).
Is it still worth $400?
I have been first-day-of-issue adopter of a CPU or two, when I saw the same system two months later on the second tier and for $400 less, I knew that I'd had the nuts for those two months, and still owned a computer that would be nonobsolete for a year, maybe two.
$400 ain't that much for that kind of egoboo.
--Blair
Actually, most Windows applications will still run faster on the 2Ghz P4, since they don't know how to take advantage of SMP. Now for a _server_, the dual MP is a big win. Not sure how many Linux applications see a performance improvement with multiple CPUs...
"Freedom means freedom for everybody" -- Dick Cheney
Personal computer and microwave in one! It bakes! It fries! It dices! It comes with a free set of steak knives... well, no, actually, it doesn't do any of those things - but with an appropriately shaped waveguide and a metal-free ceramic mug it could heat your coffee (or my herb tea) directly.
Cool!
Er, no, that doesn't sound right, either...
Got time? Spend some of it coding or testing
Well, obviously it's a personal decision.
I most definatly was not being bench-selective in the sense that I strictly pointed out that there where other benchmarks with other results. I just found it funny that it's still not a "cut and dry accross the board" faster performing chip.
The issue is, although most benchmarks where held by the P4, the $400 or nearly 380% price increase compared to a 2-5% performance increase on the more broad benchmarks (read: not Quake) makes the "it wins most benchmarks" point moot. Nevertheless, the P4 is a technology that is specifically designed to meet the marketing demands of the "Ghz" ratings, and performance is secondary. This is disgusting. Now, the new P3 is a good chip - albiet overpriced. I'd rather have one of those than a P4. And since the current P4 architecture is being phased out for the Whillimate's, I see no reason in buying Intel right now - just wait, or go AMD. Intel may still come out on top, just not with thier current offering.
There is no longer anything that can be done with computers that is nontrivial and clearly legal. -- Paul Phillips
The answer is a pretty complicated one and to explain that would require some basic knowledge that you just can't squeeze into a 30 second commercial.
Here's an eight minute video that aims to do that. It's in QuickTime, btw.
- Scott
Scott Stevenson
Tree House Ideas
You are simply wrong and you need to read some history books before you start spouting off your unsubstantiated stuff. Give me some facts to support your wild claims. Tell me what percentage of IBM's gross profit or revenue was accounted for by PC sales. Don't get on Slashdot and try to rewrite history.
So what were they supposed to do? Make a chip with a totally new instruction set that they invented and then hope that Microsoft and the software vendors would port their products to it? Get a clue! Of course the license the IA32 instruction set.
In the early days their chips were virtually identical to Intel's. They have made many good improvements to Intel's designs since then, but to even call them 'cloners' (in the Compaq sense) is an overstatement.
That shows how little you know about history, CPU design, and basic terminology (like "clone"). A "clone" CPU is not something with radically better performance at the same clock speed. Right now, the AMD 1.4ghz CPU is a good match for the Pentium 2.0ghz CPU and even outdistances it on floating point. That's not how clones work.
How's that Java thing going for you?
--Blair
The top-end, newest-model units have always been several hundred dollars more than the next step down. And the 1.4 GHz Athlon is at least three steps down, being comparable to a 1.7 GHz P4, which is now behind the 1.8, 1.9, and 2.0.
I can see a lot of people finding value in that. Personally (yes) I could do with 4 GHz now, and would gladly pay $1k just for the CPU.
Porsche stays in business by not worrying what BMW is doing.
--Blair
P.S. I think you have it backwards. The current P4 is the Willamette design. The new one is the Northwood. And it's not a phase-out; it's a shrink and a bus upgrade. The Willamette price curve will continue like all of them. Northwood will scale up to 6 GHz, and semi-official hype (it was an Intel guy, in an interview) says 10 GHz. Brookdale is the i845 chipset, which will allow the Northwood to interface to SDRAM and DDR-SDRAM.
(Go to TomsHardware.com and search on "intel roadmap"; I'd post a link, but the net is totally packed up right now...)
if you're an unreal player, this tells us [gamers.com] that the AMD 1.4ghz is STILL faster than the latest P4 offering!
And it also tells you that if you're a Quake player, it isn't.
Remember, kids, read ALL the fine print...
You're right - I got the Intel stuff backwards.
Well, the 1.4Ghz is actually closer to a 1.8 then a 1.7 performance wise. My point is that it's NOT a Porshce because a Porsche is more than 1/10th of a second faster than a BMW on a 0-60. Now, if you wanted to spend money, you could try a dual Xeon 1.7ghz, or a Dual Athlon 1.2Ghz. In which case Anandtech.com will tell you that they are moving all their Xeon's to the Athlon MP's because they scale better for half the price.
Maybe the Northwood will show AMD who's boss - and if so, I'll go for it when I need to upgrade. Right now, my $95 1.2Ghz Athlon is out rendering a low-stock $266 1.8Ghz P4 in 3DSMax, and only suffers a 1-2% speed loss in photoshop.
So, if you want to buy the fastest overall chip, then wait and buy the 2.2Ghz P4. If you want to be smart about it, stick with the new P3's or even better the Athlon's.
There is no longer anything that can be done with computers that is nontrivial and clearly legal. -- Paul Phillips