Slashdot Mirror
Intel RoadMap with P4 Stats To Boot
Anand reader writes "In the Intel Desktop CPU & Chipset Roadmap, AnandTech details the Intel roadmap before the Pentium 4 hits the streets next week. The article includes the desktop CPU and chipset strategy. They discuss and answer the questions. Does the Pentium 4 have a chance or is it doomed from the start? What will become of the Pentium III? And will Intel ever speed up the Celeron's FSB? and more including analysis of Intel's current 2000/2001 roadmap." Also see their official P4 stats and benchmarks.
Pentium4 does of course have a place. In x86 servers, for example, Intel chips will hold >90% of the market. This is because AMD chips are not fully compatible with Intel - I have entrusted servers to AMD in the past, and they've been awful. [Perhaps an AMD-compiled version of Windows would be good.]
In terms of corporate, companies will continue to buy Intel for similar reasons (reliability). Pentium 4 will take the place of previous Intel chips as prices fall, as has happened in the past, and Intel will simply stop producing P-III.
The heatsink/motherboard/memory issues are red herrings - these things have happened in the past - slot 1/socket 7, memory chips have changed, etc. It just takes time for these things to happen, but happen it will, and in 2 years will be having a similar conversation about P5, albeit with an even smaller market share for Intel.
In the home, however, Intel is dead - but we knew that already - they're unable to compete on price, and that's all that matters to users, who know nothing of chipsets, heatsinks and processor cores.
Free Anne Tomlinson!!
they are currently the two highest clocked x86 CPUs available
Since when were high performance Intel chips available? Someone at Intel has managed to redfine "available". Does available mean we can go down to our local h/w shop and buy it? Available in the Intel sense means that some h/w review companies might get hold of some if they are sponsored by Intel.
Intel should look at AMD...they have the fastest available chips!
perl -e 'print $i=pack(c5, (41*2), sqrt(7056), (unpack(c,H)-2), oct(115), 10);'
Why would you want a Pentium 4? You need like a pound of heat sink, and you need to get a new case... cause the MB won't fit in what you have now. Sorry I'll stick with my P III - 800mhz :)
A review has been posted on Tom's Hardware with benchmarks comparing performance verses the Athlon and PIII.
Some of these the P4 performs excellently in, however AMD still have a few tricks up their sleeve in other benchmarks equalling or surpassing the P4 clocked up to 1.7GHz.
Anand sez: None of the information contained in this article is provided by Intel and the following roadmap may not hold true. Let's just call it a set of "informed" guesses at what we think Intel will be doing in the next year.
Anand may (or may not) have a good idea what's going on because he's been following these things professionally for a while, but even so.. don't take his word for Intel's word.
Trees can't go dancing
So do them a big favor
Pretend dancing stinks!
I've been using AMD forever and I never had trouble using them in servers. They're rock solid for me.
Oh, I get it, you're using Windows on servers. No wonder you're having stability problems.
I would never imagine using Windows on a server, I don't even have it on my desktop.
Besides, do you think I'm going to listen to FUD from someone whose login name is buttfucker2000?
All of my servers so far (3, 1 of them high-traffic) are using AMD chips, and I've never had a problem with them, and that's without recompiling everything with AMD optimized CFLAGS.
Also, Intel in the home is all but dead. Users who don't know much about computers will get whatever they heard of - and that's usually Intel. Even if they had no technical merits at all, they'd continue (just like Microsoft - and unlike M$, Intel actually has some advantages, such as SMP support).
This message is provided under the terms outlined at http://www.bero.org/terms.html
For the most part AMD certainly seemed to have topped the Pentium 4 chip on those benchmark tests. This seems to be a bit weird, but..
At CPU speeds more than about 1GHz theres little to choose between the various options on clock speed alone. At these speeds the chips are limited by memory bandwidth, code optimization, and instruction sizes. Once a CPU is going faster than the maximum memory throughput of the RAM then any increase in clock speed is going to go to waste. As the article mentions, the code that was run on the P4 wasn't optimized for it at all. This is another limiting factor. If you optimize code for a 286 instruction set and then run it on an Athlon it won't go as fast as it possibly could. And thirdly, AMD have some instructions that do more than those on the P4, thus appearing to go quicker.
Until memory technology, compilers, and applications start really using the new parts of the P4 chips then there'll not be any quantum leaps forward in 'speed'. But once they do expect benchmarks like these to look very different. (Mind you, by that time AMD should have some new toy out, and the field will be level once again).
http://twitter.com/onion2k
i don't really follow compiler technology, but a lot of the speed improvements in the K7 and P4 look like they will depend on compiler specific optimizations. i'm sure the Intel provided C/C++ compiler will properly support all the new SIMD instructions in the P4, as will Visual C++ probably...but does gcc/egcs?
are linux users missing out on a big chunk of the potential performance available in the newer CPUs because their compilers are more tuned to cross platform availability than to x86 specific optimization, or do the GNU compilers already do a good job of supporting 3DNow! and SIMD?
i don't know...someone please tell me.
As a software developer, I don't care a great deal either, as the ABI isn't going to change. Games developers might care slightly, but even they are probably more interested in what video cards are likely to be mainstream in one or two years time as.
If I was involved in the computer hardware business, particularly, say, the memory business, this might be somewhat interesting, but these articles are not written for that audience.
Similarly If I was interested in guess what Intel's and AMD's stock was going to do, I might be interested in this article - but then again there are myriad other factors likely to impinge on their stock price, and it's not written for a financial analyst either.
So could somebody explain to me who seriously reads this stuff anymore?
Any sufficiently advanced technology is indistinguishable from a rigged demo
--Andy Finkel (J. Klass?)
I'm sometimes wondergin why should we upgrade our computing power ?
In practice, I usually play the same old games... mostly Starcraft (yes, not so old...). And a P166 is really enough for it...
I've also a small server, running apache, postgres, proftpd, exim and bind on a debian 2.2 and serving 3 small web sites... These are not big sites with 100+ hits a day... but my cable modem internet connexion won't allow such a trafic...
And that server is a 486DX2-66 with 32Mb Ram. And it has much free CPU time available... No need to upgrade it... he's able to hold the full bandwidth I've with my internet connexion.
So, why should I upgrade my system ? To play those full 3D games ? Most of them make me seasick !!! To play full movie adventure games ? I'm playing the adventures from the if-archive (text-mode only) and spend much more time solving these adventures than these full graphical one...
All is done to have you buy these P4, then the P5,... Not because YOU need them... but because Intel and such needs your money !!!
And when you try to run one of these old programs you'd enjoyed several years ago, you get a message "your computer is too fast" or the game is simply unplayable because it's too fast.
So, I'll leave these computing-power hungry people buying these machines and remain with my good old P233... bought when Pentium I were disappearing...
I think AMD is going the right way to start trying to produce SMP for everyday consumers. As later on in the future, Parallel processing will become more and more important. I expect to see some exciting development come from this. Where I work, the standard Desktop is a SGI 330 with dual 733 or 800 PIII's, and I eagerly await the Dual Athlons!
--- LOTR!!!
a lot of discussion yesterday (about a somewhat related topic) on the clock speed being elevated to the actual performance and how users will probably just go after what "looks" faster...
.02
just b/c AMD has a faster chip for right now does NOT mean that they are going to win out in desktop market share. Like everyone is saying a lot of the code isn't P4 optimized and it is showing...
I really think that people are going to stick to Intel for now. It may not be the P4 but it will still be Intel. The CeleronII's are fast enough for what most people need (and are in the correct price range).
I honestly believe that most people are going to buy whatever comes in their systems from "such and such a store". If Intel can market this damn chip correctly (and I am sure that they are looking to b/c of the major fact that marketing made the push for the higher clock speed in the first place) it is going to be the bigger winner like always.
Just my worthless
Look at the bottom of the Q3 test page.
:
In 640x480 we have :
Athlon 1,2GHz -> 170 (fps/GHz=141.66)
P4 1,5GHz -> 191 (fps/GHz=127.33)
Winner: AMD
In 1024x768, we have
Athlon 1,2GHz -> 100 (fps/GHz=83.33)
P4 1,5GHz -> 101 (fps/GHz=67.33)
Winner: AMD
--
Trolling using another account since 2005.
Look at the UT test :
The new P4 even gets poorer performances than the P3...
--
Trolling using another account since 2005.
The order of things
Pentium I
Pentium II
Pentium III
Pentium IV,........ wait, that's to difficult, they won't understand. Pentium 4 is better.
Mark
"Only two things are infinite, the universe and human stupidity, and I'm not sure about the former."
- if you love something, set it free; if it doesn't come back, hunt it down and kill it
The Celeron is dead meat against the Duron, even with a the extremely belated FSB increase to 100mhz.
As the Celeron increases speed, it begins to cut into the middle of the P3 range. P3 won't go beyond 1.133 Ghz to compete against the P4.
Wouldn't it be cheaper to discontinue the Celerons, and instead readjust the costing of existing P3's? The bulk of the savings would come from the back-end, such as avoiding retooling the Celeron lines and logistical support for two product families versus three. They could also realign Celeron production facilities into P3 or P4 production.
http://www.aceshardware.com/Spades/read.php?articl e_id=15000196
The large scope of the benchmarks was a welcome surprise...
Can anyone confirm how we know for sure that the Pentium 4 core clock really runs at 1.4Ghz/1.5Ghz and it's not just a marketing numbers game? Does anyone outside of Intel actually do / know how to do tests to verify these numbers? Given that it's a completely new architecture, surely it's easy to stick 1.4Ghz on the bottom-end chip and then get away with pumping up the Ghz over the next few years.
Linpack, a buttload of different game engines (11 or so), povray, truespace and C++ compiling
Hardocp
sisoft, q3, ZD benchmarks
For example, I got an Athlon-750 a few months back. What's that good for, other than playing Quake at 100FPS?
Shortly afterwards, my grandmother-in-law commented how badly one of her pictures had faded. My wife mentioned that you could computer enhance them...
I've now got a stack of photos by my desk at home. I've bought more memory and a better printer, but the Athlon-750 seems slow when playing with 60MB picture files.
I'm busy generating some molecular model animations at work right now. More CPU would be great- I've had to cut down the number of points to get models to build quickly while testing code. I got irritated when working on a lab with Mathematica and found that some of the Eigensystem commands took forever.
There's always a use for more CPU. And, of course, Unreal is liquid smooth...
Eric
"Seven Deadly Sins? I thought it was a to-do list!"
Um, is this thing on?
I'm only angry cause I need a little love!
You think your big time?
You think your big time?
I'll kick your ass so hard you'll be unbuttoning your neck button to piss!
People keeps talking about real world performance
of this chip, but I can't seem to find
any benchmarks on how well the P4 does
seti, rc5 and various other "real world apps"!
Anyone?
Thomas S. Iversen
...because they've upped the memory bandwidth soooo much. I've seen some performance numbers from Intel's optimized BLAS (Basic Linear Algebra Subroutines) for the P4, and they are stellar. In particular the FLOP rate for matrix-vector products (just one here guys, no reuse of the matrix or vector at a nearby, cache useful step) which our code spends 90+% of its time doing, has quintupled. And since I've verified Intel's P3 matvec numbers, I tend to be hopeful about their P4 numbers.
Yes...I am a rocket scientist.
My contribution to the fray: Damn, but the P4 sucked for distributed.net :-)!
In response to these kind of articles, someone usually posts about how they don't know what to do with all their current processor speed, and they're not sure what the benefit of upgrading is. Usually they get shouted down by people citing "video compression," "3D modeling," and "solving systems of equations with tens of thousands of unknowns."
CPU speed aside, the Pentium 4 introduction is marking the beginning of the end for constant upgrading. It is:
1. expensive
2. very power hungry & puts out a lot of heat
3. the first link in a chain requiring other components to be upgraded (need a new motherboard and power supply; only a matter of time until "Pentium 4 optimized" application start showing up).
What do were get for all of this? From the benchmarks being posted, the answer is almost nothing. In the best case you get a pointless speed increase in some 3D games, but we're talking about going from Way Too Many Frames Per Second to Way Too Many Frames Per Second Plus A Few More. The increase is buried in a lot of noise.
Review sites that even bother reviewing the P4 should find themselves another business. This processor has no practical value to anyone.
I fully expect this to be tagged as flamebait, but there's not much I can do about that.
Available here.
Wow. 2-3x as fast as Athlon's and P3's running DDR or SDR.
Who needs it a P4, let alone anything over 1Ghz?
Engineers
IT Managers and ISP's (server end)
Students (maybe)
Hardcore Users (gamers and OC tweakers)
In essense, a relative minority in comparison to the consumer market...
All in all, what has driven Intel and AMD up to this point, was inexpensive components that appealed to the needs of the general public... And truthfully, for the majority that does mainly web browsing and perhaps DVD/gaming, a 500 Mhz CPU will do quite adequately...
Especially currently, since the majority is still justifying to themselves just why they bought that $2,000 Pentium 133 based Compaq 4 years ago, and is unlikely to jump on the upgrade bandwagon even moreso...
Maybe in 2-3 years, when Microsoft releases another next gen Windows product, that requires a minimum of 800 Mhz CPU, 256 megs DDR, and an obscene (ie: 1 gig or higher) install footprint, then we may see the justification for faster CPU's...
Then again, I had a friend hand down his engineering sample of a PIII 733 to me a month back, and I still can't figure out what to do with all that power... I'm a graphic artist, so it's neet to see Photoshop do somewhat faster than a slug on my old K6-2 300, and emulate UltraHLE Mario64 @30 FPS for gaming...
But honestly, I cannot see much more viability for Joe Consumer...
Just because you can mod me down, doesn't mean you're right. Shoes for industry!
Haven't we heard this same old line, over and over again, every time Intel releases a new generation of microprocessor.
The PPro (now Pentium 3) was doomed to a server nitch market, likewise the original Pentium, and even statements for the 486 and 386. Each one, very expensive and running much hotter than those before it, and so far the story ends up the same every time. You'd think people would get used to the idea of Moore's Law and, come on now, six generations of x86 processors, it's a lot more like clockwork.... but I suppose the ordinary doesn't make for interesting headlines.
PJRC: Electronic Projects, 8051 Microcontroller Tools
Through the reviews I'm reading, including the one at Motle y Fool, I'd say any immediate buyer is throwing money away , best held in their savings account until the memory, optimization and speed give a better accounting.
--
A feeling of having made the same mistake before: Deja Foobar
Furthermore, in the original Unreal, Epic ditched a weapon at the last minute which would've been excellent: a four-barreled shotgun which fires gatling-gun style. To see the weapon, go into the Mesh Editor in Unrealed and take a look at "QuadShotHeld" and "QuadShotPickup". In Unreal1, you can even summon it (console command: summon quadshot), but it won't work since they didn't put in the code.
"Ancillary does not mean you get to rule the world." --U.S. Circuit Judge Harry Edwards, speaking to the FCC's lawyer
Pentium 4 previews and reviews leave me with the same funny feeling I get when armchair tech wannabes discuss the architecture of the PlayStation 2. You see lots of buzzwords and mumbo jumbo and speculation, but it's not at all clear why or how any of it is relevant. Do microarchitectural decisions have any real connection with end performance or usability? They often _sound_ like they do, when laid out on the table, but it's so much noise. For example, wouldn't it make more sense to discuss internal architectural decisions inside of performance demanding applications, like C++ compilers and video compressors? It's not like the performance of an application is initimately tied to the processor. With retooling, you could make most any application several hundred percent faster, which is more significant than the 10-15% increases we're seeing from expensive CPU pissing contests. But we never see articles tearing apart the reasons why major applications are so slow, for example.
In general, these elaborations of the Pentium 4 design sound like so much marketing, like phony tech-oriented car ads you see in Scientific American. Heck, you could make Linux sound like a piece of crap by trotting out the old "microkernels are more modern and beautiful" debate, but is it relevant?