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.
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);'
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.
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?)
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.
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!"
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.
Things I use my machine for that you wouldn't want to do on a P166
- Run Linux and Win2k at the same time in VMware
- Watch DVD's in software mode.
- Play MP3s while doing anything else (like browsing the web)
- Compile any project. While large projects do take longer, even small projects will get anoying if you have to wait longer then 5 seconds.
- Play 80% of the games that came out this year.
- Play 100% of the games that come out next year.
- Get kewl demos from Nvidia and "whip-it-out" in front of my geek friends
And I'm sure i'm missing something else.
this is my sig.
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
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?