Slashdot Mirror
Double-Whammy Look At The Pentium 4
SystemLogicNet writes: "We at SystemLogic.net have just taken a technical look at the Pentium 4 architecture. In the article we go over all the basics that all the other sites cover like the double pumped ALUs, iSSE2, the longer pipeline, etc, but in addition we have some discussion about how different program structurings have an impact upon the design, and performance of the Pentium 4. One of the major areas where this comes into play is how complex data structures interact with the underlying philosophy that the Pentium 4 is built upon -- extreme bandwidth. This Pentium 4 technical background can be read over here. At the same time, we've done a rigorous analysis, including benchmark description and discussion regarding the Pentium 4's performance, and this can be read over this way."
That's all well and good, but how does this help me right now? I want to buy a computer today. What should I buy? A Pentium 4 which might or might not become worth something years ahead down the road, or an Athlon which I _know_ is good _today_. Future forecasts may be fun to do, but they don't do anything for immediate purposes.
As for the Pentium Pro, Intel didn't have a real competitor at the time. Today, AMD is serious trouble for them, so they can't afford to simply sit back and tell the customers to wait 5 years.
Hertz aren't irrelevant if you don't understand the issues (read: 95% of computer buyers, corperate and personal). It has nothing to do with being rational or not, it has to do with being uninformed.
end communication
That is called truncation. It's a favorite for showing "huge" differences when the real numbers show otherwise. Chop the bottom of the chart a few points below the *bad* data set. Chop the top a few points above the *good one*. (Used to work in a shop where our motto was:"You give us the answer - we'll give you the problem to support it)
I don't think anyone has said that the P4 isn't fast necessarily... but i've heard many complaints about the price/performance ratio, which is much worse than an equivalent Athlon platform.
... hell, a friend of mines main server for his company network is an Athlon and it's worked out fine.. no problems with stability at all.
... so long as the person who built the system knows what he's doing.
I've never had any complaints about the speed or the price of an Athlon system. I've heard complaints about the stability, but it's hard to take many of those complaints seriously when there are so many people out there who don't know how to build an Athlon system properly (using crappy power supplies, cheap RAM, etc.)
I've built and used many Athlon platforms. They are as stable as you could hope for on any of the popular platforms (Windows 95/98/ME, Windows 2000, Linux)
Sorry, but I have seen no evidence of what you claim is a "choke point in performance and reliability" ever
-- Jim
Wrong! Branching is predicting the outcome of a dice roll. If you predict the outcome of 10 rolls and get a correct prediction 90% of the time and have the next instructions calculated on the outcome, you are way ahead of the game. The old way is wait for the roll then act on the outcome. Having most of the likely outcomes predicted, and the next instructions lined up in the pipeline puts you way ahead in time when an outcome becomes known. That is the advantage of prediction. To predict all possible outcomes to all chance paths is not 100% acheivable. The unlikely outcomes are not predicted. For example, predicting the next keystroke from a user can be 90% that it is a single keypress and all instructions on that can be pipelined. However predicting that the next keystroke is going to be Ctrl-tab-F7 is a waste of time and would be part of the 10% not predicted. Don't expect 100% prediction.
The truth shall set you free!
If you don't understand the issues, then by definition nothing is relevant. You won't understand it...
Sex is heriditary, if your parents didn't have it chances are good you won't either.
Check out the hardware list used for each machine, you'll see the AMD box was robbed compared to the Intel box. My AMD at home smokes my P4 machine at work. The testers are a little Intel biased, shows in the the charts blowups as well
Please! Reviewing the new features of chips is a great thing, but for fuck's sake we all know about Tom's Hardware, AnandTech and Ars Technia, All of which have covered the P4 in extensive detail.
that comment is in left field the war is on and there's talent in house working on bumping up performance/cost while making money. a lot of consumers are happy w amd now but stock holders should be really pissed that amd isn't making much money while they had a perceived lead. hold on and see what happens this fall...
And just what is so excellent about this combination?
A processor that won't scale up to 2 GHz and programs written by a bunch of anarchistic amateurs with a socialist agenda?
A bomb is bad, the bomb is good. Right?
I think I remember reading someplace that one of the two (i forget which one, I think the Intel) has an additional 32-bit core inside to deal with legacy processes.
Give me a dollar or I'll tell everyone that you touched me in the poo poo hole
Yeah, really boring, useless and Intel-biased article. Compare the newest P-IV to something a bit newer (and with AMD760 + DDR) from AMD as well...
Sorry, but everything I've seen has shown Rambus memory to be no better than DDR SDRAM, and at double the price.
- Spryguy
There are three kinds of people in this world: those that can count and those that can't
Volrath50,
Thanks for posting the Emulators, inc. link. It's a great article and I had lost the bookmark.
Pedro
----
The Insomniac Coder
To the critics I say: remember Pentium Pro. It's an all time Intel classic, it spawned several generations of Pentiums and it is still very much in use in multi processor architectures. Yet it was deemed a failure when it came out.
I still can't understand why anyone can support the temp slow down on the P4. Why should I buy a 1.8 Ghz processor if everytime I really need the processing power, it throttles down? I might as well by a PIII 1 Ghz that will remain at 1 Ghz. It would be good if Intel incorperated the Power Now feature that AMD has. That would make so much more sense.
I'll go back to Linux when Windows goes open source.
Umm... This isn't a very good analogy. Imagine instead:
STOP . AMERICA . NOW
Well, if the line is non-contiguous, ie has a discontinuity (like, y=1/x), then it could have a mid end.
Actually, I think he meant midpoint.
They pointed out that they got their processor and motherboard from Intel. They even mentioned things like that several times, and apologized for not having another system. Some people can't afford new athlons....like me :-\ (damned socket 7 piece of...)
Ummm, if intel adds the right amount of cache, for p4 mark2 , them i will be keen. like the original cereron, p4 has been crippled for market segregation reasons; legacy stings are needed to rile developers to write new code - aimed for intel only, not amd. the article is spot on. wonder if amd is cooking up its own vliw cpus. on cache. if amd goes cu/soi/.013, with more cache, lookout. My guess is cache gets hot/unreliable with factory overclocked offerings.
What goes through the mind of vendors who assume that customers will, of course, run out and replace all their software to take advantage of a new chip.
This sounds all too much like the music industry who thinks we'll run out and buy new copies of stuff we already own in order to enjoy some new technological advance.
I'm sure the P4 will be great... in a couple of years.
CUR ALLOC 20195.....5804M
Wow, Intel really loves the MHz wars. Pumping out MHz when only 90% of the brancing is correct. Most of you probably think 90% is good, but think of it this way: 1 out of every 10 times you try and click on something, or double click something, or open a file, whatever, it fails. Every 10th Word file fails. This is good? Industry servers are designed for 5 9s (99.999% uptime), yet we can accept a 10% fail rate for our processors?
Maybe you should get informed what branching means.
Everyone who makes generalizations should be shot.
Even if Intel does ramp their procs up to 2.5gigs, with the i845 chipset coming out (PC133/DDR SDRAM) those procs are going to fall flat on their faces.
RDRAM is what gives the P4's their edge. Once that's gone (and most consumer level machines WILL use the i845 because it's cheaper), you're going to see Intel in a world of hurt when it comes to performance.
Unless Intel makes some changes to their processors, or a faster DDR SDRAM technology comes out, you're going to see some serious ass kicking being done by AMD.
Which end of the middle would that be?
The way you describe it doesn't seem to fit with how the words are usually used.
Usually in sales & marketing, the term is mid _range_, mid _end_ is simply rediculous as even if the middle had an end, it's not descriptive as to what the end of a middle is, or which end assuming if there is one, or where that end is if there was only one.
Ironically the people here seem to delight in bashing Rambus which would solve this particular bottle-neck.
Yeah, now. After a few years the astronomical clockspeeds and Rambus memory will make this pretty muc irrelevant.
It's the same thing as it was with Pentium PRO. At first it sucked cause it was lousy at running 16 bit programs and everybody whined how bad a processor it was. After everybody got to use 32 bit versions of the programs and the CPU speed got ramped up the true potential of PPro started to show.
Sheesh - go down to your local computer store and get a 1.4 GHz Thunderbird at least - it'll only set you back less then 200$.
Anyhoo - I think given the actual mhz difference the Thunderbird does VERY well.
Personally, I don't agree with the Brute Force methodology by Intel; I prefer simpler, cleaner and more elegant solutions. It is difficult to deny, however, that the brute force method has worked so far. Yes, yes, I know that the "x86 suxx0rs" crowd is now going to come out of the woodwork. Let me just say this: It may not be the best architecture, and it may be kludged for backwards compatability, but... it works, and it's cheap. With any luck, the 64-bit processors will be able to buck the trend of backwards compatability (has anyone heard anything about this with regards to Itanium and/or AMD's 64-bit chip?).
"To hope's end I rode and to heart's breaking: Now for wrath, now for ruin and a red nightfall!"
You're absolutely right. But like you say about the Pentium Pro - It SUCKED when it came out.
The Pentium 4 is an inferior chip right now, so it's a poor purchase choice, again, now - and for more reasons than are made evident in this comparison.
- The parent is obviously a troll.
- AMD is dead in the water anyway - their next-gen chip is as good as dead (no support from anyone, including Cygnus and Microsoft; constrast with the Itanium, with support from both the above).
- Very few mainstream OEMs support AMD anymore (like they ever did). Want a AMD box? Go find Mom'n'Pop Fly-By-Night Computer Shop. Or build it yourself.
- AMD has no mobile technology, even as laptops become more important (as many PC manufactorers are trying to move sales to laptops as laptops still fall into the rapid upgrade catagory as laptop options improve - PC sales are falling, but laptops may replace them).
Conclusion: Renew your Intel contract, and get ready for Itanium 64-bit goodness.It is a little early to begin reviewing the Pentium IV. Intel released it early due to market pressure from AMD.
When the
Bush's education improvements were
Whoa there! That is the best feature of the chip! Once XP catches on (remember OOP 10 years ago, vs. OOP now?) Intel will have secured themselves a leg-up on the imposter brands.
Benchmarks show that programs compiled with intels compiler using P4 optimisations
That's predictable. A code recompile is needed with every one of the Pentium processor generations in order to make any significant performance gains. I'm not saying that's good or bad, there are downsides and upsides to that. For one, we'd get faster code but that means that the compilers have been re-tweaked and all our software is re-compiled, but then that usually means waiting for the next revision, and buying new software.
The link claimed that the optimizations available in modern compilers aren't much beyond Pentium.
*Bzzzzt!* Wrong. Accurate branch prediction is expecially important when you're dealing with the P4's whopping 20 stage pipeline. Each incorrect prediction costs quite a few clock cycles and slows down overall processing signifigantly. See this ArsTechnica article for details.
Tom's Hardware Guide or AnandTech
Sorry, but comparing a 1.1gig/200Mhz FSB Athlon to a 1.7gig P4 is laughable at best. What hardware review site uses a processor that's over a year old (Athlon 1.1gig/200FSB) in a comparison to one of the latest processors from the competition?
If you have any details on the P4 branch prediction please post them... Oh thats right... you don't have any details on it do you, since it's such a closely guarded secret... stfu
I must burn in hell, suffer and pay for my sins
But Gods the one who's losing, Satan always wins!
Maybe you meant "dual." Wish people could spell.
Ceci n'est pas une sig.
Dropping RDRAM and going backwards to PC133 memory is going to seriously kick P4 processors in the nuts.
This tired old article... that guy is writing from the assembly programmer's point of view, not the computer architect's point of view...
I must burn in hell, suffer and pay for my sins
But Gods the one who's losing, Satan always wins!
There is no moderation word that means "this post agreed with a previous one but provided clarification and additional information." Maybe that's because posts like that are not supposed to be modded down. If you are a moderator, make sure that you understand the meaning of the words before you moderate.
P.S. Oh no! I'm down to 48 karma points!
"an intensive technical treatment by a teenager who doesn't understand pipelining..." That said, Athlon's the better chip and CPQ is a big pussy for killing Alpha, which would have kicked all ass known to man if they'd taken it seriously.
also, note that the 1.7 ghz p4 has a 600 mhz advantage over the 1.1 ghz athlon and usually the performance difference was only 10-40%. the p4 has over 50% more processor mhz than the athlon. what an unfair comparison, especially when the 1.33 ghz athlon is out and available for purchase. processor mhz for processor mhz, the athlon beat the p4.
The point of the extremely long (20-stage) pipeline of the Pentium 4 is the ability to reach extremely high clock speeds - much higher than the Athlon could ever reach. Of course, Mhz-for-Mhz, the Athlon is going to beat the Pentium 4 performance-wise, but it wouldn't tell us anything except the obvious differences in the two's design philosophies.
Light a fire for a man and he'll be warm for a day. Light a man on fire and he'll be warm for the rest of his life.
That is a much better explanantion, and now in respone to the original comment: it is nearly impossible to criticize that "miss rate" without actually going through the design process.
Something like Patterson & Hennessy would explain the classic tradeoff well. If you make a lower miss rate (imagine 9.5 out of 10 are hits), the time for hits goes up slightly. Now the main question becomes, what is the "common case".
The most important thing before you whine about some processor is to know the design process. Is missing 1 out of 20 times (but hit-time taking twice as long) better? Is missing 1 out of 7 times (but having a lightning-fast hit-time and tolerable miss-time) better? As a /.er there's really no room to say "thats so bad" unless you actually sat at Intel/AMD, went through the design process, and there was a better option for your mix of instructions.
Using the new process of W.attage H.alting R.esistance E.ngineering, Intel can reduce pent-up system tension at an even lower cost.
Also, the WHORE system is fully compatible with the C.omposite R.ecursive A.lgorithm C.reation K.it used for extreme overclocking.
"The CRACK/WHORE combination should be a killer setup for many of our users, and we have already had several U.S. senators make inquiries" says John Thompson, head of engineering at Intel. "We even allow for massive clustering with the P.arallel I.nsulating M.ultipartite P.olymer, or PIMP management process.
Thompson also spoke of project BITCHSLAP for correcting wayward systems, but could not elaborate on it...
Did you just cut and paste a press release onto the front page of Slashdot?
I sure hope you Slashdot isn't selling Front Page space to any little company that pays...
The parent article appears to be a troll. I can't find any use of the word "Xtreme" in either cited article, and it's bizarre to claim that someone has optimized a processor to suit a software development methodology. There's a couple or three levels of abstraction inbetween. What's the possible connection?
And what about all the poor saps who buy the current P4? Oh well, like many a fascist dictator has said, your current sacrifices will be appreciated by the people of the future!
The current Slashdot moderation system is made by gay communists!
Oddly enough, most Windows users don't seem to mind...
While I agree that as technology moves forward the traditional ways of X86 programming will have to expand along with the technology, and in some areas change completely, I'd just like to share something about upcoming AMD technology in this regard.
The next-generation chips from AMD are being designed with programming optimizations done at the firmware level. For example, a FORTH interpreter is being ingrained into the preprocessing area on the chip die itself. This makes it easier not only to add firmware-level software like BIOS, bootloaders, etc more easily, without resorting to running the code through a compiler into X86 instructions and machine code, but it will also make it much easier to write more optimized C compilers (and other compilers for that matter). If you combine this with the improved instruction technology that AMD will be incorporating, it makes for a very powerful new platform for all programmers.Dwain Snyders
Research and Development, AMD
2DUP * ;
didn't you get sick of crackwhore jokes sometime in 1999 or so? --proc
the graphs are not done fairly. they almost never started at 0 to a result slightly higher than the higher result of the two processors, they were always done so that the intel bar was much longer (and therefore appeared to do much better) than the athlon when the actual results were that the two processors were pretty close.
also, note that the 1.7 ghz p4 has a 600 mhz advantage over the 1.1 ghz athlon and usually the performance difference was only 10-40%. the p4 has over 50% more processor mhz than the athlon. what an unfair comparison, especially when the 1.33 ghz athlon is out and available for purchase. processor mhz for processor mhz, the athlon beat the p4.
The 1.4 ghz athlon has been out for a couple months now... the 1.1 ghz athlon has been out for at least 10 months.
Here is a june 6 pcworld review where an amd 1.4-GHz system is "the fastest system yet tested by PCWorld.com" beating out 5 systems based on the 1.7 ghz p4.
Here is a tech report review of an amd 1.33 vs intel 1.7 where they conclude: "Intel's new entry, the 1.7GHz Pentium 4, performs about like a 1.2GHz Athlon in most situations."
You cant get duel processing power from a pentium 4 like you can with an athlon.
We have the best government that money can buy.
HOW did THIS get mod'ed up???
Shame on both of you.
Better analogy: You double click on a Word file. It fails, because Microsoft can't build a halfway decent OS - it has NOTHING to do with an incorrect branch prediction.
Wrong branch taken: the correct instruction is fed into the pipeline a tiny fraction of a second later and you're set.
I recommend any book on processor architecture.
Corporate buyers are where Intel makes it's $$$. And the corps aren't buying RDRAM, not because it's more expensive, but because it's a pain in the ass to support different types of memory on the desktop level. They also don't give a shit about performance - it's all about stability.
That's why your average Dell or whathaveyou will be i845/SDRAM, IF it proves to be a stable board, and IF Intel forces their hand by phasing out the PIII/i815 combo they know and trust.
AMD can kick ass all day long (and more power to them!), but until their chipsets get a better reputation, Intel is still sitting pretty in the most profitable market segments.
AMD chips are great but their mother boards aren't that great due to the reversed engineered AGP implementation. I have an Athlon that's gathering dust because the motherboard was a choke point in performance and reliability.
Interesting. This machine is equipped with A7M266 & TB 1200/266. It's been rather stable:
uptime
8:52pm up 127 days, 2:22, 27 users, load average: 2.06, 2.07, 2.08
A choke point in performance and reliability indeed...
Everyone who makes generalizations should be shot.
Whoa, an "assembly-level programmer." Well, there you have it folks. It's official, the Pentium 4 sucks.
Sorry, I was responding to the "Why the Pentium
4 sucks" msg, re: the url
http://www.emulators.com/pentium4.htm
There is a good page about wh the Pentium 4 sucks. It's written by an assembly-level programmer, so he know quite a bit about processors.
Oh sure, just blame the Microsoft Program like everyone else here at slashdot.inc.!!
Seriously, though, god knows what other mistakes were made in these crummy benchmarks.
I want my DDR!
The current Slashdot moderation system is made by gay communists!
P4 scales so much better than the AMD Athlon architecture that next year we'll be seeing 1.7 GHz Athlons and 2.5 GHz P4s.
AMDs only hope is that their Hammer architecture will kick Itanium's ass and now that Intel got the Alpha engineers and technology even that looks rather an iffy proposition.
While the Artical makes some good points, it is obviously biased against Intel. Some of the statements are not accurate. The artical should be taken with a grain of salt.
Any woman will tell you; it's not the size of your pipe, it's how you use it.
(They're also lying..)
end communication
1.1 Ghz 200fsb Athlon -vs- 1.7 Ghz P4????
The 1.7 was released april 23.
The 1.333 Ghz 266 fsb athlon was released april 1.
The MSI KT7 Turbo is at best a middle of the pack Motherboard. It does not use DDR.
The intel 850 is the best platform available for the p4
This is sort of like saying the ford mustang (P4) is faster than the chevy camero (1.1;200,KT133), therefore it is faster than the corvette(1.333;266AMD760). WRONG
BAD BIASED ARTICLE NO COOKIE! LOOSER INTEL SUCK UP PAID FOR JOURNALISM.
or a fan boy, therefore unpaid suckup double looser stoolie.
-1 flamebait
If voting were effective, it would be illegal by now.
I was shocked by this review site. Most all the graphs are misleading. Most magnify the area of differenc between the two processors to make the margin look larger. For example, in the benchmark "Content Creation Winstone" (http://www.systemlogic.net/reviews/hardware/proce ssors/intel/p41700/i/c7.gif), the difference is only 3.6 points, yet the scale is nearly 1/3. That's nearly 3x magnification.
Some only differ by a few percent, the lowest about -4.5% of P4 score, yet the distance represented on the graph would suggest nearly a 60% difference or more.
This review site needs to get a clue about statictics and start using proper graphing according to real differences, not magnified margins.
"I'll just chip in a bit for RedHat: I actually have that installed on my university machine." - Linus, '95
I guess /. is in the advertise_our_site biz now. Funny thing is this stupid site's interface is an exect copy of Dr. Tom's site.
The review was pretty interesting. Essentially it comes down to this:
1. The P4 1.7G is a faster processor than the Athlon 1.1G (and probably the 1.4G but they really can't say).
2. It costs a few hundred bucks more.
3. Just wait till next year's model, which will be even better.
It seems to me that the people who want the highest performance will pick up the P4, and those who want to save money will pick up a Celeron. Who would buy the Athlon? People who want to compromise between price and performance.
As for the temperature slowdown switch, I'm all for it. Why fry my processor unnecessarily?
144l. ph34r my 133t l3g4l 5k1lz!
If you don't know this kind of stuff, then don't criticize Intel. Branch Prediction is hard stuff. If I asked you to do it with 90% accuracy, I bet you couldn't.
"To hope's end I rode and to heart's breaking: Now for wrath, now for ruin and a red nightfall!"
Yes, and a review I read showed it to have the performance of a 100MHz Pentium!
Numbers 31:17,18 Now kill all the boys. And kill every woman who has slept with a man,but save for yourselves every virg
Wow, Intel really loves the MHz wars. Pumping out MHz when only 90% of the brancing is correct. Most of you probably think 90% is good, but think of it this way: 1 out of every 10 times you try and click on something, or double click something, or open a file, whatever, it fails. Every 10th Word file fails. This is good? Industry servers are designed for 5 9s (99.999% uptime), yet we can accept a 10% fail rate for our processors?
Also, the P4 needs a temperature shutdown?!?!?! Makes one think that even if Motoralla's Apple chips are lagging in MHz, at least they won't burn down your house!
Vote monkeys into Congress. They are cheaper and more trustworthy.
On the other hand, the Athlon and its offspring seem to be better no matter which way you cut it. You'd think they'd keep intel on its toes...
Whew! That review was scathing! Any time someone
bashes that hard on a product/company I get
suspicious of their data.
But in this case, I believe it. I've been madly
in love with AMD's Athlon/Duron line since I first
tried it. I upgraded all my employers PC's to
Duron processors (the day-to-day performance diff
tween Duron and Athlon not even noticable).
The dnet client on an AMD Duron/Athlon will whip
any Pentium hands down, clock-for-clock.
I do believe Intel really shit their nest this
time.
it's sad that Intel feels the need to optimize for an untested and foreign program structure (XP) when they haven't even gotten imperative programming optimizations done right. oh, and that failing-branch-10%-of-the-time might knock the wind out of the P4's sails (sales) too. i'll stick to the Open Source support of the Athlon.
Cretin - a powerful and flexible CD reencoder
Rambus is a superior memory bus. Engineerwise there's nothing wrong with it. On the hand, Rambus the corporation has tarnished the product name by predatory litigation.
Please don't let your hatred towards a company blind you from technological facts. Given increasing CPU clockspeeds Rambus wins the day.
I agree with most of what you say; however, I think many companies' time would be better spent trying to improve the bottlenecks that already occur in every-day usage (Disk, memory, bus, etc.). This would have a much more tangible impact that pumping up the processor speed. Most processors are already crippled due to the lack of a memory bus that can keep up with them, along with disk I/O. It's disappointing to see these MHz wars continue while the real performance issues receive short shrift.
"To hope's end I rode and to heart's breaking: Now for wrath, now for ruin and a red nightfall!"
The Pentium 4 is, by Intel, considered to have "Hyper pipelined technology."
I can see the ads now..... "The Pentium 4 - Because our Pipline is bigger than theirs!
S.t.e.v.e.
Intel's biggest problem is that they are losing inovative engineers. Anyone with any real talent has left Intel already. Management is running the scene and they need to pull their heads out of the ground to see what is going on. A good example of this would be with the Rambus fiasco. It was the managers that made the decision to use Rambus, not the engineers. Another example would be the web tablet. This product has been in development for a long time. In fact, if people at the last CES didn't show much excitement for it, the Web Tablet would have been scratched already. By the way, 80% of the webtablet group have been either laid-off or re-deployed to other groups. What does that tell you?
They zoom into just the ends of the graph. If the bar being twice as long done not mean twice as good what is the point of the graph you have to read the numbers 2 know what is going on.
I agree that the P4 is not the best CPU at this time. However, Intel has designed this new architecture looking out 10 years or so. Many of these choices are dictated by the laws of physics, and all other processors will be heading this direction over time.
The fundamental problem is that propagation speed of a signal on a chip is essentially fixed (that's why the minor improvement from a special trick like copper wiring was a big deal). As you speed up the transistors, the signal propagation delay becomes more of a bottleneck.
To avoid this, you have to break the logic steps into smaller pieces that live in a smaller portion of the chip. The standard way to do this in synchronous logic is to pipeline the work into more stages. The total signal propagation delay to do one instruction remains about the same, but at least you can pipeline alot of instructions to try to get more work done.
This processor is not very competetive today, but in 5 years there won't be any other way to make forward progress. By that time, Intel will have worked out the kinks (problems with branch prediction, memory interface snafus, etc.), and this core will probably be as wildly successful as the Pentium Pro/PII/PIII/Celeron core was.
BTW, remember how sucky the Pentium Pro was when it came out? It was a piece of crap on 16-bit code and it would generate huge pipeline bubbles for no good reason. Over time, they fixed these problems and made countless $billions in the process. Watch for a repeat with this new architecture.
The new Pentium 4 can currently get 400 Anusmarks, while the new Athlon can only get 350 Buttmarks. Well, I dunno about you, but that convinced me... I wanted to buy a Corvette, but the needle only went to 125 Mph, so instead I bought the Pinto that showed 140Mph on the guage.
The grammar used in the "review" and that used by you leads me to believe that you are said reviewer. "Cost cheaper"??!!?? "There will a huge"!!??!! "He know"!?!?!
It is almost as bad as Taco (and nearly the rest of Slashdot) not knowing the proper usage of the words 'then' and 'than'. I can not take people seriously when they have not mastered even their native toung.
First of all, even thought he Athlon may cost cheaper and perform better, there will a huge percentage of people, whether they are home users or corporate users, that will stick to Intel because of the name.
he know quite a bit about processors.
I have one and it's quite fast. I've been
using my P4 1.7GHz to play Tribes 2 under
Win2k and it's super smooth.
I've never heard anyone who has a P4 complain
about lack of performance or stability.
AMD chips are great but their mother boards
aren't that great due to the reversed
engineered AGP implementation. I have an
Athlon that's gathering dust because the
motherboard was a choke point in performance
and reliability.
PRIME - Indivisible by anything but ME!
Kjella
Live today, because you never know what tomorrow brings
Dude, it's 'tongue'. Of course, since you can't take seriously people who "can't master their own toung", I can assume that was funny. Right? Spelling Nazi
Ok, every article on the Intel Pentium 4 has so far shown that my expectations of the p4 are way off. I was able to get the original specs for the chip, and I must admit, I was drooling all over the paper. Things like 512k first level cash and things of that nature. Then I read the new specs on the p4 when it is released, where is this chip I drooled over. Well it dose not exist, they cut and chopped all the good stuff out. Now an Athlon 1.3 ghz is running just under a p4 in most bench marks when the p4 is running at 1.7 ghz. With a 400 mhz difference, the p4 should be whooping the Athlon for fun. But as any informed person knows, mhz dose not give a accurate idea of how fast the chip truly is. Now what gets me is who actually decided to cut all the good things out of this chip they wanted to create. Well from what I have read (I believe I found some articles through SlashDot, but am not fully sure and would love clarification on where this info would be) the engineers did not cut out the good stuff. It was the marketing and accounting departments. So we are getting business drones (we are Intel, you will be assimilated) deciding the design of Pentiums chips. This is completely wrong to let departments that do not really understand the chips except that the idea to them "BIGGER IS BETTER".
This is no way to properly run a business, and now with amd's big pushes with their Athlon chip, they are being hit hard. With amd biting Intel's heals and making major headway, you would think Intel would wake up and smell the coffee( mmmm coffee). But they are still just designing rather non-innovative chips that are not really putting up a big fight against amd's Athlons. The p4 are still considered expensive, and still are being soled mainly with the rambus (bs chips) ram.
I am actually hoping that amd will push there Athlons to higher ghz speeds soon, so that we can see a true 1.7 ghz Athlon vs. p4 1.7 ghz. Or say at that time 2 ghz vs. 2 ghz battle. That might be able to wake up Intel. But we have to wait and see. What I really would like to happen is to see a real processor war. At this point, there is only Intel getting beaten down bit by bit in the 32-bit pc market. But I guess we will have to wait and see.
My 2 cents plus 2 more
I got sick of people pointing out the 'datedness' of cultural references, oh, about 1978. STFU, you turdjuggler.
Actually, it's not exactly "hard" stuff from an implementation point of view. Cycle times are short so you want a predict equation that you can do quickly and in one cycle. In fact, you can get pretty good results with a simple 4 state strongly not taken (00) - weakly not taken (01) - weakly taken (10) - strongly taken (11) saturating counter that updates when a branch is confirmed to be taken or not taken. If your BHT (branch history table) is sufficiently large, you can get decent results. Sprinkle in some voodoo magic by adding a GHR (global history register) which hashes the opcode address based on the state of the last n taken branches and you can get a couple of extra percentage points. I've seen upwards of 95%-97% prediction rates with such implementations but that's in a RISC environment which also provides fairly accurate branch hints in the opcode itself (much like the Itanium does). (The compiler knows what the code should do and what the semantics of a branch are: an "if", "for", "switch" construct, etc.)
Where things probably get weird for Intel is that their BHT probably suffers a bit of address aliasing/underutilization due to the fact that x86 opcodes are variable length. With RISC architectures (fixed length opcodes), you can chop off the last couple of address bits since the 0,1,2,3 cases don't matter == less address aliasing over a greater range of addresses.
Mispredict bypass buffers are another nicety that help back out of branch mispredicts because you don't have to go running back to the I$ and wait two cycles. In fact, while you're going down the codestream for the "predicted taken" path, you can also load up the "not predicted taken" path into a line buffer from an alternate cache such as a BTB (branch target buffer: if the data is available, a TLB entry exists, etc) and bypass the 2 cycle hit on the I$ on the mispredict. Two cycles are two cycles...
Engineers have a very big bag of tricks to work from..but they do have to know when to cut the apron strings and say "out with the old, in with the new." I think the key to major ramp-ups in speed for the x86 architecture is going to be when Intel proclaims "The Great Simplification" (a la "A Canticle for Leibowitz") and deprecates a whole slew of ancient modes (e.g., 286 type stuff) such that they must be emulated through an OS trap. By that time, DOS based OSs like W9x will be about as common as Win311 is now so it won't even matter. About the only people who I can see complaining then are VMWare, Netraverse, Plex86, and the WineHQ Team.
Well, the layout of the graphs (don't give me that 'graphic design considerations' crap!), the failure to EMPHASIZE that you were comparing newest Intel w/ old AMD processors, failure to use a board supporting 266...all these things, they don't look so good, mate.
If you weight performance results by the clock speeds of the processors, then you can tell whether there is any actual advantage conveyed by the Intel architecture. THEN you can look at price and determine value. When this is done, IMNSHO, the AMD is the hands-down better processor.
I know you kind of conceded this point in the review, briefly, on your way to saying "Oh Boy! Wait till we get the NEW Intel CPUs!!" Just thought you bent over backwards to minimize the P4s downside. (Of course, that's the hazard of doing h/w reviews, huh?)
And you didn't even mention, that, to use a P4 you have to give money to those sleazy Patent Pirates, RAMBUTT!! THAT's a reason not to go Intel, right there....
"To be fair, I was left completely unsupervised." ~Anon
No! Crack whore jokes live on in New Zealand, and secret-passage.com
Did anyone here read the Technical Overview! They must have really been excited about the P4's architecture. It seems like every other sentance ends in an exclamation point!
"This means that the higher levels don't have to experience a cache miss before moving to the data in the second array, while the 32-byte-line design would! This has the benefit of greatly decreasing average memory access latencies for contiguously used data!"
I have honestly never seen anyone more excited about CPU Caches.
"Evil company X is threatening to restrict our rights! Let's all get together to stop--OOOH! SHINEY!!!" -- AC
Let me make your reply a little more concise 1) gshare exists 2) icache access / branch predictions aren't necessary single cycle anymore
I must burn in hell, suffer and pay for my sins
But Gods the one who's losing, Satan always wins!
I think the article makes two very good points:
Note to David Pitlyuk and Paul Mazzucco: Big Blue outperforms the top 486 in every benchmark too.
The two most common things in the Universe are hydrogen and stupidity. -- Harlan Ellison