Ahhhh, I am sure it will be said again here, but payback is in order. This sort of marketing angle will only go so far though as Apple and AMD have found out. What really matters is real power [apple.com]. This will translate into more sales as Apple is now finding out with significant interest in the G5 Xserve from a large number of corporations and government agencies. So, if Intel can get around some of the performance bottlenecks and deal with the loss of backwards compatibility, they may be able to get back on track.
When Intel abandons this scheme, what precisely will a 4500+ processor actually mean? It's bad enough trying to quantify it now, but at least we have the actual P4 GHz to compare against.
Something will clearly need to be done - independant benchmark-wise - to prevent abuse. It's going to get bad folks.
The good news: I think we're going to see '5000+' processors before the end of the year now.
by Anonymous Coward writes:
on Saturday March 13, 2004 @07:36PM (#8555844)
How is that any worse than it already is? You already need benchmarks to see which processor is best for your application. It's not like naming processors after how many GHz they run at is any better.
The difference is that as of now, we at least have one platform (Intel) accurately stating clock speed. AMD generally keeps their performance ratings close to Intel's however they have stretched the meaning of their 'XXXX+' definitions where Intel simply could not.
If BOTH of them start these arbitrary rating systems, we won't even have THAT small bit of stability. Intel could easily release a '6000+' processor tomorrow with no regard to clock speed. AMD would have to follow suit, and on it goes.
AMD have already started an entirely new naming scheme anyway with Athlon64 FX-51. Presumably they're going to go FX-52, FX-53, etc.
And if you wanted AMD to use the MHz in their marketing, then I suspect it wouldn't be much better, for instance with the AthlonXP 2600+, there were two different clock speeds which ran at about the same real speed.
It's important that numbers be sane, but when a ~2gig AMD chip can run with Intel chips clocked at a much higher speed, something needs to be done to let the public know in a non-technical fashion.
I don't think anyone can blame AMD for the switch and I think perhaps a standard benchmark/rating system might be in order.
No, I don't blame AMD (except for the questionable ratings of a few of their later Athlon XP's), HOWEVER, without a stable GHz metric to build off of, things are bound to get messy.
Marketing of both companies are going to have a field day.
They would just game the benchmark. What you'd get were CPUs that were very good at benchmarks, and not so hot at other stuff.
At least with Mhz it was harder to fake it, but Intel managed to increase clock speed without actually getting much more performance, so they even managed to play that system.
I think the article got this wrong. If you read the Anandtech Report [anandtech.com], they believe it is going to be an Opteron-ish number scheme, not an AthlonXP-ish one.
Quote from the report:
News broke earlier today that Intel will most likely change its current "Megahertz" strategy in favor of a more subdued "Model Name" approach. This does not necessarily mean Intel will change its processors to a PR rating, like "3000+". Rather, the new model system sounds very familiar to AMD's Opteron approach, with three or fou
Well since all the GHz measurements from AMD are vs an equivilant performance Intel chip, and now that reference is gone, why not use the industry standard benchmark. Name chips based on the SpecIntBase score and be done with it!
Why does this incorrect info keep getting posted (and modded as "informative" at that)? AMD stated several times quite publicly that their rating initially was meant to compare against the "Thunderbird" Athlon chips. More recently they've simply said that it's relative performance between the AthlonXP line and that it can "outperform it's closest competitors". Here's a direct quote from AMD's AthlonXP FAQ [amd.com]
Q: What does the 3200+ model mean?
A: This is a model number. AMD identifies the AMD Athlon XP processor using model numbers, as opposed to megahertz. Model numbers are designed to communicate the relative application performance among the various AMD Athlon XP processors. As additional evidence that performance is not based on megahertz alone: the AMD Athlon XP processor 3200+ operates at a frequency of 2.2GHz yet can outperform an Intel Pentium(R) 4 processor operating at 3.0GHz with an 800 FSB and HyperThreading on a broad array of real-world applications for office productivity, digital media and 3-D gaming.
AMD's model numbers not rated against Intel's P4 chips? You might want to tell AMD that!
"Name chips based on the SpecIntBase score and be done with it!"
The problem is that AMD and Intel custom design their chips to perform better at different tasks/instructions. Then there is the problem of compilers. Was the SpecIntBase compiled with AMD and/or Intel specific instructions? Which versions? Is SSE2 faster on Intel than AMD? Was 3DNow substituted for a few SSE instructions in the benchmark? Did the newest version of Lightwave 3D take any of this into account? This type of thing can make a HUGE difference in performance.
I don't think there's a simple way through this at all other than common program benchmarking and even then there will be a lot of misleading (and often wrong) results.
The good news: I think we're going to see '5000+' processors before the end of the year now.
The bad news: They will run like 4 GHz models.
A 4GHz Itanium, Pentium M, Alpha, UltraSPARC, or any other of the lower clock speed processors would be much beyond a 5000+ Pentium rating. The article said that the Pentium M, which is a great processor, is having trouble in the marketplace because people are used to the Hz rating. This will become more of an issue with multiprocessor systems and multicore processors or even with technologies like hyperthreading.
This has been done for years with cars. There are horsepower measurements displayed on car ads all the time. Of course there are many other performance measures like 0-60 times, torque, braking, etc. But those are usually only reported in enthusiest magazines (read: car geek stuff, like we are computer geeks).
I think this is going to be welcome by average consumers, but us geeks are still going to read Tom's Hardware and other media that are full of benchmarks and other performance measures.
That sounds similar to how AMD names their CPUs, and frankly I never understood what they really meant in terms of one being better than another. How about giving the power of a CPU in gigaflops?
While no measure can be truely accurate, the number of floating point operations a CPU can do per second is a more accurate judge of cpu power than the clock speed.
I'm glad Intel is choosing to use a different naming convention, hopefuly it will be something more meaningful.
Gigaflops is only a tiny fraction more useful than GHz, if at all.
Gigaflop tests come in three basic varieties. First are ones that fit entirely into the L1 cache of a processor, making the memory subsystem totally irrelevant. This is no good since the memory subsystem plays an important role in performance. In this sort of test a 2.8GHz Celeron processor with 128K of L2 cache and a 400MT/s bus speed would get a score essentially identical to a 2.8GHz P4 with 512KB or 1MB of L2 cache and an 800MT/s bus speed. In 90% of real-world applications though even a much slower 2.0GHz P4 would beat the pants off a 2.8GHz Celeron (the current Celeron chips are absolutely abysmal perfomers).
The second type of gigaflops test has a slightly larger dataset, so performance is almost entirely determined by what level of cache it fits into. For example, if they used something like a 60K dataset, an AthlonXP or Athlon64 would blow the doors off any P4 because it would be running everything in L1 cache while the P4 would be running out of (the much slower) L2 cache. Clock for clock the AthlonXP chips could easily be twice as fast in such a test. Things would get even worse if your data set fit into the L2 cache of one chip but not another, ie if you had a 750K data set, a "Prescott" P4, with 1MB of L2 cache, could be HUGELY faster than a "Northwood" P4 with only 512KB of L2 cache, even though in reality their performance is fairly close (with the "Northwood" usually being slightly faster).
The third option would be to use a HUGE dataset, turning this entirely into memory bandwidth test. Fine for what it's testing, but hardly an accurate picture of overall performance.
There are good reasons why the rather smart guys over at Ace's Hardware make use of Linpack (basic Gigaflops test used by Top500.org) to show off the memory subsystem of platform. By varying the size of your dataset it does a good job of illustrated the effects of cache and memory. However it doesn't tell you much else about processor performance.
I think that gigaflops would be a slightly worse metric for processor performance than MHz because it's FAR easier to abuse that test. The best thing for consumers is if the model numbers are really NOT meaningful at all. For example, look at video cards, where our top-dogs today are the ATI Radeon 9800 and the nVidia GeForce 5900. Nobody looks at those and says "Ohh, 9800 is bigger than 5900, therefore the ATI MUST be better". Everyone KNOWS that the model numbers here are meaningless, so if they want to know which is faster they ask a friend (or at least the salesperson) or do some research on their own. That is what I would like to see for processors as well. AMD's already got this with their Athlon64 FX line and Opteron line of processors. Hopefully Intel will do the same.
I like this explination personally. Very technical but try and keep up
Two children are playing on a beach, filling up a plastic pail with sand. The first child uses a teaspoon to scoop sand into the pail. The second child uses a much larger toy shovel, moving a great deal more sand with each scoop and working more efficiently.
The same concept also applies to processor performance. A computer with a processor that does more work per cycle, like an AMD Athlon processor, can out perform the same computer with a less efficient processor
Just wait for the Mac users to come in and say that the Dual G5 is like a steamshovel when compared to the kids.
And as I Gentoo user, I'll just have to point out that my shovel was compiled with -fomit-instructions and -fomit-marketing, and is 10x faster than your shovel.
If you gave me a big shovel and gave 30 people spoons that equalled the size of my shovel, who's to say we wouldn't have the job done in the same amount of time? We'd just have lots of little spoonfuls instead of a few big shovel fulls.
Right and for sand the teaspoons might be more efficient because less sand slips off them but for dirt the shovel might be better.
That's the whole point, it's not how quickly the processor cycles or even how much the processor does in one instruction. Rather, it's how we
Payback? No, acknowledgement that the numeric marketing angle works and that they are getting beat out on price/performance by AMD.
My fear is that this could start an inflationary "speed rating" arms race where the baseline keeps getting changed to pump numbers higher and higher. The AMD system was all good and well when it was more-or-less anchored to Intel processor MHz ratings for comparable performing processors, but what happens when Intel releases the P-IV 4800 "It's twice as fast as the old 2.4 GHz model!". Then AMD comes out with the Athlon XP 6000+, then we have the P-IV 7500 "this is really much faster than AMD's new processor, we swear" model. And so on ad nauseum.
Believe it or not, there is this alliance called AIM. It used to be Apple, IBM and Motorola, but given Moto's problems, they have essentially dropped out for the embedded market. At any rate, the G5 was very much co-developed by Apple and IBM with some chip design and fab positions solely at Apple.
Apple is basically just an upscale systems integrator.
Without getting too much into the oft hashed out facts, just think about where the computer industry would be without Apple to do the R&D? I am not saying we owe everything to Apple Computer, but think about what you are saying before you type. Off the top of my head, here are a few things we owe to Apple: 1) Integrated motherboards consolidating most functions into a few chips with the Apple ][, 2) Plug and Play compatibility with NUBUS, 3) GUI with the Lisa, 4) First to use small form floppies with the Apple ][c, 5) First to implement CD-ROMs with Macintosh, 5) First to support on board sound and graphics with Macintsoh, 6) First to include built in networking with Macintosh, 7) First to develop the laser printer and postscript printing with the Laserwriter, 8) First to develop the PDA with the Newton, 9) First to develop the laptop form factor as we know it with the Powerbook, 10) First to leverage the GPU for routine interface with OS X, 11) First speech technology with the Apple ][, 12) First virtual programming environment with Hypercard, 13) Developed Firewire, 14) First company to ship a consumer digital camera with the Quicktake, 15) First cross platform standard for multi-media with Quicktime, 16) The first "multimedia" PC with the MacTV that integrated a television with stereo CD back in 1993 or so. We could go on and on here, but you get the point.
Apple's Xserve and G5-based machines are niche machines and they don't really offer compelling performance advantages
There is a reason that the number three supercomputer in the world right now is made up from off the shelf G5 hardware. It provides the performance for less money than the alternatives.
And OS X is severely handicapped in the market relative to Linux and Windows--OS X just isn't used very widely as a server operating system.
Well, that depends upon what you mean by handicapped. Marketshare? Sure. Useability? Not on your life. I've used Solaris, IRIX, Linux, Windows and others and nothing comes close to how easy, secure and convenient OS X is to administer for servers. Even the base desktop OS includes Apache that is as easy to use as dropping your html into a folder and pressing "Start" to function as a webpage and it can handle the traffic with the best of them. In fact, I am running a retinal anatomy site on an old G3 iMac that gets upwards of 45.000 hits/day from about 3000 unique users. The site is multimedia rich and yet, I never have to worry about it. When it was being hosted on W2k, I was constantly screwing around with it to keep things up and running smoothly and when it was on IRIX, it was stable, but IRIX was expensive and arcane as can be whenever changes were needed.
But the threat to Intel is AMD, not PPC.
Give it some time as the G5 really just came out. Between Apple running OS X and IBM running Linux shipping on systems now with the G5, there is going to be some significant market share being gained by those two companies.
just think about where the computer industry would be without Apple to do the R&D?
Let's look at some of your claims:
3) GUI with the Lisa,
Xerox PARC did the R&D for modern GUIs. The Lisa was Apple's first attempt to copy the Xerox PARC GUI work, and it failed. Then, Apple tried again with Macintosh, and by cutting a lot of corners made the system cheap enough to make it a success.
7) First to develop the laser printer and postscript printing with the Laserwriter,
The laser printer was developed at Xerox PARC. Postscript was developed at Adobe, based on a more complicated PDL developed at Xerox PARC. Apple just happened to create a successful product based on those technologies.
8) First to develop the PDA with the Newton,
The Psion predates the Apple Newton by nearly a decade, and I think it wasn't the first PDA either.
9) First to develop the laptop form factor as we know it with the Powerbook,
Not even close; you can find the history of the laptop [about.com] here. In fact, the idea goes back to Alan Kay's work on Dynapad--late 1960's or early 1970's.
11) First speech technology with the Apple ][,
The Apple II was irrelevant to speech recognition research and development.
14) First company to ship a consumer digital camera with the Quicktake,
You other examples either refer to system integration issues (e.g., supposed first use of a 3 1/2" floppy--developed by Sony), or are vague and meaningless from a technological point of view.
For a few years, Apple had an R&D department that actually published a little and was fairly high quality. However, I can't think of any fundamental breakthroughs that came out of that, and they disappeared again in the mid-1990's.
In addition to demonstrating your ignorance, I find your posting just offensive: I actually know some of the people who developed the technologies you talk about and I assure you that they didn't work at Apple when they did it. For their own financial gain, Apple has deliberately created the impression that they invented a lot of things that they didn't invent at all--and you fell for that dishonest marketing. Read up on the history of computing--you'll be surprised what you find.
Good news for the average computer idiot who wants to upgrade or buy a new machine. I think it's past time to undo the damage Intel's marketing has done with the Megahertz Myth [amd.com]. I'm weary of explaining it to people. It will be nice to have something more helpfully descriptive to a consumer than "cache" and "bus", or at least clarify that they don't refer to paper money and vehicles that carry children to school.:P
Doesn't FUD imply it's untrue? If you don't like AMD (I don't, they just had a convenient explanation to link to), it's a similar situation with Apple, though they have a different architecture entirely.
Doesn't FUD imply it's untrue?
No. FUD is fear, uncertainty, and doubt. It's what results when a fact is unknown, yet decisions have to be made based on that fact. If we knew that the FUD-source was false, it wouldn't produce any FUD. Unfortunately, we can't be so sure.
Yes, but now we'll run into trouble because Intel's Performance Rating will be artificially larger than AMD's - I can't imagine Intel giving any CPU a lower PR than its MHz figure!
It would be nice to have a descriptive measure of performance written in the name. What this new naming convention will lead to, however is statements along this lines of:
"You wasted all that money on an Athlon64 3400? I got a Pentium 5 Series 17Quadrillion Hyperfubar with a squigabyte of intellicache."
"Bah, the Apple G5 can't match a Celeron G7 - the G7 must be a newer series of the same chip."
Intel has NEVER stated that Mhz equals performance. Go look on their site. They like to quote SPEC, and their own performance tests, and all the rest of the BS that companies do. Never Mhz. The Mhz myth comes from two places:
1) Fanboys. I first remember it gaining real popularity among the Apple fanboys when Apple went PPC. They claimed that the PPC showed a positive second derivitave (growth of growth) in Mhz where Intel showed a negative second deravitive and how PPC could scale to huge speeds that CISC just couldn't handle. That of course, neve came to pass. Which lead us to:
2) The anti-Mhz myth. That Mhz don't mean anything. This is just FALSE. When you compare a single architecture (meaning one kind of one brand of processor) mhz give a VERY good idea of how performance will scale. If something gets X on a processor at 500mhz, you can with confidence say it will get nearly 2*X with the same kind of processor at 1000mhz. That doesn't mean it's the be-all, end-all benchmark, just a useful (and truthful) was of evaluating chip performance within a line.
PR numbers are just a bunch of crap. So far, I've never even seen any that are reliably based off of benchmarks. Even if they were, it wouldn't matter. Show me any benchmark, I'll show you how it's not relivant to things a lot of people do. Like take SPEC. It is a big industry standard benchmark. People doing scientific and engineering work place a lot of faith into it since it benchmarks what they do.
Well Intel LOVES SPEC, their processors when mated with their compiler do very well at it. Does that mean we should use it? Hell no. SPEC isn't applicable to everyone. It's got nothing to do with games, audio, video, bussiness, servers, etc. It's a science and engineering benchmark. What's more, it's a benchmark designed to come form source code, so to bench the compiler as well as the system. It's a good, open, standard benchmark, but it won't work as the single number to completely describe chip performance (nothing will).
PR numbers improve nothing, and just confuse and BSify the situation. At least Mhz are factual numbers and have some basis in reality. From what I've seen of PR numbers, they are mainly a dream of marketing and don't apply to the real world.
2) The anti-Mhz myth. That Mhz don't mean anything. This is just FALSE. When you compare a single architecture (meaning one kind of one brand of processor) mhz give a VERY good idea of how performance will scale. If something gets X on a processor at 500mhz, you can with confidence say it will get nearly 2*X with the same kind of processor at 1000mhz. That doesn't mean it's the be-all, end-all benchmark, just a useful (and truthful) was of evaluating chip performance within a line.
Except, of course, that this isn't true either. True, mhz means something, but it's not even a good indicator within a processor line.
A 1000mhz processor will only be twice as fast as a 500mhz processor if the ram and the peripherals are ALSO twice as fast. Otherwise, it depends entirely in the workload whether the processor is faster. If your computer is basically just loading data from disk, copying it from one place to another with a simple transform, and sending it to the network or something similar, the 1000mhz processor may not be faster at all with the same ram! In fact, it could even be slower, if to get the right multiplier for the CPU, the front side bus speed was actually reduced (that does happen quite often) and hence the ram runs slower!
On the other hand, if your computer simply runs a tiny program (a few k) that fits entirely in the L1 cache, and almost never talks to main ram or the peripherals, then it may in fact run twice as fast when you double the clock speed.
In reality, real programs are somewhere in between, so to figure out whether it's worth it to get a faster processor or eg. buy more ram instead, or faster ram, or a 15krpm SCSI disk, or whatnot, you have to figure out what your computer is going to be doing and estimate accordingly. Or even better, test the actual machine out to see how fast it is before you buy a lot of them.
Not system speed. Believe it or not there are plenty of CPU intensive applications that don't hit much of the rest of the system. Also, there are plenty of cases (like the case I'm in now) where the CPU is the limiting factor. My disks are plenty fast for what I do, almost nothing slams my memory bus, all my other system and IO busses aren't even close to peaked. Any time I slam my system it's either the graphics card or the CPU that is the limiting factor. For the work slamming the CPU, I will get basically 150% performance by increasing CPU speed to 150%.
Ya, it's not the be-all, end-all number. I noted that. The problem is that there is the thinking that somehow a BSified PR number will somehow be better. Errr, no. I'd prefer that all my components be rated in real, factual, terms. I can then use those to make SOME kind of meaningful comparison. I want to buy a 7200rpm harddrive, not a PR 12000+ harddrive. I want to buy 1024MB of RAM, not PR 3500+ of RAM.
Going to BS PR numbers improves NOTHING. You are still faced with the situation of picking which part you need to improve, only now, it's difficult to make any kind of sensible comparison.
If something gets X on a processor at 500mhz, you can with confidence say it will get nearly 2*X with the same kind of processor at 1000mhz.
This is true if your benchmark (or something) is able to effectively isolate the CPU. Otherwise, you have to start worrying about bus latency, page faults, and the speed of everything else in your computer.
There's also a myth that CPU performance equates to the performance of an entire computer. This one has folks going out and buying all-new computers when what they really needed to do was buy more RAM or uninstall RealPlayer, Gator, that weather program, etc.
This myth is definitely supported by Intel, which likes to run ads that imply that buying a Pentium MCCXVI processor will help you get better audio and video streams on that computer that's still dialing into AOL with a 28.8 modem.
I quote myself (emhpasas added) "That doesn't mean it's the be-all, end-all benchmark, just a useful (and truthful) was of evaluating CHIP performance within a line."
I KNOW that the chip isn't the only thing in a computer. There is a reason why I'm still running a 1.6ghz P4, I spend my money on other subsystems since for me, they are the ones that make the most difference. However when evaulating CHIP performance specifically when evaluating, again quoting myself "a single architecture (meaning one kind of one brand of processor)" Mhz is an effective comparison. A P4 Northwood at 2.4ghz on a 400mhz bus will be able to do calculations roughly 150% the speed of a P4 Northwood on a 400mhz bus at 1.6ghz.
Now if you compare different bus speeds (533mhz vs 400mhz) different architectures (Northwood vs Prescott) or ESPICALLY wholly different architectures (P4 vs Athlon) it breaks down. But SO DO PR NUMBERS! There is NO gaurentee, and in fact a high degree of probablility, that AMD and Intel will have DIFFERENT BS schemes that have nothing to do with each other and less to do with reality.
I am not saying that Mhz is the ideal benchmark. I am saying that it is turthful and facutal and useful in limited in-line comparisons. PR numbers are the dream of a marketing department and have shit to do with shit and are worthless, even in comparing like chips.
Not only was there never a "DX" pentium, but the Pentium was never clocked as low as 25mhz. It debuted at 60mhz.
Additionally, both 25mhz & 33mhz versions of the 486 ran at the same speed as the system bus. The DX2 and DX4 ran at 2x & 4x multiples of the system bus.
I suspect you are comparing performance between the DX version of the processor between the SX and the SL versions.
Additionally, both 25mhz & 33mhz versions of the 486 ran at the same speed as the system bus. The DX2 and DX4 ran at 2x & 4x multiples of the system bus.
The unintuitively named DX4 actually ran at 3x the system bus, not 4x.
The transition to PPC that the parent post is talking about has nothing to do with G5, or G-anything, and it happened about 10 years ago or so..... He's refering to Apple's switch from the Motorola 68K CPU's to the IBM/Motorola PowerPC chips which happened IIRC in the early 90's. At that point having more than one processor in a desktop or even small server machine was little more than a pipedream, and scalability of number of processors meant nothing to ~95% of the computing world.
Just out of curiosity, what would you have them do? Are you saying that any time Intel or AMD wants to show you a CPU, they should list clock frequency, L1, L2, and L3 cache sizes, each of their individual latencies, main memory latency, clock multiplier, average IPC, number of pipeline stages, instruction set extensions (SSE, Powernow, etc), architectual information, die process size, average and max heat dissipation figures, speculative execution capabilities, out-of-order operation specs, core stepping and revisions, a picture of the actual die, and about 10,000 other things that contribute to performance?
And just what the hell are you going to do with all that information, let alone the average consumer? I seriously doubt most of the engineers at Intel or AMD could even take all that information and have a good idea of what Spec numbers or other benchmarks would look like. At some point, you've got to figure out a way to simply things so that most people can at least have a rudimentary understanding of what it is they're buying. AMD attempts to do that with the model numbering scheme, which is designed to denote the relative performance of each CPU. Intel is now moving to some sort of similar system, now that clock ramping on the P4 is reaching its limits.
There is no measurement of absolute performance. There is no single number that gives you an honest picture of how things are. You can take 100 benchmarks of different applications, and you'll still have only a relative idea of performance, at best. Intel would be lying if they sold you a chip rated at 2.4GHz, which was only actually running at 1GHz. AMD doesn't mention GHz, and until you can produce a 3GHz Thunderbird core Athlon, their model system is perfectly legitimate.
Ok, what he wants is to know is two things. 1. That Microsoft Word will now open from cache in.1 second as apposed to 2 seconds. A 100% increase in speed!!! 2. That FPS game *.* will get an extra 5FPS in 640x480. Granted he will never play it at that level.:-)
Well, maybe what they should do is a model number that have no relationship to its performance. Just pick arbitrary cool numbers like "Intel P100A" with "P" for "Processor", and "100A" for the first processor in a "100-series", etc.
Same goes for AMD btw. I think it would be good if there was NO CLUE given in the processor mode name of their performance (other than that "this 200 series is much better than the former 100 series!"). That would force the customers to actually look which is better and not be
"yes. whats wrong with that? those are all very important pieces of info. i would fully expect all that in well written liturature about a processor."
It is listed, in whitepapers. We're talking about marketing to the masses here. Tell me, do you think you can walk into a coffee shop and talk to the gal behind the counter about speculative execution for more than 10 seconds without getting her confused and bored? There's a fraction of a small percentage of people in this world who are capable of understanding all the parts of processor design. By confusing average folk with technical data, you're lying to them just as much as you are by using performance ratings. I'll bet I could go into detail about the original Pentium's design, explain all the things that were done to up the performance in really simple terms, and get a bunch of people excited about buying it so long as I never tell them its name.
Think about that for a moment - if I can sell a Pentium 200MHz system to a room full of people who could buy a Pentium 4 for the same price simply by talking up the complicated design specifics, am I any more honest than Intel is with its MHz listings, or AMD with its performance ratings?
It probably is time for a standard, it will need a group to oversee it and make sure the CPU makers post fair speed ratings. Maybe we should let ICANN handle it since they're doing such a great job with domain names:)
Really, the technical community needs to sit down and figure out a universal cross-platform benchmarking method.
Well, there's SPEC [spec.org] and TPC [tpc.org]. Other than that, benchmarks are both overrated and the best metric we have for evaluating performance. Then you have cases when a CPU is optimized for a particular benchmark to inflate performance numbers (hence the term benchmarketing).
"Really, the technical community needs to sit down and figure out a universal cross-platform benchmarking method."
That'd be nice, but the real world doesn't work so well in this regard. The platforms are different enough that all have different strengths. Your 300fps in Quake3 doesn't tell me squat about how fast Lightwave will render. If a program's optimized for one app but not another.. well shoot, there's another problem that a benchmark really cannot provide much insight into.
I'm sick of benchmarks anymore. Computers have too many little things going on that affect the overall result. The solution? There needs to be a broadening of what your computer does. Maybe voice recognition is the next big bfd. Maybe it's a flashy new interface that requires a lot more graphical power. Maybe it's getting more people interested in 3D rendering. Heck, I dunno.
I do know that my 'underpowered' laptop I'm writing this message on is still going strong and is still quite useful to me. I can't think of anything off the top of my hand (save for a few games I suppose, but I'm more of a console gamer anyway) that this thing won't do in some form. Heck, I bought it because the LCD runs at 1600 by 1200.
Maybe the next big thing isn't how fast the processor is, but how many you have running. I wouldn't mind having a render farm here.
FIrst Intel adopts the x86-64 ISA in their new chips, and now they start using performance ratings. What next? Jerry Sanders to replace Craig Barrett as CEO? How times have changed.
The AMD numbering system has never been directly related to Intel's (officially) but is instead related to the performance of older Athlons... in effect saying "The XP 2700+ is roughly equal in speed to an original Athlon running at 2700 Mhz"
and please mod this person up. (S)He is correct in stating that the AMD model numbers are derived NOT from the Pentium 4, the Athlon classic, the Centrino, Celeron, PIII, Crusoe, 8088, or any other God-forsaken chip, but from the Thunderbird core Athlon CPUs. Those were the last Athlons to advertise the clock frequency, and thus were the obvious choice for a comparison chip for the next generation of processors. If I just bought a 1.4GHz Thunderbird Athlon (common chip for the time), I would expect that an AthlonXP 1500+ would perform better than it, and I would be correct. An AthlonXP 1500+ under the new rating system, were it to be compared to the Athlon classic core (far less efficient than Thunderbird) would probably run at about 1.1GHz. As it is, the AthlonXP Palomino core 1500+, being a relatively minor revision to Thunderbird, ran at 1.33GHz.
So mod this guy up. He's right, the post he's replying to is wrong.
The planned system, which would focus on the chips' overall performance and de-emphasize how fast its chips run,
One of the effects I foresee is that consumers (and corporate management) will latch onto Intel's new system and use it to make hasty decisions and brag -- except this time, they have a better chance of being right. In a sense, Intel will have already done the work for them.
I see no problem with a marketing machine that actually helps to dispose of the "Megahertz Myth" in favor of a more accurate measurement of a chip's performance.
That's nothing, the adc and sbb (add and subtract with carry) instructions take 8 cycles! That is 8 times what it was like on the Pentium 3. At least the add, sub, xor, not, and, or, neg instructions take only 0.5 cycles.
Intel has long coasted along on what Apple likes to call the "megahertz myth." The power of a processor is more than just its clockspeed, as Apple and AMD have struggled to point out for years. Intel ignored the debate because they were ahead in clockspeed, so it was a convenient metric that always showed them to seem ahead of the competition. This change in CPU naming might indicate a recognition that its rivals may overtake it in clockspeed. Perhaps they're planning strategic changes that could take them below Apple or AMD in clockspeed and want to jump on the "clockspeed ain't everything" bandwagon as soon as they can.
This change in CPU naming might indicate a recognition that its rivals may overtake it in clockspeed. Perhaps they're planning strategic changes that could take them below Apple or AMD in clockspeed and want to jump on the "clockspeed ain't everything" bandwagon as soon as they can.
I suspect, to be honest, that it has as much to do with Intel's recently announced 64 bit desktop chip foray. Presuming they do something similar to AMD and have more general purpose registers for 64 bit mode, they need a way
The problem is that you can't measure processor performance with one number. There's just no way to do so.
Before, AMD and Intel used to use clock rates. They didn't pretend to actually be summing up their chip's performance with the metric they slap on the box. It was even okay when just AMD had a performance number, because there was no sense of putting an industry-wide metric on a box. Now, one of two things will happen:
Possibility 1) AMD and Intel will decide upon a standard benchmark suite to determine "performance" and processors will be optimized around that benchmark instead of around real world software (i.e. consumer loses).
Possibility 2) AMD and Intel will come up with *different* measurements to determine their "equivalency number". AMD will focus on chip feature X and Intel on chip feature Y, each probably choosing the one that best supports their case. Both will accuse the other one of using an inaccurate and artificial metric. Each one focuses on improving their score in their chosen test. The performance profiles of the two chips diverges more. Since most software must be least-common-denominator, all developers except those few that choose to include custom-compiled or assembly bits and processor-specific support will make software that runs slower on average. (i.e. consumer loses).
I liked it much more when Intel and AMD's marketing departments stuck with slapping stupid stickers on boxes and making deals with OEMs -- neither one directly affected me.
I think VIA started it, but I'm pissed at AMD for continuing it, and now Intel for jumping on board. Mhz are a useful and TRUTHFUL stastic. It tells you how fast a given chip cycles at. This is a fact, not a bunch of marketing BS. Further, for within chip comparisons, it is a useful number. For example:
I have a P4 1.6ghz, I know that the max my board supports is a P4 2.4ghz. Supposing I want to upgrade, how much speed will I gain by maxing my processor? Answer: A bit less than 150% of my current performanc
Uninformed consumer goes to the local discount electronics store. Looks at a computer based on Intel's CPU, sees 2000 megalobangerz. Looks at the AMD based computer right next to it, sees 1800 megalobangerz for a hundred bucks less. Decides the Intel is "better", so its ok to cost more. Reality, the computers are pretty much the same.
AMD did this becuase their chips simply do more work per clock cycle, this was done at the expense of not being able to scale the clock nearly as high as Intel. A 2000+ AMD is *roughly equivillent* to a 2.0Ghz P4.. it wins some, it looses some.
The jump you talk of was at 2600+, when AMD went from a 2.0 Ghz at 266 mhz FSB (called a 2400+) to a 1.833 Ghz at 333 mhz FSB, called a 2600+ Barton. Performance #s goes up, clockspeed goes down.. but FSB goes up! Yes, it's annoying, but this was done as to give most consumers who do minimal research a "fairer" basis for comparison when shopping for computers.
MHz is an absolutely useless metric for comparing processors today when FSBs range from 200 mhz to 800mhz and cache from 128kb to 1MB and higher. Intel and AMD went different routes when designing their offerings, and as you say, it's very difficult to come up with a single number to describe their performance. The problem is that MHz is the number that has been 'historically' used, and it just so happens that AMD went the route that yielded a smaller MHz (and god bless them that they did); so they made the transition to a BS-marketing-numbers system.
I imagine their ads will start sounding like razor commercials. "Introducing the new and improved 'Mach 19'! Now in candy-apple red and midnight blue!"
With more than one company providing relative performance indices as "names" for their processors, and none really providing a basis for these relative ratings, the consumer will now be forced to rely on product review sites like Tom's Hardware or Anandtech to evaluate the real performance of processors.
That's a good thing in as much as the numbers will stop meaning anything to those with the technical know-how to get useful information from Tom or Anand.
But there are a lot of Stupid People out there using and buying computers every day, and they will be completely in the dark when it comes to evaluating their choices. For them, the deciding factor when choosing a processor in their premanufactured desktop machine will be only what a further descent into Marketing can tell them....Which is probably exactly what Intel wants.
My Pentium(TM) Family User's Manual, Volume 3: Architecture and Programming Manual shows, on the front cover, a hand holding a chip marked "intel pentium iCOMP(TM) Index=815 (m)(c)INTEL '92 '93
It is either a 90 or a 100MHz part, don't know which.
The practice of inventing a silly(TM) performance index that looks better on your chips than your competitor's, or can't be used without a license, is pretty old.
Guess the rumours of Intel's problems with 90nm, Prescott's severe ramping problems, issues that even 775 can't solve, and the incredible heat dissipation of the newer chips are all true. This seems to be yet more confirmation, even moreso than the release of 2.4GHz Prescott chips this week. Gee, boys, guess we should have listened to Bob Colwell when he was standing around screaming about the unsustainable clock ramping and heat dissipation curves.
When the architect of the P6 says something, you usually ought to listen. Perhaps next time you'll get off your high horses and follow the suggestions of the smart people. Now he's gone, you're fucked for '04, and you're in serious trouble on the desktop front if Tejas doesn't turn out to be a rabbit out of a hat.
I can almost guarantee what this new naming move is about: a pre-anouncement of a desktop version of the Centrino (i.e. Pentium-m) CPU. For those who haven't been following, the pentium-m (completely different chip from the p4-m) is based on the p3 core, but with SSE2, big-ol cache, and some advanced heat-management thingamajigs(TM). It runs clock-per-clock much faster than p4 (as p3s always have).. the 1.7ghz version (fastest currently available) runs comparably to a p4 2.4ghz (or faster, depending on who'
That's what I say when non-technical friends and family ask me questions about what kind of computer they should buy.
"It doesn't matter."
I realize it sounds trite but these days, it's true. They can buy pretty much any new computer they can find and it's perfectly capable of doing what they want to do because, in truth, what they want to do rarely requires a state of the art machine. To simplify things further is the fact that comptuers are getting cheaper and you are getting way more for your money. Buying a new computer isn't the financial hardship it once was.
My mother doesn't care what kind of CPU is in her computer or how fast it is. She just wants to send email to her grandkids and play bridge and she can do that quite happily on a computer she can pick up at Wal*Mart for a few hundred bucks. Power to the people, indeed.
Older intel CPUs used a performance metric named iCOMP which was stamped on many CPUs. A bit of googling suggests [geocities.com] this is still around. Perhaps this is another case of reinventing an old idea?
This seems to bear out the rumours that "the next big thing" from Intel on the desktop will be based on the Pentium M which is a chip which ably demonstrates that more Megahurtz isn't necessarily better.
I guess Intel is starting this change in numbering early so it doesn't debut a new chip and a new way of labelling the speed of the chip at the same time. Launching both at the same time might look suspicious to less informed buyers, especially if Intel goes from selling 4Ghz chips to 2.4Ghz chips with a PR of 4500+. By starting early hopefully people will be more accustomed to the new numbering scheme and less likely to think they are being conned. A friend recently told me he had bought a new 3Ghz Athlon XP, he was ready to take it back to the shop after I explained what the 3000 meant!
I wonder how compatible this will be with AMD's PR ratings? What would the equivalent to an Athlon 64 with a PR of 3400 be? I hope Intel doesn't invent a PR system that deliberately uses bigger PR numbers than AMDs. I can see confusion amongst consumers who will think an Athlon 64 4000+ is not a match for a "Pentium 5 6000" even if they are equivalent performers.
While Megahurtz has long been a poor way of determining the speed of a chip, I think having two different PR systems that aren't compatible could be worse.
A friend recently told me he had bought a new 3Ghz Athlon XP, he was ready to take it back to the shop after I explained what the 3000 meant!
I hope you also explained that he got the same, if not more, power as an Intel P4 3GHz, for a cheaper price. It would be silly to educate people about what AMD ratings are not, without explaining what they really are.
How about we as the technical computer consumers come up with our own designator? We could start by basing it on a known quantity, for example a 1GHz P3 with a 133MHz bus. Then we benchmark the different parts of that CPU. FPU intensive, Integer intensive, MMX intensive, SSE intensive, cache hit intensive, cache miss intensive, and a mix intensive. Then whatever score is produced is weighted and collectively called 1.00 Then from that point on all CPUs are to be referred to by their number based on their weighted scores. So perhaps a 2GHz Pentium 4 is only a 1.5 when compared to the P3. Or even better, I'd love to see the individual scores of the different sections. I'd like to make it really easy for people to get specialized processors that best suit their needs. In some cases, it is hard to determine what would be the best cpu for the application. You may need one that can fly through compiling software but you don't really give a crap about SSE, MMX or FPU.
When I saw Intel was doing this I immediately thought "that's the end of Moore's" law. Intel has been trying to win the clock rate race for years. But, consider there newest Pentium, Prescott. This chip now has a 31 stage pipeline and is built for high clock rates. Yet, it still is clocked at less than 3.2 Ghz -- the highest speed of the older Northwood. Why is this? Even the earliest Pentium 4s were able to greatly out-clock the pentium III's when they first came out. They weren't faster overall, but did have higher clock rates than the PIII. But now we have the 31 stage Prescott and the about same clock rate.
If Intel thought it could keep bumping the clock rate up, they wouldn't move to something like AMD's performance rating. Yet here we are.
"Even the earliest Pentium 4s were able to greatly out-clock the pentium III's when they first came out. "
Yeah, you can do that when you do a complete core overhaul. Going from Northwood to Prescott is a fairly large change, but nowhere near as big a change as going from the PIII to the P4.
"But now we have the 31 stage Prescott and the about same clock rate. If Intel thought it could keep bumping the clock rate up, they wouldn't move to something like AMD's performance rating. Yet here we are. Something has changed."
What has changed is that Intel is having problems with the 90nm process, Prescott produces massive amounts of heat, the LGA 775 socket isn't going to solve those problems enough to ramp Prescott beyond 4GHz, if even that high, and the changes being made with the introduction of IA32-64 (aka AMD64) will give processors a pretty decent bump in performance.
Intel knows now that clock frequency ramps have limits. Sure, Bob Colwell told them as much when the P4 was being designed, but now they're actually slamming into walls of fire (heat). Right this second, they're not in such a serious situation that changing to performance ratings is necessary, but they will be fairly soon. Thus, if they do it now, it looks like a new initiative to give Intel an advantage in the marketplace. If they wait until their backs are against the wall, it looks like Intel is struggling to keep up and has lost its edge in the marketplace.
You see now why this is being done? It's just management finally starting to get a little smarter.
That's all fine and dandy, except that Moore's law was a prediction of exponential increase in the number of transistors on a chip, not the clock rate.
Now that's a trend I think is broadly continuing. Multi core CPU's are a part of it. We may also see async processors coming out with zillions of transistors, but no central clock.
Given the current problems with patent madness, how long will it be before someone files something like 'Method to describe the relative performance of a microprocessor architecture using a multi-tiered numbering system independant of the architecture clock speed'?
For the sarcasm imparied, I'm semi-joking. Still, I'd not be surprised if something like that was tried. Patenting something silly like 'single click purchasing' soundes ridiculous too after all.
Around my house, any new purchase must score high on the WifeMark, which is a complex combined index of software and hardware performance. The benchmark is simply my wife's reaction to me maxing out the credit card again on a computer. The levels are:
"Feels about as fast as what I have now. And last time she almost killed me for buying a new box."
"Nice, seems faster, but the wife will kill me if I spend this kind of money for nothing special."
"Damn that's fast. I want. She's just going to have to deal with it."
I've been using that benchmark for years. I don't even look at the official numbers. Once it gets to the point where the kit I run now is clearly sh*t for anything normal, I upgrade. Just come home one day with a new box and figure she'll come around.
Got a Mac G4/466 right now, specifically to run OSX. She likes OSX. Before that a used 7600/200 (G2ish) because web browsing got slow and she likes web browsing. Before that a Quadra 630 (486/33ish) because it was best for desktop publishing and we were big into that at the time. Before that, I owned a SE/30 (386/16ish) but that was before we were married. For sure, I more than double performance each time, noticing when something is finally "damn fast" for what is currently important and figuring it scores high on the WifeMark.
Happy with the G4 running Panther, it does email and web browsing and web development work Real Well (as does the 7600 to be honest, but no OSX for that one). I'll upgrade the G4/466 chip someday, maybe when I can get a G4/2000 for cheap on EBay. But otherwise I might run this box for a long time as I can't see anything coming along that scores highly on the WifeMark.
BTW, I still have all the machines listed above. Old Macs never die, they just become web servers.
i'll agree with everyone here about mhz not really meaning a whole lot by itself..
whenever i had to consult people about their pc purchases, i found the best way that they understood was basically the 3 parts of the cpu.. mhz, bus speed, and cache memory..
your cpu is a vehicle.. the mhz is the speed the vehicle can carry stuff from one place to another (this is what you are buying this ehicle to do - moving stuff) the bus speed is how fast you can load your stuff onto your vehicle.. and the cache memory is the amount of stuff the vehicle can carry...
then i go to explain how whats the point in having vehicle A that can go 1.5 times faster than vehicle B, but vehicle B can carry twice as much stuff each trip.. in the end Vehicle B is the one that gets more done.. until you get into things like it doesnt matter how fast vehicle A can go, if vehicle B can be loaded and on its way and back in the same time that A is still being loaded (bus speed)
its probly not the most refined explaination, but its the way i've talked many people into getting athelons instead of celerons, and in the end getting a better computer (dunno about the states but up here i can get an XP2200 for about the same price as a celeron 2ghz -give or take $5- and we're talking HUGE difference in performance)
. . . don't trust benchmarks. This naming scheme is just going to create yet another benchmark which will probably be biased by those marketing it. Again, stick to Tom's Hardware and don't even look at what they call it.
From what I understood, AMD got the numbers by comparing itself to the latest Pentimum chip running at that frequency
You understand wrong. AMD Performance ratings are as compared to a Thunderbird core Athlon. In other words, a "PR 3200+" chip is eqivilent to a Thunderbird running at 3.2Ghz, and not a 3.2Ghz Pentium 4.
Stellar rays prove fibbing never pays. Embezzlement is another matter.
Payback (Score:5, Insightful)
Re:Payback (Score:5, Funny)
In the future, your computer will:
1) Be a mammal.
2) Fight ALL the time.
3) Flip out and kill people.
Re:Payback (Score:5, Funny)
And indeed, the upcoming bullshit/branding/naming meta-wars are cool; and by cool I mean totally sweet.
Re:Payback (Score:5, Informative)
Re:Payback (Score:4, Funny)
Uh, or maybe not
Re:Payback (Score:5, Funny)
I think what you mean is that in the future your computer will be designed be an Electrical Engineer [rpi.edu].
EEs can calculate anything they want! EEs calculate ALL the time and don't even think twice about it.
Problem.. (Score:5, Interesting)
Something will clearly need to be done - independant benchmark-wise - to prevent abuse. It's going to get bad folks.
The good news: I think we're going to see '5000+' processors before the end of the year now.
The bad news: They will run like 4 GHz models.
Re:Problem.. (Score:5, Insightful)
Re:Problem.. (Score:5, Insightful)
If BOTH of them start these arbitrary rating systems, we won't even have THAT small bit of stability. Intel could easily release a '6000+' processor tomorrow with no regard to clock speed. AMD would have to follow suit, and on it goes.
Re:Problem.. (Score:3, Informative)
AMD have already started an entirely new naming scheme anyway with Athlon64 FX-51. Presumably they're going to go FX-52, FX-53, etc.
And if you wanted AMD to use the MHz in their marketing, then I suspect it wouldn't be much better, for instance with the AthlonXP 2600+, there were two different clock speeds which ran at about the same real speed.
Re:Problem.. (Score:4, Insightful)
Re:Problem.. (Score:5, Insightful)
A 2g Celeron performs as fast a a 2g P4, right?
I think this train left the station a long time ago.
Re:Problem.. (Score:5, Insightful)
I don't think anyone can blame AMD for the switch and I think perhaps a standard benchmark/rating system might be in order.
Probably not realistic, but it would be nice.
Cheers
Re:Problem.. (Score:5, Insightful)
Marketing of both companies are going to have a field day.
Re:Problem.. (Score:4, Insightful)
At least with Mhz it was harder to fake it, but Intel managed to increase clock speed without actually getting much more performance, so they even managed to play that system.
Re:Problem.. (Score:3, Informative)
Quote from the report:
News broke earlier today that Intel will most likely change its current "Megahertz" strategy in favor of a more subdued "Model Name" approach. This does not necessarily mean Intel will change its processors to a PR rating, like "3000+". Rather, the new model system sounds very familiar to AMD's Opteron approach, with three or fou
Re:Problem.. (Score:3, Interesting)
Re:Problem.. (Score:3, Informative)
Re:Problem.. (Score:5, Informative)
http://en.wikipedia.org/wiki/PR_rating
Re:Problem.. (Score:5, Informative)
Why does this incorrect info keep getting posted (and modded as "informative" at that)? AMD stated several times quite publicly that their rating initially was meant to compare against the "Thunderbird" Athlon chips. More recently they've simply said that it's relative performance between the AthlonXP line and that it can "outperform it's closest competitors". Here's a direct quote from AMD's AthlonXP FAQ [amd.com]
Q: What does the 3200+ model mean?
A: This is a model number. AMD identifies the AMD Athlon XP processor using model numbers, as opposed to megahertz. Model numbers are designed to communicate the relative application performance among the various AMD Athlon XP processors. As additional evidence that performance is not based on megahertz alone: the AMD Athlon XP processor 3200+ operates at a frequency of 2.2GHz yet can outperform an Intel Pentium(R) 4 processor operating at 3.0GHz with an 800 FSB and HyperThreading on a broad array of real-world applications for office productivity, digital media and 3-D gaming.
AMD's model numbers not rated against Intel's P4 chips? You might want to tell AMD that!
Re:Problem.. (Score:5, Insightful)
The problem is that AMD and Intel custom design their chips to perform better at different tasks/instructions. Then there is the problem of compilers. Was the SpecIntBase compiled with AMD and/or Intel specific instructions? Which versions? Is SSE2 faster on Intel than AMD? Was 3DNow substituted for a few SSE instructions in the benchmark? Did the newest version of Lightwave 3D take any of this into account? This type of thing can make a HUGE difference in performance.
I don't think there's a simple way through this at all other than common program benchmarking and even then there will be a lot of misleading (and often wrong) results.
Re:Problem.. (Score:5, Insightful)
The bad news: They will run like 4 GHz models.
A 4GHz Itanium, Pentium M, Alpha, UltraSPARC, or any other of the lower clock speed processors would be much beyond a 5000+ Pentium rating. The article said that the Pentium M, which is a great processor, is having trouble in the marketplace because people are used to the Hz rating. This will become more of an issue with multiprocessor systems and multicore processors or even with technologies like hyperthreading.
This has been done for years with cars. There are horsepower measurements displayed on car ads all the time. Of course there are many other performance measures like 0-60 times, torque, braking, etc. But those are usually only reported in enthusiest magazines (read: car geek stuff, like we are computer geeks).
I think this is going to be welcome by average consumers, but us geeks are still going to read Tom's Hardware and other media that are full of benchmarks and other performance measures.
Re:Problem.. (Score:5, Funny)
Re:Problem.. (Score:5, Funny)
Of course! Linux distributions have been doing this for years. That's why my "Linux 10.0" can mop the floor with your paltry Linux 2.6.
Cheers,
IT
Re:Problem.. (Score:4, Funny)
Flops (Score:5, Interesting)
While no measure can be truely accurate, the number of floating point operations a CPU can do per second is a more accurate judge of cpu power than the clock speed.
I'm glad Intel is choosing to use a different naming convention, hopefuly it will be something more meaningful.
Re:Flops (Score:4, Informative)
Gigaflop tests come in three basic varieties. First are ones that fit entirely into the L1 cache of a processor, making the memory subsystem totally irrelevant. This is no good since the memory subsystem plays an important role in performance. In this sort of test a 2.8GHz Celeron processor with 128K of L2 cache and a 400MT/s bus speed would get a score essentially identical to a 2.8GHz P4 with 512KB or 1MB of L2 cache and an 800MT/s bus speed. In 90% of real-world applications though even a much slower 2.0GHz P4 would beat the pants off a 2.8GHz Celeron (the current Celeron chips are absolutely abysmal perfomers).
The second type of gigaflops test has a slightly larger dataset, so performance is almost entirely determined by what level of cache it fits into. For example, if they used something like a 60K dataset, an AthlonXP or Athlon64 would blow the doors off any P4 because it would be running everything in L1 cache while the P4 would be running out of (the much slower) L2 cache. Clock for clock the AthlonXP chips could easily be twice as fast in such a test. Things would get even worse if your data set fit into the L2 cache of one chip but not another, ie if you had a 750K data set, a "Prescott" P4, with 1MB of L2 cache, could be HUGELY faster than a "Northwood" P4 with only 512KB of L2 cache, even though in reality their performance is fairly close (with the "Northwood" usually being slightly faster).
The third option would be to use a HUGE dataset, turning this entirely into memory bandwidth test. Fine for what it's testing, but hardly an accurate picture of overall performance.
There are good reasons why the rather smart guys over at Ace's Hardware make use of Linpack (basic Gigaflops test used by Top500.org) to show off the memory subsystem of platform. By varying the size of your dataset it does a good job of illustrated the effects of cache and memory. However it doesn't tell you much else about processor performance.
I think that gigaflops would be a slightly worse metric for processor performance than MHz because it's FAR easier to abuse that test. The best thing for consumers is if the model numbers are really NOT meaningful at all. For example, look at video cards, where our top-dogs today are the ATI Radeon 9800 and the nVidia GeForce 5900. Nobody looks at those and says "Ohh, 9800 is bigger than 5900, therefore the ATI MUST be better". Everyone KNOWS that the model numbers here are meaningless, so if they want to know which is faster they ask a friend (or at least the salesperson) or do some research on their own. That is what I would like to see for processors as well. AMD's already got this with their Athlon64 FX line and Opteron line of processors. Hopefully Intel will do the same.
Re:Payback (Score:5, Interesting)
Two children are playing on a beach, filling up a plastic pail with sand. The first child uses a teaspoon to scoop sand into the pail. The second child uses a much larger toy shovel, moving a great deal more sand with each scoop and working more efficiently.
The same concept also applies to processor performance. A computer with a processor that does more work per cycle, like an AMD Athlon processor, can out perform the same computer with a less efficient processor
Re:Payback (Score:4, Funny)
And as I Gentoo user, I'll just have to point out that my shovel was compiled with -fomit-instructions and -fomit-marketing, and is 10x faster than your shovel.
[/joke]
Re:Payback (Score:3, Insightful)
Right and for sand the teaspoons might be more efficient because less sand slips off them but for dirt the shovel might be better.
That's the whole point, it's not how quickly the processor cycles or even how much the processor does in one instruction. Rather, it's how we
Re:Payback (Score:5, Insightful)
My fear is that this could start an inflationary "speed rating" arms race where the baseline keeps getting changed to pump numbers higher and higher. The AMD system was all good and well when it was more-or-less anchored to Intel processor MHz ratings for comparable performing processors, but what happens when Intel releases the P-IV 4800 "It's twice as fast as the old 2.4 GHz model!". Then AMD comes out with the Athlon XP 6000+, then we have the P-IV 7500 "this is really much faster than AMD's new processor, we swear" model. And so on ad nauseum.
Re:Payback (Score:5, Funny)
Yeah, and Intel consumes plenty of that.
Re:Payback (Score:4, Interesting)
Believe it or not, there is this alliance called AIM. It used to be Apple, IBM and Motorola, but given Moto's problems, they have essentially dropped out for the embedded market. At any rate, the G5 was very much co-developed by Apple and IBM with some chip design and fab positions solely at Apple.
Apple is basically just an upscale systems integrator.
Without getting too much into the oft hashed out facts, just think about where the computer industry would be without Apple to do the R&D? I am not saying we owe everything to Apple Computer, but think about what you are saying before you type. Off the top of my head, here are a few things we owe to Apple: 1) Integrated motherboards consolidating most functions into a few chips with the Apple ][, 2) Plug and Play compatibility with NUBUS, 3) GUI with the Lisa, 4) First to use small form floppies with the Apple ][c, 5) First to implement CD-ROMs with Macintosh, 5) First to support on board sound and graphics with Macintsoh, 6) First to include built in networking with Macintosh, 7) First to develop the laser printer and postscript printing with the Laserwriter, 8) First to develop the PDA with the Newton, 9) First to develop the laptop form factor as we know it with the Powerbook, 10) First to leverage the GPU for routine interface with OS X, 11) First speech technology with the Apple ][, 12) First virtual programming environment with Hypercard, 13) Developed Firewire, 14) First company to ship a consumer digital camera with the Quicktake, 15) First cross platform standard for multi-media with Quicktime, 16) The first "multimedia" PC with the MacTV that integrated a television with stereo CD back in 1993 or so. We could go on and on here, but you get the point.
Apple's Xserve and G5-based machines are niche machines and they don't really offer compelling performance advantages
There is a reason that the number three supercomputer in the world right now is made up from off the shelf G5 hardware. It provides the performance for less money than the alternatives.
And OS X is severely handicapped in the market relative to Linux and Windows--OS X just isn't used very widely as a server operating system.
Well, that depends upon what you mean by handicapped. Marketshare? Sure. Useability? Not on your life. I've used Solaris, IRIX, Linux, Windows and others and nothing comes close to how easy, secure and convenient OS X is to administer for servers. Even the base desktop OS includes Apache that is as easy to use as dropping your html into a folder and pressing "Start" to function as a webpage and it can handle the traffic with the best of them. In fact, I am running a retinal anatomy site on an old G3 iMac that gets upwards of 45.000 hits/day from about 3000 unique users. The site is multimedia rich and yet, I never have to worry about it. When it was being hosted on W2k, I was constantly screwing around with it to keep things up and running smoothly and when it was on IRIX, it was stable, but IRIX was expensive and arcane as can be whenever changes were needed.
But the threat to Intel is AMD, not PPC.
Give it some time as the G5 really just came out. Between Apple running OS X and IBM running Linux shipping on systems now with the G5, there is going to be some significant market share being gained by those two companies.
you are an Apple marketing victim (Score:4, Insightful)
Let's look at some of your claims:
You other examples either refer to system integration issues (e.g., supposed first use of a 3 1/2" floppy--developed by Sony), or are vague and meaningless from a technological point of view.
For a few years, Apple had an R&D department that actually published a little and was fairly high quality. However, I can't think of any fundamental breakthroughs that came out of that, and they disappeared again in the mid-1990's.
In addition to demonstrating your ignorance, I find your posting just offensive: I actually know some of the people who developed the technologies you talk about and I assure you that they didn't work at Apple when they did it. For their own financial gain, Apple has deliberately created the impression that they invented a lot of things that they didn't invent at all--and you fell for that dishonest marketing. Read up on the history of computing--you'll be surprised what you find.
The Megahertz Myth (Score:5, Interesting)
Re:The Megahertz Myth (Score:5, Insightful)
Re:The Megahertz Myth (Score:5, Informative)
Re:The Megahertz Myth (Score:5, Informative)
Re:The Megahertz Myth (Score:5, Insightful)
Re:The Megahertz Myth (Score:5, Funny)
"You wasted all that money on an Athlon64 3400? I got a Pentium 5 Series 17Quadrillion Hyperfubar with a squigabyte of intellicache."
"Bah, the Apple G5 can't match a Celeron G7 - the G7 must be a newer series of the same chip."
Ok, now this just pissess me off (Score:5, Informative)
1) Fanboys. I first remember it gaining real popularity among the Apple fanboys when Apple went PPC. They claimed that the PPC showed a positive second derivitave (growth of growth) in Mhz where Intel showed a negative second deravitive and how PPC could scale to huge speeds that CISC just couldn't handle. That of course, neve came to pass. Which lead us to:
2) The anti-Mhz myth. That Mhz don't mean anything. This is just FALSE. When you compare a single architecture (meaning one kind of one brand of processor) mhz give a VERY good idea of how performance will scale. If something gets X on a processor at 500mhz, you can with confidence say it will get nearly 2*X with the same kind of processor at 1000mhz. That doesn't mean it's the be-all, end-all benchmark, just a useful (and truthful) was of evaluating chip performance within a line.
PR numbers are just a bunch of crap. So far, I've never even seen any that are reliably based off of benchmarks. Even if they were, it wouldn't matter. Show me any benchmark, I'll show you how it's not relivant to things a lot of people do. Like take SPEC. It is a big industry standard benchmark. People doing scientific and engineering work place a lot of faith into it since it benchmarks what they do.
Well Intel LOVES SPEC, their processors when mated with their compiler do very well at it. Does that mean we should use it? Hell no. SPEC isn't applicable to everyone. It's got nothing to do with games, audio, video, bussiness, servers, etc. It's a science and engineering benchmark. What's more, it's a benchmark designed to come form source code, so to bench the compiler as well as the system. It's a good, open, standard benchmark, but it won't work as the single number to completely describe chip performance (nothing will).
PR numbers improve nothing, and just confuse and BSify the situation. At least Mhz are factual numbers and have some basis in reality. From what I've seen of PR numbers, they are mainly a dream of marketing and don't apply to the real world.
Re:Ok, now this just pissess me off (Score:5, Insightful)
Except, of course, that this isn't true either. True, mhz means something, but it's not even a good indicator within a processor line.
A 1000mhz processor will only be twice as fast as a 500mhz processor if the ram and the peripherals are ALSO twice as fast. Otherwise, it depends entirely in the workload whether the processor is faster. If your computer is basically just loading data from disk, copying it from one place to another with a simple transform, and sending it to the network or something similar, the 1000mhz processor may not be faster at all with the same ram! In fact, it could even be slower, if to get the right multiplier for the CPU, the front side bus speed was actually reduced (that does happen quite often) and hence the ram runs slower!
On the other hand, if your computer simply runs a tiny program (a few k) that fits entirely in the L1 cache, and almost never talks to main ram or the peripherals, then it may in fact run twice as fast when you double the clock speed.
In reality, real programs are somewhere in between, so to figure out whether it's worth it to get a faster processor or eg. buy more ram instead, or faster ram, or a 15krpm SCSI disk, or whatnot, you have to figure out what your computer is going to be doing and estimate accordingly. Or even better, test the actual machine out to see how fast it is before you buy a lot of them.
We are talking about CPU speed (Score:5, Insightful)
Ya, it's not the be-all, end-all number. I noted that. The problem is that there is the thinking that somehow a BSified PR number will somehow be better. Errr, no. I'd prefer that all my components be rated in real, factual, terms. I can then use those to make SOME kind of meaningful comparison. I want to buy a 7200rpm harddrive, not a PR 12000+ harddrive. I want to buy 1024MB of RAM, not PR 3500+ of RAM.
Going to BS PR numbers improves NOTHING. You are still faced with the situation of picking which part you need to improve, only now, it's difficult to make any kind of sensible comparison.
Re:Not entirely true (Score:5, Insightful)
This is true if your benchmark (or something) is able to effectively isolate the CPU. Otherwise, you have to start worrying about bus latency, page faults, and the speed of everything else in your computer.
There's also a myth that CPU performance equates to the performance of an entire computer. This one has folks going out and buying all-new computers when what they really needed to do was buy more RAM or uninstall RealPlayer, Gator, that weather program, etc.
This myth is definitely supported by Intel, which likes to run ads that imply that buying a Pentium MCCXVI processor will help you get better audio and video streams on that computer that's still dialing into AOL with a 28.8 modem.
Is reading comprehension a skill lost on ./? (Score:5, Interesting)
I KNOW that the chip isn't the only thing in a computer. There is a reason why I'm still running a 1.6ghz P4, I spend my money on other subsystems since for me, they are the ones that make the most difference. However when evaulating CHIP performance specifically when evaluating, again quoting myself "a single architecture (meaning one kind of one brand of processor)" Mhz is an effective comparison. A P4 Northwood at 2.4ghz on a 400mhz bus will be able to do calculations roughly 150% the speed of a P4 Northwood on a 400mhz bus at 1.6ghz.
Now if you compare different bus speeds (533mhz vs 400mhz) different architectures (Northwood vs Prescott) or ESPICALLY wholly different architectures (P4 vs Athlon) it breaks down. But SO DO PR NUMBERS! There is NO gaurentee, and in fact a high degree of probablility, that AMD and Intel will have DIFFERENT BS schemes that have nothing to do with each other and less to do with reality.
I am not saying that Mhz is the ideal benchmark. I am saying that it is turthful and facutal and useful in limited in-line comparisons. PR numbers are the dream of a marketing department and have shit to do with shit and are worthless, even in comparing like chips.
Re:Ok, now this just pissess me off (Score:3, Informative)
Not only was there never a "DX" pentium, but the Pentium was never clocked as low as 25mhz. It debuted at 60mhz.
Additionally, both 25mhz & 33mhz versions of the 486 ran at the same speed as the system bus. The DX2 and DX4 ran at 2x & 4x multiples of the system bus.
I suspect you are comparing performance between the DX version of the processor between the SX and the SL versions.
Re:Ok, now this just pissess me off (Score:3, Informative)
The unintuitively named DX4 actually ran at 3x the system bus, not 4x.
/nitpick
Re:Scalability (Score:3, Insightful)
That's great. (Score:4, Insightful)
Well... (Score:5, Insightful)
And just what the hell are you going to do with all that information, let alone the average consumer? I seriously doubt most of the engineers at Intel or AMD could even take all that information and have a good idea of what Spec numbers or other benchmarks would look like. At some point, you've got to figure out a way to simply things so that most people can at least have a rudimentary understanding of what it is they're buying. AMD attempts to do that with the model numbering scheme, which is designed to denote the relative performance of each CPU. Intel is now moving to some sort of similar system, now that clock ramping on the P4 is reaching its limits.
There is no measurement of absolute performance. There is no single number that gives you an honest picture of how things are. You can take 100 benchmarks of different applications, and you'll still have only a relative idea of performance, at best. Intel would be lying if they sold you a chip rated at 2.4GHz, which was only actually running at 1GHz. AMD doesn't mention GHz, and until you can produce a 3GHz Thunderbird core Athlon, their model system is perfectly legitimate.
Re:Well... (Score:3, Funny)
1. That Microsoft Word will now open from cache in
2. That FPS game *.* will get an extra 5FPS in 640x480. Granted he will never play it at that level.
Re:Well... (Score:3, Funny)
Same goes for AMD btw. I think it would be good if there was NO CLUE given in the processor mode name of their performance (other than that "this 200 series is much better than the former 100 series!"). That would force the customers to actually look which is better and not be
Re:Well... (Score:4, Insightful)
It is listed, in whitepapers. We're talking about marketing to the masses here. Tell me, do you think you can walk into a coffee shop and talk to the gal behind the counter about speculative execution for more than 10 seconds without getting her confused and bored? There's a fraction of a small percentage of people in this world who are capable of understanding all the parts of processor design. By confusing average folk with technical data, you're lying to them just as much as you are by using performance ratings. I'll bet I could go into detail about the original Pentium's design, explain all the things that were done to up the performance in really simple terms, and get a bunch of people excited about buying it so long as I never tell them its name.
Think about that for a moment - if I can sell a Pentium 200MHz system to a room full of people who could buy a Pentium 4 for the same price simply by talking up the complicated design specifics, am I any more honest than Intel is with its MHz listings, or AMD with its performance ratings?
It might just be time for.... (Score:5, Insightful)
Really, the technical community needs to sit down and figure out a universal cross-platform benchmarking method.
Re:It might just be time for.... (Score:5, Funny)
Re:It might just be time for.... (Score:5, Funny)
Re:It might just be time for.... (Score:5, Insightful)
Great, then we'd get what we have on the graphics card market; two giants spending significant amounts of time to make 3DMark run faster.
There are complexities and tradeoffs.... ah, forget it.
Re:It might just be time for.... (Score:5, Informative)
Really, the technical community needs to sit down and figure out a universal cross-platform benchmarking method.
Well, there's SPEC [spec.org] and TPC [tpc.org]. Other than that, benchmarks are both overrated and the best metric we have for evaluating performance. Then you have cases when a CPU is optimized for a particular benchmark to inflate performance numbers (hence the term benchmarketing).
Re:It might just be time for.... (Score:5, Insightful)
That'd be nice, but the real world doesn't work so well in this regard. The platforms are different enough that all have different strengths. Your 300fps in Quake3 doesn't tell me squat about how fast Lightwave will render. If a program's optimized for one app but not another.. well shoot, there's another problem that a benchmark really cannot provide much insight into.
I'm sick of benchmarks anymore. Computers have too many little things going on that affect the overall result. The solution? There needs to be a broadening of what your computer does. Maybe voice recognition is the next big bfd. Maybe it's a flashy new interface that requires a lot more graphical power. Maybe it's getting more people interested in 3D rendering. Heck, I dunno.
I do know that my 'underpowered' laptop I'm writing this message on is still going strong and is still quite useful to me. I can't think of anything off the top of my hand (save for a few games I suppose, but I'm more of a console gamer anyway) that this thing won't do in some form. Heck, I bought it because the LCD runs at 1600 by 1200.
Maybe the next big thing isn't how fast the processor is, but how many you have running. I wouldn't mind having a render farm here.
Follow the leader (Score:3, Interesting)
So how will AMD name their CPUs now? (Score:3, Interesting)
Presenting the AMD XP 5500+, which runs at 4 gHz, but is equivalent to a Pentium V 5.5EE, which is equivalent to a 4.0 gHz!
Re:So how will AMD name their CPUs now? (Score:5, Informative)
Re:So how will AMD name their CPUs now? (Score:3, Informative)
Mods, kindly put down the crackpipe for a second.. (Score:4, Informative)
So mod this guy up. He's right, the post he's replying to is wrong.
Have a nice day.
Re:So how will AMD name their CPUs now? (Score:5, Informative)
mirror [telia.com]
from AMD's athlonXP site [amd.com] (doesnt' seem to be working right now)
web archive of AMD's site [archive.org]
introducing the new.... (Score:3, Funny)
It's Bitchin Fast! (Score:5, Funny)
Sounds fine to me. (Score:5, Insightful)
One of the effects I foresee is that consumers (and corporate management) will latch onto Intel's new system and use it to make hasty decisions and brag -- except this time, they have a better chance of being right. In a sense, Intel will have already done the work for them.
I see no problem with a marketing machine that actually helps to dispose of the "Megahertz Myth" in favor of a more accurate measurement of a chip's performance.
Finally! (Score:5, Funny)
If not, they're a bunch of hypocrites.
Re:Finally! (Score:4, Informative)
Perecursor to a change in design strategy? (Score:5, Interesting)
Re:Perecursor to a change in design strategy? (Score:3, Insightful)
I suspect, to be honest, that it has as much to do with Intel's recently announced 64 bit desktop chip foray. Presuming they do something similar to AMD and have more general purpose registers for 64 bit mode, they need a way
You can't "measure performance" with one number (Score:5, Interesting)
Before, AMD and Intel used to use clock rates. They didn't pretend to actually be summing up their chip's performance with the metric they slap on the box. It was even okay when just AMD had a performance number, because there was no sense of putting an industry-wide metric on a box. Now, one of two things will happen:
Possibility 1) AMD and Intel will decide upon a standard benchmark suite to determine "performance" and processors will be optimized around that benchmark instead of around real world software (i.e. consumer loses).
Possibility 2) AMD and Intel will come up with *different* measurements to determine their "equivalency number". AMD will focus on chip feature X and Intel on chip feature Y, each probably choosing the one that best supports their case. Both will accuse the other one of using an inaccurate and artificial metric. Each one focuses on improving their score in their chosen test. The performance profiles of the two chips diverges more. Since most software must be least-common-denominator, all developers except those few that choose to include custom-compiled or assembly bits and processor-specific support will make software that runs slower on average. (i.e. consumer loses).
I liked it much more when Intel and AMD's marketing departments stuck with slapping stupid stickers on boxes and making deals with OEMs -- neither one directly affected me.
I really hate this "PR" crap (Score:3, Interesting)
I have a P4 1.6ghz, I know that the max my board supports is a P4 2.4ghz. Supposing I want to upgrade, how much speed will I gain by maxing my processor? Answer: A bit less than 150% of my current performanc
Re:I really hate this "PR" crap (Score:5, Informative)
AMD did this becuase their chips simply do more work per clock cycle, this was done at the expense of not being able to scale the clock nearly as high as Intel. A 2000+ AMD is *roughly equivillent* to a 2.0Ghz P4.. it wins some, it looses some.
The jump you talk of was at 2600+, when AMD went from a 2.0 Ghz at 266 mhz FSB (called a 2400+) to a 1.833 Ghz at 333 mhz FSB, called a 2600+ Barton. Performance #s goes up, clockspeed goes down.. but FSB goes up! Yes, it's annoying, but this was done as to give most consumers who do minimal research a "fairer" basis for comparison when shopping for computers.
MHz is an absolutely useless metric for comparing processors today when FSBs range from 200 mhz to 800mhz and cache from 128kb to 1MB and higher. Intel and AMD went different routes when designing their offerings, and as you say, it's very difficult to come up with a single number to describe their performance. The problem is that MHz is the number that has been 'historically' used, and it just so happens that AMD went the route that yielded a smaller MHz (and god bless them that they did); so they made the transition to a BS-marketing-numbers system.
Selling the sizzle (Score:3, Funny)
Bad for the consumer? Bad for some (Score:4, Interesting)
That's a good thing in as much as the numbers will stop meaning anything to those with the technical know-how to get useful information from Tom or Anand.
But there are a lot of Stupid People out there using and buying computers every day, and they will be completely in the dark when it comes to evaluating their choices. For them, the deciding factor when choosing a processor in their premanufactured desktop machine will be only what a further descent into Marketing can tell them.
So what naming scheme to use... (Score:3, Funny)
Yeah! Maybe Intel should do the Mhz in Italian. Then they could sell to those Mac people, they like European stuff and stuff.
Or anime hyperobole. The 'super mega ultra rating' vs the 'super ultra mega excellent rating'.
=Engrish! (Score:5, Funny)
What's old is new again (Score:5, Interesting)
It is either a 90 or a 100MHz part, don't know which.
The practice of inventing a silly(TM) performance index that looks better on your chips than your competitor's, or can't be used without a license, is pretty old.
Extreme (Score:5, Funny)
Well then... (Score:5, Interesting)
When the architect of the P6 says something, you usually ought to listen. Perhaps next time you'll get off your high horses and follow the suggestions of the smart people. Now he's gone, you're fucked for '04, and you're in serious trouble on the desktop front if Tejas doesn't turn out to be a rabbit out of a hat.
Re:Well then... (Score:3, Insightful)
"It doesn't matter." (Score:5, Insightful)
"It doesn't matter."
I realize it sounds trite but these days, it's true. They can buy pretty much any new computer they can find and it's perfectly capable of doing what they want to do because, in truth, what they want to do rarely requires a state of the art machine. To simplify things further is the fact that comptuers are getting cheaper and you are getting way more for your money. Buying a new computer isn't the financial hardship it once was.
My mother doesn't care what kind of CPU is in her computer or how fast it is. She just wants to send email to her grandkids and play bridge and she can do that quite happily on a computer she can pick up at Wal*Mart for a few hundred bucks. Power to the people, indeed.
Does anybody remember iCOMP? (Score:5, Informative)
Pentium M (Score:5, Interesting)
I guess Intel is starting this change in numbering early so it doesn't debut a new chip and a new way of labelling the speed of the chip at the same time. Launching both at the same time might look suspicious to less informed buyers, especially if Intel goes from selling 4Ghz chips to 2.4Ghz chips with a PR of 4500+. By starting early hopefully people will be more accustomed to the new numbering scheme and less likely to think they are being conned. A friend recently told me he had bought a new 3Ghz Athlon XP, he was ready to take it back to the shop after I explained what the 3000 meant!
I wonder how compatible this will be with AMD's PR ratings? What would the equivalent to an Athlon 64 with a PR of 3400 be? I hope Intel doesn't invent a PR system that deliberately uses bigger PR numbers than AMDs. I can see confusion amongst consumers who will think an Athlon 64 4000+ is not a match for a "Pentium 5 6000" even if they are equivalent performers.
While Megahurtz has long been a poor way of determining the speed of a chip, I think having two different PR systems that aren't compatible could be worse.
Re:Pentium M (Score:4, Insightful)
I hope you also explained that he got the same, if not more, power as an Intel P4 3GHz, for a cheaper price. It would be silly to educate people about what AMD ratings are not, without explaining what they really are.
I'd like to see an "open" designation (Score:4, Interesting)
This may suggest that Moore's law is at it's end (Score:5, Interesting)
If Intel thought it could keep bumping the clock rate up, they wouldn't move to something like AMD's performance rating. Yet here we are.
Something has changed.
Re:This may suggest that Moore's law is at it's en (Score:4, Insightful)
Yeah, you can do that when you do a complete core overhaul. Going from Northwood to Prescott is a fairly large change, but nowhere near as big a change as going from the PIII to the P4.
"But now we have the 31 stage Prescott and the about same clock rate.
If Intel thought it could keep bumping the clock rate up, they wouldn't move to something like AMD's performance rating. Yet here we are.
Something has changed."
What has changed is that Intel is having problems with the 90nm process, Prescott produces massive amounts of heat, the LGA 775 socket isn't going to solve those problems enough to ramp Prescott beyond 4GHz, if even that high, and the changes being made with the introduction of IA32-64 (aka AMD64) will give processors a pretty decent bump in performance.
Intel knows now that clock frequency ramps have limits. Sure, Bob Colwell told them as much when the P4 was being designed, but now they're actually slamming into walls of fire (heat). Right this second, they're not in such a serious situation that changing to performance ratings is necessary, but they will be fairly soon. Thus, if they do it now, it looks like a new initiative to give Intel an advantage in the marketplace. If they wait until their backs are against the wall, it looks like Intel is struggling to keep up and has lost its edge in the marketplace.
You see now why this is being done? It's just management finally starting to get a little smarter.
Re:This may suggest that Moore's law is at it's en (Score:5, Informative)
Now that's a trend I think is broadly continuing. Multi core CPU's are a part of it. We may also see async processors coming out with zillions of transistors, but no central clock.
What's this accomplish? (Score:3, Funny)
GiggleHertz (tm) (Score:3, Funny)
Patent? (Score:3, Funny)
For the sarcasm imparied, I'm semi-joking. Still, I'd not be surprised if something like that was tried. Patenting something silly like 'single click purchasing' soundes ridiculous too after all.
Use the WifeMark benchmark (Score:5, Funny)
"Feels about as fast as what I have now. And last time she almost killed me for buying a new box."
"Nice, seems faster, but the wife will kill me if I spend this kind of money for nothing special."
"Damn that's fast. I want. She's just going to have to deal with it."
I've been using that benchmark for years. I don't even look at the official numbers. Once it gets to the point where the kit I run now is clearly sh*t for anything normal, I upgrade. Just come home one day with a new box and figure she'll come around.
Got a Mac G4/466 right now, specifically to run OSX. She likes OSX. Before that a used 7600/200 (G2ish) because web browsing got slow and she likes web browsing. Before that a Quadra 630 (486/33ish) because it was best for desktop publishing and we were big into that at the time. Before that, I owned a SE/30 (386/16ish) but that was before we were married. For sure, I more than double performance each time, noticing when something is finally "damn fast" for what is currently important and figuring it scores high on the WifeMark.
Happy with the G4 running Panther, it does email and web browsing and web development work Real Well (as does the 7600 to be honest, but no OSX for that one). I'll upgrade the G4/466 chip someday, maybe when I can get a G4/2000 for cheap on EBay. But otherwise I might run this box for a long time as I can't see anything coming along that scores highly on the WifeMark.
BTW, I still have all the machines listed above. Old Macs never die, they just become web servers.
well... (Score:5, Insightful)
whenever i had to consult people about their pc purchases, i found the best way that they understood was basically the 3 parts of the cpu.. mhz, bus speed, and cache memory..
your cpu is a vehicle.. the mhz is the speed the vehicle can carry stuff from one place to another (this is what you are buying this ehicle to do - moving stuff) the bus speed is how fast you can load your stuff onto your vehicle.. and the cache memory is the amount of stuff the vehicle can carry...
then i go to explain how whats the point in having vehicle A that can go 1.5 times faster than vehicle B, but vehicle B can carry twice as much stuff each trip.. in the end Vehicle B is the one that gets more done.. until you get into things like it doesnt matter how fast vehicle A can go, if vehicle B can be loaded and on its way and back in the same time that A is still being loaded (bus speed)
its probly not the most refined explaination, but its the way i've talked many people into getting athelons instead of celerons, and in the end getting a better computer (dunno about the states but up here i can get an XP2200 for about the same price as a celeron 2ghz -give or take $5- and we're talking HUGE difference in performance)
Leaked naming secrets from Intel (Score:5, Funny)
Q3 2004: Pentium Fast
Q2 2005: Pentium Really Fast
Q4 2005: Pentium Reeeeeeeaaally Fast
Q2 2006: Pentium Flies
Q4 2006: Pentium 0wnz
In in the words of my computer architecture prof (Score:5, Insightful)
Misread the subject (Score:4, Funny)
Re:What are they going to compare to? (Score:3, Informative)
You understand wrong. AMD Performance ratings are as compared to a Thunderbird core Athlon. In other words, a "PR 3200+" chip is eqivilent to a Thunderbird running at 3.2Ghz, and not a 3.2Ghz Pentium 4.