»

[System]

OSNews published this great article comparing the X86 platform to PPC.

Source : Osnews.com

[Hammer]

@Nicholas Blachford -

Benchmarks via GCC issues;
- One shouldn’t generalise X86 issues i.e. Pentium 4’s related issues may not be applicable to the K7 and K8 families e.g. floating point instructions (non-SSE/3DNow) and GCC.

- Regarding Opteron only for server staements...
The recently released AMD Opteron 1xx series and nVidia nForce3 are being targeted for workstation markets not just for the server markets.

- Regarding "Pentium M" embedded markets; According to http://www.intel.com/design/intarch/prodbref/25269601.pdf

1.1Ghz @ 12 Watts, 1.6Ghz @24.5 Watts.

[bhoggett]

"great article"

ROTFL

[norm]

Obviously biased but an interesting article all the same.

[bloodline]

The Article is blatent marketing... full of half truths and errors.

YOU DON'T NEED TO LIE ABOUT THE PPC TO SHOW HOW GOOD IT IS!!!!!

When will people learn :-(

[bhoggett]

@bloodline

When will people learn

Never, I guess.

What makes this sort of article junk is that it is passed on as an "analysis", when it clearly is not, and the fact that it 's mostly preaching to the converted, who will readily accept anything that re-inforces their own beliefs without bothering to check whether the facts are accurate or the conclusions justified.

[AmigaMac]

The article is not biased, it just points out a clear definition that pro x86 advocates (as well as pro PPC advocates) are truly guilty of benchmarketing than anything else. No matter if it's Apple or Intel, they will spread propaganda and fudge benchmarks to sell their products. Nothing wrong with that me guesses :-P

on another note:

great article Nicholas :-D

[bloodline]

The article is not biased, it just points out a clear definition that pro x86 advocates (as well as PPC advocates) are truly guilty of benchmarketing than anything else. No matter if it's Apple or Intel, they will spread propaganda and fudge benchmarks to sell their products. Nothing wrong with that me guesses

I ignore the benchmarks they are irrelevant, the simple fact is that the information in the article is wrong. And it's wrong in all the right places to make the x86 look bad... but there really is no point the PPC does not need this sort of credibility bashing.

The PPC is a neat CPU, if people would just look at it realisticly they would see it's advantages. You don't need to make the competition look worse... :-(

[cgutjahr]

@bhoggett/bloodline:

Maybe I'm just old-fashioned, but wouldn't it be a good idea to tell us what is wrong with the article, instead of just complaining about "the usual PPC zealotry"?

[KennyR]

Funny how stuff is always propaganda if it doesn't support one's views and the system one is currently using, isn't it?

[bloodline]

Example:
1.
It highlighted the weakness in the x87 (the FPU), it failed to note that these weakenesses have been rectified in the Pentium+ (Athlon+), with it's "free instructions" and multiple pipes etc... It also failed to note that the new PPC 970 has actually cut back the FPU as it is simply not that important on the desktop, Vector units and 3D GPU's are far more important.

2.
It claims that the PPC has a shorter fatter pipe than the Athlon. Not true the Athlon and PPC have similar sized pipes (which is why their performance is very comparable), it's the Pentium4 that has a long thin pipe. Also the article claims that the PPC 970's pipe is long and thin, but for the PPC some how this is better than the x86... It doesn't explain how or why,(which is not surprising since long and thin has benefits for any architecture when scaling performance, but this article couldn't suggest that the P4 has a more advanced design... could it?)

3.
The Term RISC and CISC has not been used by chip designers for a long time. The chips are now classified by their architecture, rather than the "design Philosiphy". Most CPU's are now "Load-Store". The x86 has a less complex instructin set than some RISCs, and the PPC has the most complex RISC instruction set I've ever seen... Both CPU's share RISC/CISC features, as it's more efficient to use both conceepts.

4.
The Article fails to note that the modern PPC and the medern x86 CPU's are infact very similar chips, they use all the same "tricks" and have all been designed by people who have kept up to date with the latest technology.

5.
The Article says that RISC designs have many more Registers than CISC designs, this is true. But what it fails to mentions is that in order to speed up context switches and due to compiler effieincies many RISC designs implement a register window. That means that the programs on the RISC CPU only see maybe 16 registers not the whole set. (it turns out that 16registers is about spot on foroptimum performance.). This means that the x86 running using register renaming is using it's registers exactly the same as a register window!!!. The x86 has too few registers but the x86-64 has more

There are plenty more, like these.

At the end of the day, I like the PPC, I even own one, and I'm hoping the Motherboard fairy brings me a Pegasos... fingers crossed. But I don't appreciate articles that are just blatent marketing.

You don't need to lie about the PPC to show how good it is!!!

I'm not an x86 Zelot. I simple use what is the most powerful for the money... that's why I bought qan Amiga ad stuck with it for10 years!!!

[downix]

@bloodline

No, the 970 is long and fat, combining the strengths of both approaches.

It has multiple pipelines along with many stages for each. The many stages of the P4 turned out to be a blessing in one way, allowing the P4 to get extremely high speeds. The fat pipes of PPC and Athlon allow them to compete with the P4 (PPC not as successfully however due to other issues). Now, what happens when the fat pipes get grown tall?

That is what the 970 has done.

[bloodline]

No, the 970 is long and fat, combining the strengths of both approaches.

Well, then you have just pointed out another error inthe OSnew article. :-)

The fat pipes of PPC and Athlon allow them to compete with the P4 (PPC not as successfully however due to other issues). Now, what happens when the fat pipes get grown tall

I have no doubt that the PPC 970 will be able to compete with the Athlon and the P4, that is why I don't understand all the lies in the OSNews article!?!?!

[mikeymike]

@ KennyR

Funny how stuff is always propaganda if it doesn't support one's views and the system one is currently using, isn't it?

What, like some MorphOS users claiming that anyone considering getting an A1/OS4 are just blindly following the name?

Please note that I said some, rather than using generalising terms.

[KennyR]

Yes mike, it cuts all ways.