PowerMac G5: World's Fastest Desktop Computer

[Cubeboy]

Originally posted by Rower_CPU
That's not the point. Apple was more than fair to the Intel chips by enabling SSE, but not taking any special measure to enable Altivec.

The performance gain by enabling SSE results in an unfair advantage to Intel, and Apple still comes out performing just fine.

I think your missing the point of my previous post, you can't gain anything from SSE2 unless you have an compiler that can implement it.

Since we're dealing with SPECfp which really is what SSE/SSE2 significantly affects, we're mostly looking at the FORTRAN compiler being used, specifically Nagware 95 and judging from the scores, I doubt it generates any SSE/SSE2 code at all.

 

[wizard]

Originally posted by Ensoniq
The point Rower_CPU was making about SSE2 and SPEC was this I believe...

Some people originally complained that SSE2 had not been enabled for the testing...which turned out to be false. But the assertion was that if SSE2 HAD been turned on (which it was) that the SPEC scores would have been higher.

For this to be true, it means that not only would SSE2 need to be enabled in the compiler (which it was) but that SPEC would have to recognize SSE2 in order for the test scores to come out better. Meaning, SPEC has SOME code in it specifically to check for and use SSE2 if it's available. I don't know if that's true, but that's the assertion I believe Rower_CPU made.

SPEC is a set of source code, when an intelligent compiler complies SPEC it has the ability to make use of all features of the CPU that are enabled. SPEC does not need to check for SSE2 at all, the compiler simply has to be setup to make use of it. If such a compiler has the switches thrown at compile time to use SSE2 and the data types and operations done are placeable into the SSE instruction unit SPEC could make use of the hardware. SPEC itself does not need to enable or check anything.

Whether it's true or not, what's perfectly clear is that the SPEC test does NOT have any code in it to detect and use AltiVec if it's available. So even if Apple had used special flags in GCC to enable the use of AltiVec (which they specificially did NOT use, even though they turned on SSE2 for their x86 counterparts), SPEC wouldn't have looked for it.

As above it is a compiler issue, SPEC doesn't have to look for it. My suspicion is that if Apple had a compiler available that supported AltVec they would have runned the SPEC suite with the support enabled and disabled and published the best figures.

So if SPEC is designed to use SSE2 (not certain) but is NOT designed to use AltiVec (an absolute fact) than right out of the gate it shows that SPEC would have an inherent bias BUILT-IN to skew scores more favorably to the x86 processors. How come no one goes out of their way to point out how THAT might be considered cheating at worst, an unfair advantage at best?

Its the compiler and the switches set at compile time. SPEC has nothing to do with it, the better the compiler the more likely it will use as many features as possible of the processor.

So far, the only claims of "cheating" have come when it may have given the Mac an edge. And though there is STILL no shred of evidence of true cheating by Apple (even the admissions on the PC side that Intel, AMD, and ATI do it, so Apple MUST too remains less than credible), it's the only drum for the Wintelers to keep banging...so that is what they have done.

-- Ensoniq

Apple has done a good job with SPEC. It sdoes appear though that some have gotten a little to excited over the SPEC results. We really need to wait until the real machines hit the market and we can run real world tests on them. This will clear up alot of outstanding questions.

thanks
Dave

 

[agdickinson]

PCI Expansion Box possibly for G5?

Hi,

Not sure if anyone knows but I have found something for video people (amongst others) who are concerned about the lack of PCI slots in the G5.

Please forgive if your already aware about it, as it appears to solve part of the concerns, then again the ugly cost icon probably rears it's head.

http://www.magma.com/pci/7slot6466/

Oh dear $2595 well, how stupid do I feel

Well at least it's an option for people who just have to have millions of PCI slot's (7 extra in total). But the cost probably pays for another G5

Cheers

Andrew

 

[ouketii]

the $1200 g4 powermacs are awfully enticing though... less than i paid for my last pc tower...