| HN Mirror

> This is marketing we're talking about, people see "supercomputer on a chip" and they get hyped up by it.

That is also not in dispute. I am disputing your specific claim that Apple somehow suggested that the G4 was of commensurate performance to a modern supercomputer, which does not seem to be true.

> Apple was 100% using the "supercomputer" claim to make their luddite audience think they had a performance advantage, which they did not.

This is why context is important (and why I'd appreciate clarity on whether you genuinely believe a supercomputer from the 1970s was anywhere near as powerful as a G4).

In the late twentieth and early twenty-first century, megapixels were a proxy for camera quality, and megahertz were a proxy for processor performance. More MHz = more capable processor.

This created a problem for Apple, because the G4's SPECfp_95 (floating point) benchmarks crushed Pentium III at lower clock speeds.

PPC G4 500 MHz - 22.6

PPC G4 450 MHz - 20.4

PPC G4 400 MHz - 18.36

Pentium III 600 MHz – 15.9

For both floating point and integer benchmarks, the G3 and G4 outgunned comparable Pentium II/III processors.

You can question how this translates to real world use cases – the Photoshop filters on stage were real, but others have pointed out in this thread that it wasn't an apples-to-apples comparison vs. Wintel – but it is inarguable that the G4 had some performance advantages over Pentium at launch, and that it met the (inane) definition of a supercomputer.

> The reason they marketed it that way was to get people to part with their money. Full stop.

Yes, marketing exists to convince people to buy one product over another. That's why companies do marketing. IMO that's a self-evidently inane thing to say in a nested discussion of microprocessor architecture on a technical forum – especially when your interlocutor is establishing the historical context you may be unaware of (judging by your comment about supercomputers from the 1970s, which I am surprised you have not addressed).

I didn't say "The reason Apple markets its computers," I said "The entire reason they made the claim [about supercomputer performance]…"

Both of us appear to know that companies do marketing, but only you appear to be confused about the specific claims Apple made – given that you proactively raised them, and got them wrong – and the historical backdrop against which they were made.

> In the first link you added, there's a photo of a Cray supercomputer

That's right. It looks like a stylized rendering of a Cray-1 to me – what do you think?

> which makes the viewer equate Apple = Supercomputer = I am a computing god if I buy this product

The Cray-1's compute, as measured in GFLOPS, was approximately 6.5x lower than the G4 processor.

I'm therefore not sure what your argument is: you started by claiming that Apple deliberately suggested that the G4 had comparable performance to a modern supercomputer. That isn't the case, and the page you're referring to contains imagery of a much less performant supercomputer, as well as a lot of information relating to the history of supercomputers (and a link to a Forbes article).

> Apple's marketing has always been a bit shady that way.

All companies make tradeoffs they think are right for their shareholders and customers. They accentuate the positives in marketing and gloss over the drawbacks.

Note, too, that Adobe's CEO has been duped on the page you link to. Despite your emphatic claim:

> Apple was 100% using the "supercomputer" claim to make their luddite audience think they had a performance advantage, which they did not.

The CEO of Adobe is quoted as saying:

> “Currently, the G4 is significantly faster than any platform we’ve seen running Photoshop 5.5,” said John E. Warnock, chairman and CEO of Adobe.

How is what you are doing materially different to what you accuse Apple of doing?

> And soon after that period Apple jumped off the PPC architecture and onto the x86 bandwagon.

They did so when Intel's roadmap introduced Core Duo, which was significantly more energy-efficient than Pentium 4. I don't have benchmarks to hand, but I suspect that a PowerBook G5 would have given the Core Duo a run for its money (despite the G5 being significantly older), but only for about fifteen seconds before thermal throttling and draining the battery entirely in minutes.