Carmack says iPhone is "more powerful than a Nintendo DS and PSP combined"

[WhizzBang]

Certainly, the CPU in the You have to remember that Carmack has made his millions riding the "brute-force programming" wave the PCs went through in the late 90's and early 00's.

Very true. This is partly why I am a retro gamer, even though Carmacks best stuff is now retro itself. When I play a game like Head Over Heals which uses less than 48k I amazed that they put so much complexity and solid gameplay into it when your average email is larger than 48k these days.

[AshTR]

Honestly, you'd have to check the bogomips. Not sure if the iPhone has some sort of way to shove Linux on there enough to check the bogomips but the PSP gets 109.82 BogoMIPS with uCLinux on PSP. http://jacksonm80.googlepages.com/screenshot0004.gif

Heck, I have a Pentium 1 processor laptop that gets better bogomips than that.

[JLF65]

Honestly, you'd have to check the bogomips. Not sure if the iPhone has some sort of way to shove Linux on there enough to check the bogomips but the PSP gets 109.82 BogoMIPS with uCLinux on PSP. http://jacksonm80.googlepages.com/screenshot0004.gif

Heck, I have a Pentium 1 processor laptop that gets better bogomips than that.

That's not a good way to check the power of a CPU. For example, uclinux on the PSP is hardly in a state to run anything - was your little test on a version that has full cache control or not? It makes a BIG difference. It's like running your test on an alpha of DOS and complaining that it doesn't match the value in the latest 64 bit linux.

You'd be better off trying to convert bogomips to native PSP than running it in uclinux at this point.

EDIT: Actually, that was pretty close. I made the stand-alone version of bogomips into a native PSP app and get 109.77 (at 222 MHz). Still, like the bogomips FAQ says,

Why to pay attention to BogoMips

To see whether your system is faster than mine. Of course this is completely wrong, unreliable, ill-founded, and utterly useless, but all benchmarks suffer from this same problem. So why not use it? This inherent stupidity has never before stopped people from using benchmarks, has it? :-)

So take bogomips with a grain of salt, and point and laugh at people who suggest using it as a benchmark. :rofl: