naTmeg wrote:
this is done on the mos-native version of amigamark.
i dunno why it get 1200 bogomips on linux..
anyway..
Well there is no native MorphOS version of AmigaMARK according to the OFFICIAL readme I found on the OFFICIAL AmigaMARK website for the LATEST version of this software.
It says:
- Hardware: - ยท Amiga/Pegasos[JIT]
JIT == Just In Time
That's mean it use the JIT 68k emulator.
So I doubt a lot he has used the MorphOS PPC Native version AmigaMARK as this version doesn't exist apparantly
Or point me to a link where I can DL one. The only one I found was this one:
AmigaMARK BetaWhich is clearly not a MOS PPC Version, this archive contain only one binary which is a pure 68k binary. So please check your information before spreading them.
This would explain the huge difference between AmigaMARK result and Linux result because this kind of test can't really benefit of the JIT as it quite never reproduce the same operation 2 times and as you may know JIT compile at the first run of an operation (for the first run it's interpreted) and the benefit of this compilation appear only if it does this same operation a second time as it'll then use the dynamically compiled version. But in the case of BogoMIPS test this type of repetitions of an operation is not happening oftenly.