Re: [hatari-devel] profiler cycles (was New WinUAE core issue with Bad Mood)

[Douglas Little <doug694@xxxxxxxxxxxxxx>]

Hi!

On 17 May 2015 at 22:16, Eero Tamminen <oak@xxxxxxxxxxxxxx> wrote:

Hi,

On perjantai 15 toukokuu 2015, Nicolas Pomarède wrote:
> Back on this "0 cycle" case.
>
> As already discussed, the 68030 has some more advanced bus handling and
> cache than the 68020 and can delay write for example.

This pretty much matches what I though when I heard about the zero cycles case - but I think there was some concern earlier about the frequency / context of these occurrences (maybe happening unexpectedly often / on instructions where it didn't make sense). 

However I don't think it's been studied fully in Hatari itself (certainly not by me! maybe others have since..) so I mean to take a closer look when I get enough time. I'll report then if it looks sensible to me.

Best,

Doug.