[hatari-devel] Could you all test this on hatari falcon new core and real hardware please ?

Laurent Sallafranque laurent.sallafranque at free.fr
Wed Aug 24 10:12:13 CEST 2011


Hi,

I'm currently trying to improve 68030-> DSP synchro and 68030 cycles and 
dsp cycles.

For this, I wrote a little prg that does some NOP loops in 68030 and add 
1 to a register in the DSP.
After 100 loops, I get the dsp result of the adds.
I do the same with 500 loops, 1000 loops and 10000 loops.

My goal is to compare the results from hatari with the real hardware 
results.
I've tried to stop as many timers as possible.

The hatari results (on my computer) are :

100 loops     : $96
500 loops     : $2ac
1000 loops   : $546
10000 loops : $3426

On my falcon, I get :
100 loops     : $b9
500 loops     : $5df
1000 loops   : $706
10000 loops : $75a4

I've tried in different resolutions, it doesn't seem (at first glance) 
to change the results.
I've also noticed that my hatari results are constant if I try many 
times, but the Falcon results are close but not constants after each try.

 From me, on the 68030 side :
     a 68030 NOP is 4 cycles, so, for 100 NOPs, 400 cycles at 16 Mhz.

On the DSP side :
      p:005a  200050         (02 cyc)  add y0,a
      p:005b  0c005a         (04 cyc)  jmp p:$005a

In theory, the formula for the result of the adds should be : 100 (loop) 
* 4 (cycles fo NOP) * 2 (32 Mhz) / 6 (DSP cycles for the add+jmp).

So, I should get :

100 NOP      : add = $85
500 NOP      : add = $29a
1 000 NOP   : add = $535
10 000 NOP : add = $3415

These results are really close to the Hatari results, but far from my 
real falcon results.

Would it be possible for Falcon gurus here to try this little prg on 
their hardware and tell me their results ?
Also if you detect something wrong with this code, it would help.
Maybe I forget some parameters in my formula, ....

(If you can't get the zip, just send me a mail, and I'll send the zip).

Best regards,

Laurent

-------------- next part --------------
A non-text attachment was scrubbed...
Name: hatari2.dbg.zip
Type: application/x-zip-compressed
Size: 4704 bytes
Desc: not available
URL: <https://lists.berlios.de/pipermail/hatari-devel/attachments/20110824/13be16d6/attachment.bin>


More information about the hatari-devel mailing list