Re: [hatari-devel] Hatari data cache tests

[ Thread Index | Date Index | More lists.tuxfamily.org/hatari-devel Archives ]


I should add - I think its better to use idealized timings to check the CPU ops, cache, and head/tail timings are accurate.

Later it would be more interesting to use real F030 video modes to get bus performance more accurate... but even at that it would be some kind of approximation I suppose.

D.


On 18 June 2015 at 21:41, Douglas Little <doug694@xxxxxxxxxxxxxx> wrote:
Hi,

Since Hatari doesn't count videl overhead I think its better to use -videl to get more ideal timings from real HW - at least until Hatari starts accounting for videl time.

Unfortunately even with videl off, the Falcon bus is not an even ratio with the CPU but at least its a fixed ratio as a baseline, and a bit closer to idealized...

D


On 18 June 2015 at 21:34, Nicolas Pomarède <npomarede@xxxxxxxxxxxx> wrote:
Le 18/06/2015 21:51, Douglas Little a écrit :
Here is an interim version which should at least provide some info while
I fill out the rest...

https://dl.dropboxusercontent.com/u/12947585/nb030_v100.zip

Invoke with -f030 for Falcon tests in the desktop video mode.
Additionally pass -videl to shut down video fetching during the tests
for a better baseline (expect a black screen for an extended period!).

It will write a nb.log file which can be extracted from a real machine
to compare with Hatari. All tests are cycle-accurate. Non-integer cycle
timings are side effects from various things - mainly the bus.

I'll post another version with more tests if it proves useful.

D.


Thanks a lot, I will try this under Hatari.

But so far, Hatari's videl emulation doesn't steal bandwidth from the cpu depending on the selected video mode as it should do on real HW.

In order to compare Hatari with real HW, does it mean we should use the -f030 or -videl to get results that don't imply the video mode ?

Nicolas






Mail converted by MHonArc 2.6.19+ http://listengine.tuxfamily.org/