Re: [hatari-devel] Hatari on constrained devices

[Thomas Huth <th.huth@xxxxxxxxx>]

Am Sun, 16 Jan 2022 16:18:53 +0100
schrieb Christian Zietz <czietz@xxxxxxx>:

> Thomas Huth schrieb:
> 
> > It's not measurable on modern CPUs.  
> 
> I would agree to that.
> 
> Linux developers seem to look down on other platforms, because Linux
> has the incredible "perf" tool. So, why not use it, I thought?
> 
> This is on a Raspberry Pi 400, certainly a less powerful CPU than in a
> current PC. Somehow inspired by the command used during the EmuTOS
> tests, I ran...
> 
> SDL_VIDEODRIVER=dummy SDL_AUDIODRIVER=dummy perf stat -e cycles -r 10
> hatari --log-level fatal --sound off --fast-forward on --run-vbls 400
> --fast-boot on --tos etos512de.img
> 
> ... to measure the amount of ARM CPU cycles spent, without any video
> or audio output overhead. These are the average values and standard
> deviations for 10 repetitions ("-r 10") respectively:
> 
> ENABLE_SMALL_MEM=0
>   3,333,167,644      cycles   ( +-  0.45% )
> 
> ENABLE_SMALL_MEM=1
>   3,267,861,361      cycles   ( +-  0.53% )
> 
> Therefore, ENABLE_SMALL_MEM=1 even seems to be (very marginally)
> faster in this test!

Thanks a lot for your measurements, Christian! Great to see that these
confirm the observations that I believed to see while staring at the
output of "top" :-)

But I guess it's likely still better to keep the switch itself around
for a little bit longer, until we've figured out the problems that have
been reported in the other mails... or maybe we should just keep it
around until the next release has been done, so that users have a an
emergency knob there, too...
By the way, Nicolas, do you have any plans for a new release? It's been
more than a year again since the last one...

 Thomas