Daedalus R14 Update: Media Engine Progress -- N64 Emulator

[CaptainMorgan4]

StrmnNrmn has updated his blog today on Tuesday, and it's about his progress on the Media Engine.

"Tuesday, November 13, 2007
Media Engine progress
Over the weekend I described my plans for getting audio list processing working on the PSP's Media Engine. I'm making some decent progress so far. I've got Daedalus loading a kernel mode PRX to handle the ME nitty gritty, and I've managed to execute some test code on the ME successfully.

I've spent some time reviewing the audio code, trying to figure out if any bits are particularly amenable to running asynchronously, and trying to figure out if there is anything that is going to cause any problems when running this code on the ME. Fortunately it looks like all of Azimer's audio code is very straightforward C so there should be no problems getting it running on the ME once the synchronisation issues are dealt with. I've also realised that alongside the audio list processing there is also some expensive 44kHz upsampling code which will run very nicely on the ME too.

Via StrmnNrmn's Blog: http://strmnnrmn.blogspot.com/

I have the feeling that debugging code on the ME is going to be particularly painful, so I want to try and catch as many of the obvious synchronisation bugs as early as possible. This evening I've started writing a job manager to 'simulate' executing code on the ME. The manager simply creates a thread which sits and waits for jobs to come in, mimicing the behaviour of the mediaengineprx. Once I've got the audio list processing running correctly through the job manager, I can easily switch things over to get these jobs running on the ME in parallel to the main core. That's the plan, anyway

-StrmnNrmn"


Glad to see he's updating alot now, hopefully he'll get through this smoothly.

[Sterist]

44kHz is a very VE-HEH-ERY (lol) small part of 333mHz

1000kHz -> 1mHz
psp cpu = 333mHz, so...

44kHz = 0.044% of 1mHz
1mHz = 0.333% of 333mHz

so...
0.044% x 0.333% = freed CPU time.
freed CPU time = 0.014652%

this is no estimation. but you have been getting estimations on the past releases

edit:

im pretty sure the speed up is only in sound enabled mode

[pibs]

wow that is freaking great news maybe ssb will have nice audio on R14

Great Job StrmnNrmn

[DessyDago]

44kHz is a very VE-HEH-ERY (lol) small part of 333mHz

1000kHz -> 1mHz
psp cpu = 333mHz, so...

44kHz = 0.044% of 1mHz
1mHz = 0.333% of 333mHz

so...
0.044% x 0.333% = freed CPU time.
freed CPU time = 0.014652%

this is no estimation. but you have been getting estimations on the past releases

edit:

im pretty sure the speed up is only in sound enabled mode

nm

[Cloudhunter]

44kHz is a very VE-HEH-ERY (lol) small part of 333mHz

1000kHz -> 1mHz
psp cpu = 333mHz, so...

44kHz = 0.044% of 1mHz
1mHz = 0.333% of 333mHz

so...
0.044% x 0.333% = freed CPU time.
freed CPU time = 0.014652%

this is no estimation. but you have been getting estimations on the past releases

edit:

im pretty sure the speed up is only in sound enabled mode

You obviously don't see the difference between CPU speed taken and sound frequency. Totally different and the code to translate the audio frequency up takes alot of CPU power, hence why he is moving it over.

Cloudy

[Raziel-chan]

You obviously don't see the difference between CPU speed taken and sound frequency. Totally different and the code to translate the audio frequency up takes alot of CPU power, hence why he is moving it over.

Cloudy

What he said :3

Doing all these things on a single CPU - no wonder that with sound the emulation was staggering :3 I remember running PS2 emulation on a single core machine o.O

Yes, the speed up will probably only occur with sound enabled, but with Mario 64 it'll mean that you'll be able to play it comfortably with sound - it already runs fast and the audio staggers only when more polygons are on the screen.

cya
Raziel-chan

[pichon]

Big thanks to StrmnNrmn for all his efforts on daedalus, can't wait for R14

[daibo]

You obviously don't see the difference between CPU speed taken and sound frequency. Totally different and the code to translate the audio frequency up takes alot of CPU power, hence why he is moving it over.

Cloudy

Only that it's sampling rate and not sound frequency, two totally different things.

[kharaboudjan]

so, what exactly does this blog update mean?

[SpacemanSpiff]

It means that he successfully executed code on the ME. And he wrote something that basically emulates the ME so he can test and see if when moving code over will cause any bugs.