forums.ps2dev.org

if you pack using a binary compressed version of a spu_shuffle pattern values are 0-31 and the 0xFF 0x80 and 0xc0 unique values and you have 16 slots on where to insert it. With a certain data ordered to your best compressed liking. you should be able to compress and decompress lossless large amount...

install the spu-gcc in the ubuntu package or wait a few days.

Make shure its all compiled 32 bit or it will fail.

We are working on a automatic build

Crazy stuff:
Render X onto a jpg Screens using existing variable length coding patterns
Decompress the screens onto the framebuffer in a "ordered" manner.

:)

Managed to reach 6.1GB/s using 3 dma's in and one out on a single one.. with what i belive is a working yuv420 to yuv2

Installation guideline moved to a separate thread.

http://forums.ps2dev.org/viewtopic.php?t=9187

Usually when you have four microphones(antennas,cameras) they are used for direction/tracking. Figuring out which is which may be nice in order to attempt to make something that translates the signals into relative directions by looking at the doppler shifts.

Ahh ok

well anyways it should be possible to reach those 12GB/S speeds doing only yuv420 to yuv2.
I have done yuv420 to ARGB at 2.5GB/s bidirectional which is a lot more processing at least when using floats. Maybe this weekend :)

Mabye i could make that into something like this. CONV_YUV420_TO_YUV(Ypointer,Upointer,Vpointer,Istride0,Istride1,Opointer,Ostride0,TAG) WAIT_CONV(TAG) //waits for that tag to be marked as complete. where TAG is a 32 bit int or something. In theory that should be capable of going in close to 24GB/s ...

Glarung

Perhaps i can make you a yuv420/yv12 to YUY2 spe converter.. should be really really fast.

put this in your /etc/fstab
then run mount /spu

none /spu spufs defaults 0 0

Seems it doesn't want to start up the spe..
is your spufs in order in fstab ?

Heres my wokaround using the SPE's :) bad joke its 5.am but in fact it kind of is. I threw an experimental SPU Xv driver on SVN. It does 1080p in X using 1 spu so it looks ok but theres lots of TODO's with it like fix interrupt handlers and timers. Expect install guideline within days inside spu-med...

threw an experimental spu Xv driver on SVN.
It does 1080p in X using 1 spu so it looks good but theres lots of TODO's with it.
Expect install guideline within days

Added the Xv driver to svn working on making it user friendly to install. Disclaimer: This is very very experimental but i got it working for 1080p playback with X running without making a complete mess out of everything.. scaling also seems to work If it doesnt update properly after fullscreen pres...

So i eventually started to think of all the people using X And started to poke around in Xv. I cant belive im doing this Xv is painful for me. Anyhow i have gotten to the stage where i at least have something registered in X when i start it up. Please not that we are still only using spu's here and ...

Sounds like a plan However i think acellerating mpeg and h264 should be higher on priority list.

.. DirectFB might be worth looking at as well.

Hi I have started some work on the spu Xv as this will not be just limited to PS3 but will also work on any future FB CELL's and will likely work for any ppc + spursengine. however it will probably need modifications to work on a x86 + spursengine but since its chars we only need to consider endiane...

It is not directly easy to solve , its very much dependant on how the data is handeled over to the scaler / csc If you have width w Height h then line 0 starts at 0 and line 1 starts at 0+w right.. however it has come to my attention that you can force an alignement stride so that line 0 starts at 0...

Anyhow i think making a XV driver based on spu scaling + csc + blit is stable and safe. Untill we se the responses to these developments.

@Glarung please take a look here http://wiki.ps2dev.org/ps3:spu-medialib As you can se we not only got the colorspace into a single spe but also a scaler into the same one. I am more than happy to extend these to whatever is needed to make some XV driver and using the stuff we have in the mplayer-vo...

I would also be more than happy to write other 2d acellerations for the spu like
yuyv perhaps.

@IronPeter Im working on spu medialib and we have made a yv12/yuv420 scaler that also does colorspace conversion at more then sufficient framereates 85FPS @1920x1080 using a single spe. we have also worked on a mplayervo using spu-medialib and libsp3fb a small fb lib we made. if we could figure out ...

@fusuke what is the resolution of the mpeg you are playing back and what video output resolutions you have tested ? @ldesnogu sync is controlled by the video framerate. swapfb (blit and swap) is executed at the time mplayer wants it to be executed. I have spent a day looking at how to do this in X m...

Ok time to recruit who wants to help ? go into spu-medialib section in the forums please. I need more people and i dont mind helping training them in how to think spu. Basic consept: Offloading anything to the spe's gives better overall performance so why not do it. Currently im looking into if its ...

Try it outside of X and se if you get the flickering there.

EDIT:
I think this is most likely caused by the X server still trying to draw to the framebuffer. However if we get some sort of overlay this will not be a problem any more or tell X to render offscreen while we are running video playback.

We have started to look into how to get X to redraw etc
however this may take some time.

nice to hear that my changes worked :)

new rev of spu-medialib on svn migth solve the problems for 32 bit users.

spu-medialib is still very in work ..
Im going to look into making a proper configure etc for it.

thanks for testing .. from what i can se it must be a problem with the 32 bit adresses probably they need to be sign corrected for MSB63->32 before the dma.. as its 0xFFFFFFFFADRESS in 32 bit but when you stick and adress into a unsigned long it doesnt extend it like that! it ends up as 0x00000000AD...

Sorry cleared out now.