Login at Kodi Home

phusho · 2011-04-18, 15:23

McGeagh Wrote:EDIT: I looked into the DrawQuad patch, and it was commited, just the trac didnt reflect this. it does now.
We do appreciate any and all patches you can provide us. Thanks

also, i have written some VFPv3 code for the mathutil functions, but havent had a chance to test it to make sure it works (mainly because i dont have a board with vfpv3 setup). If anyone does and would like to be the guinea pig, that would be very helpful.

phusho, your version looks like VFPv2 to me, so please keep them. having the different versions will ensure backward compatibility.
I have not looked into nvidias own VFPv3-D16 crap, nor NEON yet, but both would be very good to have eventually.

IDD it is VFPv2 for arm1176JZF-S

McGeagh · 2011-04-18, 15:47

after a bit of research, vfpv3-d16 is no different to standard vfpv3 (except has half the available double-registers... of which we are only using 1) so it should work for tg2 too.
i am unsure if vfpv3 code will work on vfpv2 though (says it is backwards compatible)
Also there is no need to do a NEON version, as that will only give a performance increase if it were vectorised... and currently that is not the case if changing mathutils only.
I will try test my vfpv3 and commit later.

phusho · (This post was last modified: 2011-04-19, 10:14 by phusho.)

McGeagh Wrote:after a bit of research, vfpv3-d16 is no different to standard vfpv3 (except has half the available double-registers... of which we are only using 1) so it should work for tg2 too.
i am unsure if vfpv3 code will work on vfpv2 though (says it is backwards compatible)
Also there is no need to do a NEON version, as that will only give a performance increase if it were vectorised... and currently that is not the case if changing mathutils only.
I will try test my vfpv3 and commit later.

send me the code I will test it on my board for vfpv2 compatibility

P.S. It seems that VFP code run much slower on NEON capable CPU-s. e.g there is test of VFP matrix multiplications on iPhone 3GS and VFP code is slower than ordinary C code and much slower than NEON code ... go figure it out.

McGeagh · 2011-04-19, 11:07

NEON is seperate to the VFP. Although neon can do VFP instructions, it will only give performance benefits if the code can be vectorised.
As for it being slower than C code, its entirely possible that the c compiler is smarter than whoever wrote the VFP code, and therefore optimised it better.
I am indeed trying out various different methods, and will be testing to see which version, is the best performance... this could mean standard C code may be the winner! I will keep you informed.

As for giving you my current code, i have realised an error and am working to fix it. so once i do that, ill send you the change.

PeterW · 2011-04-19, 17:33

Hello,

I have followed this thread for a while and realised that there are quite a few SoCs around on which members of this forum have more or less sucessfully installed XBMC. What would be the recommended platform?

I presume whenever developers are reporting about the port of XBMC to one or the other platform, what kind of baseboard they are using, e.g. for Telechip or Nvidia Tegra?

Kind regards,
peter

Wilmer · 2011-04-24, 11:32

dw21 Wrote:You will have to switch to the mesa egl and gles drivers while compiling as headers are not available for the sgx drivers.

Actually they are, you just have to install them yourself:

Code:
wilmer@panda:~$ dpkg -l 'lib*omap4*dev'

ii  libegl1-sgx-omap4-dev                                           1.7~git0f0b25f.3-1                                              PowerVR SGX540 EGL libraries for OMAP4, development files

ii  libgles1-sgx-omap4-dev                                          1.7~git0f0b25f.3-1                                              PowerVR SGX540 OpenGL|ES 1.x libraries for OMAP4, development files

ii  libgles2-sgx-omap4-dev                                          1.7~git0f0b25f.3-1                                              PowerVR SGX540 OpenGL|ES 2.x libraries for OMAP4, development files

@hfkou: Why --enable-tegra? Sounds like a completely different platform..

KRavEN · 2011-04-25, 13:45

Just saw this new on DealExtreme today:
http://www.dealextreme.com/p/x9-itv-2-5-...game-64005

TC8901, HDMI, Remote, LAN, WiFi, USB, similar look as the ATV2.

phusho · 2011-04-26, 08:13

KRavEN Wrote:Just saw this new on DealExtreme today:
http://www.dealextreme.com/p/x9-itv-2-5-...game-64005

TC8901, HDMI, Remote, LAN, WiFi, USB, similar look as the ATV2.

TC8901 don't have mali gpu ... so no go

McGeagh · (This post was last modified: 2011-04-27, 11:55 by McGeagh.)

The TCC890x series (including TCC8901) DOES in fact have the Mali GPU (Mali-200 specifically)

Its the same as whats in the HDX Bone

KRavEN · 2011-04-27, 13:47

McGeagh Wrote:The TCC890x series (including TCC8901) DOES in fact have the Mali GPU (Mali-200 specifically)

Its the same as whats in the HDX Bone

So that box should be able to run XBMC arm port?

McGeagh · 2011-04-27, 16:42

Not at the moment because we dont have none-X supported yet So far only Phusho has the relevant changes to make it work (correct me if im wrong)

phusho · 2011-05-03, 11:06

McGeagh Wrote:The TCC890x series (including TCC8901) DOES in fact have the Mali GPU (Mali-200 specifically)

Its the same as whats in the HDX Bone

actually not 8901 don't have but 8902 and 8903 have mali gpu Wink

we are official tcc users so i have direct contacts with telechips ....

difference between 8902/3 and 8900 is that they don't have lvds interface and 8902 don't have serial ata ....

and HDX Bone is 8900 chip I have one

All chips are pin to pin compatible

madmalkav · (This post was last modified: 2011-05-14, 19:01 by madmalkav.)

Anyone have tried with an Amlogic based device? I just discovered that SoC producer because some interesting price/performance tablets using their chips and there seems to be some dirty cheap boxes that can be fun to try to hack. If will prefer not to buy one of those blindy but if noone have tried them I probably will go for it and see what I can get.

**Starstream** · 2011-05-14, 19:06

madmalkav Wrote:Anyone have tried any made any try with an Amlogic based device? I just discovered that SoC producer because some interesting price/performance tablets using their chips and there seems to be some dirty cheap boxes that can be fun to try to hack. If will prefer not to buy one of those blindy but if noone have tried them I probably will go for it and see what I can get.

Amlogic have their own OpenLinux Arm Wiki with lots of info, don't know if it was setup by them (their commercial site has next to nothing), the platform section seems to imply they are packing Cortex A9 with Mali400 on some of the chips.

The Amlogic AML8726-M is a Cortex A9 with Mali400 GPU , there might be some stuff out there, some of the known Amlogic media boxes on the market are older chipsets based off the 86xx series.

Some Amlogic players offer the source code like the Ferguson Ariva HDplayer 200a.

madmalkav · 2011-05-14, 19:17

Didn't knew about that Ariva players, thanks for the tip.

I have been reading about 8726 because I have been considering to buy a tablet based on it. Now I found a cheap chinese player based on it, I'm considering buying it for trying some hacking and get it running vanilla arm linux distribution. The only thing I miss in the device is an ethernet port, but I'm probably go for it anyway.

By the way, yeah, the sources web is official from Amlogic, so good to see this SoC producer shows some respect for GPL, ot like Rockchip and others...