00:23
vagrantc has quit [Quit: leaving]
00:34
mac-l1 has quit [Quit: Page closed]
00:39
lkcl has quit [Ping timeout: 240 seconds]
00:43
descend has joined #linux-rockchip
01:01
lkcl has joined #linux-rockchip
01:46
Laibsch has quit [Quit: Leaving.]
02:00
cnxsoft has joined #linux-rockchip
02:55
muvlon has quit [Remote host closed the connection]
03:03
ganbold_ has joined #linux-rockchip
03:03
sjg1__ has joined #linux-rockchip
03:04
daniels_ has joined #linux-rockchip
03:06
fullstop_ has joined #linux-rockchip
03:06
dlezcano- has joined #linux-rockchip
03:06
diego71_ has joined #linux-rockchip
03:07
ganbold has quit [Ping timeout: 255 seconds]
03:07
sjg1_ has quit [Ping timeout: 255 seconds]
03:07
dlezcano has quit [Ping timeout: 255 seconds]
03:07
diego71 has quit [Ping timeout: 255 seconds]
03:07
hramrach has quit [Ping timeout: 255 seconds]
03:07
daniels has quit [Ping timeout: 255 seconds]
03:07
fullstop has quit [Ping timeout: 255 seconds]
03:07
mrueg has quit [Ping timeout: 255 seconds]
03:07
pozzoni has quit [Ping timeout: 255 seconds]
03:07
pozzoni_ has joined #linux-rockchip
03:07
sjg1__ is now known as sjg1_
03:07
pozzoni_ is now known as pozzoni
03:08
mrueg has joined #linux-rockchip
03:08
hramrach has joined #linux-rockchip
03:09
daniels_ is now known as daniels
03:14
muvlon has joined #linux-rockchip
05:38
cnxsoft1 has joined #linux-rockchip
05:41
cnxsoft has quit [Ping timeout: 252 seconds]
05:41
cnxsoft1 is now known as cnxsoft
05:45
stdint has quit [Ping timeout: 252 seconds]
05:50
stdint has joined #linux-rockchip
05:51
beeno has joined #linux-rockchip
06:18
muvlon has quit [Ping timeout: 245 seconds]
06:18
wzyy2 has joined #linux-rockchip
06:30
muvlon has joined #linux-rockchip
06:51
nighty has joined #linux-rockchip
06:52
Myy has joined #linux-rockchip
07:05
rperier has quit [Ping timeout: 245 seconds]
07:07
rperier has joined #linux-rockchip
07:22
Omegamoon has joined #linux-rockchip
07:28
<
LongChair >
stdint: morning
07:29
<
LongChair >
can you tell me more about that task API ? does it make a big difference compared to the regular MPP/MPI API ?
07:29
<
stdint >
just let me have a look on your code
07:29
<
stdint >
if you follow the unit test code, it would be token(task) version
07:30
<
stdint >
but if you look into the vpu api, you would know the parallel version of mpi
07:34
<
LongChair >
yeah i had a look at that one ... that make quite a lot more code
07:34
<
LongChair >
so I am wondering if that makes a real difference as i don't really need to decode 2 videos at the same time
07:35
<
LongChair >
if performance is the same, i'd probably stick with the current code as it looks way simpler
07:37
wadim_ has joined #linux-rockchip
07:38
<
LongChair >
so my first question will be, if we only need one decoding at a time, would it make any difference using that API ?
07:46
holin has joined #linux-rockchip
08:19
<
Omegamoon >
I am getting these... Kernel panic - not syncing: hung_task: blocked tasks
08:20
<
Omegamoon >
not pretty :-(
08:21
<
Omegamoon >
any idea where to look for the cause of this?
09:17
<
stdint >
LongChair, it is hard to talk about the task
09:17
<
stdint >
just look into vpu_api_legacy to see how the non-token version work
09:32
wzyy2 has quit [Read error: Connection reset by peer]
09:35
wzyy2 has joined #linux-rockchip
09:38
nighty has quit [Quit: Disappears in a puff of smoke]
09:47
premoboss has joined #linux-rockchip
09:51
wzyy2 has quit [Read error: Connection reset by peer]
10:00
andoma has quit [Ping timeout: 240 seconds]
10:00
andoma has joined #linux-rockchip
10:06
paulk-blaze has joined #linux-rockchip
10:12
andoma has quit [Ping timeout: 260 seconds]
10:18
paulk-blaze has quit [Ping timeout: 260 seconds]
10:19
scelestic has joined #linux-rockchip
10:20
andoma has joined #linux-rockchip
10:22
paulk-blaze has joined #linux-rockchip
10:30
nighty has joined #linux-rockchip
10:34
paulk-blaze has quit [Ping timeout: 240 seconds]
10:36
paulk-blaze has joined #linux-rockchip
10:56
lerc has joined #linux-rockchip
11:01
premoboss has quit [Ping timeout: 245 seconds]
11:09
paulk-blaze has quit [Remote host closed the connection]
11:09
paulk-blaze has joined #linux-rockchip
11:10
lkcl has quit [Ping timeout: 260 seconds]
11:14
Myy has quit [Quit: Leaving]
11:29
paulk-blaze has quit [Quit: Leaving]
11:32
mrueg has quit [Ping timeout: 255 seconds]
11:33
mrueg has joined #linux-rockchip
12:01
paulk-collins has joined #linux-rockchip
12:46
zzarr has joined #linux-rockchip
12:53
premoboss has joined #linux-rockchip
13:16
premoboss has quit [Ping timeout: 240 seconds]
13:29
premoboss has joined #linux-rockchip
13:54
<
LongWork >
stdint: i can look at the code, bu i just want to know what's the benefits of using that more complex API vs the simple one
13:56
<
LongWork >
you seemed to mention it was bringing better performance ... is it like significant ?
13:56
<
LongWork >
if we're talking about 5% more then it's probably not worth changing everything
13:56
<
LongWork >
if it's like 50% more, then i need to consider it
14:01
cnxsoft has quit [Quit: cnxsoft]
14:09
premoboss has quit [Ping timeout: 260 seconds]
14:22
premoboss has joined #linux-rockchip
14:22
<
ayaka >
I am not sure about performance as I never compare them
14:25
<
LongWork >
i seem to be able to get 4K@24p about consistently
14:25
<
LongWork >
4K@30 is already pretty tough ...
14:30
irsol has quit [Ping timeout: 260 seconds]
14:47
premoboss has quit [Ping timeout: 240 seconds]
14:50
holin has quit [Quit: leaving]
14:53
JohnDoe_71Rus has joined #linux-rockchip
14:56
tlwoerner has quit [Quit: Leaving]
15:21
<
ayaka >
I think the 4K@60fps is not a problem with mpp
15:21
<
ayaka >
if the display screen is just 1920x1080
15:36
wadim_ has quit [Remote host closed the connection]
15:44
tlwoerner has joined #linux-rockchip
16:40
<
LongWork >
ayaka: this is my current config and i can't hold 60 fps
16:41
<
LongWork >
ayaka: i'd be iterested in you looking at my code, see if you can spot anything fishy
16:41
<
phh >
LongWork: possibly miniarm's clock aren't properly set :s
16:41
<
LongWork >
which clocks ?
16:41
<
LongWork >
i'm using the miniarm dts file in rk repo ...
16:42
<
phh >
don't know, could be RAM or vpu
16:42
<
phh >
can you hdparm -T ?
16:42
<
phh >
this will bench linear ram performance
16:42
<
LongWork >
if you tell me how to do that sure :)
16:43
<
LongWork >
because that doesn't sound familiar :)
16:43
<
phh >
hdparm -T /dev/mmcblk0
16:44
premoboss has joined #linux-rockchip
16:44
<
LongWork >
hmmm does hdparam come with any package .. cuz i don't seem to have it
16:45
<
phh >
it comes in hdparm
16:45
<
phh >
please note it's parm not param
16:47
<
LongWork >
installed hdparm package but no hdparm binary there
16:48
<
LongWork >
hold on found it
16:49
<
LongWork >
linaro@linaro-alip:~$ sudo /sbin/hdparm -T /dev/mmcblk0
16:49
<
LongWork >
Timing cached reads: 1740 MB in 2.00 seconds = 870.37 MB/sec
16:49
<
LongWork >
/dev/mmcblk0:
16:49
<
LongWork >
how is that ? :p
16:50
<
LongWork >
somehow it looks like a good news that it sucks :)
16:51
<
phh >
LongWork: how many RAM chips does the board have?
16:51
<
phh >
oh wait I can check photos of it
16:51
<
phh >
that's not the question :P
16:52
<
LongWork >
oh ram chips ... no idea
16:52
<
phh >
noone took a photo underneath -_-'
16:53
<
phh >
I don't see any RAM
16:53
<
ayaka >
memory frequency is set in u-boot
16:54
<
LongWork >
i more likely use the tinekr image uboot as i only replaced the dts & zImage with a recent one
16:54
<
LongWork >
not sure what they have put there
16:55
<
LongWork >
i suppose there is no way to update only uboot ?
16:57
<
phh >
ok actually my chromebook also has ~ 900MB/s
17:07
utente has joined #linux-rockchip
17:09
<
LongWork >
so that would look like a normal bandwith ?
17:10
premoboss has quit [Ping timeout: 240 seconds]
17:19
utente__ has joined #linux-rockchip
17:22
irsol has joined #linux-rockchip
17:22
utente has quit [Ping timeout: 260 seconds]
17:24
<
phh >
(3840*2048*2*60)/(1024*1024) = 960
17:24
<
LongWork >
So it looks a bit short
17:25
<
LongWork >
in mpv if i remove framedropping, i can see that it would decode about 30-40 fps (visual estimation), but with framedrop, it's basically dropping 1 frame over 2 .. :/
17:25
<
LongWork >
24 fps looks ok
17:25
<
LongWork >
30 fps depends ...
17:26
<
LongWork >
mostly on bitrate
17:26
<
phh >
"a bit short" ? you mean there is a x2 ratio missing
17:26
<
phh >
you need both to read and to write
17:26
<
LongWork >
kinda true
17:27
<
LongWork >
phh : i'm displayng only in 1080p at this point
17:27
<
LongWork >
so write operation requires prbably much less bandwith
17:27
<
phh >
LongWork: ok, but it's the VOP/DRM who does the scaling atm?
17:27
<
LongWork >
probably, i'm using the drm stuff behind, so not sure who is doing the jb
17:27
<
LongWork >
phh: i'd be curious to see what kind of performance you can get out of gstreamer on 4K video
17:28
<
LongWork >
but if i recall what you said you can't get vpu-service on those
17:28
<
phh >
I still haven't got a device where I have a fully working vpu/hevc... I have tried with mainline, but it doesn't work, and it still couldn't boot rockchip's 4.4 on my tvbox...
17:28
<
phh >
LongWork: but testing gstreamer should be easy for you, what's your problem with it?
17:29
<
LongWork >
i didn't build it, and i don't know if getting it from a package will have the recent vpu stuff
17:30
<
LongWork >
is there a package already for the gst vpu thing ?
17:32
<
LongWork >
so that deb pkg is all i need ?
17:34
<
LongWork >
sudo dpkg -i gstreamer1.0-rockchip1_1.10-4_armhf.deb
17:34
<
LongWork >
dpkg-deb: error: `gstreamer1.0-rockchip1_1.10-4_armhf.deb' is not a debian format archive
17:37
<
LongWork >
am i doing anything wrong there ?
17:42
<
phh >
you download by right clicking download? :P
17:42
<
phh >
you need to click on the link which links to a webpage
17:42
<
phh >
then download
17:50
<
LongWork >
i seem to have deps problem to install all that
17:51
<
LongWork >
like libstdc++6 to start with
17:51
<
LongWork >
for some reasons it says i have a too old version
17:51
<
LongWork >
librockchip-mpp1 : Depends: libstdc++6 (>= 5) but 4.9.2-10 is to be installed
17:51
<
LongWork >
i'm not sure if i want to break my current devenv
17:52
<
LongWork >
i think it's because i have the defualt gcc installed which comes with 4.9 stuff
18:01
<
LongWork >
yeah looks like build-essential comes with everything in 4.9
18:01
<
LongWork >
and that all the gst / mpp / vpu packages require >= 5
18:01
<
LongWork >
kinda sad
18:46
fullstop_ is now known as fullstop
19:05
beeno has quit [Ping timeout: 240 seconds]
19:28
utente has joined #linux-rockchip
19:31
Omegamoon has left #linux-rockchip [#linux-rockchip]
19:31
utente__ has quit [Ping timeout: 260 seconds]
19:45
vagrantc has joined #linux-rockchip
20:07
utente has quit [Ping timeout: 256 seconds]
21:10
lkcl has joined #linux-rockchip
21:35
zzarr has quit [Quit: This computer has gone to sleep]
22:01
irsol has quit [Ping timeout: 240 seconds]
22:47
paulk-collins has quit [Quit: Leaving]
22:54
irsol has joined #linux-rockchip
23:54
nighty has quit [Quit: Disappears in a puff of smoke]
23:57
vagrantc has quit [Quit: leaving]