Building LeMaker Android 4.2 from Source

liab · Post time Dec 05, 2014 12:16

The reason for the fool cpu core is to search in lichee/linux-3.4. I used the linux-3.4 from the good matthuisman/android an now the second cpu is also in lemaker busy.

root@android:/ # [ 24.092414] init: untracked pid 1546 exited
mpstat -P ALL
Linux 3.4.39 (localhost)       12/05/14       _armv7l_       (2 CPU)

18:12:06    CPU %usr %nice %sys %iowait %irq %soft  %steal  %guest %idle
18:12:06    all 14.23 0.00 7.88 44.04 0.00 0.86 0.00 0.00 32.99
18:12:06    0 9.21 0.00 8.27 31.36 0.00 1.73 0.00 0.00 49.44
18:12:06    1 19.25 0.00 7.50 56.67 0.00 0.00 0.00 0.00 16.59
root@android:/ #

mattrix · Post time Dec 05, 2014 12:22

Edited by mattrix at Fri Dec 5, 2014 13:10

So, Lemaker Source is OK then?

Oh, I see. You swapped out the Kernel and then it worked.

liab · Post time Dec 05, 2014 14:01

Edited by liab at Fri Dec 5, 2014 14:27

Unfortunately it's not useful to take the other linux, the lemaker image remains slow.

Streamig with vu+ in hd will crash after a short time.

The second in this compilation is, LAN seems ok, but will not work. *) It has a MAC address. WLAN works.

So the best image for me is matthuisman/android.

*) Edit: A ping via LAN is ok, but starting an app needing network makes an error.

ChrisP · Post time Dec 05, 2014 16:56

Edited by ChrisP at Sat Dec 6, 2014 18:48

Here is the result I had from Antutu Benchmark on various image. The first one is the first version from Mattrix derived from the official Android 4.2.2. The second one is a test on image generated from LeMaker SDK. The third was on image generated from SDK2. The last one was the one done after I believed to have successfully implemented r5p0 mali driver.

memory	integer	float	score2d	scored3d	database	sram	svm	srs	smt	snand	ints	floats	score	date	cpu	model
584	554	694	710	2538	445	988	798	0	2059	411	703	761	11245	2014-11-28 02:40	1056 MHz (x2)	4.2 Clean Mattrix version\STOCK-MOD.img
567	543	671	671	2393	325	900	750	0	1946	427	699	769	10661	2014-12-04 16:52	1056 MHz (x2)	Build 4.2 from LeMaker SDK\bpi_android.img
506	478	598	698	2587	405	961	676	0	1644	352	606	663	10174	2014-11-28 01:54	1056 MHz (x2)	SDK2\bpi_android.img
501	475	595	787	2834	435	1099	683	0	1777	303	606	663	10758	2014-11-28 07:11	1056 MHz (x2)	SDK2\ChrisP-1.11-SDK2.img
577	546	666	775	2785	325	1010	767	0	1858	467	700	769	11245	2014-12-07 01:45	1056 MHz (x2)	Build 4.2 from LeMaker SDK\bpi_android-RAM480.img

ChrisP · Post time Dec 05, 2014 17:00

Edited by ChrisP at Sat Dec 6, 2014 00:06

I think I found the most important part that explain different behavior regarding memory/integer/float:

LeMaker sources have this value in fex file:
dram_clk = 432

where SDK 2 had:
dram_clk = 480

But I don't get where could the video increase in my last SDK 2 image come from. I'll republish a fixed version for investigation.

It was maybe a little precipitated to remove old SDK2 git repository, it could have been usefull for investigation :/

liab · Post time Dec 05, 2014 18:17

Edited by liab at Fri Dec 5, 2014 19:10

Just I found out, a fresh burned lemaker image works in fact with 2 CPU's. But after 1 minute
after it automatic installs something one CPU is lost! What is that?

root@android:/ # mpstat -P ALL
Linux 3.4.39 (localhost)       12/06/14       _armv7l_       (2 CPU)

00:14:05    CPU %usr %nice %sys %iowait %irq %soft  %steal  %guest %idle
00:14:05    all 18.68 4.51 15.46 30.30 0.00 1.94 0.00 0.00 29.10
00:14:05    0 16.36 3.41 18.01 21.70 0.00 3.81 0.00 0.00 36.71
00:14:05    1 21.08 5.64 12.84 39.19 0.00 0.01 0.00 0.00 21.23
root@android:/ # mpstat -P ALL
Linux 3.4.39 (localhost)       12/06/14       _armv7l_       (1 CPU)

00:15:27    CPU %usr %nice %sys %iowait %irq %soft  %steal  %guest %idle
00:15:27    all 17.46 4.40 14.33 31.06 0.00 1.95 0.00 0.00 30.80
00:15:27    0 15.61 3.44 16.85 22.10 0.00 3.84 0.00 0.00 38.14
root@android:/ #

Edit: Now I saw suddenly there are 2 CPU's again. Perhaps it have something to do with
the powermanagement. If nothing to do 1 CPU and if it's needed 2 CPU's are working.

tony_zhang · Post time Dec 05, 2014 21:32

ChrisP replied at Fri Dec 5, 2014 17:00
I think I found the most important part that explain different behavior regarding memory/integer/flo ...

In order to be more stable, I set the dram frequency to 432MHz. Though the 480 can result better performance.

tony_zhang · Post time Dec 05, 2014 21:32

Edited by tony_zhang at Fri Dec 5, 2014 21:33

liab replied at Fri Dec 5, 2014 18:17
Just I found out, a fresh burned lemaker image works in fact with 2 CPU's. But after 1 minute
after ...

I think the Android power management auto select cpu.

ChrisP · Post time Dec 06, 2014 11:50

Just updated the benchmark list, which show that both cores are working fine with this SDK. Going to 480 MHz allow to go back to hugher performance of the best past images.

But 1080p is still no go

dlanor · Post time Dec 06, 2014 16:45

I'm not sure exactly what you mean by 'no go', but it is an unavoidable speed problem that 1080p involves 2.25 times the amount of pixels per screen, as compared to 720p. And thus it also involves 2.25 times the amount of screen RAM to be processed in each full screen update. That will always have a huge impact on overall speed, reducing it drastically. So 720p is probably the highest resolution that will give us satisfactory speed.

Best regards: dlanor

Login

Building LeMaker Android 4.2 from Source

Building LeMaker Android 4.2 from Source