ICS Roms Benchmarked

Search This thread
By:
Advanced…
H

horndroid

Senior Member
Jan 30, 2012
542
182
San Francisco
Used Quadrant Standard Edition 2.0
This was done on 3-28-2012. Pretty much all the ROMs have had new releases since then. So these benchmarks do not accurately reflect the current performance of the ROMs.
Full wipe procedure done before each flash.
Coldboot done for each ROM before running Quadrant. Not doing coldboot resulted in lower I/O score in some cases.

Testing was done using the default settings and kernel of the ROM. No kernels were flashed separately.
Overclock was tested only if the ROM and its default kernel supported it, using the maximum frequency allowed in the ROM's settings + force GPU rendering set to enable in developer settings.

ggNdV.gif


8Bgvh.gif


5KpX8.gif


L8DPu.gif


WHxkc.gif


4CQN9.gif


Android 4.0.4 ROM

YmENS.gif
 
Last edited:
  • Like
Reactions: myeepad, Sir Flashalot, kevhuff and 4 others
C

cspiby

Senior Member
Jun 10, 2011
478
34
What the hell is going on with the 2D scores? Why is stock so far ahead of the others?
 
Goatshocker

Goatshocker

Senior Member
Oct 23, 2010
945
416
I dont have any fancy diagrams or tables like you but...
I ran quadrant on eos build 12 and got a total of 3.5k (average, 3 runs).

Settings: CPU at 1.4Ghz, no forced gpu rendering.
Breakdown:
cpu: 6200
memory: 3200
I/O: 6000
2D: 110
3D: 1800

Interesting though that stock ICS performs that well compared to the other roms.
So in raw performance there isnt much difference between custom and stock rom, until you start tuning the cpu.
 
H

horndroid

Senior Member
Jan 30, 2012
542
182
San Francisco
Yup, the reason EOS and CM9 have such high scores is because of the I/O. I wonder how perceivable the difference is to an average user.

Team EOS's has a tiny FPS lag when scrolling home screens despite its high score.
 
A

asdfuogh

Senior Member
Jun 22, 2011
573
66
Looks like the forced GPU rendering didn't score as high this time though; do you know the explanation? Just curious, not particular adept at computer stuff so unnecessary to answer if you don't have time..
 
H

horndroid

Senior Member
Jan 30, 2012
542
182
San Francisco
asdfuogh said:
Looks like the forced GPU rendering didn't score as high this time though; do you know the explanation? Just curious, not particular adept at computer stuff so unnecessary to answer if you don't have time..
Click to expand...
Click to collapse

I don't think you should give much thought to those minor differences.
The scores fluctuate way too much. Honestly, only 3 attempts don't give accurate averages.
 
M

mattcoz

Senior Member
Dec 26, 2007
417
23
Chicago
asdfuogh said:
Looks like the forced GPU rendering didn't score as high this time though; do you know the explanation? Just curious, not particular adept at computer stuff so unnecessary to answer if you don't have time..
Click to expand...
Click to collapse
Looks to me like it scored 8 higher... or are you comparing to the score when overclocked to 1.64GHz?
 
J

justmara

Senior Member
Feb 21, 2011
68
2
DammedKiller said:
I was waiting to the Frozn release but comparing its benchamark with the CM9 ones I think that I am going to continue using CM9.
Click to expand...
Click to collapse

yep. just checked on my cm9 with test8 kernel @ 1,7Ghz:
total: 4185, cpu: 8230, mem: 3274, io: 7466, 2d: 121, 3d: 1834
(2d is low, because 'force 2d' makes some apps flicker and also lowers all other stats in this bench ;) )
so I think I'll stay on CM9
 
You must log in or register to reply here.

Similar threads

Gary Key
Official ASUS Thread - ICS Update on TF101 (20-Mar-2012)
Replies
4K
Views
804K
pilotn
pilotn
oka1
READ THIS NOW !!!•••POST ALL ICS AND ICS RELATED INFO HERE ONLY !!!!!
Replies
570
Views
152K
T
thumbslinger
E
Root ASUS Transformer TF101 On Android 4.0.3 ICS
Replies
14
Views
128K
RLShiftyDoggit
RLShiftyDoggit
I
  • Poll
[TOOL]"1-Click Transformer Root"-Root/Unroot/cwm/stock rec-TF101(G)/201/300T(G)/SL101
Replies
801
Views
654K
M
mr_fosi
jparity
  • Poll
ICS Updates (Not) Fixing Random Reboot and Other Problems
Replies
564
Views
112K
M
maddoxtj

Top Liked Posts

24 Hours All time
  • There are no posts matching your filters.
  • 7
    H
    horndroid
    Used Quadrant Standard Edition 2.0
    This was done on 3-28-2012. Pretty much all the ROMs have had new releases since then. So these benchmarks do not accurately reflect the current performance of the ROMs.
    Full wipe procedure done before each flash.
    Coldboot done for each ROM before running Quadrant. Not doing coldboot resulted in lower I/O score in some cases.

    Testing was done using the default settings and kernel of the ROM. No kernels were flashed separately.
    Overclock was tested only if the ROM and its default kernel supported it, using the maximum frequency allowed in the ROM's settings + force GPU rendering set to enable in developer settings.

    ggNdV.gif


    8Bgvh.gif


    5KpX8.gif


    L8DPu.gif


    WHxkc.gif


    4CQN9.gif


    Android 4.0.4 ROM

    YmENS.gif
    View
    4
    H
    horndroid
    There wasn't really any performance increase in 4.0.4. The changes probably had to do with something else.

    CM9 March 28 version + stock kernel
    daAcL.gif

    CM9 March 29 version(Android 4.0.4) + stock kernel
    YmENS.gif
    View
    3
    H
    horndroid
    JtxZ8.gif
    View
    1
    H
    horndroid
    Here's what I got. Pretty much same as yours.
    kdeAS.gif
    View

New posts