Database Users

GLBenchmark Results!

I've tried to overclock, lagfix, change roms and kernels, but I didn't see any big difference.
I would like to stay with real FPS benchmarks like GLBenchmark or others not like quadrant.
I've seen many people using ext2 instead of ext4, other say rfs is better, so I'm getting very confused. And also many people around here.
Each one of us has got a personalized SGS. Let's run each one of us GLBenchmark OpenGl 2.0 test without FSAA (The one of egypt) and see the results of each one of us.
Dlownload glbenchmark here: http://www.glbenchmark.com/download.jsp
Please specify model, rom, kernel, launcher, running apps, free mem before doing the test... Like every bit of info you can give, so we could find the best settings!
Thanks to all ! I'll run the test and post in few minutes!

Ok, here is the template 1.0 to use ;P just copy and paste and modify!
OK, got:
2438 Frames (21.6 Fps) with no fsaa.
My settings:
MODEL: European, I9000 SGS 16gb Vodafone
SPEED (GHZ): 1.0
LAUNCHER: Go Launcher
KERNEL: Lastest speed mod.
ROM: Darky's 8.0
LAGFIXES: On, System converted, on fast mount.
PROGRAMS INSTALLED: Very few, just wiped it.
FREE RAM: I forgot!
OTHER INFO: Wifi on, and overclock @ 1.2 makes worse FPS.

Lagfix will have no effect on glbench
Sent from my GT-I9000 using XDA App

Bench marks do not say how responsive or laggy the phone is and unless you are obsessive with numbers are a waste of time .
jje

yes, but games performance is equal to FPS, so more FPS=More optimized system.
Just because that reason i proposed to use glbenchmark, as it is an only graphical test.

Best rom for quadrant scores ?

Most roms that I`ve tried (CM7 based and MIUI) perform a bit slow in quadrant (1000-1250) ,
and I`ve seen hd2`s with over 2000 , 3000 and even closing near 4000 .
I want the device to enter to a database of quadrant scores I have in my forum ,
if anyone could recommend any good roms for this purpose I`d appreciate it .
Thanks ,
Danny .

Try coredroid 1.6 and make a overclock!

Quadrant scores as has been said countless times does not mean that the actual build in question is necessarily faster (or more stable) than another build where it might score a lower Quadrant score it is just a benchmark and should not be taken as meaning the build is blazing fast, a build i had about 7 months ago had a score about 2250 yet the build i have on my phone now Hyperdroid CM7 is considerably faster and more stable and the Quadrant score is about 1300 but it doesn't bother me in the slightest.

why do you want a synthetic benchmark rating system to tell you how fast your device isnt?

Virtuous XooM v1.1.2 HC 3.2 Benchmarks very nice rom

I installed this rom the other day and so far everything works except the screen rotation lock button but no rom has that working.
Frst its HC 3.2 ported over from the xoom has the new feature of being able to upscall the smaller apps to the larger screen.
Over clocking is built in just get set cpu and off you go.
My acer is over clocked to 1.5 and here are my benchmark scores.
Useing Quadrant I got 3421 (best of three runs) and frame rates around 45
Useing Linpack I got 45.438 mflpos on single thread in 1.85 seconds and
71.53 mflops on multi-thread in 2.36 seconds again best of three runs
Useing AnTuTu Benchmark I got a score of 6159 and frame rates right at around 60 fps
Useing Vellamo (its new and a benchmark tool for a tablets browser to see how ell the browser performs does things like java and flash stress tests and load speeds of web pages) I got a score of 1072
These are the top 4 bench mark tools for android and these scores while may not look impressive are awsome. in comparisons on benchmark tools grafs these score are much higher them most tablets.
bottom line this tablet rocks.
If your into benchmarking and tweaking as I am please post your results here list benchmark toos used,scores and with rom your running and cpu speed. so we can get and over all view of this remarkable tablet.

I got 1291 from Vellamo using Stock 3.1 with custom Kernel Taboonay CPU 1408Mhz

same rom, same oc, similar scores XD this tablet does rock!!!!!!

ROM & KERNEL Performance discussion for Galaxy S I9000

Hi,
Now a days everyday there is new ROM for Samsung Galaxy S GT-I9000 released.
It is very difficult for a person to choose one from the list.
So, I started the thread for discussion of ROM & KERNEL Performance, experience, Problems and Troubleshooting advises.
Participate and share your experience for each ROM you use.
Submit your Quadrant Score with ROM & KERNEL Details.
Thanks & Regards,
-niemesh

Doctorz ROM
I am using Doctorz ROM which I found very good and stable with good inbuilt applications

1. What is KERNAL?
2. Why use Quadrant to measure performance?
Sent from my GT-I9000

KERNEL is a bridge between applications and the actual data processing done at the hardware level
Quadrant Standard is used for measuring performance of android mobile.

sry but by using quadrant to verify a rom speed you are disqualifying yourself

i din't say quadrant used to verify rom speed. I told that it is a standard for measuring Android mobile speed. being specific quadrant is benchmark for mobile performance for data writing, reading, 2D, 3D, etc.
I included quadrant in this post as the quadrant scores are different from rom to rom due to its data processing ability.

Quadrant is a random number generator, useless. there are other bench tools around but i dont really care about those tools. as long as my SGS performs for me fast and smooth i dont care about any bench results.
JVT kernels are similar to each other. so suggest Semaphore, Galaxian or TalonDev. me using last one.
JVT rom is up to you and your theme choice. all are fast and smooth. the more its customized the more problems you can get. I use almost stock. all working great and fast even battery life is good.

[BENCHMARK] GN2 kernels benchmarks

These are the result of the benchmarks done to the kernels that are being developed (4 Apr 2013) for the Samsung Galaxy Note 2 .
The settings used are the default that come with N7100XXDMB6 on a GN2 baseband N7100XXDLK7. The changes from the stock areas follows , rooted, TWrecovery 2.3.3.2 , 240 dpi. Brightness used during test 100 %, WiFi on, Nova Launcher Pro, Force GPU rendering (enabled) under Developer options, Power saving option OFF, GPS off , Screen rotation on, sound on 100%, multiwindow active.
Kernels used Stock mb6, Perseus 34.2, Adam 2.2.1 , Neak 1.7
Applications used 3dMark 1.0.0-875 , RL Benchmark:SQLite 1.3 , Vellamo 2.0.2 , CF-Bench 1.2 , AnTuTu Benchmark 3.2.2 , PowerTutor 1.4
Addition applications Linpack for Android 1.2.8, Pi Benchmark 1.0, Quadrant Standart 2.1.1, Geekbench2 2.4.2, SD Tools 3.0.
Methodology used : The benchmarks were run in sequence 1 minutes after a clean reboot was done (cleaning cache and dalvik-cache).
Explanation about the results,
3dMark has 2 scores the first is the normal and the second the extreme suite (Higher is better).
RL Benchmark:SQLite measures the time in seconds needed to dullfill the tests incuded ( smaller is better).
Vellamo has two scores first is HTML5 and second is the metal suite score ( Higher is better).
CF-Bench has three scores first is native score, second is java score and third is overall score ( Higher is better).
AnTuTu just the overall result ( Higher is better).
PowerTutor measures the power usage in milliWatt for the last 5 minutes ( smaller is better).
Linpcack for Android measures floating point performance of the system , has two numbers first is single thread second is multi threaded score in Mflops (higher is better).
Pi benchmark measures the time in seconds to calculate pi, I settled for 200 000 numbers ( smaller is better).
Quadrant Standart 2.1.1 ( higher better).
Geekbench2 2.4.2 cross platform bench ( higher better).
SD Tools measures the read and write speed in Mb/s from the sdcard, first number is writting speed second is read speed (higher better).
Results :
Stock MB6
3dMark 3339x2502
Sql 14.837
Vellamo 1763x610
CFbench 26604x7402x15082
Antutu 16979
Powertutor 803 mW
Perseus 34.2
3dMark 3034x2305
Sql 14.482
Vellamo 1743x612
CFbench 26027x7407x14855
Antutu 17140
Powertutor 816
Adam2.2.1
3dMark 3203x2421
Sql 20.406
Vellamo 1776x619
CFbench 26253x7423x14955
Antutu 17311
Powertutor 805
Neak 1.7
3dMark 3199x2432
Sql 15.855
Vellamo 1710x624
CFbench 26934x7558x15308
Antutu 15911
Powertutor 810
Stock MB5
3dMark 3312x2476
Sql 14.54
Vellamo 1753x610
CFbench 25915x7355x14779
Antutu 17268
PowerTutor 807 mW
Stock MC3
3dMark 3282x2474
Sql 15.181
Vellamo 1768x599
CFBench 26544x7652x15208
Antutu 17024
PowerTutor 502 mW
Linpack 64 x 211
Pi 200 000 53.67
QuadrantS 6991
Geekbench 2059
SD Tools 6.0x12.5
Abyss 2.3.1
3dMark 3200x2387
Sql 14.334
Vellamo 1740x619
CFBench 25870x7077x14595
Antutu 16780
PowerTutor 500 mW
Linpack 62 x 68
Pi benchmark 53.29
QuadrantS 7149
Geekbench 2105
SdTools 6.2x14.9
RedPill 1.42
3dMark 3145x2379
Sql 16.854
Vellamo 1502x618
CFBench 25297x7373x14542
Antutu 16927
PowerTutor 501 mw
Linpack 62x129
Pi benchmark 53.12 s
QuadrantS 6635
Geekbench 2005
SdTools 6.4x12.8 Mb/s
Devil 0.12
3dMark 3177x2315
Sql 14.668
Vellamo 1744x604
CFBench 24850x7335x14341
Antutu 17227
PowerTutor 508
Linpack 64x124
Pi benchmark 53.79
Quadrant S 6661
Geekbench 1696
SdTools 5.8x12.6
The intention of these test is to show the devs their strength/weakness regarding the benchmarks area. These benchmarks are purely synthetic which means they DO NOT represent real life scenario usage.
I am opened to every suggestion possible for further monthly or bimonthly benchs.
Edit: For accuracy have to clarify that about the difference in results with PowerTutor due to removing of an application that used exactly 300 mw the results of the recent test show 300 mw less than the previous ones.

Adam Kernel
Thanks, good job
Would you prefer the Adam Kernel ?

dianlb50 said:
Thanks, good job
Would you prefer the Adam Kernel ?
Click to expand...
Click to collapse
Stock has given me no problems so far, it seems it gives a perfect middle point for my usage, as for the optimizations done to specific kernels, the efforts of the dev is not well represented in the results of such simple bench tests bcs the results are within margins of error of such test, but again have to stress out that these are purely synthetic benchs therefore DO NOT apply to real life scenarios.

Here you go fully stock non-rooted xxDMB5.

hagba said:
Here you go fully stock non-rooted xxDMB5.
Click to expand...
Click to collapse
Added results for the Stock MB5 on the OP.

Added results for Stock MC3 , RedPill and Abyss kernels. plus some additional benchmark tools.

Stock DMB5, Perseus Kernel
@ 1.8 ghz.
Sent from my GT-N7100 using xda premium

The point of the tests is to compare the kernels performance side by side in the same environment/setup in MY device, using the DEFAULT settings (no tweaking or OC) with which they are delivered to end user, and if you are careful to notice, I have included MORE than just a simple Antutu result aiming to be as close as possible to real usage scenarios.

abauer said:
The point of the tests is to compare the kernels performance side by side in the same environment/setup in MY device, using the DEFAULT settings (no tweaking or OC) with which they are delivered to end user, and if you are careful to notice, I have included MORE than just a simple Antutu result aiming to be as close as possible to real usage scenarios.
Click to expand...
Click to collapse
My bad, but the OP is TL;DR.
Sent from my GT-N7100 using xda premium

ThankS for posting
Sent from my GT-N7100 using xda premium

Added Devil kernel results.

Perseus 35
Geekbench
Quadrant
Sql

Antutu
Sent from my GT-N7100 using Tapatalk 2