Database Users

Post your official Froyo /Gingerbread bechmarks here (without lagfix)

post your official froyo / Gingerbread bechmarks here (without lagfix)
if you got upgrade via kies

Got jp6 trough norwegian kies
1020 is highest before lagfix
2015 is highest after oclf lagfix
Sent from my GT-I9000 using XDA App

as I've noticed before, without lagfix on 2.1 the I/O check takes ages
but as compare,
2.1 without lagfix around 850
2.2 without lagfix around 1000
2.1 with lagfix around 2200
2.2 with lag fix, not tested yet, need to find a root

AsgardCurse said:
as I've noticed before, without lagfix on 2.1 the I/O check takes ages
but as compare,
2.1 without lagfix around 850
2.2 without lagfix around 1000
2.1 with lagfix around 2200
2.2 with lag fix, not tested yet, need to find a root
Click to expand...
Click to collapse
here is a root for you
http://forum.xda-developers.com/showthread.php?t=788108
OCLF only boost IO on Galaxy s : nexus 1 is still way faster in processor optimization test and this is what we need in galaxy s

dadyal said:
OCLF only boost IO on Galaxy s : nexus 1 is still way faster in processor optimization test and this is what we need in galaxy s
Click to expand...
Click to collapse
Faster in real world performance or in synthetic benchmarks?

DarthV said:
Faster in real world performance or in synthetic benchmarks?
Click to expand...
Click to collapse
I guess for using FPU intensive task, like Mathematical design, database, encoding video or MP3, file sharing and sugh... :|
For me, I use the phone for mostly GPU intense task, such as taking pictures/video, listening to video, gaming, browsing pictures, etc. so I asume that better gpu makes it better all around eh!
Kinda like being able to lift heavy wieght but doing a desk job I assume!
(BTW, sorry for the sarcasm )

2.2 without lagfix 1001

2.1
before: 854
after: 2273

Sorry guy for a stupid question but which app are you using for the benchmark test?
Sent from my GT-I9000 using XDA App

Quadrant Standard banchmark - U can find it in market
Sent from my GT-I9000 using XDA App

Thx for the app info! I got 1010
Sent from my GT-I9000 using XDA App

t1mman said:
I guess for using FPU intensive task, like Mathematical design, database, encoding video or MP3, file sharing and sugh... :|
For me, I use the phone for mostly GPU intense task, such as taking pictures/video, listening to video, gaming, browsing pictures, etc. so I asume that better gpu makes it better all around eh!
Kinda like being able to lift heavy wieght but doing a desk job I assume!
(BTW, sorry for the sarcasm )
Click to expand...
Click to collapse
So wouldn't benchmarks for your specific application be better than synthetic benchmarks suck as linpack and quadrant? The snapdragon CPU in the n1 is very very friendly with linpack (NEON + 128bit SIMD). I doubt that the hummingbird in our SGSs will ever score as high, but that doesn't mean that real performance is going to be worse. And well quadrant is pretty much a joke or at least how it weights cpu/gpu/io.
Maybe someone group will get a bunch of phones together and test things like gaming speed, web render times etc etc. That would be meaningful.

DarthV said:
So wouldn't benchmarks for your specific application be better than synthetic benchmarks suck as linpack and quadrant? The snapdragon CPU in the n1 is very very friendly with linpack (NEON + 128bit SIMD). I doubt that the hummingbird in our SGSs will ever score as high, but that doesn't mean that real performance is going to be worse. And well quadrant is pretty much a joke or at least how it weights cpu/gpu/io.
Maybe someone group will get a bunch of phones together and test things like gaming speed, web render times etc etc. That would be meaningful.
Click to expand...
Click to collapse
you mean VFP? the Hummingbird is the one with the ARM Neon chip...
VFP is pretty much a floating point accelerator which is why benchmarks are so high on linpack which calculates floating points.

my score is 1034, was over 2000 before Froyo update

Lostja said:
my score is 1034, was over 2000 before Froyo update
Click to expand...
Click to collapse
you got this update via kies ?
i flashed JPA and it go 970 - 1050

960 without
How to do the OCLF? It says "Unavailable" on everything...
Edit: got it fixed
1819 with

If everything shows unavailable check the following:
Phone is Rooted,
Ext2 tools installed,
BATTERY MUST BE MORE THAN 40%
last one is the one that most people dont check

Score was around 1008 with standard Froyo. (Kies update)
With root and lagfix i get around 1873.
With official Enclair and lagfix i could easily get 2200+ points.

970. not the best!

frankatboy said:
If everything shows unavailable check the following:
Phone is Rooted,
Ext2 tools installed,
BATTERY MUST BE MORE THAN 40%
last one is the one that most people dont check
Click to expand...
Click to collapse
Battery is more than 40%.
How do I root and install Ext2? (stupid question I know but I am new lol). I see it can root and install ext2 as well, but those are unavailable too.
Edit: *fixed* 1819 with lagfix

Samfirmware "speed test" Nexus S vs Galaxy S "credibility" of samfirmware

Samfirmware "speed test" Nexus S vs Galaxy S "credibility" of samfirmware
Not much to say to it really. But with this I lost any last drop of "faith" I had for them, even after the fiasco with the latest JVK.
http://goo.gl/t3uik
Are they joking? I mean, late 1 april joke? (link to the youtube video http://goo.gl/3ADAD )
For those that wont understand what I am saying with this:
1. quadrant cant be used to test the "real" speed or "user experience" its completely irrelevant. (look up threads about it)
2. they compared 2 different filesystems rfs4 vs ext4 .
The test and samfirmware along with it is a joke
(If its already here, erase me , if I got into the wrong forum do the same )

very true!
once the video started, and that guy clicked run benchmark, i did the same with my phone and it ended up completing only a second later than the nexus s.. besides i am on 2.2.1 wheras the nexus one was 2.3.3.. very strange?? but if u overlook the speed of completing the test, the scores were correct. that is purely because of the crappy touch wiz....but this does not in any way mean that nexus s was faster in reality.. and hey did u check the colours in galaxy s compared to nexus s.. i mean both have the same screen but it did not seem that way, probably the nexus s used for the display was super lcd..!

Well I meant with this test that samfirmware should know better as to compare rfs with ext4.
The Samsung Galaxy S has rfs compared to ext4 to the nexus S. The filesystem itself will give another score in the "benchmark". But this benchmark cant be used as a reference. NOT even comparing speed on one phone. Look up threads about it.
And yeah the colors look better on SGS,but thats irrelevant too

Why RFS is on Samsung Galaxy S ??????????????????????????

Noticed that the Colors on Gingerbread version of Nexus S look a bit off. White looks Yellowish. Noticed this with CM7.
http://www.engadget.com/2011/02/27/nexus-s-2-3-3-update-adjusts-screens-color-temperature-we-go-e/

Naeem786 said:
Why RFS is on Samsung Galaxy S ??????????????????????????
Click to expand...
Click to collapse
ive tried ext4 on my 2.3.3 and its not as smooth... im now using stock and its much smoother.
my phone is faster and smoother than my old froyo 2100 quadrant setup - yet scores 980 on avg on quadrant.
ive already left a few comments on that samfirmware post.
enable jit and add ext4 to samsung galaxy s, which is a match to the nexus s and the galaxy s wins by some distance.
2300 - galaxy s with jit enabled and ext4
1800 - nexus s
Sent from my GT-I9000 using Tapatalk

chrisjcks said:
...enable jit...
Click to expand...
Click to collapse
Thing is JIT is enabled on JVK (and I think since froyo roms). Dunno why some ppl thing its still disabled
the build.prop line that everyone is tweaking is the one with stagefright to tweak/hack the quadrant score. (it pushes the score from 1600-1700 above 2000)
But funny their comment to me:
We just test both phones on his speed.
Its only a show how slow Samsungs own software is when you compare this with a clean Google rom. like the Nexus S.
Click to expand...
Click to collapse
@Samfirmware ITS NOT A SPEED TEST! Its testing books with tanks....
Samfirmware
We are bringing Samsung mobile fans together!
Trusted by 3 Site Members!

i am running stock xxjvk, rooted with cf-root 2.7.
started the benchmark at the same time, finished it 13 seconds BEFORE GOOGLE NEXUS S, 990 points ).

It's clear that the SGS they are using have an issue when I/O test get stuck there at 0/4 for a long time, however, change this line in build.prop from :
media.stagefright.enable-player=false
Click to expand...
Click to collapse
Click to expand...
Click to collapse
to:
media.stagefright.enable-player=true
Click to expand...
Click to collapse
Click to expand...
Click to collapse
And your quadrant score will be 1600-1700 points, now install the hacked kernel by supercurio and enable ext4: http://forum.xda-developers.com/showthread.php?t=975349 and see your device score 2400-2500 if not more.
Samfirmware have proved again that they mean as much as a Quadrant score in a worthless comparison that is only meant to promote Nexus S against Galaxy S, even though that we all know that they are mainly the same device.
Thanks to PAGOT for this find

Quadrant means nothing, in my desire I had about 3000pts, on my galaxy s about 2400pts but the galaxy is quicker when you use it..

I know that you all say quadrant score means nothing, or maybe it's just sgs owners that say that (ducks for cover ;-)
...but if you go over to the Droid X forum, there is a video review of a Droid X with Gingerbread and it clearly shows that the Droid X Quadrant score is doubled with Gingerbread and the phone looks really speedy on the video...
http://www.youtube.com/watch?v=339bnvTQ87g
Can anyone explain this?

nice ginger on droid x look faster than my Froyo on galaxy

Oh yeah, and just FYI, I though that the samfirmware video review was absolute rubbish too.

markdj57 said:
I know that you all say quadrant score means nothing, or maybe it's just sgs owners that say that (ducks for cover ;-)
...but if you go over to the Droid X forum, there is a video review of a Droid X with Gingerbread and it clearly shows that the Droid X Quadrant score is doubled with Gingerbread and the phone looks really speedy on the video...
http://www.youtube.com/watch?v=339bnvTQ87g
Can anyone explain this?
Click to expand...
Click to collapse
The topic of this thread is about comparing to devices which are pretty much similar to each other, both have Gingerbread 2.3.3 installed but they have installed ext4 on one of them and left the other with RFS, beside that the SGS gets stuck on I/O test which is clearly indicate a problem with SGS which non of us have while running quadrant...this comparison is worthless..this is my opinion.
Although this is pretty much off-topic, but:
I wrote how to boost score numbers by changing only 1 line in build.prop from 900-1000 points to 1600-1700 points which proves how worthless quadrant scores are.
Beside that, any SGS owner will tell you that he/she can get 56fps in 3d test, while DroidX fails to deliver more than 10fps in that test.
Moving to linpack, DroidX scores 10-12 MFLOPS, any SGS owner can confirm that SGS scores no less than 14 MFLOPS.
Based on scores now, how is DroidX faster than SGS ? Well it's not, but in the other hand I can agree that Motorola software is better optimized for DroidX than Samsung have done with SGS.

Thanks ramad, I did notice that the fps on the quadrant test were very very low in comparison to the SGS which maxs out at 56fps (on planet test) so I do agree but interesting that so many rely on Quadrant so much that it seems flawed.

http://forum.xda-developers.com/showthread.php?t=1012556

Have anyone noticed in Quadrant if you are on RFS the database write/read test finishes very quickly compared to ext4 whhch takes 2-3x longer to finish. Yet the score with ext4 is higher. THis does'nt make sense at all. Something is really very WRONG with Quadrant.

Quadrant? oh puuuhleeeezz.. shocked @ samfirmware..

Accurate benchmarking.

Quadrant is very inaccurate the tests are not up to spec for testing +1Ghz devices accurately.
The reason i say this is due to the fact that the benchmark varies from test to test.
I suggest AnTutu Benchmark.
https://market.android.com/details?id=com.antutu.ABenchMark
It is much more accurate, as the the scores are closely similar time and time again.
The tests are a bit longer
But that is the good thing "accuracy"
It also gives info on each testing stage.
I got 2176 on WB's 007.1 TW rom, BB.67 with custom kernel.

OmegaRED^ said:
Quadrant is very inaccurate the tests are not up to spec for testing +1Ghz devices accurately.
The reason i say this is due to the fact that the benchmark varies from test to test.
I suggest AnTutu Benchmark.
https://market.android.com/details?id=com.antutu.ABenchMark
It is much more accurate, as the the scores are closely similar time and time again.
The tests are a bit longer
But that is the good thing "accuracy"
It also gives info on each testing stage.
I got 2176 on WB's 007.1 TW rom, BB.67 with custom kernel.
Click to expand...
Click to collapse
Good, will give it a try but it'd been better if you post this in themes & apps I guess
by the way what scores do you get with this rom in quadrant?

Chainfire released his new benchmarking tool yesterday, its called CF-Bench, search in the market

i've got 1973 on CM6 006 at 1.1Ghz

benchmarking
It does not matter what benchmarking utility you use. They all give you a general idea of the performance of your phone. I think the OP just wants to use the tool that gives him the score he wants to see.
In reality the score of any phone using any utility is always relative to the scores of other phones using the same utility.
The thing to focus on is not the actual figures you get back but how your device measures up to other phones using the same benchmark test.

kryptoner said:
Chainfire released his new benchmarking tool yesterday, its called CF-Bench, search in the market
Click to expand...
Click to collapse
2232 hmm right behind the nexus s
Cm6 wb bb67 custom kernel z
Sent from my X10i using XDA App

Try smartbench 2011. That's the best one
Sent from my x10 on gingerbread

All benchmarking apps generaly suck. Its about how you feel using your phone. Not the numbers.
Sent from my X10i using XDA App

pepy_24 said:
All benchmarking apps generaly suck. Its about how you feel using your phone. Not the numbers.
Sent from my X10i using XDA App
Click to expand...
Click to collapse
But it's a good comparison between phones after having a average score for each phone. But like you say, the numbers don't mean anything. Everything is personal.

zodiac100 said:
It does not matter what benchmarking utility you use. They all give you a general idea of the performance of your phone. I think the OP just wants to use the tool that gives him the score he wants to see.
In reality the score of any phone using any utility is always relative to the scores of other phones using the same utility.
The thing to focus on is not the actual figures you get back but how your device measures up to other phones using the same benchmark test.
Click to expand...
Click to collapse
True about benchmark apps but I don't think I think the OP just wants to use the tool that gives him the score he wants to see. What the OP is saying that with this app the difference between each time's score is not much hence why calling it accurate.

To look for a good benchmark is more important if you use a new phone with dual core CPU cos the old benchmarks aren´t optimised for them. I read that CF-Bench is optimised for dual cores and stresses the CPU and not so much the GPU of the phone.
But interesting that it seems that the overclocking have such a huge influence. With the first run (Wolfbreaks CM6 TW007) i had 2800 points with 1152MHz and in the second run with 998MHz 2400 points.
But true....it´s more a interesting gadget than to take it too seriously

maddes1402 said:
To look for a good benchmark is more important if you use a new phone with dual core CPU cos the old benchmarks aren´t optimised for them. I read that CF-Bench is optimised for dual cores and stresses the CPU and not so much the GPU of the phone.
But interesting that it seems that the overclocking have such a huge influence. With the first run (Wolfbreaks CM6 TW007) i had 2800 points with 1152MHz and in the second run with 998MHz 2400 points.
But true....it´s more a interesting gadget than to take it too seriously
Click to expand...
Click to collapse
It comes down to what you have happening in the background.
If your phone suddenly "for example" decides to fetch data off of 3G or suddenly refreshes the media midway thru the bench then it can effect your score. this is why it's best to do tests when the rom is clean and gone silent. "no background activity" with data disabled.
Benchmarking is used to place the current performance of a device in a certain category.
It's no different from benchmarking PC's.
A whole profession has been built around PC benchmarking with people competing for a first place.
If your score is higher than everyone else you win the competition.

i got 2232 on custom kernel at 1113 mhz processor
Sent from my X10 TripNMiUI-IRIS

CF-Bench
Smartbench 2011
Quadrant
Antutu Benchmark
what is the best now?

Wolfbreak said:
CF-Bench
Smartbench 2011
Quadrant
Antutu Benchmark
what is the best now?
Click to expand...
Click to collapse
CF Bench (full version) has the most stable results, and IMO its the best out there.
Sent from my Sony Ericsson Xperia™ phone

Linpack is perfect

kantk20111 said:
Linpack is perfect
Click to expand...
Click to collapse
Linpack only tests the cpu.
I haven't checked how CF bench works yet.
will report.

Wolfbreak said:
CF-Bench
Smartbench 2011
Quadrant
Antutu Benchmark
what is the best now?
Click to expand...
Click to collapse
CF bench 101%

Wolfbreak said:
CF-Bench
Smartbench 2011
Quadrant
Antutu Benchmark
what is the best now?
Click to expand...
Click to collapse
Chainfire one!
that thing is scale-able across cores (single/multi-cores) and fairly accurate

Gingerbread slower on 3d gaming

is there a way how to speed up the gingerbread on 3d gaming like on froyo?
in froyo my NFS Shift is like 55 - 60 fps but in gingerbread its just around 30 - 40 fps..
same on Quadrant in 3d rendering the red and blue dna like rolling figure is 49 - 50 fps in FROYO but in gingerbread it wont pass 30 fps
any tweaks on how to boost 3d rendering speed?

First of all, wrong section
Froyo indeed had better hardware acceleration than gb, and the kernel was also a lot better, Samsung rushed gb and messed things, but does it really affect you, the human eye can see @ ~30fps max, so does it matter?

honestly im seeing the difference.. 30fps is like lagging/stuttering to my naked eye..
i dont know but maybe its because I'm used to a high FPS on my computer.. the lowest FPS i see on my PC game is 90 fps. that's why I can differenciate 30fps to 60fps

cdesai said:
First of all, wrong section
Froyo indeed had better hardware acceleration than gb, and the kernel was also a lot better, Samsung rushed gb and messed things, but does it really affect you, the human eye can see @ ~30fps max, so does it matter?
Click to expand...
Click to collapse
Some people can really tell the difference. Sadly, I'm one of them
But I started using the tab as more of a work device than gaming, so the newer features of Gingerbread far outweighed the gaming performance of Froyo for me.

Karry025 said:
honestly im seeing the difference.. 30fps is like lagging/stuttering to my naked eye..
i dont know but maybe its because I'm used to a high FPS on my computer.. the lowest FPS i see on my PC game is 90 fps. that's why I can differenciate 30fps to 60fps
Click to expand...
Click to collapse
codewisp said:
Some people can really tell the difference. Sadly, I'm one of them
But I started using the tab as more of a work device than gaming, so the newer features of Gingerbread far outweighed the gaming performance of Froyo for me.
Click to expand...
Click to collapse
LOL i'm also one of them, and this was one of the reasons HC needed froyo bootloader!

actually in terms of UI rendering and office apps specially on loading.. Gingerbread beats froyo over a mile ahead.. gingerbread is smoother only the 3d gaming is the problem.. but very well going to stick on gingerbread 2.3.6..
and btw.. Froyo also allows to underclock the CPU with higher value than gingerbread.. on froyo I can run 1.4ghz with -350mv stable but on gingerbread I cant get past -50mv stable on 1.4ghz..
any other tweak on how are the others getting a monstrous 3K score on quadrant?

Karry025 said:
actually in terms of UI rendering and office apps specially on loading.. Gingerbread beats froyo over a mile ahead.. gingerbread is smoother only the 3d gaming is the problem.. but very well going to stick on gingerbread 2.3.6..
and btw.. Froyo also allows to underclock the CPU with higher value than gingerbread.. on froyo I can run 1.4ghz with -350mv stable but on gingerbread I cant get past -50mv stable on 1.4ghz..
any other tweak on how are the others getting a monstrous 3K score on quadrant?
Click to expand...
Click to collapse
GB is faster than froyo, it would more, but Samsung rushed out the update, and that ruined it partially.
UV is kernel issue, try with some other kernel first, and -350mv is insane!
3k in quadrant is nothing, its just a score, can be fooled, mostly its fooled in I/O part

-350mv running stable on 1.4ghz is true..
have you tried a FROYO with any kuxodaxi's kernel?
i suggest you try it and see for yourself
yeah Gingerbread is faster in froyo but not on samsung..
on tab froyo beats gingerbread in terms of 3d gaming
by the way what is the best I/O scheduler for you?

Karry025 said:
-350mv running stable on 1.4ghz is true..
have you tried a FROYO with any kuxodaxi's kernel?
i suggest you try it and see for yourself
yeah Gingerbread is faster in froyo but not on samsung..
on tab froyo beats gingerbread in terms of 3d gaming
by the way what is the best I/O scheduler for you?
Click to expand...
Click to collapse
Honestly, no
I got my tab from my dad sometime back, and i had already updated to gb via *cough* kies *cough*, so didnt get a chance to try it out more.

i hope someone can port the UI speed of Gingerbread to the Froyo XD

Please adopt a little common sense when creating new threads.
Unless you have developed something, ROM/MOD/etc.. then the Development section is off limits for threads. Post it in General or Q&A.
You do not want to anger the XDA God of Tidiness

why do you have a common sense to spare? lol just kiddin

ICS benchmarks versus GB

Previously with GB:
Browsermark - 99,857
Sunspider - 1826ms
ICS after this mornings update:
Browsermark - 124,672
Sunspider - 1488ms
Wow, roughly 25% improvement in both

Could you please try a full benchmark with Quadrant?

Quadrant standard full benchmark - 3748 (3871 on second run)

straxusii said:
Quadrant standard full benchmark - 3748
Click to expand...
Click to collapse
Thanks!
So a little bit higher than the score with ICS Stunner. Hope NeoBuddy updates it soon.

No real difference with quadrant, I think that was roughly the same as my GB score

oh ........great benchmarks .....why are people obsessed with synethetic benchmarks?

CF Bench 1.2 - Overall score 7601

Richy99 said:
oh ........great benchmarks .....why are people obsessed with synethetic benchmarks?
Click to expand...
Click to collapse
Its a geek thing methinks. Tried Quadrant on my Note running stock UK GB just now it got a score of 3977 & 3668 & 3732 which is faster than anything I ever owned...but it still lags like ****.

Quadrant Full Benchmark Results -
Stock GB 2.3.6 - 2684
Current Stock ICS 4.0.3 (German release) - 3445

Antutu?

Castellano2 said:
Antutu?
Click to expand...
Click to collapse
Bungaga
Sent from my Xoom using xda premium

I am getting around 3800 in Quadrant on ICS LiquidSmooth and I was getting about 3200 on official GB.

zen123 said:
Its a geek thing methinks. Tried Quadrant on my Note running stock UK GB just now it got a score of 3977 & 3668 & 3732 which is faster than anything I ever owned...but it still lags like ****.
Click to expand...
Click to collapse
Yep my turbo ricer pimped Honda makes 430hp on the dyno but still sucks in the 1/4 mile.
Sent from my GT-N7000 using Tapatalk

Can someone please post a Nenamark 2 and GLBenchmark Egypt or Pro offscreen?
Thank you!

Castellano2 said:
Antutu?
Click to expand...
Click to collapse
AnTuTu 2.7.3 - 6769

MindBlank said:
Can someone please post a Nenamark 2 and GLBenchmark Egypt or Pro offscreen?
Thank you!
Click to expand...
Click to collapse
GLBenchmark 2.1.4, Egypt 2.1 standard - 46fps (was vsync limited at times)

Can you please try the offscreen bench for Egypt?
Sent from my GT-I9000 using XDA

MindBlank said:
Can you please try the offscreen bench for Egypt?
Click to expand...
Click to collapse
60 fps

48 fps on stock GB. Very nice increase of 12 fps. I'm running an OC'ed GPU on GB (400Mhz) and it gives 68 fps. So the increase in case of ICS + 400Mhz GPU would be 85 fps. Can't wait to flash it.
Sent from my GT-I9000 using XDA

straxusii said:
Previously with GB:
Browsermark - 99,857
Sunspider - 1826ms
ICS after this mornings update:
Browsermark - 124,672
Sunspider - 1488ms
Wow, roughly 25% improvement in both
Click to expand...
Click to collapse
Very, very good scores. These best everything AnandTech has ever benchmarked, with the exception of the Lava XOLO and SGS 3. Absolutely dusts the iPhone 4S, wow.