Database Develop

Performance

Okay, another question that makes me feel kinda dumb.
How can I improve my N1's performance?
Specifically, how in the world do I get my nexus even close to the N1's I see on Linpack's "Top Devices"?
I'm running diet_2.6.33.2.hybrid_avs_925mv_OC with cyanogen 5.0.6. I can get 7.778 MFLOPS. Honestly, I don’t even know what that means. All I know is that I want more. Or do I? Does it even make that much of a difference in everyday usage?
I've noticed that in the JIT thread under development they talk about getting up to 17 MFLOPS, but no one really explains what JIT is or does. Just that it's unstable and that if your not sure what it is, you don't need it.
I can benchmarkPi in 2790 - how in the hell do I get it lower? Under the rom description of some of the top 50 they mention JIT and experimental kernels, but there's not much room for more than just the generic names of them. Where do I get these magical roms and kernels? Do I even want them? Are they so unstable that they can only be used to gain geek cred on some benchmark lists and once they hit the "high score" they explode in flames? Do I need safety goggles before I flash the update.zip?
Seriously though, I know I'm not the only one with these questions - so any info would help. And do me a favor, please do not respond to say that if I don't know - I don’t need to know. At one point, you didn't know either. No one was born with this knowledge.
I know there is a very bright person on here that is willing to take a couple of minutes to shed some light on us simpletons. I'd like to thank you in advance. Thanks.

Even if you get higher linpack scores, you will barely notice any difference in your devices performance... That's why I tend to ignore it. If its possible to get faster than Cyanogen ROMs (not in terms of linpack) I don't know how different things would be.. im curious about how quick Froyo is though.
Oh and have you searched, Jit has been covered in more places than just xda developers, several times it has been discussed I believe.. while using it, my Linpack scores did get into the double digits though - but this (not even that noticeable actually) speed increase was not worth the random reboots, and such. When Jit is stable though, it will be quite nice.. hopefully Froyo has it.

Linpack number did not make any differences in overall usage . Now, I am using my own UV kernel and setcpu max freq to 500MHz.. only... but, I still able to get 26.8 fps in Neocore's 3D benchmark. Playing games, 3D or not, still smooth and fluid.
I also waiting for Froyo and hope we can get even efficient and fast OS.
TQ.

Updated benchmarks + battery tests with Nov 13th OTA update!

Engadget has the first update:
http://www.engadget.com/2012/11/12/nexus-4-and-nexus-10-android-4-2-final-update-adds-lock-screen-w/
Doesn't look like much has changed that much so far...
Anandtech's review:
http://www.anandtech.com/show/6440/google-nexus-4-review
Battery still meh if you are a heavy user, and benchmarks still affected by thermal throttling...it's hard to get a proper gauge though because the devices that the N4 is compared to change from graph to graph...I wish there was a consistent comparison with the LG Optimus G
+ve about the build quality and apparently it has been dropped a few times without issues...so could be not bad depending on how it's dropped. Running stock android is also another +
Will update thread with more links as they are posted.

Performance is good enough omg. We want better battery life. But once I have Cm10.1 on my N4 I'll uc the cpu so I have better battery life.
Gesendet von meinem GT-I9100 mit Tapatalk 2

There were so many posts, that low benchmark scores where because of not final software....
they were all wrong
I bet camera photo and video is still **** @ 9mbps 22FPS

Raw hardware specs do not simply cease to 'exist' because software benchmarks show certain numbers.
We know the specs of the device, the hardware in it is more powerful than the majority of the phones out there, calling this OTA conclusive is still flawed.
Wait a while, or have fun joining in on the XDA arguing that I see as still pointless. The HTC One X forums taught me a lot about benchmarks...

Audioboxer said:
Raw hardware specs do not simply cease to 'exist' because software benchmarks show certain numbers.
We know the specs of the device, the hardware in it is more powerful than the majority of the phones out there, calling this OTA conclusive is still flawed.
Wait a while, or have fun joining in on the XDA arguing that I see as still pointless. The HTC One X forums taught me a lot about benchmarks...
Click to expand...
Click to collapse
The problem we're having is with the battery life, not the benchmarks. It's been proven that the poorer benchmark results are due to the CPU overheating and throttling down - which in turn gives it poor battery life - 5 hours video playback vs 8 hours on the Optimus G.
That's why people are dying over the new benchmark results, to see if it still throttles down or not.

Daemos said:
Engadget has the first update:
http://www.engadget.com/2012/11/12/nexus-4-and-nexus-10-android-4-2-final-update-adds-lock-screen-w/
Doesn't look like much has changed that much so far...
Will update thread with more links as they are posted.
Click to expand...
Click to collapse
Still sucks ...
I think I will hold my purchase till got clarification what's the true story about this under-performed S4 pro compare to LG G9.
My GNex is still more than capable anyway.

omersak said:
The problem we're having is with the battery life, not the benchmarks. It's been proven that the poorer benchmark results are due to the CPU overheating and throttling down - which in turn gives it poor battery life - 5 hours video playback vs 8 hours on the Optimus G.
That's why people are dying over the new benchmark results, to see if it still throttles down or not.
Click to expand...
Click to collapse
Agreed. Call it early indicator if you will. If the benchmarks shows abnormal activities compared to sibling LG Optimus G than we have a problem. It also possible that Engadget's N4 has thermal problems like Anandtech but they didn't put in the fridge to proved thermal problems since both websites early benchmarks are equally crap compared to The Verge.

omersak said:
The problem we're having is with the battery life, not the benchmarks. It's been proven that the poorer benchmark results are due to the CPU overheating and throttling down - which in turn gives it poor battery life - 5 hours video playback vs 8 hours on the Optimus G.
That's why people are dying over the new benchmark results, to see if it still throttles down or not.
Click to expand...
Click to collapse
I hear what you're saying, but no other phone runs 4.2 from Google does it? I'd wait till later this week when we have many rooted devices, custom ROMS/kernels and what not.
The software HTC shipped the One X running on was an unoptimized mess (which also had heat issues).
The people storming around shouting conclusive and saying the phone has hardware issues only serve to make people fearful at this stage where it is too early to be conclusive of any hardware issues. Software issues will be aplenty on a launch of new hardware.

Audioboxer said:
Raw hardware specs do not simply cease to 'exist' because software benchmarks show certain numbers.
We know the specs of the device, the hardware in it is more powerful than the majority of the phones out there, calling this OTA conclusive is still flawed.
Wait a while, or have fun joining in on the XDA arguing that I see as still pointless. The HTC One X forums taught me a lot about benchmarks...
Click to expand...
Click to collapse
But there is a problem if the performance in benchmarks does not add up to what the 'specs' say.
It's like building two identical computers, put one in a different case...one running windows vista and say one running windows 8...
If the hardware is identical, the benchmarks should be VERY similar, if not there is something wrong with the build, hardware, drivers, software etc...and it is not working to it's potential.

This is quite alarming. Agreed with everyone that something is wrong. That's a huge difference: 4984 vs 7628. This might potentially make me wait to see if this some kind of bug. I mean in all seriousness, if I have the same hardware I would like it to perform the same. Google won't admit any wrong doing here either....that's good for ya. Let's hope they see the issue and try to find a fix.
Ugh. What a way to start my day....

new 3,4 kernel guys...give to google some times to fix that.

Well I just ordered one because I'm not really bothered by benchmarks. This is the first phone running on 4.2 and it's powerful enough as it is.
One thing I will point out is (from what I've seen) the N4 beats the Optimus G consistently in Geekbench 2 posting scores of over 2000. We need to ignore the browser benchmarks as chrome is not as well optimised as the old stock browser on Android.
We need to wait and see how the phone matures in time, I don't think there is a hardware issue here everyone is panicking over 2 phones that don't quite match each other...I know if my N4 goes wrong due to some unknown issue I know I can get a new one sent to me from Play so it's not really something that is going to bothering me.
Anyway, who buys their phone on benchmarks?! Are you benching it 24/7? No, so what's the need for you to see how a phone performs in tasks that you would never ever ask it to do in real world situations...

Came across this site:
lwn.net/Articles/524631/rss
(Guess I can't post direct links for now)
Can anyone explain what this CPU isolation actually means and how it translates to actual performance and benchmark scores?

iluk3 said:
Well I just ordered one because I'm not really bothered by benchmarks. This is the first phone running on 4.2 and it's powerful enough as it is.
One thing I will point out is (from what I've seen) the N4 beats the Optimus G consistently in Geekbench 2 posting scores of over 2000. We need to ignore the browser benchmarks as chrome is not as well optimised as the old stock browser on Android.
We need to wait and see how the phone matures in time, I don't think there is a hardware issue here everyone is panicking over 2 phones that don't quite match each other...I know if my N4 goes wrong due to some unknown issue I know I can get a new one sent to me from Play so it's not really something that is going to bothering me.
Anyway, who buys their phone on benchmarks?! Are you benching it 24/7? No, so what's the need for you to see how a phone performs in tasks that you would never ever ask it to do in real world situations...
Click to expand...
Click to collapse
Not the benchmark score itself, but the "battery life" ... N4 is worse compared to LG OG, 5 hours video run-down vs 8 hours.
That's what worries me ...

NODO-GT said:
There were so many posts, that low benchmark scores where because of not final software....
they were all wrong
I bet camera photo and video is still **** @ 9mbps 22FPS
Click to expand...
Click to collapse
And we are still not at final software. It will be multiple OTAs before we are at final software.
So, there's that.

I believe its a kernel problem. And also, why are you all comparing a jellybean ROM with a new kernel with an ICS one? That's not a really fair comparison in my eyes. That's just my opinion though
Sent from my T-Mobile myTouch 4G

gogol said:
Not the benchmark score itself, but the "battery life" ... N4 is worse compared to LG OG, 5 hours video run-down vs 8 hours.
That's what worries me ...
Click to expand...
Click to collapse
ips vs amoled
people hate on amoled but I'll take the battery life..

ziddey said:
ips vs amoled
people hate on amoled but I'll take the battery life..
Click to expand...
Click to collapse
Doesn't the Optimus G have same screen as N4?
Sent from my Galaxy Nexus using Tapatalk 2

0.0 said:
I believe its a kernel problem. And also, why are you all comparing a jellybean ROM with a new kernel with an ICS one? That's not a really fair comparison in my eyes. That's just my opinion though
Sent from my T-Mobile myTouch 4G
Click to expand...
Click to collapse
More of a fact than an opinion :good:

I thought Optimus G has a IPS screen. Same one in the N4

[Q] [ AnTuTu Benchmarks on Note 4! 50,000+ ??? ]

Post up your AnTuTu Benchmarks! (Snapdragon 805's ... well Exynos too I guess haha. Darn you with the 55k+'s!!!)
(In this format please to keep it organized. It's ideal to just copy/paste it and fill in your numbers.)
==================Copy==================
ROM Info:
FireKatN4 Deodex V2 w/ Stock Kernel
AnTuTu Score:
49,694
=================Paste=================
Let it fly!

here is mine..!!

Okarina26 said:
here is mine..!!
Click to expand...
Click to collapse
hi can you tell me what did you change to get that high score. i m at 46 k and dont know how to get it better. thnks

capecubano said:
hi can you tell me what did you change to get that high score. i m at 46 k and dont know how to get it better. thnks
Click to expand...
Click to collapse
Exynos

Okarina26 said:
Exynos
Click to expand...
Click to collapse
got you. that sucks we are stuck on snapdragon.

Haha! Great answer.... I should have said, SD805'S only hahaha....
Okarina26 said:
Exynos
Click to expand...
Click to collapse

Snapdragon 805's dream with a stock kernel. Even with a custom kernel, Exynos will always stomp.
What carrier are you running your international variant on?
Great score by the way! Best I've seen. Well of course, exynos lol.
Okarina26 said:
here is mine..!!
Click to expand...
Click to collapse

49,863 on STOCK KERNEL running FireKatv2 ROM!!!
Almost 50K on STOCK Kernel!!!!

Anyone break 49K on stock kernel? State your ROM you're using too...
This is all for fun, but has anyone hit 49K on the stock kernel?
I've tested all the available ROM's on the other N4 in my household and none has has hit 49K except, FireKatv2.
Show me! :good::good:

100% Stock rom and Stock kernel no root
I dont get it. I have been on a quest to make my phone better since the note 2. I always hit XDA and tinker and learn as much as I can but sometimes I see scores and I see people really excited about the "speed increase and battery life improvements with new roms etc, and I dont get it because for example this is my score without any work on the phone at all. My battery life is about 7.5 hours screen time with gps on and sync on all the time. Screen set to auto. Dont get me wrong I am a lover of modding and hate all the bs that carriers and sammy puts on the phones I am here because I love to work on my phone but I see no real difference right now even maybe I slow the phone down if I do anything to it. Whats going on? I remember on my note 3 I was able to see some improvement on my benchmarks over stock (not by much) and a little better battery life but again not a huge difference. Also I thought I should mention that on echoe rom I was able to score 24 to 25,000 on quadrant clocked at 2.2 ALL THE TIME I once even scored 27,000 when I was overclocked at 2.5. How come I never break 26,000 even tho I am clocked at 2.7 now. Also why am I scoring so high over modded phones

That's an excellent score! Well in your case it just proves that the stock software isn't terrible. It works....Simple as that. As for the modded peeps with custom ROM's, a lot of them have so much crap on there apps wise and have it heavily tweaked with wanam/xposed where it is really weighing down their phones.
I also have a theory about the CPU's in that they are not all created equal. Remember with the Note 3's there was a prompt in the dialer where you could go to a secret menu to see what type of processor you had. I think it was from 0-7 or something and the closer the number was to 7 meant you had a more efficient CPU, but not friendly / "as tolerant" to overclock as oppose to someone with a number closer to "0" which meant that it was more power hungry and more tolerant to over clocking. If you search for it you'll find what I'm talking about. ...
Anyway, I think we have the same thing going on here....where some of us just happen to have stronger CPU's. It's just like car engines.....not all are the same as every one of them have their own unique character. I remember when I got my AMG C Class and my buddy had the same one but a year newer. He used to smoke me (stock) where I had intake/exhaust/flashed chip. I just didn't get it. Sometimes you just end up with a [email protected]$$ CPU coming from a good batch LOL.
Another example is microSD cards...you can buy the same brand / type and all, but will always have different results. My Samsung 64GB PRO is faster than my other Samsung 64GB Pro that I have in another N4. Same phone, same chip...different speeds.
You have an awesome piece. Great score! I can't wait to break 50K's on a stock kernel!
triman13 said:
I dont get it. I have been on a quest to make my phone better since the note 2. I always hit XDA and tinker and learn as much as I can but sometimes I see scores and I see people really excited about the "speed increase and battery life improvements with new roms etc, and I dont get it because for example this is my score without any work on the phone at all. My battery life is about 7.5 hours screen time with gps on and sync on all the time. Screen set to auto. Dont get me wrong I am a lover of modding and hate all the bs that carriers and sammy puts on the phones I am here because I love to work on my phone but I see no real difference right now even maybe I slow the phone down if I do anything to it. Whats going on? I remember on my note 3 I was able to see some improvement on my benchmarks over stock (not by much) and a little better battery life but again not a huge difference. Also I thought I should mention that on echoe rom I was able to score 24 to 25,000 on quadrant clocked at 2.2 ALL THE TIME I once even scored 27,000 when I was overclocked at 2.5. How come I never break 26,000 even tho I am clocked at 2.7 now. Also why am I scoring so high over modded phones
Click to expand...
Click to collapse

50,429! FireKatv2 (Stock Kernel) No CPU app. Bone stock.
Finally did it! Woke up, ran it....bam! As stated above this is with FireKatv2, Stock Kernel, Bone Stock and No App. I cleaned up a lot of my apps and my set up is real clean and simple. This is crazy....maybe I'm dreaming right now as I just woke up. No wait, I am awake. :victory:
For fun...enjoy.

Mine is 58483
Im using Galaxy Note 4 T mobile running on marshmallow, I am using beastmode kernal

Low Multi-Core Geekbench Score?

I noticed Geekbench 4 Pro was free for a limited time on Play Store, so I downloaded it and ran a benchmark.
Device Status;
-OOS 5.0
-Stock Kernel
-Magisk 14.5 with IOS 11 Icons, and Greenify4Magisk
My Geekbench benchmarks were lower than the OnePlus 3! Any clue how this happened?

Why people give so much importance to benchmark ?
Now that this app told you these results, you gonna hate your phone ?
Live your life with your phone, what's matter the most is your experience, no the what a 3rd party application tells you.

Thats just a benchmark not a real world usage thing. If u believe something like that then xda is not for u. Only those who don't knkw abt xda would think that benchmark is everything

casual_kikoo said:
Why people give so much importance to benchmark ?
Now that this app told you these results, you gonna hate your phone ?
Live your life with your phone, what's matter the most is your experience, no the what a 3rd party application tells you.
Click to expand...
Click to collapse
jokerpappu said:
Thats just a benchmark not a real world usage thing. If u believe something like that then xda is not for u. Only those who don't knkw abt xda would think that benchmark is everything
Click to expand...
Click to collapse
First of all, hardware degradation exists. I'm not going to hate my phone just because it's benchmarks are low, I'd like to know WHY this occurs. THE TECHNICAL SIDES OF THIS ANOMALY. Yes, I know my experience is what matters to me, But I asked this question to understand why and how this happens. I didn't ask a solution for this did I?
Lmao, who're you to tell me XDA ain't for me? I asked a legitimate question in the "Q&A" section. I don't lose trust or faith in my device since my benchmarks are down, I wanted someone with the technical know-how to explain to me why the benchmarks differ from a less power SoC to a higher power SoC.
Clearly you're not someone who knows anything about why this happens, and stop wasting your time telling people your opinion of what you think benchmarks represent. I asked a legitimate question, and that's my right on XDA.

thes3usa said:
First of all, hardware degradation exists. I'm not going to hate my phone just because it's benchmarks are low, I'd like to know WHY this occurs. THE TECHNICAL SIDES OF THIS ANOMALY. Yes, I know my experience is what matters to me, But I asked this question to understand why and how this happens. I didn't ask a solution for this did I?
Lmao, who're you to tell me XDA ain't for me? I asked a legitimate question in the "Q&A" section. I don't lose trust or faith in my device since my benchmarks are down, I wanted someone with the technical know-how to explain to me why the benchmarks differ from a less power SoC to a higher power SoC.
Clearly you're not someone who knows anything about why this happens, and stop wasting your time telling people your opinion of what you think benchmarks represent. I asked a legitimate question, and that's my right on XDA.
Click to expand...
Click to collapse
Ur daily usage performance is being degraded also?
Or is it just benchmark being decreased?

Look at my benchmark its much lower than urs. Bt its my phone is performing just like it used to besides this numbers also. Its about experience with the phone nkt numbers ok. So dont be all about benchmark

Sustained performance isnt as good as Samsung hoped

So I just got my new phone and while I was installing apps from Google Play restoring from backup, I decided to run a geekbench benchmark on it, and well the results are attached as below. Don't get me wrong I know that performance is supposed to be lower, especially given that it is still installing apps, but the device isn't even hot and I would have expected it to score at least a 7 or 8 K. 5K is really quite disappointing.

Talk about a strange thread. I wonder what compels someone to think it's a good idea to benchmark while installing apps and then trying to quantify that with the phone has poor sustained performance? That's a bit of a reach, don't you think?

Um ok.

Do us a favor and return the phone if you're disappointed with the performance from a benchmark and not real life testing.
This is like having a gasoline truck that normally gives you 16 mpg. Then you slap on a tow hitch and haul a 5 ton tailer and you're surprised the truck now only gives you 9-10 mpg.
Sent from my Pixel 2 XL using Tapatalk

AB__CD said:
So I just got my new phone and while I was installing apps from Google Play restoring from backup, I decided to run a geekbench benchmark on it, and well the results are attached as below. Don't get me wrong I know that performance is supposed to be lower, especially given that it is still installing apps, but the device isn't even hot and I would have expected it to score at least a 7 or 8 K. 5K is really quite disappointing.
Click to expand...
Click to collapse
So, you think that the device doesn't use any system resources while restoring data and installing apps?
I hope you are just trolling or I(and the other fellow members) didn't understand you correctly, otherwise - it's normal. Benchmarks are run while the device DOES NOT do anything else. Otherwise system resources are used and the scores will be lower. By how much will depend on the workload. For example GPU bench will not be affected that much as a CPU or storage test while installing apps.

high_voltage said:
So, you think that the device doesn't use any system resources while restoring data and installing apps?
I hope you are just trolling or I(and the other fellow members) didn't understand you correctly, otherwise - it's normal. Benchmarks are run while the device DOES NOT do anything else. Otherwise system resources are used and the scores will be lower. By how much will depend on the workload. For example GPU bench will not be affected that much as a CPU or storage test while installing apps.
Click to expand...
Click to collapse
Some system resources? Yes. I'm just rather surprised it's close to half of such a powerful phone's resources.

Benchmark people are the reason I left the PC scene. No one judges anything in tech based on what it's actually used for, only what it can or can't potentially do. And that's the reason the industry is crappy and overpriced as it is. Same thing has happened to the phone industry.
You ran a benchmark that pushes your device to limits you will NEVER EVER get it to again with daily usage. Not even if you're playing music while playing Fortnite and other apps in the back.

AB__CD said:
Some system resources? Yes. I'm just rather surprised it's close to half of such a powerful phone's resources.
Click to expand...
Click to collapse
This might help you. Android apps are written in Java. This allows them to be compatible with a wide variety of Android devices. When you install them on your phone, they are compiled to machine code specific to your particular device. This only needs to happen when you first install or subsequently update your app. However, this process is pretty resource intensive, and larger apps like Facebook take more resources. This slows down the rest of the phone. So the worst possible time to run a benchmark is when you are doing the most system intense thing you can do on your phone. The results are unsurprising and normal.

i think OP is learning new things here...

Must believe the Earth is flat. ??

Snapdragon 845 score is much better than my Note 8

@rbiter said:
Must believe the Earth is flat. ??
Click to expand...
Click to collapse
Flat? How about a cube?!