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.

Quadrant sucks, howto properly bench our devices?

I'm creating this thread based on what i read here: http://briefmobile.com/cyanogen-demonstrates-quadrants-flaws
I'd really like to know what lagfix gives me the best results and i lost my faith in quadrant. Are there any decent alternatives? Most benchmarks i know are only good for testing cpu performance...

Its not fair to say that quadrant sucks, and particularly I don't like that the article seems to be implying that the lagfixes that a lot of us are running are simply artificially inflating the SGS's score. The SGS has the best harware on the market crippled by bad firmware, and tbh I think its the lag fix that has allowed the hardware to be reflected in quadrant scores.
Anyway, quadrant doesn't suck. Its not perfect, but it does help you determine for example, how different ROMs on the same device compare for performance, as well as showing off things like GPUs that often don't get seen.
However it just runs a series of tests and weights the results accordingly. Particularly, the I/O seems to be given a lot of weight and so can be nobbled to increase the score. However, as anyone who has experienced excessive lag on their SGS can attest, it also works the other way. Without the lag fix, the SGS is a very pedestrian device, as the ~1000 quadrant scores tell you, while with the fix it FLIES.

Actually, some people are saying they notice no difference with the lag fixes it seems. And I've also seen forums full of people saying they can hear the difference between WASAPI/Exclusive audio and shared audio in Windows. Amazingly, out of the dozens of people trying to destroy me and demand it was implemented, none of them were willing to blind test (they were all just willing to say "it's obvious"). How many people here running the lagfix, have run any kind of blind test, or test with predictable steps to demonstrate a difference? Please, raise your hand people, because there is a huge difference between "it seems lag is gone" and "Lag is verified gone".
Quadrant is a guide, it doesn't test interactivity, and it only tests a few operations. It's similar to how a browser can pass ACID3, but have terrible compliance to new standards. Because people became so convinced of benchmarks accuracy, Nvidia and ATI started optimising for benchmarks.
Normal SSD's are also blazingly fast on benchmarks initially, but if they don't have TRIM, their performance drops significantly. That's another example of something benchmarks don't accurately test (because the testing is incomplete).
Use it to get a general idea of how the phone performs (although, specs might be more useful in some cases), but you probably need profiling and a predictable list of steps to diagnose the lag exactly. Run benchmarks which test according to the types of applications you are planning to run (if you play 3D games for instance, use a 3D game benchmark). But don't rely on them exclusively to tell you how well a device performs, because only running the applications and testing them yourselves can tell you.

LostAlone said:
Its not fair to say that quadrant sucks, and particularly I don't like that the article seems to be implying that the lagfixes that a lot of us are running are simply artificially inflating the SGS's score. The SGS has the best harware on the market crippled by bad firmware, and tbh I think its the lag fix that has allowed the hardware to be reflected in quadrant scores.
Anyway, quadrant doesn't suck. Its not perfect, but it does help you determine for example, how different ROMs on the same device compare for performance, as well as showing off things like GPUs that often don't get seen.
However it just runs a series of tests and weights the results accordingly. Particularly, the I/O seems to be given a lot of weight and so can be nobbled to increase the score. However, as anyone who has experienced excessive lag on their SGS can attest, it also works the other way. Without the lag fix, the SGS is a very pedestrian device, as the ~1000 quadrant scores tell you, while with the fix it FLIES.
Click to expand...
Click to collapse
But do you really think that one-click-lagix or whatever is that much faster than mimocan's one (like 2800 vs 1800)? I don't think so...

andrewluecke said:
How many people here running the lagfix, have run any kind of blind test, or test with predictable steps to demonstrate a difference? Please, raise your hand people, because there is a huge difference between "it seems lag is gone" and "Lag is verified gone".
Click to expand...
Click to collapse
*raisehand*
Predictable steps to demonstrate a difference:
1. Use 2 SGS, firmware of your choice
2. One with, say, 1 Click Lag Fix - the other one stock
3. Now for the test, perform simultaneously:
3.1. Open Market and go to "Downloads", update an app, close.
3.2. Open Contacts, quickly switch to favourites, dial Number. Drop call. Exit.
3.3. Open Messaging, conversation of your choice, quickly switch the writing language, write, send, exit.
3.4. bla bla goanforeva
Now if you don't notice an improvement there and in many other cases you most certainly have done something wrong.
If you are saying people are just being placebo-ed you are implying that everybody else besides you is unable to tell a real difference. Think about it, maybe it's the other way around.

When I got my device it came with the Asian JG4 firmware I think and I used it for 48hrs as a point of reference for this so called "lag" I updated my firmware to the latest we have and found zero difference in terms of performance ( same 2 day usage ) decided to flash my device with JM5 and used it w/o a lag fix for 2 days, notice a very slight improvment on how fast the inbox/contacts can open and then did a fresh flash with lagfix 2.x installed I didnt NOT notice any performance difference but I am always open and welcome to any lagfix that is stable,safe and fast ( in that order ) right now I have JG8 installed w/o lag fix and its very snappy, I still want to install a lag fix for this even if i dont see/feel any performance difference at all.. thats just me.. Now im wondering w/c lag fix is the most stable and safe.. stability/safty > speed
EDIT:
Also I believe it could be possible that certain versions of lagfixes work better with certain versions of firmware also, its all about getting the perfect combination.. altho my question still stands on w/c is the safest lagfix heheheh

Well actually i gave up on benchmarks.
To me the whole user experience is more important. If apps open instantly and the phone runs smooth then it's fine with me. I did notice some firmwares are better then other ones.
Right now i'm running JM1 (rev 3) with CFLagFix1.80 installed which makes the phone very stable and running smoothly so right now i'll stick to this firmware until a proper GPS fix is released or until Froyo is released.

Phandroid said:
*raisehand*
Predictable steps to demonstrate a difference:
1. Use 2 SGS, firmware of your choice
2. One with, say, 1 Click Lag Fix - the other one stock
3. Now for the test, perform simultaneously:
3.1. Open Market and go to "Downloads", update an app, close.
3.2. Open Contacts, quickly switch to favourites, dial Number. Drop call. Exit.
3.3. Open Messaging, conversation of your choice, quickly switch the writing language, write, send, exit.
3.4. bla bla goanforeva
Now if you don't notice an improvement there and in many other cases you most certainly have done something wrong.
If you are saying people are just being placebo-ed you are implying that everybody else besides you is unable to tell a real difference. Think about it, maybe it's the other way around.
Click to expand...
Click to collapse
Lol I think you didn't understand my question... I'm sure that these lag fixes all work, no doubt about that. But which of them is faster? For that i can't rely on quadrant i'm sure...

[Q] Anything better than JPC froyo?

Anything better than JPC froyo?

Sliced Bread?

No. Its the best IMO and I've tried 3 2.2 firmwares. With any luck Samsung will release the official one this month.

I hope so.

Jm7 is way better
Sent from my GT-I9000 using Tapatalk

my question is how come on the current froyo roms the linpack scores don't jump much... on the desire and nexus get somewhere in the region of 40 mflops...
Is it just cause they haven't properly optimised jit on the SGS yet?

Toast?
Sent from my GT-I9000 using XDA App

Sorry the HK 2.2 is by far better than JPC...

Ibanez33 said:
my question is how come on the current froyo roms the linpack scores don't jump much... on the desire and nexus get somewhere in the region of 40 mflops...
Is it just cause they haven't properly optimised jit on the SGS yet?
Click to expand...
Click to collapse
In another thread i pointed out the same thing as you are, because i read somewhere else that HTC had to do very little job to optimize JIT for Snapdragon, having google done that with AOSP.
They replied to me saying that first Froyo FWs for Desire and N1 reached ~ the same jump from Eclair Build: 8 to 14 Mflops. Only later, with progressively better setup, they reached the 40 Mflops zone.
It could also be that JIT, the feature that most of all power up Linpack benchmark, is completely disabled in Froyo builds like JPC. I asked how we could check this, but no-one answered properly to that until now.

I've just upgraded from JM2 to JPC and for sure JM2 is better. JPC has poor responce on finger gestures and is sometimes slow. I hope these problems are solved in the final release. I'm downgrading today!

clubtech said:
Sorry the HK 2.2 is by far better than JPC...
Click to expand...
Click to collapse
Care to elaborate and cite the differences?

Stefanauss said:
In another thread i pointed out the same thing as you are, because i read somewhere else that HTC had to do very little job to optimize JIT for Snapdragon, having google done that with AOSP.
They replied to me saying that first Froyo FWs for Desire and N1 reached ~ the same jump from Eclair Build: 8 to 14 Mflops. Only later, with progressively better setup, they reached the 40 Mflops zone.
It could also be that JIT, the feature that most of all power up Linpack benchmark, is completely disabled in Froyo builds like JPC. I asked how we could check this, but no-one answered properly to that until now.
Click to expand...
Click to collapse
Oh right.. I assumed JIT was enabled but poorly implemented. 14 Mflops without JIT it pretty good! can't wait to see what happens.. Can't wait for a better leak or a proper release..

Ibanez33 said:
Oh right.. I assumed JIT was enabled but poorly implemented. 14 Mflops without JIT it pretty good! can't wait to see what happens.. Can't wait for a better leak or a proper release..
Click to expand...
Click to collapse
JIT is enabled in JPC. We might see a 20 in the final release if we're lucky, but definitely nothing more than that. The Snapdragon phones apparently have a dedicated FPU which enable them to reach such ridiculous scores. Droid X, Droid 2 and all other 1GHz non-snapdragon phones get sub 20 linpack scores on Froyo.
Sent from my GT-I9000 using XDA App

ed10000 said:
JIT is enabled in JPC.
Click to expand...
Click to collapse
How do you know that for sure?
It's a proper question, it's not that i don't believe you.

Stefanauss said:
How do you know that for sure?
It's a proper question, it's not that i don't believe you.
Click to expand...
Click to collapse
I didn't think it was.

EarlZ said:
Care to elaborate and cite the differences?
Click to expand...
Click to collapse
- Does not mess with you efs folder. That alone makes the HK version a winner.
- Excellent GPS reception and lock.
- Excellent battery life
- No lag
- I only had ONE FC with the HK JP2, unlike JPC.

Stefanauss said:
How do you know that for sure?
It's a proper question, it's not that i don't believe you.
Click to expand...
Click to collapse
There are messages about it in the log e.g.
I/dalvikvm(18078): Jit: resizing JitTable from 8192 to 16384
D/dalvikvm( 2477): JIT code cache reset in 5 ms (1048428 bytes 19/0)

we'd need samsung to optimize the jit for their hummingbird, while it might not reach N1 scores it could probably get quite a bit better
but having seen how good samsung code is, well, that just isn't happening
ps: i agree i got less issues with jp2 hk than jpc as well, especially the lags and FC's and *battery life* (it's like double time)

I've been running JPC for 5 days now, and it's great. I have no desire to switch back to an Eclair rom. I still don't have a lag fix installed and don't feel I need to. I'm also not getting any FCs at all.
What's the deal with everyone wanting massive Linpack scores anyway? What software requires that grunt? Movies run perfectly, games are fast, and most other software wouldn't even touch the capabilities of either the Snapdragon or Hummingbird processors.
If it's a pissing contest you want to win against an N1 or Desire owner, simply load up Real Football 2010 and show them how comically fast it is, since it was written for their phone and no frame limiter was appied.

For me it's not about the benchmark per se.
JIT is one of those great Froyo features, and it can massively impact performance (it's clear, for instance, that Snapdragon vs Hummingbird architecture has very little percentage impact on Linpack, it's all about JIT optimization, like 15 to 40 just tuning JIT), not just in some pointless floating point benchmark.
Nevertheless, JIT is an issue where Samsung has to put its hands on code-wise, and they definitely proved during this childhood of this phone that they can very very very much suck at that.
So this benchmark could be helpful to understand how much effort Sammie is putting into Galaxy S Development, maybe.

Poll: Do you use JIT or not?

Simple poll. I am curious to see who uses JIT and who has it disabled? If you answer, please explain why you do or do not use JIT. Just thought I would get people's different input on this

i used to have it enabled but had seen no positive outcomes, just more lag.
but that was when i was running CM6... i havent tried it on CM7 yet.

I know JIT on Sense 2.1 was disastrous for the most part. Have stayed away from it for the most part.
JIT on CM7 is actually very stable, however I observe absolutely no improvement or noticeable change in performance anywhere.
Then again, people also claim a smoother experience when "Allow purging of assets" is unchecked, even thought it is meant to improve performance of low memory devices like ours... YMMV, I guess.

My question is, what are the supposed benefits? Scoring higher on a particular benchmark score and thats it? I agree. It doesn't seem to make my phone any smoother, if anything, it makes it more laggy.

I've been using jit since the days of Ic3 rom and damage's roms as well. I think it just improves data. No speed on the phone just how the phone complies data. I think. But from my time on here if you can't overclock to 768 and run stable then I'd recommend avoiding jit.
Yea its Me Again With The
Modified Hero

In aosp 2.2 I would get an extra 20 or so on my quadrant score with JIT enabled. In gingerbread I haven't seen any improvement at all. I leave it disabled because I heard it uses more ram to speed things up.

I use JIT and I always have since installing custom ROM images. There's a lot of hearsay left over from long before I joined xda-developers that says it causes instability. But this is probably more to do with the original way JIT was brought to the Hero.
The latest official software for the Hero is built from Android 2.1. JIT was not introduced into Android until 2.2. So as far as I know, the original method to implement JIT on the Hero was to hack it into the official software. This is likely where the instabilities were found.
I've been using JIT since dabbling with CM6 (and its derivatives), and I've never seen any negative effects. I do, however, always decrease my VM heap to 24m and enable compcache at 18% when using JIT. Not doing so MAY cause JIT to starve the phone of memory, which could be another source of the instabilities you've seen mentioned.
Some people say JIT isn't necessary because its effects are only noticed in benchmarks such as Linpack. This, simply put, is false. JIT is always going to offer a performance increase. Now, depending on how you use your phone, the increase may not always be very noticeable, but that doesn't mean it's not there. And the less time the VM spends using the processor, the more battery life you're going to see. That's an angle that isn't always addressed when JIT is discussed.
My advice is to leave it enabled as long as you don't specifically see any issues with it. Our sister phone of sorts, the Droid Eris, now has it enabled by default in CM7.

Thanks jasonmaloney, I always prefer hearing answers from people with technical know-how such as yourself. On a CM performance related note, what is your opinion on people reporting better performance with "Allow purging of assets" disabled?

c00ller said:
Thanks jasonmaloney, I always prefer hearing answers from people with technical know-how such as yourself. On a CM performance related note, what is your opinion on people reporting better performance with "Allow purging of assets" disabled?
Click to expand...
Click to collapse
I was actually the one who submitted the patch to enable it by default. I've only ever heard of specific issues in relation to ADWLauncher, which, in my opinion, shouldn't ever be used in the first place due to the numerous better-written alternatives.
But I'm starting to wonder whether it has anything to do with the GPS problems people have been seeing.
All I really know for sure is that the graphics subsystems in CM7 for the Heroc are screwed up, and that they're probably going to be that way even when CM7 is finalized.
EDIT: If anyone can find compelling evidence that having it enabled is causing issues, I'll revert the patch and make it disabled by default.

jasonmaloney said:
All I really know for sure is that the graphics subsystems in CM7 for the Heroc are screwed up, and that they're probably going to be that way even when CM7 is finalized.
Click to expand...
Click to collapse
Is that a good or bad thing? Yes the words used dictates it's meaning, but what would have been the plus factors if it were squared away?

oohaylima said:
Is that a good or bad thing? Yes the words used dictates it's meaning, but what would have been the plus factors if it were squared away?
Click to expand...
Click to collapse
The most glaring example of a problem is seen in running Neocore. None of the textures show up.

EXT4 worth it?

Hi, so after cm rooting i noticed there is also an ext4 upgrade...is this worth it and will I have data lose during the change? Im on 2.3.3 and am wondering if it is really worth it! Ed

are you kidding me?
besides that this post should not even be in this forum (try Q & A) there are hundreds of other posts and threads discussing this topic if you only use your -(0-0)- !

Yes and no
It may have some advantages but as for what I'm not sure but as for nay major advantages I would say no. I'm still using EXT2 and my benchmarkes are still 1900+. I've tried almost all the other lagfixes and found no real advantage. The only thing I hate about custom kernels with lagfix is the secondary samsung splash screens and custom splash screen. They kill the post time.

I would say it isn't as worth it as what people say. First thing most people do after converting their filesystem is run quadrant. It's possible that improved quadrant scores don't translate to real world performance though.
Even worse, running quadrant actually engages the placebo effect so you walk in with a more positive impression. Meanwhile, I don't recall ever seeing anyone from the EXT4/EXT2 i9000 community running blind tests, and neither development community has actually shown any evidence formal testing has been performed. All the arguments seem to be based around quadrant and PC testing. If methods like this were applied to clinical testing, every drug would pass
Honestly, give both a try, but do it blindly.
Why Quadrant may be wrong
This is just a bit of background why Quadrant's scores may not reflect real life performance. Until we check the actual ratio's of Quadrant, and compare with actual usage ratio's though, we can't identify how "real" it's scores are.
Consider a benchmark which produces 1 final score. It may be calculated by:
[MAX TIME - Time to read 1000mb] + [Max time - time to write 1000MB]. In this case, both scores contribute to 50% of the final score, which can be worth 2x MAX Time.
Scenario 1: Time to read/write is both the same
Scenario 2: Read time is 1% shorter than Scenario 1, but write time is 1% longer. Both will have the same score in Quadrant..
Scenario 3: Read time is 5% longer than Scenario 1, but write time is 50% shorter. Scenario 3 will get the best score
Which one is ACTUALLY faster though. The benchmark-toting individuals will claim Scenario 3 is faster, because of the score. HOWEVER, that may be incorrect. Consider the following:
If a user reads 100x more data than they write:
1) Clearly, faster read scores are more important.
2) The BEST filesystem will be Scenario 2, despite being equal last.
3) Scenario 1 will be mid place
4) The scenario with the best score, will actually have the WORST performance.
5) A drop in 1% read performance would need a HUGE increase in write performance to actually be faster.
Until we have an idea of how accurate Quadrant REALLY is, run your own tests, and do so without knowing which filesystem is running. High quadrant scores may boost your e-penis size, but as you can see, it is theoretically possible for the scores which are produced to score slower performing filesystems more highly than faster ones. Disappointingly though, a decreasing number of users/developers at XDA these days are actually interested in the truth, and simply in not being wrong.
Even worse, the community for some reason seems VERY anti-RFS, and wont give it a chance regardless. It might be a LOT better than it used to be. Either way, it seems to be good enough for me.
Ignore the theatrics and run a blind test. That's the only way to determine what is ACTUALLY faster.

monkeytennis said:
Hi, so after cm rooting i noticed there is also an ext4 upgrade...is this worth it and will I have data lose during the change? Im on 2.3.3 and am wondering if it is really worth it! Ed
Click to expand...
Click to collapse
I guess you mean CF root right? Will just answer the data loose question. No you shouldnt. But do a backup before. Its fast and easy (if you are on CF root that is)
If its worth depends on you? You experience any lag on rfs? Phone slow?
ramrod54 said:
It may have some advantages but as for what I'm not sure but as for nay major advantages I would say no. I'm still using EXT2 and my benchmarkes are still 1900+. I've tried almost all the other lagfixes and found no real advantage. The only thing I hate about custom kernels with lagfix is the secondary samsung splash screens and custom splash screen. They kill the post time.
Click to expand...
Click to collapse
@ramrod54 , where did you get ext2 support on JVK? And what the?
What samsung splash screens and custom splash? What rom and kernel are you on? And what lagfixes? And we both know quadrant score doesnt matter does it ?

Yes, it's worth it. Some things (Android Market, Gmail) works really MUCH faster then on rfs.

Unrealwolf said:
Yes, it's worth it. Some things (Android Market, Gmail) works really MUCH faster then on rfs.
Click to expand...
Click to collapse
Hrm, I've never noticed a difference. Market is slow on any room, hell market.android.com is slow too. Gmail always worked fast for me, on any rom.
Personally, I don't see or feel the point in using anything but rfs, but I suppose if someone has half a bazillion apps installed, then maybe an alternative filesystem might be better.
I say try it. If you notice a difference, good for you. If you don't, then stick with rfs.

What about battery performance ? from what I have read, battery performance is also better with RFS.

I always use ex4, its not as needed now on gingerbread but I just prefer the file system...it is better than RFS...but RFS has improved a great deal so you may not noticed that much difference, the rom may become a little smoother..You wont get data lose because of ex4, maybe the way the kernel is built...dont forget that 2.3.3 gingerbread is still beta and without the source code for the kernel you cant expect great things yet, although chainfire has done some amazing work and now we can change the file system using his app....works really well.
Also regarding battery, the difference in performance is such a small margin that its not even an issue.
What alot of people aren't aware of is that the Nexus S for example uses ex4 file system as default straight out of the box
Its not just a lagfix for the galaxy s, its a very good file system too...
Just a side note on Quadrant, ex4, ex2 will trick the app...if you buy the pro version, you will see how much the file system stretches on the bar...Quadrant is more for fun....or HTC

Think it´s worth cause rfs slow down your system after a while