Related
So I've gotten anywhere between 2.5 to 5.1 MFLOPS using various ROMS and have yet to be able to notice something incredibly different.
710...768...806 - What does it matter? What program other than Linpack shows a sizable difference? Sure, maybe things open quicker? What am I missing here?
I read all this about achieving high MFLOPS and OC Kernels yet I still can't achieve smooth game play on 16 bit emulator on my phone with 5 MFLOPS.
MFLOPS mean jack when there is little way to observe the difference.
Carreno43 said:
So I've gotten anywhere between 2.5 to 5.1 MFLOPS using various ROMS and have yet to be able to notice something incredibly different.
710...768...806 - What does it matter? What program other than Linpack shows a sizable difference? Sure, maybe things open quicker? What am I missing here?
I read all this about achieving high MFLOPS and OC Kernels yet I still can't achieve smooth game play on 16 bit emulator on my phone with 5 MFLOPS.
MFLOPS mean jack when there is little way to observe the difference.
Click to expand...
Click to collapse
Linpack MFLOPS - measures the floating point performance of your phone.
710...768...806 - refers to CPU frequencies
increasing the CPU frequency should equate to better general-case performance, including things opening quicker as you mention, but also other types of general snappiness like moving between screens and so forth.
"I read all this about achieving high MFLOPS and OC Kernels yet I still can't achieve smooth game play on 16 bit emulator on my phone with 5 MFLOPS." - This may have less to do with the performance of your phone and more to do with the emulator itself. Emulation is a surprisingly CPU intensive operation, especially if the emulater isn't well written. Rather than looking a ton into overclocking and JIT, etc, maybe you ought to look for a better piece of software.
Yea,
I've tested most emulators. Wish there was an Atari emulator!
Thanks for the response.
Carreno43 said:
Yea,
I've tested most emulators. Wish there was an Atari emulator!
Thanks for the response.
Click to expand...
Click to collapse
I have run roms with 5.1 MFLOPS and now am running a rom that gets 3. I can honestly say I see no difference.
Spencer_Moore said:
I have run roms with 5.1 MFLOPS and now am running a rom that gets 3. I can honestly say I see no difference.
Click to expand...
Click to collapse
I can see a difference... in battery life! Lolz
g00gl3 said:
I can see a difference... in battery life! Lolz
Click to expand...
Click to collapse
Haha Awesome
it looks like to me that everyone is look at the wrong things.
for example:
I am running a Tom that is getting on a average of 4.9 mflops.
I get smoother screen changes....
streaming videos online is so much faster compared to a 3.0 mflop rom. ...
tubetube and other....... websites.
to me everything I do is faster...
I.don't play game on my phone so I don't know how that is.... but everythng else I do is very much faster.
I love high mflop roms...
I have notice about mflops is that it matters about the kernal that u use.
Isn't it true that the MSM7201 in our phones is already overclocked to get to 528mhz as it is? I see a lot of different places saying Qualcomm chips in general are just not worth overclocking... and since our chip is factory overclocked to begin with... just seems like we're pushing the already-pushed here. But the way this board goes crazy for overclocking... it's contradictory. I don't know what to think, cause I've run Linpack myself and gotten ~4.9 with JIT + OC versus ~2.5 without... but I'm with the OP on this one... only difference I'm seeing is my battery draining faster and my phone getting physically hotter.
xatch said:
Isn't it true that the MSM7201 in our phones is already overclocked to get to 528mhz as it is? I see a lot of different places saying Qualcomm chips in general are just not worth overclocking... and since our chip is factory overclocked to begin with... just seems like we're pushing the already-pushed here. But the way this board goes crazy for overclocking... it's contradictory. I don't know what to think, cause I've run Linpack myself and gotten ~4.9 with JIT + OC versus ~2.5 without... but I'm with the OP on this one... only difference I'm seeing is my battery draining faster and my phone getting physically hotter.
Click to expand...
Click to collapse
I have OC and JIT and getting about 5.1 mflops and haven't had worse battery life or a hotter phone. It could be the battery I'm using but meh (got a replacement one that's 2000 mAh) but I got worse battery life on leak 2.1 than with the rom I'm using now that has OC, JIT, LWP, etc. I can go about 8 hours with heavy texting, moderate internet usage and my lwp's running and it only goes to about 65%
so OC and Jit don't make that big of a difference in gameplay?
Sent from my Eris using the XDA mobile application powered by Tapatalk
What the OP and all the respondents are noting is frankly quite typical of what happens when performance tuning focuses on a single benchmark: the results obtained are essentially meaningless for different kinds of activities on the same device.
That's because there's a whole chain of dependencies that are specific to a given task, any number of which could become the rate-limiting factor; and a different task on the device will have a different set of dependencies and therefore different rate-limiting behaviors.
For instance, let's take writing to an SD card as an example: there's really no way that OC'ing will speed that up in a measurable way - because the CPU isn't the rate limiting factor.
That Linpack benchmark measures floating-point performance using a software library (as the Eris has no hardware FP capability). Most of the apps on the phone do very little FP work at all. But, it's not a bad test of CPU speed, because it performs no I/O. It also may not be very memory bandwidth intensive, either (if the problems it works on stays in the uP cache and there are few page faults).
OTOH, a game emulator needs to write to the graphics display (at a minimum) and possibly also do read I/O from flash.
Different task, different results. Sometimes things can be improved by hardware or firmware; sometimes the software itself needs to be improved.
bftb0
im sorry, but could you just answer in plain english
Sent from my Eris using the XDA mobile application powered by Tapatalk
TheSonicEmerald said:
im sorry, but could you just answer in plain english
Sent from my Eris using the XDA mobile application powered by Tapatalk
Click to expand...
Click to collapse
Lima beans bad.
Pork good.
Slow phone bad.
Fast phone good.
bftb0
Thanks for my laugh of the day on that one.
What I'm trying to get at is -
I should be able to play, at the basic level, Sonic or Mario - Without issues.
At the very least
I prefer roms over market games any day (Sonic, Mario, Zelda, DK-Country) and it cripples the phone, at least in my view, that I cannot enjoy the fruits of old games.
Although, I was able to find some old Atari games - which, thankfully, work without stuttering.
Right now the jump between 1ghz to 1.1ghz shows no real world benefit. I have a couple of questions:
1. Does overclocking to 1.1ghz effect the battery enought to see a difference?
2. Does undervolting save battery enough to see a difference?
3. If i have a custom kernal but still running at 1ghz, will the battery be the same/worse/better then runnning 1ghz on stock kernel
4. Does undervolting have any negative effects on performance
Thanks in Advance!! XDA RULES!!
The best type of experience, is 1st hand.
Why not try it out and make this thread a log of your results?
1username4thisforum said:
The best type of experience, is 1st hand.
Why not try it out and make this thread a log of your results?
Click to expand...
Click to collapse
Not trying to be rude, but does not answer my question. Why go through the procedure when someone who has already done it or has experience with it is kind enough to post answers.
primeboss said:
Right now the jump between 1ghz to 1.1ghz shows no real world benefit. I have a couple of questions:
1. Does overclocking to 1.1ghz effect the battery enought to see a difference?
2. Does undervolting save battery enough to see a difference?
3. If i have a custom kernal but still running at 1ghz, will the battery be the same/worse/better then runnning 1ghz on stock kernel
4. Does undervolting have any negative effects on performance
Thanks in Advance!! XDA RULES!!
Click to expand...
Click to collapse
1 Yes it does, but the phone only uses that frequency when pushed to limits, so not much.
2 Yes, i believe it does.
3 I found faux kernel to drink my battery like water even oj stock clock. Edgan's didnt have that problem.
4 it may cause random reboots if ur UV lvls are beyond the phone's capabilities.
Ps1: hes got a point, all impressions are too personal, they dont translate to universal experience.
Ps2: the greatest use of OC on the atrix right now is the webtop, that really pushes all possible processing power.
Sent from my PocketDock
Viamonte said:
1 Yes it does, but the phone only uses that frequency when pushed to limits, so not much.
2 Yes, i believe it does.
3 I found faux kernel to drink my battery like water even oj stock clock. Edgan's didnt have that problem.
4 it may cause random reboots if ur UV lvls are beyond the phone's capabilities.
Ps1: hes got a point, all impressions are too personal, they dont translate to universal experience.
Ps2: the greatest use of OC on the atrix right now is the webtop, that really pushes all possible processing power.
Sent from my PocketDock
Click to expand...
Click to collapse
Thank You!
Hello,
I've had the phone rooted and the new cm7 (bad***), it all runs great I just wonder how some people are getting 5k Quad score while I am at the same 3.2 as it was on stock. I do have the same Kernel and everything when rooting and flashing went so smooth. Is there something I am missing.......
Thanks in advance.
MyyH said:
Hello,
I've had the phone rooted and the new cm7 (bad***), it all runs great I just wonder how some people are getting 5k Quad score while I am at the same 3.2 as it was on stock. I do have the same Kernel and everything when rooting and flashing went so smooth. Is there something I am missing.......
Thanks in advance.
Click to expand...
Click to collapse
You can overclock it to 1.6 ghz in the CM settings.
flucks said:
You can overclock it to 1.6 ghz in the CM settings.
Click to expand...
Click to collapse
I did, than quadrant freezes while I'm running it. As in when I click submit score, it automatically goes back to the 1st 2d test and than force closes.
"sorry I left that out" :/
call me ignorant but do people STILL think that quadrant scores mean soemthing? why are people still comparing them???
Some people just want to stroke their epeen on the net.
And as to overclocking - not everyone will be able to overclock. There's a reason the device is only sold as 1.2 GHz - that's all it was tested to. Some might hit 1.4, some might hit 1.6, some might be right at the edge and only be able to do 1.2.
its not the quadrant score that matters. Its the idea of why it is different. All the devices have the same cpu have the same kernel and are rooted/flashed as stated in the forum (the same way). So why is mine doing so when clocked and running. I don't care what the score is. even 1200 score is enough for a phone. I didn't want to stroke anything. Its the matter of where the problem/case/scenario is coming from. As in, will it cause other problems and is it a problem at all. having had 5 android rooted/flashed devices I've never experienced it........... Why do people have to be ignorant and troll a forum is an issue I cant understand?
Bump for help
Sent from my SGH-I777 using XDA App
Cm7 rooted love it
MyyH said:
its not the quadrant score that matters. Its the idea of why it is different.
Click to expand...
Click to collapse
if you're asking why your quad score differs from other ppl's phone with the same setup, then you need to research more.
Not all phones are built the same. Just because they all have the same hardware and software, doesnt mean they'll all operate the same.
So I installed SetCPU today. Been testing the kernels ability to work underclocked at the max of 918mhz. Also set the scaling to conservative. After a days use it's been as good as normal full speed, 1512mhz
The battery lasted throughout the day, compared to my first two days of stock settings with only 6 hours of good use.
I'll keep playing. Still want to do some testing and benchmarks to make sure it's not under performing. But at least at the user level it seems to react the same.no lag.
I did confirm the clock speed out side of SetCPU using system panel.
Sent from my rezound.
Don't bother using benchmarks to rate a phones performance that is a fatal error there. Benchmarks never effectively rate a phones performance. I just go by how smooth the phone runs and it does it run everything I throw at it. If so gg pz end of story.
zetsumeikuro said:
Don't bother using benchmarks to rate a phones performance that is a fatal error there. Benchmarks never effectively rate a phones performance. I just go by how smooth the phone runs and it does it run everything I throw at it. If so gg pz end of story.
Click to expand...
Click to collapse
True, but people still like to get the general idea. There are many factors.hence why I said the over all feel seems the same. Im going to use antutu, and quadrant. 5 times each to get a range.=-)
Sent from my rezound.
Izeltokatl said:
True, but people still like to get the general idea. There are many factors.hence why I said the over all feel seems the same. Im going to use antutu, and quadrant. 5 times each to get a range.=-)
Sent from my rezound.
Click to expand...
Click to collapse
Well whatever works for you. Just saying Quadrant is a poor tool to use to bench for many reasons which I won't go over. Antutu is nice for SD speed testing I think, oter than that meh. Benches are just for numbers for people to flex their epeens with. They just really don't truly gauge a devices performance.
zetsumeikuro said:
Well whatever works for you. Just saying Quadrant is a poor tool to use to bench for many reasons which I won't go over. Antutu is nice for SD speed testing I think, oter than that meh. Benches are just for numbers for people to flex their epeens with. They just really don't truly gauge a devices performance.
Click to expand...
Click to collapse
Benchmarks do have a some good uses... while comparing different phone models with benchmarks can be iffy, it can give an overall insight, (things like graphics capabilities with very GPU extensive games) but in the end user experience and daily use are the real judges.
Where benchmarks can be of the most use, is when comparing changes to the same phone model.
E.G. Comparing performance impacts of AOSP vs Sense, overclocking and under-clocking, and de-sensing/bloat removal.
When used for these reasons, you can get a really good feel for how changes are affecting your device overall. Even then, benchmarks are not the be all end all, and user experience is still important. As you may introduce lag or other performance issues that do not show up in benchmarks.
Which temp root method are you using? Mine isn't staying rooted long enough for me to justify using setCPU at all...
The new version and the one that comes with the newest clean tool stays until reboot.
Marine6680 said:
The new version and the one that comes with the newest clean tool stays until reboot.
Click to expand...
Click to collapse
Thx for the info, guess I must still be using the outdated method. I'll run the latest version of Scott's Clean tool and give it a shot.
Izeltokatl said:
So I installed SetCPU today. Been testing the kernels ability to work underclocked at the max of 918mhz. Also set the scaling to conservative. After a days use it's been as good as normal full speed, 1512mhz
The battery lasted throughout the day, compared to my first two days of stock settings with only 6 hours of good use.
I'll keep playing. Still want to do some testing and benchmarks to make sure it's not under performing. But at least at the user level it seems to react the same.no lag.
I did confirm the clock speed out side of SetCPU using system panel.
Sent from my rezound.
Click to expand...
Click to collapse
Please let us know what settings you use that work for you.
I generally stay temprooted unless I'm going to be away from a charger for a bit and need BT (since you can't turn BT back on after temproot). I wouldn't have SetCPU autostart on boot (since it won't ever be able to get root access immediately after boot).
Meanwhile, I also set it to conservative and will see what that accomplishes.
A kernel needs to support setcpu, stock kernels do not. You need to flash a custom kernel, so you need a development phone or s-off.
Sent from my ADR6400L using XDA App
This kernel apparently does work with SetCPU. I've confirmed using other cpu monitoring apps that the clock speed changes are capped.
I own 7 android phones, and have been rooting, overclocking, undervolting each and every single one of them (well one I still cant get rooted). I know when the cpu is under clocked and when it is not. Been doing these tweaks for 4 years now. If you use a tool like System Panel, at stock settings you can see the max cpu around 1500 on our little bad boy. When it peaks out the clock speed is shown. When you under clock it, then check again it won't go beyond the max cpu set in my testing I put a ceiling at 918mhz. System Panel reported full CPU usage (100%) at clock speed 918mhz. Typically with stock kernels, your absolutely right, changes to SetCPU do nothing at all to the real cpu. Which is confirmed, when I reboot and dont have root, if I attempt to use SetCPU and make the changes, System Panel reports 1500mhz (roughly) at full load regardless of what I set it to in SetCPU. If I did this to any of my other phones with stock kernels, you are correct it makes no difference as SystemPanel reports the stock max setting.
No I'm not being mean or aggressive, just saying. =-) And no don't believe me, but test it yourself and confirm or prove me wrong some other way and I admit error. Either way, half the fun is messing with the phone and trying to get it to do things it should not do.
Grnlantern79 said:
A kernel needs to support setcpu, stock kernels do not. You need to flash a custom kernel, so you need a development phone or s-off.
Sent from my ADR6400L using XDA App
Click to expand...
Click to collapse
Sent from my rezound.
Izeltokatl said:
No I'm not being mean or aggressive, just saying. =-) And no don't believe me, but test it yourself and confirm or prove me wrong some other way and I admit error. Either way, half the fun is messing with the phone and trying to get it to do things it should not do.
Click to expand...
Click to collapse
Or I would say, "half the fun is messing with the phone and trying to get it to do things it should have always been allowed to do...." Just sayin'.
Are you using the profiles at all? Im interested to know what seems to be working out the best for you.
Izeltokatl said:
True, but people still like to get the general idea. There are many factors.hence why I said the over all feel seems the same. Im going to use antutu, and quadrant. 5 times each to get a range.=-)
Sent from my rezound.
Click to expand...
Click to collapse
In my view, the "benchmarks" would be an OK measurement if you were comparing apples to apples.
I tried running both Linpack and Quadrant on the very recently and dearly departed Incredible right after a fresh reboot and having charged the battery overnight...when the thing should have been at it's freshest.
I got wildly different scores each time I ran it after a reboot...knowing that on both programs the scores would improve the more times you ran the test.
It didn't seem to me that either program was a reliable indicator of what my phone was capable of. I didn't even trust them to tell me whether something I'd done...cleared cache or deleted bloatware...had any real effect.
It simply boils down to how the phone feels. That's not scientific, but it works for me.
douger1957 said:
In my view, the "benchmarks" would be an OK measurement if you were comparing apples to apples.
I tried running both Linpack and Quadrant on the very recently and dearly departed Incredible right after a fresh reboot and having charged the battery overnight...when the thing should have been at it's freshest.
I got wildly different scores each time I ran it after a reboot...knowing that on both programs the scores would improve the more times you ran the test.
It didn't seem to me that either program was a reliable indicator of what my phone was capable of. I didn't even trust them to tell me whether something I'd done...cleared cache or deleted bloatware...had any real effect.
It simply boils down to how the phone feels. That's not scientific, but it works for me.
Click to expand...
Click to collapse
Linpack and Quadrant are not reliable benchmarks. TBH I don't take any of the benchmarks seriously, they are more for entertainment for me. But to each their own right?
Yeah some of the benchmark apps are a bit unreliable to say the least...
If I use one, I try to use ones that Anandtech uses. I trust them to find the better benchmark tools.
Ok so im rooted and overclocked and was using setcpu then decided i wanna try something different so i tried system tuner! When i checked the cpu it said that one of the processors are off line! Then i pressed the info button and sure enough it says only reading one! So i went through the settings and found force both cores online!
Since then i have no lag and virtually no checkerboarding on the web! Anyway i was just wondering if im the only one who noticed this and maybe it could help those who say that they are still getting lag on they're roms using dag's kernel!
Also i hope devs will notice this thread since i can't post there yet and take advantage of this how ever they can!
Now don't quote me on this but most likely the second core only turns on for processor intensive activities such as high graphics games or multiple programs running at once. I do find it hard to believe that it would be totally disabled. Most likely this is done to conserve battery.
blitzer320 said:
Now don't quote me on this but most likely the second core only turns on for processor intensive activities such as high graphics games or multiple programs running at once. I do find it hard to believe that it would be totally disabled. Most likely this is done to conserve battery.
Click to expand...
Click to collapse
Nope i checked that i had 10 apps open two were games (dead space and gta III) One cpu online even on performance! I see 50 views i hope others chime in and let us know what you are thinking
Btw they Did this i heard to the galaxy nexus with the tiomap 1.2 so we'll see what others find
truth77 said:
Nope i checked that i had 10 apps open two were games (dead space and gta III) One cpu online even on performance! I see 50 views i hope others chime in and let us know what you are thinking
Click to expand...
Click to collapse
Okay if this really is the case I could also see at&t disabling the second core totally to save battery because of lte but i guess it will take a dev that has more experience with how qualcomm's multicore cpus work in android. report back with differences in battery life like how much faster does it drain now that both cores are forced on.
if you want both cores on click on boot settings and enable force all cpus online. that heats up your phone and eats more battery though+I do not see any benefits doing that.
blitzer320 said:
Okay if this really is the case I could also see at&t disabling the second core totally to save battery because of lte but i guess it will take a dev that has more experience with how qualcomm's multicore cpus work in android. report back with differences in battery life like how much faster does it drain now that both cores are forced on.
Click to expand...
Click to collapse
I've had it like this for 4 days on average i will take of the charger at 8am now is 8:30pm and i have 27% but i use my navigation for my Job! By 10:30 or so ill have 15% and recharge!
Settings
1836 max
192 min
Governer
Smartassv2
Both cores pushing
Screen off
192 max
In call
384 max
Tomorrow ill post some pics of battery life usage!
And my phone doesn't get any hotter than normal not even while using my navi! Mostly it just gives no lag and better rendering in the browser/maps/etc!!
I was under the impression that Gingerbread didn't fully utilize multiple cores. Need HC or ICS...
Broken said:
I was under the impression that Gingerbread didn't fully utilize multiple cores. Need HC or ICS...
Click to expand...
Click to collapse
Same, but having a better processor helps. Like exynos. I bet once we update to ics if it ever happens, the differences will be only minor between processors, as it runs so nice.
Got system tuner pro, and it shows speed bars on both cpus running? I didn't change a thing?
canecbr600 said:
Got system tuner pro, and it shows speed bars on both cpus running? I didn't change a thing?
Click to expand...
Click to collapse
Really? I switched Roms twice today and had to reset that each time! Cpu.0 online Cpu.1 offline! Like i said am i the only one? Lets hear from more people and let us know of any lag or rendering changes after turning on both cpu's! Battery too, i'll post mine tomorrow.
I thought I'd play and I have CPU0 running and CPU1 running.
truth77 said:
Btw they Did this i heard to the galaxy nexus with the tiomap 1.2 so we'll see what others find
Click to expand...
Click to collapse
Not entirely true.. the Galaxy Nexus has a kernel governor that turns one core off when the SCREEN IS OFF, but not when the phone is being used. Multiple kernel creators have since implemented this into their kernels. It is called "hot plugging" and it just turns CPU 1 offline when the screen is off and turns it back on when the screen is on
Sent from my DROID3 using xda premium
Just checked mine, rooted and OC with DaG's 0.1 version (first version). When I looked, it said the second CPU was offline. Changed it to online, we'll see how that impacts battery life.
How much of an advantage is smartassv2 anyway?
I just tried this with system tuner and both cpus were working but wone was of and on and zero was always on.
I am running stock rooted. If you just sit yhere and watch it you will see tje sevond core fires and shuts down alot.
truth77 said:
Really? I switched Roms twice today and had to reset that each time! Cpu.0 online Cpu.1 offline! Like i said am i the only one? Lets hear from more people and let us know of any lag or rendering changes after turning on both cpu's! Battery too, i'll post mine tomorrow.
Click to expand...
Click to collapse
Same for me (CPU 0 on, CPU1 off, most times) and I'll say I have noticed no real changes in functionality (speed, rendering, etc) or battery life...
I guess jury is still out or is this a YMMV kind of thing?
I installed system runner and watched the cpus. One was on and the other kicked in periodically
Mine said it was offline as well. Forced it on and am not noticing any difference in speed or temp.
Ill leave it like this to test it further.
Sent from my SAMSUNG-SGH-I717 using Tapatalk
Do you have to be rooted to force both cores on?
Sent from my SAMSUNG-SGH-I717 using xda premium
g2theno said:
Do you have to be rooted to force both cores on?
Sent from my SAMSUNG-SGH-I717 using xda premium
Click to expand...
Click to collapse
As far as I know yes you must have super user permission to alter such system activities
I don't know why everyone is in such a rush to force the second core online, it turns on and off when it needs to.