[Q] FPS cap/framerate question - Galaxy S I9000 General

Hi,
I have a question about the framerate of the sgs.
How come when running benchmarks or just monitoring your fps, the framerate is OR 67 (on galaxian) OR 33/34. The frequency's in between are really rarely used.
It seems like when the framerate of 67 is not achieved, the framerate drops to half the speed automatically.
It's not just on galaxian kernel but every kernel i ever used.
Has anyone some information on this?
It's not a problem or anything just personal interest.

I have it too.
I had it on speedmod, and now i have it on galaxian.
So it's not only galaxian which is doing it.
On speedmod the max fps was 55 (i think) and in quadrant i could see it was doing 55 or 28 (exactly half of it) with al the 3d tests.

Exactly... anyone knows what is behind this?
Sent from my GT-I9000 using XDA App

I haven't heard of limits other than the default(?) ~55-56 fps. Pretty sure it's there because rendering 60+ is a waste of battery life.

Its a byproduct of vsync when the phone can't hold the fps steady at the frame limit.
Sent from my GT-I9000 using XDA App

Increasing framerate also seem to cause colour profile to change and appears washed out. Check out snail talon kernel if you want to try.
Sent from my GT-I9000 using XDA App

Related

Linpack goes multithread!!

Finally we have a fair test for the dual cores. Just been running it and i have the top 5 scores!!
Is that 1608mhz , your phone must be on fire
Now have 150.595. It was a bit warm. I expect it to fall as the number one soon, i m sure there are guys on here with over 1.7ghz. I cant seem to get that to stay stable.
Finally! My highest (1.2) was 122 although that was an inconsistent result. My average high is around 100. Wonder what the Sensation and Tegra devices are hitting.....
Regards.
Best i can do so far.
I'm getting wildly inconsistent results. Managed to get 120 at 1200mhz with a accuracy of 2.2 after a dozen runs.
Sent from my GT-I9100 using XDA Premium App
Yeah you just have to keep trying until you get a high score with a valid accuracy. It wont let you save unless its consistently accurate.
MaBlo said:
I'm getting wildly inconsistent results. Managed to get 120 at 1200mhz with a accuracy of 2.2 after a dozen runs.
Sent from my GT-I9100 using XDA Premium App
Click to expand...
Click to collapse
did you set both minimum speed and maximum speed to 1200?
152 is my new high, thats it for a while, battery flat, phone rather warm!
140 is my best stable score, running @1.425ghz using Tegrak
rovex said:
152 is my new high, thats it for a while, battery flat, phone rather warm!
Click to expand...
Click to collapse
the top 10 has only your results in it, lol
Its the Moto Zooms i worry about., Although the Tegra is slower the Zoom seems to be able to hit up to 2GHz. We need a 1.8Ghz SGS2 to keep them down..
I do wonder if the Atom powered tabs will beat us though.
ph00ny said:
did you set both minimum speed and maximum speed to 1200?
Click to expand...
Click to collapse
Yes I did.
Sent from my GT-I9100 using XDA Premium App
I got 155.597 MFLOPS with my Galaxy S II overcloked to 1.56 GHz at 1.375v on Core voltage.
The rest is default.
I can probably break 160 MFLOPS if i take the CPU speed up to 1.65 GHz if i can get it to run stable there.
rovex said:
Its the Moto Zooms i worry about., Although the Tegra is slower the Zoom seems to be able to hit up to 2GHz. We need a 1.8Ghz SGS2 to keep them down..
I do wonder if the Atom powered tabs will beat us though.
Click to expand...
Click to collapse
Let me get this straight, you're 'worried' about another phone putting in a better score than your phone on a benchmark program?
Sent from my GT-I9100 using Tapatalk
Pagnell said:
Let me get this straight, you're 'worried' about another phone putting in a better score than your phone on a benchmark program?
Sent from my GT-I9100 using Tapatalk
Click to expand...
Click to collapse
LOL, my thoughts exactly reading this entire thread...
Pagnell said:
Let me get this straight, you're 'worried' about another phone putting in a better score than your phone on a benchmark program?
Sent from my GT-I9100 using Tapatalk
Click to expand...
Click to collapse
He's not even talking about a phone, if I understood what he meant, he's talking about the Xoom tablet.
[Sarcasm] Yes im going to have sleepless nights for weeks about it..[/sarcasm]
I would have thought the context (competitive spirit) was obvious..
Anyway it seem the Sensation bunch have found the Linpack cheat. 200 on a 1.2ghz non overclocked Sensation.. Nah...
Ok, now i managed to get 170.027 MFLOPS in Linpack with the CPU at 1.58 GHz and the Core voltage on 1.375v .
So far the phone are 100% stable at this clock.
Tom-Helge said:
Ok, now i managed to get 170.027 MFLOPS in Linpack with the CPU at 1.58 GHz and the Core voltage on 1.375v .
[image]
So far the phone are 100% stable at this clock.
Click to expand...
Click to collapse
Precision: Inconsistent Result

[Q] really slow a500/ quadrant score 656???

Hi,
as i'm using my iconia a500 i noticed some heavy Performance issues. i rooted and installed several Roms but my Quadrant score keeps being low. right now i am on lightspeed 1.0.1 with Richard's Kernel and my Quadrant score is only 656!!!
i'm really curious about this any suggestions?
thanks in advance
kiark
Just a guess, but the cpu probably is not running full during the test. Might have to use a app to force to 1000 during the test.
Running 2.4 kernel? If so, the default intersctive scaling governor is borked so either use setcpu to change to on demand or flash back to 2.3. Im personally running 1.6ghz as max speed with on demand.
thank u very much, setting the cpu up with setcpu worked!
CPU really does not have much effect on quadrant score. It is the combination of the Rom and the kernel it self.
Sent from my SGS-t959 using XDA Premium App
IM using the xoom 3.2 rom
My acer is over clocked to 1.5 and here are my benchmark scores.
Useing Quadrant I got 3421 (best of three runs) and frame rates around 45
Useing Linpack I got 45.438 mflpos on single thread in 1.85 seconds and
71.53 mflops on multi-thread in 2.36 seconds again best of three runs
Useing AnTuTu Benchmark I got a score of 6159 and frame rates right at around 60 fps
Useing Vellamo (its new and a benchmark tool for a tablets browser to see how ell the browser performs does things like java and flash stress tests and load speeds of web pages) I got a score of 1072
naturallight said:
CPU really does not have much effect on quadrant score. It is the combination of the Rom and the kernel it self.
Sent from my SGS-t959 using XDA Premium App
Click to expand...
Click to collapse
not sure on this. if it doesnt have much effect why do you see such a huge difference between 216 Mhz and 1.5 Ghz clock speeds in quadrant?

New Quadrant -> Support For Multiple Cores And ICS

A call for all the benchmark whores, this is your time to shine. Your e-peen will grow like no other. You can post your new quadrant scores, without anyone telling you that it's outdated!
Article link
Market link
AndroidPolice said:
When it comes to benchmarks, one name usually stands above all others: Quadrant. Even though it has been proven to be easily faked, there's just something about running it and see a 3000+ score show up at the end to make you feel your device is untouchable.
Despite its popularity, Quadrant has been missing one key feature: multi-core support. That all changes with an update that was pushed to the Market earlier today, which brings Quadrant up to version 2.0, though. Not only does Quadrant now support multiple-core chips, but the update also brings ICS support, GUI improvements, support for Polish, and a fix for slow frame rates on PowerVR SGX 540 GPUs.
Click to expand...
Click to collapse
If it would matter, mine would be 3547.
It also occurred to me, that I might have not posted in the correct subforum. If so, I kindly ask Scotty to beam me up and back down a bit to the left.
And in the meantime it also occurred to me, that someone else had posted a similar thread already. I can only blame the forums for not giving me relevant search results.
It's still crap, because it doesn't display per-test scoring so you can know WHAT changed a score.
For example, disabling per-file sync in the filesystem code gains you a few hundred points in Quadrant - in AnTuTu it's clear that this improvement is in database write tests. (It also doesn't skew the scores nearly as much. Quadrant's weighting sucks.)
With ICS 'LPB' i got 3914.
I got 4004 on i9100 with ICS XXLPB
However...
Quadrant reports that my device has only one core, which is quite an important mistake, and some of the graphics tests keep hitting the 60fps ceiling, which ruins the integrity of the test, assuming it is based on measuring the maximum possible framerate.
hedgepigdaniel said:
I got 4004 on i9100 with ICS XXLPB
However...
Quadrant reports that my device has only one core, which is quite an important mistake, and some of the graphics tests keep hitting the 60fps ceiling, which ruins the integrity of the test, assuming it is based on measuring the maximum possible framerate.
Click to expand...
Click to collapse
The s2 framerate is capped at 60 fps because of vsync, it can't be changed..
And Quadrant results are more accurate on quallcomm device.. Other than that results may vary and could even be manipulated, CMIIW
I suggest you to run nenamark2 benchmark instead.. It's free on the market and gives a comparable results too..
Sent from my GT-I9100 using xda premium
Guys, is the planet part of the test scores only about 38+ fps?
Sent from my GT-I9100 using xda premium
3875 on XLB remix 9.2
Using omega's ics rom...
Sent from my GT-I9100 using xda premium
Gorjess said:
The s2 framerate is capped at 60 fps because of vsync, it can't be changed..
And Quadrant results are more accurate on quallcomm device.. Other than that results may vary and could even be manipulated, CMIIW
I suggest you to run nenamark2 benchmark instead.. It's free on the market and gives a comparable results too..
Sent from my GT-I9100 using xda premium
Click to expand...
Click to collapse
The 60fps limit can't be changed, but quadrants graphics test can be made more challenging so that the limiting factor is power rather than the arbitrary fps limit. It's not an accurate test if its hitting the 60fps ceiling.
ephraim033 said:
Guys, is the planet part of the test scores only about 38+ fps?
Sent from my GT-I9100 using xda premium
Click to expand...
Click to collapse
mine stuck @ 45 fps for the same test, are you in ICS rom?
edit:
between got 4285 in LPB
4346 here and planet test is at 38 fps.
Sent from my GT-I9100 using XDA App
3510 on CM9 latest
bala_gamer said:
mine stuck @ 45 fps for the same test, are you in ICS rom?
edit:
between got 4285 in LPB
Click to expand...
Click to collapse
Nope, i'm using Hyperdroid ROM
Sent from my GT-I9100 using xda premium
Hmm... it seems to me that CM9 gets lower scores than other ICS ROMs. That, I think, can be explained by the lack of full kernel support. Let's hope for the better, when they will get their hands on the kernel sources.
Please don't discuss Quadrant scores in this forum. Search "quadrant" in GSII General for the 7 or 8 threads we've closed for the reasons why.
Thanks

Opinions about nexus 10

Is the nexus 10 truly a good tablet? I was looking on you tube and the benchmarks are really low for the 1.7 ghz processor.
So that is why I'm asking if it's fast when you use it? Is it efficient? Does it multi task well? Is the screen resolution as good as they claim? Numbers don't mean a thing that's why I'm asking you the users. Thanks to anyone who has any input. If I haven't ask something and someone has done input I'll take that too. The benchmarks just confused me as I know they aren't everything. But my stock HTC evo 4g lte scores1 third higher at 1.5 ghz. Again, thanks
Sent from my EVO using Xparent Blue Tapatalk 2
Well i can tell you the screen is amazing. Probably the best out there. Ive only had mine for about a week now but so far everything works great. Multitasking is fine and its really smooth. Games work great for me like gta vice city with no lag at all. Im using stock rom and stock kernel. Its been great so im not even going to unlock it. You also get the new updates right when theyre out and you dont have to wait. Ive seen lots of other threads like this and i can say most users will agree with this. :thumbup:
Sent from my Xperia Play (r800x)
Look at some benchmarks in the KTManta and Trinity kernel threads. Custom kernels are the way to true performance on this tablet as it lets us modify the very conservative thermal throttling settings that come stock, as well as give undervolting capability to help save battery and be less hot, and allow for overclocking too if you want even more performance on top. I actually underclocked my CPU to 1GHz just now and did an overclocking on the GPU and still scored higher than anyone else's 3DMark scores using stock speed of 1.7GHz and 533MHz GPU. The Nexus 10 is among the top devices in any benhcmark there is right now when you start using a custom kernel. So ya, its very fast. I love this tablet.
I can break 20,000 point in AnTuTu now
And someone else broke the 10,000 point mark in 3DMark. And I get a 58.3 frame per second AVERAGE in the high quality test of Epic Citadel. The only reason citadel benchmark is at that (which is basically perfect anyway) is because vsync caps the FPS to 60, so the score would be much higher but it just isnt possible get any higher. lol
It's awesome...
[/thread]

[Q]Very low antutu score

dear moderator please delet this thread , regards,
You can get different scores on the exact same phone just by switching ROMs (the stock G2 ROM tends to run a couple thousand points higher than AOSP ROMs, if I remember right). There's a lot that goes into it, and it's probably not worth worrying about as long as you are otherwise satisfied with your phone's performance.
Hi,
Have you tried this: http://forum.xda-developers.com/showthread.php?p=46388128? To have less thermal throttling, stock is too agressive.
It was almost the same thing with my D802... about 28 000 before, about 36 000 after. In Antutu it's not just about a few FPS difference that the overall score is impacted by almost 8 000 points or even more (compare the detailed score).
In any case, even with the mod above, let your phone cool down before running a bench.
Sent from my LG-D802 using xda premium
Yes bro i did but nothing changed. ...see attached screenshots
.....
Sent from my LG-D802 using xda app-developers app
no suggestions guy's ???? i did a test i put the phone in the feezer and my antutu score was 35500 , that mean i have an aggressive thermal throlling , with 27° i get only 28000pts and viking37 solution didnt help ... any idea how can i fix that ?

Categories

Resources