Database Info

[Q] System I/O Speeds

I have been looking at the system I/O speeds on my phone and running Antutu benchmark and it shows my system I/O at really low marks at 50-65. Ive seen scores as high as 150+ and i was wanting to know how to do that please to speed my system up.

veteranmina said:
I have been looking at the system I/O speeds on my phone and running Antutu benchmark and it shows my system I/O at really low marks at 50-65. Ive seen scores as high as 150+ and i was wanting to know how to do that please to speed my system up.
Click to expand...
Click to collapse
If you use the OTB kernel there is an option within Voltage Control to switch schedulers, you may see some speed increase there but probably not enough to make a big difference.
Most of the I/O scores you see (quadrant) are bloated scores and are not accurate benchmarks

bdemartino said:
If you use the OTB kernel there is an option within Voltage Control to switch schedulers, you may see some speed increase there but probably not enough to make a big difference.
Most of the I/O scores you see (quadrant) are bloated scores and are not accurate benchmarks
Click to expand...
Click to collapse
Ive messed with the schedulers and didnt see any difference. And i dont use quadrant anymore bc i found a better benchmark app called antutu.

Honestly I use lindpack for benchmarks. It measures MFLOPs and from the info I can find that is the measure of the processor power. It is the same method used to test the worlds supercomputers. Before OTB I would get about 13 MFLOPs. After OTB I get about 16MFLOPs. Hope this helps ya.
Tap-a-Talked.

[Q] Quadrant Scores for the 7 Plus?

Hi guys,
I have a Galaxy Tab 7 Plus 6210 (WiFi only) and I'm getting Quadrant Scores mostly close to 3250. Meanwhile a lot of the reviews I've read online report 3600 to 3800.
Should I be worried?

Maybe off topic but I think people should stop using quadrant. It's really old.
The CPU part it does not work well with multicore and for the GPU part almost all tests reach FPS limitation set by ROM. So the score of it cannot really differentiate performance now.

It's also WAY too sensitive to I/O tweaks - disabling per-file write syncs gives you 600+ points on Quadrant which is insane.
Similarly, there were hacks (like the Stagefright hacks) that would cause Quadrant scores to skyrocket (I think people were figuring out how to hit 3000+ on Captivates) but would make real-world usage of the device utter crap.

I know of Quadrant's shortcomings - but my theory is that for two devices that haven't had any significant modifications to them, the score should be similar (no matter how flawed Quadrant itself may be to tweaking)

not too shabby for stock, hangs at I/O 2of 4.

That app is useless imho... rebooting my Tab bumped it 600 points

try AnTuTu benchmark. I got a score of 6030 with v6 Supercharger and KAK tweak.

[Q] Infusion coreA kernel may has some problems with GPU in zeus

I`m running zeus 5.2，everything is good.thank you dman!
but i notice some questions：
If you choose the governor ondemond,there is olny 50fps in game or neocore test,it is a little bit lag.But high cpu and IO score in quadrant(3300)
then you change the governor to perfrmence or conservative or interactiveX
you`ll get 56fps in game and neocore,the game runs quite good,but cpu and io score is lower in quadrant ( 2100 point)
I wonder what`s wrong with this problem?It someting wrong thunderbolt or kernel ?
thank you for your help.

neocore and quadrant are a joke. besides that kernel is no longer supported as all the old kernel devs left and there hasnt been any new source code to build from.
file system scores on quadrant are laughable, infact dont pay any attention to quadrant if you can help it, miui and a tweaks script can get you near 5000, that doesnt mean you increased capabilities by 5 times over stock.
if you want a file system benchmark then i dont know what to tell you, i dont know of any good ones. if you want a cpu benchmark then use chainfire bench. if you want a gpu bechmark use one that can actually bog down the gpu. neocore isnt enough of a challenge for anything with a modern gpu, thats for old snapdragon phones (nexus 1, incredible, evo....) or low level phone. the kernel limits the fps to about 56 fps, the reason the different governors show lower is that the thresholds and logic is different so it doesnt step you up as aggresively. being 6 fps off the cap doesnt show a deficientcy nessessarily, it might just be some lag in the step up or a high threshold for step up. or there may be a slight issue with that governor on that kernel.

Dani,thank you for your answer
I`m totally agree what you said that neocore and quadrant are a joke ^0^
I dont care the score but because i`m a noob,so I was curious with some something strange.
you could feel the different between 50fps with 56fps in some games, such as Dungeon hunter2 or bcakstab HD,but not in doodle jump ：）
maybe those kernel is no longer supported,and problems will not be solved,so I only hope that some new kernels come out soon .LoL

Overclocking Confusion!!

Finally figured out how to over clock my CPU/GPU on One X with CM11 KitKat rom. Bumped the CPU to 1809 (what I researched is stable) and GPU to 512. My Antutu benchmark score dropped from low 17k's to mid 13k?
Help please!! Could running Trickster Mod App interfere with Performance option in CM11....?

Trickster Mod isn't interfering with the performance, it just means your phone won't perform at its peak with those settings. Higher CPU/GPU clocks don't necessarily mean better performance, I've seen this through extensive personal testing. Dial the settings back to stock and increase the clock speed incrementally while testing after each increase, you'll reach a point where performance suffers, dial it back one notch and there you have your "peak" settings.
Unless you're doing some really hardcore gaming on your phone it's all pretty pointless. There's no advantage to overclocking in everyday use of the device other than to say it's overclocked, you just can't notice a difference, any noticed difference is more than likely a placebo. I actually underclock my CPU to 1242mhz to improve battery life and have zero negative response whosoever, no matter what I throw at it.
Sent from my Evita

I agree with Tim here. I'm running cm11 on power saver mode, and it runs just fine. A little slow opening and closing apps, but buttery smooth for everything else.
Sent from my One X using xda premium

[RESEARCH] Overclock on Qcom useless due to screened SoC's

Some weeks ago @Quarx told me that he tried to overclock his MotoG. At a first look it works. The system is stable and cpuinfo apps show 1.9GHZ.
BUT: there isn't any performance change. Then I checked it on my device(Xiaomi Mi2) - exactly the same result.
I watched a video about Nexus4 overclock: https://www.youtube.com/watch?v=96hsPe-JH2M
As you can see there isn't any change, too(the minor differences are just random).
Then Quarx found a very interesting commit in MotoG's kernel log:
https://github.com/Quarx2k/kernel-moto-g/commit/ed82c3f26ec4a7ab39a436647643bdaf71dcb67a
The message tells us, that QCOM devices normally are "screened" which basically means, that if your max freq is 1.2GHZ, it doesn't matter what you change in the kernel source. it will always be 1.2GHZ even if it shows 100GHZ because the SoC is limiting that.
There are some older SoC's with adreno 2xx which seem to be overclockable without any problems.
But all new SoCs seem to be screened which prevents overclocking.
Some more tests of other devices and SoC's would be helpful.

I'd recommend you get a buttload of single-thread Linpack benchmarks at different frequencies and do some statistical analysis. Maybe make a Google Form where you can input Device, Frequency, and MFLOPS
Linpack because it's exclusively CPU, doesn't vary much between devices of the same model, and scales nicely with frequency.

scy1192 said:
I'd recommend you get a buttload of single-thread Linpack benchmarks at different frequencies and do some statistical analysis. Maybe make a Google Form where you can input Device, Frequency, and MFLOPS
Linpack because it's exclusively CPU, doesn't vary much between devices of the same model, and scales nicely with frequency.
Click to expand...
Click to collapse
I think Linpack isn't reliable enough because it's completed too fast. For me it takes 1-2s to complete and the result variate's very much.
Sth like Antutu(only the CPU score) with performance governor and maybe even on a clean install would be better.

m11kkaa said:
I think Linpack isn't reliable enough because it's completed too fast. For me it takes 1-2s to complete and the result variate's very much.
Sth like Antutu(only the CPU score) with performance governor and maybe even on a clean install would be better.
Click to expand...
Click to collapse
So how we can really test it? test in game to see if FPS get more high? I really dont believe that is just a placebo effect, in my kernel with 1.5Ghz I really feel the speed and will test when i finish the OC of 1.8Ghz.

BryanByteZ said:
So how we can really test it? test in game to see if FPS get more high? I really dont believe that is just a placebo effect, in my kernel with 1.5Ghz I really feel the speed and will test when i finish the OC of 1.8Ghz.
Click to expand...
Click to collapse
well I only said that linpack looks unreliable. Antutu or other cpu intensive benchmarks should work just fine. Just ignore gpu benchmarks, because the gpu is definitely overclockable.