Related
Does using setCPU with the Tegra 3 and it's 5th core muck up the Tegra 3's native power saving capability (ie. using the fifth core as a low energy solution for minimal activities)?
Has anyone seen tests of battery use with and without?
What I have seen from my use over the past week or so with SetCPU is that you can set the governor and the minimum clock both of which have an effect (although minimum clock is not strictly adhered to).
I don't believe the 5th core is exposed to the android OS so SetCPU shouldn't effect that at all.
I'm testing the beta and no it does not effect the max 100% of the time the tegra power management seems to kick in. I have informed mike (setcpu author) about this issue he is looking in to it.
Sent from my HTC One X using xda premium
I guess set cpu is not supported quad core yet
As James pointed out, the 5th Slave core is Transparent and not visible to Android, so it 'shouldn't' be effected by SetCpu
nibbleart said:
I guess set cpu is not supported quad core yet
Click to expand...
Click to collapse
It supports quad core CPU scaling, the question is about the 5th core.
That the 5th core is invisible does make it seem like it wouldn't effect this issue, however I would like to understand a bit more about how it works to be sure.
From what I understand, when processor use is low and the CPU is scaled below 500mhz(?) then the 5th core alone is used, whereas at higher frequencies the other 4 cores are fully engaged.
I would just be worried that setting the CPU speed through methods other than whatever method HTC/nvidia had arranged for might negate this benefit. It'd be good to know from the setCPU guy what's going on, since he likely understands a lot about how CPU scaling works...
Here's my Feedback on using SetCPU with HOX:
When trying to underclock my phone
Max: 1000 Min:51
Result: rebooted within 5 minutes and then kept on doing this untill I reset the SetCpu settings to phone defaults and uninstalled
similar user experience here: http://forum.xda-developers.com/showthread.php?t=1596992&highlight=setcpu
I have seen that there is an app created for the HOX:
CoreControl: http://forum.xda-developers.com/showthread.php?t=1652136
I want to give this a go and I feel this a relevant topic to be stickied maybe under a different Topic Title ie. Custom CPU settings
Will install CoreControl and revert...
BTW: what settings have you tried using with SetCPU to underclock that doesnt result in a random reboot and that works, also what version of setCpu are you using
system tuner will allow to set the clocks for T3 properly
CoreControl is for enable/disable cores, not for overclock/underclock, I've been using it for a while, at least my HOX doesn't heat up much
Sent from my HTC One X using xda premium
Man it would be nice top have core control on the thrill
Sent from my LG-P920 using XDA
CoreControl Feedback
vegasphinx said:
CoreControl is for enable/disable cores, not for overclock/underclock, I've been using it for a while, at least my HOX doesn't heat up much
Sent from my HTC One X using xda premium
Click to expand...
Click to collapse
I can now concur with @vegasphinx it doesn't heat up as much and I dont notice the difference besides the toastie popping up every so often saying CoreControl has been granted SU
can any of you give me an idea how to setup the Battery Stats within CoreControl
It crashes because there's no kernal that supports overclock/underclock.
Sent from my HTC One X using Tapatalk 2
anyone got this overclocked
mox123 said:
anyone got this overclocked
Click to expand...
Click to collapse
And instantly overheated? :cyclops:
Yes .
Sent from my HTC One X using Tapatalk 2
Gpu overclock would be more useful than CPU.
Sent from my HTC One X using xda app-developers app
treebill said:
Gpu overclock would be more useful than CPU.
Sent from my HTC One X using xda app-developers app
Click to expand...
Click to collapse
ok gpu overclock then?
I would overclock my HOX...in a block of ice. Or...well, in real life i dont want to overclock it because it would smoke out in my hand
Overheating is a big problem even without overclocking, imagine it running on 1,6ghz...
Sent from my Renovated HTC One X using Tapatalk 2
Can't really see why you would want to overclock the One X, the phone is blazing fast anyway, 4 cores at 1.5 is enough..
But like everybody else said, the phone would probably burn up..
I wouldnt overclock my device - at least not at the stage we reached now.
Why?
a) As long as there is no way to lower the voltage this might toast your device - its a unibody, keep that in mind!
b) 100 MHZ more would have literally no effect - its a 6 GHZ device, even if you boost it up to 6,4 - you wont notice, it will just drain your battery.
6 GHZ is WAY enough...this is smartphone...I mean...seriously...its got more power than my 4 years old 1K €uro notebook...
Illux said:
I wouldnt overclock my device - at least not at the stage we reached now.
Why?
a) As long as there is no way to lower the voltage this might toast your device - its a unibody, keep that in mind!
b) 100 MHZ more would have literally no effect - its a 6 GHZ device, even if you boost it up to 6,4 - you wont notice, it will just drain your battery.
6 GHZ is WAY enough...this is smartphone...I mean...seriously...its got more power than my 4 years old 1K €uro notebook...
Click to expand...
Click to collapse
well first of all you can't just multiply the frequency by the number of cores. I'd much prefer an actual 6Ghz single core processor over 4x1.5Ghz because it won't have any compatibility and efficiency issues. Assuming they are of the same architecture and power usage of course.
Also the ARM low power SOCs probably don't have comparable number of commands per clock cycle as an x86 high performance CPU, even if it's 4 years old.
jacobgong said:
well first of all you can't just multiply the frequency by the number of cores. I'd much prefer an actual 6Ghz single core processor over 4x1.5Ghz because it won't have any compatibility and efficiency issues. Assuming they are of the same architecture and power usage of course.
Also the ARM low power SOCs probably don't have comparable number of commands per clock cycle as an x86 high performance CPU, even if it's 4 years old.
Click to expand...
Click to collapse
i agree.. when the multi-core CPUs first came out intel said doubling the core number would give as 47% boost in total performance (not x2 like apple says as they do not know it) lets assume that to be %50 to make the math a little bit easier..
so basically we can make the math here as; 4 cores at 1.2Ghz (when the all 4 active the clock is 1.2Ghz) gives us 1.2 x 3/2 x 3/2= 2.7 Ghz single core performance.. this value for SGS3 is; 1.4 x 3/2 x 3/2= 3.15Ghz
and here we can say dual core at (X) Ghz gives us (X) x 3/2=2.7 thus the (X) = 1.8 Ghz.. so, if you overclock any arm9 based Dual CPU to 1.8 Ghz you get the same performance "on paper".. if you want to catch up with SGS3 we need to OC it to 2.1 Ghz which is impossible at the moment i guess..
what makes the difference here is the lower loads or multiple loads on the CPU.. corecontrol users probably would have noticed; sometimes when the all 4 core are active the clock is only 480 or 640 Mhz (even 320 sometimes if i remember correctly) .. the same amount of load could be taken care of by a dual core at about 720 or 960Mhz.. but here the quad core system stays cooler with a little less energy consumed (or wasted) (as long as all the cores are in one uni-body structure, putting 2 or 4 single cores phsically together is not the case for our smartphones) this is how apple made sure about the smoothness of the ipad 2, new ipad and the iphone 4s.. they used lower clocked 2 power vr 543 GPUs.. when the load is little they can clock down to very low speeds and share the load..
and also you can always find an emtpy core waiting for new task when the others are busy..
so, long story for short; if we were dealing with a little amount but hard processes, having a single core at 2.7Ghz would be good since the quad core design would not cut one task into 4 pieces... as long as we were not thinking about the battery life and the heat.. but since we are dealing with lots of tasks which all could be handled by 1.2Ghz power having 4 cores is better for battery saving and having an empty core for a new task to run parallel with the other running tasks in the background..
It is OC out of the box I think Nvidia OC them for us and it's already pushing itself at the very edge of what is possible for it to do based on temperature, I seem to remember Hamdir saying something along those lines once upon a time...
Why bother to OC it's fast enough as it is.
---EDIT---
hamdir said:
only faux kernel betas allow OC
big warning OC is bad for the HOX given the thermal envelope
you are risking both you battery and processor if you OC
i know you are used to OC from other devices but those had headroom, it is not the case this time, T3 is operating at its max thermal capabilities on the HOX
Click to expand...
Click to collapse
hamdir said:
the snapdragon 2 on the Arc had a lot of headroom
the chipset is rated @ 1.5ghz stable!
not the case with T3 its milking the very maximum of the 40nm process
in other words Nvidia is OCing its T3 out of box because their chips are designed to survive massive amount of heat (sadly it doesnt mean the battery or other components would survive)
it is already Overclocked lol
sometimes you have to listen to the "science" of it and surrender
Click to expand...
Click to collapse
Can someone tell me where I can find over-clock able kernel for my international One X? And what is the biggest clock speed on ONE X?
At present faux kernel can oc depending on what variant CPU you have but max at 1.6ghz
I have a v2 and can do 1.55 quad fine
Sent from my HTC One X using xda app-developers app
Eternity Project has an OC version up to 1.7GHz single core and 1.6GHz quad core
ZeroInfinity said:
Eternity Project has an OC version up to 1.7GHz single core and 1.6GHz quad core
Click to expand...
Click to collapse
Can you post link?
stefan063 said:
Can you post link?
Click to expand...
Click to collapse
http://forum.xda-developers.com/showthread.php?t=1640532
Be careful of OC, always remember, not all chips are made equal
About last Repacked Eternity Project for ARHD 9.x.x
Hello,
I try the Last repacked eternity project kernel for ARHD 9.x.x the Kernel: 3.4 v0.38 (Overclocked) at :
http://forum.xda-developers.com/showthread.php?t=1654982
But the module file was repacked for CMW ROM.
Who find good repacked module corresponding to this kernel ?
Thank you for jour help.
Underclock
As this thread is about setting CPU speeds, can somebody help me with my problem as no one is responding?
Its about underclocking..
http://forum.xda-developers.com/showthread.php?t=1868011
Thanks in advance!
how does the OC work? i mean then running all our core it is limited to 1.2 ghz and is 1.5 on a single core.
does that men all cores run at the OC value or just the single core?
Sent from my Transformer TF101 using xda app-developers app
I suggest you flash faux's kernel.
It can oc to 1.6GHZ for most user~
and it support s2W!
I expect many users will be aware of this information, but just in case you aren't.
Anyone overclocking should be aware that this will usually lead to higher power consumption which leads to more heat produced and lower battery life.
Especially if it is necessary to overvolt to acheive higher clock frequencies with stability.
Power consumption is proportional to Voltage squared, so small increases in core coltage can result in larger increases in power consumption than mught be thought.
Needless to say this can have negative impacts on battery discharge time and overall life (due to higher temperatures).
Plus there may be some throttling back of frequency if high temperatures are reached. Also possible that frequency may be reduced to 1Ghz maximum when battery voltage is low (i.e when discharged)
Hope this is helpful (first post here)
paul_59 said:
I expect many users will be aware of this information, but just in case you aren't.
Anyone overclocking should be aware that this will usually lead to higher power consumption which leads to more heat produced and lower battery life.
Especially if it is necessary to overvolt to acheive higher clock frequencies with stability.
Power consumption is proportional to Voltage squared, so small increases in core coltage can result in larger increases in power consumption than mught be thought.
Needless to say this can have negative impacts on battery discharge time and overall life (due to higher temperatures).
Plus there may be some throttling back of frequency if high temperatures are reached. Also possible that frequency may be reduced to 1Ghz maximum when battery voltage is low (i.e when discharged)
Hope this is helpful (first post here)
Click to expand...
Click to collapse
CPU throttle starts at 85c with thermal TJ-max of 99c.
also there is many debates about this, higher speed need more power which drains battery, but that said it means work gets faster meaning it can idle faster saving power, same the other side slower speeds save power but take longer to get work done using more power.
Sent from my Transformer TF101 using xda app-developers app
stefan063 said:
Can someone tell me where I can find over-clock able kernel for my international One X? And what is the biggest clock speed on ONE X?
Click to expand...
Click to collapse
Go to Faux123 and read the opening post
http://forum.xda-developers.com/showthread.php?t=1647993
it will teach you about Tegra 3 variants.
Flash Faux123 latest kernel to know what variant you have.
You can have 1.5ghz quadcore minimum, except if you have the poor variant0 of the Tegra 3, and 1.6ghz quadcore max if you have variant 3
So the overclocking you can achieve depends on your Tegra 3 variant, whatever the kernel, don't trust the figures in kernel threads titles, they just give the max if you have variant 3. And the majority of people have variant 1 so limited to 1.5ghz quadcore and there's nothing to do about it, no future kernel can change the way your CPU was manufactured.
Just, SetCPU can display 1.6ghz or more, but if you have variant 0 or 1 it will never use it (CPUspy will say 1550 and 1600 are unused frequencies)
Variant 1 can go upt to 1550mhz but not for quadcore, so who cares....! Same for kernels claiming up to 1.7ghz, it's in single/dual core, so once more, who cares?
What is important is what max speed you can achieve in quadcore, nothing else, and the limits are clearly defined by your Tegra3 variant
"all chips are not created equal" was a silly bull**** invented more than one year ago as an easy answer to noobs claiming they couldn't overclock their dual core at their max. Now, on the One-X and because of Nvidia unstable quality"all chips are not created equal" is sadly the truth.
PS: wrong=> to say that overclocking means more voltage, undervolting a custom kernel a little can surprisingly reduce heat when you push your CPU to its max,I can have both 1500mhz quadcore and less voltage than stock, as well as less heat (I was surprised, really, on the Sensation I had always found undervolting kinda useless)
PPS: true=> thermal throttle will always come pretty soon and reduce your max speed......
i900frenchaddict said:
Go to Faux123 and read the opening post
http://forum.xda-developers.com/showthread.php?t=1647993
it will teach you about Tegra 3 variants.
Flash Faux123 latest kernel to know what variant you have.
You can have 1.5ghz quadcore minimum, except if you have the poor variant0 of the Tegra 3, and 1.6ghz quadcore max if you have variant 3
So the overclocking you can achieve depends on your Tegra 3 variant, whatever the kernel, don't trust the figures in kernel threads titles, they just give the max if you have variant 3. And the majority of people have variant 1 so limited to 1.5ghz quadcore and there's nothing to do about it, no future kernel can change the way your CPU was manufactured.
Just, SetCPU can display 1.6ghz or more, but if you have variant 0 or 1 it will never use it (CPUspy will say 1550 and 1600 are unused frequencies)
Variant 1 can go upt to 1550mhz but not for quadcore, so who cares....! Same for kernels claiming up to 1.7ghz, it's in single/dual core, so once more, who cares?
What is important is what max speed you can achieve in quadcore, nothing else, and the limits are clearly defined by your Tegra3 variant
"all chips are not created equal" was a silly bull**** invented more than one year ago as an easy answer to noobs claiming they couldn't overclock their dual core at their max. Now, on the One-X and because of Nvidia unstable quality"all chips are not created equal" is sadly the truth.
PS: wrong=> to say that overclocking means more voltage, undervolting a custom kernel a little can surprisingly reduce heat when you push your CPU to its max,I can have both 1500mhz quadcore and less voltage than stock, as well as less heat (I was surprised, really, on the Sensation I had always found undervolting kinda useless)
PPS: true=> thermal throttle will always come pretty soon and reduce your max speed......
Click to expand...
Click to collapse
Nice words and I just won't to add variant 1 can now go to 1.55ghz with faux 07vf I'm currently usein with the lowest most stable undervolt values and less heat than stock kernel and gameplay is amazing also on arhd 9.4
Sent from my HTC One X using xda premium
treebill said:
CPU throttle starts at 85c with thermal TJ-max of 99c.
also there is many debates about this, higher speed need more power which drains battery, but that said it means work gets faster meaning it can idle faster saving power, same the other side slower speeds save power but take longer to get work done using more power.
Sent from my Transformer TF101 using xda app-developers app
Click to expand...
Click to collapse
Your argument makes sense, but unless the governor is very efficient at controlling the CPU speed very quickly, in most cases your argument doesn’t hold true. For example when playing a game or running a CPU intensive application (where overclocking has any use) the processor works at full speed for the duration of the application.
EDIT: Frankly I don’t see any point in overclocking a phone like One X. I don’t play many games, but the few games I have played ran very smoothly. And if people are overclocking because of the (barely noticeable) laggy UI then overclocking is not a real fix anyway. Installing a custom ROM (perhaps JB), a different launcher, tweaking background apps/services are some of the more sensible and effective things to do instead.
No disrespect to the devs who are working on overclocking, but IMO HTC and nVidia must have spent a considerable amount of time and effort designing the CPU and deciding the optimal operational parameters to maximize performance while minimizing battery drain. Therefore anything out of those parameters (in theory at least) should impact either stability, or battery life. Perhaps the values HTC has decided are not the maximum possible values , because I assume they would have designed the phone to handle few exceptional conditions (i.e: extremely hot weathers). But I think over clocking would probably cause more problems in the long run than whatever the little gains you experience in short term. Just my 2c.
joewong1991 said:
Nice words and I just won't to add variant 1 can now go to 1.55ghz with faux 07vf I'm currently usein with the lowest most stable undervolt values and less heat than stock kernel and gameplay is amazing also on arhd 9.4
Sent from my HTC One X using xda premium
Click to expand...
Click to collapse
Late reply, I hope you'll read it anyway
I tried faux 007b5, so overclock free too, I had 1.55ghz indeed, but never for quadcore, just for single or dual. Sadly I wasn't able to reach 1.5ghz quadcore but 1.4
With 007u, I have 1.5ghz quadcore, but 1.55 is an unused frequency
Can you check, with tegrastats, if you reach 1.55ghz quadcore or only for 1,2 (or3??) cores?
i900frenchaddict said:
Late reply, I hope you'll read it anyway
I tried faux 007b5, so overclock free too, I had 1.55ghz indeed, but never for quadcore, just for single or dual. Sadly I wasn't able to reach 1.5ghz quadcore but 1.4
With 007u, I have 1.5ghz quadcore, but 1.55 is an unused frequency
Can you check, with tegrastats, if you reach 1.55ghz quadcore or only for 1,2 (or3??) cores?
Click to expand...
Click to collapse
I tried tegrastats and I got 1.55 4 cores for about 20 sec and then 2 shut of and then ran 2 at 1150 playin dead trigger and on cod zombies 2 cores at 1350 witch I find strange faux 0105b
Sent from my HTC One X using xda premium
In this thread we will discuss governors.
Primarily differences between ondemand and conservative based ones. This thread was created because ktoonsez made a hotpluging conservative governor. ... perhaps this needs explanation for the general community, that will imo prove the vast superiority of conservative based governors. First here is a link about governors in general it is sort of abridged but, covers allot of governors http://blog.g4team.com/?p=5519
As you can see it makes mention that most of these governors are similar to ondemand. So outlining the major differences. Ondemand scales to the highest frequency as soon as a load occurs. Conservative scales upward based on the frequency step variable which means for the most part will scale through every frequency to achieve the target load thresholds. What this practically means is ondemand is prone to wasting power on unneeded clock cycles. Ondemand also features something called a down differential, this variable determines how long the governor will remain at the given frequency before scaling down. Conservative does not have this, but instead relies on having a down threshold which insures that as soon as the load drops below a given variable it scales down as fast as the sampling rate allows. The result to this is a governor which attempts to keep the load level tolerable and save you battery! Now ! Ktoonservative Is that but in addition contains a hotpluging variable which determines when the second core comes online. The governor shuts the core off when it drops below the hotplug down threshold thus giving us a handle on the second performance factor in our CPUs behavior. While by default conservative is a poor performer it can be made to perform comparably to even performance governor. Here are some settings to discuss and start with. They are slightly less battery friendly under a load but very very well performing.
after realizing just everything mpdecision does i recommend turning it off for this govenor to work properly "stop mpdecision" in the terminal should do. it not only allows for things like benchmarks to lock frequency but generally will disturb these settings under a load, it will do something completely different. so when i turned it off i discovered the govenor behaving differently....more over exactly as you would expect this also meant with some ideas from mw86 that we dont really need touch booster. id recommend the first set of settings and use the last if you want mpdecision on. despite looking less aggressive for battery savings they usually will be with the absence of mpdecision
SAMPLING_RATE="15000"
UP_THRESHOLD="67"
DOWN_THRESHOLD="47"
FREQ_STEP="3"
SAMPLING_DOWN_FACTOR="1"
IGNORE_NICE_LOAD="0"
UP_THRESHOLD_HOTPLUG="85"
DOWN_THRESHOLD_HOTPLUG="33"
SAMPLING_RATE="40000"
UP_THRESHOLD="67"
DOWN_THRESHOLD="52"
FREQ_STEP="5"
SAMPLING_DOWN_FACTOR="1"
IGNORE_NICE_LOAD="0"
UP_THRESHOLD_HOTPLUG="68"
DOWN_THRESHOLD_HOTPLUG="40"
And here is the link for the kernel containing such http://forum.xda-developers.com/showthread.php?t=1800576
A further edit for jb builds most benchmarks are niced so you must turn off ignore nice load to test settings with them
Sent from my SPH-L710 using Tapatalk 2
The results
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
[/IMG]
Sent from my SPH-L710 using Tapatalk 2
Great post and discussion freecharlesmanson. I'm using your specs above and FREQ_STEP="5" I changed to 1, so it would be more like Lazy governor and save me extra power at the cost of a little lag since it must go through the full frequency scale instead of jumping to target frequency in a step or two. Watching cpu frequency in a graph shows this governor and your tweaks do great at being conservative but with power ready to be tapped. For frequency step at 1 im seeing stuff that ramped up in no time takes a half a sec more due to the frequency ladder it must climb... but I'm hoping it will mean it only uses high frequencies when its been under load for quite some time and not just from a basic background task I may care little about the speed in which its completed. Battery life is through the roof with this governor and Ktoonsez Kernel.
edit: if i set down threshold to 60 does it save more power without a lot of complications or does it cause large hiccups or uneeded frequency changing? would it be better to be near 50, stay at 45 or drop down under to 40-35? i was using your settings in other kernel thread but now using yours here and the rest as mentioned.
mw86 said:
Great post and discussion freecharlesmanson. I'm using your specs above and FREQ_STEP="5" I changed to 1, so it would be more like Lazy governor and save me extra power at the cost of a little lag since it must go through the full frequency scale instead of jumping to target frequency in a step or two. Watching cpu frequency in a graph shows this governor and your tweaks do great at being conservative but with power ready to be tapped. For frequency step at 1 im seeing stuff that ramped up in no time takes a half a sec more due to the frequency ladder it must climb... but I'm hoping it will mean it only uses high frequencies when its been under load for quite some time and not just from a basic background task I may care little about the speed in which its completed. Battery life is through the roof with this governor and Ktoonsez Kernel.
Click to expand...
Click to collapse
Yep if you can deal with the lag it will do the trick . You could try to slightly raise that number and just raise the up threshold and hot plug threshold allot like 85 up and 80 hotplug. Then raise the freq step to 2 or three maybe it might give a similar result by discouraging up scaling thru the demand end but would allow quicker scaling ever so slightly with less likelihood of jumping steps. By my math each freq step represents 4.3% total available scaling
Sent from my SPH-L710 using Tapatalk 2
Great work on this, appreciate you taking the time to explain it all!
Sent from my SPH-L710 using xda app-developers app
I can't stand any form of lag! Complete smoothness is the way to be
Sent from my SPH-L710
Lol if you're lagging using conservative with your shiny S4, you're doing it wrong.
I've used conservative exclusively over ondemand ever since root was achieved with my Epic4g which uses the 1ghz hummingbird processor and there's no lag...
I now use smartassv2...seems to give even faster performance and shuts things down quicker than conservative!
Sent from my SPH-D700 using xda app-developers app
A_Flying_Fox said:
Lol if you're lagging using conservative with your shiny S4, you're doing it wrong.
I've used conservative exclusively over ondemand ever since root was achieved with my Epic4g which uses the 1ghz hummingbird processor and there's no lag...
I now use smartassv2...seems to give even faster performance and shuts things down quicker than conservative!
Sent from my SPH-D700 using xda app-developers app
Click to expand...
Click to collapse
Smart ass is based on interactive my issue still falls with load regulation. Most of that it seems like it would race thru frequency more. Which may deliver good performance but if at all it would deliver the same but worse battery
This is how well it works for idle regulation and I should point out smart ass doesn't hotplug so in turn because it cannot regulate the second core most likely results in less efficient scaling and if the second core preempted scaling it offers more performance than scaling right off ,those screens are of it being used alittle before bed then alittle more after I woke up
Sent from my SPH-L710 using Tapatalk 2
Just applied values. So far so good. I was just curious, are you over clocking at all? Would it be safe to run this thing at 2106?
Sent from my SPH-L710 using xda app-developers app
drewmonge said:
Just applied values. So far so good. I was just curious, are you over clocking at all? Would it be safe to run this thing at 2106?
Sent from my SPH-L710 using xda app-developers app
Click to expand...
Click to collapse
Rofl. Anything over 1.5 is a waste.
Sent from my SPH-L710
drewmonge said:
Just applied values. So far so good. I was just curious, are you over clocking at all? Would it be safe to run this thing at 2106?
Sent from my SPH-L710 using xda app-developers app
Click to expand...
Click to collapse
Its a governer not voltage settings so I can't see why you'd have a problem
Sent from my SPH-L710 using Tapatalk 2
Custodian said:
Rofl. Anything over 1.5 is a waste.
Sent from my SPH-L710
Click to expand...
Click to collapse
Fantastical.
Sent from my SPH-L710 using xda app-developers app
Freecharles manson I was tinkering more and decided to go in a different direction. can you tell me how this would act theoretically? it seems to do good at no lag and saves power still.
SAMPLING_RATE="13500"
UP_THRESHOLD="49"
DOWN_THRESHOLD="23"
FREQ_STEP="1"
SAMPLING_DOWN_FACTOR="4"
IGNORE_NICE_LOAD="1"
UP_THRESHOLD_HOTPLUG="24"
i chose these because I have a theory on single core load vs dual core load in our multi core setup. Since the governor can be multicore aware... I was thinking about what that means.
dual core cpu 100% load = 1 core 100% and the other. dual core 50% load can mean 1 core is at 100% load and second core 0% or anything in between to 50% on both the cores which is still the same... 50% load of a dual core cpu. So lets just say a rouge app pegs at 100% load regardless of 2nd core status. If we set up threshold or hotplug above 50% it means the load to up the frequency or amount of cores activated must be over the load of having 1 core fully loaded to 100% to activate.. ie one at 100% and the other a little over or vise versa both cores loaded to 51% total atleast. So I want my up threshold for frequency at 50% area so if one core ever loads to 100% it adds a frequency step. At the same time I want my second core to activate not while idle but at any load under the upthreshold. So to still save power i want down threshold just under the load required to activate core 2. So 25% seems like a good number. it is equivalent to a 50%load on one core alone or a balance of 25% load over both cores. So down threshold 1 percent under that so unless load is above that it lowers frequency as needed.
so to make sure its easier for the thresholds to jump in at right time i dropped each measurement 1% so it wouldn't literally need 100% load single core to up the frequency. so thats why i went 49%, 24% and 23%. this way the cpu doesnt often stay at a full load unless needed but ramps up when things take a few to calculate and hopefully finish faster saving juice by using the closest matched speed needed. To save power the frequency step is minumum but by the way thresholds are set it will ramp it up very quickly to whats needed even under light loads. battery life hasnt been too bad set like this over the day.
any thoughts on this and if it will work how I am hoping? I'm not sure the direction i took this for my personal use but my goal is a Conservative on demand governor with good hotplugging and to be sure it doesnt use speeds which are overkill for the task nor underpowered either. lazy Ktoonservative
i played around with the values differently and didn't like having hot plug kick in after frequency increase. i figure as load increases from zero it will stay at lowest speed till 23% then at 24% core 2 will kick in and if that doesn't lower cpu load by time it reaches 49% load it will stay in dual core and go up one cpu step... if load doesnt drop it will continue to add speed and stay in dual core. but as soon as load drops below 49% speed will stay same and then core two will shut off at 24% and either finish the work load at that speed in single core, drop to lowest cpu speed in single core or as needed renenable core two to start process all over and therefore either finishing work load or ramping again while in dual core up in frequency till load once again drops into the threshold ranges.
Custodian and Freecharlesmanson i respect your info and would love to know how accurate this is. I am new to Android as of this year but not new to cpus so if you have advice or feedback for this discussion Id be very appreciative.
So my issue atm is with ES explorer scrolling. It's super choppy.... I'm exploring more values in hopes of finding a sweet spot. I can confirm that the choppiness doesn't exist on ICS but does on asop ROMs. So I'm trying to see what's up now.
Sent from my SPH-L710
mw86 said:
Freecharles manson I was tinkering more and decided to go in a different direction. can you tell me how this would act theoretically? it seems to do good at no lag and saves power still.
SAMPLING_RATE="13500"
UP_THRESHOLD="49"
DOWN_THRESHOLD="23"
FREQ_STEP="1"
SAMPLING_DOWN_FACTOR="4"
IGNORE_NICE_LOAD="1"
UP_THRESHOLD_HOTPLUG="24"
i chose these because I have a theory on single core load vs dual core load in our multi core setup. Since the governor can be multicore aware... I was thinking about what that means.
dual core cpu 100% load = 1 core 100% and the other. dual core 50% load can mean 1 core is at 100% load and second core 0% or anything in between to 50% on both the cores which is still the same... 50% load of a dual core cpu. So lets just say a rouge app pegs at 100% load regardless of 2nd core status. If we set up threshold or hotplug above 50% it means the load to up the frequency or amount of cores activated must be over the load of having 1 core fully loaded to 100% to activate.. ie one at 100% and the other a little over or vise versa both cores loaded to 51% total atleast. So I want my up threshold for frequency at 50% area so if one core ever loads to 100% it adds a frequency step. At the same time I want my second core to activate not while idle but at any load under the upthreshold. So to still save power i want down threshold just under the load required to activate core 2. So 25% seems like a good number. it is equivalent to a 50%load on one core alone or a balance of 25% load over both cores. So down threshold 1 percent under that so unless load is above that it lowers frequency as needed.
so to make sure its easier for the thresholds to jump in at right time i dropped each measurement 1% so it wouldn't literally need 100% load single core to up the frequency. so thats why i went 49%, 24% and 23%. this way the cpu doesnt often stay at a full load unless needed but ramps up when things take a few to calculate and hopefully finish faster saving juice by using the closest matched speed needed. To save power the frequency step is minumum but by the way thresholds are set it will ramp it up very quickly to whats needed even under light loads. battery life hasnt been too bad set like this over the day.
any thoughts on this and if it will work how I am hoping? I'm not sure the direction i took this for my personal use but my goal is a Conservative on demand governor with good hotplugging and to be sure it doesnt use speeds which are overkill for the task nor underpowered either. lazy Ktoonservative
i played around with the values differently and didn't like having hot plug kick in after frequency increase. i figure as load increases from zero it will stay at lowest speed till 23% then at 24% core 2 will kick in and if that doesn't lower cpu load by time it reaches 49% load it will stay in dual core and go up one cpu step... if load doesnt drop it will continue to add speed and stay in dual core. but as soon as load drops below 49% speed will stay same and then core two will shut off at 24% and either finish the work load at that speed in single core, drop to lowest cpu speed in single core or as needed renenable core two to start process all over and therefore either finishing work load or ramping again while in dual core up in frequency till load once again drops into the threshold ranges.
Custodian and Freecharlesmanson i respect your info and would love to know how accurate this is. I am new to Android as of this year but not new to cpus so if you have advice or feedback for this discussion Id be very appreciative.
Click to expand...
Click to collapse
Well I'll explain it this way despite the freq step being low the issue is it will aim to unload the first CPU at 49% which won't take much after that while it will rest eventually because it is still so low on hotplug the second core will be constantly on. The second core offers more performance but much much more battery then slightly increases clock rate the issue is balancing that because so often you either end up with the clock rate racing up wards or the core staying on. . Personally don't take a shot in the dark. Take settings you know work and work towards your idea incrementally recording the changes the CPU time states record I think though not allowing the CPU to shift a full state up will be to major detriment to performance. Per CPU freq state is 4.3% I have found over 80% on available cores causes stuttering . I gave the settings a spin looks like the second core is on a bit much so you'd want to balance that out. But test test test test and let me know
Sent from my SPH-L710 using Tapatalk 2
Custodian said:
So my issue atm is with ES explorer scrolling. It's super choppy.... I'm exploring more values in hopes of finding a sweet spot. I can confirm that the choppiness doesn't exist on ICS but does on asop ROMs. So I'm trying to see what's up now.
Sent from my SPH-L710
Click to expand...
Click to collapse
Running es right now no issues . Sense it exist only on aosp I'm gonna guess it wasn't governor related? Can you confirm the same results running a different governor?
Sent from my SPH-L710 using Tapatalk 2
freecharlesmanson said:
Running es right now no issues . Sense it exist only on aosp I'm gonna guess it wasn't governor related? Can you confirm the same results running a different governor?
Sent from my SPH-L710 using Tapatalk 2
Click to expand...
Click to collapse
It's not gov related. Tested with performance, ondemand, conservative
Sent from my SPH-L710
---------- Post added at 04:25 AM ---------- Previous post was at 04:20 AM ----------
Meh dunno wtf going on. It's only with ES rxplore.
vm.swappiness = 0
Testing. Just cause. Lol.
Sent from my SPH-L710
Yeah phones don't benefit from swappiness but I'd leave a slight amount just in case you ever approach oom if you have it turned off and you ever hit oom it will kill random possibly important apps or just plain lockup
Unless you go oom though it makes no difference
Swappiness is set to 15% on my desktop and its only using 200kb arbitrarily I might add
Sent from my SPH-L710 using Tapatalk 2
freecharlesmanson said:
Well I'll explain it this way despite the freq step being low the issue is it will aim to unload the first CPU at 49% which won't take much after that while it will rest eventually because it is still so low on hotplug the second core will be constantly on. The second core offers more performance but much much more battery then slightly increases clock rate the issue is balancing that because so often you either end up with the clock rate racing up wards or the core staying on. . Personally don't take a shot in the dark. Take settings you know work and work towards your idea incrementally recording the changes the CPU time states record I think though not allowing the CPU to shift a full state up will be to major detriment to performance. Per CPU freq state is 4.3% I have found over 80% on available cores causes stuttering . I gave the settings a spin looks like the second core is on a bit much so you'd want to balance that out. But test test test test and let me know
Sent from my SPH-L710 using Tapatalk 2
Click to expand...
Click to collapse
okay great explanation. It was a good read I'll go back to drawing board test test test and post back with more theory and results when i've come up with something that is working good for me. I'll keep in mind I need Hotplug to not kick in as often nor have cpu frequency shoot up to max so its a balancing act. I appreciate your info thank you. I'm reading as much as i can find on more governors and their adjustments to get ideas from them too like you said to base off an existing one and modify from there.
mw86 said:
okay great explanation. It was a good read I'll go back to drawing board test test test and post back with more theory and results when i've come up with something that is working good for me. I'll keep in mind I need Hotplug to not kick in as often nor have cpu frequency shoot up to max so its a balancing act. I appreciate your info thank you. I'm reading as much as i can find on more governors and their adjustments to get ideas from them too like you said to base off an existing one and modify from there.
Click to expand...
Click to collapse
What you are shooting for is the opposite end of the stick so. Getting the same results off a diametrically opposed idea is awesome keep it up
Sent from my SPH-L710 using Tapatalk 2
Any one else notice how high the minimum click speed is foe the CPU? It's showing at once 600 MHz? Is there a purpose behind this?
Can't get the pics to attach for some reason. Used CPU spy to check and the built in help app on the device.
Milly7 said:
Any one else notice how high the minimum click speed is foe the CPU? It's showing at once 600 MHz? Is there a purpose behind this?
Can't get the pics to attach for some reason. Used CPU spy to check and the built in help app on the device.
Click to expand...
Click to collapse
600 Mhz is fast enough to take care of background tasks as they pop up since the a53 cores in the snapdragon 625 are not very fast, but are highly efficient. The CPU also has a power state lower than 600 mhz which is the sleep state, if you check kernel auditor it will tell you how much your cpu is in the sleep state, which should be most of the time your phone is asleep. If your CPU is not in the sleep state while off you probably have a wakelock preventing your phone from going into deep sleep.
jon7701 said:
600 Mhz is fast enough to take care of background tasks as they pop up since the a53 cores in the snapdragon 625 are not very fast, but are highly efficient. The CPU also has a power state lower than 600 mhz which is the sleep state, if you check kernel auditor it will tell you how much your cpu is in the sleep state, which should be most of the time your phone is asleep. If your CPU is not in the sleep state while off you probably have a wakelock preventing your phone from going into deep sleep.
Click to expand...
Click to collapse
Thanks. I get what you're saying. But, my post is geared more so as to why there aren't any clock speeds below the 652 MHz such as 422 and 300 MHz to handle the lower loads and background tasks such as in the snapdragon 810 etc.
Milly7 said:
Thanks. I get what you're saying. But, my post is geared more so as to why there aren't any clock speeds below the 652 MHz such as 422 and 300 MHz to handle the lower loads and background tasks such as in the snapdragon 810 etc.
Click to expand...
Click to collapse
Honestly, I dont know. From what I can tell the snapdragon 625 has a similar configuration of big and LITTLE cores as the snapdragon 808 and 810 had, but the cores are all the same, just 2 seperate clusters. Maybe during testing they found 600 mhz was an effective frequency to keep the other 4 cores from coming out of sleep mode. Once again though, as long as you dont have wake locks or intentionally keep your phone awake it shouldnt make much of a difference whether your minimum frequency is 300 mhz or 600 mhz. Even during normal usage it is entirely possible to only run on 4 cores and leave the other 4 in sleep mode.