Related
So, for all us CM7 users, there have recently been alot of questions as to why there is such a disparity between the stock CM7 kernel, and the 1.1Ghz kernel, given both are made by the same person (dalingrin). Really, there are two questions -
1) Why is the quadrant score different between the kernels?
2) How does this equate to real-world use?
To help answer #1, i went ahead and purchased a copy of Quadrant Advanced. The advanced version lets me run the bench offline (helpful at work ), and also shows each piece of the score (the important part, as seen in the results). this breakdown shows where the difference is.
But to answer #2, I have to go well beyond Quadrant, and look at many different benches. I tried to find a variety of both system and 3D benches in a hope to uncover any problems anywhere. If there is a more widespread problem, it may be uncovered in other benchmarks. So, without further ado, the test system:
CM7- nightly 27, running on eMMC
Stock CM7 Kernel, 925Mhz, Performance Governor
OC CM7 Kernel, 1000Mhz, Performance Governor
OC CM7 Kernel, 1100Mhz, Performance Governor
I kept the gov on performance, to help rule out any differences between governors. Performance runs the CPU at full speed all the time, so it keeps the benches comparable. For every CPU speed/kernel change, i rebooted the system, and ran each bench once in the order listed. And the results!
Stock kernel
CPU @ 925, Performance gov,
Quadrant (First run only):
Total: 1536
CPU: 2504
Mem: 1080
I/O: 3629
2D: 188
3D: 278
Linpack:
12.078Mflops
NenaMark:
16.7 Fps
Benchmark PI (https://market.android.com/details?id=gr.androiddev.BenchmarkP):
Pi found in 1636ms
Antutu System benchmark (https://market.android.com/details?id=com.antutu.ABenchMark):
Total Score: 1675
Memory: 407
CPU Integer: 578
CPU Float: 129
2D Graphics: 100
3D Graphics: 276
Database IO: 10
SD Card Write: 5.0 MB/s
SD Card Read: 12.5 MB/s
An3DBench (https://market.android.com/details?id=com.threed.jpct.bench):
Fillrate ST/MT: 6.21/6.22 MP/s
High object count: 27.03 Fps
Multiple Lights: 40.19 Fps
High polygon count: 19.97 Fps
Keyframe animation: 39.97 Fps
Game level: 30.04 Fps
Total score: 4278
3/16 Overclock Kernel
CPU @1000Mhz, Performance gov
Quadrant (First run only):
Total: 960
CPU: 2693
Mem: 1099
I/O: 522
2D: 202
3D: 286
Linpack:
12.983Mflops
NenaMark:
17.0 Fps
Benchmark PI:
Pi found in 1627ms
Antutu System benchmark :
Total Score: 1832
Memory: 445
CPU Integer: 631
CPU Float: 144
2D Graphics: 109
3D Graphics: 302
Database IO: 20
SD Card Write: 5.8 MB/s
SD Card Read: 12.3 MB/s
An3DBench:
Fillrate ST/MT: 6.23/6.19 MP/sec
High object count: 30.46 fps
Multiple Lights: 39.96 fps
High polygon count: 20.16 fps
Keyframe animation: 40.40 fps
Game level: 30.43 fps
Total score: 4397
CPU @1100Mhz, Performance gov
Quadrant (First run only):
Total: 1001
CPU: 2833
Mem: 1085
I/O: 566
2D: 213
3D: 306
Linpack:
MFlops: 13.917
NenaMark:
16.8 Fps
Benchmark PI:
Pi found in 1460
Antutu System benchmark:
**Would not run at 1100**
Total Score:
Memory:
CPU Integer:
CPU Float:
2D Graphics:
3D Graphics:
Database IO:
SD Card Write:
SD Card Read:
An3DBench :
Fillrate ST/MT: 5.89/6.01
High object count: 17.53 fps
Multiple Lights: 40.22 fps
High polygon count: 20.13 fps
Keyframe animation: 40.37 fps
Game level: 30.44
Total score: 4054
The results speak alot, i think, and yet they don't. The big difference, is that the IO score on Quadrant tanks on the OC kernel, but is fine/better on every other test. Specifically, i noticed that file system writes takes much longer on the OC kernel, than the stock. 3D performance makes obvious gains with increasing clock speed, and other CPU / IO benches show no problem either.
The antutu bench failing at 1.1 is very odd, since my system has never shown any instability at this speed. It crashes almost immediately , where are 1.0Ghz makes it through just fine. Could it be my system is instable? Possibly...
just for the heck of it, i set the gov to interactive, and here is what i got (1100Mhz, OC kernel, Interactive Gov):
Antutu System benchmark:
Total Score: 1089
Memory: 481
CPU Integer: 701
CPU Float: 154
2D Graphics: 101
3D Graphics: 209
Database IO: 10
SD Card Write: 4.9 MB/s
SD Card Read: 10.4 MB/s
who knows....
Thus, I am left with this question: Is the Quadrant bench testing an IO function that no other bench i tried is, or is it testing something in a way no other bench does, and just doesn't like this kernel? Obivously, SOMETHING is going on, becuase the problem is measurable and repeatable. The kernel change showing the problem alludes to a possible issue, but other benches say that the likelyhood of noticing it is minimal.
That said, our device isn't the only one that seems like it has a problem with IO scores: http://androidforums.com/samsung-captivate/136969-quadrant-scores.html
Hopefully, this is a starting point for people, and might even help a dev or two pinpoint what might be happening. I am no expert, but am willing to help where i can.
Data Formatting
Thanks for the bench scores. Hopefully its a starting point to understand the issue.
Here is a better looking version of your numbers :
{
"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"
}
Wow.. many thanks for the awesome graph; it really makes things so much neater!
Also the guesses that it may be a problem with quadrant may pan out. I always thought the OC kernel seemed snappier as far as user interaction (especially launching the applications list w/ animations.)
chisleu said:
Also the guesses that it may be a problem with quadrant may pan out. I always thought the OC kernel seemed snappier as far as user interaction (especially launching the applications list w/ animations.)
Click to expand...
Click to collapse
The user interaction improvement is due to increased CPU clock and 2D performance. IO matters when you install or load something.
amtrakcn said:
The user interaction improvement is due to increased CPU clock and 2D performance. IO matters when you install or load something.
Click to expand...
Click to collapse
Except those numbers are inaccurate.
chisleu said:
Except those numbers are inaccurate.
Click to expand...
Click to collapse
The performance increase I've experianced with the o/c kernal leads me to agree with your point about the quad benchmark numbers being off the mark. That said, I was wondering if your statement is based on a deeper understanding of what is causing the low io quadrant numbers, and if it is, that you would be willing to share your thoughts. Thanks.
I think the statement really is worth looking into - the performance variance should be explored; just because quadrant is the only bench that shows and issue, doesn't mean there isn't one in the system...
Divine_Madcat, just wanted to say I appreciated the way you analyzed the issue and presented your findings. I learned alot from your approach. Enjoying your post. I'll send a thanks your way next time I sign in from my web browser.
Sent from my SGH-I897 using XDA App
vizographic said:
The performance increase I've experianced with the o/c kernal leads me to agree with your point about the quad benchmark numbers being off the mark. That said, I was wondering if your statement is based on a deeper understanding of what is causing the low io quadrant numbers, and if it is, that you would be willing to share your thoughts. Thanks.
Click to expand...
Click to collapse
I am not making a statement based on personal knowledge, but simply parroting something the guy who manages the kernal builds said.
So which should we use?
evilmerlin said:
So which should we use?
Click to expand...
Click to collapse
The OC Kernel. The OP was documenting something in detail to try to help out. There is a weird issue causing the OC kernel to show up slower than the stock in one benchmark. It's faster in all other benchmarks. There is probably something wrong with the benchmark.
chisleu said:
The OC Kernel. The OP was documenting something in detail to try to help out. There is a weird issue causing the OC kernel to show up slower than the stock in one benchmark. It's faster in all other benchmarks. There is probably something wrong with the benchmark.
Click to expand...
Click to collapse
Thanks for all the feedback guys. Chisleu, i would say you are correct, that it probably is the bench. Yet, there is just this small nagging part of me that wonder if quadrant isn't using something nothing else is, and found a hidden problem. Needless to say, i am not done looking at all this yet.
Divine_Madcat said:
Thanks for all the feedback guys. Chisleu, i would say you are correct, that it probably is the bench. Yet, there is just this small nagging part of me that wonder if quadrant isn't using something nothing else is, and found a hidden problem. Needless to say, i am not done looking at all this yet.
Click to expand...
Click to collapse
It is worth investigating though I must say it is low on my priority list. I don't put much weight in Quadrant and especially their I/O tests. Their I/O tests are known to be especially flaky.
When I get a chance, I will go through and remove the tweaks that are not in common with the CM7 kernel to see what is causing it. Unless someone beats me to it. *hint hint*
Thank you, Mr. Divine_Madcat! Hopefully you will continue your highly valuable benchmarking work with every significant CM7 nightly and RC, and Froyo/HC, to show the progress and better appreciate the work of our devs.
Quadrant marks peculiarities are, yes, puzzling. And they are not just in their absolute values, but the scatter of these between consequent benchmarkings.
Also, I know it's not the opportune time, but just to get into an understanding of a baseline FPS for OpenGL ES HW acceleration (or lack thereof), it might be worth the effort to do Neocore, at least on CM7 builds.
Thank you.
dalingrin said:
It is worth investigating though I must say it is low on my priority list. I don't put much weight in Quadrant and especially their I/O tests. Their I/O tests are known to be especially flaky.
When I get a chance, I will go through and remove the tweaks that are not in common with the CM7 kernel to see what is causing it. Unless someone beats me to it. *hint hint*
Click to expand...
Click to collapse
I got confused going into the kernel code. It looked like you guys only changed 8-10 lines of code from the B&N release. The last CVSystem I've used was CVS. heh. This new fangled "git" thingie is blowing my mind.
EDIT: NM... I wasn't seeing all the commits. Now I get it. Do we have to make config/menuconfig/whatever to setup the kernel, or are all the flags ready to go?
EDIT: Man I have some catching up to do. I remember when menuconfig was hot ****. The last kernel I built was 2.2.something IIRC.
Can't find the .config. Surely it's not hidden?
i know that quadrant puts a big emphasis on i/o score. just going from ext3 to ext4 on a archos 101 gave ~800-1000 pts.
scores have been around 2900 on quadrant for a device that feels slower than a galaxy tab.
I seem to have more touchscreen lag/miscalibration when using the oc kernal. It's only really apparent when i'm typing on the keyboard. I was using the stock kernal for about a week with no real issues. Is this something anyone else is experiencing? I was going to flash back to stock, but if it seems isolated, and i'll just flash the new nightly and the OC kernal on top of it again.
xwint3rxmut3x said:
I seem to have more touchscreen lag/miscalibration when using the oc kernal. It's only really apparent when i'm typing on the keyboard. I was using the stock kernal for about a week with no real issues. Is this something anyone else is experiencing? I was going to flash back to stock, but if it seems isolated, and i'll just flash the new nightly and the OC kernal on top of it again.
Click to expand...
Click to collapse
search for the touchscreen calibration. it's like 1 su/adb command.
chisleu said:
I am not making a statement based on personal knowledge, but simply parroting something the guy who manages the kernal builds said.
Click to expand...
Click to collapse
Thanks for the clarification. I take it you are referring to dalingrin. I think I recall the issue being addressed in a thread but I can't remember exactly what was said or where it was brought up. Do you have the threads post number by chance, since any observations on his part are worthy of serious consideration. Just hoping to learn something new here. Thanks in advance.
Web page refresh showed post by chisleu which quoted dalingrin on the io issue. If this was the post You were referring to then please ignore the above request.
Based on the newest HTC source code.
Overclocked CPU, added optimized CPU frequency tables with CPU frequencies up to 1836 MHz and L2 cache frequencies up to 1566 MHz.
Increased CPU voltage limits (700 mV - 1400 mV).
Added CPU Voltage Table interface that allows voltage adjustment.
Fixed CPUFreq.
Overclocked GPU, increased maximum GPU frequency in 3D mode from 267 MHz to 320 MHz (300 MHz by default), increased bus bandwidth.
Added USB OTG.
Enabled USB Host.
Added support for different types of USB peripherals: USB Hub, USB mass storage devices (e. g. USB HDD, USB Stick, MP3 player), USB HID devices (e. g. USB mouse, USB keyboard, Wireless mouse or keyboard with USB receiver).
v1.4.0
First release built from kernel source code vigor-ics-crc-3.0.16-d0049f1. Thanks to HTC!
Optimized.
Added higher values to L2 cache frequency tables.
Updated CPU frequency tables.
Fixed ACPU and perflock to allow setting different maximum CPU frequency than highest available.
Fixed issue with changing minimum and maximum CPU frequencies by the system daemons. Replaced thermald.
Extended CPU voltage limits.
Added 300 MHz GPU clock settings.
Increased GPU bus bandwidth in 3D mode.
Modified Adreno220 drivers.
Overclocked GPU in 3D mode to 300 MHz by default, maximum 320 MHz.
Enabled USB OTG.
Added NTFS support.
Added SCSI.
Added USB Host.
Added USB storage and USB storage drivers.
Added USB HID.
Added drivers for USB HID devices.
Added support for zRam swap.
CIFS, SquashFS.
Enabled CPUFreq stat.
Added CPU Voltage Table - interface that allows adjustment of the CPU voltage (thanks to snq-, faux123 and show-p1984).
v1.3.0
Based on new kernel 3.0.16-g480e1b0 (August 3).
v1.20
Based on new kernel 3.0.16-g4a9c8a3 (March 10).
Fixed CPUFreq, mfreq related bug (which caused performance issues).
v1.10
Three kernel variants with different maximum CPU frequency.
First release based on kernel 3.0.16-g837f300.
Modified CPU frequency tables, CPU speed limits and voltage limits.
Modified information about CPU frequency displayed in Hardware information.
CPU Temperature daemon:
thermald v1.0.0 (SebastianFM)
The thermald daemon is a system service which monitors CPU temperature. It turns on the thermal sensor and sets thresholds to the thermal driver. Threshold are defined in file /system/etc/thermald.conf. If temperature reaches threshold, kernel sends notification to userspace. When thermald receives notification, it decreases CPU frequency to avoid CPU overheat.
The stock thermald doesn't work properly because when the CPU temperature drops below threshold, or when mpdecision turns on the second core, it always sets maximum CPU frequency to the highest available frequency.
I wrote my own thermald daemon which works very similiar, but when the CPU temperature is too high, it saves the current maximum CPU frequency and restores it later.
Currently my thermald doesn't parse external config file, it uses predefined thresholds.
Code:
[tsens_tz_sensor0]
sampling 3000
thresholds 75 78 81 84 87
thresholds_clr 72 75 78 81 84
actions cpu cpu cpu cpu cpu
action_info 1296000 1188000 918000 756000 384000
If you include my thermald in your ROM or kernel package, please don't forget give credit to me.
Current downloads:
v1.4.0, link, md5: 6ea612dd76b816e1ef10b5bf637b0d16
Older downloads:
v1.3.0 1728 MHz, link, md5: 3f6ab21ade2972f466baa8bbb80f7ab3
v1.3.0 1782 MHz, link, md5: f40b4578fb3c97f1556c53e926adfeb1
v1.3.0 1836 MHz, link, md5: 982e3fad23402556c48442f218d080b4
v1.20 1728 MHz, link 1, link 2, md5: d451991973bf26db28b6de1dcd1c6250
v1.20 1782 MHz, link 1, link 2, md5: 8051e4a094245ad0bad60b502ea264c9
v1.20 1836 MHz, link 1, link 2, md5: 42ae1d7416d46d68b59000f7c8d2995b
Installation:
This is flashable zip intended for install from recovery.
If your device is S-ON, installation will fail but PH98IMG.zip will be created on SD card. Reboot into bootloader, kernel will be flashed from this file.
OC:
The CPU frequency 1782 MHz should be stable but every device is different.
To increase maximum GPU frequency in 3D mode to 320 MHz:
echo 320000000 > /sys/devices/platform/kgsl-3d0.0/kgsl/kgsl-3d0/max_gpuclk
{
"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"
}
Source code:
GitHub
Thanks:
zone23, for testing and for AnTuTu scores, thank you.
con247, my installation scripts are based on con247's work, thanks.
I love you!! i went on your thread on the sensation a couple of weeks ago begging for this kernel and asking how you did this without source and everyone told me how amazing you were, im soo glad to see you on this thread for the rezound. Thank you!
Oh baby this is hot!
zetsumeikuro said:
Oh baby this is hot!
Click to expand...
Click to collapse
Nice choice of words...
Yum
Sent from my ADR6425LVW using XDA App
so im guesing that this will only work on a sense based ics rom correct?
JohnShaft69 said:
so im guesing that this will only work on a sense based ics rom correct?
Click to expand...
Click to collapse
Yup. HTC bases only for this kernel.
this kernel doesnt work. gets stuck at white screen on Joelz Rom, im sure its a easy fix. still hyped over this. especially antutu scores
Easton999GS said:
this kernel doesnt work. gets stuck at white screen on Joelz Rom, im sure its a easy fix. still hyped over this. especially antutu scores
Click to expand...
Click to collapse
I'm on Joelz Rom, not having that issue. Running great for me.
Sent from my ADR6425LVW using xda premium
Works for me, on 4.0.1 with Sense, very smooooooth. Using CPU Master though, and the frequencies I set do not always stick... any suggestions?
TheRedmonian said:
I'm on Joelz Rom, not having that issue. Running great for me.
Sent from my ADR6425LVW using xda premium
Click to expand...
Click to collapse
Are you running the latest version of Joel's ROM that he posted last night?
If so, is this running better than the kernel from his ROM?
WizeGuyDezignz said:
Are you running the latest version of Joel's ROM that he posted last night?
If so, is this running better than the kernel from his ROM?
Click to expand...
Click to collapse
Yes and Yes. Much smoother.
Sent from my ADR6425LVW using xda premium
SebastianFM said:
This is hex edited by me, overclocked, stock HTC kernel.
Thanks:
con247 for script and tests.
Click to expand...
Click to collapse
Thanks again for doing this! I tested this on an older version of Tachi91's rom Here (2.x maybe?) for the past few days and it has ran fine and been stable. It should work on any sense ics rom seeing that we dont have kernel source yet and the current ics kernels floating around are either the same are almost the same.
SebastianFM said:
This is hex edited by me, overclocked, stock HTC kernel.
Features:
v 1.00
Unlocked and increased CPU and L2 cache maximum frequency and voltage limit.
Added values to frequency tables for CPU up to 1.728 GHz and for L2 cache up to 1.566 GHz.
Installation:
This is flashable zip intended for install from recovery.
I used con247 Automatic Kernel Installation for S-ON Unlocked Devices, so you can flash this kernel on any ROM.
Download:
1.728 GHz OC kernel 3.0.13-gaf15497-dirty v1.00 md5sum:
Thanks:
con247 for script and tests.
Click to expand...
Click to collapse
Sebastian do you recommend a specific app to manage the OC, governor, I/O scheduler with this Kernel or is it purely self contained?
TheRedmonian said:
Yes and Yes. Much smoother.
Sent from my ADR6425LVW using xda premium
Click to expand...
Click to collapse
Awesome, thanks for the reply!
Are you using SetCPU or anything similar, or just the kernel as is? If you are using an app, what do you have your settings at?
I only ask because I'm running the same ROM as you and would like to duplicate your results!
Thanks!
I can confirm that this works extremely well on newts sense rom. No problems and very smooth
I'm living on a yellow submarine
WizeGuyDezignz said:
Awesome, thanks for the reply!
Are you using SetCPU or anything similar, or just the kernel as is? If you are using an app, what do you have your settings at?
I only ask because I'm running the same ROM as you and would like to duplicate your results!
Thanks!
Click to expand...
Click to collapse
I've been running as is for now.
Sent from my ADR6425LVW using xda premium
Working good for me on Newts senseless. Now all we need is done governors to go with and it will be perfect. Great job!
Sent from my ADR6425LVW
Njenson said:
Working good for me on Newts senseless. Now all we need is done governors to go with and it will be perfect. Great job!
Sent from my ADR6425LVW
Click to expand...
Click to collapse
I believe the governors and I/O scheduler stuff might have to wait until the ICS kernel source is released (at least to make them as effective as possible and backport the latest kernel changes from Linux).
This is orgasmic.
Sent from my ADR6425LVW
In AnTuTu Benchmark i get worse score for CPU and Memory. Is it my Phone Died? I will never again buy used Phone. I have new Gigabyte GSmart Roma R2 (Plus Edition) with very fast CPU and Alcatel Pop C3 and both works great.
Sandi1987 said:
In AnTuTu Benchmark i get worse score for CPU and Memory. Is it my Phone Died? I will never again buy used Phone. I have new Gigabyte GSmart Roma R2 (Plus Edition) with very fast CPU and Alcatel Pop C3 and both works great.
Click to expand...
Click to collapse
The CPU and Memory benchmarks depend on the ROM, the number of Apps you've installed, and a lot more factors. Also, this phone is 4.5 years old now, so what more do you expect out of it? Your phone is not dead. Go ahead and try out some custom ROMs, Kernels and MODs for your i9100.
Sandi1987 said:
In AnTuTu Benchmark i get worse score for CPU and Memory. Is it my Phone Died? I will never again buy used Phone. I have new Gigabyte GSmart Roma R2 (Plus Edition) with very fast CPU and Alcatel Pop C3 and both works great.
Click to expand...
Click to collapse
What's your antutu score? Anything above 12000 should be considered alright. I personally get around 15000 on antutu. Perhaps look more at the specs of the cpu and etc to confirm if product is gunuine or not.
gsstudios said:
What's your antutu score? Anything above 12000 should be considered alright. I personally get around 15000 on antutu. Perhaps look more at the specs of the cpu and etc to confirm if product is gunuine or not.
Click to expand...
Click to collapse
12735 (Version 5.1). I tried PassMark PerformanceTest and Quadrant Standard Edition and i got lower Results on the same ROM. Something is wrong with CPU and Memory.
EDIT:
I got Score 13451 in version 5.7, but CPU and Memory Score are too bad.
@Sandi1987
Put your phone in a fridge for 1 hour . Clear recent apps menu and ram and run the test again. Tell us results.
And i'm not joking about 1 hour in fridge.
Wysłane ze Slim-fonika 9.0 powered by Apolo 7.3
In SuperPI i got normal Results (1M) and Games works normally.
Sandi1987 said:
12735 (Version 5.1). I tried PassMark PerformanceTest and Quadrant Standard Edition and i got lower Results on the same ROM. Something is wrong with CPU and Memory.
EDIT:
I got Score 13451 in version 5.7, but CPU and Memory Score are too bad.
Click to expand...
Click to collapse
CPU and memory scores affected by version of android (as well as runtime and etc). Usually stock won't give the best performance, but custom roms usually have more performance. Installing a custom kernel can also boost performance too.
{
"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"
}
Same Android and AnTuTu version.
I have:
RAM: 970
CPU Integer: 1205
CPU Float-Point: 205
CPU Float-Point Score is so bad.
Why i have lower Scores then on Alcatel Pop C3 with 1300 MHz Dual Core in Benchmarking Software, but Games works normally like always? Android System works fast.
My CPU works only at Max. 800 MHz, not 1200 MHz. This is the reason why i get lower Scores. I Overclock CPU from 1200 MHz to 1400 MHz and it's works only at 800 MHz.
EDIT:
I found the problem. I have Enabled Energy Saver.
{
"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"
}
Read Carefully!
Code:
#include
/*
* Your warranty is now void.
*
* We are not responsible for bricked devices, dead SD cards,
* thermonuclear war, or you getting fired because the alarm app failed. Please
* do some research if you have any concerns about features included in this ROM
* before flashing it! YOU are choosing to make these modifications, and if
* you point the finger at us for messing up your device, we will laugh at you.
*
*/
Kernel Features:
CPU
-Big Core overclocked to 2.00 GHz
-Little Core Overclocked to 1.65 GHz
-Reduced Cpu voltage ceiling
-Mild Undervolt for Heat Reduction
-Reduced Regulator Min Microvolt
Governors
-Lionfish
-Darkness
-Peqasusq
-Barry_allen
-Interactive
-Ondemand
-Userspace
-Powersave
-Perfomance
GPU
-Overclocked to 650 MHZ
Governors:
-Powersave.
-Performance.
-Simple_Ondemand.
-Userspace.
-msm-adreno-tz.
-cpu-freq.
Display
-KCAL included (Use Color Control App for KCAL)
Sound
-Faux Sound Control Support
-THERMAL TAB:
-Core Control
-VDD RESTRICTION.
-Temperature Throttle.
IO SCHEDULERS
-Fiops
-Noop.
-Deadline.
-Row.
-cfq.
OPTIMIZATIONS AND TWEAKS
-Updated to latest caf branch '/LA.BR.1.2.9_rb1.24'
-Fixed dirty Kernel Version
-Optimized Console FrameBuffer for upto 70% increase in Performance
-Reduced CPU Load-Average
-Fixed High-Load Average due to Drivers
-Optimized Integer SQRT. for upto 3x faster operation
-Added support for Controlling Sched. Features
-Network Speed Tweak
-Implemented PowerEfficient WQ for Regulator Core
-Enabled High-Priority WorkQueue for DevFreq
-Entropy Tweaking
-Boot with all 8 cores
-Reduced RQ Lock-Contention for upto 0.7% increase in Performance
-Optimized Task-Search for upto 6% increase in Performance
-Reduced WakeLocks
-Optimized task_sched_runtime for upto 20% increase in Performance
-Tweaked MSM-Thermal
-Disabled CPU L2 Cache during Video Sessions
-Reduced CPU Average-Load drastically
-Disabled CRC-Check upto 30% faster I/O.
MISC CONTROLS:
-Vibration Strength.
-TCP Congestion Algorithm.
Low Memory Killer:
Adaptive Low Memory Killer.
Click to expand...
Click to collapse
Download:
For LineageOS 14.1 (1.1 kernel version) .
Download from Here!
For Resurrection Remix 5.8.3 (Nougat 7.1.2) (Latest )
Download from Here
Installation Steps:
Boot to Twrp
Go to Flash
Flash as image > Boot
Special Thanks:
@Demetris
@FireLord
@Huskied
@Magus
@Nikomccreary
@kal250
@Sinister Drake
@OrphansCode
XDA:DevDB Information
[Kernel][7.1.2][6045][OC][UV]Extreme Kernel for idol3 5.5 [CPU 2.00 GHZ][GPU 650 MHZ], Kernel for the Alcatel Onetouch Idol 3
Contributors
Alek Dev
Source Code:https://github.com/AlekDev1/android_kernel_alcatel_msm8916/tree/cm-14.1-new
Version Information
Status: Stable
Current Stable Version: 1.2
Stable Release Date: 2017-06-17
Created 2017-06-13
Last Updated 2017-09-09
Changelog,Benchmarks and Battery Tests,Recommended Settings
Changelog:
Release 1.1
LineageOS 14.1 Kernel
-Fixed Ril Compactibillity issues with Latest Builds
Resurrection Remix 7.1.2 Kernel
-First Release
Release 1.2
Resurrection Remix 7.1.2 Kernel
-Updated to latest caf branch '/LA.BR.1.2.9_rb1.24'
-Fixed dirty Kernel Version
-Optimized Console FrameBuffer for upto 70% increase in Performance
-Reduced CPU Load-Average
-Fixed High-Load Average due to Drivers
-Optimized Integer SQRT. for upto 3x faster operation
-Added support for Controlling Sched. Features
-Network Speed Tweak
-Implemented PowerEfficient WQ for Regulator Core
-Enabled High-Priority WorkQueue for DevFreq
-Entropy Tweaking
-Boot with all 8 cores
-Reduced RQ Lock-Contention for upto 0.7% increase in Performance
-Optimized Task-Search for upto 6% increase in Performance
-Reduced WakeLocks
-Optimized task_sched_runtime for upto 20% increase in Performance
-Tweaked MSM-Thermal
-Disabled CPU L2 Cache during Video Sessions
-Reduced CPU Average-Load drastically
-Disabled CRC-Check upto 30% faster I/O.
Experimental Settings:
************BATTERY SAVER************
CPU TAB:
BIG:
Max Freq: 800 MHz
Min Freq: 150 MHz
Governor: Darkness.
Little:
Max Freq: 800 MHz
Min Freq: 100 MHz
Governor: Darkness.
GPU TAB:
Max Freq: 465 MHz.
Min Freq: 160 MHz
Governor: Powersave.
IO Sched:
Internal:
Scheduler: Noop.
Read-ahead: 512kb
External:
Scheduler: Noop.
Read-Ahead: 896 kb.
Everything else to Default.
************BALANCED************
CPU TAB:
BIG:
Max Freq: 1651 MHz
Min Freq: 1113 MHz
Governor: Lionfish
Little:
Max Freq: 1497 MHz
Min Freq: 998 MHz
Governor: Lionfish
GPU TAB:
Max Freq: 550 MHz.
Min Freq: 220 MHz
Governor: Simple_ondemand.
IO Sched:
Internal:
Scheduler: fiops.
Read-ahead: 512kb
External:
Scheduler: Noop.
Read-Ahead: 896 kb.
Everything else to Default.
************PERFOMANCE************
CPU TAB:
BIG:
Max Freq: 2000 MHz
Min Freq: 1651 MHz
Governor: Lionfish.
Little:
Max Freq: 1651 MHz
Min Freq: 1209 MHz
Governor: Lionfish
GPU TAB:
Max Freq: 650 MHz.
Min Freq: 310 MHz
Governor: msm-adreno-tz.
IO Sched:
Internal:
Scheduler: fiops.
Read-ahead: 512kb
External:
Scheduler: fiops.
Read-Ahead: 896 kb.
Everything else to Default
Click to expand...
Click to collapse
Benchmarks and Battery Tests:
Benchmark and Battery Test by @Sinister Drakeusing lionfish governor (freq not changed)
Click to expand...
Click to collapse
Details about Custom Governors:
Lionfish
The Lionfish governor combines traits of the conservative, ondemand, and interactive governors. It is designed to maximize battery life without noticeably impacting performance. It responds quickly to heavy loads (similar to ondemand and interactive) while staying within the region of optimal CPU performance per watt. With moderate loads, it periodically votes to raise, maintain, or decrease the frequency. When there are enough votes to change the frequency, it is ramped up and down gradually. The voting mechanism reduces frequency jitter compared to ondemand and conservative. squid2's testing had found that this governor uses moderate frequencies (where efficiency is optimal) more effectively than interactive, ondemand, and conservative. This improved frequency distribution results in a moderate reduction in CPU power consumption while maintaining responsiveness comparable to the interactive governor
Click to expand...
Click to collapse
.
Darkness:
I
t's based on nightmare but more simple and fast, basic configs but very complex structure. It is an updated nightmare gov and improved stability, so far it is quite stable in tests
Click to expand...
Click to collapse
Pegasysq
The Pegasus-q / d is a multi-core based on the Ondemand governor and governor with integrated hot-plugging.
Ongoing processes in the queue, we know that multiple processes can run simultaneously on. These processes are active in an array, which is a field called "Run Queue" queue that is ongoing, with their priority values arranged (priority will be used by the task scheduler, which then decides which process to run next).
Click to expand...
Click to collapse
Barry-Allen
It's based on interactive. The governor is supposed to be more battery friendly and at the same have good performance.
Click to expand...
Click to collapse
Wow, impressive, but i have idol 4 with snapdragon 617. Cant use it but maybe i will switch to idol 3 5.5
Nice!, thanks for the effort.
Will test it soon.
Enviado desde mi GRACE mediante Tapatalk
That's crazy! Just one thing, I'm worried about temperatures cause even on stock kernel it's unpleasant to hold.
I've made a backup of stock lineage kernel, and it is emmc.win file. Should I just rename it to .img or I have to convert it somehow diverent?
Nikola Jovanovic said:
That's crazy! Just one thing, I'm worried about temperatures cause even on stock kernel it's unpleasant to hold.
I've made a backup of stock lineage kernel, and it is emmc.win file. Should I just rename it to .img or I have to convert it somehow diverent?
Click to expand...
Click to collapse
Device will not be hot,i do Undervolt....and you don't need to rename the backup of los kernel
But how to flash the backup I've made in win format ? Twrp can't see it that way..
Sent from my TCL IDOL3 using Tapatalk
Nikola Jovanovic said:
But how to flash the backup I've made in win format ? Twrp can't see it that way..
Sent from my TCL IDOL3 using Tapatalk
Click to expand...
Click to collapse
if you make backup just go to restore...
Alek Dev said:
if you make backup just go to restore...
Click to expand...
Click to collapse
It's blazing fast. But also the phone gets warm even in the pocket I'll try to lower the frequencies but I really like it because of the kcal screen saturation option. Set on 40 and it really makes the screen eye candy.
Thaat's the clutch. Thanks.
New Kernels Version 1.1
For LineageOS 14.1
-Fixed Ril Compactibillity issues with Latest Builds
Download from Here
For Resurrection Remix 7.1.2
-First Release
Download from Here
Also i update the Second post of thread with Some Recommended Settings and Benchmarks,Battery Tests....
Thank you friends bascore
korbu83 said:
Wow, impressive, but i have idol 4 with snapdragon 617. Cant use it but maybe i will switch to idol 3 5.5
Click to expand...
Click to collapse
I would make the switch. The idol 4 is a nice phone but overall has lack of support here at XDA. The Idol 3 overall is a better phone as it is Alcatel's flagship device. Plus there are a lot of people here at XDA that can help with support. We also have a few of us (myself included) that are developing and maintaining ROMs. We are also trying to get on the official support list for LineageOS so we can continue to get security updates for our awesome device.
Little cores don't utilize at all when the big ones work.
Sent from my TCL IDOL3 using Tapatalk
Nikola Jovanovic said:
Little cores don't utilize at all when the big ones work.
Sent from my TCL IDOL3 using Tapatalk
Click to expand...
Click to collapse
What issues did you have?
Too much use of big cores with almost none for of the little ones. I'll post sc
Sent from my TCL IDOL3 using Tapatalk
Can this kernel be used on stock rooted rom? Thank you
zapper_master said:
Can this kernel be used on stock rooted rom? Thank you
Click to expand...
Click to collapse
Nada. Kernel is based on Lineage and RR.
Hey guys I am using this kernel and it's blazing fast but 1 big issue... The battery drain is real! I am currently switching between different countries govenors but still can't find the ideal one for balance and battery life... Please share what govenors ur using and which his best for battery life... Thanks!
gohaaron said:
Hey guys I am using this kernel and it's blazing fast but 1 big issue... The battery drain is real! I am currently switching between different countries govenors but still can't find the ideal one for balance and battery life... Please share what govenors ur using and which his best for battery life... Thanks!
Click to expand...
Click to collapse
i personally use Lionfish or Darkness Governor i get around 4 hrs Sot
Sent from my TCL IDOL3 using Tapatalk
DRAGON KERNEL SOURCE PROJECT FOR
J51x AND J5x devices
{
"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"
}
Supported devices:
SM-J510FN (High binned)
SM-J500FN (High binned)
SM-J500G (Low binned
SM-J500H (Low binned)
SM-J500M (Low binned)
Features:
CPU governors: blu_active, cultivation, chill, interactive (default), ondemandplus, performance and relaxed
I/O schedulers: bfq, cfq, deadline, fiops, maple (default), noop, sioplus, and zen
CPU hotplugs: AutoSMP
Custom voltage control
Power Efficient workqueues
Backported Zen Interactive tunings from Zen 4.10
WireGuard support
KCAL advanced color control (http://forum.xda-developers.com/andr...ntrol-t3032080)
Fsync on/off support
USB fast charge
State notifier
Compiled with Linaro GCC 4.9.4 toolchain
Features for hight binned produtcs:
CPU frequency up to 1.36 GHz
GPU frequency up to 620 MHz
Various efuse registers
Downloads:
DRAGON-V2
XDA:DevDB Information
DRAGON, Kernel for the Samsung Galaxy J5
Contributors
BulgarianJesus
Source Code: https://github.com/DragO0nFly/android_kernel_samsung_msm8916_j5x-DRAGON
Kernel Special Features:
Version Information
Status: Stable
Created 2018-10-03
Last Updated 2018-10-05
<Mod Edit>
Thread closed
Changelog
V2.1
Toolchain: Switched to Linaro GCC 7.1.3
CPU: unlocked low binned devices and their registers
CPU: overclocked low binned devices up to 1.36 GHz
GPU: unlocked low binned devices and their registers
GPU: unlocked 465 MHz for low binned devices
GPU: Overclocked both low and high binned devices up to 620 MHz
GPU: initial power-up level set at 200 MHz for better battery life
Information
CPU: Binning
Some devices are high binned, meanwhile others are low binned. If your device is high binned, it will boot at 1.36 GHz CPU and 465 MHz GPU default speeds, if this process fails it means your device is low binned and it's not really designed for being overclocked. Even if I stated that FN models are high binned, I found out that some J5F models are also high binned. All this depends on luck actually, my OC is different compared to others! Due to the fact I use the stock Qualcomm values, speed bins and register in order to obtain such type of overclock.
CPU: Overclocking
Overclocking is the increase of clock speed beyond the manufacturer's maximum rated clocks. Since manufacturers are only required to meet the minimum advertised specifications, the potential for overclocking of a product is not typically tested during the binning process. Therefore, it should not be assumed that higher-rated products will overclock better than lower-rated ones. Applying to this, our source code is limited in a really stupid way. The SoC can't switch between speed-bins which allow it to change efuse as well. Having the right efuse and speed-bin, unlock the "default" state of MSM8916 which is 1.36 GHz on CPU and 465 MHz on GPU. Previous methods of OC, just re-write manually the speed-bin to workload as 1.36 GHz without using an efuse or the correct speed-bin.
GPU: Overclocking
Both high binned and low binned devices support maximum frequency up to 620 MHz, with or without an efuse.
BUS: Overclocking
Current bus clock is 595.2 MHz, but it does support a frequency up to 740 MHz
Is it a touchwiz or aosp kernel?
Flegmon said:
Is it a touchwiz or aosp kernel?
Click to expand...
Click to collapse
touchwiz but soon it will be also AOSP I hope
Where is J510F??
Great
Working fine on J510GN :good:
Congratulations for the amazing kernel, my j500F even though low binned seems ultra fast.
Battery usage is also balanced..
Great work dude and Welcome! ??
Best kernel runa greda on j510FN lighting nastane ice cool but how to overxloxk bus oni se kernel auditorium?
works great on my J510GN.
Doesnt lag while gaming.
jscheah said:
works great on my J510GN.
Doesnt lag while gaming.
Click to expand...
Click to collapse
What rom do you use?
Kernel is very good.It's on par with quasar.It matches quasar for gaming and that is something.Games run fast and smooth and framerates are great and sound is superb.The only negative was in memory it benchmarks 2000 less for memory than quasar but matches everything else.Will run it and see how battery is but that is minor to me.Nice work.
RicardoArantes said:
What rom do you use?
Click to expand...
Click to collapse
revenge os
Congratulations for the amazing kernel, my j510fn
I am really glad, you people like it @updesh94 thanks a lot man @Bogdans29 the BUS is already overclocked, it's designed to work at maximum speed with the specific overclock
deleted
Keep up the great work ??
jscheah said:
revenge os
Click to expand...
Click to collapse
Do you have the 3.0 link?
Battery is amazing doesn"t run at stupid high frequencies when not necessary and the battery usage is truly amazing hardly any percentage drop with phone apps been running 5 hours and 3 hours deep sleep incredible.This is better than quasar.The memory benchmark the only difference but phone can deal with that.You have the best nougat TW kernel Bulgarian Jesus.Congratulations superb work.