• Introducing XDA Computing: Discussion zones for Hardware, Software, and more!    Check it out!

[Kernel | Android 10 | One UI 2.5 | FUF5/FUH1/FUJ2] BeastMode Kernel v2 for N960F | v2.15a | 20211130

Search This thread

trevinutomo

Member
Oct 13, 2016
28
4
No. It’s the manager not being able to control the DVFS. The DVFS is doing as it pleases. If you disable it in sys/devices/platform/17500000.mali by removing read and write permissions from “dvfs “, “dvfs max lock” and “dvfs min lock” you will be able to use the frequencies you set up. (You have to use a root file explorer. A decent one). Unfortunately it’s a temporary solution, as it resets every reboot.

I assume DVFS is also the thing dropping frequencies for no reason on the CPU. If it’s not a timer nor temperature related
Confirmed

Disabling DVFS by revoking all read and write access making GPU run at any freq we set in hKTweak (even 572Mhz all the way long). Plus we need to disable game booster, game optimizer and friends. Those thing make instant re enable DVFS by itself (not even until reboot).
 
  • Like
Reactions: TechNoobForSale

ykkfive

Inactive Recognized Developer
Jul 25, 2010
3,099
2,940
ykkfive.blogspot.com
No. It’s the manager not being able to control the DVFS. The DVFS is doing as it pleases. If you disable it in sys/devices/platform/17500000.mali by removing read and write permissions from “dvfs “, “dvfs max lock” and “dvfs min lock” you will be able to use the frequencies you set up. (You have to use a root file explorer. A decent one). Unfortunately it’s a temporary solution, as it resets every reboot.

I assume DVFS is also the thing dropping frequencies for no reason on the CPU. If it’s not a timer nor temperature related

i thought he was talking about the gpu freq not shown correctly in those kernel managers

by looking at time_in_state you will find the real numbers
 

ykkfive

Inactive Recognized Developer
Jul 25, 2010
3,099
2,940
ykkfive.blogspot.com
Confirmed

Disabling DVFS by revoking all read and write access making GPU run at any freq we set in hKTweak (even 572Mhz all the way long). Plus we need to disable game booster, game optimizer and friends. Those thing make instant re enable DVFS by itself (not even until reboot).

i have read similar things before, so good to confirm it

l will let you guys to explore this. thanks
 

ykkfive

Inactive Recognized Developer
Jul 25, 2010
3,099
2,940
ykkfive.blogspot.com
i will go back to the sources
so in the mean time, pls discuss and share any thoughts, findings and results

but also please note that, since the introduction of cpu/gpu oc things in the past was a failure which degraded the overall performance, i decided to drop those tweaks and started over again, which was reflected in v2.10 i believe. so chances that some of the controls, not limiting to cpu/gpu oc, may not work properly, were partially done or have been rolled back to stock basis

please be patient and hope that they can be solved later

thanks
 
Last edited:
  • Like
Reactions: TechNoobForSale
i thought he was talking about the gpu freq not shown correctly in those kernel managers

by looking at time_in_state you will find the real numbers
The GPU frequencies in my experience are shown correctly. The problem is that you can't control them when dvfs is on. I think you should disable both CPU and GPU dvfs. It kills performance and is probably the culprit behind the 1950MHz bug
 

trevinutomo

Member
Oct 13, 2016
28
4
Just had a random reboot while the phone was in deep sleep (screen off). Again, it's a fast reboot. The phone does not turn itself off and show the samsung galaxy note 9 logo. It goes back to the Samsung glowing logo and then boots. Some settings remain applied.
i think you must be in unstable ROM i'm afraid. Cause in Dr.Ketan ROM this kernel work fine.
 
most likely rom issue then
btw, i have heard that alexis 3.0 requires a permissive kernel, how can you install it over this kernel?
I have no idea. I installed the ROM first, let it boot and then installed this Kernel by going back in TWRP. I had Selinux on enforced for a while but recently I put it on permissive on this kernel. I guess it managed to work because the kernel still supports permissive. This ROM was my last hope to revive my phone after I accidentally deleted the stock OS. So I don’t care if it was luck or anything else, I am glad it works on it lmao
 

ykkfive

Inactive Recognized Developer
Jul 25, 2010
3,099
2,940
ykkfive.blogspot.com
I have no idea. I installed the ROM first, let it boot and then installed this Kernel by going back in TWRP. I had Selinux on enforced for a while but recently I put it on permissive on this kernel. I guess it managed to work because the kernel still supports permissive. This ROM was my last hope to revive my phone after I accidentally deleted the stock OS. So I don’t care if it was luck or anything else, I am glad it works on it lmao

i see, cool
 
Admittedly I wonder why I didn’t install Dr Ketan ROM or Noble ROM or Lineage OS instead of this one. But it’s probably because I was highly distressed there, and knowing that I had positive experiences with the Alexis Rom (saved my S8 too. Lineage failed me once), I was super sure Alexis would’ve saved the day.
 

ykkfive

Inactive Recognized Developer
Jul 25, 2010
3,099
2,940
ykkfive.blogspot.com
i have built some beta builds based on a new kernel with pelt added. they only difference are, they come with different pre-defined settings like cpu max freq, mif values etc. some of them may be visible like max freq allowed but others are not

based on my tests on geekbench 5, they scored as high as 22xx (~10% increase) with multi cores and 70x (~15% increase) with single core, which both of them were new heights (for me) since the bm v2 released a few mths ago. and, it's not all about the scores but the smoothness, battery consumptions as well for instance, and in fact higher freq does not gurantee a better, overall performance due to the extra heat generated. i have seen huge degrades with higher cpu freq but more stable and higher ips (12xk with cpu throttling test) with lower freq

now, i would like to invite you guys to help me to test them out thoroughly since i am unable to test them one by one or otherwise you will have to wait for a few years :D . and in order not to screw up this thread, i tend to distribute them via pm and discussions will be carried out in another new thread

if you are brave enough and interested in taking the risks and share your findings together, pls drop me a pm. please also note that they are NOT supposed for normal users and experiemental, and they are NOT FREE! you will need to provide feedbacks!!

again, this is for you guys, i am more than satisifed with the current kernel

NOTE although i have tested them by myself, i cannot gurantee they are 100% safe. so you will have to bare all the risks, as usual


ps, a bit more info
i know may be some of you are frustrated, why this but not more oc and dealing with the throttling first?
well, as i have discussed with some of you guys, i wanna one for optimizing the overall performance instead of fast but inefficient kernel. in short, i am willing to scarifice for a few percentage gain in speed with relatively less power consumption per percentage gain in performance. i want to find the equalibrium in stead of speed chasing with substantial losses in battery power. i understand it is some what an ideal situation which may not be fruitful

and once this and other queuing things etc are solved, you can raise it as high as you like even if it is beyond the optimal point or with diminishing returns. it's up to you, no problem and no contradiction. on the other hand, if i go for the speed now and the new scheduler make you sad later, it will be irreversible (hard to reverse i mean), at least for me, kernel wise

wow, such a long post...
i hope you will understand my philosophy behind and the logic in the development, and of coz, my poor english :D

thanks a lot


edit 1
the differences between the builds are mainly cpu related, like little core max at 1950000/2002000, big core min freq at 650000/962000 etc. one of them is based on AndreiLux's cpu settings and there are no crazy things included

edit 2
this is the best cpu throttling test i have got but i forgot to write down the settings i have made.... the only clues i have are little core max = 964 and big core max=1794 by looking at the cpu monitor. however, i could not arrived at similar results again so far after more than 20 attempts
results:
121287 gips max, 96059 gips min with no sign of serious throttling
Screenshot_20211025-012621.jpg

edit 3
the 22xx and 70x i got from geekbench 5 were based on little core max at 949 only, so there are still rooms to improve
 
Last edited:
i have built some beta builds based on a new kernel with pelt added. they only difference are, they come with different pre-defined settings like cpu max freq, mif values etc. some of them may be visible like max freq allowed but others are not

based on my tests on geekbench 5, they scored as high as 22xx (~10% increase) with multi cores and 70x (~15% increase) with single core, which both of them were new heights (for me) since the bm v2 released a few mths ago. and, it's not all about the scores but the smoothness, battery consumptions as well for instance, and in fact higher freq does not gurantee a better, overall performance due to the extra heat generated. i have seen huge degrades with higher cpu freq but more stable and higher ipc (12xk with cpu throttling test) with lower freq

now, i would like to invite you guys to help me to test them out thoroughly since i am unable to test them one by one or otherwise you will have to wait for a few years :D . and in order not to screw up this thread, i tend to distribute them via pm and discussions will be carried out in another new thread

if you are brave enough and interested in taking the risks and share your findings together, pls drop me a pm. please also note that they are NOT supposed for normal users and experiemental, and they are NOT FREE! you will need to provide feedbacks!!

again, this is for you guys, i am more than satisifed with the current kernel

NOTE although i have tested them by myself, i cannot gurantee they are 100% safe. so you will have to bare all the risks, as usual


ps, a bit more info
i know may be some of you are frustrated, why this but not more oc and dealing with the throttling first?
well, as i have discussed with some of you guys, i wanna one for optimizing the overall performance instead of fast but inefficient kernel. in short, i am willing to scarifice for a few percentage gain in speed with relatively less power consumption per percentage gain in performance. i want to find the equalibrium in stead of speed chasing with substantial losses in battery power. i understand it is some what an ideal situation which may not be fruitful

and once this and other queuing things etc are solved, you can raise it as high as you like even if it is beyond the optimal point or with diminishing returns. it's up to you, no problem and no contradiction. on the other hand, if i go for the speed now and the new scheduler make you sad later, it will be irreversible (hard to reverse i mean), at least for me, kernel wise

wow, such a long post...
i hope you will understand my philosophy behind and the logic in the development, and of coz, my poor english :D

thanks a lot
Your philosophy, at least to me, seems like the one that puts as a long term objective building a Kernel that guarantees maximum performance but at the same time great efficiency, which is pretty respectable.

As always, I am fully open to test new builds. However you really make the safety side sound menacing lmao. What did you change/add exactly other than PELT? Is the possible safety issue you are talking about coming from the increased frequencies? What kind of numbers are we talking about? I can test, but I'd like to know what I'm dealing with first.

If you increased frequencies to the point of possible instability on some devices, 7xx and 22xx scores on Geekbench 5 are pretty low. Because I'd expect to get over 2300 and maybe even 2400. I have all the tools I need to keep the temperatures under check, but even then, just what did you do that caused the phone to throttle so much? I think you are aware that the peak frequency this phone can handle before hitting an efficiency wall is 4x2314MHz on the A75 cores. 2106 being the more conservative choice.
 

ykkfive

Inactive Recognized Developer
Jul 25, 2010
3,099
2,940
ykkfive.blogspot.com
Your philosophy, at least to me, seems like the one that puts as a long term objective building a Kernel that guarantees maximum performance but at the same time great efficiency, which is pretty respectable.

As always, I am fully open to test new builds. However you really make the safety side sound menacing lmao. What did you change/add exactly other than PELT? Is the possible safety issue you are talking about coming from the increased frequencies? What kind of numbers are we talking about? I can test, but I'd like to know what I'm dealing with first.

If you increased frequencies to the point of possible instability on some devices, 7xx and 22xx scores on Geekbench 5 are pretty low. Because I'd expect to get over 2300 and maybe even 2400. I have all the tools I need to keep the temperatures under check, but even then, just what did you do that caused the phone to throttle so much? I think you are aware that the peak frequency this phone can handle before hitting an efficiency wall is 4x2314MHz on the A75 cores. 2106 being the more conservative choice.

yeah you are right, i should have mentioned what the changes are. anyway i have updated the post above. pls read it again
 
  • Like
Reactions: TechNoobForSale
yeah i know, and that's why i want more to join. it's impossible for me to do all the tests alone
Then If you are okay with it I can start testing immediately. These changes, except for the PELT introduction, don’t look like they would be cause of serious instability to me (Imagine my phone gets soft bricked or hard bricked as soon as I install the test build LMAO). But it really shouldn’t be the case. Either way if these are all the changes you included, I can start testing as soon as you want me to.
 

Top Liked Posts

  • There are no posts matching your filters.
  • 2
    record breaker!!
    max 128k, min 107k

    btw, builds updated with fuj2 sources coming soon, with some addressed the gpu driver
    Screenshot_20211130-205403.jpg
    2
    Can you suggest a best profile for battery saver? I'm using EX kernel manager but I don't know how to config a profile properly. Please give me advice. Thanks.
    i don use kernel manager, but i can share with you my settings

    my aim is to make it as efficient as possible
    so,
    for the big cores, i set max=max, min=9xx
    while for the little cores max=the freq above the big cores' min freq, and min=min

    so that it will provide a smooth transition from the little to the big cores by letting the big core min freq covers part of the little cores max freq

    since the big cores are more efficient l let them do those heavy tasks by lowering the max freq of the little cores. ie if needed, go big pls, and i will further enhance this (big cores bias) in the future

    for the gpu,mi set it to min=266, boost to 3xx when the loading is above 30%. you can adjust these numbers according to your needs to avoid lagging while save some battery (note you can scroll the screen to see if it is smooth enough for you)

    usually it will consume about 8% battery for surfing the net for an hour

    hope it helps
    2
    I followed your advice and turned off everything. Hope you are ready for some weird results. The situation did not change, however I noticed that:

    - heavy throttle takes place when the cpu temp is below throttling point? (screenshot 1)
    - performance gain when the temp is 70 degrees (screenshot 2)

    Dr Ketan has just released a new update so I am curious to check the behavior of the stock kernel on his rom, after I will flash beast of course (edit: just noticed that new rom is on FUJ2 base so I might skip custom kernel flash until the next update).
    Which version to be installed on FUJ2, Nov security patch Dr ketan ROM?


    i have made one for fuj2, will upload it later
    daxx busy installing and reinstalling the phone due to a crash before. it made me sick!

    will try to answer other questions later

    sorry about that
    1
    So finally I decided to try your kernel, as I see great potential. Noob question here, but I am not sure if the kernel has been installed correctly, please see the attached picture. With ExKernel manager, I am able to set the I/O governor to noop, but not the CPU governor. As well, in the phone info it does now show BM Kernel, but only the stock kernel. Finally, I cannot find the RGB fade option. I am using Dr Ketan's Q17 Pro.

    Thanks in advance for your help :)

    it's not bm v2 kernel. try twrp 3.3.1.0
    if success it shoud show beastmode kernel v2
    1
    Resuming the testing.

    Geekbench 5 Run 1:
    Single: 725
    Multi: 2247

    Highest single core score I've ever reached on this Kernel. My record remains 732, on stock Samsung firmware for single core. Let's see if I can get more with another run

    Geekbench 5 Run 2:
    Single: 728
    Multi: 2216

    Note: On the multi core aspect there seems to be no improvement. However I see a slight improvement on the Single core score average. It very rarely falls below 700 now. Ykkfive has most likely tweaked the managing of the single core frequency, as I've seen 2886MHz being used much more frequently in the Single Core section. But this is still not enough. We should be seeing scores in excess of 745 in single core with a frequency of 2886MHz. But we are closing in. Rememeber that single core frequency is very important because it seems the system uses it when opening apps. And if the device uses that frequency more, app booting times will be reduced. 2496MHz and 2704MHz frequencies are still used way too much instead of 2886MHz in single core tests. Little CPUs keep capping at 1950MHz but that's my ROM's problem at this point. I just hope it won't bother me when frequencies above 1794MHz will be applied on big cores as well. I really hope so.

    Geekbench 5 Run 3, last one:
    Single: 733
    Multi: 2252

    Pretty good! However the multi core still falls short of the highest ever recorded on 9810, which is around 2350. Probably scored by a heavily throttled overclocked 9810, but we are closing in at stock big frequencies. So that's great. Let's go on. Keep in mind that L Speed is uninstalled.

    AnTuTu V9, first run: 456,761
    Everything performed well....except CPU, which fell short of about 5,000 points compared to its best possible performance.

    AnTuTu V9, second run, last one (Battery): 459,439

    Almost. Overall this Kernel release is exactly as the developer said. An improvement over the previous one, made by tweaks here and there. Nothing drastic. Therefore the performance is not too far away to be called "better" but not even the same as before. There is an improvement. That's it for today. Time to let my poor phone take a well deserved break. Considering that we started off from an Exynos 9810 that scored 370,000 on average and 410,000 in the best case scenario on stock firmware, this is definitely almost a generational leap ahead.
  • 12
    Hi all,

    It's ME again, being inactive for a few years due to my health conditions since Android Marshmallow! Today I would like to present you something I wanted for so long... an updated kernel for One UI 2.5! To be honest, I knew there were a lot of changes since MM, but not until these days I realized how troublesome they are, including rooting a device these days!! ( just rooted my N960F/DS running stock pie for more than a year ;) )
    OK, here we go!!


    This is an update to the BeastMode Kernel vR154 originally developed by @freeza and patched with latest Samsung One UI 2.5 kernel sources.

    Some of the features from R154 include:
    - enforcing kernel (switchable between enforcing/permissive)
    - cpu/gpu oc
    - dt2w (double tap to wake)
    - wireguard support


    However, due to my health conditions, I cannot spend too much time to update this kernel everyday although I am jobless, nor to have frequent updates as what @freeza did to his BeastMode Kernel. So please don't expect things will come very often. Thank you



    Special notes for BeastMode Kernel v2 initial release:
    - in the initial release (v2.02) there is no fix nor new feature added to the BeastMode Kernel vR154, as it servers as an update for new One UI 2.5 ROMs released by Samsung only
    - for existing features, problems or solutions, please visit the original BeastMode Kernel thread by @freeza
    - new features will be added in later releases



    BeastMode Kernel v2:
    - built with EVA GCC 12 and Proton Clang 13.0.0
    - for cts profile/safetynet fix, please install the Universal SafetyNet Fix by @kdrag0n



    Planned features:
    - more IO schedulers
    - more governors
    - OC/UV
    - f2fs (DONE!)



    If you like this, please consider donating a loaf of bread or something to support my living or buy some treats for my old dog @ https://paypal.me/ykkfive ( I don't need coffee or beer :giggle: ). Thanks!



    Important Notes:
    if you are using a kernel manger, please go to here and see if you are affected



    Downloads:
    Changelog and downloads in post #2



    Credits:
    Big thanks to @freeza for allowing me to use his work and publish this update
    Samsung open source
    @evdenis
    @yarpiin
    @Da-BOSS
    @flar2



    Source code:
    github
    5
    NOTE: I am not responsible for bricked devices, loss of data, etc. Flash it with your OWN RISKS and ALWAYS DO A FULL BACKUP first



    Changelog and Download (NO mirror please):

    *** TWRP 3.3.1.0 is recommended


    20211130 - v2.15a
    - patched with latest FUJ2 sources
    - some more tweaks
    - IMPORTANT: please set the io scheduler to noop (by default) as to increase the ext4 performance


    Downloads (mediafire) *make sure you get the right version for your rom (you can check your rom version by tapping on the dialer, and type *#1234# and read the AP shown):
    FUF5
    BM-Kernel-v2.15a-FUF5-magisk_patched.zip (patched with Magisk 23.0)
    boot.img (no root)

    FUH1
    BM-Kernel-v2.15a-FUH1-magisk_patched.zip (patched with Magisk 23.0)
    boot.img (no root)

    FUJ2
    BM-Kernel-v2.15a-FUJ2-magisk_patched.zip (patched with Magisk 23.0)
    boot.img (no root)









    20211121 - v2.14b2-FIXED
    - FIXED no sound ocasionally after reboot (tested for more than 10 reboots)
    - added PELT
    - undervolt including memory/bus, etc
    - gpu oc to 598 again
    - many other performance and battery saving tweaks, as well as other that I could not remember
    - swithed back to 250 HZ due to the no sound bug
    - IMPORTANT: please set the io scheduler to noop as to increase the ext4 performance


    Downloads (mediafire) *make sure you get the right version for your rom (you can check your rom version by tapping on the dialer, and type *#1234# and read the AP shown):
    FUF5
    BM-Kernel-v2.14b2-FIXED-FUF5-magisk_patched.zip (patched with Magisk 23.0)
    boot.img (no root)

    FUH1
    BM-Kernel-v2.14b2-FIXED-FUH1-magisk_patched.zip (patched with Magisk 23.0)
    boot.img (no root)

    FUJ2
    BM-Kernel-v2.14b2-FIXED-FUJ2-magisk_patched.zip (patched with Magisk 23.0)
    boot.img (no root)









    Previous releases:


    20211120 - v2.14b2
    - REMOVED due to an old minor bug was re-introdecued which occasionally produce no sound after a reboot
    - pls download the v2.14b2-FIXED above







    20211024 - v2.12
    - for FUF5/FUH1 (NOTE: 2 different versions)
    - updated to latest samsung FUH1 sources
    - fixes for slow ext4 performance due to bugs introduced by ext4 and kernel updates
    - IMPORTANT: please set the io scheduler to noop as to increase the ext4 performance


    Downloads (mediafire) *make sure you get the right version for your rom (you can check your rom version by tapping on the dialer, and type *#1234# and read the AP shown):
    FUF5
    BM-Kernel-v2.12-FUF5-magisk_patched.zip (patched with Magisk 23.0)
    boot.img (no root)

    FUH1
    BM-Kernel-v2.12-FUH1-magisk_patched.zip (patched with Magisk 23.0)
    boot.img (no root)







    20210920 - v2.11c6
    - for FUF5/FUH1 (NOTE: 2 different versions)
    - updated to latest ext4 and f2fs
    - full f2fs support (cache and data partitions tested, system not yet tested) ** MAKE SURE you know how to go f2fs first
    - linux upstream to 4.9.280
    - some other tweaks and patches


    Downloads (mediafire) *make sure you get the right version for your rom (you can check your rom version by tapping on the dialer, and type *#1234# and read the AP shown):
    FUF5
    BM-Kernel-v2.11c6-FUF5-magisk_patched.zip (patched with Magisk 23.0)
    boot.img (no root)

    FUH1
    BM-Kernel-v2.11c6-FUH1-magisk_patched.zip (patched with Magisk 23.0)
    boot.img (no root)








    20210818 - v2.10
    - revised from the beginning with updates to FUF5
    - cpu oc/uv
    - gpu overclock/under voltage removed (awaiting fixes)
    - some changes reverted
    - Wake Gestures and Boeffla wakelocks included
    - bring back the performance from initial release (up to 23% or more with multi cores, and nearly 3x memory performance when compared with v2.04) ** thanks for reporting this issue



    Downloads (mediafire):
    BM-Kernel-v2.10-magisk_patched.zip (patched with Magisk 23.0)
    boot.img (no root)







    Known Issues:

    20210730:

    (I) for version up to v2.05, the following features do not work as expected due to my mistakes

    - Wake Gestures including double tap to wake (dt2w), swipe to wake (s2w), etc
    - Boeffla wakelocks
    - These problems will be fixed in the next version soon
    .
    FIXED. Please accept my sincere apology

    (II) in v2.05 default gpu voltage may incorrectly show the modified values as default values in kernel manager

    (III) since v2.04m the performance is not as good as v2.03 due to the introduction of some kernel changes





    20210730 - v2.05a
    - Wake Gestures and Boeffla wakelocks problems fixed
    - no other changes, bugs fixing release of v2.05







    20210729 - v2.05
    - updated with Samsung FUF5 sources just released
    - no other changes
    - REMOVED, superseded by v2.05a







    20210726 - v2.04m
    - compatible with FUF5 (** may have problems if you use lockscreen or samsung account with possible fix here. ALWAYS do a full backup first)
    - overclocked: cpu little to 2002000Mhz, gpu to 598000Mhz
    - undervoltaged: cpu/memory
    - gpu undervoltage support awaiting a fix
    - linux upstreamed to 4.9.250
    - cherry picked some kernel tweaks
    - for undervolting the gpu, you may go and read my settings here awaiting a fix






    More Previous releases:


    20210628 - v2.03
    - added "magisk detected" BASIC fix to prevent apps trying to detect if magisk is installed (only some of the detections are prevented)
    - you can see the difference by installing an app from google play store called "Дія" issued by Ministry of Digital Transformation of Ukraine

    before applying fix
    after fix applied


    - for more info, please read:
    https://darvincitech.wordpress.com/2019/11/04/detecting-magisk-hide/
    - for a comprehensive solution (NOT TO BE SUPPORTED/DISCUSSED HERE):
    https://forum.xda-developers.com/t/magisk-detected-on-bankapp-solved.4258245/
    IMHO, if there's nothing bothering you, you can ignore this comprehensive solution atm. but of coz it's up to you









    20210621 - v2.02 (init release)
    *** Special announcement for Dr.Ketan ROM Q16 - 20210623 ***
    it seems there are some compatibility issues with Dr.Ketan ROM Q16 and this kernel, due to the fact that Q16 is based on N960FXXU8FUE1 while this kernel is N960FXXS8FUE5. As a result you may not be able to login to Samsung Account, or have cts profile/safetynet issue. So please MAKE A FULL BACKUP before proceed.


    - updated with N960FXXS8FUE5 sources
    - tested with stock rom UE5, Dr Ketan Q16 with some patches
    - working properly with DevBase 7.4 and Alexis ROM 2.8 from users feedbacks
    *** make sure you have flashed N960FXXS8FUE5 AP, BL, modem etc



    .
    3
    20210920 - v2.11c6 released
    for fuf5 and fuh1 respectively
    3
    Now I migrated bm v2.02m + Alexis 2.8 combination. All seems decent for now. Still boeffla and double tap sections are missing. But it's okay.
    Here is the devchecks ram performance attachment. (on v2.02)

    I am going to perform antutu and geekbench and post here.
    u mean 2.04m?

    I am on v2.05

    Ram performance is decreased, confirmed with doing devcheck comparison and antutu bench.

    tap to wake and sleep options are gone.
    boeffla options are gone.

    Accordig to Devcheck,

    Cmemcopy: around 5000 Mb/s
    Cmemset: aroud 7500 Mb/s

    on R154 these were 10000 MB/s and 15000 Mb/s respectively.

    Cpu an GPU performance are good.

    I am on Alexis 2.9 Note 9 SM N960F


    And also the voltage table that given by dev is passed two full antutu bench. No crashes.
    i have did some tests today and yes, 2.02 is the fastest one, it was the original one without any "enhancements" in other aspects like cpu/gpu overclocking. it is not unusual that these enchancements can be beaten by the one without in terms of performance. it all depends on the usage, and more importantly everthing comes with a price. so you may find it at stock max speed outperforms an overclocked cpu due to the heat generated (which trigger the mechanism to lower the cpu freq as to cool it down). eg a 10 seconds task running with 2000Mhz may be better than 3 seconds with 2400mHz plus 7 seconds with 1700Mhz. you see what i mean? of coz, once again, it depends on the usage and the way of using it like benchmarking or daily use

    anyway, thanks for your feedbacks, as well as others. without you guys' feedback i couldnt discover the bugs myself

    also, i may consider to make an extreme version, which will be rebased on 2.02 with FUF5 but without any unneccessary changes for those who focus more on the speed due to different usage patterns if there are demands for it. but in general, 2.02 is still working fine with FUF5 except samsung account login issues for some users i believe

    on the other hand, i will continue to cherry pick some useful changes to optimize it in general for the main stream version

    thanks
    3
    EDIT 20210804
    a more aggressive gpu voltage settings is posted here awaiting a fix



    BM-Kernel-v2.04m released

    20210726 - v2.04m
    - compatible with FUF5 (** may have problems if you use lockscreen or samsung account with possible fix here. ALWAYS do a full backup first)
    - overclocked: cpu little to 2002000Mhz, gpu to 598000Mhz
    - undervoltaged: cpu/memory
    - support gpu under voltage
    - linux upstreamed to 4.9.250
    - cherry picked some kernel tweaks
    - for undervolting the gpu, you may refer to my initial safe settings below and adjust them by yourself. there are still rooms to undervolt, but it is suggested you do it bit by bit, and one by one and test the new voltage before next