I found a new jit for our xt720!
linpack score 12.449 at 900 MHz!
Very fast !
Very simple!
First download all in one optimizer
Two download this mediafire.com/?djm9ggkil4d168m
Tree copy the folder app2sd from all in one
Four take lib an bin from jit enabler and put them in app2sd\jit
Five launch all in one and install jit
The end !
So, where do these come from if you don't mind me asking? I've been poking around the optimizer script and couldn't trace the JIT back to its source.
I believe the JIT in the optimizer script originates here
Ok, it installed over the previously installed optimizer version and the phone came up fine.
The only changed files from v9 of the all-in-one optimizer are /system/lib/libdvm.so and /system/bin/dexopt (md5sums identical for the other files).
I believe the JIT in the optimizer script originates here
Click to expand...
Click to collapse
I guess my question is that just looking at these files and the files included in the optimizer how do we know which one is newer? I'd found that site previously, when studying the all-in-one optimizer script, but I couldn't match md5sums from the all-in-one to either FrozenEclair_8.zip or FrozenEclair_9_beta1.zip (these don't match either).
Edit: Forgot to clear dalvik-cache--I don't think the all-in-one does that. After deleting the dalvik cache files and rebooting I see 13.6 MFLOPS @1GHz (was 9.8 before!). Awesome!
PS: How do you get 900MHz? I can only select multiples of 200MHz (in Milestone Overclock).
Mind posting the original discussion or source link ? Would like to know more about this update. Much appreciated.
How do you get 900MHz? I can only select multiples of 200MHz (in Milestone Overclock)
Click to expand...
Click to collapse
If you hit the menu button there is an option for custom settings. Set the speed you want & move the slider all the way to the right to apply the custom setting.
There is only one new file came from a jit v2 for x10!!! My phone is fast at 550 MHz !!! I develop nothing i'm just a smart man...
Sent from my Milestone XT720 using XDA App
I work actualy on the hardware acceleration .Our phone is not fully optimised we must have the same score as defy .All idies are Welcome.
Sent from my Milestone XT720 using XDA App
what rom is support for this new jit?i use central europe rom ,can I use this?
Sent from my Milestone XT720 using Tapatalk
Yes good for all 2.1
Sent from my Milestone XT720 using XDA App
xavwanted said:
Yes good for all 2.1
Sent from my Milestone XT720 using XDA App
Click to expand...
Click to collapse
okay..i ve try and it work sir...thank's
original thread for new JIT
http://forum.xda-developers.com/showthread.php?t=885977
i alrealy used jit 9b1 1month ago
i got that from spica's rom
It improves the linpack score...but quadrant remains near enough the same...so I.am left wondering what that means..
is one a better measure of something than the other...or are they are separately great measures of differing things...and what those differing things may be.
Sent from my Milestone XT720 using XDA App
Linpack mostly measures floating point operations which are important for scientific calculations and simulations. I suspect floating point performance isn't really a high priority for a typical phone workload. Linpack did demonstrate to me that the new JIT is superior to what it replaced in some respect.
I do know that my Linpack score didn't change before I cleared the dalvik cache--which makes sense if the improvements require new dex to be generated by dexopt. Unfortunately, I didn't run quadrant before I replaced the JIT (currently score 680 @1GHz in quadrant standard free).
I installed it and ran Linpack aftwards. Seems to have increased from ~10 to ~12.5. Phone seems a bit snappier but definitely not night and day improvement from what I've noted so far.
Thanks for the tip about the update
tq for the info update...
my linpack score now 15++ same score with froyo..
quadrant 879 @1.1ghz...
The score in quadrant don't move because the hardware video decoder is not activate .But you can see a real difference.I need a full rom 2.1 zip for defy for see what is the difference.
Sent from my Milestone XT720 using XDA App
Ah...cool..thanks for the info guys. Yeah I noticed the response was better...but was not sure if that was due to cleaning out the dalvik cache as suggested.
I did notice the phone becoming very laggy of late...especiially for launcher pro home screens loading up ...but after installing this and clearing out the cache it is flying again and a bit faster than before
Sent from my Milestone XT720 using XDA App
at 800MHz
Linpack score: 11.4 MFLOPS
Quadrant Standard score: 610 ...
at 1.2 GHz
Linpack score: 16.8 MFLOPS
Quadrant Standard score: 796
a lot faster. thanks guys.
Related
Just did a linpack scan on my JG1 flashed SGS running Lagfix and got a score of 8 Mflops. Is this is a good / bad score?
What are your scores?
8.2Mflops or so on JM5. I don't think anything other than JIT (in 2.2) is going to increase that; lag fixes certainly won't change it.
Mithent said:
8.2Mflops or so on JM5. I don't think anything other than JIT (in 2.2) is going to increase that; lag fixes certainly won't change it.
Click to expand...
Click to collapse
Sorry but I keep seeing JIT everywhere, anybody care to explain what it stands for and how it all relates to awesomeness (thanks)
fakekullu said:
Sorry but I keep seeing JIT everywhere, anybody care to explain what it stands for and how it all relates to awesomeness (thanks)
Click to expand...
Click to collapse
JIT Just IN Time
Read on..
Android Developers
Android and me
its not in xxjp3 yet ha? or is it?
Also, keep in mind that Linpack is a synthetic benchmark and doesn't accurately reflect real performance. In fact, code like Linpacks will probably receive the biggest gain from JIT (more than real programs).
I'm using the I9000XXJP2 firmware and I think JIT is broken but I've been getting scores of 13.9 mflops with the lag fix installed!
I don't think it is broken but the dalvik files are not compiled to use ARM v7, cortex a8, or neon optimization.
Sent from my SGH-T959 using XDA App
So DK28 is supposedly 2.2.1 but I ran Quandrat with the stock rom and it comes up 873, almost exactly the same as Galaxy S 2.1, leading me to believe that JIT is not in the rom. Correct?
avenger213 said:
So DK28 is supposedly 2.2.1 but I ran Quandrat with the stock rom and it comes up 873, almost exactly the same as Galaxy S 2.1, leading me to believe that JIT is not in the rom. Correct?
Click to expand...
Click to collapse
I may be wrong but quadrant:
1) Isn't the best way to base performance
2) Doesn't really show improvements that JIT provides
Download linpack if you want and your score should be around a 14 or so, compared to the 8.5-9 on 2.1
Quadrant isn't a real life benchmark, and is highly flawed. Check out Quantum's "warp speed edition" ROM for proof.
Sent from my SPH-D700 using XDA App
I got 1205 with stock dk28 but I have noticed others reporting lower scores. Variability in testing with a bad benchmark perhaps?
I've got 1839 lol... For some reason I doubt that's accurate
I did a quadrant test with a stock epic 2.1 and an epic on dk28 and the scores were pretty much the same every time. The major difference was that the Froyo epic ran the cpu benchmarks much faster but hung during the first I/O test. The 2.1 epic ran everything about the same speed and completed the whole test much faster than the froyo epic.
I also noticed this and posted in another thread...
to quote myself
I was getting around 8.3xx in 2.1, and now I'm getting 13.7xx in 2.2.
(I used the 1506bdf2e04b.update-SPH-D700_DI18ToDK28.zip renamed to update.zip method.)
Saw a video the other day showing a nexus 1 scoring 20+ on 1st run and 40+ on 2nd.. My friends Evo (with 2.2) scored @ 38 or so..
Quadrant still shows me well under all of the 2.2+ phones listed.
Click to expand...
Click to collapse
I expected a bit more of an increase..
I too am wondering if the JIT was left out of our Froyo (if that's even possible, I'm still a total nube to andriod stuff).
What exactly is JIT, does it speed the phone up?
Sent from my SPH-D700 using XDA App
Just In Time compiling...
From what I know about .Net (I'm a C# coder), it allows for compilation of the app for the specific CPU during the 1st run.
Someone please correct me if this differes from andriod's JIT...
the epic has fast computation hw between the cpu and gpu, it could be the case that the JIT benefit doesn't show in the benchmark margins.
the device is a fast one, all compared.
I've tried to overclock, lagfix, change roms and kernels, but I didn't see any big difference.
I would like to stay with real FPS benchmarks like GLBenchmark or others not like quadrant.
I've seen many people using ext2 instead of ext4, other say rfs is better, so I'm getting very confused. And also many people around here.
Each one of us has got a personalized SGS. Let's run each one of us GLBenchmark OpenGl 2.0 test without FSAA (The one of egypt) and see the results of each one of us.
Dlownload glbenchmark here: http://www.glbenchmark.com/download.jsp
Please specify model, rom, kernel, launcher, running apps, free mem before doing the test... Like every bit of info you can give, so we could find the best settings!
Thanks to all ! I'll run the test and post in few minutes!
Ok, here is the template 1.0 to use ;P just copy and paste and modify!
OK, got:
2438 Frames (21.6 Fps) with no fsaa.
My settings:
MODEL: European, I9000 SGS 16gb Vodafone
SPEED (GHZ): 1.0
LAUNCHER: Go Launcher
KERNEL: Lastest speed mod.
ROM: Darky's 8.0
LAGFIXES: On, System converted, on fast mount.
PROGRAMS INSTALLED: Very few, just wiped it.
FREE RAM: I forgot!
OTHER INFO: Wifi on, and overclock @ 1.2 makes worse FPS.
Lagfix will have no effect on glbench
Sent from my GT-I9000 using XDA App
Bench marks do not say how responsive or laggy the phone is and unless you are obsessive with numbers are a waste of time .
jje
yes, but games performance is equal to FPS, so more FPS=More optimized system.
Just because that reason i proposed to use glbenchmark, as it is an only graphical test.
along with setup please.
Figured we might as well record benchmark progress as kernels and ROMs get faster. I'll start off.
Linpack -- 56.264 high, 52-55 consistent
Quadrant -- 2090 high, 2000-2050 consistent
Setup:
bcnice's 1.5 OC kernel
NFX's stock deodexed ROM
SetCPU 245/1516 interactive
Dread's GB theme modified
Thanks to all the devs working on this phone. Can't wait to see what else this thing is capable of.
my scores
Running:
Bcnices 1.8 Gingerbread AOSP kernel
Evervolv Alpha Update 3
Deodexed
Quadrant:
Highest: 2968 , 26-2800 consistently
Linpack:
Highest: 60.XXX, 55-58 consistently
Its also important to note which quadrant version you are using as well. Scores vary widely between the paid and free versions.
Jeezimus said:
Its also important to note which quadrant version you are using as well. Scores vary widely between the paid and free versions.
Click to expand...
Click to collapse
This is very true. The test that scored 2968 was run using Quadrant Advanced 1.1.1 Rev 1352
New screenshot is the same system as above but run on the newest version of Quadrant Standard (1.1.7) available.
I get about 2000 on Quadrant at 1.8GHz. How is there such a big difference?
Sent via carrier pigeon.
He's on an aosp rom with no sense framework
Sent from my PG06100 using XDA App
this was on regular quadrant OC'd to 1.8 on stock sense ROM and rooted
Is this any good?
If you have Advanced you can go into the Custom run and disable volumetric shadowing for the hallway. Scores will jump by 300-400. How the hell did you get over 4000?
When we got the stock GB upgrade, I found myself missing my ROOT and of course the BAUXITE Kernel.
Well we got the ROOT back quickly and now Thanks to Mr. Eui Woo Jeong we have overclocking. TEGRAK ULTIMATE overclock on the market website now supports the Sprint Tab w/GB.
Life is good.
What speed are you overclocking to?
DanielNTX said:
What speed are you overclocking to?
Click to expand...
Click to collapse
I'm just cruising through at 1.2 no volt adjustment. Just "ONDEMAND".
No issues....
Did you mean the non ultimate version?
The ultimate version is $ 1.99
Sent from my SPH-P100 using XDA App
The ultimate version is not working for me. It does a checking stability for 300 seconds and never counts down for the Set on Boot option.
What are the best speeds to overclock to? I am over clocking to 1.1 ghz and it keeps locking up and freezing
I guess I can't support the widgets that I would like to without it being too slugish
Sent from my Sprint Galaxy Tab
I've noticed that oc'd past 1.2 my performance drops. It runs laggy and 1.3 benchmark scores were half that of 1.0 UNLESS I plug it into the wall. Is the battery not able to keep up or it it being undervolted?
Also, using this app, any thoughts on undervolting at 1.0 to increase battery? I would imagine undervolting won't fry anything, just maybe lock up, so is ot safe to experiment?
Sent from my SPH-P100 using XDA App
throwback1718 said:
What are the best speeds to overclock to? I am over clocking to 1.1 ghz and it keeps locking up and freezing
I guess I can't support the widgets that I would like to without it being too slugish
Sent from my Sprint Galaxy Tab
Click to expand...
Click to collapse
1.2 seems to be spot on for me.
Sent from my SPH-P100 using XDA App
I will be definitely trying 1.2... The reason I didn't try that before was because I feared it would Surely kill my battery life.
I'll give you guys feedback... I also wanna know how long you guys batt life lasts on 1.2?
Sent from my SPH-P100 using XDA App
Works amazing on my Sprint GTab! Runs at 1.2Ghz without a problem. I only got the free one. I'm stingy like that.
Sent from my SPH-P100 using XDA Premium App
My Tuppence
I've played around a lot with the paid version of tegrak.
Free version works fine at 1200mhz max for me and I got the following AnTuTu results
1000mhz stock (Gingerbread 2.3.3 and Odin root, 32gb micro sd installed too) - score = 2676 = rank 56752
1200mhz - score = 2676 = rank 51544
With paid Tegrak I've managed to tweak up to a max of 1228mhz before it got unstable and rebooted, here are my results.
1220mhz (core voltage increased to 1325mv from 1300mv) - score = 3097 = rank 40166
1224mhz (core 1325) - score = 3130 = rank 39620
1228mhz (core 1325) - score = 2890 = rank 47433. So a drop in performance at which point I gave up testing further.
I'm happy with these results for $1.99.... pretty substantial update in performance. Plus going from an AnTuTu rank of 56752 to 39620 an improvement of 17132 in the rankings I'm happy.