JIT Optimization - Vibrant General

Is all the 2.2 roms for vibrant JIT Optimization enabled?
I heard that JIT would make our Vibrant more fast....

seems not, jit in 2.2 only optimized for some cpus, the cpu vibrant used is been optimized in android 2.3, same as nexus s

2.2 has jit. jit typically improves performance on all phones running it, but jit's improvements are dependent on what app you are running.

the reason jit isn't apparent on our phones is due to pretty much 2 reasons.
1) is due to how samsung built the CPU in our phones.
While it is arm a8 based, there are other things companies add to it to make it more targeted. Samsung designed part of this different than qalcom did.
2) Google's coding
Google implemented jit with a "spcific" generalization for it (i.e, they kinda based it around qalcom cpu's). Since the vibrant had a different implementation of a specific feature that benifited from jit, the jit optimization was rendered "unoptimised" and therefore we have a "slower" jit effect.
In real world practice, jit doesn't help our phones that much, it's more synthetic.

geoffcorey said:
the reason jit isn't apparent on our phones is due to pretty much 2 reasons.
1) is due to how samsung built the CPU in our phones.
While it is arm a8 based, there are other things companies add to it to make it more targeted. Samsung designed part of this different than qalcom did.
2) Google's coding
Google implemented jit with a "spcific" generalization for it (i.e, they kinda based it around qalcom cpu's). Since the vibrant had a different implementation of a specific feature that benifited from jit, the jit optimization was rendered "unoptimised" and therefore we have a "slower" jit effect.
In real world practice, jit doesn't help our phones that much, it's more synthetic.
Click to expand...
Click to collapse
i'm curious where you are getting this info... cause i can't find anything from google saying they optimized jit for the snapdragon.
snapdragon and hummingbird use the same isa, so while the hw implementation is different that shouldn't realistically have much impact on performance.
but that isn't as relevant as the fact that jit is reducing the necessity to interpret (and reinterpret) code which is where a lot of the performance benefits of jit are.

funeralthirst said:
i'm curious where you are getting this info... cause i can't find anything from google saying they optimized jit for the snapdragon.
snapdragon and hummingbird use the same isa, so while the hw implementation is different that shouldn't realistically have much impact on performance.
but that isn't as relevant as the fact that jit is reducing the necessity to interpret (and reinterpret) code which is where a lot of the performance benefits of jit are.
Click to expand...
Click to collapse
iirc humming bird and snapdragon (well qalcom chips for the most part) implement SIMD is different bit sizes.
qalcom uses 128bit while hummingbird uses 64bit. Since google worked with a lot of qalcom chips, i'm assuming the 2.2 jit was optimized more for the higher bit length SIMD than what samsung used. With 2.3, google optimized for larger and smaller SIMD bit lengths.

geoffcorey said:
iirc humming bird and snapdragon (well qalcom chips for the most part) implement SIMD is different bit sizes.
qalcom uses 128bit while hummingbird uses 64bit. Since google worked with a lot of qalcom chips, i'm assuming the 2.2 jit was optimized more for the higher bit length SIMD than what samsung used. With 2.3, google optimized for larger and smaller SIMD bit lengths.
Click to expand...
Click to collapse
yeah, i remember seeing that somewhere with the SIMD bit length. so now, is it something that can be optimized or is it simply a hw limitation/difference?

Yes, Google optimized hit to work with both the Samsung simd and the Qualcomm simd in 2.3. But it 2.2, the Samsung simd optimization isn't there and there really isn't a way to work around it.
Sent from my SGH-T959 using XDA App

geoffcorey said:
Yes, Google optimized hit to work with both the Samsung simd and the Qualcomm simd in 2.3. But it 2.2, the Samsung simd optimization isn't there and there really isn't a way to work around it.
Sent from my SGH-T959 using XDA App
Click to expand...
Click to collapse
seems like it would manifest somewhere, but so far running cm7 i'm getting maybe a little better performance than 2.2 roms. same linpack and quadrant. granted cm7 is far from perfect. more what i'd expect just from progress on the os than an optimization. and what about moto? are the omaps just screwed until google decides that moto is their next nexus manufacturer?

funeralthirst said:
seems like it would manifest somewhere, but so far running cm7 i'm getting maybe a little better performance than 2.2 roms. same linpack and quadrant. granted cm7 is far from perfect. more what i'd expect just from progress on the os than an optimization. and what about moto? are the omaps just screwed until google decides that moto is their next nexus manufacturer?
Click to expand...
Click to collapse
i think the omaps have a wider SIMD bit length than samsung chose, so they saw improvements in the 2.2 jit.
I think the reason CM7 hasn't show much optimization is jit is because it still has a lot of debugging enabled in the kernel level.

funeralthirst said:
seems like it would manifest somewhere, but so far running cm7 i'm getting maybe a little better performance than 2.2 roms. same linpack and quadrant. granted cm7 is far from perfect. more what i'd expect just from progress on the os than an optimization. and what about moto? are the omaps just screwed until google decides that moto is their next nexus manufacturer?
Click to expand...
Click to collapse
CM7 Quadrant CPU score:5800
2.2 Roms Quadrant CPU score:1500
But i think it just skip the H.264 decoding test to achieve the high score(like the HTC devices which have qualcomm cpu)

plane501 said:
CM7 Quadrant CPU score:5800
2.2 Roms Quadrant CPU score:1500
But i think it just skip the H.264 decoding test to achieve the high score(like the HTC devices which have qualcomm cpu)
Click to expand...
Click to collapse
really? my quadrant is about 1500 on cm7 and an average of about 14mflops on linpack. and mflops should directly relate to simd/neon implementation.

plane501 said:
CM7 Quadrant CPU score:5800
2.2 Roms Quadrant CPU score:1500
But i think it just skip the H.264 decoding test to achieve the high score(like the HTC devices which have qualcomm cpu)
Click to expand...
Click to collapse
the number is not important, it's the breakdown of numbers (i.e. what's the number in the i/o portion of that score?).

Related

JP7 at Linpack

Found the following entry at: http://www.greenecomputing.com/apps/linpack/linpack-by-device/ (Samsung Galaxy S - Position 6)
1000.0MHz samsung/GT-I9000/GT-I9000/GT-I9000:2.2/FROYO/XXJP7:user/release-keys
I know thats possible to set the note manually, but maybe JP7 is inofficially out now.
Is there a download available?
See also: http://samsunggalaxysforums.com/showthread.php/1268-you-will-hate-me-for-this-but...
hmmm our galaxy benchmarks seems bit slow compare to desire doesn't it?
Think Froyo with JIT enabled will boost up our galaxy.
JIT is not working in JP1/2/3.
http://androidandme.com/2010/05/news/jit-performance-boost-coming-with-android-2-2/
Why do u think its not working?Look at the scores of Droid 2 which comes with FROYO. It has the same scores as SGS. Looks like the jit is more optimised fro qualcomm CPUs.
Aery said:
JIT is not working in JP1/2/3.
Click to expand...
Click to collapse
In fact, it's disabled in JP1 and JP2, but it is enabled in JP3.
Mikulec said:
Why do u think its not working?Look at the scores of Droid 2 which comes with FROYO. It has the same scores as SGS. Looks like the jit is more optimised fro qualcomm CPUs.
Click to expand...
Click to collapse
I was just thinking the same thing..
Mikulec said:
Why do u think its not working?Look at the scores of Droid 2 which comes with FROYO. It has the same scores as SGS. Looks like the jit is more optimised fro qualcomm CPUs.
Click to expand...
Click to collapse
I can understand it is more optimized for qualcomm's cpus but there is a 100% difference in the score.
Seems a bit odd to me.
Mikulec said:
Why do u think its not working?Look at the scores of Droid 2 which comes with FROYO. It has the same scores as SGS. Looks like the jit is more optimised fro qualcomm CPUs.
Click to expand...
Click to collapse
Sigh. Damn the N1.
More optimized for Qualcomm CPUs??? Isn't the CPU part of both the Samsung Hummingbird and the Snapdragon in essence the same ARM11 Cortex-A8? Yes they have some minor differences but please, nearly 3 times difference????? I'm beginning to think that Linpack is favoring Qualcomm chips!
And something else! How the hell did the Nexus One score 78 MFLOPS ?!?!?!?!?!?!?
Lets get back to the more important thing - what about the JP7, fake or real?
All I can say is that the snapdragon CPU and Hummingbird are built on the same architecture so they should perform quite close to each other.
Only thing that will prevent it from such a thing are drivers. But just wait I think Samsung will show the true power of the device with 2.2 soon.
they all based on coretex a8 more or less, if that what you say.
like Motorolas using TI OMAP 3 dont get high scores, so is galaxy s.
never get 30MFlops.
There is another thread somewhere that mentioned jp7 so yes i think its out in the wild somewhere.
I dont know , but maybe VFP (FPU hardware) functionality enabled in 2.2 snapdragon .
(limpack is FPO intensive).
For example: (in s3c6410 arm v6)
(mod enables VFP)
Average Linpack scores :
Stock: ~2.8 - 3.0
Stock w/ JIT: ~4.5
Stock w/ this mod: ~4.6
Stock w/ Jit & this mod: ~7.5 - 7.7
http://forum.sdx-developers.com/android-2-1-development/arm11-optimized-libdvm-so-3587/
edit: "(limpack is FPO (floating point operations) intensive)" instead "(limpack is FPU intensive)"
I'm hoping Samsung has put a performance-leach on the test versions because they want to blow peoples minds once they release it properly.
It's a bit of a stretch though...
pepitodequetequejas said:
(limpack is FPU intensive).
Click to expand...
Click to collapse
If true, this makes linpack a very very poor benchmark for phone speed... Nothing really uses the FPU on a phone besides for graphics, and that is all done by the graphics chipset and not the CPU anyway.
RyanZA said:
If true, this makes linpack a very very poor benchmark for phone speed... Nothing really uses the FPU on a phone besides for graphics, and that is all done by the graphics chipset and not the CPU anyway.
Click to expand...
Click to collapse
Yes , my slower (800Mhz armv6 wm) i8000 can easily beat my SGS in
FPO per second with chainfire moded libraries ( enables VFP ).
http://en.wikipedia.org/wiki/LINPACK
Pardon my language, but the benchmarks made me cry WTF is up with Samsung. but then Linpack may have a multiplier x2 if it sees Motorola as the brand name or something. LOL
After All why do we care about Linpack score?
OrionBG said:
After All why do we care about Linpack score?
Click to expand...
Click to collapse
Because the kind of geeks who read a forum like this our obsessed with benchmarks and anything they can point to to say they've got the best geek-toy on the planet currently!
MomijiTMO said:
Sigh. Damn the N1.
Click to expand...
Click to collapse
Yeah, damn the N1. LOL. Seriously, I have one, and it's such a love/hate relationship:
Perfect form factor/size/weight (well, wouldn't mind a 4" screen).
Great button layout.
Quality build.
Gets the latest greatest Google sh*t first.
Horrible touchscreen - almost impossible for me to type anything on it.
Horrible red bias to the screen/display.
Horrible pink dot in pictures.
Unusable in sunlight.
So close to the perfect phone, but not quite.
Same can be said for our SGS, though. Hardware pretty damned sweet. Screen accurate and beautiful and useable in sunlight, weight perfect, size perfect, works in sunlight. Of course, out of the box it's almost unusable because of the lag! At least the SGS can be fixed with software for the most part. The N1's flaws are hardware and permanent. I'm not even sure HTC attempted to fix any of them in later builds of the phone.

Hummingbird

http://www.gsmarena.com/samsung_i8700_omnia_7_joins_the_wp7_game_with_some_big_guns-news-1991.php
This may be a mistake in the article, but if it's true then it may mean that Samsung realized its' Hummingbird processor, although great looking on paper it's not as good as Snapdragon in everyday use (like the issue with 128bit registers allowing Snapdragons to gain much more performance boost on 2.2 than Hummingbird is able to).
Maybe. We can only speculate... But Its a different phone, different OS, different target audience, maybe snapdragon is better suited to that?
Correct me if im wrong.. But if i remember well.. Microsoft said few months ago that all windows phones will be based on same hw specs.. means all gonna have snapdragon!
There are higher throughput SIMD FP units in Qualcomm's CPUs, which mean they score higher in Linpack and the CPU segment of Quadrant, but it's a performance gain that doesn't translate to smoother day to day usage.
Samsung are using the older 65nm snapdragon processor. It's not better than their Hummingbird.
morvaeldd said:
http://www.gsmarena.com/samsung_i8700_omnia_7_joins_the_wp7_game_with_some_big_guns-news-1991.php
This may be a mistake in the article, but if it's true then it may mean that Samsung realized its' Hummingbird processor, although great looking on paper it's not as good as Snapdragon in everyday use (like the issue with 128bit registers allowing Snapdragons to gain much more performance boost on 2.2 than Hummingbird is able to).
Click to expand...
Click to collapse
Samsung aren't stupid, and I'm sure they are well aware of what their processor is capable of.. Remember, our JIT scores have been based entirely on pre-release versions of Froyo thus far.
And everyone is recycling the same information about the registers. That article was based on an assumption though.

Is HummingBird Really Slower than Snapdragon Gen 2? [Independent of JIT]

I know this topic has been debates over time but I noticed that most people attributed the differences in performance is caused by firmware difference (2.1 vs. 2.2).
Today there's an article release about G2 overlock to 1.42 Ghz. Along with the article I noticed "Native Benchmark" using SetCPU which doesn't uses JIT.
Lower is Better.
G2 Result:
{
"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"
}
Now My Vibrant at 1.2 Ghz:
C: 702.89
Neon: 283.15
The difference between the two phone is so great that I doubt it is due to the 200 MHz difference alone.
As a comparison, my score at regular 1 GHz is:
C: 839.21
Neon: 334.51
There is about 130 ms decrease for 200 Mhz overclock, which is Vibrant is at 1.4 Ghz would put the two CPU really close to each other but with G2 having a slight edge. Remember this test is suppose to be JIT independent running Native Codes. But since the vibrant can only be stable overclocked to 1.3 Ghz (what is available anyways), the newer generation of Snapdragon may just be more efficient than Hummingbird, despite us the galaxy owner believes otherwise.
Another thing to keep in mind though, is that Snapdragon are supposedly to have an edge in Neon instruction Set, so I didn't look into that score too much.
It appears to be true.
It appears Hummingbird is not only slower than the new Generation Scorpions, it also appears the Hummingbird is unable to fully capture the CPU performance gain of the Dalvik JIT compiler in Froyo 2.2
http://www.youtube.com/watch?v=yAZYSVr2Bhc
Dunno Something Is Not Right About This 2.2
The Thing That Really Bugs Me Is 2.2 is Suppose To Allow The Full Functionality Of Our 512MB of Ram..But It Doesn't
Erickomen27 said:
Dunno Something Is Not Right About This 2.2
The Thing That Really Bugs Me Is 2.2 is Suppose To Allow The Full Functionality Of Our 512MB of Ram..But It Doesn't
Click to expand...
Click to collapse
It's not 2.2, its Samsung.
SamsungVibrant said:
It's not 2.2, its Samsung.
Click to expand...
Click to collapse
I agree, they should use ext 4 on their phones.
I don't see why they would stick to their old RFS.
SamsungVibrant said:
It appears Hummingbird is not only slower than the new Generation Scorpions, it also appears the Hummingbird is unable to fully capture the CPU performance gain of the Dalvik JIT compiler in Froyo 2.2
http://www.youtube.com/watch?v=yAZYSVr2Bhc
Click to expand...
Click to collapse
I'm sorry, but could you explain what your youtube link has to do with the topic? I'm curious, as I wasn't any wiser on the question at hand when I watched it.
NEON is architecture extension for the ARM Cortex™-A series processors*
Is Snapdragon an ARM Cortex™-A series processor? NO!
Remember SSE instruction set in Intel, and the war AMD vs Intel?
Welcome back, LOL
*The source for NEON: http://www.arm.com/products/processors/technologies/neon.php
Probably is, but does it really matter?
Sent from my SGS Vibrant.
Scorpion/Snapdragon have faster FPU performance due to a 128 bit SIMD FPU datapath compared to Cortex-A8's 64 bit implementation. Both FPUs process the same SIMD-style instructions, the Scorpion/snapdragon just happens to be able to do twice as much.
http://www.insidedsp.com/Articles/t...ualcomm-Reveals-Details-on-Scorpion-Core.aspx
2.2 isnt going to magically give the galaxy S similar scorpion/snapdragon high scores
just look at droidX and other Cortex-A8 phones that already have official 2.2 ROMS they avr 15-20 linpack scores
This doesn't make the hummingbird a bad CPU at all LOL its stupid benchmarks IMHO not going to show in realword use...maybe when the OS matures and becomes more complex but not now..and even by then we will have dualcore CPU's...its a gimmick for HTC to have the "Fastest CPU"
IMO in real world use they are pretty much on par but then when you look at GPU performance its quit obvious the galaxy S pulls ahead thanks to the 90mts PowerVR SGX540
demo23019 said:
Scorpion/Snapdragon have faster FPU performance due to a 128 bit SIMD FPU datapath compared to Cortex-A8's 64 bit implementation. Both FPUs process the same SIMD-style instructions, the Scorpion/snapdragon just happens to be able to do twice as much.
http://www.insidedsp.com/Articles/t...ualcomm-Reveals-Details-on-Scorpion-Core.aspx
2.2 isnt going to magically give the galaxy S similar scorpion/snapdragon high scores
just look at droidX and other Cortex-A8 phones that already have official 2.2 ROMS they avr 15-20 linpack scores
This doesn't make the hummingbird a bad CPU at all LOL its stupid benchmarks IMHO not going to show in realword use...maybe when the OS matures and becomes more complex but not now..and even by then we will have dualcore CPU's...its a gimmick for HTC to have the "Fastest CPU"
IMO in real world use they are pretty much on par but then when you look at GPU performance its quit obvious the galaxy S pulls ahead thanks to the 90mts PowerVR SGX540
Click to expand...
Click to collapse
Once again quoting ARM HQ website:
NEON technology is cleanly architected and works seamlessly with its own independent pipeline and register file.
NEON technology is a 128 bit SIMD (Single Instruction, Multiple Data) architecture extension for the ARM Cortex™-A series processors, designed to provide flexible and powerful acceleration for consumer multimedia applications, delivering a significantly enhanced user experience. It has 32 registers, 64-bits wide (dual view as 16 registers, 128-bits wide.
Click to expand...
Click to collapse
Scorpion is not ARM Cortex™-A series processor
Fuskand said:
I'm sorry, but could you explain what your youtube link has to do with the topic? I'm curious, as I wasn't any wiser on the question at hand when I watched it.
Click to expand...
Click to collapse
I provided the link, because the first part of the link talks about the JIT compiler which increases CPU performance. I put that there in-case someone has never heard of this before. Thus, when I mentioned the Hummingbird can not take full advantage of the JIT compiler, someone would know what I'm talking about.
demo23019 said:
Scorpion/Snapdragon have faster FPU performance due to a 128 bit SIMD FPU datapath compared to Cortex-A8's 64 bit implementation. Both FPUs process the same SIMD-style instructions, the Scorpion/snapdragon just happens to be able to do twice as much.
http://www.insidedsp.com/Articles/t...ualcomm-Reveals-Details-on-Scorpion-Core.aspx
2.2 isnt going to magically give the galaxy S similar scorpion/snapdragon high scores
just look at droidX and other Cortex-A8 phones that already have official 2.2 ROMS they avr 15-20 linpack scores
This doesn't make the hummingbird a bad CPU at all LOL its stupid benchmarks IMHO not going to show in realword use...maybe when the OS matures and becomes more complex but not now..and even by then we will have dualcore CPU's...its a gimmick for HTC to have the "Fastest CPU"
IMO in real world use they are pretty much on par but then when you look at GPU performance its quit obvious the galaxy S pulls ahead thanks to the 90mts PowerVR SGX540
Click to expand...
Click to collapse
Search the net, people have made real world Videos of galaxy s running 2.2, compared to G2. The G2 is faster in the real world on things like launching aps.
lqaddict said:
Once again quoting ARM HQ website:
Scorpion is not ARM Cortex™-A series processor
Click to expand...
Click to collapse
LOL i never said the scorpion is ARM Cortex™-A
try reading my post again
SamsungVibrant said:
Search the net, people have made real world Videos of galaxy s running 2.2, compared to G2. The G2 is faster in the real world on things like launching aps.
Click to expand...
Click to collapse
LOl if it is faster it might be by the most 1-2 sec if its lucky
sorry its going to take allot more than that to impress me..again its a phone now a highend PC
SamsungVibrant said:
Search the net, people have made real world Videos of galaxy s running 2.2, compared to G2. The G2 is faster in the real world on things like launching aps.
Click to expand...
Click to collapse
Due to different filesystem implementation largely, once there is a workable hack to convert the entire filesystem on the Galaxy S to a real filesystem you can make the comparison of the things like launching apps.
Demo, I didn't mean to come off as a **** I was just pointing out the flaw in the OP benchmark - NEON instruction set execution is flawed. G2 processor is ARMv7 which is the base of Cortex-A8, Cortex-A8 adds the instructions specifically targeted for application, like multimedia, and that's where NEON comes into place.
lqaddict said:
Due to different filesystem implementation largely, once there is a workable hack to convert the entire filesystem on the Galaxy S to a real filesystem you can make the comparison of the things like launching apps.
Click to expand...
Click to collapse
Agreed. +10 char
lqaddict said:
Demo, I didn't mean to come off as a **** I was just pointing out the flaw in the OP benchmark - NEON instruction set execution is flawed. G2 processor is ARMv7 which is the base of Cortex-A8, Cortex-A8 adds the instructions specifically targeted for application, like multimedia, and that's where NEON comes into place.
Click to expand...
Click to collapse
No problem I didn't really take it
Also noticed i overlooks allot of things in OP...blame the ADD
What difference does it make? In real world use the difference is negligible. And in three months our phones will be mid-tier anyway. At least we don't have hinges that will fall apart in two months.
how is the hummingbird not able to fully take advantage of JIT?
Well there is a fix for our phones now. And from what I can tell there no way the g2 can open apps faster than my vibrant with the z4mod. Its smocking fast.by far the fastest I've ever seen this phone. No delays whatsoever. Can't wait till I get froyo with ocuv and this will be unreal. I feel like this phone us a high end pc running android or something. When I say instant it's instant lol.
Kubernetes said:
What difference does it make? In real world use the difference is negligible. And in three months our phones will be mid-tier anyway. At least we don't have hinges that will fall apart in two months.
Click to expand...
Click to collapse
Exactly.
People seem to forget that the SGS line is like 6 months old now, we should be glad they're still doing as well as they are.
Then theres the fact that there aren't many other phones that come with 16gb internal. To me, having 16GB and being able to upgrade to 48 [minus the 2GB that Samsung steals] total is worth way more than starting with 4GB [1.5GB usable] and upgrading to a max of 36 [minus what HTC steals from internal].
But, if you don't like your phone, SELL IT while it's still worth something!

Does 2.2 fully support dual core?

Obviously is does to an extent, but I thought Gingerbread/Honeycomb are the first official OS's to support it?
Anyone know the details around this? When the Atrix gets Gingerbread, will there be processing improvements?
2.3 does... which makes you wonder wtf moto was thinking.
I use SeePU as a CPU monitor and when I swipe the screen and other basic things, the CPU maxes briefly. No lag at all for the most part. However, I'm wondering if Froyo isn't completely optimized for the dual-cores.
As a funny note, I'm wondering if we're all going to see some nice improvements once we get Gingerbread as we did with the 2.1 to 2.2 improvements.
kenyu73 said:
Obviously is does to an extent, but I thought Gingerbread/Honeycomb are the first official OS's to support it?
Anyone know the details around this? When the Atrix gets Gingerbread, will there be processing improvements?
Click to expand...
Click to collapse
Don't believe Froyo was made with dual core in mind. Biggest thing is that apps haven't been optimized for dualcore yet.
kenyu73 said:
Obviously is does to an extent, but I thought Gingerbread/Honeycomb are the first official OS's to support it?
Anyone know the details around this? When the Atrix gets Gingerbread, will there be processing improvements?
Click to expand...
Click to collapse
It seems there is already multi core support on the OS level, but probably not a strong support on the API level. Read, for example, androidnexus [dot] com/android-news/nvidia-tegra-2-review-and-multi-core-support-in-android . That means that the OS will already distribute threads between cores, which for example should eliminate any lag that I sometimes experience in single core when I am playing a game and Android is synching mail in the background. *edit* And generally improve performance while multitasking. *end edit*
I think only Android 3.x will really take advantage of multi core processors (they explicitly stated that as a feature for Honeycomb); I doubt there would be a big difference between Froyo and Gingerbread as far as performance is concerned.
how long do u think Moto will let us update to 2.3? maybe 1 year?
bl0wf1sh said:
It seems there is already multi core support on the OS level, but probably not a strong support on the API level. Read, for example, androidnexus [dot] com/android-news/nvidia-tegra-2-review-and-multi-core-support-in-android . That means that the OS will already distribute threads between cores, which for example should eliminate any lag that I sometimes experience in single core when I am playing a game and Android is synching mail in the background. *edit* And generally improve performance while multitasking. *end edit*
I think only Android 3.x will really take advantage of multi core processors (they explicitly stated that as a feature for Honeycomb); I doubt there would be a big difference between Froyo and Gingerbread as far as performance is concerned.
Click to expand...
Click to collapse
Thanks for the information! However, I believe Gingerbread 2.3 was "canned" and reversioned to 2.4 which includes dual-core support. I've read this in more then a few tech blogs recently.

Fully working JIT

I know this has been discussed but will samsung or google ever do this? I believe that it isn't a hardware limitation because up until 2.2 the hummingbird was faster and all native benchmarks show the same. Who needs another phone if they get this working our phone would perform as well as a tegra 2 imho.
Sent from my SCH-I500 using XDA App
I lol'ed at this one
JIT isn't that magical...is it?
Sent from my Fascinate with CM7 Gingerbread
No its not but with some overclocking and the great devs here I'm sure it would pick up considerably. Sgs 2linpacks at 47 or so stock. Second gen snapdragons are pretty fast. Also I don't think outside of emulators there will be anything that will really push the hummingbirds gpu for a while yet.
Sent from my SCH-I500 using XDA App
You can't compare us to snapdragons. Linpack doesn t like hummingbirds. Your logic is that's because they have a high number we are worse? Well buddy does your phone seem 1/8 times slower then other phones? Mine doesn't.
Sent from my SCH-I500 using Tapatalk
No it doesn't but it's just a shame that it isn't optimized for our phones. All cpu benchmarks tell the same story when it comes to cpu performance. The reason we don't score over 3000 in quadrant or as high as other phones in productivity in smartbench it's because of the jit. Take.everyone back to 2.1 and see who's on top. My hope is with the nexus phone having a hummingbird sooner or later this will happen.
Sent from my SCH-I500 using XDA App
I dont give a Jit
Sent from my SCH-I500 using XDA App
stephenj37826 said:
No it doesn't but it's just a shame that it isn't optimized for our phones. All cpu benchmarks tell the same story when it comes to cpu performance. The reason we don't score over 3000 in quadrant or as high as other phones in productivity in smartbench it's because of the jit. Take.everyone back to 2.1 and see who's on top. My hope is with the nexus phone having a hummingbird sooner or later this will happen.
Sent from my SCH-I500 using XDA App
Click to expand...
Click to collapse
The Nexus S has JIT with Gingerbread doesn't it? I thought JIT scored higher on snapdragons because it was first developed on the Nexus One.
Sent from my Fascinate with CM7 Gingerbread
ya seriously, like the hummingbird processes over 90 million triangles a second, thats freakin ridiculous, and i feel like the phone is underperforming, especially when other phones can do only around 22 million a second.. like wtf yo
This OP is a moron. Has no idea what the [email protected]$! he is talking about. We have JIT, we have a hummingbird cpu, we have a fast freaking phone. A number means ****. Can we get a mod close this?
You're a moron if you think we have a compiler built for the hummingbird processor. I guess you well never buy another phone seeing how this one is as fast as you'll ever need. Righhhhhhttttt LoL. It would help everything including battery life. The more time the cpu stays at higher clock speeds the more battery it uses. If you don't have something constructive to say just shut up. Also if you don't like the topic why the hell did you even click on it? And he calls me a moron lmao.
Sent from my SCH-I500 using XDA App
I <3 flaming. Can't wait till ashasaur gets his computer back up.
Sent from my SCH-I500 using XDA App
TheSonicEmerald said:
The Nexus S has JIT with Gingerbread doesn't it? I thought JIT scored higher on snapdragons because it was first developed on the Nexus One.
Sent from my Fascinate with CM7 Gingerbread
Click to expand...
Click to collapse
No. Linpack is a pipeline test. This is where Snapdragons excel, because, they have a deeper, 128 bit pipeline, versus the 64 bit pipeline of all the other Cortex A8 CPUs. The Hummingbird excels in "integer" performance, and the Snapdragon excels in "float point operations." In normal use, the difference in performance between a Hummingbird and 2nd gen Snapdragon is nonexistent. You really only notice under specific circumstances, such as benchmarks. And the OMAP3 is just slow and doesn't excel in anything.
GoogleAndroid said:
No. Linpack is a pipeline test. This is where Snapdragons excel, because, they have a deeper, 128 bit pipeline, versus the 64 bit pipeline of all the other Cortex A8 CPUs. The Hummingbird excels in "integer" performance, and the Snapdragon excels in "float point operations." In normal use, the difference in performance between a Hummingbird and 2nd gen Snapdragon is nonexistent. You really only notice under specific circumstances, such as benchmarks. And the OMAP3 is just slow and doesn't excel in anything.
Click to expand...
Click to collapse
Ah ok, thanks. I learn something everyday
Sent from my Fascinate with CM7 Gingerbread
GoogleAndroid said:
No. Linpack is a pipeline test. This is where Snapdragons excel, because, they have a deeper, 128 bit pipeline, versus the 64 bit pipeline of all the other Cortex A8 CPUs. The Hummingbird excels in "integer" performance, and the Snapdragon excels in "float point operations." In normal use, the difference in performance between a Hummingbird and 2nd gen Snapdragon is nonexistent. You really only notice under specific circumstances, such as benchmarks. And the OMAP3 is just slow and doesn't excel in anything.
Click to expand...
Click to collapse
Thanks for the useful information.
Sent from my SCH-I500 using XDA App
nevermind.
Sent from my brain on channel 64!
Benchmarks mean nothing between even the same model of device. They're only good for measuring changes with software or settings.
JIT either works or it doesn't. There is no "fully implemented" for JIT in Dalvik. It's either on or off.
Sent from my SCH-I500 using Tapatalk
stephenj37826 said:
Thanks for the useful information.
Sent from my SCH-I500 using XDA App
Click to expand...
Click to collapse
You're welcome. I was always curious as to why the Snapdragons scored so highly in Linpack, and so I looked into it, and that's what I found out.
found this here http://phandroid.com/2010/05/26/going-deeper-with-android-2-2s-jit-compiler/
Russell Troywest 1 comment collapsed Collapse Expand
@GODCYPH
Yes, you're right, the JIT would need to be coded to know the 'tricks' are there. I have absolutely no idea how the android JIT is designed (although if it's part of the open source package I might try and find some time to go find out). I suspect it doesn't do anything too clever, but it does need to know what processor it is compiling for to do its job so I guess the information is available to it...
Again, I'm not a JIT designer, I have enough knowledge of how they work to be dangerous and not much more
ALSO THIS
The whole idea of using a VM was that code could be run in virtually any instruction set (ie x86) without the need for recompiling. In essence, it compiles at runtime, basically the VM is an Interpreter. If a JIT is capable of utilizing a specific instruction set's "tricks", does that mean the JIT must be optimized for the processor it is running on? Wouldn't that mean a different JIT for every different processor/instruction set that would be made available?
Wouldn't a our processor be classified as different? Seeing as the nexus one is snapdragon.
Unless you're doing extreme HPC implementations where you absolutely need to squeeze every single bit of performance out of every possible configuration, you're not going to be coding, or even compiling for specific processors. You code for architectures and instruction sets.
Hummingbird and Snapdragon are both Arm Cortex v8 processors. When coding or compiling, you code for that.
The JVM, and a step further with the JIT take partially compiled code that is architecture agnostic and translate it to architecture-specific machine code at execution time. It's a step between scripting (JavaScript, PHP, perl, etc) and native compiled code (C, C++, etc).

Categories

Resources