Related
So, heard about this from a few sources, but engadget have a hands on video (of sorts) up, heres the link:
http://www.engadget.com/2010/02/17/myriad-dalvik-turbo-hands-on-android-apps-just-got-fast/
They say its only going to be available to manufacturers who pay for it, boo!
Am I right in saying, though, that if we manage to get our hands on it, it can be cooked into a custom ROM? So its just a matter of waiting for someone to get hold of a copy?
I'm totally psyched about this, it always amazed me how much worse the Hero performs when compared to an iPhone 3G with a much slower processor. Turns out Google was the ones screwing us over, imagine that!
As for your question, yes I believe it would be doable. For example I've been told that the performance gain in this video:
youtube.com/watch?v=vgi4O5ix3lU&feature=player_embedded
on a nexus one was done through implementing a JIT compiler which is a part of that myriad dalvik turbo dealio.
And hey, if the N1 guys can do it, why wouldn't the Hero ones be able to? Everyone knows that the real pros dev for the Hero!
yes, this was what I was looking forward to most at the MWC
Hopefully with the help of skillful devs, we could have it on hero!
asterboter said:
I'm totally psyched about this, it always amazed me how much worse the Hero performs when compared to an iPhone 3G with a much slower processor. Turns out Google was the ones screwing us over, imagine that!
As for your question, yes I believe it would be doable. For example I've been told that the performance gain in this video:
youtube.com/watch?v=vgi4O5ix3lU&feature=player_embedded
on a nexus one was done through implementing a JIT compiler which is a part of that myriad dalvik turbo dealio.
And hey, if the N1 guys can do it, why wouldn't the Hero ones be able to? Everyone knows that the real pros dev for the Hero!
Click to expand...
Click to collapse
In the video they are using the Google JIT as far as i know?:
http://groups.google.com/group/andr...5636f5f532/662b32b98d9b9bba?#662b32b98d9b9bba
http://groups.google.com/group/0xlab-devel/browse_thread/thread/1edef26f4e5b7427
This is different from the commercial Myriad versio (Dalvik Turbo). Google is actively investing in the JIT system:
http://code.google.com/events/io/2010/sessions/jit-compiler-androids-dalvik-vm.html
Yes of course I realize there's a difference, I was merely comparing the implementation of that jit and dalvik turbo (which, I believe, also includes a jit compiler). Though I am no dev so don't take my word for it, but I am hopeful
And even if dalvik turbo can't be implemented, that jit from the video undoubtedly should be possible, which should result in a performance boost, which really is all that we're after, right?
Yeah, we're on the same page for sure.. It just is a matter which technique is available and stable first and ask some cook to implement it into a rom. It would be sweet to run 2.1 with JIT on the hero faster then optimized 1.5 we run now..
Hrrrm.... The iphone doesn't have a slower processor. Less mhz, yes, but different instruction set. It's like comparing the 550mhz in the Droid/Milestone to the 528mhz in the Hero. The Droid one is roughly 1.8times faster, even at less mhz.
And then there is the OS itself. The iphone OS is desigend for just that one device and for exactly those functions. The apps run native, while under google they run in a Java VM environment. That makes compatible even on other devices with other processors.
You simply can't compare the two.
dipje said:
Hrrrm.... The iphone doesn't have a slower processor. Less mhz, yes, but different instruction set. It's like comparing the 550mhz in the Droid/Milestone to the 528mhz in the Hero. The Droid one is roughly 1.8times faster, even at less mhz.
Click to expand...
Click to collapse
Erhhhmmm, the Samsung processor in the iPhone 3G uses a ARM11 core, same as the Qualcomm processor in the Hero, and uses the same instruction set. Whilst both processors are SoCs from different manufacturers you can broadly compare the two processors computing power on a clock-for-clock basis because they share the same processor core.
The iPhone 3GS however, uses an ARM Cortex-A8 core, which is clock-for-clock a fair bit faster than anything based on an ARM11 core. See here for further detail.
Regards,
Dave
foxmeister said:
Erhhhmmm, the Samsung processor in the iPhone 3G uses a ARM11 core
Click to expand...
Click to collapse
Ahh! Thanks. 'Did not know that'. Thought it was a newer ARM set.
But my point still stands, you can't compare the performance of the CPU's because the way apps are compiled and work (and the OS itself) are way to different.
But the iphone 3g still has a (somewhat) dedicated GPU chip in it, right?
dipje said:
But the iphone 3g still has a (somewhat) dedicated GPU chip in it, right?
Click to expand...
Click to collapse
There's a PowerVR MBX-Lite accelerator in the iPhone 3G, which is part of the Samsung SoC (as opposed to a physically separate GPU).
However, similarly, the Qualcomm MSM7200 SoC in the Hero has an Imageon accelerator (formally an ATI/AMD part, but Qualcomm bought the Imageon line).
I've no idea which is supposed to be faster though.
Regards,
Dave
Please, do not forget at these comparisons between iPhone OS and Android,
the iPhone is monotasking.
If you jailbreak your iPhone and run more apps then one iwht the backgrounder app, the speed feeled speed is slower than the Hero speed.
Otherwise also, the 3 months I used my iPhone I found, the it weas getting slower and slower from week to week....
Otherwise also, the 3 months I used my iPhone I found, the it weas getting slower and slower from week to week....[/QUOTE]
+1 to that....
And don't forget minor benefits of the firmware updates....
Well just got upgraded to the SGS II.
Curious if there is anything i should know about the device. I know its beautiful.. and i herd about screen issues but i was holding one and could see anything wrong with the screen...
So Pros, Cons, Quirks, anything you wish you knew off hand?
Depends on what you plan on doing with it ... If you bought for the snazzy voice talk options beware that some roms don't include it and doubletap of the home button to activate it is removed and many roms don't even have voice talk in them .... I got kinda frustrated with that at first ... And just installing the apk wouldnt get it working..... (
with my bluetooth headset ) () to claify that the call button wouldnt activate / open voice talk
Sent from my SGH-T989 using XDA App
freakyliciousfishy said:
Depends on what you plan on doing with it ... If you bought for the snazzy voice talk options beware that some roms don't include it and doubletap of the home button to activate it is removed and many roms don't even have voice talk in them .... I got kinda frustrated with that at first ... And just installing the apk wouldnt get it working..... (
with my bluetooth headset ) () to claify that the call button wouldnt activate / open voice talk
Sent from my SGH-T989 using XDA App
Click to expand...
Click to collapse
not entirely true about voice talk actions. the Samsung one may have been taking out since it sucks anyways. stock android voice commands work better IMO.
I recently switched from the sensation to the Galaxy S2 and im 1000% glad i did, samsung did a amazing job on this device. And TouchWiz is pretty cool and not laggy and slow as sense.
Only con i can even think of is the screen issue with some lines and blotches. My screen personally has the blotches but its really not noticible unless you looking for it in a dark room and with dark lighting but even then its not bothersome at all.
Thanks for the replies. I am excited about this phone. Sucks that it is on back order and will be another week or more till it even ships .
immunityx said:
Only con i can even think of is the screen issue with some lines and blotches. My screen personally has the blotches but its really not noticible unless you looking for it in a dark room and with dark lighting but even then its not bothersome at all.
Click to expand...
Click to collapse
also the actual processor and gpu sucks compared to Exynos used in the real SGS2 variants. I cant even consider TMo's SGS2 a real SGS2. just a little beefier Samsung Hercules.
brian_v3ntura said:
also the actual processor and gpu sucks. I cant even consider TMo's SGS2 a real SGS2. just a little beefier Samsung Hercules.
Click to expand...
Click to collapse
theres nothing wrong with the processor ,my phone rocks and performs the same if not better than any other stock version of SGS2
tigerz0202 said:
theres nothing wrong with the processor ,my phone rocks and performs the same if not better than any other stock version of SGS2
Click to expand...
Click to collapse
nothing wrong? its old hardware. i would rather have the better performing Exynos processor than the watered down Snapdragon TMo SGS2. i dont see why Tmobile will sacrifice the main component that made the SGS2 an SGS2 just to claim that the phone supports up to HSPA+ 42mbps....which we will never see those speeds before the SGS3
brian_v3ntura said:
also the actual processor and gpu sucks compared to Exynos used in the real SGS2 variants. I cant even consider TMo's SGS2 a real SGS2. just a little beefier Samsung Hercules.
Click to expand...
Click to collapse
The processor doesn't suck. It has better browser performance according to anandtech. The problem is that samsung has hardware acceleration for the stock rom on their other variants and not this one. The miui phone apparently blows most phones out of the water with its processor which is the same as this phone. Tons of optimization. All the same games run on both processors without hiccups. Also 42mbs is not the speed it can theoretically go up to that speed.
Realistic speeds are more along the lines 20 down and whatever uplpoad. I seen some people even get 26 down which is basically advertised lte speeds from Verizon. Also when you put both phones on gingerbread lets say cyanogen mod since its optimized you won't see a difference. You only see it on a stock touchwiz rom i doubt you'll see a difference when your on ice cream sandwich as well.
brian_v3ntura said:
nothing wrong? its old hardware. i would rather have the better performing Exynos processor than the watered down Snapdragon TMo SGS2. i dont see why Tmobile will sacrifice the main component that made the SGS2 an SGS2 just to claim that the phone supports up to HSPA+ 42mbps....which we will never see those speeds before the SGS3
Click to expand...
Click to collapse
well no one on any network will see those speeds for a while, att uses the same processor for their LTE network, i dont have a problem with speeds where i live , i get 15 meg on a regular basis and spikes up to 20 sometimes. And as far as performance it seems to hold up fine against the other phones. The phone is fine
tigerz0202 said:
well no one on any network will see those speeds for a while, att uses the same processor for their LTE network, i dont have a problem with speeds where i live , i get 15 meg on a regular basis and spikes up to 20 sometimes. And as far as performance it seems to hold up fine against the other phones. The phone is fine
Click to expand...
Click to collapse
I don't see what people always say inferior processor. I don't see what my processor can't do that the other processors can. Quadrant scores ,benchmarks, don't matter in real life performance. The exynos processor doesn't give any magical ability to fly or anything.
Killbynature said:
I don't see what people always say inferior processor. I don't see what my processor can't do that the other processors can. Quadrant scores ,benchmarks, don't matter in real life performance. The exynos processor doesn't give any magical ability to fly or anything.
Click to expand...
Click to collapse
i dont get it either, and as far as benchmarks even though they really dont matter my scores on the phone stock not rooted out of the box were 200 points better than any review on any website had the other variants at with the exynos.Gotta watch which article you read because it hard to find them that are un-biased .Naturally if they are reviewing a phone for a carrier its gonna be biased towards it. Only way of really reviewing a phone is hands on so you can do it yourself. Some people just care wayyy too much about stuff that dont matter.....i love this phone
tigerz0202 said:
well no one on any network will see those speeds for a while, att uses the same processor for their LTE network, i dont have a problem with speeds where i live , i get 15 meg on a regular basis and spikes up to 20 sometimes. And as far as performance it seems to hold up fine against the other phones. The phone is fine
Click to expand...
Click to collapse
that wasnt my point. it was just a waste for tmobile to choose the dual-core snapdragon processor just so they can claim their phone supports up to 42mbps. exynos only supports up to 21mbps which is just fine for real world experience.
yes the processor used in the TMo SGS2 is just fine,but thats just it....its just fine.
Killbynature said:
I don't see what people always say inferior processor. I don't see what my processor can't do that the other processors can. Quadrant scores ,benchmarks, don't matter in real life performance. The exynos processor doesn't give any magical ability to fly or anything.
Click to expand...
Click to collapse
the biggest difference between exynos and our dual-core snapdragon is GPU performance. i'm not even going to try to explain the differences myself as its already been said main times. so i will just quote from this article:
In return for this boost in possible data rates, some things are lost with the change over to Snapdragon. Perhaps the most important difference between the Exynos and Snapdragon is the graphics performance. As is the case with all SoCs, these chips have dedicated GPUs. The Qualcomm chip in the T-Mobile Galaxy S runs an Adreno 220, which is a fine component. Exynos, on the other hand, far surpasses it in graphical prowess.
The Exynos is the first mainstream SoC to license and use the ARM Mali-400 GPU. This is a quad-core graphics processor that bests all the other chips in GPU performance. So by going with a Snapdragon, even one clocked up to 1.5GHz, T-Mobile is sacrificing a significant amount of performance.
Straight processing power is also greater on the Exynos chip, but the gap is smaller than for the GPU. Qualcomm still uses its Scorpion core — a core developed to match the Cortex-A8, but Exynos is Cortex-A9. Snapdragon isn’t completely left in the dust because it’s still a solid custom architecture, but a 1.2GHz Exynos will still crunch more bits than a 1.5GHz Snapdragon.
The Snapdragon will offer users one additional benefit in the form of better battery life. The Qualcomm-designed Scorpion to be capable of asynchronous operation, making it possible for an unneeded core to be clocked down independently. This is much better for standby time and low-impact tasks.
Click to expand...
Click to collapse
http://www.extremetech.com/mobile/96267-how-samsungs-chip-change-up-affects-the-t-mobile-galaxy-s2
idk about you guys, but i rather have the best of the best. i definitely dont want to miss out on the new-gen high-end games when they do come out.
brian_v3ntura said:
that wasnt my point. it was just a waste for tmobile to choose the dual-core snapdragon processor just so they can claim their phone supports up to 42mbps. exynos only supports up to 21mbps which is just fine for real world experience.
yes the processor used in the TMo SGS2 is just fine,but thats just it....its just fine.
the biggest difference between exynos and our dual-core snapdragon is GPU performance. i'm not even going to try to explain the differences myself as its already been said main times. so i will just quote from this article:
Click to expand...
Click to collapse
well my sensation supported up to 14 meg and in the same exact areas never saw over 5. also tell me what you can do with a Xyenos processor that you cant do with the one we got
brian_v3ntura said:
that wasnt my point. it was just a waste for tmobile to choose the dual-core snapdragon processor just so they can claim their phone supports up to 42mbps. exynos only supports up to 21mbps which is just fine for real world experience.
yes the processor used in the TMo SGS2 is just fine,but thats just it....its just fine.
the biggest difference between exynos and our dual-core snapdragon is GPU performance. i'm not even going to try to explain the differences myself as its already been said main times. so i will just quote from this article:
Click to expand...
Click to collapse
Um your point valid we know its an inferior. But still it does what i needs to do you won't actually see the performance difference on the same optimized rom like cyanogenmod or miui. You won't even notice fps difference since their both locked at 60fps. So its fine. The point is its superior as seen on paper and benchmark test but they both work perfectly fine. The exynos doesn't give you wings.
There are no games the both processors can't play smoothly. Tell the truth most apps and everything start up at the same time and speed. So having all that processing power which will be null and void in like a year or two will really matter. A lot of apps and games say not compatible with the samsung galaxy s2 yet. Because of the processor and gpu combo. This is for the original version of the galaxy s2.
If the exynos made me play a game that can only run on that processor then yeah. But it doesn't. It doesn't make anything load faster either.
by the time a game comes out that fully puts a either of those processors to use we will be using another phone with different processors and who cares about games on a phone, just get a ps3,360 or pc for that
brian_v3ntura said:
idk about you guys, but i rather have the best of the best. i definitely dont want to miss out on the new-gen high-end games when they do come out.
Click to expand...
Click to collapse
You have a warped sense of reason if you think that the difference in performance between the Exynos and the SD3 constitutes your statement: "the actual processor sucks".
tigerz0202 said:
well my sensation supported up to 14 meg and in the same exact areas never saw over 5. also tell me what you can do with a Xyenos processor that you cant do with the one we got
Click to expand...
Click to collapse
i alrdy told you, CLIFF NOTES: better gaming and better processing crunch.
you're talking about the sensation. not remotely close to anything equipped with exynos. its easy to claim something without providing concrete proof. you can say your sensation never got past 5mbps in the same areas, but that can depend on a number of things.
1)reception efficiency of the radio
2)tower upgrade timeline in specific areas
3)blowing smoke.
Killbynature said:
Um your point valid we know its an inferior. But still it does what i needs to do you won't actually see the performance difference on the same optimized rom like cyanogenmod or miui. You won't even notice fps difference since their both locked at 60fps. So its fine. The point is its superior as seen on paper and benchmark test but they both work perfectly fine. The exynos doesn't give you wings.
There are no games the both processors can't play smoothly. Tell the truth most apps and everything start up at the same time and speed. So having all that processing power which will be null and void in like a year or two will really matter. A lot of apps and games say not compatible with the samsung galaxy s2 yet. Because of the processor and gpu combo. This is for the original version of the galaxy s2.
If the exynos made me play a game that can only run on that processor then yeah. But it doesn't. It doesn't make anything load faster either.
Click to expand...
Click to collapse
there are no games that both processors cant play smoothly? i guess you played EVERY GAME then right? Here's an example of a game; dungeon defenders.
i'm just waiting for the new-gen of games to come out to really see the limits of this qualcomm dual-core snapdragon. the new-gen games are closer to release dates than you think.
PLUS any mobile processor is pretty much null and void within a year or two. But at least the Exynos has a better chance of holding its ground.
redline06 said:
by the time a game comes out that fully puts a either of those processors to use we will be using another phone with different processors and who cares about games on a phone, just get a ps3,360 or pc for that
Click to expand...
Click to collapse
not entirely true. not willing to summarize what i said above. i forgot to add that "Bladeslinger" may be THE game that will show the performance difference between the two.
i care about mobile gaming. its a nice thing to to have when you're away. its fun. plus the only thing i play on console is COD.
Bimboy said:
You have a warped sense of reason if you think that the difference in performance between the Exynos and the SD3 constitutes your statement: "the actual processor sucks".
Click to expand...
Click to collapse
sucks in the sense of old hardware.
All in all. It's your opinion and your view of what fits your needs right? It's not being constructive to give criticism when it only is one sided. I can tell you value the best and fastest in technology. there are ways to express it than to bring everyone down. I could care less about gpu or the type of processor because I have an actual laptop for that. I am happy with the speed and response of this phone. So to downplay things you think are wrong with this phone with cliffnotes and technical theories then you really aren't being constructive.
brian_v3ntura said:
i alrdy told you, CLIFF NOTES: better gaming and better processing crunch.
you're talking about the sensation. not remotely close to anything equipped with exynos. its easy to claim something without providing concrete proof. you can say your sensation never got past 5mbps in the same areas, but that can depend on a number of things.
1)reception efficiency of the radio
2)tower upgrade timeline in specific areas
3)blowing smoke.
there are no games that both processors cant play smoothly? i guess you played EVERY GAME then right? Here's an example of a game; dungeon defenders.
i'm just waiting for the new-gen of games to come out to really see the limits of this qualcomm dual-core snapdragon. the new-gen games are closer to release dates than you think.
PLUS any mobile processor is pretty much null and void within a year or two. But at least the Exynos has a better chance of holding its ground.
not entirely true. not willing to summarize what i said above. i forgot to add that "Bladeslinger" may be THE game that will show the performance difference between the two.
i care about mobile gaming. its a nice thing to to have when you're away. its fun. plus the only thing i play on console is COD.
sucks in the sense of old hardware.
Click to expand...
Click to collapse
Sent from my SGH-T989 using XDA App
brian_v3ntura said:
i alrdy told you, CLIFF NOTES: better gaming and better processing crunch.
you're talking about the sensation. not remotely close to anything equipped with exynos. its easy to claim something without providing concrete proof. you can say your sensation never got past 5mbps in the same areas, but that can depend on a number of things.
1)reception efficiency of the radio
2)tower upgrade timeline in specific areas
3)blowing smoke.
there are no games that both processors cant play smoothly? i guess you played EVERY GAME then right? Here's an example of a game; dungeon defenders.
i'm just waiting for the new-gen of games to come out to really see the limits of this qualcomm dual-core snapdragon. the new-gen games are closer to release dates than you think.
PLUS any mobile processor is pretty much null and void within a year or two. But at least the Exynos has a better chance of holding its ground.
not entirely true. not willing to summarize what i said above. i forgot to add that "Bladeslinger" may be THE game that will show the performance difference between the two.
i care about mobile gaming. its a nice thing to to have when you're away. its fun. plus the only thing i play on console is COD.
sucks in the sense of old hardware.
Click to expand...
Click to collapse
I played dungeon defenders I'm rooted it doesn't slow down or anything. I don't see your point. BladeSlinger is for all android devices.... Not to mention ShadowGun looks exactly like it in quality and i can play that on my device as well smoothly. Bladeslinger also pauses in the middle of gameplay to do a special move. Shadowgun enemies are always shooting at you.
Chainfire prove before that all you need is simple plugins to run the tega2 only games or qualcomm only games on any device. What makes you think it will be so different in the future. No one will be using the same exynos next year majority of ppl will sell of the galaxy s2 or the galaxy s3. It will be the same with the Qualcomm processor for the new krait or the new tegra3 processor. I can play dungeon defenders on mytouch 4g with its single core processor on miui. So what?
There have been a lot of people who have been doing comparisons of various phones (particularly the Galaxy S2) to the Galaxy Nexus. I recalled during the Samsung/Google event them saying they chose to use an industry leading hardware inside the phone, so I decided to look into this a little further. As I'm sure you're well aware, the first thing people tend to point at are benchmarks. The gpu benchmarks are particularly what have come under fire when people make their comparisons. Though the mali 400 does bench out higher than the SGX540 the higher performance on the mali isn't a tangible benefit as "end device applications have not yet caught up with the highest graphics performance delivered by these" (http://armdevices.net/2011/10/26/interview-with-the-texas-instruments-omap4-team/). In other words that's like having a road with a 300mph speed limit but the cars are only able to achieve 120mph. Driving on the road with the 300mph speed limit won't get you there any faster than driving on a road with a 200mph speed limit if the speed of the car is the same.
As for processors, the processors as they are now are roughly on par with each other with them both being 45nm A9's clocked at 1.2. The difference between them is that the exynos 4210 is clocked at it's true clock speed at 1.2, whereas the omap 4460 is actually underclocked to 1.2 and has a true clock speed of 1.5. Thus meaning the processor has more speed potential than that of the exynos.
One thing that does stand out as an advantage of the omap 4460 over some of the competition is it's memory bus bandwidth. For those that don't know, in simple terms, it's how fast information can be read from and stored to memory by the processor. In other words, you can have the fastest processor in the world but if you don't have enough memory bandwidth to accommodate the amount of information that needs to be transferred then that speed won't matter because it will be bottlenecked. For example, let's say you have a car that can reach 200mph and you want to drive that car at full speed. However the street you're driving on can only handle 20 cars at a time, and you're the 21st car, well in this case you're going to be stuck in traffic. Sure you have the raw potential of doing 200mph, but you won't ever get close to that because of traffic congestion. The same concept applies when we're talking about memory bandwidth. That being said, the memory bandwidth on the omap 4460 is 6.4GB/s, the exynos 4210 is 6.4GB/s, the iphone 4s is 6.4GB/s, and the Tegra 2 is 2.5 GB/s. Add all of this with the fact that the TI processor is underclocked to 1.2ghz (for power savings) as opposed to running at full strength and full power (ie. Galaxy S2), you have what is in my opinion the superior processor. Personally, I'd rather have an underclocked processor that delivers the same or better performance and saves me power, than to have a gpu that has excessive power that I can't even make use of. It's kind of like saying you have a rocket launcher for self defense, sure the rocket launcher is powerful but it isn't something you can really make use of. In closing I think AnandTech said it best when they said "Until Tegra 3 and Krait show up, the CPU side of the 4460 is as good as it gets."
Sources:
http://www.samsung.com/global/business/semiconductor/productInfo.do?fmly_id=844&partnum=Exynos 4210
http://www.anandtech.com/show/2911
https://docs.google.com/viewer?a=v&...mA2j6n&sig=AHIEtbTE8LvpHXPUcE4w_wGU5apdbGD0Eg
http://armdevices.net/2011/10/26/interview-with-the-texas-instruments-omap4-team/
https://plus.google.com/105051985738280261832/posts/2FXDCz8x93s
http://www.phonearena.com/news/Why-...Galaxy-Nexus-Android-ICS-poster-child_id23089
http://www.anandtech.com/show/5133/galaxy-nexus-ice-cream-sandwich-initial-performance
Nice post!
Gave me some more insight in the decision for the Omap processor and makes me feel i made a real good decision ordering the GN.
Maybe some paragraphs in your text would be nice, to make it easier to read.
Kind regards.
Thanks, now I feel even better for chosing my Nexus....
wow that was very informative. all that confusion the past couple of months about why the g-nex would be using the TI OMAP 4460 instead of, what was believed to be more powerful processors like the Exynos. but this post really cleared that up for me.
thanks!
Thanks !! Nice and simple.
Woah, huge walloftext.jpg
Anyway, hate to break it to you, but the processors in Galaxy Nexus are 4460, but they're probably binned 1.5ghz processors i.e. processors that couldn't run at the full 1.5ghz
https://twitter.com/#!/coolbho3k/status/140218721774997504
https://twitter.com/#!/coolbho3k/status/140214089183010819
Oh, and this: https://plus.google.com/105051985738280261832/posts
Galaxy Nexus runs at significantly higher res than Galaxy S II, and has to push many many more pixels...
Rawat said:
Woah, huge walloftext.jpg
Anyway, hate to break it to you, but the processors in Galaxy Nexus are 4460, but they're probably binned 1.5ghz processors i.e. processors that couldn't run at the full 1.5ghz
https://twitter.com/#!/coolbho3k/status/140218721774997504
https://twitter.com/#!/coolbho3k/status/140214089183010819
Oh, and this: https://plus.google.com/105051985738280261832/posts
Galaxy Nexus runs at significantly higher res than Galaxy S II, and has to push many many more pixels...
Click to expand...
Click to collapse
I think you're missing my point. Yes the full speed potential of the 4460 chip is 1.5ghz, but it is clocked at 1.2ghz. Whether or not you will be able to clock the chip back up to 1.5 isn't what I'm getting at. The point is it has comparable processing power at a lower clock speed that it is spec'ed at. Meaning it can give comparable processing power as it's competitors but use less power, which obviously is a good thing. As for your last statement, you do realize that person you linked to is one of the sources I cited . The fact that so many more pixels have to be pushed is exactly why having more memory bandwidth is so important. Had they gone with an exynos processor clocked at 1.2 instead, there's a chance the user experience may have suffered. Think about this, the galaxy not has the exynos, but they had to clock it to 1.5 (instead of the 1.2) AND give it a 2500mah battery so that it can get decent battery life. Obviously they wouldn't be able to fit a battery of that capacity (or even close to it) in the galaxy nexus, so if they put a exynos in the nexus clocked that high, there would be a serious battery problem...and if they put a 1.2 in there with the lower memory bandwidth, there could also be a potential for user experience issues. The overall point that I'm making is that the 4460 is actually a very good chip due to the high memory bandwidth and the fact that it's more power efficient.
"More power efficient"
More power efficient than what? Exynos is pretty power efficient itself, and Note doesn't have such a large battery to counter the clock speed of Exynos, it's because it's a huge fricking phone, and they can fit it inside.
OMAP4460 is rather decidedly the 3rd best smartphone SoC in the market. A5 and Exynos are ahead (well, not CPU on a5, but GPU more than makes up for it) but it's better than Tegra2, and snapdragon. At least that's something, eh?
Awsome! Well explained, thank you, make sticky please!
Sent from my X10i using xda premium
Rawat said:
"More power efficient"
More power efficient than what? Exynos is pretty power efficient itself, and Note doesn't have such a large battery to counter the clock speed of Exynos, it's because it's a huge fricking phone, and they can fit it inside.
OMAP4460 is rather decidedly the 3rd best smartphone SoC in the market. A5 and Exynos are ahead (well, not CPU on a5, but GPU more than makes up for it) but it's better than Tegra2, and snapdragon. At least that's something, eh?
Click to expand...
Click to collapse
I will keep my response to you brief, since it's obvious you didn't read what I posted (judging from the fact that you posted link to the same person that I already had a link to in my sources). That being said, explain why the Exynos and the A5 are ahead. Instead of making a generalized please use some facts to support what you state. If that is what you think, I'd love to read why.
Rawat said:
Anyway, hate to break it to you, but the processors in Galaxy Nexus are 4460, but they're probably binned 1.5ghz processors i.e. processors that couldn't run at the full 1.5ghz
Click to expand...
Click to collapse
Hate to tell you this, but if it is indeed a 4460, these are 1.5 GHz parts. Plain and simple, if they weren't they would have a wildly different part number (think of Intel CPU's...the new I7 39xx series are binned Xeon parts...) than the one shown in the pictures or on the IC's themselves. Why? To put it bluntly, false advertisement. Every single thing online states 1.5 GHz for the part. No literature (that I can find) says anything less than that. And yes, I know a few things have the wording 'up to', but that doesn't change the fact that it's still a 1.5 GHz part. It just isn't rated for higher than 1.5 GHz. It's similar to how Apple clocks the A5 down to 800 MHz for the Iphone 4S. Get some power savings at the price of a small bit of performance. Does this mean that the A5's in the Iphone 4s can't do 1 GHz? Probably not.
Got proof of the accused binning? Then maybe I'll start considering that belief. But until I see 'real' proof, I highly doubt that TI is selling binned parts that can't make 1.5 GHz. That would kind of be pointless to say the 4460 is a 1.5 GHz part, but sell it with a max of 1.2 GHz without atleast changing the part number in some way (ie 4450 for instance).
mysterioustko said:
I think you're missing my point. Yes the full speed potential of the 4460 chip is 1.5ghz, but it is clocked at 1.2ghz. Whether or not you will be able to clock the chip back up to 1.5 isn't what I'm getting at. The point is it has comparable processing power at a lower clock speed that it is spec'ed at. Meaning it can give comparable processing power as it's competitors but use less power, which obviously is a good thing.
Click to expand...
Click to collapse
This is faulty reasoning. You are claiming that because the OMAP4460 in the GN is underclocked from 1.5GHz to 1.2GHz, it must consume less power than a Exynos 4210 clocked at 1.2GHz. This is only true if the OMAP4460 at 1.5GHz consumes the same amount of power as the Exynos 4210 at 1.2GHz. But we have no evidence that this is the case. The OMAP4460 at 1.5GHz might simply have a higher thermal envelope than the Exynos 4210 at 1.2GHz and is able to draw more power. Thus the OMAP4460 at 1.2GHz might consume power comparable to the Exynos 4210.
darkhawkff said:
Hate to tell you this, but if it is indeed a 4460, these are 1.5 GHz parts. Plain and simple, if they weren't they would have a wildly different part number (think of Intel CPU's...the new I7 39xx series are binned Xeon parts...) than the one shown in the pictures or on the IC's themselves. Why? To put it bluntly, false advertisement. Every single thing online states 1.5 GHz for the part. No literature (that I can find) says anything less than that. And yes, I know a few things have the wording 'up to', but that doesn't change the fact that it's still a 1.5 GHz part. It just isn't rated for higher than 1.5 GHz. It's similar to how Apple clocks the A5 down to 800 MHz for the Iphone 4S. Get some power savings at the price of a small bit of performance. Does this mean that the A5's in the Iphone 4s can't do 1 GHz? Probably not.
Got proof of the accused binning? Then maybe I'll start considering that belief. But until I see 'real' proof, I highly doubt that TI is selling binned parts that can't make 1.5 GHz. That would kind of be pointless to say the 4460 is a 1.5 GHz part, but sell it with a max of 1.2 GHz without atleast changing the part number in some way (ie 4450 for instance).
Click to expand...
Click to collapse
From the kernel code of the Galaxy Nexus arch/arm/mach-omap2/id.c:
Code:
if (cpu_is_omap446x()) {
si_type =
read_tap_reg(OMAP4_CTRL_MODULE_CORE_STD_FUSE_PROD_ID_1);
switch ((si_type & (3 << 16)) >> 16) {
case 2:
/* High performance device */
omap4_features |= OMAP4_HAS_MPU_1_5GHZ;
omap4_features |= OMAP4_HAS_MPU_1_2GHZ;
break;
case 1:
default:
/* Standard device */
omap4_features |= OMAP4_HAS_MPU_1_2GHZ;
break;
}
}
There appears to be something in the OMAP hardware that designates whether it is a "high performance device" or a "standard device". A standard device can only operate at 1.2GHz, not 1.5GHz. It is unclear if "device" here refers to the SoC or the phone. If it refers to the SoC, then it would suggest that the SoCs are binned into high and low performance categories, with the low performance devices incapable of performing at 1.5GHz.
But here's some preliminary evidence that the SoC itself may be missing something that's required for 1.5GHz to work: http://forum.xda-developers.com/showpost.php?p=19931580&postcount=97
mysterioustko said:
That being said, the memory bandwidth on the omap 4460 is 7.5GB/s the exynos 4210 is 6.4GB/s, and the Tegra 2 is a mere 2.5 GB/s.
Click to expand...
Click to collapse
Where are you getting that the memory bandwidth of the OMAP 4460 is 7.5GB/s? The Galaxy Nexus uses the Samsung K3PE7E700M-XGC1 1GB memory package, which is a 400MHz, LPDDR2, 32-bit dual-channel memory package. This means it has a memory bandwidth of 400 * 2 (for DDR) * 32 * 2 (for dual-channel) = 51200Mb/s = 6.4GB/s, same as the Exynos 4210.
See: http://www.samsung.com/us/business/oem-solutions/pdfs/PSG2011_web.pdf for details on the memory package used in the GN.
mysterioustko said:
I will keep my response to you brief, since it's obvious you didn't read what I posted (judging from the fact that you posted link to the same person that I already had a link to in my sources). That being said, explain why the Exynos and the A5 are ahead. Instead of making a generalized please use some facts to support what you state. If that is what you think, I'd love to read why.
Click to expand...
Click to collapse
I actually read your whole post, but skipped over reading the sources you had linked to.
A5 and Exynos are widely regarded as the 2 best SoC on the market (not including Tegra3, which just launched). Don't take my word for it, see anandtech here and here. But of course, it's hard to directly compare A5 to another (non-apple) SoC, because they run on different OSes
Rawat said:
I actually read your whole post, but skipped over reading the sources you had linked to.
A5 and Exynos are widely regarded as the 2 best SoC on the market (not including Tegra3, which just launched). Don't take my word for it, see anandtech here and here. But of course, it's hard to directly compare A5 to another (non-apple) SoC, because they run on different OSes
Click to expand...
Click to collapse
I don't care what it's "widely regarded" as. I asked for concrete information that supports what you state. You support your argument by stating that people's opinion of it is that it's best....that's not exactly a compelling argument.
I didn't read a word seeing as how it's all big one wall of text but I got the gist of it from the title. Yay my Nexus is even further ahead of the competition now than it was 20 seconds ago
mysterioustko said:
I don't care what it's "widely regarded" as. I asked for concrete information that supports what you state. You support your argument by stating that people's opinion of it is that it's best....that's not exactly a compelling argument.
Click to expand...
Click to collapse
Clock speeds aside, the A5 is clearly a better SoC. The CPUs in all three are pretty much the same, dual-core Cortex A9s on a 45nm process. It comes down to the GPU. The A5 has a better GPU simply because it's pretty much the multicore version of the GPU in the OMAP4460. Between the OMAP4460 and the Exynos 4210, it's more difficult to say. The PowerVR540 and Mali400 have different strengths and weaknesses, so I won't speculate here.
I would also suggest that you modify your original post. It contains quite a bit of misinformation and clearly many people have read it and taken it to heart. That's not a good thing, and I hope you will do the responsible thing and try to reverse the misinformation that you've spread.
Chirality said:
Clock speeds aside, the A5 is clearly a better SoC. The CPUs in all three are pretty much the same, dual-core Cortex A9s on a 45nm process. It comes down to the GPU. The A5 has a better GPU simply because it's pretty much the multicore version of the GPU in the OMAP4460. Between the OMAP4460 and the Exynos 4210, it's more difficult to say. The PowerVR540 and Mali400 have different strengths and weaknesses, so I won't speculate here.
I would also suggest that you modify your original post. It contains quite a bit of misinformation and clearly many people have read it and taken it to heart. That's not a good thing, and I hope you will do the responsible thing and try to reverse the misinformation that you've spread.
Click to expand...
Click to collapse
Omap vs Exynos ? The latter doesn't support HSPA+ or LTE.
Dmw017 said:
Omap vs Exynos ? The latter doesn't support HSPA+ or LTE.
Click to expand...
Click to collapse
This is hardly anything to do with "performance".....and not to mention that ICS is a TON more dependant on GPU renders....hardly a place it has any room to fall short.
Sent from my SAMSUNG-SGH-I777 using XDA App
Dmw017 said:
Omap vs Exynos ? The latter doesn't support HSPA+ or LTE.
Click to expand...
Click to collapse
Exynos will do 21Mbps, HSPA+
Sent from my GT-I9100 using Tapatalk
Chirality said:
Where are you getting that the memory bandwidth of the OMAP 4460 is 7.5GB/s? The Galaxy Nexus uses the Samsung K3PE7E700M-XGC1 1GB memory package, which is a 400MHz, LPDDR2, 32-bit dual-channel memory package. This means it has a memory bandwidth of 400 * 2 (for DDR) * 32 * 2 (for dual-channel) = 51200Mb/s = 6.4GB/s, same as the Exynos 4210.
See: http://www.samsung.com/us/business/oem-solutions/pdfs/PSG2011_web.pdf for details on the memory package used in the GN.
Click to expand...
Click to collapse
You are correct, I mistakenly read the the 4470's bandwidth when researching the 4460 (the 4470's bandwidth was referenced in the same TI interview where they discussed the 4460).
I posted this in the XDA general section not too long ago and didn't get too many replies, I was hoping I could get some more info here.
"I've been doing quite a bit of research on GPU's and CPU's in phone's/tablets lately. And I have a few unanswered questions that I can't seem to find an answer for.
1: What's the best chipset available for mobile phones and tablets right now? This link cleared quite a bit up for me, it does a fairly indepth comparison for both GPU and CPU performance between the Qualcomm S4, Tegra 3, OMAP 4470, and the Exynos 4212. And I dont want the 'Well this is better because it has more jiggahertz". Shut up, that's not what I need. I need something more indepth. If studies on individual GPU comparison can be provided, please drop a link. I'd like to know these things very well in depth.
2: What individual GPU is currently the best? I realize the Ipad3 came out with with a graphics chip that's supposedly superior to the Xbox/PS3's (which is bogus). However I take anything Apple says with a grain of salt, they're notorious for shooting flaming BS out of their rear. However based on the little bit of searching I've done, the Adreno GPU's seem to be ahead of their time, as well as the PowerVR series seen in apple products. I previously thought the Mali 400 GPU in the Exynos chipset was one of the best, but apparently it's outdated. Again, links to tests/studies/comparisons would be appreciated.
3: What's the deal with the Tegra 3 GPU? It's a 12 core set, but it's constantly outperformed by quad core GPU's, even dual core Adreno GPU's perform better than whatever is inside the the Tegra 3, the Kal-El or whatever it's called. The Power VR's M4 gpu in the Ipad (as said as it is to say) destroys pretty much everything else out there. What's the deal.
If you're able to answer any one of these, even exclusively, that would be appreciated. I just like knowledge "
The Mali mp400 won't be used next exynos .... the nvidia is inferior due to number of instructions per core per cycle didn't change they just brought more cores...... adreno has proven middle of the road but better then tegra and powervr in the latest is the best to see the market the Mali mt series isn't in any products yet.... but I'm hopeful
Sent from my SPH-D710 using Tapatalk
Some food for thought,,
Is Qualcomm cheating in Vellamo?
A few days ago we were happy to report about the first set of leaked HTC One X scores on an American device powered by Qualcomm’s new 28nm S4 chip.
The scores look quite good for Qualcomm, but since we got hold of an Asus Transformer Prime we decided to dig a bid deeper. Both Nvidia and Qualcomm do not want to get involved in official fight but we were quite surprised with what we learned. We also talked to some engineers that want to remain unnamed and we came up with a few interesting things.
The fastest CPU in Quadrant is Hummingbird S5PC110 from Nexus S as tested here.
Since we have tested this phone you can easily tell that this benchmark doesn't really use two or four cores properly. In this test S4 scores 4920 where the Tegra 3 based Transformer Prime scores 3954 and Tegra 2 scores 2154 on a custom ROM Optimus 2X.
The second test is the Vellamo benchmark was a bit more disturbing as once you run it you see Qualcomm ads all over it. This didn't give us much confidence and it turns out that Qualcomm has a lot of power over this particular benchmark.
Asus Transformer Prime scores 1408, while Qualcomm in Vellamo scores over 2000, our guess is between 2200 and 2300 as we didn't see the full number. Our good buddy Anand compared the One S powered by the S4 as well as the One X powered by Tegra 3 and you can see that Tegra 3 on this phone usually ends up faster or tied with the S4. It is faster in Sunspider Javascript benchmark 0.9.1, loses by a few points in Browsermark to S4 based HTC One S and dominates GLBenchmark. There is no 2X performance lead that we saw in the leaked S4 benches and frankly we see no point in taking Vellamo seriously until the issue is addressed.
Our engineering friends are telling us that Velamo disables some hardware acceleration in compositing Deap Sea Canvas and See the sun canvas subtest. Honeycomb and ICS support hardware acceleration by default and disabling this probably hurt the general score. One can argue that it hurts S4 scores as well, but it definitely hurts Tegra 3 more. The benchmark isn't flushing commands in the Pixel Blender subtest and there is a suspicion that this might help Qualcomm S4 to gain a better score.
The most important issue is the fact that it is unclear how Vellamo scores sub test scores. In Third party benchmarks such as Sun Spider and Google V8 it turns out that Vellamo penalizes high Google V8 scores and if your score gets too high in V8, the general score gets lower. There are a lot of benchmarks out there and some of the ones that like more cores include Antutu, CF benchmark and Moonbat.
French enthusiasts managed to run Antutu here, and Tegra 3 phone scores 10597, while the S4 based HTC One S scores 6458. This doesn't look so good for the phone that is based on S4 cores that should go after ARM’s upcoming A15 and it looks like that it cannot really beat the A9-based Tegra 3. In the real world, as long as the application is aware of four cores, there is a good chance that Tegra 3 will end up faster than the S4.
Naturally if you are reading this from the US and you really like your LTE from AT&T or Verison, I guess that you won’t have much choice and you will get the HTC One X with Qualcomm S4 as this chip also supports LTE. In the US it’s all about LTE and in Europe despite the fact that countries like Austria have LTE for more than a year now, even at €50 for 40GB there is almost no interest whatsoever. Networks need to put more advertising money and make 4G cool and it might happen. Of course, the lack of 4G devices is also an issue, but technology has a way of catching up.
The story gets even better when you know that there are lot of former ATI employees who take care of Adreno graphics and if natural selection and theory of evolution have taught us anything, it is that Nvidia and ATI are sworn enemies in any universe. Some readers might see a pinch of poetic justice in all of this, as Nvidia was accused of tweaking its GPU drivers to score more in PC benchmarks years ago.
Tudor Brown, the president of ARM that we meet a few years back at GlobalFoundries Dresden fab, once said that ARM does not want to get involved in GHz fight and this is now exactly what is going on, as punters are using benchmarks to prove of A is faster than B. Frankly I would be more concerned about battery life that I can get from a brand new phone as we got from five day battery life on feature phones to a day or so of battery life, and with LTE and heavy use, even this can go down to a few hours at best. If I found myself in Qualcomm’s shoes, this is what I would emphasize, the new 28nm process and energy efficiency, not skewed benchmarks.
Phones should be about the overall user experience, but how can you benchmark experience? It's a very subjective category and can hardly be expressed with cold numbers and statistics. We are not talking about PC components and the race for more performance, smartphones should be viewed as a complete package, battery life, build quality, UI and design come into play. Sheer performance is just one aspect and for many users it is still not the deciding factor and we believe it should not be.
In any case, watching the phone market will definitely be fun in the months to come.
Click to expand...
Click to collapse
Source: Here
arthasz said:
Some food for thought,,
Source: Here
Click to expand...
Click to collapse
haha fun stuff ill quote some of it in my thread if you don't mind thanks
to be honest this is exactly what i felt the moment i thought the score, its ridiculous
glad we got confirmation from some devs too
---------- Post added at 12:13 PM ---------- Previous post was at 11:56 AM ----------
speaking of which, their Adreno3x series is far from ready
Qualcomm has Imagination
Apparently they might go with PowerVR for the windows s4 devices, i find this hard to believe
Semi accurate is part of this fud game
Now things make sense. That's why people don't blindly trust these benchmark score. Try real work applications you'll better idea of the device like running 12 HD video in T3 etc.
I've always trusted Antutu
& apparently, the tegra 3 version is a beast, scoring over 10,000!
My SGS2 scores just 4,700 on gingerbread & around 5,700 on ICS.
Sent from my GT-I9100 using Tapatalk
My overclocked (1,4 GHz) Desire Z (ICS with Sense 4.0A) got around 1 200 points in Vellamo, in graph it was just above Transformer Prime. Qualcomm must cheating.
Edit: added screenshots (due to my bad memory - it was just above while at 1,4 GHz ), at 1,6 GHz it is will be better than Prime (according to benchmark)
Reremnu said:
My overclocked (1,4 GHz) Desire Z (ICS with Sense 4.0A) got around 1 200 points in Vellamo, in graph it was just above Transformer Prime. Qualcomm must cheating.
Click to expand...
Click to collapse
hahaha now that is crazy, disappointed that qualcomm took this direction they always been more transparent
actually its wrong that they make a test themselves it can never be considered impartial
snapdragon 4 cores are impressive as they are they don't need this kind of fud just because they don't have a quad ready
If this is really true, how about other benchmarks with other devices? can they be trusted?