Benchmarks vs Transformer Prime (and other tabs) - Eee Pad Transformer General

I was looking into buying either the TF / Prime this past week, and have been looking into the benchmarks I see on the net. I've seen a few reviews, one from AnandTech, and the other one from Slashgear and random Antutu benches across the web.
If I'm understanding correctly, it seems the Prime obviously does have an edge, however for general non-gaming use it seems the differences are minimal? Can anyone confirm or if you own both to test it out?
In a javascript benchmark (AnandTech.com), I'd only see a 0.4-0.5 second difference loading JS heavy webpages?
{
"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"
}
The BrowserMark comparison at slashgear shows a 0.5-0.6 second gain by the Prime:
So are the benches really showing the difference is this minimal or are there more to talk about that I'm not seeing? (Not referring to game benches, not too interested in gaming)

From what I understand the main difference is in the GPU so for games and such it will matter... Also more hardware support for video making 1080p a feature now.
The cpu itself is clocked higher so I wonder what the differences would be with an equally clocked TF101. I guess barely noticable...
Off course there's the quadcore vs dualcore but I wonder if that really matters in day to day use. I don't expect a huge difference in user experience so in that regards I don't think there's a big reason to upgrade from TF101 to TF201.
I still will though, because the size decrease (and weight decrease) combined with the other factors still make it a nice upgrade. But looking at just performance, meh...

i overclock my Tf101 to 1.5ghz and its very fast now. i would argue an overclocked Tf101 would perform the same if not better than a prime in most of these tests.

But then again, the prime might have just as much overclocking room... Giving it the lead again.

The problem is that benchmarks generally mean absolutely nothing. Having a good benchmark doesn't mean you are going to get great real world use.

pside15 said:
The problem is that benchmarks generally mean absolutely nothing. Having a good benchmark doesn't mean you are going to get great real world use.
Click to expand...
Click to collapse
That's the thing, having a machine that benchmarks 26% faster (TF201 vs TF 101) does not mean that it is going to necessarily be faster in real life depending on the software and how it uses it.

Benchmarks should prove the Prime to be a better machine, singularly. Dual/quad-core, it’s all about apps utilization and user functionality.
Then there’s price/performance, (in my case) a $250 101 beats the 201.

That's the part of what I've been trying to say. If I'm only going to see a split second of differences (0.5 second) in browsing around heavy javascript or just general web browsing performance, is there more than this?
Seems like so far the only argument I can see about getting a Prime is a GPU and CPU boost to gaming fps by 20-30 fps.
What about outside of gaming, in respect to general tasks that can take some time, like compressing a zip of a nand backup or large rom files, general encryption, etc.
The price per performance of the TF101 definitely seems to be taking the lead if we aren't talking about gaming apps.

dagrim1 said:
But then again, the prime might have just as much overclocking room... Giving it the lead again.
Click to expand...
Click to collapse
My impression is that quad core performance vs dual core does not follow a linear scale.. If the way the architecture of 4x ARM CPU's (TF201) vs 2x (TF101) is any similar to how Intel Quad vs Duo started getting popularity a few years ago, I feel that there are going to be relatively few noticeable differences, when the dual can suit an average user without noticeably seeing any changes using a quad for their tasks... Mainly it will have to wait until which apps can utilize the multiple cores efficiently. Crysis for android?
Course I might be off base with this, that's why I wanted to ask you guys who have owned it.

Unless you are using high end games specifically designed for the Quad core/GPU, you should not notice a real difference. Much of what you do with any tablet or computer is speed dependent on outside sources ie network speed, ( both on your end and the other end) input speed etc. If you are using or rendering high end graphics, you will notice the difference, but then why use a tablet for that in the first place.

The first benchmark for Prime is done is slowest, power saving mode.

Asus TF201 Prime is the best

GasGuzz said:
Benchmarks should prove the Prime to be a better machine, singularly. Dual/quad-core, it’s all about apps utilization and user functionality.
Then there’s price/performance, (in my case) a $250 101 beats the 201.
Click to expand...
Click to collapse
The 201 actually has a 5th core that is for normal usage, so most of the time you will be running a single core. I have seen in benchmarks that the internal flash on the 201 is slower than the 101. The 201 also has only a mono speaker compared to the stereo 101. The 101 right now has overclocking and custom ROMs. Add in price and that is the reason I just bought a 101 instead of a 201.
Cheers!
-M
Xda member since 2007

Related

Samsung Galaxy S2 Specs (2GHz, 1GB RAM, etc.)

Source: http://www.redmondpie.com/samsung-galaxy-s2-specs-will-blow-your-brains-out/
The current generation of smartphones – with their 1GHz processors and 512MB of RAM – are already very impressive at what they can do. But rumored specifications (along with a photo) are spreading of the next generation of Samsung’s Galaxy S smartphone – the Galaxy S2 – and its specs will. freaking. blow. your. head. off.
{
"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"
}
It is supposedly scheduled for release sometime in early 2011 and will supposedly have the following specifications:
-A 2GHz Processor. Possibly the next-generation version of Samsung’s Hummingbird CPU.
-1GB RAM along with 4GB of ROM. This is, as with the CPU, twice the magnitude of current-gen hardware.
-32GB built-in flash memory. MicroSD card slot expandable to 32GB making the Galaxy S2 able to hold 64GB of data.
-8 megapixel camera with full HD (1920×1080) video recording. Current-gen smartphones record video at 720p (1280×720).
-A 4.3” 1280×720 Super AMOLED display
-GPS, Bluetooth 3.0, b/g/n Wi-Fi, accelerometer, gyroscope, proximity / ambient light sensors.
-Run on Android 3.0 “Gingerbread”
While all these specifications are well and sweet, I really, honestly believe smartphone manufacturers, especially of the Android variety, should focus on increasing battery life by optimizing hardware + software instead of just blindly increasing clock speeds and doubling RAM. My HTC Desire still doesn’t last more than 15-16 hours whereas Taimur’s iPhone 4 blows past the 24 hour category without even going below 50%.
And yes, these specs are rumored. But if HTC and Motorola’s intentions of releasing 2GHz smartphones are anything to go by, they aren’t unbelievable.
Click to expand...
Click to collapse
What do you guys think the battery quality will be?
Jesus, its only 8 threads under this
http://ip208-100-42-21.static.xda-developers.com/showthread.php?t=817358
Doubting this, especially if scheduled for early 2011.
Specs looks two gen ahead of current, but if for real, I like it...well, except for the 4.3in screen.
I fail. Delete thread please.
I don't care until they actually give me froyo.
I don't know it sounds more like someones dreams/wish someone had more then a matter of fact...can anyone confirm that Samsung will be releasing Galaxy S2 at all?
they do love dangling the proverbial carrot in front of us don't they?
seriously though, why would you ever need dual core phones? I understand it's the next logical step, but I don't plan on bit torrenting HD porn from my phone. The original Galaxy still seems plenty new and amazing enough for me to not care about another phone for at least a year.
SeanFloyd said:
they do love dangling the proverbial carrot in front of us don't they?
seriously though, why would you ever need dual core phones? I understand it's the next logical step, but I don't plan on bit torrenting HD porn from my phone. The original Galaxy still seems plenty new and amazing enough for me to not care about another phone for at least a year.
Click to expand...
Click to collapse
Someone posted this elsewhere yesterday and those were my exact thoughts on it. I mean I get it but is that something necessary (if it were actually true) for the near future? We haven't even hit 6 months with this beast yet.
Sexy Vibrant featuring Sombionix 1.9.1, JAC's OC/UV, FFC installed
bdveteran18 said:
Someone posted this elsewhere yesterday and those were my exact thoughts on it. I mean I get it but is that something necessary (if it were actually true) for the near future? We haven't even hit 6 months with this beast yet.
Sexy Vibrant featuring Sombionix 1.9.1, JAC's OC/UV, FFC installed
Click to expand...
Click to collapse
You can't never have too much speed on a phone. Flash contents need quite a bit of CPU and GPU power, emulators will benefit from this, Browsing Speed, Multitasking, etc.
It can't hurt to have the phone boot up faster either.
OMG this again....dud research its beeen posted few down from you......
its fake this rumor started July 5 and people are just blogging...ect of late for attention or they have been living under a rock last few months
Also you would think with these guys bringing up such an old rumor/news they would have something else to go on other than repeating what already been said almost 4 months prior.
You guys really think specs for a new galaxy S would "leak" just few weeks after its predecessor's release...just my opinion
I'd have to agree with the quote in the op though. Instead of doubling the specs, phone manufacturers should work on increasing battery life. The iphone doesn't have ridiculous specs but still manages to do nearly everything android phones do and do it smoother while still lasting a full day.
I don't really need my phone to do much more than it currently does. It matches the iphone in 3d smoothness which is great.. Now I just need it to open and close apps smoother and last a full day. The g2 does it with less ghz, so it should be possible with the vibrants current 1ghz processor.
Sent from my SGH-T959 using XDA App
allthrottle said:
I'd have to agree with the quote in the op though. Instead of doubling the specs, phone manufacturers should work on increasing battery life. The iphone doesn't have ridiculous specs but still manages to do nearly everything android phones do and do it smoother while still lasting a full day.
I don't really need my phone to do much more than it currently does. It matches the iphone in 3d smoothness which is great.. Now I just need it to open and close apps smoother and last a full day. The g2 does it with less ghz, so it should be possible with the vibrants current 1ghz processor.
Sent from my SGH-T959 using XDA App
Click to expand...
Click to collapse
G2 does it with less mhz/ghz is because it is on a 45 nm fabrication vs. vibrant's 65 nm fabrication. The smaller the more efficient.
PaiPiePia said:
G2 does it with less mhz/ghz is because it is on a 45 nm fabrication vs. vibrant's 65 nm fabrication. The smaller the more efficient.
Click to expand...
Click to collapse
The Hummingbird is 45nm also
http://pdadb.net/index.php?m=cpu&id=a10010&c=samsung_s5pc110
CPU probably handles 800mhz at a really low voltages and found it to be the sweet spot that also conserves battery life
And to answer why its faster well maybe its designed better, such as better cache and maybe some type of "hyper threading" technique....that would explain the extra pipelines on the scorpion ...raw speed isn't always everything
BTW this is all just a guess so dont hold me to this..i know PC's not so much this

Desire Z vs Galaxy S performance

I've just saw Galaxy S Antutu Benchmark screens that had 3900 score @ ~~1400MHz and I'm wondering why our device even if it's pretty similiar does score only 2900 ? It's a huge difference.
Even oldie like tuned Xperia X8 can score 2400 which isn't even ARMv7 and has 256MB RAM with older GPU.
I'm a bit disappointed by our ROMs, because there are many of them but none is perfect. ILWT seemed to me the best (and it is), but has lower score than ARHD, which needs swap and many improvements to work smoothly and it isn't still capable running games like GTA3, MC3, ICS can't run them too because phone just reboots (ICS is in beta stage so I'm not looking at stability yet, but that's bad ).
ILWT result in best performance as for GTA3, this game was running great.
Here's screen of SGS Antutu:
http://desmond.imageshack.us/Himg855/scaled.php?server=855&filename=1331989260894.jpg&res=medium
X8 (for reference, score is without sdcard): http://iv.pl/images/61942066283720320721.png
and our Desire Z's in this thread, which is highest
http://forum.xda-developers.com/showthread.php?t=1560772
Why devs won't focus on improving performance? schedulers, more oc values, governors isn't everything, why then SGS can get 2x more score in RAM if it has 512MB too. Overclocking in SGS by 100MHz steps improve score by ~200, and in Desire Z it looks like it's not working as good because I didn't noticed that BIG boost, just ~50pts. I know it's not that easy to develop, but we're alot behind with performance than SGS.
SGX540 is probably better GPU and there's other processor, but if stock software had 3000pts in SGS, and they(devs) managed it to improve by 1000pts our had 2600 and got improved by 300 only.
I try to be optimistic, as I respect all the work done by developers. Every software IMO is good for everyday usage, but well, by modding I though it could be bit better
I am just dropping my two cents here, but I think that the devs go by the thought that benchmarks are - as Microsoft put it - not relevant to real day-to-day use scenarios. A phone with awesome benchmarks (or a ROM such as ARHD) may act quite sluggishly and crappily in day-to-day usage without a ton of tweaks and stuff (like ARHD does).
So, you see... the mechanic tells you that you can get 300km/h in your new Toyota, but at 160km/h the wind is screeching in the inside of the car so loud that you would *not* want it to go to 300/h.
I hope you understand my analogy. The point is - take benchmark results with a grain of salt.
I know what you mean, also saw people talking about desire z being smoother than sgs in stock config, but also there's something that sgs devs did if scores went over 25% higher
As far as I know:
benchmark =! reality
And the desire Z is worse than sgs, the gpu is worse, don't know about cpu, the ram may be different not only from how much it is (even if I've seen they're both ddr1)
Apart from this I'm not saying that we'd better have not more than 10 roms and more devs trying to add something very new to the phone. We've many ICS roms, many cyano roms, many sense 3.5 roms, many ics sense roms, many miui roms. I'd rather have two of each group and ie usb host or something a bit trickier... I mean, with all the respect possible for developers of every kind, hacking is becoming not hacking anymore, I mean everyone can with a bit of knowledge make his own rom (I remember of people under fifteen...). But hacking, imo, is when siul, OdienManSam, taz were trying to port ICS, all the work that many here are doing making things work in ics (Flinny, blk_jack), what on One X forums people are trying to do to gain S-OFF, when OdienManSam was trying to port usb host (will never know if he succeded)... I think there's much more juice to squeeze from our phones, less people willing to do it...
I'm not deplorating devs works, just my opinion...
If it means anything:
{
"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"
}
I'd say that it's pretty close to what the SGS performed in the benchmark (considering I was actually playing music whilst testing). Regardless, benchmarks are indeed far from everyday use scenarios.
Andromadus @ 1.2GHz. As the dude above me states, our device really doesn't score that much lower all things considered.
Sent from my HTC Vision using xda premium
Mine is at 3400, too with Andromadus ICS ROM @1,2GHz. And tested up to 1,6GHz running stable. So I have some reserves if I like, but it´s smooth enough at 1,2GHz, so why bother?
Mike

Sony Xperia Z2 pips HTC One (M8) for benchmark crown

Sony Xperia Z2 displaced the One (M8) at the Basemark OS II bench.
The two scored identical in the CPU and GPU test, but faster memory performance helped the Sony smartphone reach the top spot.
The Xperia Z2 is currently third in the gaming benchmark, but an update could push it forward – after all the M8 and Z2 use the same chipset and display resolution.
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
Source GSM Arena
meyourchum said:
Sony Xperia Z2 displaced the One (M8) at the Basemark OS II bench.
The two scored identical in the CPU and GPU test, but faster memory performance helped the Sony smartphone reach the top spot.
The Xperia Z2 is currently third in the gaming benchmark, but an update could push it forward – after all the M8 and Z2 use the same chipset and display resolution.
Source GSM Arena
Click to expand...
Click to collapse
I love the look of the back of the htc one (and m8) but its that bloody huge bottom bezel/htc logo area that for me is an eye-sore. It almost looks like it's got three bezels! I want a nice symmetrical front face to my phones, with thin side bezels. Hence my excitement at the z2, now that it's fixed the flaws of the z1. Barring any disasters rearing their heads when it gets reviewed, Sony is onto a winner here.
Well as far as benchmarks are concerned, I think the S5 might overtake them all as it's running at a slightly higher clockspeed of 2.5Ghz. Even the M8 Asian version is running at 2.5Ghz.
Having a higher battery.. it makes me wonder why Sony decided to go for 2.3Ghz instead. I feel it could be the cheaper batch of CPUs with low speed yields..
MasK said:
Well as far as benchmarks are concerned, I think the S5 might overtake them all as it's running at a slightly higher clockspeed of 2.5Ghz. Even the M8 Asian version is running at 2.5Ghz.
Having a higher battery.. it makes me wonder why Sony decided to go for 2.3Ghz instead. I feel it could be the cheaper batch of CPUs with low speed yields..
Click to expand...
Click to collapse
Cheaper batch of CPUs? No, the processor in all the 3 phones is the same. (Snapdragon 801)
Being a computer engineer it is my opinion that the practical differences between the same processor clocked at 2.3 GHz and 2.5 GHz will be little to none. Sure, the benchmarks would show a slight difference but during actual use? Nopes. However, the extra 1 GB of RAM can make a fair amount of difference in practical usage especially if you run memory intensive apps and games.
g4rvd4 said:
Cheaper batch of CPUs? No, the processor in all the 3 phones is the same. (Snapdragon 801)
Being a computer engineer it is my opinion that the practical differences between the same processor clocked at 2.3 GHz and 2.5 GHz will be little to none. Sure, the benchmarks would show a slight difference but during actual use? Nopes. However, the extra 1 GB of RAM can make a fair amount of difference in practical usage especially if you run memory intensive apps and games.
Click to expand...
Click to collapse
Well, the chip binning is different, and that will constitute to different prices.
8974-AB vs 8974-AC. It's physically sold as a different part number.
http://en.wikipedia.org/wiki/Snapdragon_(system_on_chip)
But sure.. in real life, the differences will be close to none. I'm thinking Sony added the extra 1GB RAM for 4K video and timeShift video.
IMO the hardware wars are coming to an end soon with cell phones and they will become appliances. This is generally considered to be the point where performance capabilities are no longer an issue and design, styling, and features become the selling points. The OEMs know it and outside of the ability to monetize proprietary software they are trying to capture buyers with it because the hardware itself wont be the thing they are selling in the not too distant future.
I have an N5, it has no lag and is completely fluid everywhere. Everything opens instantaneously unless it involves network connection speed. I do recognize there are people who game that will leverage further hardware advances but for me the future is already here, I don't care which processor the Z2 has because phones are flat getting kick ass on the upper end and I know it will make no difference as I click about the GUI.

benchmarks

http://browser.primatelabs.com/geekbench3/search?dir=desc&q=Sony+SGP771&sort=multicore_score
I have to say i am very impressed!!!
This is mine!
{
"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"
}
Iviato dal mio Sony Z4 Tablet utilizzando Tapatalk
kutulu32 said:
http://browser.primatelabs.com/geekbench3/search?dir=desc&q=Sony+SGP771&sort=multicore_score
I have to say i am very impressed!!!
Click to expand...
Click to collapse
So much for better thermal capabilities of a tablet. Apparently the Snapdragon 810 throttles as much as ever, despite the more space offered by the tablet.
Here's M9's scores by comparison: http://browser.primatelabs.com/geekbench3/search?dir=desc&q=htc+one+m9&sort=score
And exynos' (doesn't throttle): http://browser.primatelabs.com/geekbench3/search?dir=desc&q=+SM-G920S&sort=multicore_score
....in one word, disappointing.
BTW SD810 was/is supposed to perform (almost) the same as exynos 7420 when it doesn't throttle. Hoped that this tablet would too, well it doesn't (it throttles) so it is a pass for me :/
It's a shame if it in fact throttles despite being a tablet and the new revision of the chip but it will not affect normal usage and should not be a problem.
Skickat från min LG-V500 via Tapatalk
The processor shouldn't get throttled in this tablet as it's inside a larger shell and should be able to disperse heat a lot better than inside a phone.
Sent from my SGP612 using Tapatalk
Sent from my SGP712 using Tapatalk
Stevethegreat said:
So much for better thermal capabilities of a tablet. Apparently the Snapdragon 810 throttles as much as ever, despite the more space offered by the tablet.
Here's M9's scores by comparison: http://browser.primatelabs.com/geekbench3/search?dir=desc&q=htc+one+m9&sort=score
And exynos' (doesn't throttle): http://browser.primatelabs.com/geekbench3/search?dir=desc&q=+SM-G920S&sort=multicore_score
....in one word, disappointing.
BTW SD810 was/is supposed to perform (almost) the same as exynos 7420 when it doesn't throttle. Hoped that this tablet would too, well it doesn't (it throttles) so it is a pass for me :/
Click to expand...
Click to collapse
Even mi note pro throttles i know but nevertheless even with throttling the specs are nice.
My lg gflex 2 also throttles but with the right tweaking gaming performance is perfect.i think this tablet is very good for gaming. As for the comparisom between 810 and exynos (s6) nobody said that 810 is better.
kutulu32 said:
Even mi note pro throttles i know but nevertheless even with throttling the specs are nice.
My lg gflex 2 also throttles but with the right tweaking gaming performance is perfect.i think this tablet is very good for gaming. As for the comparisom between 810 and exynos (s6) nobody said that 810 is better.
Click to expand...
Click to collapse
Yeah but they should had been equal (given their specs) if it was not for throttling. I just can't see why a tablet should throttle at all. Maybe it's bad design from Sony's part. For example nexus 9 doesn't throttle despite the fact that Tegra K1 has a greater TDP than Snapdragon 810. I mean SD810 has a relatively low TDP, it should not throttle on tablets, period...
Stevethegreat said:
I just can't see why a tablet should throttle at all.
Click to expand...
Click to collapse
The reason it throttles is likely because excessive power dissipation, even if it doesn't cause heating problems can still degrade the battery life. So Sony has possibly and wisely chosen this strategy so you and I can have close to 20 hours of running time. I am sure if you run exynos at full clock rate the battery life will be horrible too. So I guess if you want long battery life that is the price you pay.
Keep I mind that the maximum performance is still there to utilize if you need it once in a while, just not continually, which is consistent with most real life use scenarios . 99% of users don't see any significant impact on their user experience.
najoor said:
The reason it throttles is likely because excessive power dissipation, even if it doesn't cause heating problems can still degrade the battery life. So Sony has possibly and wisely chosen this strategy so you and I can have close to 20 hours of running time. I am sure if you run exynos at full clock rate the battery life will be horrible too. So I guess if you want long battery life that is the price you pay.
Keep I mind that the maximum performance is still there to utilize if you need it once in a while, just not continually, which is consistent with most real life use scenarios . 99% of users don't see any significant impact on their user experience.
Click to expand...
Click to collapse
Depends on what you do. On multi window situations 20% more sustained performance can be a godsend, the difference between a leggy and a fluid experience. On my Samsung Tab's multiwindow low performance is always an issue and only Exynos 7420 / Snap 810 may solve it.
Now I understand that Xperia Tab is not that (no multiwindow), but I was thinking to install Linux arm and use it as my net book (in conjuction with the keyboard dock) as well as my tablet. Now I'm having second thoughts. I know I'm a minority in my needs from a tablet but I think a tablet SoC should behave differently than its phone counterpart. More potentialities in tablets.
I would think that next to stamina mode , a performance mode (existing only in Xperia tabs) would be welcomed. Sure battery would suffer but even 6-7 hours of laptop use is great for what it is. It would be like having a "laptop mode" (where one can use the full potential of the SoC) and a tablet mode (as it is today). I don't like constraints it is all...
BTW exynos 7420 throttles significantly less even after sustained usage (15-30 minutes). It still throttles but nowhere near SD810 levels, there is a gulf between them making Exynos to seem the significantly faster (even tough it isn't in raw numbers). Here's hoping Tab S2 would be using the 7420 (and not any older model), still I prefer Sony, xperia's weight and aspect ratio. For someone like me, this tablet represents a lost chance all because of throttling :/
Do we know which 810 version gives those numbers?
There is a word out there that there is a newer version of the SD810 that had the overheating problem solved. Looks like it is not very wide spread yet though, and many early batches still have the old version.
So, we need to know if there is a difference in throttling between both version or not. After all those who plan to get the devices will buy it with the new version most probably.
Anyone knows how to know which processor version the tablet has?
Has anyone tested the SD 815 USA version of the z4?
6thfloor said:
Has anyone tested the SD 815 USA version of the z4?
Click to expand...
Click to collapse
Couldn't find anything on that. Afaik there is/won't be no US model of the Z4T. And afaik the Snapdragon 815 doesn't exist.

One "BIG" A57 core always active?

Hi,
Been monitoring battery performance and CPU sleep states, and one thing I notice is that on my device the A53's spent a surprising amount of time at 1Ghz+ when the screen is on, and one of the A57 cores is always running a 384 when the device is idle, while the other 3 sleep. Is this Sony's attempt to keep the UI snappy? Having the A57 on all the time (screen on), even at that low frequency is going to use in the region of 100mW+ (which is about 4x that of each A53 core)
Can someone else sanity check my results?
I'm using perfmon, systempanel, and "floating monitors"
Perfmon can be found here: http://forum.xda-developers.com/showthread.php?t=1933284
It's also on the market for the price of a coffee, please consider buying it - great tool!
Yep sounds about right this Greek review:
https://translate.google.co.uk/tran.../2015/10/24/sony-xperia-z5-review/&edit-text=
Found that in most cases only one A57 core runs in the Z5.
{
"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"
}
Pardon my ignorance but...how much worse do you think it is to run only the big cores and throttle them from 2Ghz to 300Mhz without turning ON and switching to the little ones? (In other words...disable the big little technology and just use the best 4 cores).
We're now using the little cores more than the big ones....and that 1.5Ghz cap could be the reason of a lot of stutters.
Changing the topic, now that Google is selling Nexus devices (5X and 6P) with big little. I think they will improve this ARM technology in future Android versions (including the kernel).
Sent from my E5823
thesebastian said:
Pardon my ignorance but...how much worse do you think it is to run only the big cores and throttle them from 2Ghz to 300Mhz without turning ON and switching to the little ones? (In other words...disable the big little technology and just use the best 4 cores).
We're now using the little cores more than the big ones....and that 1.5Ghz cap could be the reason of a lot of stutters.
Changing the topic, now that Google is selling Nexus devices (5X and 6P) with big little. I think they will improve this ARM technology in future Android versions (including the kernel).
Sent from my E5823
Click to expand...
Click to collapse
The little cores will be perfectly fine for most daily mundane tasks, such as checking emails, messaging etc. The stutters you mention probably is because the phone launched just before Marshmallow and Sony are focusing more on that OS, same kind of thing with the camera. The current camera app is just a placeholder for the proper app due for release in a week or two.
thesebastian said:
Pardon my ignorance but...how much worse do you think it is to run only the big cores and throttle them from 2Ghz to 300Mhz without turning ON and switching to the little ones? (In other words...disable the big little technology and just use the best 4 cores).
We're now using the little cores more than the big ones....and that 1.5Ghz cap could be the reason of a lot of stutters.
Changing the topic, now that Google is selling Nexus devices (5X and 6P) with big little. I think they will improve this ARM technology in future Android versions (including the kernel).
Sent from my E5823
Click to expand...
Click to collapse
In short, no. The little cores, whilst relative to the A57's are weak, they are by no means underpowered for running the UI and such. Do consider that the A53 core is faster than the A9 cores that powered previous flagships such as the Galaxy S3. Leaving one of the A57's ticking in the background is probably not such a bad idea having thought about it, as it allows fast handover when the high performance is required; I do however hypothesise that some of the stuttering might be due to threads being handed over to the A57, whilst it is running down at 384, which will be somewhat slower than the high frequency A53 core(s) the process is being passed from. It may be that we see a touch-boost or more aggressive CPU governor brought in to rectify this.
On a related note, there is a good article on the power-aware BIG.little implementation in the Snapdragon 810 here:
http://www.anandtech.com/show/8933/snapdragon-810-performance-preview/4
Definitely for performance.
If they weren't set is this fashion the UI would feel sluggish and sluggish on wake up.
Your findings sound perfectly normal/adequate, resemble a "interactive" CPU governor.

Categories

Resources