PDA

View Full Version : bow to the new king!!! benchmarking inside note 3 takes all octo core can use all 8




skratch77
Sep 11, 2013, 05:22 PM
I know many will say who cares but the geeks in us want to brag about benchmarks and even the apple folks like braging when there soc scores higher.

We have some benchmarks coming in from the s800 note 3 and so far it the fastest cell out! Can't wait to compare it with the octo core exynos evolved version to see how the krait compared to the true pure bread a15s in the exynos version.


http://blog.gsmarena.com/the-first-benchmarks-scores-of-samsung-galaxy-note-3-are-in/

Ohh goshh Samsung just confirms the octo core can use all 8 cores at once in the new exynos evolved soc in the note 3


http://m.androidauthority.com/samsung-releases-octa-pella-video-show-new-exynos-5-octa-can-use-eight-cores-simultaneously-267316/

http://www.youtube.com/watch?v=fLrSTJECVaU



MacRumorUser
Sep 11, 2013, 05:23 PM
Stop making me want this phone when I really don't need it... :)

Skika
Sep 11, 2013, 05:24 PM
Is it 64 bit though

MacDawg
Sep 11, 2013, 05:24 PM
Can't wait to compare it with the octo core exynos evolved version to see how the krait compared to the true pure bread a15s in the exynos version.

I'm proud to say that I have no idea what this sentence even means :)

skratch77
Sep 11, 2013, 05:26 PM
Is it 64 bit though

What good is 64 bit when it has 4 cores running at 2.3 GHz!

----------

I'm proud to say that I have no idea what this sentence even means :)

Haha the 3g version of the phone has Samsung's exynos chip that uses faster CPUs and supposed better gpu

Skika
Sep 11, 2013, 05:27 PM
What good is 64 bit when it has 4 cores running at 2.3 GHz!

yeey more cores, more ghz!

True inuvashion!

skratch77
Sep 11, 2013, 05:28 PM
Stop making me want this phone when I really don't need it... :)

I'm trying to pre order it on Verizon but the site is overloaded and it won't even let me sign in.

They say shipped by 10/10 and its 299 for the 32gb version with a 2 year!

blackhand1001
Sep 11, 2013, 05:31 PM
Is it 64 bit though

Does the iPhone need to address more than 4gb of ram. No? Than 64 bit is a giant waste.

F123D
Sep 11, 2013, 05:34 PM
That LG G2 is pretty impressive.

skratch77
Sep 11, 2013, 05:35 PM
Does the iPhone need to address more than 4gb of ram. No? Than 64 bit is a giant waste.

Talk about fragmentation too! Apple just fragmented there Eco system way worse then android has ever been.

Now devs will need to code for 32 and 64 but versions of Facebook and twitter!

mellofello
Sep 11, 2013, 05:45 PM
Wow in many tests it is 4x faster then note 2. I have had no complaints how quick my note 2 is so this should be amazingly fast. Face book is gonna fly on this bad boy.:D

bbeagle
Sep 11, 2013, 05:57 PM
What good is 64 bit when it has 4 cores running at 2.3 GHz!

Bragging about cores and GHz means absolutely nothing. It makes me laugh inside when people think these numbers mean anything.

If the chips inside were the same, then cores and GHz would be relevant, but they aren't, and thus the numbers really don't mean much, it's comparing apples and oranges.

For example, treat GHz (number of instructions a processor can execute per second) to RPM (number of revolutions per minute)... If one car can go 200RPM, and another can go 2000 RPM, the one going 2000 RPM is surely faster ?

Not at all. On could be a scooter with small wheels, and the other is a monster truck with huge wheels. The scooter's wheels are going 10x faster, but the distance travelled by the monster truck in the same time is greater, because the wheels take it further with less turns per minute.

Cores could be treated like number of wheels, and the chip is like the engine. All matter when put together, an numbers don't tell the whole story. The best we can do are benchmark scores.

skratch77
Sep 11, 2013, 06:03 PM
Bragging about cores and GHz means absolutely nothing. It makes me laugh inside when people think these numbers mean anything.

If the chips inside were the same, then cores and GHz would be relevant, but they aren't, and thus the numbers really don't mean much, it's comparing apples and oranges.

For example, treat GHz (number of instructions a processor can execute per second) to RPM (number of revolutions per minute)... If one car can go 200RPM, and another can go 2000 RPM, the one going 2000 RPM is surely faster ?

Not at all. On could be a scooter with small wheels, and the other is a monster truck with huge wheels. The scooter's wheels are going 10x faster, but the distance travelled by the monster truck in the same time is greater, because the wheels take it further with less turns per minute.

Cores could be treated like number of wheels, and the chip is like the engine. All matter when put together, an numbers don't tell the whole story. The best we can do are benchmark scores.

Thanks for the quicky and we all know exactly what cores mean and how the exynos soc uses pure arm a15 cores that clock for clock have about 15-20% instruction per clock improvement over the snap dragon krait a9/a15 hybrid

Tell that to a server farm running 64 CPU clusters using more cores for more raw power.

I would take a quad core snapdragon at 2.3ghz running 32bit over a dual core a7 64bit chip any day of the week.

The exynos octo core will also out perform its own snapdragon version and Samsung finally fixed it and it can now run all 8 cores at once!

So would you take an arm quad a15 quad a7 at 1.8ghz or a dual core a7 64 bit soc from apple?

Cnasty
Sep 11, 2013, 06:37 PM
But is it made out of gold????

http://www.killermovies.com/images/movies/golden_boy.jpg

scott craft
Sep 11, 2013, 07:34 PM
That LG G2 is pretty impressive.

Yes it is, I really want that phone.

Dr McKay
Sep 11, 2013, 07:38 PM
No way the Octo-Core will see Cyanogenmod, so I won't be getting it.

Applefan4
Sep 11, 2013, 07:50 PM
The real life usage speed is what matters most, not benchmarks. There are many "real life" usage comparisons on you tube that shows that iPhone 5 matches or outperforms droids that were released this year.

ChrisTX
Sep 11, 2013, 09:10 PM
Let's hope this phone doesn't suffer the same lag the GS4 does! I'm really considering this phone but can't have a laggy phone. :cool:

blackhand1001
Sep 11, 2013, 09:29 PM
The real life usage speed is what matters most, not benchmarks. There are many "real life" usage comparisons on you tube that shows that iPhone 5 matches or outperforms droids that were released this year.

No not really. Especially since iPhone uses really long drawn out animations to hide loading times. Go compare the moto x/droid maxx to the iPhone. Its not crazy specces but it just as smooth as the iPhone and loading times are much shorter.

watchthisspace
Sep 11, 2013, 09:45 PM
Now devs will need to code for 32 and 64 but versions of Facebook and twitter!

In the keynote, the guys who make Infinity Blade mentioned with Apple's tools, they were able to convert the game from 32bit to 64bit, in 2 hours. An only one dev did that task.

I don't think fragmentation will be an issue over 64bit.

Mr. Retrofire
Sep 11, 2013, 10:33 PM
For example, treat GHz (number of instructions a processor can execute per second)
That's the clock rate, not the number of instructions per second. A modern CPU core can execute many instructions in parallel.

Even the older PowerPC 604 processors (http://en.wikipedia.org/wiki/PowerPC_600#PowerPC_604) in old Macs could execute...
...up to six instructions every cycle

1 cycle = 1 clock cycle

technowar
Sep 11, 2013, 11:48 PM
Talk about fragmentation too! Apple just fragmented there Eco system way worse then android has ever been.

Now devs will need to code for 32 and 64 but versions of Facebook and twitter!

http://cdn.alltheragefaces.com/img/faces/large/misc-so-hardcore-l.png

appledes7
Sep 12, 2013, 12:49 AM
Does the iPhone need to address more than 4gb of ram. No? Than 64 bit is a giant waste.

Ya thinking ahead sure is a giant waste :cool:

In the keynote, the guys who make Infinity Blade mentioned with Apple's tools, they were able to convert the game from 32bit to 64bit, in 2 hours. An only one dev did that task.

I don't think fragmentation will be an issue over 64bit.

Thats good to hear. I expect Android will make the jump within the next couple of years too.

----------

Especially since iPhone uses really long drawn out animations to hide loading times.

You have no idea how real time GPU rendering works.

Carlanga
Sep 12, 2013, 01:03 AM
Talk about fragmentation too! Apple just fragmented there Eco system way worse then android has ever been.

Now devs will need to code for 32 and 64 but versions of Facebook and twitter!

64 bit iPhones can run 32 bit applications and apps can be upgraded to 64 rather easily according to the keynote. so there should be 0 fragmentation.


I like android tablets not so much android phones... While the Note is cool, it's just wayyy too big and I'm not a fan of man purses...

Apollo 13
Sep 12, 2013, 01:39 AM
of course it's going to look like it's 4x faster then the Note 2 when Samsung is programming the device to cheat in benchmarks. Will it really be 4x faster then the Note 2? NO it will not.

Dontazemebro
Sep 12, 2013, 02:01 AM
64 bit iPhones can run 32 bit applications and apps can be upgraded to 64 rather easily according to the keynote. so there should be 0 fragmentation.


I like android tablets not so much android phones... While the Note is cool, it's just wayyy too big and I'm not a fan of man purses...

Yea but what they fail to mention is that you still get zero benefit for recoding an app meant for a 32 bit system. Actually I believe it hamstrings the OS because then now you're dealing with nearly double the size but only half the data. Which could force other issues like bad battery performance since now you're asking the CPU to perform tasks that aren't even essential to the core operation of the OS

Don't get me wrong I applaud the 64 bit but it's really only a base for better content to come later. Now imagining what that content could be? That's the game changer right there.

throAU
Sep 12, 2013, 02:45 AM
Does it use 1% battery per minute to do basic web browsing like my HTC One does here?

----------

Yea but what they fail to mention is that you still get zero benefit for recoding an app meant for a 32 bit system. Actually I believe it hamstrings the OS because then now you're dealing with nearly double the size but only half the data.


Just... no.

Code size MAY increase slightly. 64 bit doesn't mean all the code is 2x the size. Data size will stay the same, and data is where the bulk of the memory consumption is.

however, it does mean that the CPU can process operands twice as large in a single clock cycle. so battery throughput may IMPROVE (assuming the app/OS is recompiled for 64 bit) as less clock cycles are needed to do the same work. thus, the chip can spend more time asleep.

Carlanga
Sep 12, 2013, 09:45 AM
Yea but what they fail to mention is that you still get zero benefit for recoding an app meant for a 32 bit system. Actually I believe it hamstrings the OS because then now you're dealing with nearly double the size but only half the data. Which could force other issues like bad battery performance since now you're asking the CPU to perform tasks that aren't even essential to the core operation of the OS

Don't get me wrong I applaud the 64 bit but it's really only a base for better content to come later. Now imagining what that content could be? That's the game changer right there.

I agree, this is just setting a foundation for whats to come.

jamezr
Sep 12, 2013, 09:53 AM
of course it's going to look like it's 4x faster then the Note 2 when Samsung is programming the device to cheat in benchmarks. Will it really be 4x faster then the Note 2? NO it will not.
really? You know this how?

jrswizzle
Sep 12, 2013, 11:09 AM
Thanks for the quicky and we all know exactly what cores mean and how the exynos soc uses pure arm a15 cores that clock for clock have about 15-20% instruction per clock improvement over the snap dragon krait a9/a15 hybrid

Tell that to a server farm running 64 CPU clusters using more cores for more raw power.

I would take a quad core snapdragon at 2.3ghz running 32bit over a dual core a7 64bit chip any day of the week.

The exynos octo core will also out perform its own snapdragon version and Samsung finally fixed it and it can now run all 8 cores at once!

So would you take an arm quad a15 quad a7 at 1.8ghz or a dual core a7 64 bit soc from apple?

Time will tell, but take a look at this thread posted by a member here - very good analysis of the A7, which in all likelihood is actually a quad-core chip.

http://forums.macrumors.com/showthread.php?t=1634100

blackhand1001
Sep 12, 2013, 12:41 PM
of course it's going to look like it's 4x faster then the Note 2 when Samsung is programming the device to cheat in benchmarks. Will it really be 4x faster then the Note 2? NO it will not.

No, the snapdragon 800 really is that far ahead.

skratch77
Sep 12, 2013, 12:51 PM
No, the snapdragon 800 really is that far ahead.

But its only 32bit!!!

nickchallis92
Sep 12, 2013, 05:31 PM
I only purchase 512-bit phones

SlCKB0Y
Sep 15, 2013, 03:36 AM
In the keynote, the guys who make Infinity Blade mentioned with Apple's tools, they were able to convert the game from 32bit to 64bit, in 2 hours. An only one dev did that task.


That's one app, with presumably full assistance from Apple and done by a very talented professional developer. What about the other 900,000 apps?

You know how many Android apps will need to be recompiled when Google makes the switch? Presumably only those which use NDK. For the rest (the vast majority) Google just needs to compile Dalvik to work on 64bit CPUs and the apps will automatically work.

----------

when Samsung is programming the device to cheat in benchmarks. Will it really be 4x faster then the Note 2? NO it will not.

How are they doing this and how do you know?

ReanimationN
Sep 15, 2013, 04:07 AM
How are they doing this and how do you know?

http://www.anandtech.com/show/7187/looking-at-cpugpu-benchmark-optimizations-galaxy-s-4

adder7712
Sep 15, 2013, 04:19 AM
Does it use 1% battery per minute to do basic web browsing like my HTC One does here?

----------




Just... no.

Code size MAY increase slightly. 64 bit doesn't mean all the code is 2x the size. Data size will stay the same, and data is where the bulk of the memory consumption is.

however, it does mean that the CPU can process operands twice as large in a single clock cycle. so battery throughput may IMPROVE (assuming the app/OS is recompiled for 64 bit) as less clock cycles are needed to do the same work. thus, the chip can spend more time asleep. Cue in the second 'bit' war.

Remember the 90's?

ReanimationN
Sep 15, 2013, 04:32 AM
Cue in the second 'bit' war.

Remember the 90's?

http://www.old-computers.com/museum/photos/nintendo_n64_2s.jpg > http://static.ddmcdn.com/gif/playstation-sonyps3.jpg

adder7712
Sep 15, 2013, 04:40 AM
I would respectfully disagree. :D

daneoni
Sep 15, 2013, 05:14 AM
I know many will say who cares but the geeks in us want to brag about benchmarks

What good is 64 bit when...

So which is it...care or don't care?

You can't pick and choose arguments as and when it suits you.

Technarchy
Sep 15, 2013, 07:31 AM
Image (http://www.old-computers.com/museum/photos/nintendo_n64_2s.jpg) > Image (http://static.ddmcdn.com/gif/playstation-sonyps3.jpg)

A good example. Out the gate "Super Mario World" world showed the potential and advantages of 64 bit processing over 32 bit consoles like the PSX and Sega Saturn.

Over the following couple of years the differences became more pronounced.

ReanimationN
Sep 15, 2013, 09:03 AM
I would respectfully disagree. :D
:D

Don't get me wrong, I loved the PS1 too, but the 64 had so many instant classics. ;)

The cartridge format really held back the N64 in some genres though, for example, the PS1 was the go-to console for RPGs.
A good example. Out the gate "Super Mario World" world showed the potential and advantages of 64 bit processing over 32 bit consoles like the PSX and Sega Saturn.

Over the following couple of years the differences became more pronounced.
I've still never had as much fun with a console as I did with the N64. It was so good for multiplayer games.

Klosefabrinio
Sep 15, 2013, 09:58 AM
if the octa core chip can use all of the 8 cores at once, it's obvious that it'd score higher. my personal experience says that snapdragon chips are better, A LOT BETTER!:)

skratch77
Sep 15, 2013, 10:07 AM
So which is it...care or don't care?

You can't pick and choose arguments as and when it suits you.

What good is 64 bit when your bottlenecking it with 2 threads and 1gb total system ram?

adder7712
Sep 15, 2013, 08:57 PM
Legitimate question.

Do phones really need a 64-bit processor?

TSE
Sep 15, 2013, 09:26 PM
And you need this processor in a phone, why??? To text??? To... call??? To... uh... web browse??? To... play Angry Birds??? Hm... yeah... that's right, you don't.

I'm sorry, but... I don't get it.

Kariya
Sep 15, 2013, 09:32 PM
Legitimate question.

Do phones really need a 64-bit processor?

Not really a legitimate question. Its like asking if phones need a 1080p screen on a 5" or lower display, or if phones need 4 cores or 8 cores.

There was a time people wondered if we needed more than 512MB of RAM in a computer.

If people listened to those who asked/are asking these questions then we'd still be in the dark ages of technology.

The OP brags about a phone having 8 cores then turns and question what usefulness 64-bit architecture brings to mobile. I'm sorry but...what? He even goes on to dismiss it without knowing the full details of the A7 chip. Come on.

Bet if Android was the first out of the gate with the technology he wouldn't bother questioning it.

linkgx1
Sep 15, 2013, 09:38 PM
Image (http://www.old-computers.com/museum/photos/nintendo_n64_2s.jpg) > Image (http://static.ddmcdn.com/gif/playstation-sonyps3.jpg)

There's nothing new under the sun?:confused:

Bilalo
Sep 15, 2013, 09:57 PM
Talk about fragmentation too! Apple just fragmented there Eco system way worse then android has ever been.

Now devs will need to code for 32 and 64 but versions of Facebook and twitter!

Apple said that apps are backwards compatible and will only take a few hours to become 64 bit alone. Then both will be supported depending on ios device. And 64 bit isn't only about ram, for someone talking like a geek as u said u should know better and appreciate rather than mock because your a samsung fan...

throAU
Sep 16, 2013, 12:15 AM
Legitimate question.

Do phones really need a 64-bit processor?

Probably not.

however, again... as per my previous post, if it means they can process operands twice as large in one clock cycle, they can maybe be clocked lower or sleep more, which could potentially save power.

64 bit CPUs also tend to come with other features, so it may not just be the 64 bit-ness that the phone OEMs are switching to 64 bit CPUs for.

with vector instructions commonplace in modern CPUs the whole bit-ness thing of the CPU is a little bit ambiguous now anyway. is it in refernce to the address size, the internal word size, the vector instruction operand size, etc?


And with regards to the N64... classic example of this ambiguity: the bus size on the N64's CPU is 32 bits. Whilst a Pentium onwards for example has a 64 bit bus.

So whilst the N64 was called "64 bit" and the Pentium 3 was called "32 bit", the Pentium 3 could actually crunch through data quicker than the N64. The Pentium 3 also had 128 bit vector processing instructions (SSE), so maybe when comparing to the N64 it should be counted as 128 bit? :)

jrswizzle
Sep 19, 2013, 04:19 PM
Thanks for the quicky and we all know exactly what cores mean and how the exynos soc uses pure arm a15 cores that clock for clock have about 15-20% instruction per clock improvement over the snap dragon krait a9/a15 hybrid

Tell that to a server farm running 64 CPU clusters using more cores for more raw power.

I would take a quad core snapdragon at 2.3ghz running 32bit over a dual core a7 64bit chip any day of the week.

The exynos octo core will also out perform its own snapdragon version and Samsung finally fixed it and it can now run all 8 cores at once!

So would you take an arm quad a15 quad a7 at 1.8ghz or a dual core a7 64 bit soc from apple?

Are you sure?

http://www.anandtech.com/show/7335/the-iphone-5s-review

5S A7 is a DUAL CORE chip that beats the G2's Snapdragon 800 and HANDILY beats the GS4 (at least my US version) in Geekbench 3.

Hey - if these idiotic benchmark wars are going to continue, I might as well brag when my side wins. ESPECIALLY when they do it with an INFERIOR DUAL CORE chip.

Lol.....you just got :apple:learned.

skratch77
Sep 19, 2013, 07:16 PM
Are you sure?

http://www.anandtech.com/show/7335/the-iphone-5s-review

5S A7 is a DUAL CORE chip that beats the G2's Snapdragon 800 and HANDILY beats the GS4 (at least my US version) in Geekbench 3.

Hey - if these idiotic benchmark wars are going to continue, I might as well brag when my side wins. ESPECIALLY when they do it with an INFERIOR DUAL CORE chip.

Lol.....you just got :apple:learned.

I don't have time to read the review but the gs4 and lg g2 are not on 4.3 so no open gl 3.0 support and the benchmark I think the dual core chip you are talking about is a gpu bench not a cpu bench

wait for official note 3 benchmarks to come out before you get super excited that your side is winning!

ps the note 3 already has a leaked gpu Egypt bench out gunning the a7 by 12fps in the off screen run

sunspider is a java benchmark and not a cpu bench mark also and my old nexus with an a9 dual core chip out scores my gs4 because its using a better java engine

sviato
Sep 19, 2013, 07:20 PM
8 cores? Maybe now Android won't stutter when swiping through home screen pages ;)

jrswizzle
Sep 19, 2013, 07:42 PM
I don't have time to read the review but the gs4 and lg g2 are not on 4.3 so no open gl 3.0 support and the benchmark I think the dual core chip you are talking about is a gpu bench not a cpu bench

wait for official note 3 benchmarks to come out before you get super excited that your side is winning!

ps the note 3 already has a leaked gpu Egypt bench out gunning the a7 by 12fps in the off screen run

sunspider is a java benchmark and not a cpu bench mark also and my old nexus with an a9 dual core chip out scores my gs4 because its using a better java engine

If you can't be bothered to read it, don't post about things you don't know.

imaginex20
Sep 20, 2013, 01:29 AM
if most modern day PC's can't even take advantage of 8 cores what makes you think a phone will? Most apps besides photo/video apps can't/don't even take advantage of multiple core processors. Obviously the OP doesn't know much about specs when he has to compare cores to ram and threads vs 32/64 bit.

unobtainium
Sep 21, 2013, 02:57 AM
I don't have time to read the review

Anandtech does an amazing in-depth analysis of the A7 SoC. If you haven't read it yet, you should.

ChrisTX
Sep 21, 2013, 06:18 AM
I don't have time to read the review but the gs4 and lg g2 are not on 4.3 so no open gl 3.0 support and the benchmark I think the dual core chip you are talking about is a gpu bench not a cpu bench

wait for official note 3 benchmarks to come out before you get super excited that your side is winning!

ps the note 3 already has a leaked gpu Egypt bench out gunning the a7 by 12fps in the off screen run

sunspider is a java benchmark and not a cpu bench mark also and my old nexus with an a9 dual core chip out scores my gs4 because its using a better java engine

According to Gizmofo, the iPhone 5S A7 handily runs laps around even the Samsung Exynos Octa. Android fans wanna brag about specs, until the iPhone wins. Then all of the sudden, "Specs don't matter".

bobenhaus
Sep 21, 2013, 01:02 PM
Is it 64 bit though

Does it really matter?? Most apps need to be optimized and there is not much in performance except for handling more memory. BTW Samsung made the new A7 CPU for Apple. So don't really know what you meant by 64bit??

----------

According to Gizmofo, the iPhone 5S A7 handily runs laps around even the Samsung Exynos Octa. Android fans wanna brag about specs, until the iPhone wins. Then all of the sudden, "Specs don't matter".

Yeah everyone should be praising Samsung for making the A7 for Apple :)

tbayrgs
Sep 21, 2013, 02:13 PM
Does it really matter?? Most apps need to be optimized and there is not much in performance except for handling more memory. BTW Samsung made the new A7 CPU for Apple. So don't really know what you meant by 64bit??

----------



Yeah everyone should be praising Samsung for making the A7 for Apple :)

Yes, Samsung manufactured it. Who do you think designed it? ;)

F123D
Sep 21, 2013, 06:22 PM
Yes, Samsung manufactured it. Who do you think designed it? ;)

Samsung's former chip designer that apple hired? :p

tbayrgs
Sep 21, 2013, 06:40 PM
Samsung's former chip designer that apple hired? :p

Touche!!

thunng8
Sep 21, 2013, 07:00 PM
Samsung's former chip designer that apple hired? :p

Samsung actually do not design their own CPU cores - so far their own SOCs integrate ARM based cores (ie. ARM A9 in the s2, s3 and Note 2 and A15 in the s4, note 3). Even then, at least for the vast Marjority of markets that have LTE coverage, they are using Qualcomm's wholly designed Snapdragon SOCs.

Not saying that might change in the future .. but that is how it is at the moment.

technowar
Sep 22, 2013, 02:02 AM
Does it really matter?? Most apps need to be optimized and there is not much in performance except for handling more memory. BTW Samsung made the new A7 CPU for Apple. So don't really know what you meant by 64bit??

Does Android supports quad/octo cores?

Technarchy
Sep 22, 2013, 02:26 AM
8 cores? Maybe now Android won't stutter when swiping through home screen pages ;)

A very simple thing, and even with all that horsepower under the hood my gs4 chokes too often when scrolling between home screens.

adder7712
Sep 22, 2013, 08:21 AM
Samsung actually do not design their own CPU cores - so far their own SOCs integrate ARM based cores (ie. ARM A9 in the s2, s3 and Note 2 and A15 in the s4, note 3). Even then, at least for the vast Marjority of markets that have LTE coverage, they are using Qualcomm's wholly designed Snapdragon SOCs.

Not saying that might change in the future .. but that is how it is at the moment.

I've read they might move on to manufacturing and designing their own ARM-derived chips.

Dmaynard83
Sep 22, 2013, 10:03 AM
8 cores? Maybe now Android won't stutter when swiping through home screen pages ;)

Probably not. I feel like the lag is on the software side of things. Hopefully Kit Kat fixes it.

bobenhaus
Sep 22, 2013, 04:51 PM
Does Android supports quad/octo cores?

ummm yes. Samsung GS4 is comes either 4 or 8 core. The new MotoX is 8 core as well. ALso all the new ANdorids will be starting to rollout 8 cores. Dunno but Android is not late to the 8x party.

technowar
Sep 22, 2013, 11:55 PM
ummm yes. Samsung GS4 is comes either 4 or 8 core. The new MotoX is 8 core as well. ALso all the new ANdorids will be starting to rollout 8 cores. Dunno but Android is not late to the 8x party.

I think you misunderstood my question. Yes, the phone does support multi-core processors. But my question is, does Android supports it - and what I mean about Android is the OS.

jrswizzle
Sep 23, 2013, 04:16 PM
A very simple thing, and even with all that horsepower under the hood my gs4 chokes too often when scrolling between home screens.

Do you use NovaPrime?

I don't experience any stuttering on my GS4 and I'm running NovaPrime. At some point I'll get around to changing the god-awful icons....

----------

ummm yes. Samsung GS4 is comes either 4 or 8 core. The new MotoX is 8 core as well. ALso all the new ANdorids will be starting to rollout 8 cores. Dunno but Android is not late to the 8x party.

Uhh I thought the MotoX was a dual core phone?

http://www.motorola.com/us/FLEXR1-1/moto-x-specifications.html

"Architecture

Motorola X8 Mobile Computing System which includes a software optimized Qualcomm Snapdragon S4 Pro (1.7GHz Dual-Core Krait CPU, quad-core Adreno 320 GPU), a natural language processor and a contextual computing processor"

The anandtech review of the 5S actually mentions the MotoX as being an Android phone which does a great job at maximizing efficiency with two cores. It, along with the 5S, are proof that quad core (or even octa core) isn't better if the cores are crap.

thunng8
Oct 1, 2013, 09:01 AM
Samsung stoops to new lows with the benchmark cheating.

It is safe to say all results from the Note 3 can be disregarded.

arstechnica.com/gadgets/2013/10/galaxy-note-3s-benchmarking-adjustments-inflate-scores-by-up-to-20/

LSUtigers03
Oct 1, 2013, 09:40 AM
Probably not. I feel like the lag is on the software side of things. Hopefully Kit Kat fixes it.

In my experience it's more of a Touchwiz problem than an Android problem. My Moto X has a lowly dual core processor and never lags because it's pretty much stock Android. While my S4 would lag doing the simplest things. The HTC One and One Mini are also very smooth. Samsung really needs to overhaul Touchwiz. It looks terrible and it drags down even the most powerful processors.

adder7712
Oct 1, 2013, 11:54 AM
Samsung stoops to new lows with the benchmark cheating.

It is safe to say all results from the Note 3 can be disregarded.

arstechnica.com/gadgets/2013/10/galaxy-note-3s-benchmarking-adjustments-inflate-scores-by-up-to-20/

Still a fast phone regardless. Considering the G2 was swift and the actual scores are actually close to the G2.

ReallyBigFeet
Oct 1, 2013, 12:16 PM
But the question remains: why would Samsung deliberately take the time to spoof their code specifically to manipulate benchmarking scores? Is it possible that they realize how many consumers are gullible enough to believe that the "specs matter the most" message that they intentionally use this instead of bettering their products?

Why would you invest the time to do this unless you were being specifically manipulative in some way?

F123D
Oct 1, 2013, 12:36 PM
Still a fast phone regardless. Considering the G2 was swift and the actual scores are actually close to the G2.

The ironic thing is, even with the benchmark booster disabled, the Note 3 still comes out faster than the G2 in this test. If the intent behind the boosting was simply to ensure that the Note 3 came out ahead in the benchmark race, it doesn't appear to have been necessary in the first place.



___________________________




But the question remains: why would Samsung deliberately take the time to spoof their code specifically to manipulate benchmarking scores? Is it possible that they realize how many consumers are gullible enough to believe that the "specs matter the most" message that they intentionally use this instead of bettering their products?


Idk, to brag? Still pointless since no one buys a phone due to benchmark scores. Benchmarks aside, people can't honestly say the Note 3 isn't a better product than the Note 2.

ReallyBigFeet
Oct 1, 2013, 12:56 PM
Idk, to brag? Still pointless since no one buys a phone due to benchmark scores. Benchmarks aside, people can't honestly say the Note 3 isn't a better product than the Note 2.

I think there is a certain percentage of the population that buys SPECIFICALLY due to benchmarking scores and specs. Just like a certain percentage of the population buys gold-colored phones. But the fact remains I find it incredulous that Samsung would go so far as to change their code specifically JUST to manipulate these scores and, by default, this percentage of the population.

Unless, of course, the percentage is actually much higher than I believe it to be. In which case, it makes sense as manipulating the gullible is always a sound strategy.

MACis122
Oct 1, 2013, 01:11 PM
I'm doubtful of this as the GP edition of the GS4 and touchwiz version have pretty much the same benchmarks and perform almost identical.

ReallyBigFeet
Oct 1, 2013, 01:18 PM
I'm doubtful of this as the GP edition of the GS4 and touchwiz version have pretty much the same benchmarks and perform almost identical.

Disassembly of the Samsung firmware actually shows the coding tags Samsung put in place to detect benchmarking apps and crank up the CPU accordingly just for those. Not sure if this is at all impacted by Touchwiz....if I were coding it, I'd put it at the firmware level.

Peterg2
Oct 1, 2013, 01:30 PM
Samsung stoops to new lows with the benchmark cheating.

It is safe to say all results from the Note 3 can be disregarded.

arstechnica.com/gadgets/2013/10/galaxy-note-3s-benchmarking-adjustments-inflate-scores-by-up-to-20/

It is not just a Samsung issue. Others, including HTC, have been "gaming" the benchmarks.

I quote:

The Galaxy Note 3 is more or less the fastest Android smartphone we've tested up to this point. In the situations where we can do cross platform (OS/browser) comparisons, it isn't quite as fast as the iPhone 5s but in some cases it comes close. I should mention that the Note 3 (like many other Android devices - SGS4, HTC One) detects certain benchmarks and ensures CPU frequencies are running at max while running them, rather than relying on the benchmark workload to organically drive DVFS to those frequencies. Max supported CPU frequency is never exceeded in this process, the platform simply primes itself for running those tests as soon as they're detected. The impact is likely small since most of these tests should drive CPU frequencies to their max state regardless (at least on the CPU side), but I'm going to make it a point to call out this behavior whenever I see it from now on.

http://www.anandtech.com/show/7376/samsung-galaxy-note-3-review/4

charlesdayton
Oct 1, 2013, 02:01 PM
http://www.macrumors.com/2013/10/01/samsung-again-caught-inflating-benchmarking-scores-phil-schiller-calls-shenanigans/

user-name-here
Oct 1, 2013, 02:55 PM
But the question remains: why would Samsung deliberately take the time to spoof their code specifically to manipulate benchmarking scores? Is it possible that they realize how many consumers are gullible enough to believe that the "specs matter the most" message that they intentionally use this instead of bettering their products?

Why would you invest the time to do this unless you were being specifically manipulative in some way?

Because spec geeks are potential customers and, by nature of them looking at numbers instead of experience, can be quite gullible.

F123D
Oct 1, 2013, 05:29 PM
True. Like how some members on this forum were boasting that the new 5s was 40x faster than the previous iPhone.

http://cdn.cultofmac.com/wp-content/uploads/2013/09/i-Z34ss3K-M.jpg

adder7712
Oct 2, 2013, 02:28 AM
Disassembly of the Samsung firmware actually shows the coding tags Samsung put in place to detect benchmarking apps and crank up the CPU accordingly just for those. Not sure if this is at all impacted by Touchwiz....if I were coding it, I'd put it at the firmware level.

Games could benefit a lot from the boosted CPU mode.

ReallyBigFeet
Oct 2, 2013, 12:39 PM
Games could benefit a lot from the boosted CPU mode.

If the device makers would give us a "turbo" switch to turn on/off per app, I'd agree. But rather than focus this into a useful feature, they only chose to focus on benchmark spoofing. That's the question that still remains...why bother?

Anandtech has a good article on this front page today. Virtually all the major players EXCEPT Motorola and Apple appear to be doing this.

http://www.anandtech.com/show/7384/state-of-cheating-in-android-benchmarks

I guess we can pretty much throw out the "better specs" argument entirely at this point as almost all the ones are involved in spoofing the tests.

Assault
Oct 2, 2013, 03:31 PM
If the device makers would give us a "turbo" switch to turn on/off per app, I'd agree. But rather than focus this into a useful feature, they only chose to focus on benchmark spoofing. That's the question that still remains...why bother?

Anandtech has a good article on this front page today. Virtually all the major players EXCEPT Motorola and Apple appear to be doing this.

http://www.anandtech.com/show/7384/state-of-cheating-in-android-benchmarks

I guess we can pretty much throw out the "better specs" argument entirely at this point as almost all the ones are involved in spoofing the tests.

Does this really matter? I have yet to see any data that shows any phone "overclocking" to generate inaccurate data, but rather ramping up to max cpu freqs during these whitelisted benchmarks. Ironically, even Anandtech notes that other benchmark apps that are not explicitly mentioned in the code were behaving the exact same way as whitelisted apps.

So, is this called spoofing numbers or just giving max performance numbers? Because when playing a game like Dead Trigger, wouldn't you want to know what max numbers are for CPU,GPU and FPS, to let the user know the game will run smoothly? Who gives a crap about normal everyday benchmark numbers when you are using powerpoint, web surfing or reading an ebook?

Or does this all boil down to "my phone is better than yours, and if it isn't it is because you cheated on benchmark numbers"? This is just plain silly.

P.S. I'm not directing this at you 'reallybigfeet'. It's more of a rhetorical post to comment on this discussion as a whole. Your quote just happened to fit best with my comments. ;)

cynics
Oct 2, 2013, 04:07 PM
I don't know if I'd call that cheating or not. Is there a way or has someone figured out a way to disable its ability to prime itself then run the same benchmark?

Peterg2
Oct 2, 2013, 04:16 PM
I don't know if I'd call that cheating or not. Is there a way or has someone figured out a way to disable its ability to prime itself then run the same benchmark?

One benchmark has been revised to prevent this:

https://play.google.com/store/apps/details?id=com.pctvtv.android.ttsx