iPhone 6s was the most powerful smartphone of 2015 by a mile

This topic is locked from further discussion.

Avatar image for musicalmac
musicalmac

25098

Forum Posts

0

Wiki Points

0

Followers

Reviews: 15

User Lists: 1

#1  Edited By musicalmac  Moderator
Member since 2006 • 25098 Posts

A report brought to you by, yes, Cult of Android.

Powered by a dual-core A9 processor clocked at 1.85GHz and only 2GB of RAM, the iPhone 6s looks almost laughable compared to rivals like the Galaxy Note 5, which boasts an octa-core Exynos 7420 chip clocked at 2.1GHz, and 4GB of RAM.

Even 2014’s iPhone 6, which is powered by the older A8 processor and just 1GB of RAM, managed to earn a higher ranking than a number of flagship Androids from 2015, including the Nexus 6P, and the apparent “2016 flagship killer,” the OnePlus 2.

The iPhone 6 was an incredible value, because it's still keeping up with, or outpacing, the competition a year later. This is a significant performance gap.

Look at it, would you just look at it?

EDIT: Apple gets a lot of flak for pricing, but they're giving you a whole lot more performance bang for your buck than you're getting with android flagships. A lot more.

Avatar image for NVIDIATI
NVIDIATI

8463

Forum Posts

0

Wiki Points

0

Followers

Reviews: 0

User Lists: 0

#2 NVIDIATI
Member since 2010 • 8463 Posts

I would hope so, after the Snapdragon 820 was delayed, the A9 was the only major SoC launched in the second half of 2015.

I'm not very familiar with Antutu, but version 6 puts strong emphasis on single core performance, this would definitely bring up the scores of the A8 and A9 (and it does). This approach is strange, as Android (as tested) actually sees performance benefits from the increase in cores, where it's a different story for iOS. It can also be seen that the 2 core Tegra K1 (Denver) doubles in score to overtake the 3 core A8X.

The second place phone is from Huawei using an in-house chip (8 core). It's quite impressive to see them competing with the larger players so quickly.

All in all, Antutu doesn't appear to do a good job at comparing devices.

Avatar image for musicalmac
musicalmac

25098

Forum Posts

0

Wiki Points

0

Followers

Reviews: 15

User Lists: 1

#3 musicalmac  Moderator
Member since 2006 • 25098 Posts

@NVIDIATI: I'm not compelled to agree with your analysis, for a couple reasons.

  • AnandTech also cited, in very plain English, that the A9 is the best SoC in a phone today, and
  • Real-world usage tests have shown that Apple's devices tend to finish first by a significant margin

Apple is way, way ahead.

Avatar image for FireEmblem_Man
FireEmblem_Man

20248

Forum Posts

0

Wiki Points

0

Followers

Reviews: 7

User Lists: 0

#4 FireEmblem_Man
Member since 2004 • 20248 Posts

Don't care, why should we? Oh right, this is all about bragging rights

Avatar image for NVIDIATI
NVIDIATI

8463

Forum Posts

0

Wiki Points

0

Followers

Reviews: 0

User Lists: 0

#5 NVIDIATI
Member since 2010 • 8463 Posts

@musicalmac said:

@NVIDIATI: I'm not compelled to agree with your analysis, for a couple reasons.

  • AnandTech also cited, in very plain English, that the A9 is the best SoC in a phone today, and
  • Real-world usage tests have shown that Apple's devices tend to finish first by a significant margin

Apple is way, way ahead.

I don't understand what you're disagreeing with. Maybe you should re-read my post.

Avatar image for mister-man
Mister-Man

616

Forum Posts

0

Wiki Points

0

Followers

Reviews: 0

User Lists: 5

#6  Edited By Mister-Man
Member since 2014 • 616 Posts

@FireEmblem_Man: You should care, because the phone you say is over priced and inferior is actually destroying anything coming out of Microsoft and Googles asses, making them effectively look like... asses. All while staying fragmentation-free, streamlined and able to play nice with every single other iOS device.

Avatar image for musicalmac
musicalmac

25098

Forum Posts

0

Wiki Points

0

Followers

Reviews: 15

User Lists: 1

#7 musicalmac  Moderator
Member since 2006 • 25098 Posts

@NVIDIATI said:
@musicalmac said:

@NVIDIATI: I'm not compelled to agree with your analysis, for a couple reasons.

  • AnandTech also cited, in very plain English, that the A9 is the best SoC in a phone today, and
  • Real-world usage tests have shown that Apple's devices tend to finish first by a significant margin

Apple is way, way ahead.

I don't understand what you're disagreeing with. Maybe you should re-read my post.

It's pretty simple:

All in all, Antutu doesn't appear to do a good job at comparing devices.

I don't agree. For the reasons I stated above, and because Antutu is primarily an android phone website, yet they published an article that displayed just how far ahead Apple is in terms of SoC's.

Your reply is also curious because you start like this...

I would hope so, after the Snapdragon 820 was delayed, the A9 was the only major SoC launched in the second half of 2015.

...and then end by criticizing Antutu for their poor methods that place the A9 way ahead.

I will question the information if it appears questionable, but I don't see anything demanding that sort of skepticism right now.

(Side note: Apple is also going to annihilate the 820)

Avatar image for NVIDIATI
NVIDIATI

8463

Forum Posts

0

Wiki Points

0

Followers

Reviews: 0

User Lists: 0

#8  Edited By NVIDIATI
Member since 2010 • 8463 Posts
@musicalmac said:

It's pretty simple:

All in all, Antutu doesn't appear to do a good job at comparing devices.

I don't agree. For the reasons I stated above, and because Antutu is primarily an android phone website, yet they published an article that displayed just how far ahead Apple is in terms of SoC's.

Your reply is also curious because you start like this...

I would hope so, after the Snapdragon 820 was delayed, the A9 was the only major SoC launched in the second half of 2015.

...and then end by criticizing Antutu for their poor methods that place the A9 way ahead.

I will question the information if it appears questionable, but I don't see anything demanding that sort of skepticism right now.

You're right, it is pretty simple. Antutu v6 weighs single core performance above just about anything else. It also tests one of its two graphics benchmarks onscreen.

According to Antutu v6, Tegra K1 (2 Denver cores + Kepler GPU + LPDDR3 RAM + 28 nm process) outperforms Tegra X1 (4 Cortex A57 cores + 4 Cortex A53 cores + Maxwell GPU + LPDDR4 RAM + 20 nm process).

Tegra K1 Denver (in the Nexus 9 with a ~3.14 million pixel display): ~106,000

Tegra X1 (in the Pixel C with a ~4.6 million pixel display): ~92,000

Why is this the case? Because a single Denver core outperforms a single Cortex A57 core and the Pixel C has a higher resolution.

If it hasn't been clear by now, the fact remains that Tegra X1 is considerably more powerful than Tegra K1 Denver.

Again, it doesn't do a good job at comparing devices.

(Side note: Apple is also going to annihilate the 820)

I don't know what gave you that impression.

Avatar image for musicalmac
musicalmac

25098

Forum Posts

0

Wiki Points

0

Followers

Reviews: 15

User Lists: 1

#9 musicalmac  Moderator
Member since 2006 • 25098 Posts

@NVIDIATI said:

You're right, it is pretty simple. Antutu v6 weighs single core performance above just about anything else. It also tests one of its two graphics benchmarks onscreen.

According to Antutu v6, Tegra K1 (2 Denver cores + Kepler GPU + LPDDR3 RAM + 28 nm process) outperforms Tegra X1 (4 Cortex A57 cores + 4 Cortex A53 cores + Maxwell GPU + LPDDR4 RAM + 20 nm process).

Tegra K1 Denver (in the Nexus 9 with a ~3.14 million pixel display): ~106,000

Tegra X1 (in the Pixel C with a ~4.6 million pixel display): ~92,000

Why is this the case? Because a single Denver core outperforms a single Cortex A57 core and the Pixel C has a higher resolution.

If it hasn't been clear by now, the fact remains that Tegra X1 is considerably more powerful than Tegra K1 Denver.

Again, it doesn't do a good job at comparing devices.

(Side note: Apple is also going to annihilate the 820)

I don't know what gave you that impression.

I'm not compelled to change my mind because of a single example. Antutu has gone through many variations with their testing and has been fine tuning for a long time, relatively speaking (I looked it up, because I, too, was curious about who Antutu was).

And it was AnandTech who gave me the impression that the 820 wasn't going to be something to get too excited about.

Meanwhile more broadly speaking, our initial data doesn’t paint Snapdragon 820 as the SoC that is going to dethrone Apple’s commanding lead in ARM CPU performance.

Pretty simple. Note the 'commanding' in the AnandTech quote.

Avatar image for NVIDIATI
NVIDIATI

8463

Forum Posts

0

Wiki Points

0

Followers

Reviews: 0

User Lists: 0

#10  Edited By NVIDIATI
Member since 2010 • 8463 Posts
@musicalmac said:

I'm not compelled to change my mind because of a single example. Antutu has gone through many variations with their testing and has been fine tuning for a long time, relatively speaking (I looked it up, because I, too, was curious about who Antutu was).

And it was AnandTech who gave me the impression that the 820 wasn't going to be something to get too excited about.

Meanwhile more broadly speaking, our initial data doesn’t paint Snapdragon 820 as the SoC that is going to dethrone Apple’s commanding lead in ARM CPU performance.

Pretty simple. Note the 'commanding' in the AnandTech quote.

A single example that highlights a flaw in the benchmark. This isn't a glitch, this is just the way the scores are weighted. The focus on single core and onscreen performance doesn't offer the full picture. For that matter, the "new" benchmark doesn't even test graphics beyond OpenGL ES 3.0.

Later in the paragraph for the Anandtech link, they clearly outline how S820's Adreno 530 outperforms the A9's PVR 7XT GPU:

What seems to be rather concerning is the performance of existing software that isn't yet optimized for the new architecture, well have to see how targeted compilers for Kryo will be able to improve scores in that regard. The Adreno 530 on the other hand looks to to perform very well for a smartphone SoC, besting Apple's latest, and I think there’s a good chance for retail devices to hold their edge here.

Looking directly at CPU compute, only NVIDIA seems to be able to compete with Apple with regards to core for core ARMv8 performance. As for the Snapdragon, we'll see how things turn out as retail devices arrive. Early benchmarks of a LeEco (LeTV) Snapdragon 820 phone show higher scores than the development device, so that's rather promising.

Avatar image for musicalmac
musicalmac

25098

Forum Posts

0

Wiki Points

0

Followers

Reviews: 15

User Lists: 1

#11  Edited By musicalmac  Moderator
Member since 2006 • 25098 Posts

@NVIDIATI: So you think it's flawed, and this is why:

 3. New CPU Testing Added

 The employment of multi-core CPU caused the incompetent of actual using experience and hardware limiting performance. In view of this situation, Antutu V6.0 adjusts CPU testing items and adds several new one, based on practical use with more pratical meaning. Antutu found that in most cases, only one core is doing work and many applications are poorly supported by multip-core.We increase the proportion of single core test significantly. All these will make the testing results be more realistic.

Sketchy translation aside, their methodology and reasoning seems logical.

Avatar image for NVIDIATI
NVIDIATI

8463

Forum Posts

0

Wiki Points

0

Followers

Reviews: 0

User Lists: 0

#12 NVIDIATI
Member since 2010 • 8463 Posts
@musicalmac said:

@NVIDIATI: So you think it's flawed, and this is why:

 3. New CPU Testing Added

 The employment of multi-core CPU caused the incompetent of actual using experience and hardware limiting performance. In view of this situation, Antutu V6.0 adjusts CPU testing items and adds several new one, based on practical use with more pratical meaning. Antutu found that in most cases, only one core is doing work and many applications are poorly supported by multip-core.We increase the proportion of single core test significantly. All these will make the testing results be more realistic.

Sketchy translation aside, their methodology and reasoning seems logical.

That reasoning is flawed, which brings me back to my previous Anandtech reference:

While for Apple it can be argued that we're dealing with a very different operating system and it is likely iOS applications are less threaded than their Android counter-parts.

In the end what we should take away from this analysis is that Android devices can make much better use of multi-threading than initially expected. There's very solid evidence that not only are 4.4 big.LITTLE designs validated, but we also find practical benefits of using 8-core "little" designs over similar single-cluster 4-core SoCs.

Avatar image for musicalmac
musicalmac

25098

Forum Posts

0

Wiki Points

0

Followers

Reviews: 15

User Lists: 1

#13  Edited By musicalmac  Moderator
Member since 2006 • 25098 Posts

@NVIDIATI said:
@musicalmac said:

@NVIDIATI: So you think it's flawed, and this is why:

 3. New CPU Testing Added

 The employment of multi-core CPU caused the incompetent of actual using experience and hardware limiting performance. In view of this situation, Antutu V6.0 adjusts CPU testing items and adds several new one, based on practical use with more pratical meaning. Antutu found that in most cases, only one core is doing work and many applications are poorly supported by multip-core.We increase the proportion of single core test significantly. All these will make the testing results be more realistic.

Sketchy translation aside, their methodology and reasoning seems logical.

That reasoning is flawed, which brings me back to my previous Anandtech reference:

While for Apple it can be argued that we're dealing with a very different operating system and it is likely iOS applications are less threaded than their Android counter-parts.

In the end what we should take away from this analysis is that Android devices can make much better use of multi-threading than initially expected. There's very solid evidence that not only are 4.4 big.LITTLE designs validated, but we also find practical benefits of using 8-core "little" designs over similar single-cluster 4-core SoCs.

Right, you posted that before. It's obvious that developers aren't going to make apps that utilize 8 cores for iOS when Apple favors using just two. I'm not sure why that even needs to be said.

As far as all those cores go, it doesn't seem to help in real-world situations. While the linked test isn't entirely scientific, it does display a much better showing for Apple's iPhone. The iPhone came out way ahead of the 2nd place phones with 6 fewer cores and half the RAM.

Your quote from Anand says that those extra cores are valid designs, better than similar single-cluster 4-core designs. But it really doesn't mean anything in the context of this conversation, because they're not as well designed as the A9 ("On the SoC side, it’s pretty safe to say that the A9 SoC is the best SoC in any phone today." Anand). In fact, using Anand quotes to downplay the strength of Apple's A9 is downright foolish. Let's go back to the iPhone 6s/+ review:

On the SoC side, it’s pretty safe to say that the A9 SoC is the best SoC in any phone today. We can talk about the TSMC and Samsung controversy, but at the end of the day regardless of which one you end up with the performance is going to be far and away better than anything else we’ve seen thus far. There are a lot of reasons for this, but at the end of the all that really matters is that the phone delivers the best user experience in areas where GPU or CPU performance is a gating factor. Again, I keep coming back to web browsing but due to the nature of wasteful yet necessary abstraction that occurs in websites and web applications it’s incredibly important that a high-end phone starts to challenge 2-in-1 and passively-cooled laptops in burst performance for a good user experience.

While CPU and strong browser optimization is critical for good web browsing performance, GPU is the other half of the equation to this SoC, even if it isn’t necessarily used to the fullest extent. The reality is that a high end phone is going to be used for gaming by a lot of people, and at the high-end gaming performance really needs to be impressive. The iPhone 6s’ are going to do well at this. GFXBench isn’t the same thing as an actual game, but the fact that the iPhone 6s and 6s Plus are basically pegging T-Rex at the maximum possible frame rate for most of a 3-4 hour infinite run of this intense benchmark basically means that gaming on the iPhone is going to be the best possible experience due to its incredibly high unthrottled GPU performance and the length of time that it’s able to sustain that unthrottled GPU performance. No other SoC I've tested this year can sustain this level of performance for this level of time.

A speedtest that chooses not to reward extra cores makes sense to me.

EDIT: I chose to highlight a couple key points in Anand's review of the iPhone 6s/+. Both quotes point to best-in-class operation, backed up by Antutu's tests, as well as the end-user testing as seen in the TechRadar video.

Avatar image for NVIDIATI
NVIDIATI

8463

Forum Posts

0

Wiki Points

0

Followers

Reviews: 0

User Lists: 0

#14  Edited By NVIDIATI
Member since 2010 • 8463 Posts

@musicalmac said:

Right, you posted that before. It's obvious that developers aren't going to make apps that utilize 8 cores for iOS when Apple favors using just two. I'm not sure why that even needs to be said.

As far as all those cores go, it doesn't seem to help in real-world situations. While the linked test isn't entirely scientific, it does display a much better showing for Apple's iPhone. The iPhone came out way ahead of the 2nd place phones with 6 fewer cores and half the RAM.

Your quote from Anand says that those extra cores are valid designs, better than similar single-cluster 4-core designs. But it really doesn't mean anything in the context of this conversation, because they're not as well designed as the A9 ("On the SoC side, it’s pretty safe to say that the A9 SoC is the best SoC in any phone today." Anand). In fact, using Anand quotes to downplay the strength of Apple's A9 is downright foolish. Let's go back to the iPhone 6s/+ review:

On the SoC side, it’s pretty safe to say that the A9 SoC is the best SoC in any phone today. We can talk about the TSMC and Samsung controversy, but at the end of the day regardless of which one you end up with the performance is going to be far and away better than anything else we’ve seen thus far. There are a lot of reasons for this, but at the end of the all that really matters is that the phone delivers the best user experience in areas where GPU or CPU performance is a gating factor. Again, I keep coming back to web browsing but due to the nature of wasteful yet necessary abstraction that occurs in websites and web applications it’s incredibly important that a high-end phone starts to challenge 2-in-1 and passively-cooled laptops in burst performance for a good user experience.

While CPU and strong browser optimization is critical for good web browsing performance, GPU is the other half of the equation to this SoC, even if it isn’t necessarily used to the fullest extent. The reality is that a high end phone is going to be used for gaming by a lot of people, and at the high-end gaming performance really needs to be impressive. The iPhone 6s’ are going to do well at this. GFXBench isn’t the same thing as an actual game, but the fact that the iPhone 6s and 6s Plus are basically pegging T-Rex at the maximum possible frame rate for most of a 3-4 hour infinite run of this intense benchmark basically means that gaming on the iPhone is going to be the best possible experience due to its incredibly high unthrottled GPU performance and the length of time that it’s able to sustain that unthrottled GPU performance. No other SoC I've tested this year can sustain this level of performance for this level of time.

A speedtest that chooses not to reward extra cores makes sense to me.

EDIT: I chose to highlight a couple key points in Anand's review of the iPhone 6s/+. Both quotes point to best-in-class operation, backed up by Antutu's tests, as well as the end-user testing as seen in the TechRadar video.

I said it again, because it shows that a benchmark (in this case Antutu) needs to provide versatility for both platforms in order to provide a real comparison. The multi core use is valid as it actually makes a difference in real world Android performance (again, which is why I linked the article). Antutu doesn't provide that balance, by focusing on single core performance, they're ruling out a real world advantage on Android. This skews results even among Android SoC's as devices that have higher single core performance suddenly have a higher score than they should relative to other devices with more smaller cores. The use of onscreen 3D benchmark also makes a further mess of things as a 3D app (such as a game) doesn't have to be running at a device's native resolution.

There's nothing to downplay over the A9's performance, I don't know why you assumed that was the case. There also isn't a reason to try and boast about it at this time. It is powerful, but it also had no rival close to its time of launch. Everyone else is still sitting on a 20 nm process (with the exception of Samsung) with designs from the start of 2015.

From the Anandtech's Exynos 7420 deep dive:

Exynos 7420’s Mali T760MP8 combined with the 14nm process not only makes this the fastest SoC we’ve seen in a smartphone but also currently the most efficient one that we measured.

If we made the thread earlier in the year, it would have a different tone when Samsung surprised everyone with an SoC that not only beat out Qualcomm, but offered many new features not seen on Apple's A8 (only to be introduced almost half a year later in the A9).

I'm still waiting on more bite and less bark.

Avatar image for mister-man
Mister-Man

616

Forum Posts

0

Wiki Points

0

Followers

Reviews: 0

User Lists: 5

#15 Mister-Man
Member since 2014 • 616 Posts

When mounting evidence of real-world usage tests and data-packed benchmarks paint a clear picture of the iPhone being the best, but NVidiati hangs onto if/when scenarios to undermine the truth,

Avatar image for musicalmac
musicalmac

25098

Forum Posts

0

Wiki Points

0

Followers

Reviews: 15

User Lists: 1

#16 musicalmac  Moderator
Member since 2006 • 25098 Posts

@NVIDIATI said:

I said it again, because it shows that a benchmark (in this case Antutu) needs to provide versatility for both platforms in order to provide a real comparison. The multi core use is valid as it actually makes a difference in real world Android performance (again, which is why I linked the article). Antutu doesn't provide that balance, by focusing on single core performance, they're ruling out a real world advantage on Android. This skews results even among Android SoC's as devices that have higher single core performance suddenly have a higher score than they should relative to other devices with more smaller cores. The use of onscreen 3D benchmark also makes a further mess of things as a 3D app (such as a game) doesn't have to be running at a device's native resolution.

There's nothing to downplay over the A9's performance, I don't know why you assumed that was the case. There also isn't a reason to try and boast about it at this time. It is powerful, but it also had no rival close to its time of launch. Everyone else is still sitting on a 20 nm process (with the exception of Samsung) with designs from the start of 2015.

From the Anandtech's Exynos 7420 deep dive:

Exynos 7420’s Mali T760MP8 combined with the 14nm process not only makes this the fastest SoC we’ve seen in a smartphone but also currently the most efficient one that we measured.

If we made the thread earlier in the year, it would have a different tone when Samsung surprised everyone with an SoC that not only beat out Qualcomm, but offered many new features not seen on Apple's A8 (only to be introduced almost half a year later in the A9).

I'm still waiting on more bite and less bark.

I returned recently from a long break in Mexico, and read through the thread to catch up on all this stuff (because it's been a while). Beautiful times with family and friends.

The pace at which Apple has been moving with their internal processor designs seems to be outpacing the competition. I doubt new phones with an 820 or the newest Exynos will be able to rival the A9's performance. If that proves wrong, I'll gladly admit I'm wrong, just like I've always done. Whether or not you, as one person, dislikes how some benchmarks are handled by entire organizations is something you can reconcile with yourself.

Reviewing this thread was enlightening, because I often times give too much credit to some users in hopes that they're truly as reasonable as they seem. Then I see cringe-worthy comments like that bark and bite thing.

Either way, Apple is firmly leading the way in every metric that matters. Including SoC design.

Avatar image for NVIDIATI
NVIDIATI

8463

Forum Posts

0

Wiki Points

0

Followers

Reviews: 0

User Lists: 0

#17 NVIDIATI
Member since 2010 • 8463 Posts
@musicalmac said:

I returned recently from a long break in Mexico, and read through the thread to catch up on all this stuff (because it's been a while). Beautiful times with family and friends.

Glad to hear, a break from the cold is always nice.

The pace at which Apple has been moving with their internal processor designs seems to be outpacing the competition. I doubt new phones with an 820 or the newest Exynos will be able to rival the A9's performance. If that proves wrong, I'll gladly admit I'm wrong, just like I've always done. Whether or not you, as one person, dislikes how some benchmarks are handled by entire organizations is something you can reconcile with yourself.

The Xiaomi Mi5 (Snapdragon 820) already beat the Antutu score (for whatever that's worth). The device has 4 cores and a 1920x1080 display. It weighs less than the iPhone 6S, but has a slightly larger footprint.

The device is also priced very low, starting at $260 USD (32 GB model with glass backing) to $350 USD (128 GB with ceramic backing).

The faults with Antutu still remain, the way it evaluates devices with different CPU configurations and native display resolutions is not on an equal playing field, that much is clear. Whether it be across different operating systems or on the same one, there are discrepancies that won't disappear because you choose not to see them.

Reviewing this thread was enlightening, because I often times give too much credit to some users in hopes that they're truly as reasonable as they seem. Then I see cringe-worthy comments like that bark and bite thing..

The master of often antagonizing rhetoric can't handle when it comes his way? That's disappointing.

Either way, Apple is firmly leading the way in every metric that matters. Including SoC design

Apparently not.

Avatar image for musicalmac
musicalmac

25098

Forum Posts

0

Wiki Points

0

Followers

Reviews: 15

User Lists: 1

#18 musicalmac  Moderator
Member since 2006 • 25098 Posts

@NVIDIATI: That's fascinating, it did edge out the 6s. After reading Anand's take on the 820, that's a genuine surprise. It's probably incapable of sustaining a high level of performance that would rival the A9, though. Even with just doing a quick search, PhoneArena noted that the 6s feels smoother generally than an 820-saddled phone (I say an 820-saddled phone and not the specific LG model because other previews have noted similar hitches with the S7).

It is curious that you're referring to Antutu to make a point on synthetic performance, given how hard you fought against it (basically this entire thread). You made it seem as though it wasn't a reliable benchmark. So when you say, "For what it's worth," it's not worth anything, is it?

That Xiaomi Mi5 is more of a concern for Samsung than it is for Apple. That phone is racing to the bottom, and that's not where Apple's customer base is (or the 96%+ profit share Apple enjoys).

And I think you misunderstood my point about the cringe-worthy rhetoric...

Avatar image for NVIDIATI
NVIDIATI

8463

Forum Posts

0

Wiki Points

0

Followers

Reviews: 0

User Lists: 0

#19 NVIDIATI
Member since 2010 • 8463 Posts

@musicalmac I wouldn't assume anything about sustained performance just yet, especially when Vulkan v1.0 is now rolling out on Android. UI performance often depends on the skin running on Android, this is why in the past we've seen Nexus devices offer higher UI performance than skinned devices with the same (if not stronger) SoC. Samsung, for example, also has had more demanding features, such as split screen, a part of their UI for a number of years now. So there are certain trade-offs depending on the user's needs. "For what it's worth" is based on your perception, you're the one that put enough faith into Antutu to make this thread. I don't see as much value in these scores based on the discrepancies (highlighted above) in the benchmark's scoring.

Avatar image for ameerhaddad
ameerhaddad

37

Forum Posts

0

Wiki Points

0

Followers

Reviews: 0

User Lists: 0

#20 ameerhaddad
Member since 2016 • 37 Posts

Of course iPhone 6S is the best phone ever made and wait iPhone 7 it will blow your mind .

bye