Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

iOS 12 Core ML Benchmarks

heartbeat.fritz.ai

Post reply on HN
Print view View original

31–40 of 59 posts

Re: iOS 12 Core ML Benchmarks

#31

Post by jamesonthecrow »

KSS42 wrote: post #26

The article also points out iPad 2018 being faster than iPhone 7/8/X. This is odd. The article states that iPad 2018 uses A10X, but it actually use the A10. Is there a mix up with one of the iPad Pros? I can see an A10X (which has more GPU cores) beating the other iPads.

Thats a good point. I mixed up the iPad Pro 2 with the 6th Gen iPad from 2018. The 2018 iPad just squeaked through my threshold for having enough data to be included here, so it's possible that this is just noise. I'll dig into the variance as more data comes in. The article is updated to reflect it. Thanks!

Re: iOS 12 Core ML Benchmarks

#32

Post by coder543 »

Are there any apps I can use that would let me see the difference in performance? Or even just use the Neural Engine for anything outside of the built-in camera app and the Measure app.

EDIT: I see that Heartbeat is mentioned in the article, but I'm also still wondering what else is out there.

Re: iOS 12 Core ML Benchmarks

#33

Post by npunt »

walterbell wrote: post #30
ghop02 wrote: post #10

Earlier quoted context omitted.

It's my understanding that the neural engine API wasn't actually exposed to Core ML until the iPhone XS. The GPU is the important factor for performance of those models

Will it be exposed on the iPhone XR (the "mass market" model)? Presumably it will be supported on the upcoming iPad Pro and iOS' (mOS?) Arm laptop.

No reason to think they wouldn't. It'd be very un-Apple like to bifurcate core APIs like that.

Re: iOS 12 Core ML Benchmarks

#34

Post by dep_b »

jeffbax wrote: post #25
dep_b wrote: post #2

Impressive but with a specialized coprocessor it's not unexpected. It's a bit of a gamble for Apple though, as other ARM SoC's are probably able to bridge the gap in raw single-core and multi-core performance in a year. The whole ML thing is a bit fuzzy for a lot of people even for programmers like me that are still wondering how their regular applications are going to benefit from all this silicon.

You clearly haven't really kept up with Apple and ARM for the past 4 years have you. They're cleaning everyone's clock (pun unintended) with no signs of that abating. Last years X is still a generation faster than the fastest Qualcomm/Samsung chip today let alone what generic designs ARM licenses to the cheaper chip companies.

Oh that's why I get all of the downvotes, finally I understand it.

But you haven't really kept up with Apple and ARM for the past 4 weeks have you? Performance of the A12 is up something like 15% up - which is still impressive if you compare it to what Intel does on a yearly basis - but a lot less than it used to be for Apple SoC's.

In the mean while the latest Qualcomm SoC's (845 is like 35% faster than 835) are performing almost as well as the A11, while the performance gap used to be more than two years.

If Qualcomm manages to get another 35% increase next year their SoC will be faster at least until the A13.

So: - Qualcomm is catching up - While single core and multicore did not improve as much as it used to YoY for Apple

Re: iOS 12 Core ML Benchmarks

#35

Post by overcast »

hokumguru wrote: post #20
overcast wrote: post #19

Earlier quoted context omitted.

It's not, my 6S did the same thing with intensive apps, like Instagram. With IG it's probably ALWAYS ramped up constantly scrolling, playing , downloading. They definitely sacrificed battery life for speed in older phones. My XS lasts like two days though.

What the heck are you doing to get 2 days from your XS? I barely get one!

really just business stuff with instagram / email / text!

Re: iOS 12 Core ML Benchmarks

#36

Post by dep_b »

rhencke wrote: post #24
dep_b wrote: post #6

Earlier quoted context omitted.

I guess the same can be said for AMD's x86_64 CPU's? Still it's fair to compare them to Intel x86_64 CPU's. The big difference is that ARM has something like a reference design where Intel doesn't want to share anything if they don't have to.

It's actually the other way around, humorously enough. x86_64 is also known as AMD64, and for good reason. AMD created the core 64-bit x86 design, but, more importantly, they have patents to key pieces of the ISA required to legally implement it. So, long story short, it is actually AMD who didn't have to share anything with Intel if they did not want to - Intel's 64-bit x86 CPUs are fundamentally AMD64-compatible CP…

Well AMD might want to sell the 64 part to you, but Intel doesn't want anybody having the x86 part if they can prevent it.

Re: iOS 12 Core ML Benchmarks

#38

Post by deaddodo »

hokumguru wrote: post #20
overcast wrote: post #19

Earlier quoted context omitted.

It's not, my 6S did the same thing with intensive apps, like Instagram. With IG it's probably ALWAYS ramped up constantly scrolling, playing , downloading. They definitely sacrificed battery life for speed in older phones. My XS lasts like two days though.

What the heck are you doing to get 2 days from your XS? I barely get one!

My XS Max gets ~1.5 days with fairly regular-heavy usage.

Re: iOS 12 Core ML Benchmarks

#39

Post by pohl »

aphextron wrote: post #12

I've noticed on my SE that everything is running much much faster with iOS 12. It seems like the app store is actually really usable now. Does anyone have any idea what they did?

There were several things in addition to the adjustments they made to the clock frequency curve others have mentioned.

There were a couple of fixes in Autolayout constraint resolution that were at least quadratic but are now linear.

The prefetching in table views was optimized to make scrolling them smoother.

A lot of RAM is saved by big improvements to the backing stores for image resources.

They made app launching faster.

The on screen keyboard comes up faster, and they made it respond to typing faster.

Opening the camera from the lock screen has been made faster.

Re: iOS 12 Core ML Benchmarks

#40

Post by coder543 »

walterbell wrote: post #30
ghop02 wrote: post #10

Earlier quoted context omitted.

It's my understanding that the neural engine API wasn't actually exposed to Core ML until the iPhone XS. The GPU is the important factor for performance of those models

Will it be exposed on the iPhone XR (the "mass market" model)? Presumably it will be supported on the upcoming iPad Pro and iOS' (mOS?) Arm laptop.

The XR has the same CPU/GPU/NE as the XS, and it's advertised as such from what I recall. It definitely should be there.
Post reply on HN