Hacker News Reader

Comment by garagemc2 | Hacker News Reader

> Right now Apple is several years ahead of other high end phone manufacturers in CPUs.

I hear this statement a lot... how is this determined?

Performance and features. In single threaded performance, Apple's A chips are way ahead. That's because Apple highly customizes and optimizes their core designs, while Qualcom and Samsung use largely vanila ARM reference designs with maybe a few tweaks. Apple chips also have considerably more cache. That's difficult for the competition to counter because they are very price sensitive and cache size eats up expensive die space.

The counter argument is that the other systems make up for this by having more cores, which is really a cop out. Single threaded execution has a far more direct effect on user experience, gaming performance, etc. They can't compete in core engineering so make it up by slapping on more fairly generic cores. It does appear that Samsung is responding to this and investing in more advanced core designs.

The final area is custom features like the neural engine behind real-time face recognition, real time 3D face lighting effects and such. The competition don't really have these at all, so we don't know how far behind they are.

There's a pretty good article on this linked below.

https://seekingalpha.com/article/4138071-apple-cpu-advantage...

The Samsung M1, M2 and soon the M3 are all fully custom.

Yep, it does look like Samsung may be in a position to catch up soon. That could make a real problem for Qualcom the other Android manufacturers. Samsung are the biggest manufacturer of high end Android phones. If Qualcom can't sell high end CPUs to them any more, it might make manufacturing any truly high end CPUs uneconomical, or at least drive up costs even further.

Watch out for what comes out of ARM Austin. Their last core was the A72 from a couple of years ago. Rumour has it they've been working on a big core to better compete with Apple and Samsung.

Looking back, it makes sense that Qualcomm discarded their underperforming custom design efforts (at least for the mobile market). If ARM can deliver a competitive design, why not fully commit to their roadmap and save significant amounts on R&D costs?

Because if ARM cannot deliver they are fucked.

A lesson Apple learned at the hands of Motorola.

I sometimes wonder how much of It Just Works was influenced by having slower machines. When doing everything takes longer, if you do it right the first time then it’s still faster than doing it twice.

ARM is not just one company - it's a semi-standard.

Would you mind backing up your claim? To my knowledge, ARM is one company that licenses their designs to other companies, who are free to parameterize and modify as they please.

I don't know what the above comment was referring to but they are more than what you describe. I'd submit AMBA as an example of this; I've seen this tech utilised by IP for ASICs that don't actually contain any ARM processor cores themselves.

https://en.m.wikipedia.org/wiki/Advanced_Microcontroller_Bus...

I think the idea is that it probably matters very little to Apple or Samsung or any other company that has an architectural license how well the ARM originated core performs because they are building their own core and ARM is basically a standard committee to them. Obviously companies that are using the actual ARM cores care about ARM's ability to perform.

Why don't companies just come up with their own designs?

First off designing a whole core architecture from scratch is a huge and very expensive undertaking. Youd need to be able to get a really big competitive advantage to make it worthwhile.

Secondly theres a large ecosystem of add on components designed work with ARM and be dropped into ARM SOCS, such as GPUs, Wifi modules, Gyroscopes, wireless modems, GPS, etc.

Thirdly there are a lot of SOC engineers very familiar with ARM. You can hire them streight from competitors, or college, including PHDs that have done research on it. Youd need to train up any new hirs from scratch on your architecture.

Finally theres a huge software development tool chain built around the established processor architectures. To support a new architecture youd also need to build a set of compiler back ends, bearing in mind the existing ones benefit from many years of tweaking and optimization.

Yes, SW is the key; especially Linux. ARM is way ahead of other embedded CPU architectures in terms of Linux support.

There are two types of ARM licenses. One is an Architectectural license. This allows licensees to design and implement the ARM ISA. Apple and QCOM among others have Architectural licenses. They can add customizations such as # pipelines stages. This license is very expensive.

The other license is getting ARM's implementation of a CPU (ie A57, A72 etc). Customers can parametize # cores, cache size, memory width etc, but the basic architecture is fixed.

Because it gives you no competitive advantage.

Apple made the decision to pursue performance at the cost of device life.

>Performance and features.

I think both these metrics are now adequate, battery life is the single metric I am interested in now.

Battery life is, realistically, part of performance- it’s just “per watt”. Apple is also a leader in that area as well.

>That's because Apple highly customizes and optimizes their core designs, while Qualcom and Samsung use largely vanila ARM reference designs with maybe a few tweaks

Here's the Anandtech article on the "few" tweaks Samsung has made to its 6 wide decode custom M3 cores in the upcoming Exynos 9810.

https://www.anandtech.com/show/12361/samsung-exynos-m3-archi...

Apple's CPUs win benchmarks, but a lot of this is more down to economics. They're making CPUs for a single client, themselves, mostly for the high end, and they don't need to make a profit on them.

Qualcomm probably could make better CPUs...but it needs to sell them for a profit, and they might not fit into all phone's physical size or power budget.

So, Qualcomm ends up making somewhat lowest-common-denominator chips. Economies of scale make it difficult to make a run of super good chips when Samsung uses its own in many markets, Apple uses its own--the world of high-end smartphones outside of Samsung and Apple is just too small.

Isn't Apple cheating?

They're taking their CPUs and clocking them at speeds the device can't support, except when brand new, then letting the device slow down over the corse of its usable lifespan.

It would be interested to compare an Apple and Qualcomm CPU after a year and a half, to see how the benchmarks have changed.

That's incorrect. The CPUs don't degrade, the batteries do.

The CPU speed decreases. So doesn't matter if it technically is still able to reach higher clock speeds. In reality it runs slower.

Right, as an alternative to random crashes. Bear in mind this is not an Apple problem, its a battery problem. All the other manufacturers have this problem, they just dont attempt to detect battery power fluctuations and mitigate it with throttling. They just eat the system crashes. Its got nothing to do with the CPU design, otherwise replacing the battery wouldnt fix the problem.

> All the other manufacturers have this problem, they just don't attempt to detect battery power fluctuations and mitigate it with throttling. They just eat the system crashes.

Really, because I have not heard of any other manufacturer with this problem?

Then you have not looked into it. Android forums have been filled with complaints over “random crashes” when doing something CPU heavy for years.

Care to cite any sources as I'm only coming up evidence that they don't (the last one is a forum like you said and the reasoning explained there is due to bloat)

https://mashable.com/2018/01/04/apple-slowing-down-iphones-w...

https://www.theverge.com/circuitbreaker/2017/12/29/16829512/...

https://www.engadget.com/2017/12/29/samsung-lg-claim-older-p...

https://forums.androidcentral.com/samsung-galaxy-note-8/8589...

Source: basic understanding of how batteries & CPUs work while following tech forums for decades.

This isn’t considered controversial

You're completely ignoring the question. Do other smartphones start out fast due to new batteries and slow down due to the battery degradation like Apple or do they account for the battery degradation and keep performance stable?

Other smartphones either do the same thing (slow down) or just plain crash (most of them do this). It’s a common complaint.

It takes quite awhile for the battery to degrade to the point it can’t run the CPU at max capacity anymore. And it still could, but it would be potentially unstable.

Twitter pundits commenting on Geekbench benchmarks, mostly.

Snark aside, Apple's CPUs are pretty(really pretty) far ahead of Qualcomm's in single-threaded performance.

Qualcom's chips tend to struggle to keep up with whatever Apple released two generations ago.

But it doesn't matter because if you're building an Android device you can't buy an A chip for it.

Given how highly multithreaded mobile OSes are, that is only advantageous for lazy coding.

Any proper iOS application with be doing lots of GCD dispatchs, for starters.

Likewise on Android, Google had to change the OS behavior to just kill apps that insist in misusing the UI thread for long running tasks.

Single threaded programming isn't 'lazy coding'

It is, in the age of ubiquitous multi-core hardware.

I don't remember when it was the last time any of my applications only had a single thread of execution on them, beyond shell and Python scripts.

Maybe around 2000.

And even then, the OS is juggling processes across all cores every few ms, so outside any benchmark winning game, there isn't much real world value in single thread performance.

Except for JavaScript performance: https://twitter.com/codinghorror/status/954493740600578049

What I see is the quality of a JIT compiler implementation, not the use of cores.

Are you serious? Multithreadjng is not Parallelism. It’s not about processing an image in the UI thread, it’s about making that processing faster on the background thread that picks up the work. Don’t get me wrong but lots of people still write iterators, for loops and single threaded functions. Parallel algorithms are hard

Uh nope, single threaded performance is the key parameter. It’s what made intel (et al) blow up with Meltdown and Spectre. It’s what they’d still be pushing if it weren’t for physics.

Reply on news.ycombinator.com