A14X Bionic Performance Stats Leak Out – Easily Outperforms Core I9 MacBook Pro

Author: pinewurst

Score: 29

Comments: 26

Date: 2020-11-06 03:35:31

Web Link

_________________________________________________________________________________

trixie_ wrote at 2020-11-06 06:24:56:

Apple should of made the iPhone dockable years ago. They could own the PC market right now. There’s no reason I should have a separate laptop or desktop with an iPhone 11 in my hand.

rbanffy wrote at 2020-11-06 12:59:53:

You will still want a keyboard, trackpad, and at least one screen. At that point, you might as well add a CPU and some memory, flash and battery and have a full laptop that can sync with (icloud does an excellent job at that) and charge your phone. Many companies tried dockable phones and it never worked well. The cost of a dock is more or less the same as the cost of a desktop as smart or smarter than a smartphone.

trixie_ wrote at 2020-11-06 20:25:39:

Other companies tried mp3 players, and then there was apple. A cost of a desktop dock would be nothing compared to the cost of a tower. The mouse/keyboard/monitor you'd have to buy either way.

rbanffy wrote at 2020-11-06 21:53:30:

The design constraints of a phone are much different from a desktop computer or a laptop. A good phone is not a good laptop and the corpses along the way more or less prove that.

A phone will run a benchmark faster than a laptop for a couple minutes. Keep it under pressure for an hour - say, render a 4K video with a couple layers - it'll have nowhere to dump the excess heat.

There is one way to really pull it off, however - when plugged, the phone hands over processing and RAM to the docking station (maybe via an image transfer from one hypervisor to the other), but there is very little to be gained here - coordination between the two, the way Apple already does it between macOS and iPhone, is a great experience. If the hypervisors keep the memory image in sync, say, every second copying dirty state to the phone, you can even unplug it without risking much.

trixie_ wrote at 2020-11-07 01:10:25:

People watch videos and play 3d games on their iPhones for hours now already. Absolutely no need to make a dock more complicated than a dumb proxy for input/output devices.

randyrand wrote at 2020-11-06 06:45:39:

whats the advantage? A tad cheaper?

I gladly prefer to be able to use my phone and laptop simultaneously for different tasks and will pay that premium.

trixie_ wrote at 2020-11-06 20:26:57:

Depends how it is 'attached'. If it were wirelessly attached you could use both. Similar to how wireless CarPlay works.

rbanffy wrote at 2020-11-06 13:03:04:

Don't know why you got downvoted. I makes a lot of sense to tightly integrate desktop and phone (answer and make calls from the desktop, continue browsing on any other device) but it makes little sense to demand the phone to also be a good desktop, as those are two conflicting engineering goals.

B1FF_PSUVM wrote at 2020-11-06 11:10:32:

I believe HP tried a dockable Windows phone a few years ago. Looked neat.

It's a pity that Windows phone failed, it was pretty good and we could use a third choice.

Edit: 2016 HP Elite X3, e.g.

https://www.cnet.com/reviews/hp-elite-x3-preview/

trixie_ wrote at 2020-11-06 20:28:05:

Asus tried too. Many companies tried to make MP3 players before Apple as well. The point is execution, and I believe it is a slam dunk for Apple. Majorly upsetting the balance of PC ownership.

joreilly wrote at 2020-11-06 04:41:19:

I'm not well versed in CPU design; how does a 3.1Ghz peak clock A14X outperform a 4.8GHz peak clock i9 [1]? The only thing that immediately comes to mind is a massive hypothetical instructions-per-clock advantage.

[1]:

https://www.apple.com/shop/buy-mac/macbook-pro/16-inch-space...

microtherion wrote at 2020-11-07 02:13:52:

It's not always just instructions-per-clock, sometimes it's also data-per-clock. Specifically, the Apple Neural Engine in the Bionic chips can perform some vector computations faster than anything in either the CPU or GPU of any Intel Mac.

wmf wrote at 2020-11-06 05:33:08:

Apple's IPC advantage isn't hypothetical; it's been measured (mostly by AnandTech) for years.

That being said, I'm a little skeptical of a 4 big + 4 little A14X beating Intel's 8 big cores.

gravypod wrote at 2020-11-06 04:45:15:

The time it takes to execute an x86 instruction is not constant and the amount of concurrently executing instructions (pipelining) is not the same between these two CPUs. Also, power management works every different in arm so it has a lot of boosting head room.

redrobein wrote at 2020-11-06 04:55:37:

Not too familiar with cpus but if it's known that arm outperforms x86 while also being more power efficient, why aren't everyone using it? Why did it take until now for a major computer manufacturer to switch?

rbanffy wrote at 2020-11-06 13:13:13:

> f it's known that arm outperforms x86 while also being more power efficient, why aren't everyone using it?

PowerPC and Alpha did that in the 90's and the reason is software.

Intel's x86 has a huge software ecosystem. In 1999 (thanks to a procurement mistake) I was reading my e-mail and browsing documentation on a wicked fast 64-bit computer. It would be a good couple more years before I could edit a Word document on a 64-bit computer because Microsoft didn't have Office for them. I only got to read e-mail on that ridiculously fast Unix workstation because nobody wanted to use it and it was just sitting there running our timesheet software and magnificent screensavers.

Multi-processor x86 desktop machines only became popular when Windows XP became popular. Multi-processor Macs only became popular when Apple moved to OSX. IBM only added multi-processor support for their mainframes when they hit a dead end and had to move to machines with slower CMOS processors with more processors to make up for the speed they lost.

Software dynamics holds hardware evolution back.

wmf wrote at 2020-11-06 05:30:00:

ARM doesn't outperform x86. Apple Silicon—which only Apple has—outperforms x86, and only this year.

rbanffy wrote at 2020-11-06 13:17:46:

ARM did outperform x86 at the start. An Archimedes could do floating point faster than a Compaq Deskpro 386 with a 387 FPU.

k_sze wrote at 2020-11-06 05:18:39:

Part of the reason is that _ensuring_ things work for a different CPU architecture is simply a non-trivial task. There are libraries with hand-written x86 assembly, and others in C/C++ that depend on x86 intrinsics to perform acceptably, and then there are those that work accidentally on x86 because of how compilers implement some undefined behaviour for x86.

rbanffy wrote at 2020-11-06 13:24:52:

Cloudflare did a very interesting post that made the rounds here:

https://blog.cloudflare.com/neon-is-the-new-black/

Discussion:

https://news.ycombinator.com/item?id=16831609

karmakaze wrote at 2020-11-06 15:18:32:

Note that it says it outperformed an "Core i9 MacBook Pro" not a "Core i9" so depends on throttling due to heat. It's quite easy to believe the A14X is more efficient and can win in those conditions.

rasz wrote at 2020-11-06 13:42:16:

Geekbench is a scam

Dkuku wrote at 2020-11-06 07:23:28:

How it compares to normal i9 device. Linus took apart a macbook air and the cooling was so bad that it may be the reason the i9 cooling so badly designed. It may be badly designed on purpose to show that the performance of arm chips in macbooks is comparable to an i9 without cooling

https://youtube.com/watch?v=MlOPPuNv4Ec

rowanG077 wrote at 2020-11-06 08:28:01:

The i9 is not in an Macbook air. It's in a Macbook pro 16 inch which has a completely different design. But you are right that all ultra mobile laptops on the market have way too shitty cooling. You could easily get an additional 10% of performance if the OEM would stop the insane thinness war.

tonyedgecombe wrote at 2020-11-06 11:58:26:

Interestingly the latest MacBook Pro did get thicker than its predecessor. Not a lot but perhaps they have got to the point where they are thin enough.

the_lucifer wrote at 2020-11-06 15:50:44:

The added thickness was attributed to the keyboard changing back to the Scissor mechanism from the Butterfly mechanism that was plagued with issues