Live data from Hacker News

Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

macrumors.com

541–550 of 1001 posts

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#541

This idea of “actual professionals” that always comes up in response to apple’s “Pro” moniker amuses me to no end. Everybody throws the term around and no two people have the same definition! What in the world is an actual professional? There are professional journalists that just need a browser and text editor. There are professional programmers working on huge code bases in compiled languages that do need a beefy m…

Of course there are specific niches, but it's pretty easy to answer in general: 'actual professionals' need some combination of two criteria - capacity and reliability/durability/usability. A device which can handle 'large' loads - be it CPU-bound, memory/storage-bound, or even screen size bound, and can be worked hard for 6-8-10-12 hours per day, 5-6-7 days per week without either the machine or the user breaking. T…

To be fair, it's pretty outdated terminology.

It comes from an era when computers were so genuinely slow that doing almost anything - even using page layout like Pagemaker, or setting up just a single track song in a DAW, had tons of render lag. Even spreadsheets would take significant amounts of crunch time to run their calcs, in the very early days. This meant that most work done on computers, with anything larger than a "toy/hello-world" dataset, was going to be painfully slow. That's why they called it "professional" - because you were actually using datasets large enough to burden the beast. Actually balancing a whole company's finances with a spreadsheet, rather than tallying up a little 10-item list.

I want to emphasize that "majoritarian" aspect of it - it wasn't just a few specific kinds, it was a majority of ALL kinds of work.

And that's changed.

We're now at a point where only a tiny minority of tasks done on computers actually have throughput limits based on the computer rather than the operator.

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#542
post #48

This is pretty crazy to see, even if the full story isn't clear yet. A base level MacBook Air is taking the crown of the best MacBook Pro. Wow. SVP Johny Srouji and all of the Apple hardware + silicon team have been smashing it for the past many years. For what it's worth, I have a fully specced out 16 inch MacBook Pro with the AMD Radeon Pro 5600m and even with that I'm regularly hitting 100% usage of the card, and…

I wonder if M1 dominates an i9-9980HK at multithreaded workloads that make full use of available SIMD? Does an M1 dominate at peak theoretical flops?

M1 is not magic and can't break the laws of physics. SMT makes better use of silicon and will probably push speeds closer. OTOH, M1 has a fast memory that the i9 can't match.

I still bet on the i9, but it'd be interesting to run a test.

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#543

Nobody ever saved a dime by switching to the apple ecosystem. Whatever real innovation lies within this silicon will be available to the normal PC ecosystem in no time.

My Mac products (MBP and iPhone) usually well outlast devices I've owned that were Windows or Android by a factor of 2x. So I'd say I definitely saved more than a dime by using them.

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#544

Earlier quoted context omitted.

Back in the 1980s I used spend a fair amount of work time in rooms with a VAX and can attest to their powerful and noisy fans. If you are a pro with a VAX, you had better be a fan liker.

I don't think VAX was the intended meaning in anti-vaxxer.

It’s a joke son, it’s a joke

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#545

Earlier quoted context omitted.

Not quite. You can't synthetically compare one chip to another and draw organic conclusions. Apple computers with M1 don't support the software that I use. That's why I bought a fully spec'd Intel MBP13 today. All this talk about battery life and benchmarks gets flipped on its head when I can't use the product in the real world.

Isn't there Rosetta that they talked about?

And with rosetta it is certainly slower than running it native on x86

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#546

Earlier quoted context omitted.

Someone here posted when the M1 powered Macs launched that they're essentially ASICs now and that made me do a double take. Since you cannot change the operating systems anymore, aren't these essentially ASICs?

Not even close. An ASIC is a program on a chip. These are still general purpose, programmable computing machines.

An FPGA is a program on a chip. An ASIC is literally just a chip. Calling the M1 an ASIC is insulting to the Apple hardware team.

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#547

I've been holding onto my late 2013 15" MacBook Pro for almost 7 years now and it's wild to see it get absolutely out-spec'd by the MacBook Air. It's been a long time, but I've always convinced myself that I'm not missing out on that big of a processor improvement. I do a lot of audio work with it, but even then it doesn't always feel like a slow experience.

same here. My friends don't believe it when we work together at a cafe and my battery lasts about as long as their brand new mbp.

my only pb are the smears on the screen, otherwise i think i'll keep it for another 7 years.

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#548
post #475

Earlier quoted context omitted.

Shouldn't we wait for non synthetic benchmarks to be performed by third parties running real applications? We could even compare some cross platform apps across both OS and cpu and see how the total package performs.

I've personally found Geekbench results representative of real time workloads. So do more traditional benchmarks like SPECint.

Fantastic since many pieces of kit have been released to the public wherein both geekbench and more traditional measurements of actual performance exist can you point out some instance where real benchmarks are well correlated with differences in geekbench score?

Re: Apple Silicon M1 chip in MacBook Air outperforms high-end 16-inch MacBook Pro

#550

Earlier quoted context omitted.

Laptop Macs of late are known for heavy throttling due to inadequate cooling, which cannot have been unnoticed in simulations

I’d go so far as to say “laptops of late”, thermal throttling isn’t unique to MacBooks. My XPS15 regularly throttles and sounds like it’s about to take off.

It was Surface that started the trend, then MacBook followed and became a feature.

By the way, “throttling” refers to CPU _slowing down_ despite cooling working at full capacity, so loud fans in itself isn’t one.

e: Another way to explain thermal throttling would be “thermal fading”, like brake fading on a car. Whether brake fading is considered a design fault or a feature that allow bursts of stronger brakes is semantic.

Post reply on HN