Apple Silicon M1 Disruption • Hacker News Board

Re: Apple Silicon M1 Disruption

#41

Post by kergonath » Mon, Dec 07, 2020, 12:59 AM UTC

codeflo wrote: post #33

Is there already an in-depth analysis of the M1 by someone with a low-level perspective? I want to develop an intuition on why/where the M1 is fast. E.g. is it branch prediction, reordering, memory latency. Unfortunately, most articles don’t go any deeper than “seems to be optimized for macOS”.

Andrei Frumusanu’s articles at AnandTech are quite good: https://www.anandtech.com/show/16226/apple-silicon-m1-a14-de...

https://www.anandtech.com/show/16252/mac-mini-apple-m1-teste...

There is a reasonable discussion of the cache hierarchy, decoding units and out-of-order window.

Re: Apple Silicon M1 Disruption

#42

Post by faitswulff » Mon, Dec 07, 2020, 12:59 AM UTC

trynewideas wrote: post #26

Since these keep floating up, I'm already exhausted with this specific rebuttal to Morehead's review: > As pointed out in John Gruber’s hard takedown of Moorhead’s piece, most of the problems he encountered were software problems, not M1 hardware issues. Morehead's allegiances and work are relevant biases, as are Gruber's. But Morehead's review wasn't of the M1 processor or architecture as a technology. It was a revi…

I think the reason it keeps coming up is that it is the most prominent bad review, but due to Moorhead’s allegiances, poor calls in the past, and eclectic selection of software, his negative review comes across as being in bad faith.

Re: Apple Silicon M1 Disruption

#43

Post by whynotminot » Mon, Dec 07, 2020, 1:01 AM UTC

amelius wrote: post #34

gizmodo59 wrote: post #3

I have seen so many articles on HN in front page about M1 over the past few weeks. Like a curious child I read all of them because somewhere in me I want to believe there exists a possibility of a giant leap for Desktop/Laptop. Having tried it myself, I should say this is going to be remembered just like the iPhone in 2007.

> I should say this is going to be remembered just like the iPhone in 2007. I hope people will not forget about TSMC who made this all possible.

Apple made it possible for TSMC to be able to do this. It's a tight partnership, and you don't understand the relationship between the two if you think TSMC's accomplishments come in isolation.

Your sentiment is better expressed as "I hope TSMC gets some credit for the role they've played."

Would recommend reading "Mobile Unleashed" by Daniel Nenni if you want to know more about ARM history in general.

Re: Apple Silicon M1 Disruption

#44

Post by kergonath » Mon, Dec 07, 2020, 1:01 AM UTC

jeffbee wrote: post #30

naderkhalil wrote: post #11

> Will Microsoft now offer an official Windows 10 on ARM that can run on M1 Macs?...This could create trouble in the x86 PC world. Or will Microsoft, less committed to Windows than it is to its applications running everywhere, be content to see Office and more run (and generate revenue) on M1 Macs…and how will HP, Asus, Dell and others react? This is just the beginning of a new competitive layout. Could this be good…

I think it will benefit Linux but not that way. It will force the x86 vendors to adopt the microarchitectural aspects of the M1 that make it fast in practice, instead of spending so much area/power budget chasing SPEC benchmarks. We will get better chips through competition.

I don’t think these goals are exclusive. I am not sure about the M1, but the A13 and A14 are doing quite well in SPEC benchmarks. If they have compromised these scores, it’s not obvious to me.

Re: Apple Silicon M1 Disruption

#45

Post by ehejsbbejsk » Mon, Dec 07, 2020, 1:02 AM UTC

gizmodo59 wrote: post #3

I have seen so many articles on HN in front page about M1 over the past few weeks. Like a curious child I read all of them because somewhere in me I want to believe there exists a possibility of a giant leap for Desktop/Laptop. Having tried it myself, I should say this is going to be remembered just like the iPhone in 2007.

And we haven’t even seen what Apple can do for their “pro” line. I can’t wait till they roll out Mac Pro.

Re: Apple Silicon M1 Disruption

#46

Post by untog » Mon, Dec 07, 2020, 1:03 AM UTC

2muchcoffeeman wrote: post #32

untog wrote: post #14

Earlier quoted context omitted.

I doubt that very much. The iPhone was a true revelation: in user interface, in form factor, in the things it allowed you to do. The M1 is amazing but it doesn’t compare. Performance (both raw and thermal) is a big boost but it’s not going to reinvent computing.

Loads of people didn’t think much of the iPhone when it came out either. No physical keyboard, other devices have large touch screens, no stylus, can’t copy and paste. Appreciating the iPhone is largely done in hindsight. Best not to make predictions too far into the future.

> Appreciating the iPhone is largely done in hindsight.

I’m sorry but that’s definitely not true. Yes, there were a vocal minority of folks who said the iPhone was nothing special but the mass market response was huge and it was heralded as a huge deal by the vast majority.

And to go back to my original point: there’s a difference between “this new invention allows you to do new things, but those things aren’t important” and “this new invention does not allow you to do new things”. Reaction to the iPhone was the former. My reaction to the M1 is the latter. It allows you to do the things you already do faster and cooler and it’s a big technological shift. But it isn’t going to change the way people use computers in the way the iPhone did.

Re: Apple Silicon M1 Disruption

#47

Post by jaimex2 » Mon, Dec 07, 2020, 1:04 AM UTC

phkahler wrote: post #39

Where are some benchmarks comparing M1 to the best x86 processors from AMD? Since M1 is only 4 big cores maybe it would be fair to compare it to the 4 core 8 thread APUs and not crush the poor thing with an 8 core version. A1 is cool. Good for Apple, but it's not the computing miracle it's made out to be.

That's not how things work in the Apple world. Anything Apple release is disruptive and innovative even if its been done before. Just ignore it and continue on in reality.

Re: Apple Silicon M1 Disruption

#48

Post by no_wizard » Mon, Dec 07, 2020, 1:04 AM UTC

If the M1 proves anything at all it’s that ARM 64 can and will be a performance chip not just a chip that is strictly intended for low power devices. I think that’s what the M1 will finally signal to all the other vendors, even though many have been saying this for a long time it’s proof in the wild that you can build desktop class ARM chips.

My other thought is I wonder if this will open up the idea of vendors support specific co-processors analogous to how Apple has things like the T1, some offloading to a specific chip for ML etc.

This is exciting if more vendors do this, I predict the first one to do it in an open way will win the day long term as it will be attractive to all upstream manufacturers like Dell etc

Re: Apple Silicon M1 Disruption

#49

Post by wyldfire » Mon, Dec 07, 2020, 1:04 AM UTC

amelius wrote: post #34

gizmodo59 wrote: post #3

I have seen so many articles on HN in front page about M1 over the past few weeks. Like a curious child I read all of them because somewhere in me I want to believe there exists a possibility of a giant leap for Desktop/Laptop. Having tried it myself, I should say this is going to be remembered just like the iPhone in 2007.

> I should say this is going to be remembered just like the iPhone in 2007. I hope people will not forget about TSMC who made this all possible.

Is that really the case? Apple's design of the CPU itself seems like it's a bigger unique factor than the fab. Doesn't TSMC make competitors chips that are benchmarking much poorer than M1?

Qualcomm got rid of their mobile ARM CPU designs a while back. Can the snapdragon cx / SQ2 series hope to compete using ARM reference designs, with Apple out so far ahead?

Re: Apple Silicon M1 Disruption

#50

Post by grecy » Mon, Dec 07, 2020, 1:04 AM UTC

trynewideas wrote: post #26

Since these keep floating up, I'm already exhausted with this specific rebuttal to Morehead's review: > As pointed out in John Gruber’s hard takedown of Moorhead’s piece, most of the problems he encountered were software problems, not M1 hardware issues. Morehead's allegiances and work are relevant biases, as are Gruber's. But Morehead's review wasn't of the M1 processor or architecture as a technology. It was a revi…

> For the love of whatever stupid internet points people are trying to win, let Morehead's review go.

Do you not think it's the least bit concerning that Moorhead has Intel, AMD and NVIDIA as his clients?

Do you really think he can write an unbiased piece about a competitor of theirs when they put food on his table?

(EDIT: For reference, I'm in the 4x4/travel world and write for a stack of magazines. Big car OEMs fly journalists all around the world, put them in expensive hotels, feed them 5 course meals and then have them review their new vehicles. I want you to guess what percentage of those reviews are absolutely glowing. )