Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
You mean like what the PPC processors didn't have when they migrated to the technically laden debt of the x86 instruction set? :D
Except then, Apple was at the mercy of IBM and Motorola for the design and manufacturing of chips. Now Apple designs their own class leading chips and is at no ones mercy.
 
Except then, Apple was at the mercy of IBM and Motorola for the design and manufacturing of chips. Now Apple designs their own class leading chips and is at no ones mercy.
I see, so it wasn't solely, x86 technical baggage.
 
You know that AMD has been unable to deliver these mobile chips in large quantities. Hard to buy a machine with one and the ones that exist are low-end plastic junk.If Apple decides to go AMD custom,
They don't, they just ditched the technical debt that is the x86 instruction set and didn't worry about compatibility with third-party hardware either. This is what happens when you control the entire pipeline.
No, they don’t control the entire pipeline.

The ARM architecture is licensed.
 
Of course you just said you said you think Cinebench is a much better test than Geekbench. Well, for 90% of the computer buying population, Cinebench is even less relevant than Geekbench.

Sorry, you just contradicted yourself. You can’t can’t have it both ways.
I did? Where?
Uh really? Right here.
Cinebench is worlds better than Geekbench. But one must realize it is but one benchmark. Relying on a single benchmark is foolish. The best benchmark is the one testing the application(s) you use.
I agree with the second point but your first point is what I took issue with in the first place.
 
  • Like
Reactions: pioneer9k
My 2010 Mac Pro with a single six core 3.46GHz x64 CPU achieves a Cinebench 23 multi CPU score of 4,376. That's 42% slower than this system. Given my Mac Pro is over 10 years old and the processor technology used within is even older I'm not sure performance is anything to write home about. I would expect over 12 or so years technology to improve.
 
  • Disagree
Reactions: diandi
Actually, next year Apple will sell more Apple Silicon chips worldwide (A and M chips in computers, iPhone and iPad) than all the x86 chips (intel and AMD).

Fair point.

But then we should talk about Qualcomm if we're expanding the topic beyond just laptop and desktop chips, right?

Qualcomm sells more chips than anyone thanks to the billion Android phones sold every year.

Will Apple Silicon still "dominate" if we include ALL mobile phones and tablets?

My point was... Apple-made chips are a fraction of any industry. Though I do agree that they are amazing. :p
 
The difference in wattege is only 40%, not 60. And how is it disingenuous? Those extra 10W give 20% increase in R20, it's likely they would do the same in R23. There really isn't that much difference between those two benchmarks.
Whoops, good catch on the 40% 👍. I still stand by my initial assessment; it's disingenuous because we simply don't know how cinebench scales have changed between r20 and r23, other than the fact that they do. Cinebench even says not to compare across generations. Simple arithmetic scales don't always translate. (Try doing this in a high quality peer-reviewed journal, I dare ya! I've made similar mistakes in the past, and was ripped by reviewers.)

Actually, no. The throttling effects are important. Geekbench is designed to prevent throttling, but that's only relevant if your real-life usage consists of short bursty loads. Case in point, my i7-1065g7 can easily go over 35W for short periods of time, but that's way beyond sustainable thermal envelope.

I don't disagree that throttling effects are important, but I thought the conversation was about the chips themselves, not the machines they are embedded in (I imagine the air having worse R23 and the mini better); hence, Geekbench scores would be the better metric in comparing pure performance -- we still don't have any concrete picture of the M1's TDP; the best we know is something along the lines of 10-18W.
 
Uh really? Right here.

I agree with the second point but your first point is what I took issue with in the first place.
The second point is related to the first. You intentionally ignored the second point in order to misrepresent what I said. In the future do try and be honest when having a discussion with me.
 
My 2010 Mac Pro with a single six core 3.46GHz x64 CPU achieves a Cinebench 23 multi CPU score of 4,376. That's 42% slower than this system. Given my Mac Pro is over 10 years old and the processor technology used within is even older I'm not sure performance is anything to write home about. I would expect over 12 or so years technology to improve.
Well, It's Intel that didn't improve much in that time. I don't think you want to compare battery life.
 
My 2010 Mac Pro with a single six core 3.46GHz x64 CPU achieves a Cinebench 23 multi CPU score of 4,376. That's 42% slower than this system. Given my Mac Pro is over 10 years old and the processor technology used within is even older I'm not sure performance is anything to write home about. I would expect over 12 or so years technology to improve.
its faster than base 16" mbp in terms of cpu performance. and ur mac pro cpu consumes 80W tdp, M1 is faster than ur cpu and only consumes up to 15-18W. Single core also better on M1
 
  • Like
Reactions: NetMage
I don’t understand what you are saying. You thought the bottom of the line processor found in a $699 mac mini should blow away a Mac Pro chip?

This chip blows away the chip it was replacing. The chip in the 16” MBP and high end 13” MBP, when those are converted to ARM, will blow away the chips they replace (Apple has indicated they may still call that chip an “M1,” but it won’t be the same chip as the chip running the benchmark today).
There are a lot of people in these forums who have unrealistic expectations or are simply so misled by the rumors and speculation as to not be able to understand the true sea change that is happening at this moment.

Instead, they are simply looking at performance number x and not seeing it outperform number xxxx and calling it a disaster.

Anyone thinking the M1 is supposed to outdo a 12- to 28-core Xeon is clearly delusional or just screwing around.

There are also a lot of people who think their rig is just the bees knees and pride won’t shut them up when they really should.
 
Well, It's Intel that didn't improve much in that time. I don't think you want to compare battery life.
Just saying that 71% increase in performance over 12 year old technology is nothing to write home about.

Edit: What we're observing with the M1 is the natural progression of technology. As technology advances one expects lower power, higher performing parts / systems.
 
  • Disagree
Reactions: diandi
4600U is slightly faster in multicore, but significantly slower in single core.

Zen 2 to Zen 3 IPC improvement will erase that single-core advantage while pulling even further ahead on multi-core plus additional gains with 7nm to 5nm node shrink while retaining 100% compatibility with existing software. M1, though, is good enough for grandma with limited software requirements.
 
There are a lot of people in these forums who have unrealistic expectations or are simply so misled by the rumors and speculation as to not be able to understand the true sea change that is happening at this moment.

Instead, they are simply looking at performance number x and not seeing it outperform number xxxx and calling it a disaster.

Anyone thinking the M1 is supposed to outdo a 12- to 28-core Xeon is clearly delusional or just screwing around.

There are also a lot of people who think their rig is just the bees knees and pride won’t shut them up when they really should.
I was in the camp of people hoping this was a sea change, but I'm just not seeing it.

Apple basically made their own 11th gen Intel Core i7 chip, which itself has fallen behind AMD's Ryzen mobile chips.

Battery life may be a game changer for many, and I applaud Apple for that. But performance? I'm just not seeing it. There are other chips from Intel and AMD that are as good or better.
 
  • Angry
  • Disagree
Reactions: NetMage and P-DogNC
Entry level...in a Macbook PRO.

I boxed up my iMac Pro and am using this PC build specifically because the iMac Pro didn't reach the ceiling of performance that I needed. So if M1 is going to make me switch back at some point, it will need to far surpass the performance of my power-hungry, hot, desktop PC. :D
M1 is not designed for
I was in the camp of people hoping this was a sea change, but I'm just not seeing it.

Apple basically made their own 11th gen Intel Core i7 chip, which itself has fallen behind AMD's Ryzen mobile chips.

Battery life may be a game changer for many, and I applaud Apple for that. But performance? I'm just not seeing it. There are other chips from Intel and AMD that are as good or better.
Can you link to these chips for us uninformed? These all run in the same wattage class right?
 
But it's called MacBook... Pro

I get it that's it's the base model, but they should just call it "MacBook".
As someone pointed or it already outperforms the most expensive 13” Intel variant that’s still on sale as well as the base mode 16” variant. That’s without taking into account you can get through two full business days on a single charge.

For an entry level model it’s plenty “pro”.
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.