Apple needs to stop explaining stats in vague weeb speak and just give us what the actual compile times in GCC are.
>Then again, that takes courage.
M3 Macs: there's more to performance than counting cores
31–40 of 419 posts
Re: M3 Macs: there's more to performance than counting cores
#32It seems like the M3 favors efficiency and thermals over raw power. This makes sense for the devices they've put it in. I wonder if we're going to see different processors (M3X or M4) for the next release of the pro desktops, that favor power over thermals and efficiency? Maybe there will be a kind of tick-tock, with odd numbered processors favoring efficiency and even numbered processors for power? M3, M5, M7 for th…
For the M3 and M3 Pro, they kept the same number of cores or in the case of the Pro actually decreased them.
On the other hand, the M3 Max gained 4 Performance cores for a total of 16 cores (12P 4E) vs the M2 Max's 12 cores (8P 4E).
The M3 Max beats the M2 Ultra (2x M2 Max dies) in single and multicore benchmarks.
Seems like Apple is leaning towards efficiency on their lower end chips, but also using the extra transistor density to push performance on M3 Max, increasing the gap between the low and high end chips.
That M3 Max is presumably going to be turned into an M3 Ultra sometime next year with 32 cores, which would roughly double the M2 Ultra multicore performance.
Re: M3 Macs: there's more to performance than counting cores
#33Feels like we’ve gone from “it’s just better, it’s obviously better you can see with your eyes and feel it as you use it” when M1/2 dropped. To trying to justify why the M3 is 20% faster than the M1 and the M2 was also 20% faster than the M1 and weirdly Apple is only comparing it to their older processor. Like people, maybe it’s just an underwhelming update… no need to pretend it’s not.
20% performance increases generation over generation, every 18 months or so, seems pretty great to me.
If people were expecting gains like the Intel to M1 transition on an annual basis I'm not sure that was ever realistic.
Re: M3 Macs: there's more to performance than counting cores
#34It seems like the M3 favors efficiency and thermals over raw power. This makes sense for the devices they've put it in. I wonder if we're going to see different processors (M3X or M4) for the next release of the pro desktops, that favor power over thermals and efficiency? Maybe there will be a kind of tick-tock, with odd numbered processors favoring efficiency and even numbered processors for power? M3, M5, M7 for th…
Doesn't prioritizing efficiency and thermals make sense for any device? Even a desktop has moments when it's doing almost nothing but has tasks that can adequately be handled by an E core where powering up a P core is overkill. Doesn't being efficient mean that more of the thermal budget can be held in reserve for when it's actually needed? Don't desktop users desire for their powerful machine to also be quiet?
Not really, no. Case in point:
https://www.notebookcheck.net/AMD-Ryzen-9-7940HS-analysis-Ze...
Adjusting the TDP from 80W all the way down to 35W costs you relatively little in performance and gives you about the same efficiency as an M2 Pro. That is not done because it does not sell.
> Don't desktop users desire for their powerful machine to also be quiet?
No. That is not an "also" but an "instead". People claim they would make that trade-off but that is just not the case. Same for "make it heavier but give me more battery life".
Re: M3 Macs: there's more to performance than counting cores
#35This is good to know. I worry about the longevity of these new M-series processors from Apple since they're so (relatively) new. What is the usable lifespan of a base M1-MacBook Air for example? I guess I'll find out since I just bought one for my kid who is a junior in HS and I'm hoping this will last until they graduate college.
From my experience with M1, M1 Max, and M2 Max laptops, I think the only real limitation to useful longevity of the M1 machines is configured RAM and Apple's willingness to provide software updates.
A point in its favor is that Apple is still selling the M1 MacBook Air new today as their entry level laptop, which is now 3 years old. And it's still a great machine with better performance and battery life than a lot of competitors and it's completely fanless. I expect Apple to push for dropping new OS support for Intel machines fairly quickly, but the countdown clock on M1 support probably doesn't even start until they stop selling them as new.
My previous Intel MacBook Pro was still perfectly serviceable 8 years after purchase when I traded it in, although it wasn't going to receive major OS updates going forward.
The only time I've had issues with my M1 MacBook Air 8GB is when I temporarily tried using it as a real dev machine while waiting for a backordered company laptop. As soon as you really hit that RAM ceiling due to running docker and big IDEs you really feel the performance drop, but until that point it was perfectly competent, and again this is a fully fanless machine.
Re: M3 Macs: there's more to performance than counting cores
#36This seems to be a lot of effort to rationalize the surprisingly small performance increase from M2 to M3. Initially the assumption was that M2 to M3 would be a bigger step than M1 to M2, not a smaller one. Perhaps TSMC 3nm is showing the limits of scaling?
Isn't it a 15% increase? I really don't consider any double digit percent increases to be small.
Re: M3 Macs: there's more to performance than counting cores
#37Feels like we’ve gone from “it’s just better, it’s obviously better you can see with your eyes and feel it as you use it” when M1/2 dropped. To trying to justify why the M3 is 20% faster than the M1 and the M2 was also 20% faster than the M1 and weirdly Apple is only comparing it to their older processor. Like people, maybe it’s just an underwhelming update… no need to pretend it’s not.
>Like people, maybe it’s just an underwhelming update… no need to pretend it’s not.
"Buy the new M3, a small incremental improvement on the M1/M2" would probably get a lot of people fired as a marketing campaign.
While I agree with you, we live in a reality where hype, hyperbole, misleading, and intentionally manipulative information is accepted and common place for selling things. It sure would be nice to look at a product or service and get a clear comparison without having to read between the lines, pick out subtle vague language usage, and keep up with the latest propaganda techniques but alas, it's everywhere.
On the bright side it should teach everyone you shouldn't trust the majority of information at face value, which is a useful skill in life. On the downside we continuously erode trust in one another and I worry it's wearing on social structures and relationships everywhere as more people see and mimic these behaviors everywhere for everything.
Re: M3 Macs: there's more to performance than counting cores
#38Feels like we’ve gone from “it’s just better, it’s obviously better you can see with your eyes and feel it as you use it” when M1/2 dropped. To trying to justify why the M3 is 20% faster than the M1 and the M2 was also 20% faster than the M1 and weirdly Apple is only comparing it to their older processor. Like people, maybe it’s just an underwhelming update… no need to pretend it’s not.
The M3 Max performs similarly to an M2 Ultra. That feels pretty big to me as a current M1 Max user.
It’s also more expensive than a M2 Max or M1 Max if I’m not mistaken.
Re: M3 Macs: there's more to performance than counting cores
#39Earlier quoted context omitted.
1. I think you set your expectations too high. 2. I assume Apple compared the M3 to M1 because most of the customers they are targeting are still on the M1. M2 customers bought a computer less than a year ago and that pool of people is relatively small compared to the number on M1 today.
> I think you set your expectations too high. Well, they did announce it in an event called "scary fast". I mean there's always marketing exaggeration, but I did expect more than trying to understand if it's even faster at all . Otherwise I'm not entirely certain what the point was.
Literally the only point of confusion here is M3 Pro versus M2 Pro, where Apple seems to have simply made different choices around what the Pro chip should be.
M3 Max is a massive gain over M2 Max. And M3 is a nice improvement over M2.
Hope that helps.
Re: M3 Macs: there's more to performance than counting cores
#40Feels like we’ve gone from “it’s just better, it’s obviously better you can see with your eyes and feel it as you use it” when M1/2 dropped. To trying to justify why the M3 is 20% faster than the M1 and the M2 was also 20% faster than the M1 and weirdly Apple is only comparing it to their older processor. Like people, maybe it’s just an underwhelming update… no need to pretend it’s not.
I bought my M1 MacBook Pro not long after they were released. It's approaching 3 years old which is a pretty standard age for people to start looking at a replacement - I guess that's why they're comparing it to the M1. Slight tangent - even though the MBP has been struggling to handle my dev work (partly because the codebase I'm working on has grown significantly in the last two years) I won't be upgrading. Work bou…
Comparing against the device 2 generations back does seem to make more sense from a “should I upgrade” point of view, and seems like a fine thing to put in marketing slides (as well as comparisons vs current peers, since that’s relevant to the question of “what should I upgrade to.”
The lackluster year-to-year is a bit of a bad sign WRT the long term trajectory, but they’ve been doing this successfully for quite a while, they’ve recovered from worse I suspect.