M3 Macs: there's more to performance than counting cores
eclecticlight.co
eclecticlight.co
If your efficiency cores are always close to max usage, but your performance cores are idle, is your system being heavily or barely used?
I understand that system load isn't really a useful metric between systems, but it's useful to compare on a single system I think. I just want a better at-a-glance thing to communicate to me if my computer is under or overloaded.
(Additionally, do you have to specify that a particular app can run on efficiency cores, or does the process scheduler do it all without input from a human?)
This is in contrast to another contended resource, memory bandwidth, "waiting" for which manifests at the process level as CPU cycles like any other code. It's possible to use profiling tools to distinguish memory waits from other CPU activity, but as far as I know nobody has built the infrastructure to bubble that data up in some form so it could be tracked systemically by the OS.
I can guess why: The memory hierarchy is complicated, and what you can derive about it from CPU performance counters is indirect and limited. Still, even some basic estimation for how many cache lines a process was responsible for driving over the memory bus would be helpful for those building high-performance systems and applications.
additionally, context switches are the same on everything that can run Linux, whereas PMU counters are highly CPU-specific (potentially even different in each CPU stepping), so given the current state of affairs, a generic interface would be very limited.
Some critical path, single-threaded task is at 100% of capacity of a core; the system has 10 cores -- is my system at 10% utilization or 100% utilization?
---
If your system is running it on CPU, GPUs, high-efficiency, low-efficiency, etc....that's the performance level of your system, not the load on your system.
This is nothing new. We've had power-saving CPU throttling for ages. Carry on.
* TSMC N3B being a bit of a flop (yield issues, too expensive)
* Brain drain from Apple's chip design teams over the last few years
* Tim Cook trying to push the average selling price up to keep revenue growth going in the face of sales declines (e.g. hobbling memory bandwidth, reducing the number of performance cores for M3 Pro)
I don't expect there to be a M1 style generational leap for a long time, expect 2010s Intel style yearly performance gains from here on out.
Another point is the CPU improvements are constant. In about two years the base M3 is now on par with the M1 Max.
Even if they did, there is very little in Apple Arcade which taxes the GPU, most target the lowest common denominator in terms of supported iOS/phone combinations.
The original Apple Arcade strategy was for AAA titles, but for whatever reason that wasn’t pursued, so now we have a tonne of casual games and re-releases of old titles.
Apple just seems to run hot and cold on gaming.
Can you prove that statement? I bet you can't, cause it's simply not true. Every Arcade title is playable from an iPhone to a Mac by way of Apple TV. It was never going to get AAA titles.
Apple wants more Grindstones.
I own almost every Apple device in the ecosystem, but I never game on them…
Is it? Does it matter? Unified RAM is cool. But I’d rather have an Nvidia 4090.
Apple Silicon is amazing. But if you’re doing heavy GPU it’s not very exciting.
Intel saw very little gain this year at all in return for a 400 watt power draw under load.
The plain old M3 saw a 20% performance gain along side efficiency gains.
Having a 22 hour battery life is insane and you certainly aren't going to manage that with a 400 watt power draw.
20% increase on performance is compared to M1 not, M2 - which also had 20% increase in performance on M1.
Nope.
> The M3 chip has single-core and multi-core scores of about 3,000 and 11,700, respectively, in the Geekbench 6 database. When you compare these scores to those of the M2's single-core and multi-core scores (around 2,600 and 9,700, respectively), the M3 chip is indeed up to 20% faster like Apple claims.
https://www.laptopmag.com/laptops/macbooks/apple-m3-benchmar...
> 400 watts is on a desktop chip where there is no concept of battery life.
Yes, and in exchange for that ridiculous 400 watt power draw, Intel saw negligible performance gains.
> In some areas, the extra clock speeds available on the Core i9-14900K show some benefit, but generally speaking, it won't make much difference in most areas.
https://www.anandtech.com/show/21084/intel-core-i9-14900k-co...
Intel only wishes they could hit a 20% gain in exchange for all that increased power draw and heat. As that review noted the best improvement they saw in any of the common benchmarks was just 6%.
From a generational perspective, the M3 Max is offering the same level of performance as the M2 Ultra. That's amazing as the m3 max is 12p/4e vs 16p/8e in the m2 Ultra. The M3 Ultra should be a substantial lift.
At least according to Geekbench, it's a 20% performance increase.
> The M3 chip has single-core and multi-core scores of about 3,000 and 11,700, respectively, in the Geekbench 6 database. When you compare these scores to those of the M2's single-core and multi-core scores (around 2,600 and 9,700, respectively), the M3 chip is indeed up to 20% faster like Apple claims.
https://www.laptopmag.com/laptops/macbooks/apple-m3-benchmar...
Along side a battery life increase to 22 hours? It's been a pretty good showing.
Now, if they want a wider core for M4, that means more transistors and more heat. They are then forced to: not go wider, decrease max clockspeed, hold max clockspeed for a pitiful amount of time, or increase power consumption.
On the whole, I'd rather have a wider core and lower clockspeeds then turn the other power savings into either battery life or a few more E-cores.
In case you didn’t notice, A17 Pro on iPhone 15 has hardware accelerated ray tracing as well.
I don't think we're going to see the performance increases past the ~10-20% each fab cycle now.
Performance per watt and having dedicated HW for video decoding / other tasks(AI?) I think might end up being the answer to the continuation of Moore's law. Especially considering that we are in the era of heterogenous computing.
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 the laptops
M4, M6, M8 for the pro desktops
?
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".
It's not done because it doesn't sell in the PC market. Apple's kind of your only choice and if they say you're getting perf/W you're getting perf/W :)
> People claim they would make that trade-off but that is just not the case.
It's not 2 dimensional, tdp vs noise. It's tdp vs size vs noise vs price. You get a large ATX mid-tower and throw some Noctua 140mm fans in there and you won't hear a thing as it dispenses 1KW of heat into your feet area.
There's some jobs I want a fast desktop for and other jobs, like browsing cooking recipes, I'll take my M1 macbook air for.
Consumers purchase large, heavy phones more than one would expect given their pricing and one of the reason they do so is that they have better battery life.
Intel did just ship 14th Gen Core i9 chips with a 400 watt power draw under load and very little in the way of a performance gain.
> In some areas, the extra clock speeds available on the Core i9-14900K show some benefit, but generally speaking, it won't make much difference in most areas.
The most significant win performance for the Core i9-14900K came in CineBench R23 MT... the Core i9-14900K sits 6% ahead in this benchmark
https://www.anandtech.com/show/21084/intel-core-i9-14900k-co...
Having your best benchmark result only see a 6% gain in return for a more than 400 watt power draw makes it pretty clear that just as with the Pentium IV of old, Intel isn't on a sustainable path.
It also makes the M3's 20% performance gain along side efficiency gains look pretty darn good in comparison.
No. If you have the cooling to sustain the higher power mode it can be worth it to pay the power bill to get work done faster. Compared to the productivity gains for compute limited workloads the increased power bill is little more than a rounding error or even a net power saving because you need less supporting infrastructure per worker to accomplish the same assuming that the tasks are even efficiently parallelizable to multiple (human) workers.
Apple is dictating how much power the CPU is allowed to draw and they don't let it scale up. They are also making a static choice about how much die area and power to spend on the GPU, which might not suit every user. I know I personally don't give a rip about the GPU in my M2 mac mini, beyond the fact that it can draw things on the screen.
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.
With higher-end hardware, you should get more meaningful results by running a few copies of the benchmark software in parallel and reporting the sum of multicore scores as the true multicore score. That would reflect the common use case of running several independent tasks in parallel.
When they switch to N3E and get better yields, I imagine that we'll see chip size grow. As we're getting close to the number of cores that the average consumer can use or would want to use in a desktop, I imagine that we'll be seeing an increase in GPU, NPU, and other specialized units instead of more CPUs though.
I don't think they care much about pro desktops given the pretty embarrassing MacPro. They just don't mean much for the bottom line compared to consumer lifestyle devices.
I expect they would be happily rid of the customer segment - annoying power users wanting low-level access and customisation. They keep their machines for too long and don't give much upselling opportunity for subscriptions, fashion accessories, house and family trinkets.
For so long it was just Macbook Air, Macbook Pro, iMac, Mac Mini, Mac Pro. Now there's a whole new family member and it's a desktop. Apple is managing the slow death of desktops very well.
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.
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 bought me a MacStudio (M2 Max), which mainly runs headlessly on my desk (also running Homebridge and plugged into my big speakers for AirPlay). This means I'm keeping the MBP as my portable machine (using VSCode's remote extensions and/or CodeServer to do dev work from wherever). I also have a late-2015 27" iMac at the office (with OpenCore Legacy Patcher so it can run whatever the latest macOS is called nowadays). This also works perfectly well now all the hard stuff is done on the MacStudio - and the screen is still lovely. (My previous 27" iMac was in active service for 10 years, although it was almost unusable towards the end).
Another tangent - I bet that's why they're not doing the larger "pro" iMacs. If it weren't for VSCode Remote Extensions and OCLP, I would have ended up with a beautiful monitor that was essentially useless (as was my original 27" iMac). People who need that extra power should probably avoid all-in-ones and I won't be getting one again.
But for most people, who tend to have a single machine, a comparison to the 3 year old equivalent seems pretty fair to me.
I develop on it every day, and i've no need to upgrade it, so i'll wait for the M4 :)
Is this really true? Three years sounds very new to me, and no one in their right minds would replace it.
there's also the relatively static pricing of these and generally growing wages, making short upgrade times more common.
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.
Mine is the M1-with-touchbar (same design as the intel version) which was released at the same time as the M1 MacBook Air - late 2020.
0. https://everymac.com/systems/apple/macbook-air/specs/macbook...
1. https://everymac.com/systems/apple/macbook-air/specs/macbook...
A new model with the same configuration is also $3899.
Edit: But in any case, the difference would not be huge from what I can see, so I guess my point is moot
If people were expecting gains like the Intel to M1 transition on an annual basis I'm not sure that was ever realistic.
"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.
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 feel like this is giving Apple the benefit of the doubt.
Most people here wouldn't say the same of Intel if they started comparing to 2 or 3 generations ago.
No, most likely they're comparing to M1 because it's the biggest difference that is still plausible to explain.
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.
M3 Max is a massive gain over M2 Max. And M3 is a nice improvement over M2.
Hope that helps.
> Well, they did announce it in an event called "scary fast".
> I mean there's always marketing exaggeration
> I did expect more than trying to understand if it's even faster at all
> I'm not entirely certain what the point was.
That said, early benchmarks are indicating that the M3 Max performance is on par with the M2 Ultra. I consider that “scary fast” myself.
The only real exception to that is the M3 Pro, which is closer to the performance of the M2 Pro at a reduced core count.
The stats compare to m2 are there. They are just not the headline/summary.
Comparing M3s to old Intel Macs would also be lame, and a fairly meaningless comparison.
It would be interesting to know how many people compare M series performance to Intel performance when buying, as those are usually going to be different markets surely?
This is what product iterations look like, M2 only came out a year ago and M3 is a notable speed increase and just as important bump in battery life (22hrs is insane for the performance you get).
They compared to M1 and intel because people almost always wait 1-2 cycles before upgrading because MacBooks easily last 2yrs under heavy use and it’s an expensive upgrade.
Sarcasm obviously. As an Apple enthusiast it’s so annoying how they sniff farts.
QED seemingly works out well for Apple though.. :P
I’m still hoping for some ex Apple folks to create some new version of NeXT computers. I would switch immediately to someone’s alternative offering trying to actually play at Apple’s level of quality.
This is a bad reason to upgrade. If you were supposed to know about it, it'd be in the specs.
It's not there to improve performance or be more forward compatible, it's because the camera upgrades need it.
But yeah 16gb is so cheap Apple stop it
8gb wasn't even enough in 2015!
Apple competes and demolishes anything from PC in battery and build quality. Certainly not in usability and subjectively comfort.
Also, low tier PCs support multiple monitors. Try getting that on the macbook Air.
UI is very buggy and inconsistent.
CLI tools/shell is attempting to follow more-or-less standardish unix/linux setup but fails pretty hard, with many of the same commands existing but behaving just differently enough to be annoying.
Uses it's own set of shortcuts, different from what's standard on windows/linux and most other operating systems.
Not sure what people mean when they say completely vague and ambiguous things like 'usability' and 'comfort' - are you referring to the fact that it has rounded buttons and corners and pretty ads?
It basically falls in between a standard windows and highly modified ubuntu setup, but does far worse at both. The UI, apps, etc is far more buggy and unintuitive than windows, and the os is far less 'unix' and far less customizable than ubuntu.
I'm pretty sure this is simply you expecting GNU and actually getting FreeBSD-based tooling. It's not wrong, it's just different than what you expected.
My Mac and Linux shortcuts align more than my Windows and Linux/Mac ones. For the most used ones it’s CMD + whatever the standard key is for that shortcut, instead of Control. Overal I prefer that the Super key is more useful than what has been the default for many years with Windows.
I also use the CLI for virtually everything on Mac and Linux, MacOS isn’t all that different and feels more like another Linux flavour than it’s own beast.
The only UI gripes I can think off immediately is no window snapping and closing the window doesn’t mean you’ve exited the application. The first requires a third-party tool (I recommend Rectangle), the latter is a change in behaviour.
Frankly I’m not really all that interested in defending MacOS, but I hope you realise that saying “very buggy and inconsistent” without naming anything specific isn’t any less vague and ambiguous than “usability and comfort”.
Your reaction comes off as “I’m used to this, therefore the other thing is bad and unintuitive.” I’m sure this isn’t your intention, so specifics would be illuminating.
I posted a list of recent issues I've run into elsewhere in the thread, but there are many bugs and inconsistencies in macos:
- Doc breaking/becoming inaccessible.
- Running app windows disappearing/becoming inaccessible.
- Cursor/caret disappearing when editing text.
- Can't move windows between workspaces.
- Constant issues with external monitors.
- Switching between windows via command-tab regularly breaks.
> My Mac and Linux shortcuts align more than my Windows and Linux/Mac ones
Because.. you changed your linux shortcuts to match macos? The most obvious example is that ctrl+c/s/v etc are instead command+c/s/v on macos.
> I hope you realise that saying “very buggy and inconsistent” without naming anything specific isn’t any less vague and ambiguous than “usability and comfort”.
There are literally dozens of examples of issues listed in this thread. I hope you realize that saying 'give me examples' when there are many many examples all around the post your replying too is a bit disingenuous. I can't keep repeat ing what I've already posted in the thread in every single comment.
Just a couple concrete examples, if you open an app in a workspace, then switch screens to a different workspace, then click the app in the dock, nothing happens. I would expect to be taken to the screen and have the app made visible, but instead, nothing. I kept thinking that the app must be frozen or something until I switched screens and found it.
Another example, I was carrying my laptop to and from work. I put it in my backpack with padding that protects the laptop. I didn’t jostle it around, I literally just carried it to and from work. I get home and the screen is in some sort of weird flickering bugged out state. I had to forcefully restart it just to get it working again.
With all that said, the trackpads and gestures on Macs are amazing. The displays are also very visually appealing. The performance is good.
I find that more often than not I can't make it through the Windows setup without worse janky stuff happening. Pretty often when toggling off all the bullshit privacy settings that shouldn't be opt-out to begin with, I'll get a visual indication of the switch starting to move after my click, then turning around and going back to the default—so my click was definitely received, but rejected somehow. That seems worse to me than a correct response delayed.
> if you open an app in a workspace, then switch screens to a different workspace, then click the app in the dock, nothing happens. I would expect to be taken to the screen and have the app made visible, but instead, nothing.
There is a visual indication in that the contents of the menu bar change to reflect the newly active app; unlike on Windows a Mac app can be active without having an active or foreground window. There's a system setting to control whether to switch spaces in this scenario, but I don't recall whether the behavior you describe is the default or something you accidentally configured to annoy you.
macOS is UNIX certified and POSIX compliant. You're probably expecting GNU commands, but macOS is based off of FreeBSD (and is not related Linux).
Mac OS predates both.
Also, this is personal preference, but I find engaging Command with my thumb far more comfortable than Control with my pinky.
CLI tools/shell is attempting to follow more-or-less standardish
unix/linux setup but fails pretty hard, with many of the same commands existing but behaving
just differently enough to be annoying.
Everyone knows that macos (and windows) took a lot from unix/bsd. But that does not mean they are actively following any kind of reasonable modern standard. And saying they might be following some 30 year old supposed bsd standard is pretty hilarious for an OS that portends to be cutting-edge, intuitive and well-integrated.
What is this for? Games? I avoided this to save money the last time I bought a phone. I honestly can't think of use case where a phone display needs to update higher than 60 Hz
Instead VFR allows saving battery by slowing down the refresh rates, down to as low as 1FPS for static or high latency content. That's part of why always on display is only available on the 15 Pro: at 60Hz it's a battery killer.
> Sort of like going from a slowly accelerating station wagon to a Porsche/sports car even when (capped by the speed limit) if you've experienced that.
So... functionally useless.
The bigger difference I notice is in loading times for apps.
This analogy is also flawed, of course.
This is obviously not a critical feature, mind you, but it does add to the experience of using a device, even if it's just productivity-related tasks.
(Much like how the iPhone Pro has faster USB-C data transfer speeds vs base iPhone)
or
Give me an "air" with two external monitors and 64GB ram.
The pros are clunky and heavy. I'm on an air, and will stay there for a long time because if this
It uses the 6950 DisplayLink chip, which can do 4K@60Hz.
It's 90 dollars and drives 2 screens.
Software is less good. I had to enable Rosetta2 to get the pkg to install. Then you have to boot to recovery mode to allow signed 3rd party drivers. And you get a creepy notice that someone is watching your screen, which is how the display driver works.
Performance is pretty good, just a bit laggy on mouse movement.
The way I have it set up: the i-tec dock is connected to a regular USB-C hub (from Ugreen). The USB-C hub is also connected to a 4k monitor. This way I connect 1 cable to my Mac and get everything: power delivery, Ethernet, peripherals, 4k monitor running natively and 2 2K monitors running on displaylink. It is… perfect. I havent touched my desktop computer for about a year.
Basically it is better to use the Displaylink monitors for static content - running 4K video on a 4K monitor on Displaylink would probably take about 40% CPU on my M1 chip. So everything dynamic goes onto my native 4k monitor, whereas the Displaylink monitors have easier content - browsers, vscode, notes etc.
But like, I regularly also play video on my 2K displaylink monitors and honestly I never ran into issues, or noticed a difference. Just dont do this on 4k monitors I guess.
Sorry for the delay, still havent figured out a way to get notified about replies on HN.
Since I also don't get notified of replies I've been checking back on this comment in hopes that someone had a clever solution like yours. Thanks!
At least, not the last time I tried.
It supports a 6K screen in addition to the built-in screen. It's reasonable to say that if you need 3 screens to get your job done, then that is not representative of the market for apple's lowest-end laptop.
This is arbitrary market segmentation. I need two external monitors mostly because I share the same single cable to my dock with work and because macOS is so stupid about monitors it randomly connects to one or the other, not both. So I have to manually power off the wrong monitor each time and turn it on for work. Really annoying.
Btw a quick check on Elitebooks start at $1,760 and support at most a single 5k screen.
RAM and fan has nothing to do with it, the cheapest low-end Windows laptops can do this with ease, it doesn't stress the RAM, CPU or GPU at all.
- M-series uses unified memory, the ram does in fact matter.
- Heat also matters, because throttling. The Air uses a fanless, heatsink system.
- Whatever cheapest low-end PC you’re imagining is not fanless and not running an external 6k monitor at 60Hz.
- None of those systems are optimised to maintain performance while possessing an 18 hour battery life. None of those even have an 18 hour battery life.
The Air serves a clear market segment. It’s their entry level laptop, the problem isn’t the laptop.
It may also be they have chips that have bad display controllers and they are using this as one way of offloading those chips with the bad controllers lasered off.
- Monitor randomly resets/readjusts for no apparent reason. Like multiple times every hour.
- Windows disappear, become inaccessible after moving between monitors, even though it still open and active according to doc/task list.
- Why can't I move a window to a monitor/workspace that has a maximized window? Like, you can do it by un-maximizing the window in question, moving the other window over and then re-maximizing the window again. But why is this nonsense needed? What problem could this restriction possibly be solving?
- Lots of other monitor/workspace related problems (quick google will show dozens related problems without any obvious solutions or explanations for the completely nonsensical behaviour).
I really don't understand how people can say macos has good and consist overall UI? I mean, yeah - it's consistently buggy and un-intuitive:
- Doc constantly breaks/becomes inaccessible. This is a known problem for at least 5+ years - the solution is to manually kill and restart the process???
- Text cursor/caret randomly disappears when editing text, so you can't see where the cursor is, and you can't fix this unless you restart the app (happens to pretty much all apps).
- Was working with unicode characters recently, now whenever I press command+s to save something, it gives me a visual unicode character selector popup, with no apparent way to stop/cancel this behaviour from the popup itself.
- Bad defaults in terms of keypress repeat times and rate. No apparent way to change this from settings - need to run commands and re-login to test new behaviour.
Just an overall crap OS and UI imo.
> Why can't I move a window to a monitor/workspace that has a maximized window?
Because it’s fullscreened, not maximized. macOS doesn’t really have window maximization in the traditional sense out of the box, you need a utility like Magnet or Moom for that.
That fullscreen mode was introduced in 10.7 Lion and a lot of long time mac users have found it silly from day one. Personally I never use it.
> Text cursor/caret randomly disappears when editing text, so you can't see where the cursor is, and you can't fix this unless you restart the app (happens to pretty much all apps).
I’ve seen this, but only in Chromium browsers and Electron apps. Seems like it might be a Blink bug.
Regarding other OSes, multimonitor on Linux is mostly fine (so long as you’re using Wayland; X11 is another matter especially if you’re doing something slightly uncommon like using two GPUs, in which case xorg.conf mucking will likely be necessary).
By far the most frustration I’ve had with multimonitor is in Windows, which is generally weak there. IIRC it only recently gained the ability to set per-display wallpaper; before you had to glue wallpapers together into a single image that spanned across them, which is silly.
I use it to compartmentalize stuff I'm working on, and 4 finger swipe between them.
I have a couple instances of VSCode, some app/debugging browser windows, some chrome profile windows etc... all running full screen and I spend my day brush swiping between them.
It may be different for me because I work on a 14" macbook pro, mostly at coffee shops or unusual work locations, so I don't have a large monitor setup. I don't think I'd use it much if I had more of a traditional desk/multimonitor config.
I use workspaces on my linux laptops all the time - this 'feature' has existed for ~20 years, and is not hard to implement. The difference being that macos seems to force the restriction of having only 1 window per workspace and not being able to drag a window from one workspace to another. If that's the behaviour you want (one window per workspace), you can easily operate in this way without having the forced restriction.
Generally I’m working at my desk with at least 2x 27” displays. If I’m out somewhere it’s instead 16” MBP + 12.9” iPad with Sidecar.
I don't really buy this explanation. I'm talking about using a single external monitor here, a monitor which I regularly also use with linux (intel/amd) laptops without a single issue.
> Because it’s fullscreened, not maximized. macOS doesn’t really have window maximization in the traditional sense out of the box, you need a utility like Magnet or Moom for that.
That's not really a good reason though. It still doesn't explain why the restriction exists. Why can't a non-maximized/fullscreen window be displayed on top of a fullscreen/maximized window? What problem does that solve?
> That fullscreen mode was introduced in 10.7 Lion and a lot of long time mac users have found it silly from day one. Personally I never use it.
It's default though.
Might be model-specific then. It’s not something I’ve seen with displays from Asus, Alienware, and Apple. I briefly owned a Dell monitor that would periodically flicker but it got returned.
> That's not really a good reason though. It still doesn't explain why the restriction exists. Why can't a non-maximized/fullscreen window be displayed on top of a fullscreen/maximized window? What problem does that solve?
Probably because it’d be easy for windows to get “lost” if the fullscreen window were focused and non-fullscreened windows fell behind it, with there being no obvious indicator that those windows exist.
I would not buy any new monitor for MacOS that does not explicitely advertize MacOS support.
Agreed, however it's arguably for a different mental model. If people think of it as "focus mode" or "workspace mode" it makes more sense. Four finger swipe to slide between the workspaces or focuses.
More importantly, you don't need MOOM.
- - -
To maximize a window to the dimension of the screen without entering full screen mode, either:
1) hold shift option ⌥ and click the green maximize button on the top left of the window
- or -
2) hold the Option key and double click a corner of a window to maximize without full screen focus, and doing that again will size it back to where it was
This is a handy trick to know, but has caveats. Option-green-functionality is actually defined by apps, not the OS, and so in some cases it will for example act as a “fit window to content” button.
Option-double-clicking a corner appears to be consistent across windows however.
I've seen all of those things listed.
It would be one thing if OSX/Linux/Windows UIs would just stay at their basic usability from around 2010. They haven't. They just get steadily worse.
OSX has been the most stable of them, quirks and all, even with a goddamn architecture change, but its closed hardware, a forced upgrade cycle, and bad backwards compatibility.
Linux once would just rewrite window managers every 5 years as soon as they got stable, now Linux is rewriting with Wayland and Vulkan, and ... about 5 years in they'll probably start rewriting those once they get a little stable.
Windows? Committed UI suicide with the tiles and two desktops thing in Windows 8. Now there's ARM in the future and a break with the only thing it has going for it: backwards compatibility.
But yes, everything the author complains about happens in OSX with laptop + monitor / dual monitors, and even without with disappearing mouse cursors.
(And I for one hasn't bought a Macbook since 2020 because I am not going to spend at least $1,999 just to get dual monitor support. A $500 asus laptop can do dual monitor without any problem, and it turns out that machine is good enough for my productivity needs. That money is better spent elsewhere)
Obviously you have some kind of problem with your system.
- Windows disappear, become inaccessible after moving between monitors, even though it still open and active according to doc/task list.
This indeed happens relatively often if you have multiple monitors and switch between them for any reason. e.g. in my case I have two machines and two monitors, sometimes I switch the primary monitor to a specific machine and this almost always fucks up macOS. Solution is to disconnect and reconnect the monitor.
- Why can't I move a window to a monitor/workspace that has a maximized window? Like, you can do it by un-maximizing the window in question, moving the other window over and then re-maximizing the window again. But why is this nonsense needed? What problem could this restriction possibly be solving?
A lot of people who use macOS agree that the fullscreen window thing is needless and makes for quirky behaviour.
- Dock constantly breaks/becomes inaccessible. This is a known problem for at least 5+ years - the solution is to manually kill and restart the process???
- Text cursor/caret randomly disappears when editing text, so you can't see where the cursor is, and you can't fix this unless you restart the app (happens to pretty much all apps).
Yep, happens quite frequently to multiple people I know and in multiple apps.
- Bad defaults in terms of keypress repeat times and rate. No apparent way to change this from settings - need to run commands and re-login to test new behaviour.
Indeed this is very painful for people who are non-developers and are used to be able to have higher repeat rates.
They make a small MacBook Pro that is suited for that task.
It would be annoying if you had to get a 16” laptop to be able to hook up to multiple external displays. I love my 16” MBP but my Air is the one that goes everywhere in my handbag.
[1] https://www.apple.com/macbook-pro/specs/ (scroll down to “Display Support”)
Also, the base MBP 14" doesn't support more than 1 display either.
They're selling a $1600 machine which can't drive two external displays, it's sad. Intel's HD Graphics have been doing better since 2012 and they're trash.
It is Apple’s best selling computer by quite a bit. They sell metric assloads of the $999 base model each fall when school starts.
IMO the $999 one (or $899 with education discount) is literally the best price:perf ratio of any computer available today or at any time in my recent memory. It’s astounding how good it is for that price.
> IMO the $999 one (or $899 with education discount) is literally the best price:perf ratio of any computer available today or at any time in my recent memory. It’s astounding how good it is for that price.
It is possible for your comment to be correct while the poster above is also correct. The M chips are amazing, but let's not pretend that Apple doesn't knowingly gimp the hardware to upsell the more expensive versions.
"But that would make it more expensive."
Yes it would... by pennies. It is a bit ridiculous to sell a phone as expensive as the current iphones and limit them to USB 2.
- the 14" M3 is $1600, but limited to a single external display, and actually only has two TB ports, it's just sad
- the M3 Pro is limited to two external displays, despite an entry price of $2000
$3199 is the baseline to be able to use 3 external displays (although at that price you can plug up to 4).
Really looking forward to some detailed M3 Pro analysis.
The M3 Pro's "reduced memory bandwidth" is still double the memory bandwidth you see on Intel and AMD's HEDT chips.
Step up to the M3 Max and you're looking at five times the memory bandwidth of Intel and AMD's chips.
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.
With so little RAM had to sacrifice ability to properly run VMs, but yet till this day there just no comparable hardware on market.
8GB versions though... Certainly Apple should be damned for selling laptops with 8GB RAM in 2023 when my x220i ran 16GB in 2011. At some point they will all become e-waste due too little RAM or dead soldered SSD because of extreme swapping.
I would not recommend the 8GB variant to anyone who plans on using it for more than a couple browser tabs and some light tasks.
Which is basically all my kids do. Less than 10 tabs, nothing else.
Apple Silicon will definitely be the architecture best supported by Apple for the foreseeable future. There is no downside to it in terms or reliability or longevity.
Sure, macs from 20 years ago still work "fine", but the reason they aren't widely used anymore is not the lack of software updates.
I kept my previous 2014 MBP for 6 years and I can't see this one being any different.
Every new release I drool over getting the new shiny but the reality is that for my personal laptop it's AOK for almost everything I do. Sometimes a bit slow and frustrating due to the RAM but again, that's on me.
I have a M1 Pro since release day and I don't see myself wanting to replace this until probably the M5 is out.
I tend to run it with a large external 4k 120hz screen and don’t see the need to upgrade for better IO for a long time and the thing is very, very fast.
Want 3 monitors? Have to pay for the Max.
https://www.macrumors.com/2023/11/02/m3-chip-still-supports-...
Regardless, most people aren't going to be plugging in three monitors into their laptops, so most people aren't going to care about this.
Even my crappy little Lenovo M600 with an N-series Celeron supports 3 displays. Two 4k ones fine. I didn't have a third to test it with.
It's either an architectural fuck up or intentional segmentation.
Do you think there is any chance that Apple would have had to make some engineering compromise (cost, performance, efficiency) for a feature that very few people would use?
> Adding support has a cost that most customers don't need to pay.
> most people aren't going to be plugging in three monitors into their laptops, so most people aren't going to care about this.
Many people want portability, but also want to use external displays at home or at the office .
I’m not trying to justify Apple here, but this usage seems quite niche and it’s understandable to me to need a non-base setup. It doesn’t sound ridiculous at all. As a matter of fact, the vast majority of notebook users never even plug a single monitor in.
I say it’s ridiculous because the computers I’ve been using over the past 10 years — most of them much less expensive than a Max — have had no issues with them. Not because it’s a common need.
They are saying a single 4K feed, but if you could break that into segments it would change the game. That would be 4 x 1080p screens + the laptop.
If you could slice the rectangles anyway you wanted and rotate them individually then you have the perfect environment. Which you would be able to change instantly, presumably, with Mission Control.
Personally I would pay lots of dollars for that.
Can I sidecar to two or more iPads with this yet?
--
"Use an iPad as a second display for a Mac"
One I can understand as I used to travel with my iPad Pro and used it as a second screen. But two? I’ve switched to a much lighter and much nicer UHD HDR usb-c monitor that is amazing for the price and the weight difference.
You also don’t get the random disconnections when sidecar weirds out for no reason.
Again, no idea if this is actually the case / for other workflows than mine. I would be curious to know if anyone else had made the same observation potentially with actual “high load performance” data to back it up?
The company has a about as much ethics as wet tea towel. A facade of good intentions masking greed. I couldn't care less if their laptops get an hour extra battery or are a few seconds faster. The company is scum from an ethics and waste standpoint. Surprises me so many can turn a blind eye to it for 3 months of chart topping numbers.
Which could be seen as an indication that those cores have less caching and less parts for prefetching and stuff like that.
The efficiency core would do less things per cycle but also use less power per cycle. The performance cores would do 3 instructions in a cycle but the efficiency core might only do half an instruction.
ON M3 PERFORMANCE GAINS:
The jump from M2 to M3 seems smaller than M1 to M2, especially for the regular M3 chip. Some speculate this shows limits in further scaling down process nodes.
The M3 Pro reduced performance cores from 8 to 6 compared to M2 Pro, suggesting a focus on efficiency, yields and costs rather than maximum performance.
But the M3 Max increased performance cores from 8 to 12 versus M2 Max. It matches or exceeds the M2 Ultra, indicating significant gains at the high end.
The M3 line overall shows Apple is diversifying core configurations across the range. This makes comparing performance gains more complex than simple core counts.
There is debate around how much benchmarks like Geekbench reflect real-world usage. Things like frequency management and cluster configurations affect multicore performance.
The 20-30% gains over M2 may seem small yearly, but comparing to M1 shows solid doubling of performance over 2 years.
ON EFFICIENCY CORES:
Some argue the M3 wasted the process shrink on just frequency gains rather than wider cores or gains in other areas.
But others note efficiency is still improved. The regular M3 efficiency cores clock higher while using the same power as M1's.
Efficiency cores handle lightweight threads well, not just background tasks. Their performance can be significant when frequencies are maximized.
ON THERMAL MANAGEMENT AND BATTERY LIFE:
The M3 line generally favors efficiency and thermal management over peak performance. This suits laptop use cases well.
But it's unclear if a future M4 will tune for performance over efficiency in desktop models, or just add more cores.
Either way, the 22 hour battery life on M3 Air is seen as a major achievement showing efficiency strides.
Both in Single and Multicores and GPU memory bandwidth
https://browser.geekbench.com/processors/intel-core-i9-13900... https://browser.geekbench.com/v6/cpu/3364975
Yes there are competitor chips from AMD and the like that are faster when plugged in, but at a power budget that mean they are severely throttled when unplugged. This is what Apple cares about, and at this point they are unmatched. Apple likes to have fast desktop machines (and they do), but they don't care about that nearly as much as they care about laptops-in-laptop-mode. We are a couple of years into this, and Intel is making noises about trying to match this, but has not yet, and Apple seems to be pulling further ahead in specifically this area.
And they have a huge overlap in this focus in the development of the related processors for their iPhones/iPads/AppleTV products, and the upcoming headset. A lot of the development work gets largely reused in that other space, making Apples ROI even better.
So long as their is a big enough market that cares about that (and from the look of sales, there is), Apple's strategy seems to be a winning one.
Only a tiny, tiny fraction of people who buy computers have conversations like this with their friends. I am a software engineer and could not care less which chips my friends have in their laptops.
The biggest advantage of ARM over x86 is security, efficiency is second. Performance is nice to have but is kind of coincidental (depending on workload) and I'd expect everyone else to catch up.
So there's got to be something either more productive or more grass-touching to do.
I would point out that Apple had no first mover advantage with the iPhone. Apple was using standard ARM cores for the first 5 years. It's not like ARM didn't have a multi-decade head start on Apple designing ARM cores.
There are certainly risks, but so far it looks like Apple is making the right decision. Intel and AMD are mostly still targeting a higher power/thermal level than Apple is looking for. Apple likes being able to run things without relying on an external GPU. Having the ability to design things themselves means they're able to make what is most important to their users.
With Intel, Apple was always at the whims of what Intel wanted to produce. It took forever to get the 1038NG7 28W part from Intel which meant that Apple couldn't offer a 13" laptop with the speed that a lot of users wanted. It also meant that they were beholden to crappy Intel graphics - even as they paid up for the Iris graphics.
With their own CPUs, their destiny is in their hands. It's worked extremely well for the iPhone and it's working well for their Macs too.
One of the things to remember: Apple already needs to design these cores for their iPhones and iPads. Once you're doing that, it makes a certain amount of sense to re-use those core designs for the Macs. It isn't zero effort, but they aren't starting from scratch.
I'd also note that Apple tends to do less than a lot of companies and the same applies to their processors. Intel, AMD, and Qualcomm are trying to make parts for a huge range of devices. Apple has a much narrower field of products. While Qualcomm is trying to create processors for $100 cheap phones, Apple just goes with a single CPU for its mobile devices (sometimes using last year's CPU for some devices). With the Mac, Apple has a little more variety, but it's still pretty constrained. An M Ultra is basically just two M Maxes put together. Most of the time, the design is basically the same and Apple has just changed the core count or something like that.
Will Apple compete with Nvidia's GPUs? Probably not, but an M2 Ultra is competing with an Nvidia RTX 3070 desktop GPU. Sure, that's not the current generation or Nvidia's highest spec, but it's still good - and OpenCL isn't great on Mac so it isn't even a fair test. The new M3s have much upgraded graphics and it'll be interesting to see how well they do.
You can say it has never worked before, but I think that might ignore a few things. First, one of the reasons that Intel came to dominate things is because everyone who tried to vertically integrate their processors tried to charge too much. Regardless of what you think of Apple's pricing, they aren't charging more for the privilege of their M processors than they were for their Intel ones. I think it also ignores the fact that Apple has so much money. Finally, in terms of cores shipped in the segments that Apple is shipping them, they're huge. ARM isn't shipping many X-series cores (their top performance cores). They're mostly shipping lower spec'd cores. There aren't a ton of flagship Android phones being sold. Intel is mostly shipping lower-end laptop CPUs destined for machines in the $400-800 range, server CPUs, etc. Apple has a lot of scale for the cores it is designing.
There is risk, but Apple took that risk a decade ago with their iPhone CPUs and they've had a great advantage there. While Intel and others are looking to revitalize their CPU game, it seems like they're doing it at a higher thermal/power level than Apple is looking for - and trying to benchmark themselves against Apple parts at a fraction of the power. Apple is getting to design parts that do what they need and they've proven that they can beat the industry for more than a decade. I'd say it was the right decision to move to Apple Silicon for Macs.
As for the rest, Apple enjoyed a lead in the phone chips for a while, but a lot of it is related to the cash at hand and the possibility to sell most of your products at very high margin. Androids didn't invest as much money, because there is significantly less people willing to put as much cash in a phone if it doesn't come with the "social status" thing Apple has. And now even though the Qualcomm chips are somewhat worse than Apple's, it doesn't matter for the vast majority of people. In the end Apple went and chased premium margin instead of volume and I think it's going to bite them in the ass in the long term because in technology volume and network effect are what matters. There are many "superior" technologies that disappeared or never really took off just because of that, so I doubt Apple will fare much better. I think it's all downhill from here and by the time they notice they actually have to compete on price they will have lost the war since there will be less people willing to go for the non-standard. But then we will hear about how their competitors are villain monopolist oppressing them even though they had the money and means to pursue a more general competitive approach.
Apple fans seems to believe they are winning with their efficient chips but as far as I am concerned, they are losing everywhere it matters. High performance desktop, device convergences, cloud, AI, gaming, 3D focused softwares... They still have 3 OS and laughed at Microsoft unifying strategy, but now a Surface can run both desktop software and more mobile optimized software gracefully and you still have to run a half assed iOS "big" version on a 1k+ iPad Pro.
Time will tell...
>Then again, that takes courage.
Also, because I've disagreed so much with Apple's decisions in the past years I've abandoned their ecosystem altogether so I'm also much less invested in the topic. Though I still use a Mac for work as a "least bad" option.
Too bad because he did have good technical insights.
In 2004 I moved to Mac because it was a powerful and configurable Unix OS with the benefit of a consistent UI (nothing on Linux was there then, it was a mess) and major commercial apps like Office and Photoshop.
The latter are still true but the platform is so locked-in that most of its features are useless to me as a multi-OS person. And the hardware is quite locked down as well which simply doesn't work for me. A lot of the reasons for this are not user-centric but commercial.