Iphone 17 Chip Becomes the Fastest Single-Core CPU in the World on Passmark

But the average user will never encounter this. Typical web browsing and office tasks are bursty and mostly single threaded.

Gaming is the only area where it may be more of a problem. But it’s fine for this to simply not be a great gaming laptop. Most laptops aren’t.

Claude Code, some light video and photo editing, YouTube, and Netflix.

Not sure what others using an entry level laptop would expect it to do.

The A series has been passively cooled for 15 years inside of systems with much less thermal mass.

Ah but a Chromebook or low end budget PC laptop will? From experience these things fire up like jet engines just to open a text editor.

I would expect to see them use the same sort of game plan for an A series MacBook that they used with the iPhone SE.

Use previous gen parts for items like the screen and body (for cost savings) along with current gen SOCs.

Apple TV 4K at 200, MacBook at 600

Back of the napkin math but it checks out.

With all of Apple's service offerings these days, they could also potentially justify slim margins by positioning the A-series MacBook as both a loss leader and gateway drug.

The iPads even more so, as some literally have the same kinds of hardware as a MacBook already (minus the keyboard detaches).

For whatever reason the community now is filled with a weird mix of corporate bootlickers who want to give the largest corporations money while they take away our freedoms and they simultaneously want to make known their entitled behavior by claiming individual developers and small businesses should only ever give away their software for free.

It was bad enough people here chime in technical conversations that they have no experience with loudly contesting the points of actual experts and practitioners, but now they also want to tell us that we don’t have a right to use our property how we want.

If I pay for hardware, I want to use it however I want. I know that is a fucking crazy idea for them corporation bootlickers.

Interesting how people rationalize this stuff. My phone can dock to a screen; I've never used the feature, but it doesn't obstruct anything I do. It's a nice-to-have, and it would be kinda appealing if Firefox and Spotify both work like normal. I might even deign to say I could get work done on it (though I've never tried).

Presumably the real reason is that Apple is still afraid to segment their market. A plug-in iPhone would stop people from buying the AppleTV or Mac Mini for home theater applications.

The biggest hurdle standing in the way is that making a single one of iPhone/iPad/Mac too powerful (in terms of usability, not just raw processing power) will take away sales from the other two.

s/uninterested/unaware/

In reality, for such hardware to make sense, it would have to be a full MacBook Air minus the PCB. Would you be willing to spend 500-1000 USD for a piece of hardware that only works when your phone is connected? (i.e. an iPhone accessory)

Did you come to that conclusion based on the market not using a product that doesn’t exist?

Offering a dockable screen/keyboard/mouse, using the phone battery/compute/storage seems like it would be trivial for Apple.

Obviously cannibalises laptop or tablet sales, but that's not the market's disinterest.

It would mean a lot more work for developers though if your app needs two different UI designs.

One issue that sticks out is that touch controls of a usable size just take up so much more screen space.

Also, look at how many years it took Microsoft to provide touch friendly access to the Windows control panels.

I stopped using Windows when Microsoft made it obvious that they fully intend to force users to use an online account to log into their own local machine.

Requiring an online account if you want to use optional online features was perfectly acceptable.

Needing an online account to access your own PC?

Absolutely not.

The laptop has a device makes less and less sense now that the cpu and gpu inside a phone are good enough for most. It’s propped up only because phone providers artificially limit what the software on the phone can do.

It obviously doesn't scale well if every potential end user has to benchmark every device.

SPEC has been the industry standard performance benchmark for comparing between different CPU architectures for decades.

It takes all freaking day to run, but Anandtech published the benchmarks as soon as they got their grubby little hands on a new core design for every well known architecture.

Is GeekerWan on YouTube the only outlet still doing this today, albeit in Chinese with English subtitles?

You would think that Chips and Cheese, at least, would take up the gauntlet.

Pushing this point further, x86 chips are also slower when the entire task fits in cache.

The real observation is how this isn’t some Apple black magic. All three of the big ARM core designers (Apple, ARM, and Qualcomm) are now beating x86 in raw performance and stomping them in performance per watt (and in performance per watt per area).

It’s not just apples deep pockets either. AMD spent more in R&D than ARM’s entire gross profit margin last I checked. Either AMD sucks or x86 has more technical roadblocks than some people like to believe.

Meanwhile the AI Max+ 395 has at least twice the bandwidth + same number of cores and comes to more like a ~15% loss on single and ~30% loss on multithread due to other "traditional" reasons for performance difference. I still like my 395 though, but more for the following reason.

The more practical advantage of soldered memory on mobile devices is the power/heat reductions, same with increasing the cache on e-cores to get something out of every possible cycle you power rather than try to increase the overall computation with more wattage (i.e. transistors or clocks). Better bandwidth/latency is a cool bonus though.

For a hard number the iPhone 17 Pro Max is supposed to be around 76 GB/s, yet my iPhone 17 Pro Max has a higher PassMark single core performance score than my 9800X3D with larger L3 cache and RAM operating at >100 GB/s. The iPhone does have a TSMC node advantage to consider as well, but I still think it just comes out ahead due to "better overall engineering".

So I think there's more to it than memory bandwidth.

This makes a lot of sense. If the calculations are fast, they need to be fed quickly. You don't want to spend a bunch of time shuffling various caches.