Faster per watt I agree. Per clock, they could be somewhat similar with caveats. Per Core, the clock speeds that can be achieved with intel are much higher (even if it throttles). I think both are good enough for 90% of the population.

I don't see anyone building an external compute/accelerator platform around an ARM Mac ecosystem. It's a niche market as is and the direction has always been to integrate functions like this onto the chip / package directly. I think the latter is certainly an opportunity apple will choose as they will be able to claim their new processors have a special sauce that intel does not have and charge an apple premium for it.

Are you suggesting plugging in a dongle that has a CPU on it? I'm very confused if true. As the bandwidth between RAM and CPU is ~50GB/s, any external dongle would not be able to communicate with the system RAM without a huge slowdown, so the dongle would need it's own RAM too, how this would communicate with a GPU is questionable again and this is already a weird crazy expensive dongle.

I think this is the part that will make 3rd party developers give on on the Mac. Mac ports are given the least love as is, mostly because apple will break your application on such a regular basis it's not worth the cost to port/support, but this change adds so much more burden to the developer, I think most will wait a few years before making a commitment unless apple throws money as them.

Takes me back to the Apple IIe that I used to develop 6502 controllers with in assembler. It had a Z80 add on that ran CP/M and Wordstar that I used for writing the documentation.

I remember the Orange PC cards that let you run DOS/Windows inside a Mac. Slow as hell though...

https://www.macworld.com/article/1014858/orangepc.html

> 3. There's no reason a dedicated x86-64 dongle can't be sold for ARM-powered Macs that need to run software that hasn't been ported yet. It would be a spectacular coup if those x86-64 dongles had chips made by AMD but I digress...

Fun suggestion, so I'll bite :-) would a USB-C dongle actually be a speed improvement compared to host dynamic binary translation? Especially since all RAM operations would need to be funneled over I/O...

1. Please don't extrapolate from a useless program like Geekbench to a general concept such as "faster"

2-3. TB3 is a single PCIe x4 link, which is not even enough for a single state-of-the-art SSD. It's certainly not fast enough to connect an entire other computer to, except for certain embarrassing workloads.

When it's a laptop, I'm quite the fan of having as much as possible built into the machine as a single unit. That's the point of the form factor, after all.

I think the last thing the MacBooks need are more dongles.

Is that actually the point of the form factor? Seems like laptops (designed to be easily portable) should be as small and portable as possible with optional add-ons for specific use cases. Desktops can have as much as they want because they’re not designed to be moved very often.

Dongles for vital functions every user will have an ongoing need for are a problem.

Dongles for legacy functions in the process of deprecation that some users may not want/need seems sensible.

I suppose it depends on how quickly they go from "Apple says this legacy" to actual legacy tech.