There’s literally nothing on the market that even remotely compares to M series chips right now in terms of performance and battery life. Macbooks are great machines in terms of hardware, and while macos has been enshittifying, it’s still a unix that works fine for dev work. So plenty of experienced devs use macs. You can also put Asahi Linux on them, which works fairly well at this point. The only thing that it can’t do is hibernate. Of course, app selection with it is more limited, but still works as a daily driver.
How well does this work? Is it like Linux on Chromebooks where something could break at the drop of a hat and you have to fight the computer to get it installed?
Saying M series is far behind is a wild take when you look at the actual numbers. Check out the benchmarks. The M5 isn’t just keeping up. but literally beating the flagship desktop chips in single-core performance.
Check the latest Tom’s Hardware coverage on the base M5. The M5 is actively humiliating flagship desktop silicon in single-thread performance. In a recent CPU-Z benchmark, a virtualized M5—running through a translation layer on Windows 11, mind you, and still scored roughly 1,600 points. Compare that to AMD’s upcoming gaming king, the Ryzen 9 9950X3D, which sits around 867.
That’s a roughly 84% gap in favor of a mobile chip running in a VM. While a base 10-core M5 obviously won’t beat a 16-core/32-thread desktop monster in raw multi-core totals, the fact that it’s gapping the fastest x86 cores in existence by nearly double in single-core IPC, while sipping tablet-tier power, is genuinely absurd. The mobile-grade architecture argument actually works against your point here.
but literally beating the flagship desktop chips in single-core performance
See, this is what I despise about x86. AFAIK it’s literally RISC on the bare metal but there are hundreds of “instructions” running microcode which is basically just a translation layer. You’re not allowed to write code for the actual RISC implementation because that’s a trade secret or something. So obviously single core performance would be shit because you’re basically running an emulator all the time.
RISC-V can’t come fast enough. Maybe someone will even make a chip that’s RISC-V but with the same instruction/microcode support as x86. So you can run RISC-V code directly or do the microcode thing and pretend you’re on x86. Though that would probably get the shit sued out of them by Intel because god forbid there’s actual innovation that the original creator can’t cash in on.
only if you are a first world dev that can shell out (good) used car money for an overpriced laptop. i bet you could get that in that overall performance ballpark for much cheaper.
Sure, they are expensive, I’m simply pointing out that it is a genuinely good architecture. And you really can’t get the same performance with CISC. I’m personally hoping we’ll start seeing RISCV based machines that are built in a similar way.
i liike mac’s too and i’ve been using them for work since 2008; but i would never buy one for myself unless linux starting working on them better than asahi does rn.
I got one from a startup I worked at a couple of years ago, and then when the whole Silicon Valley bank crash happened they laid me off, but let me keep it. And yeah Asashi is still pretty barebones mainly cause you can basically just use open source apps on it that can be compiled against it. I’m really hoping to see something like M series from China but using RISCV and with Linux.
you do if you use eg a jetbrains IDE and your codebase is all dockerized and requires 34 separate containers to be running and also the company makes you install a “security” software that constantly scans every fucking file on the machine…
There’s literally nothing on the market that even remotely compares to M series chips right now in terms of performance and battery life. Macbooks are great machines in terms of hardware, and while macos has been enshittifying, it’s still a unix that works fine for dev work. So plenty of experienced devs use macs. You can also put Asahi Linux on them, which works fairly well at this point. The only thing that it can’t do is hibernate. Of course, app selection with it is more limited, but still works as a daily driver.
How well does this work? Is it like Linux on Chromebooks where something could break at the drop of a hat and you have to fight the computer to get it installed?
The main problem is you’re pretty limited with software since you can only run stuff that’s been compiled against it.
Doesn’t the Mac have hardware x86 emulation? Or did they remove that because they want everyone to move to ARM?
@HiddenLayer555 @yogthos Yes using rosetta2
it’s all ARM now, there’s software x86 emulation on macos. I guess you could run x86 vm on Linux, but not sure how fast that will be.
Battery life? Yes, because it’s (mobile-grade) ARM. Performance? They are far behind high-end Ryzen or Ultra.
Saying M series is far behind is a wild take when you look at the actual numbers. Check out the benchmarks. The M5 isn’t just keeping up. but literally beating the flagship desktop chips in single-core performance.
Check the latest Tom’s Hardware coverage on the base M5. The M5 is actively humiliating flagship desktop silicon in single-thread performance. In a recent CPU-Z benchmark, a virtualized M5—running through a translation layer on Windows 11, mind you, and still scored roughly 1,600 points. Compare that to AMD’s upcoming gaming king, the Ryzen 9 9950X3D, which sits around 867.
That’s a roughly 84% gap in favor of a mobile chip running in a VM. While a base 10-core M5 obviously won’t beat a 16-core/32-thread desktop monster in raw multi-core totals, the fact that it’s gapping the fastest x86 cores in existence by nearly double in single-core IPC, while sipping tablet-tier power, is genuinely absurd. The mobile-grade architecture argument actually works against your point here.
https://www.tomshardware.com/pc-components/cpus/virtualized-windows-11-test-shows-apples-m5-destroying-intel-and-amds-best-in-single-core-benchmark-chinese-enthusiast-pits-ryzen-9-9950x3d-and-core-i9-14900ks-against-apples-latest-soc
Incidentally, a good rundown of why RISC and SoC architecture is so performant https://archive.ph/Nmgp3
See, this is what I despise about x86. AFAIK it’s literally RISC on the bare metal but there are hundreds of “instructions” running microcode which is basically just a translation layer. You’re not allowed to write code for the actual RISC implementation because that’s a trade secret or something. So obviously single core performance would be shit because you’re basically running an emulator all the time.
RISC-V can’t come fast enough. Maybe someone will even make a chip that’s RISC-V but with the same instruction/microcode support as x86. So you can run RISC-V code directly or do the microcode thing and pretend you’re on x86. Though that would probably get the shit sued out of them by Intel because god forbid there’s actual innovation that the original creator can’t cash in on.
But you’re using a Mac and my conscience won’t allow that!
only if you are a first world dev that can shell out (good) used car money for an overpriced laptop. i bet you could get that in that overall performance ballpark for much cheaper.
Sure, they are expensive, I’m simply pointing out that it is a genuinely good architecture. And you really can’t get the same performance with CISC. I’m personally hoping we’ll start seeing RISCV based machines that are built in a similar way.
your employer doesn’t provide you with one?
i liike mac’s too and i’ve been using them for work since 2008; but i would never buy one for myself unless linux starting working on them better than asahi does rn.
I got one from a startup I worked at a couple of years ago, and then when the whole Silicon Valley bank crash happened they laid me off, but let me keep it. And yeah Asashi is still pretty barebones mainly cause you can basically just use open source apps on it that can be compiled against it. I’m really hoping to see something like M series from China but using RISCV and with Linux.
Where?
You don’t need the fastest computer in order to open word documents or write clean code.
you do if you use eg a jetbrains IDE and your codebase is all dockerized and requires 34 separate containers to be running and also the company makes you install a “security” software that constantly scans every fucking file on the machine…
Also don’t forget having to run electron apps like Slack that a lot of companies use.
oh yeah. and zoom eats up an entire god damned core minimum. jumps to two entire cores occasionally.
modern software is absolutely incredible for all the wrong reasons