←back to thread

447 points stephenheron | 7 comments | | HN request time: 0.966s | source | bottom

Hi,

My daily workhorse is a M1 Pro that I purchased on release date, It has been one of the best tech purchases I have made, even now it really deals with anything I throw at it. My daily work load is regularly having a Android emulator, iOS simulator and a number of Dockers containers running simultaneously and I never hear the fans, battery life has taken a bit of a hit but it is still very respectable.

I wanted a new personal laptop, and I was debating between a MacBook Air or going for a Framework 13 with Linux. I wanted to lean into learning something new so went with the Framework and I must admit I am regretting it a bit.

The M1 was released back in 2020 and I bought the Ryzen AI 340 which is one of the newest 2025 chips from AMD, so AMD has 5 years of extra development and I had expected them to get close to the M1 in terms of battery efficiency and thermals.

The Ryzen is using a TSMC N4P process compared to the older N5 process, I managed to find a TSMC press release showing the performance/efficiency gains from the newer process: “When compared to N5, N4P offers users a reported +11% performance boost or a 22% reduction in power consumption. Beyond that, N4P can offer users a 6% increase in transistor density over N5”

I am sorely disappointed, using the Framework feels like using an older Intel based Mac. If I open too many tabs in Chrome I can feel the bottom of the laptop getting hot, open a YouTube video and the fans will often spin up.

Why haven’t AMD/Intel been able to catch up? Is x86 just not able to keep up with the ARM architecture? When can we expect a x86 laptop chip to match the M1 in efficiency/thermals?!

To be fair I haven’t tried Windows on the Framework yet it might be my Linux setup being inefficient.

Cheers, Stephen

1. bsenftner ◴[] No.45025734[source]
Well, there is a major architectural reason why the entire M-series appears to be "so fast" and that is the unified memory, which completely eliminates the buffer-to-buffer data copying that is probably over half of what a non-unified memory architecture chip is doing at any given time. M-series chips have an architecture that completely eliminates data copying, just reference the data where it is, and you're done.
replies(4): >>45026086 #>>45029916 #>>45030966 #>>45047853 #
2. rollcat ◴[] No.45026086[source]
I really like the principles behind AMD's chiplet design, of course they've had different design goals behind it (easier diversification of their product portfolio), but it remains a fact that you can slap a not-so-terrible GPU right next to a CPU core.

There's probably a lot still missing: Apple integrated the memory on the same die, and built Metal for software to directly take advantage of that design. That's the competitive advantage of vertical integration.

replies(1): >>45028626 #
3. kube-system ◴[] No.45028626[source]
> Apple integrated the memory on the same die

It's on the same package but not the same die

4. hajile ◴[] No.45029916[source]
Apple made a big deal about this, but other iGPUs have done this for years.
replies(1): >>45031686 #
5. superconduct123 ◴[] No.45030966[source]
Is that what game consoles have done for years?
6. bsenftner ◴[] No.45031686[source]
It's not just the GPU memory, it's also I/O memory. That speeds up a lot: just update the pointer to where the memory is, no copying out of I/O memory.
7. teleforce ◴[] No.45047853[source]
I think the UMA is the secret sauce for faster PC/laptop that people tend to overlook since You Can Never Has Enough RAM (TM).

I'm planning to buy HP ZBook Ultra G1a laptop with AMD Ryzen Strix and it seems to be a very good alternative to Apple M series laptop [1]. It can support up to 128 GB RAM (up to 96 GB VRAM) and should be able to run GPT-OSS 120B model.

[1] HP ZBook Ultra G1a 14" Mobile Workstation PC:

https://www.hp.com/us-en/workstations/zbook-ultra.html