First impressions: Lenovo T14s with Qualcomm Snapdragon ARM64 CPU

From: Poul-Henning Kamp <phk_at_phk.freebsd.dk>
Date: Fri, 15 Nov 2024 20:52:03 UTC
Those of you how know me, know that I am not a big fan of the X86
architecture, which I think is a bad mess, mangled by market power
considerations, rather than the CPU architecture this world actually
needs, in particular in terms of performance/energy ratio.

So when my regular HW-pusher had a T14s G6 with Qualcomm Snapdragon
ARM64 CPU, for only EUR1000 + VAT, and I couldn't resist.

Physical:
---------

Lenovo T-series as we know it.

FreeBSD-current status:
-----------------------

-CURRENT needed some patches to ARM64-specific interrupt stuff,
that too half a day or so, patches are in transit.

A lot of my time were spent trying to slow down the EFI console
enough to be able to capture the boot messages with my mobile phone's
camera.

One particular note here is that the VT console switches to a 25Hz timer
driven screen update once interupts are supposed to work, and if they dont,
you wont see why on the screen.

I think we ought to have a loader-tunable, settable to a number,
which slows down the console proportional to that number, and if
non-zero, the VT console should not rely on the timer.  That would
have saved me some trouble and confusion yesterday.

With those pending patches:

What works:  Screen, NVME, the two USB-A ports and that's probably about it.

What does not work: Keyboard, mouse, TB & USB-C ports, thermal/freq mgt.

What is not tested: Everything else

Worldstone:
-----------

	>>> World built in 3210 seconds, ncpu: 12, make -j12

... using 24 Wh of energy, measured with a proper power-meter.

Likely explanation: Twelve real CPUs and none of that HTT-crap ?

Conclusion:
-----------

Highly recommended.

-- 
Poul-Henning Kamp       | UNIX since Zilog Zeus 3.20
phk@FreeBSD.ORG         | TCP/IP since RFC 956
FreeBSD committer       | BSD since 4.3-tahoe
Never attribute to malice what can adequately be explained by incompetence.