#
✕ nick:mmediouni[m]
#asahi-dev · 2026-09-26 11:54
mmediouni[m]> The Storage tab of the System Settings app says that the M1 MacBook Air and MacBook Neo needed around 14GB of space for Apple Intelligence after a fresh install. On the M3 MacBook Air, that number was 22.42GB.
#asahi-dev · 2026-09-26 11:52
mmediouni[m]between the newly staged OS and the space needed for Apple Intelligence (tm) quite a bit of space is needed for updates
#asahi-dev · 2026-09-26 11:38
mmediouni[m]Is 10GbE also using realtek or did they stick with Marvell AQC
#asahi-dev · 2026-09-26 11:26
mmediouni[m]as far as I heard a lot of M5 Ultra buyers are waiting for the 512GB model...
#asahi-dev · 2026-09-24 18:27
mmediouni[m]CPU tile is the same though
#asahi-dev · 2026-09-24 18:27
mmediouni[m]M5 Pro and Max are different tapeouts for the base tile that contains dram controllers and GPU
#asahi-dev · 2026-09-16 19:47
mmediouni[m]M1 is effectively the A14X, so yes
#asahi-dev · 2026-09-16 18:11
mmediouni[m]the disclosed securerom bug (in dubious circumstances, there's a lawsuit by a private exploit firm over it) works all the way to A13
#asahi-dev · 2026-09-16 18:07
mmediouni[m]myria: A14 and M1 are the same core. A15 and M2 are also the same cores
#asahi-dev · 2026-09-16 16:23
mmediouni[m]and don't even have the same decoder width apparently...
#asahi-dev · 2026-09-16 16:23
mmediouni[m]M6 and A20 Pro super cores are not the same
#asahi-dev · 2026-09-16 12:30
mmediouni[m]because LLM usage could have resulted in it anyway...
#asahi-dev · 2026-09-16 12:30
mmediouni[m]well, there were things that'd have been interesting projects before, now people just go meh if you do it
#asahi-dev · 2026-08-15 18:43
mmediouni[m]yuka: doesn't seem like it
#asahi-dev · 2026-08-15 18:32
mmediouni[m]Oh so recfg is locked down too
#asahi-dev · 2026-08-15 18:31
mmediouni[m]That and the register masks lockdown
#asahi-dev · 2026-08-15 18:31
mmediouni[m]What makes sure that the HIDx register values persist across deep sleep?
#asahi-dev · 2026-08-09 09:53
mmediouni[m]nickchan: wasn't there AGX0? realworldtech claims that the Apple-designed shader core shipped in the A8: https://www.realworldtech.com/apple-custom-gpu/
#asahi-dev · 2026-08-08 12:13
mmediouni[m]the 32-bit arm FPU/simd situation was a big mess for quite a long time: FPA and Intel's wmmx outright had a conflict in opcode space
#asahi-dev · 2026-08-08 12:11
mmediouni[m]happened with iwmmxt
#asahi-dev · 2026-08-08 12:11
mmediouni[m]sobek: Arm did heavily regret custom ISAs getting into binaries before
#asahi-dev · 2026-08-08 12:09
mmediouni[m]Arm has two important and conflicting roles for CPUs: being a standards body for an ISA, and providing first party cores. the second has the advantage that architecture licensees cannot license out their cores (hence why they got really mad at the nuvia situation) or it'd have a much harder time surviving
#asahi-dev · 2026-08-08 12:03
mmediouni[m]not RV64
#asahi-dev · 2026-08-08 12:03
mmediouni[m]they're RV32 cores too
#asahi-dev · 2026-08-08 12:02
mmediouni[m]on the a19
#asahi-dev · 2026-08-08 12:02
mmediouni[m]AVE has an arm64 primary coprocessor and a bunch of RISC-V secondaries
#asahi-dev · 2026-08-08 12:01
mmediouni[m](for video)
#asahi-dev · 2026-08-08 12:00
mmediouni[m]the M33 adds a custom instruction interface but apple chose to RISC-Vify the thing instead of using that
#asahi-dev · 2026-08-08 11:58
mmediouni[m]but the private peripheral interface is APB only on the cortex-m3
#asahi-dev · 2026-08-08 11:57
mmediouni[m]the primary interfaces can be AHB-Lite (and then bridged over to AXI or whatever outside the core)
#asahi-dev · 2026-08-08 11:56
mmediouni[m]but not too relevant of a question especially in this context lol
#asahi-dev · 2026-08-08 11:56
mmediouni[m]the Cortex-M private peripheral interface is APB only, so wouldn't be surprised if there's some APB here and there - especially for the Ms in the video decode part?
#asahi-dev · 2026-08-08 08:12
mmediouni[m]> Broadcom will produce advanced radio frequency components — including FBAR filters — and advanced wireless connectivity technologies at the Fort Collins facility
#asahi-dev · 2026-08-08 08:12
mmediouni[m]https://www.apple.com/newsroom/2026/07/apple-to-increase-spend-with-broadcom-to-produce-billions-more-us-chips/ if this means anything maybe some future machines will have BCM wireless again
#asahi-dev · 2026-08-08 08:06
mmediouni[m]do they still use bcm touchpad controllers
#asahi-dev · 2026-08-08 08:05
mmediouni[m]Oh older hw will stay relevant for quite a while...
#asahi-dev · 2026-08-08 08:05
mmediouni[m]The MacBook Pros updates use Apple's own and the MacBook Neo uses mediatek
#asahi-dev · 2026-08-08 08:04
mmediouni[m]chadmed: it's already gone
#asahi-dev · 2026-08-08 07:58
mmediouni[m]but is that over USB4 streams
#asahi-dev · 2026-08-08 07:58
mmediouni[m]Apple has an oddball Thunderbolt RDMA non-standard thing too
#asahi-dev · 2026-08-08 06:48
mmediouni[m]sven: the EC2 Mac setup with exposing a PCIe switch over thunderbolt and then attaching/detaching devices to that works, but even that didn't work for years on macOS before being fixed...
#asahi-dev · 2026-08-08 06:41
mmediouni[m]on non-Apple arm64 TBT is also pretty broken
#asahi-dev · 2026-08-06 16:01
mmediouni[m]I wonder how much it takes just for Thunderbolt monitors instead of PCIe tunnelling
#asahi-dev · 2026-08-05 18:52
mmediouni[m]Looks like difficulty was set to 6 which makes the git.kernel.org web UX not actually usable really
#asahi-dev · 2026-08-05 11:17
mmediouni[m]Apple did the transition in the Apple A9 but had the opportunity to enforce it even before for aarch64. AArch32 apps in the right setting managed to get an RWX page though
#asahi-dev · 2026-08-05 11:10
mmediouni[m]Think that at least for the first round or Android with 16KB pages in production some OEMs will opt-out still
#asahi-dev · 2026-08-05 11:04
mmediouni[m]they tried as much as they could while not changing the kernel... but that has its limits...
#asahi-dev · 2026-08-05 11:03
mmediouni[m]uploaded an image: (616KiB) < https://matrix.org/oftc/media/v1/media/download/AUyUW4L-Gzr_Se2kE_iap5KYx83kcQSlgFSQF7IXrzuy85VcJjC0JJMXXvIHCb6lYVTxYz8UdsM5ZRMFuXErbSJCegGbEHqQAG1hdHJpeC5vcmcvaW9EQWx3dGptYURHVVlhS2tzUVNwZG9r >
#asahi-dev · 2026-08-05 11:02
mmediouni[m]https://lpc.events/event/19/contributions/2116/attachments/1861/3985/LPC2025-4KB-ELFs-on-16KB-Devices.pdf
#asahi-dev · 2026-08-01 05:53
mmediouni[m]isn't it all included in ioreg -l pretty much?

plus ›