#
✕ nick:kov
#asahi · 2022-02-20 12:23
kovtpw_rules, \o/
#asahi · 2022-02-19 23:31
kovI guess that would require cooperation from qemu though
#asahi · 2022-02-19 23:30
kovtpw_rules, hmm or is hvf able to hide the 4k somehow?
#asahi · 2022-02-19 23:24
kovyeah, now that I think about it, I think my test on a VM on the m1 mini did it in ~20m
#asahi · 2022-02-19 23:23
kovtpw_rules, same time as which one? or do you mean the vm did it in the same time as linux bare metal?
#asahi · 2022-02-19 23:17
kov(now I want to ask povik for his change to linux to build it on macos and compare xD)
#asahi · 2022-02-19 23:09
kovI doubt the single core boost would make such a big dent?
#asahi · 2022-02-19 23:08
kovjust repeated the build on my m1 mini, 21:50, the fact I got ~16m on macos makes me think there may be some more 'need to enable L3 cache' that haven't been found heh
#asahi · 2022-02-19 22:50
kovaxboe, btw you said you're running these with E cores disabled?
#asahi · 2022-02-19 22:44
kov(I haven't put linux bare metal on the max yet, using the air for my testing for now xD)
#asahi · 2022-02-19 22:42
kovaxboe, ok, found my notes here, I got 11:30 on macos and 15:23 on the linux 8-core VM running a standard distro kernel on my m1 max
#asahi · 2022-02-19 22:35
kovaxboe, looks great, seems like more recent intel are much better than older ones (at least the ones that gobble power)
#asahi · 2022-02-19 22:27
kovand my xps 13 1185G7 did it in 44m if I'm not mistaken pff
#asahi · 2022-02-19 22:24
kovaxboe, nice, thanks! that's the same time my standard m1 does on the mac fwiw
#asahi · 2022-02-19 21:58
kovaxboe, btw you probably want to do 2 runs, as it downloads a bunch of stuff, so what I did was I ran the build once, deleted build/{bootstrap,aarch64-unknown-linux-gnu}, then timed the second run (making sure no ccache or sccache was on the way of course hehe)
#asahi · 2022-02-19 21:54
kovaxboe, yeah, I've done a cross-compile to x86-64 once to see if it made a difference, it's close enough
#asahi · 2022-02-19 21:53
kovj`ey, hah, but then I lose the C++ part (I still have to compile WebKit and Chrome for work - and for the 16k patches ;D)
#asahi · 2022-02-19 21:52
kovthe rust compiler is a nice benchmark for me because it's a mix of C++ and Rust
#asahi · 2022-02-19 21:51
kovbut it carried on nicely to rust, which is what I'm doing mostly these days
#asahi · 2022-02-19 21:51
kovthe thing that got me hooked originally was the compile times they were advertising for WebKit (I used to work on WebKitGTK)
#asahi · 2022-02-19 21:50
kovaxboe, that'd be great! I'd really like to see 5950x and 12th gen numbers if you have the time
#asahi · 2022-02-19 21:49
kovI tend to use building the rust compiler as my benchmark and the difference between the M1/M1 Max and my intel machines is massive
#asahi · 2022-02-19 21:48
kovit certainly does use a lot of memory (and binaries are bigger usually)
#asahi · 2022-02-19 21:48
kovtpw_rules, yeah, I figure C++ and Rust need to keep a lot more state while compiling
#asahi · 2022-02-19 21:47
koverm axboe ^
#asahi · 2022-02-19 21:47
kovtpw_rules, Glanzmann one thing I noticed on my testing is that the M1 chips seem to prefer C++/Rust compilation to C
#asahi · 2022-02-19 18:43
kovtpw_rules, I'm doing some more reading on libpas (the bmalloc replacement, impressive how much work went in since I was active =P) and it seems to use 16k as the smaller page size it cares about, I guess it's no surprise Apple has basically started using 16k as *the* page size ;P
#asahi · 2022-02-19 18:26
kovtpw_rules, k, comment added
#asahi · 2022-02-19 18:22
kovI haven't looked in detail on the reason for the crash but from their talking about bmalloc I'm wondering if it's related to some kind of alignment requirements
#asahi · 2022-02-19 18:21
kovin the end the change stuck, there was a fix for the crash
#asahi · 2022-02-19 18:21
kovtpw_rules, basically because they no longer needed it for RHEL and users were seeing it and enabling it without understanding what they were doing heh https://bugs.webkit.org/show_bug.cgi?id=227905
#asahi · 2022-02-19 18:10
kovkov@morango ~/P/WebKit (16k)>
#asahi · 2022-02-19 18:10
kovSource/WTF/ChangeLog-2021-03-18: Add new build option USE(64KB_PAGE_BLOCK)
#asahi · 2022-02-19 18:10
kovSource/WTF/ChangeLog: Remove USE_64KB_PAGE_BLOCK
#asahi · 2022-02-19 18:10
kovkov@morango ~/P/WebKit (16k)> git grep PAGE_BLOCK Source/
#asahi · 2022-02-19 18:10
kovit went in, then out:
#asahi · 2022-02-19 18:10
kovmcantarazzo works on fedora, probably did that for centos kernels
#asahi · 2022-02-19 18:09
kovlet me check the code
#asahi · 2022-02-19 18:09
kovtpw_rules, looks like it did
#asahi · 2022-02-19 18:08
kovtpw_rules, I'm basically saying that it's more common to do custom builds for the embedded platforms than for m1
#asahi · 2022-02-19 18:08
kovtpw_rules, yeah
#asahi · 2022-02-19 18:06
kovtpw_rules, yeah, I'm writing a comment about that idea of building specifically for M1, let me know if you want me to relay anything
#asahi · 2022-02-19 18:05
kovtpw_rules, yes! it's been applied and in theory has already been pulled into the stable branch as well
#asahi · 2022-02-19 18:04
kovand having opt/command as parameters to the module will be much better than using the tweaks trick ;D
#asahi · 2022-02-19 18:03
kovmps, hah nice, I didn't know there was an option to switch fn and control
#asahi · 2022-02-19 18:00
kovtpw_rules, https://bugs.webkit.org/show_bug.cgi?id=236564#attach_451821
#asahi · 2022-02-19 17:58
kovhmm looks like it sets dconf keys, so need to look into gnome settings daemon probably https://github.com/GNOME/gnome-tweaks/blob/1aa39325396754476061f58ac3f3dc84a49bea0c/gtweak/tweaks/tweak_group_xkb.py#L137
#asahi · 2022-02-19 17:55
kovI wonder how tweak does it, I suppose it's libinput settings, but I know very little about this (more than I wanted to know already)
#asahi · 2022-02-19 17:54
kov(I use the us intl with dead keys layout)
#asahi · 2022-02-19 17:54
kovGlanzmann, hmm how did you switch command and option? I used gnome's tweak tool to selected that 'alt and win are swapped' option and I seem to be able to use the right-side option key for the special characters option + s => ß

plus ›