• Joined on 2022年06月01日
mahkoh opened issue adnano/wmenu#76 2026年05月20日 19:12:48 +02:00
wmenu attaches a buffer before receiving a configure event
mahkoh commented on pull request dnkl/foot#2186 2025年10月04日 15:55:31 +02:00
Add tweak.min-stride-alignment

Yes, level 2 should always work now. However, level 2 is already incompatible with immediate release.

mahkoh commented on pull request dnkl/foot#2186 2025年10月04日 15:48:55 +02:00
Add tweak.min-stride-alignment

There are three levels of optimization that can be performed. Only the highest level requires the strict alignment.

mahkoh commented on pull request dnkl/foot#2186 2025年10月04日 12:51:17 +02:00
Add tweak.min-stride-alignment

Also needs documentation; what it's for, why 256

AMD hardware has no programmable stride and the stride must always be width * bpp rounded up to 256. This is hardcoded everywhere in mesa.

a...

mahkoh commented on issue dnkl/foot#2182 2025年10月04日 12:42:01 +02:00
Use a stride that is a multiple of 256

This is slow - in most cases slower than memcpy:ing the buffer.

The compositor doesn't have access to a faster memcpy implementation than the client.

I've looked into this in the past but...

mahkoh commented on pull request dnkl/foot#2184 2025年10月04日 12:11:08 +02:00
Enable zero-copy handling of memfds

Logs are under ~/.local/share/jay/log/jay. Based on the vibes, you're not using systemd.

mahkoh commented on pull request dnkl/foot#2184 2025年10月04日 10:38:41 +02:00
Enable zero-copy handling of memfds

There are two commits.

mahkoh created pull request dnkl/foot#2184 2025年10月03日 16:58:36 +02:00
Enable zero-copy handling of memfds
mahkoh created branch jorth/zero-copy in mahkoh/foot 2025年10月03日 16:56:54 +02:00
mahkoh pushed to jorth/zero-copy at mahkoh/foot 2025年10月03日 16:56:54 +02:00
ac342ff9c0 shm: don't grow-seal the memfd
c462bad08c shm: align the stride to 256 bytes
Compare 2 commits »
mahkoh created repository mahkoh/foot 2025年10月03日 16:55:55 +02:00
mahkoh commented on issue dnkl/foot#2182 2025年10月03日 13:22:57 +02:00
Use a stride that is a multiple of 256

I don't know how to verify we're hitting the zero-copy path

You can run the current master of https://github.com/mahkoh/jay. I'm not aware of any other compositor that tries to do this at the...

mahkoh opened issue dnkl/foot#2182 2025年10月02日 16:23:14 +02:00
Use a stride that is a multiple of 256
mahkoh commented on pull request dnkl/foot#1794 2025年10月01日 23:06:44 +02:00
WIP: Vulkan memory experiment

It is nowadays possible for the compositor to import the memfd created by foot as a udmabuf. This allows the compositor to perform the copy from the foot shm to the GPU texture on the GPU without...

mahkoh commented on issue sugar700/enum-map#147 2024年11月21日 12:22:02 +01:00
Is this project dead?

I've gone ahead and written a replacement for my usecases: https://docs.rs/linearize

I also took the opportunity to fix some of the remaining issues with enum-map:

  • The traits of the map,...
mahkoh opened issue sugar700/enum-map#147 2024年11月14日 12:59:55 +01:00
Is this project dead?
mahkoh commented on pull request dnkl/foot#1061 2022年06月01日 23:52:50 +02:00
Add support for xdg_toplevel.wm_capabilities

wm_capabilities.minimize