Using DMA instead of SHM in non OpenGL apps (Wayland)
-
wrote on 4 Aug 2023, 20:38 last edited by
I have noticed that Qt uses shared memory for buffer sharing with Wayland compositors in non-OpenGL rendering applications. However, a more efficient approach would be to use the zwp_linux_dmabuf_v1 protocol. By creating a DMA buffer, mapping it, and performing CPU rendering there, the compositor could directly import the buffers into the GPU, eliminating the need for extra copies. This optimization would significantly improve performance, especially when scaling a large window on HiDPI displays, and the implementation on the Qt side should be almost identical to using shared memory.
-
Hi,
That's something you should bring to the development mailing list. You'll find there Qt's developers/maintainers. This is more a user forum.
-
Hi,
That's something you should bring to the development mailing list. You'll find there Qt's developers/maintainers. This is more a user forum.
wrote on 7 Aug 2023, 04:31 last edited by@SGaist Ups, sorry, I didn't know that.
-
@SGaist Ups, sorry, I didn't know that.
No worries ! Please post a link to the thread if you open one so people can more easily find it :-)
-
No worries ! Please post a link to the thread if you open one so people can more easily find it :-)
wrote on 10 Aug 2023, 02:07 last edited by@SGaist Ok, here is the thread link:
https://lists.qt-project.org/pipermail/development/2023-August/044234.html
1/5