Hi all,
I’ve noticed when I wanted to port LvGL V9.1 to my STM32H757, I’ve noticed there is no support for DMA2D in lv_config at all.
Is it possible to bring back this feature?
I’ve noticed performance reduction compared to V8.4.
Adding support for this feature might solve the issue.
Regards.
Here is the reason as to why.
Hi,
I made many measurements when implemented the DMA2D support and I found that usually it’s really not faster then LVGL’s software rendering.
DMA2D supports very simple opearations:
fill an area
copy an area
blend two areas with opacity
and color format conversations during this operations but we don’t use it
For fill area and copy area apparently DMA2D can not work faster than a well-written memset or memcpy.
For blending DMA2D could be faster but SW rendering is very well optimized her…
In v9 we add built-in GPU support only for your partners. We are working on setting up our partnership with ST and I hope we can added it back soon.
I’m sorry for this issue.
In other word, you are looking for support of Vector Graphic GPU (NeoChromVG), right?
Yes, it’s planned too. But we still need some time to get there.