This discussion has been locked.
You can no longer post new replies to this discussion. If you have a question you can start a new discussion

Processing order of vertices and fragments in arm gpu

When the ARM GPU processes vertices and fragments, in what order are they distributed and processed? Vertices are in index order? What about fragment? Can we try to control the order of the index on the cpu side to improve the efficiency of the GPU?
For example: Does the optimization of the link below improve the gpu of arm? If there is an improvement, what features of the GPUs they use? github.com/.../meshoptimizer
Parents
  • Hi Shawn, 

    Older Mali GPUs (Utgard, Midgard) render vertices in incrementing index order, between min and max referenced index, ignoring the actual order in the index buffer. 

    Newer Mali GPUs (Bifrost) render vertices in the order in the index buffer (in contiguous blocks of 4), and can skip ranges that are not referenced (except those that are in the same block of 4 as a referenced vertex).  

    Using mesh conditioning tools such as meshoptimizer are a very good idea; the algorithms applied will work well for both types of Mali GPU, either to minimize bandwidth or reduce shading cost.

    HTH, 
    Pete

Reply
  • Hi Shawn, 

    Older Mali GPUs (Utgard, Midgard) render vertices in incrementing index order, between min and max referenced index, ignoring the actual order in the index buffer. 

    Newer Mali GPUs (Bifrost) render vertices in the order in the index buffer (in contiguous blocks of 4), and can skip ranges that are not referenced (except those that are in the same block of 4 as a referenced vertex).  

    Using mesh conditioning tools such as meshoptimizer are a very good idea; the algorithms applied will work well for both types of Mali GPU, either to minimize bandwidth or reduce shading cost.

    HTH, 
    Pete

Children