radeonsi: fix applying the NGG minimum vertex count requirement

The code applied the restriction too late, which could overflow LDS size,
which started happening more often after the minimum vertex count was
increased for Sienna.

Incorporate the clamping into the previous code for rounding up the counts.
Now the LDS size can never overflow, but it may use vector lanes less
efficiently (max_gsprims can be decreased more), which will be addressed
in the next commit.

Fixes: 4ecc39e1aa1 ("radeonsi/gfx10: NGG geometry shader PM4 and upload")
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>

diff --git a/src/gallium/drivers/radeonsi/gfx10_shader_ngg.c b/src/gallium/drivers/radeonsi/gfx10_shader_ngg.c
index ee242da7ed15f6daa7bbe68d051e5141176b2f7a..0797f9cdb3a79716d052489f5bbfd94d4ac058e6 100644 (file)
--- a/src/gallium/drivers/radeonsi/gfx10_shader_ngg.c
+++ b/src/gallium/drivers/radeonsi/gfx10_shader_ngg.c
@@ -2022,6 +2022,8 @@ retry_select_mode:
             max_esverts =
                MIN2(max_esverts, (max_lds_size - max_gsprims * gsprim_lds_size) / esvert_lds_size);
          max_esverts = MIN2(max_esverts, max_gsprims * max_verts_per_prim);
             max_esverts =
                MIN2(max_esverts, (max_lds_size - max_gsprims * gsprim_lds_size) / esvert_lds_size);
          max_esverts = MIN2(max_esverts, max_gsprims * max_verts_per_prim);

+         /* Hardware restriction: minimum value of max_esverts */
+         max_esverts = MAX2(max_esverts, min_esverts - 1 + max_verts_per_prim);

 
          max_gsprims = align(max_gsprims, wavesize);
          max_gsprims = MIN2(max_gsprims, max_gsprims_base);
 
          max_gsprims = align(max_gsprims, wavesize);
          max_gsprims = MIN2(max_gsprims, max_gsprims_base);


@@ -2031,10 +2033,13 @@ retry_select_mode:
          clamp_gsprims_to_esverts(&max_gsprims, max_esverts, min_verts_per_prim, use_adjacency);
          assert(max_esverts >= max_verts_per_prim && max_gsprims >= 1);
       } while (orig_max_esverts != max_esverts || orig_max_gsprims != max_gsprims);
          clamp_gsprims_to_esverts(&max_gsprims, max_esverts, min_verts_per_prim, use_adjacency);
          assert(max_esverts >= max_verts_per_prim && max_gsprims >= 1);
       } while (orig_max_esverts != max_esverts || orig_max_gsprims != max_gsprims);

-   }

 
 

-   /* Hardware restriction: minimum value of max_esverts */
-   max_esverts = MAX2(max_esverts, min_esverts - 1 + max_verts_per_prim);
+      /* Verify the restriction. */
+      assert(max_esverts >= min_esverts - 1 + max_verts_per_prim);
+   } else {
+      /* Hardware restriction: minimum value of max_esverts */
+      max_esverts = MAX2(max_esverts, min_esverts - 1 + max_verts_per_prim);
+   }

 
    unsigned max_out_vertices =
       max_vert_out_per_gs_instance
 
    unsigned max_out_vertices =
       max_vert_out_per_gs_instance