fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-06 09:28:07 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

radeonsi: fix applying the NGG minimum vertex count requirement

Browse source 
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: 4ecc39e1aa ("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>
(cherry picked from commit 64c741ffb7)
This commit is contained in:
Marek Olšák 2020-07-30 08:19:48 -04:00 • committed by Eric Engestrom
parent a4dfa2bdf8
commit cad3caba1a
2 changed files with 9 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.pick_status.json
View file

@ -3739,7 +3739,7 @@
"description": "radeonsi: fix applying the NGG minimum vertex count requirement",
"nominated": true,
"nomination_type": 1,
"resolution": 0,
"resolution": 1,
"master_sha": null,
"because_sha": "4ecc39e1aa1568f19ebf54a99ffe14643bac7d15"
},

11
src/gallium/drivers/radeonsi/gfx10_shader_ngg.c
View file

@ -2003,6 +2003,8 @@ void gfx10_ngg_calculate_subgroup_info(struct si_shader *shader)
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, 23 + max_verts_per_prim);
max_gsprims = align(max_gsprims, wavesize);
max_gsprims = MIN2(max_gsprims, max_gsprims_base);
@ -2012,10 +2014,13 @@ void gfx10_ngg_calculate_subgroup_info(struct si_shader *shader)
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, 23 + max_verts_per_prim);
/* Verify the restriction. */
assert(max_esverts >= 23 + max_verts_per_prim);
} else {
/* Hardware restriction: minimum value of max_esverts */
max_esverts = MAX2(max_esverts, 23 + max_verts_per_prim);
}
unsigned max_out_vertices =
max_vert_out_per_gs_instance