nir: Fix divergence analysis for tessellation input/outputs

The load_per_vertex_{input,output} intrinsics simply mean that they're
reading an arrayed input/output, which have one element per invocation.
Most accesses to those use gl_InvocationID as the subscript.  However,
it's totally possible to read any element of the array.  For example,
an evaluation shader might read gl_in[2].gl_Position, or a control
shader might read output[0].

For threads processing a single patch, an input/output load is
convergent if and only if both sources (the per-vertex-array subscript
and the offset) are convergent.  For threads processing multiple
patches, we continued to mark them divergent.

Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Acked-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5613>

diff --git a/src/compiler/nir/nir_divergence_analysis.c b/src/compiler/nir/nir_divergence_analysis.c
index 6589299cad4bfeaf1612ea15e5d478bffdb96e21..3e2e4b86e2045dff3778a817392be0ffaead2840 100644 (file)
--- a/src/compiler/nir/nir_divergence_analysis.c
+++ b/src/compiler/nir/nir_divergence_analysis.c
@@ -145,6 +145,16 @@ visit_intrinsic(nir_intrinsic_instr *instr, struct divergence_state *state)
       else
          is_divergent = true;
       break;
+   case nir_intrinsic_load_per_vertex_input:
+      is_divergent = instr->src[0].ssa->divergent ||
+                     instr->src[1].ssa->divergent;
+      if (stage == MESA_SHADER_TESS_CTRL)
+         is_divergent |= !(options & nir_divergence_single_patch_per_tcs_subgroup);
+      if (stage == MESA_SHADER_TESS_EVAL)
+         is_divergent |= !(options & nir_divergence_single_patch_per_tes_subgroup);
+      else
+         is_divergent = true;
+      break;
    case nir_intrinsic_load_input_vertex:
       is_divergent = instr->src[1].ssa->divergent;
       assert(stage == MESA_SHADER_FRAGMENT);
@@ -158,6 +168,12 @@ visit_intrinsic(nir_intrinsic_instr *instr, struct divergence_state *state)
       else
          is_divergent = true;
       break;
+   case nir_intrinsic_load_per_vertex_output:
+      assert(stage == MESA_SHADER_TESS_CTRL);
+      is_divergent = instr->src[0].ssa->divergent ||
+                     instr->src[1].ssa->divergent ||
+                     !(options & nir_divergence_single_patch_per_tcs_subgroup);
+      break;
    case nir_intrinsic_load_layer_id:
    case nir_intrinsic_load_front_face:
       assert(stage == MESA_SHADER_FRAGMENT);
@@ -302,8 +318,6 @@ visit_intrinsic(nir_intrinsic_instr *instr, struct divergence_state *state)
    case nir_intrinsic_load_sample_pos:
    case nir_intrinsic_load_vertex_id_zero_base:
    case nir_intrinsic_load_vertex_id:
-   case nir_intrinsic_load_per_vertex_input:
-   case nir_intrinsic_load_per_vertex_output:
    case nir_intrinsic_load_instance_id:
    case nir_intrinsic_load_invocation_id:
    case nir_intrinsic_load_local_invocation_id: