compiler/nir: add a divergence analysis option for non-uniform workgroup id

The V3D hardware allows us to pack multiple workgroups together to avoid
wasting execution lanes in shader cores.

For example, if we dispatch 16 workgroups with a local size of 1 element, we
can pack all 16 workgroups in a single 16-wide dispatch where each lane
executes a different workgroup, instead of 16 1-wide dispatches.

When we do this, we don't have a uniform workgroup id any more.

Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10541>

src/compiler/nir/nir.h

@@ -3126,6 +3126,7 @@ typedef enum {
    nir_divergence_single_patch_per_tes_subgroup = (1 << 2),
    nir_divergence_view_index_uniform = (1 << 3),
    nir_divergence_single_frag_shading_rate_per_subgroup = (1 << 4),
+   nir_divergence_multiple_workgroup_per_compute_subgroup = (1 << 5),
 } nir_divergence_options;
 
 typedef struct nir_shader_compiler_options {

src/compiler/nir/nir_divergence_analysis.c

@@ -101,7 +101,6 @@ visit_intrinsic(nir_shader *shader, nir_intrinsic_instr *instr)
    case nir_intrinsic_vote_ieq:
    case nir_intrinsic_load_push_constant:
    case nir_intrinsic_load_work_dim:
-   case nir_intrinsic_load_work_group_id:
    case nir_intrinsic_load_num_work_groups:
    case nir_intrinsic_load_local_group_size:
    case nir_intrinsic_load_subgroup_id:
@@ -233,6 +232,11 @@ visit_intrinsic(nir_shader *shader, nir_intrinsic_instr *instr)
          assert(stage == MESA_SHADER_TESS_CTRL);
       break;
 
+   case nir_intrinsic_load_work_group_id:
+      assert(stage == MESA_SHADER_COMPUTE);
+      is_divergent |= (options & nir_divergence_multiple_workgroup_per_compute_subgroup);
+      break;
+
    /* Clustered reductions are uniform if cluster_size == subgroup_size or
     * the source is uniform and the operation is invariant.
     * Inclusive scans are uniform if