nir: Reduce destination size of ballot intrinsic when possible

Some hardware, like i965, doesn't support group sizes greater than 32.
In that case, we can reduce the destination size of the ballot
intrinsic, which will simplify our code generation.

Reviewed-by: Connor Abbott <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>

2 files changed, 20 insertions, 0 deletions

diff --git a/src/compiler/nir/nir.h b/src/compiler/nir/nir.h
index 5ddab57776f..78684fd50c8 100644
--- a/src/compiler/nir/nir.h
+++ b/src/compiler/nir/nir.h
@@ -1843,6 +1843,8 @@ typedef struct nir_shader_compiler_options {
     */
    bool use_interpolated_input_intrinsics;
 
+   unsigned max_subgroup_size;
+
    unsigned max_unroll_iterations;
 } nir_shader_compiler_options;
 
diff --git a/src/compiler/nir/nir_opt_intrinsics.c b/src/compiler/nir/nir_opt_intrinsics.c
index 4f36166510b..f12dc8779cb 100644
--- a/src/compiler/nir/nir_opt_intrinsics.c
+++ b/src/compiler/nir/nir_opt_intrinsics.c
@@ -62,6 +62,24 @@ opt_intrinsics_impl(nir_function_impl *impl)
             replacement = nir_imm_int(&b, NIR_TRUE);
             break;
          }
+         case nir_intrinsic_ballot: {
+            assert(b.shader->options->max_subgroup_size != 0);
+            if (b.shader->options->max_subgroup_size > 32 ||
+                intrin->dest.ssa.bit_size <= 32)
+               continue;
+
+            nir_intrinsic_instr *ballot =
+               nir_intrinsic_instr_create(b.shader, nir_intrinsic_ballot);
+            nir_ssa_dest_init(&ballot->instr, &ballot->dest, 1, 32, NULL);
+            nir_src_copy(&ballot->src[0], &intrin->src[0], ballot);
+
+            nir_builder_instr_insert(&b, &ballot->instr);
+
+            replacement = nir_pack_64_2x32_split(&b,
+                                                 &ballot->dest.ssa,
+                                                 nir_imm_int(&b, 0));
+            break;
+         }
          case nir_intrinsic_load_subgroup_eq_mask:
          case nir_intrinsic_load_subgroup_ge_mask:
          case nir_intrinsic_load_subgroup_gt_mask: