intel/nir: Add a memory barrier before barrier()

Our barrier instruction does not implicitly do a memory fence but the
GLSL barrier() intrinsic is supposed to.  The easiest back-portable
solution is to just add the NIR barriers.  We'll sort this out more
properly in later commits.

Cc: mesa-stable@lists.freedesktop.org
Closes: #2138
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>

diff --git a/src/intel/compiler/brw_nir_lower_cs_intrinsics.c b/src/intel/compiler/brw_nir_lower_cs_intrinsics.c
index 434ad005281172e3268359c12e9de411fc33d172..3f48a3c5dda6c1c8110643b34cb6cc18248a20bf 100644 (file)
--- a/src/intel/compiler/brw_nir_lower_cs_intrinsics.c
+++ b/src/intel/compiler/brw_nir_lower_cs_intrinsics.c
@@ -55,6 +55,20 @@ lower_cs_intrinsics_convert_block(struct lower_intrinsics_state *state,
 
       nir_ssa_def *sysval;
       switch (intrinsic->intrinsic) {
+      case nir_intrinsic_barrier: {
+         /* Our HW barrier instruction doesn't do a memory barrier for us but
+          * the GLSL barrier() intrinsic does for shared memory.  Insert a
+          * shared memory barrier before every barrier().
+          */
+         b->cursor = nir_before_instr(&intrinsic->instr);
+
+         nir_intrinsic_instr *shared_barrier =
+            nir_intrinsic_instr_create(b->shader,
+                                       nir_intrinsic_memory_barrier_shared);
+         nir_builder_instr_insert(b, &shared_barrier->instr);
+         continue;
+      }
+
       case nir_intrinsic_load_local_invocation_index:
       case nir_intrinsic_load_local_invocation_id: {
          /* First time we are using those, so let's calculate them. */