diff --git a/src/amd/compiler/aco_insert_exec_mask.cpp b/src/amd/compiler/aco_insert_exec_mask.cpp
index 04928c3c722..e1dd3929910 100644
--- a/src/amd/compiler/aco_insert_exec_mask.cpp
+++ b/src/amd/compiler/aco_insert_exec_mask.cpp
@@ -585,8 +585,7 @@ process_instructions(exec_ctx& ctx, Block* block, std::vector<aco_ptr<Instructio
          }
       } else if (instr->opcode == aco_opcode::p_demote_to_helper) {
          /* turn demote into discard_if with only exact masks */
-         assert((ctx.info[block->index].exec[0].second & (mask_type_exact | mask_type_global)) ==
-                (mask_type_exact | mask_type_global));
+         assert(ctx.info[block->index].exec[0].second == (mask_type_exact | mask_type_global));
 
          int num;
          Temp cond, exit_cond;
@@ -605,7 +604,15 @@ process_instructions(exec_ctx& ctx, Block* block, std::vector<aco_ptr<Instructio
             }
          } else {
             /* demote_if: transition to exact */
-            transition_to_Exact(ctx, bld, block->index);
+            if (block->kind & block_kind_top_level && ctx.info[block->index].exec.size() == 2 &&
+                ctx.info[block->index].exec.back().second & mask_type_global) {
+               /* We don't need to actually copy anything into exact, since the s_andn2
+                * instructions later will do that.
+                */
+               ctx.info[block->index].exec.pop_back();
+            } else {
+               transition_to_Exact(ctx, bld, block->index);
+            }
             assert(instr->operands[0].isTemp());
             cond = instr->operands[0].getTemp();
             num = ctx.info[block->index].exec.size() - 1;