aco/insert_exec_mask: optimize top-level transition to exact before demote

fossil-db (Sienna Cichlid):
Totals from 5767 (3.55% of 162293) affected shaders:
Instrs: 3264949 -> 3257527 (-0.23%); split: -0.23%, +0.00%
CodeSize: 17835692 -> 17806004 (-0.17%); split: -0.17%, +0.00%
Latency: 45990060 -> 45987924 (-0.00%); split: -0.00%, +0.00%
InvThroughput: 7643850 -> 7643835 (-0.00%); split: -0.00%, +0.00%
Copies: 193641 -> 186219 (-3.83%); split: -3.84%, +0.01%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15244>

diff --git a/src/amd/compiler/aco_insert_exec_mask.cpp b/src/amd/compiler/aco_insert_exec_mask.cpp
index 04928c3..e1dd392 100644 (file)
--- 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;