aco: Fix optimizing branching sequence with s_and_saveexec.

This optimization was broken for two reasons:
- s_and_saveexec has two operands, the copy value and exec
- s_and_saveexec has an exec read, so exec_write_used will always be true
  before we find branch_exec_val_idx

Foz-DB Navi21:
Totals from 31453 (23.31% of 134913) affected shaders:
CodeSize: 204831260 -> 204831156 (-0.00%)
Instrs: 38157117 -> 38157091 (-0.00%)
Latency: 533708882 -> 531211721 (-0.47%); split: -0.47%, +0.00%
InvThroughput: 107088408 -> 106719188 (-0.34%); split: -0.35%, +0.00%
Copies: 2326179 -> 2502490 (+7.58%)

Signed-off-by: Georg Lehmann <dadschoorse@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18049>

1 files changed, 8 insertions, 5 deletions

diff --git a/src/amd/compiler/aco_ssa_elimination.cpp b/src/amd/compiler/aco_ssa_elimination.cpp
index f82058a6c44..2d8c3a10dfc 100644
--- a/src/amd/compiler/aco_ssa_elimination.cpp
+++ b/src/amd/compiler/aco_ssa_elimination.cpp
@@ -544,7 +544,7 @@ eliminate_useless_exec_writes_in_block(ssa_elimination_ctx& ctx, Block& block)
 
       /* For a newly encountered exec write, clear the used flag. */
       if (writes_exec) {
-         if (!logical_end_found && branch_reads_exec && instr->operands.size() == 1) {
+         if (!logical_end_found && branch_reads_exec && instr->operands.size()) {
             /* We are in a branch that jumps according to exec.
              * We just found the instruction that copies to exec before the branch.
              */
@@ -560,13 +560,16 @@ eliminate_useless_exec_writes_in_block(ssa_elimination_ctx& ctx, Block& block)
          }
 
          exec_write_used = false;
-      }
-
-      if (branch_exec_tempid && !exec_write_used && instr->definitions.size() &&
-          instr->definitions[0].tempId() == branch_exec_tempid) {
+      } else if (branch_exec_tempid && instr->definitions.size() &&
+                 instr->definitions[0].tempId() == branch_exec_tempid) {
          /* We just found the instruction that produces the exec mask that is copied. */
          assert(branch_exec_val_idx == -1);
          branch_exec_val_idx = i;
+      } else if (branch_exec_tempid && branch_exec_val_idx == -1 && needs_exec) {
+         /* There is an instruction that needs the original exec mask before
+          * branch_exec_val_idx was found, so we can't optimize the branching sequence. */
+         branch_exec_copy_idx = -1;
+         branch_exec_tempid = 0;
       }
 
       /* If the current instruction needs exec, mark it as used. */