[Bug middle-end/23848] [4.0/4.1/4.2/4.3 Regression] stack deallocation can be more efficient

["jakub at gcc dot gnu dot org" <gcc-bugzilla at gcc dot gnu dot org>]

------- Comment #4 from jakub at gcc dot gnu dot org  2007-11-04 21:35 -------
I'll be testing the following patch.  It is quite simplistic, in that it will
give up on bb boundaries, still it should IMHO trigger in quite a lot of cases.
Each optimized out pair of __builtin_stack_save/__builtin_stack_restore will
typically save one call saved register (resp. memory slot if we run out of
them).

--- tree-ssa-ccp.c.jj10 2007-09-04 23:09:30.000000000 +0200
+++ tree-ssa-ccp.c      2007-11-04 22:16:03.000000000 +0100
@@ -2598,6 +2598,76 @@ fold_stmt_inplace (tree stmt)
   return changed;
 }


+/* Try to optimize out __builtin_stack_restore.  Optimize it out
+   if there is another __builtin_stack_restore in the same basic
+   block and no calls or ASM_EXPRs are in between, or if this block's
+   only outgoing edge is to EXIT_BLOCK and there are no calls or
+   ASM_EXPRs after this __builtin_stack_restore.  */
+
+static tree
+optimize_stack_restore (basic_block bb, tree call, block_stmt_iterator i)
+{
+  tree stack_save, stmt, callee;
+
+  if (TREE_CODE (call) != CALL_EXPR
+      || call_expr_nargs (call) != 1
+      || TREE_CODE (CALL_EXPR_ARG (call, 0)) != SSA_NAME
+      || !POINTER_TYPE_P (TREE_TYPE (CALL_EXPR_ARG (call, 0))))
+    return NULL_TREE;
+
+  for (bsi_next (&i); !bsi_end_p (i); bsi_next (&i))
+    {
+      tree stmt = bsi_stmt (i);
+      tree call;
+
+      if (TREE_CODE (stmt) == ASM_EXPR)
+       return NULL_TREE;
+      call = get_call_expr_in (stmt);
+      if (call == NULL)
+       continue;
+
+      callee = get_callee_fndecl (call);
+      if (!callee || DECL_BUILT_IN_CLASS (callee) != BUILT_IN_NORMAL)
+       return NULL_TREE;
+
+      if (DECL_FUNCTION_CODE (callee) == BUILT_IN_STACK_RESTORE)
+       break;
+    }
+
+  if (bsi_end_p (i)
+      && (! single_succ_p (bb)
+         || single_succ_edge (bb)->dest != EXIT_BLOCK_PTR))
+    return NULL_TREE;
+
+  stack_save = SSA_NAME_DEF_STMT (CALL_EXPR_ARG (call, 0));
+  if (TREE_CODE (stack_save) != GIMPLE_MODIFY_STMT
+      || GIMPLE_STMT_OPERAND (stack_save, 0) != CALL_EXPR_ARG (call, 0)
+      || TREE_CODE (GIMPLE_STMT_OPERAND (stack_save, 1)) != CALL_EXPR
+      || tree_could_throw_p (stack_save)
+      || !has_single_use (CALL_EXPR_ARG (call, 0)))
+    return NULL_TREE;
+
+  callee = get_callee_fndecl (GIMPLE_STMT_OPERAND (stack_save, 1));
+  if (!callee
+      || DECL_BUILT_IN_CLASS (callee) != BUILT_IN_NORMAL
+      || DECL_FUNCTION_CODE (callee) != BUILT_IN_STACK_SAVE
+      || call_expr_nargs (GIMPLE_STMT_OPERAND (stack_save, 1)) != 0)
+    return NULL_TREE;
+
+  stmt = stack_save;
+  push_stmt_changes (&stmt);
+  if (!set_rhs (&stmt,
+               build_int_cst (TREE_TYPE (CALL_EXPR_ARG (call, 0)), 0)))
+    {
+      discard_stmt_changes (&stmt);
+      return NULL_TREE;
+    }
+  gcc_assert (stmt == stack_save);
+  pop_stmt_changes (&stmt);
+
+  return integer_zero_node;
+}
+

 /* Convert EXPR into a GIMPLE value suitable for substitution on the
    RHS of an assignment.  Insert the necessary statements before
    iterator *SI_P. 
@@ -2682,6 +2752,12 @@ execute_fold_all_builtins (void)
                result = integer_zero_node;
                break;

+             case BUILT_IN_STACK_RESTORE:
+               result = optimize_stack_restore (bb, *stmtp, i);
+               if (result)
+                 break;
+               /* FALLTHRU */
+
              default:
                bsi_next (&i);
                continue;


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=23848