c++: fold calls to std::move/forward [PR96780]

A well-formed call to std::move/forward is equivalent to a cast, but the
former being a function call means the compiler generates debug info,
which persists even after the call gets inlined, for an operation that's
never interesting to debug.

This patch addresses this problem by folding calls to std::move/forward
and other cast-like functions into simple casts as part of the frontend's
general expression folding routine.  This behavior is controlled by a
new flag -ffold-simple-inlines, and otherwise by -fno-inline, so that
users can enable this folding with -O0 (which implies -fno-inline).

After this patch with -O2 and a non-checking compiler, debug info size
for some testcases from range-v3 and cmcstl2 decreases by as much as ~10%
and overall compile time and memory usage decreases by ~2%.

	PR c++/96780

gcc/ChangeLog:

	* doc/invoke.texi (C++ Dialect Options): Document
	-ffold-simple-inlines.

gcc/c-family/ChangeLog:

	* c.opt: Add -ffold-simple-inlines.

gcc/cp/ChangeLog:

	* cp-gimplify.cc (cp_fold) <case CALL_EXPR>: Fold calls to
	std::move/forward and other cast-like functions into simple
	casts.

gcc/testsuite/ChangeLog:

	* g++.dg/opt/pr96780.C: New test.

gcc/c-family/c.opt

@@ -1731,6 +1731,10 @@ Support dynamic initialization of thread-local variables in a different translat
 fexternal-templates
 C++ ObjC++ WarnRemoved
 
+ffold-simple-inlines
+C++ ObjC++ Optimization Var(flag_fold_simple_inlines)
+Fold calls to simple inline functions.
+
 ffor-scope
 C++ ObjC++ WarnRemoved
 

gcc/cp/cp-gimplify.cc

@@ -41,6 +41,7 @@ along with GCC; see the file COPYING3.  If not see
 #include "file-prefix-map.h"
 #include "cgraph.h"
 #include "omp-general.h"
+#include "opts.h"
 
 /* Forward declarations.  */
 
@@ -2756,9 +2757,44 @@ cp_fold (tree x)
 
     case CALL_EXPR:
       {
-	int sv = optimize, nw = sv;
 	tree callee = get_callee_fndecl (x);
 
+	/* "Inline" calls to std::move/forward and other cast-like functions
+	   by simply folding them into a corresponding cast to their return
+	   type.  This is cheaper than relying on the middle end to do so, and
+	   also means we avoid generating useless debug info for them at all.
+
+	   At this point the argument has already been converted into a
+	   reference, so it suffices to use a NOP_EXPR to express the
+	   cast.  */
+	if ((OPTION_SET_P (flag_fold_simple_inlines)
+	     ? flag_fold_simple_inlines
+	     : !flag_no_inline)
+	    && call_expr_nargs (x) == 1
+	    && decl_in_std_namespace_p (callee)
+	    && DECL_NAME (callee) != NULL_TREE
+	    && (id_equal (DECL_NAME (callee), "move")
+		|| id_equal (DECL_NAME (callee), "forward")
+		|| id_equal (DECL_NAME (callee), "addressof")
+		/* This addressof equivalent is used heavily in libstdc++.  */
+		|| id_equal (DECL_NAME (callee), "__addressof")
+		|| id_equal (DECL_NAME (callee), "as_const")))
+	  {
+	    r = CALL_EXPR_ARG (x, 0);
+	    /* Check that the return and argument types are sane before
+	       folding.  */
+	    if (INDIRECT_TYPE_P (TREE_TYPE (x))
+		&& INDIRECT_TYPE_P (TREE_TYPE (r)))
+	      {
+		if (!same_type_p (TREE_TYPE (x), TREE_TYPE (r)))
+		  r = build_nop (TREE_TYPE (x), r);
+		x = cp_fold (r);
+		break;
+	      }
+	  }
+
+	int sv = optimize, nw = sv;
+
 	/* Some built-in function calls will be evaluated at compile-time in
 	   fold ().  Set optimize to 1 when folding __builtin_constant_p inside
 	   a constexpr function so that fold_builtin_1 doesn't fold it to 0.  */

gcc/doc/invoke.texi

@@ -3124,6 +3124,16 @@ On targets that support symbol aliases, the default is
 @option{-fextern-tls-init}.  On targets that do not support symbol
 aliases, the default is @option{-fno-extern-tls-init}.
 
+@item -ffold-simple-inlines
+@itemx -fno-fold-simple-inlines
+@opindex ffold-simple-inlines
+@opindex fno-fold-simple-inlines
+Permit the C++ frontend to fold calls to @code{std::move}, @code{std::forward},
+@code{std::addressof} and @code{std::as_const}.  In contrast to inlining, this
+means no debug information will be generated for such calls.  Since these
+functions are rarely interesting to debug, this flag is enabled by default
+unless @option{-fno-inline} is active.
+
 @item -fno-gnu-keywords
 @opindex fno-gnu-keywords
 @opindex fgnu-keywords

gcc/testsuite/g++.dg/opt/pr96780.C

@@ -0,0 +1,38 @@
+// PR c++/96780
+// Verify calls to std::move/forward are folded away by the frontend.
+// { dg-do compile { target c++11 } }
+// { dg-additional-options "-ffold-simple-inlines -fdump-tree-gimple" }
+
+#include <utility>
+
+struct A;
+
+extern A& a;
+extern const A& ca;
+
+void f() {
+  auto&& x1 = std::move(a);
+  auto&& x2 = std::forward<A>(a);
+  auto&& x3 = std::forward<A&>(a);
+
+  auto&& x4 = std::move(ca);
+  auto&& x5 = std::forward<const A>(ca);
+  auto&& x6 = std::forward<const A&>(ca);
+
+  auto x7 = std::addressof(a);
+  auto x8 = std::addressof(ca);
+#if __GLIBCXX__
+  auto x9 = std::__addressof(a);
+  auto x10 = std::__addressof(ca);
+#endif
+#if __cpp_lib_as_const
+  auto&& x11 = std::as_const(a);
+  auto&& x12 = std::as_const(ca);
+#endif
+}
+
+// { dg-final { scan-tree-dump-not "= std::move" "gimple" } }
+// { dg-final { scan-tree-dump-not "= std::forward" "gimple" } }
+// { dg-final { scan-tree-dump-not "= std::addressof" "gimple" } }
+// { dg-final { scan-tree-dump-not "= std::__addressof" "gimple" } }
+// { dg-final { scan-tree-dump-not "= std::as_const" "gimple" } }