tree: Fix up tree_code_{length,type}

On Thu, Jan 26, 2023 at 09:45:35AM -0500, Patrick Palka via Gcc-patches wrote:
> > +#define DEFTREECODE(SYM, NAME, TYPE, LENGTH) TYPE,
> > +#define END_OF_BASE_TREE_CODES tcc_exceptional,
> > +
> > +
> >  /* Class of tree given its code.  */
> > -extern const enum tree_code_class tree_code_type[];
> > +constexpr enum tree_code_class tree_code_type[] = {
> > +#include "all-tree.def"
> > +};
> > +
> > +#undef DEFTREECODE
> > +#undef END_OF_BASE_TREE_CODES
> >
> >  /* Each tree code class has an associated string representation.
> >     These must correspond to the tree_code_class entries.  */
> >  extern const char *const tree_code_class_strings[];
> >
> >  /* Number of argument-words in each kind of tree-node.  */
> > -extern const unsigned char tree_code_length[];
> > +
> > +#define DEFTREECODE(SYM, NAME, TYPE, LENGTH) LENGTH,
> > +#define END_OF_BASE_TREE_CODES 0,
> > +constexpr unsigned char tree_code_length[] = {
> > +#include "all-tree.def"
> > +};
> > +
> > +#undef DEFTREECODE
> > +#undef END_OF_BASE_TREE_CODES
>
> IIUC defining these globals as non-inline constexpr gives them internal
> linkage, and so each TU contains its own unique copy of these globals.
> This bloats cc1plus by a tiny bit and is technically an ODR violation
> because some inline functions such as tree_class_check also ODR-use
> these variables and so each defn of tree_class_check will refer to a
> "different" tree_code_class.  Since inline variables are a C++17
> feature, I guess we could fix this by defining the globals the old way
> before C++17 and as inline constexpr otherwise?

And I'd argue with the tiny bit.
In my x86_64-linux cc1plus from today, I see 193 _ZL16tree_code_length vars,
374 bytes each, and 324 _ZL14tree_code_type vars, 1496 bytes each.
So, that means waste of 555016 .rodata bytes, plus being highly non-cache
friendly.

The following patch does that.

Tested on x86_64-linux in my -O0 working tree (system gcc 12
compiler) where .rodata shrunk with the patch by 928896 bytes, in last
stage of a bootstrapped tree (built by today's prev-gcc) where .rodata
shrunk by 561728 bytes (in neither case .text or most other sections
changed sizes) and on powerpc64le-linux --disable-bootstrap
(system gcc 4.8.5) to test also the non-C++17 case plus with
fully x86_64-linux, i686-linux and powerpc64le-linux bootstraps/regtests.

BTW, wonder if tree_code_type couldn't be an array of unsigned char
elements rather than enum tree_code_class and we'd then cast it
to the enum in the macro, that would shrink that array from 1496 bytes
to 374.  Of course, that sounds like stage1 material.

2023-01-27  Patrick Palka  <ppalka@redhat.com>
	    Jakub Jelinek  <jakub@redhat.com>

	* tree-core.h (tree_code_type, tree_code_length): For
	C++17 and later, add inline keyword, otherwise don't define
	the arrays, but declare extern arrays.
	* tree.cc (tree_code_type, tree_code_length): Define these
	arrays for C++14 and older.

2 files changed, 37 insertions, 4 deletions

diff --git a/gcc/tree-core.h b/gcc/tree-core.h
index 8124a13..acd8dee 100644
--- a/gcc/tree-core.h
+++ b/gcc/tree-core.h
@@ -2284,17 +2284,20 @@ struct floatn_type_info {
 /* Matrix describing the structures contained in a given tree code.  */
 extern bool tree_contains_struct[MAX_TREE_CODES][64];
 
+/* Class of tree given its code.  */
+#if __cpp_inline_variables >= 201606L
 #define DEFTREECODE(SYM, NAME, TYPE, LENGTH) TYPE,
 #define END_OF_BASE_TREE_CODES tcc_exceptional,
 
-
-/* Class of tree given its code.  */
-constexpr enum tree_code_class tree_code_type[] = {
+constexpr inline enum tree_code_class tree_code_type[] = {
 #include "all-tree.def"
 };
 
 #undef DEFTREECODE
 #undef END_OF_BASE_TREE_CODES
+#else
+extern const enum tree_code_class tree_code_type[];
+#endif
 
 /* Each tree code class has an associated string representation.
    These must correspond to the tree_code_class entries.  */
@@ -2302,14 +2305,18 @@ extern const char *const tree_code_class_strings[];
 
 /* Number of argument-words in each kind of tree-node.  */
 
+#if __cpp_inline_variables >= 201606L
 #define DEFTREECODE(SYM, NAME, TYPE, LENGTH) LENGTH,
 #define END_OF_BASE_TREE_CODES 0,
-constexpr unsigned char tree_code_length[] = {
+constexpr inline unsigned char tree_code_length[] = {
 #include "all-tree.def"
 };
 
 #undef DEFTREECODE
 #undef END_OF_BASE_TREE_CODES
+#else
+extern const unsigned char tree_code_length[];
+#endif
 
 /* Vector of all alias pairs for global symbols.  */
 extern GTY(()) vec<alias_pair, va_gc> *alias_pairs;
diff --git a/gcc/tree.cc b/gcc/tree.cc
index 7473912..952bbec 100644
--- a/gcc/tree.cc
+++ b/gcc/tree.cc
@@ -74,7 +74,33 @@ along with GCC; see the file COPYING3.  If not see
 #include "asan.h"
 #include "ubsan.h"
 
+#if __cpp_inline_variables < 201606L
+/* Tree code classes.  */
 
+#define DEFTREECODE(SYM, NAME, TYPE, LENGTH) TYPE,
+#define END_OF_BASE_TREE_CODES tcc_exceptional,
+
+const enum tree_code_class tree_code_type[] = {
+#include "all-tree.def"
+};
+
+#undef DEFTREECODE
+#undef END_OF_BASE_TREE_CODES
+
+/* Table indexed by tree code giving number of expression
+   operands beyond the fixed part of the node structure.
+   Not used for types or decls.  */
+
+#define DEFTREECODE(SYM, NAME, TYPE, LENGTH) LENGTH,
+#define END_OF_BASE_TREE_CODES 0,
+
+const unsigned char tree_code_length[] = {
+#include "all-tree.def"
+};
+
+#undef DEFTREECODE
+#undef END_OF_BASE_TREE_CODES
+#endif
 
 /* Names of tree components.
    Used for printing out the tree and error messages.  */