From 1815e313a8fb519a77c94a908eb6dafc4ce51ffe Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Fri, 14 Jul 2023 11:46:22 +0200
Subject: cprop: Do not set REG_EQUAL note when simplifying paradoxical subreg
 [PR110206]

cprop1 pass does not consider paradoxical subreg and for (insn 22) claims
that it equals 8 elements of HImodeby setting REG_EQUAL note:

(insn 21 19 22 4 (set (reg:V4QI 98)
        (mem/u/c:V4QI (symbol_ref/u:DI ("*.LC1") [flags 0x2]) [0  S4 A32])) "pr110206.c":12:42 1530 {*movv4qi_internal}
     (expr_list:REG_EQUAL (const_vector:V4QI [
                (const_int -52 [0xffffffffffffffcc]) repeated x4
            ])
        (nil)))
(insn 22 21 23 4 (set (reg:V8HI 100)
        (zero_extend:V8HI (vec_select:V8QI (subreg:V16QI (reg:V4QI 98) 0)
                (parallel [
                        (const_int 0 [0])
                        (const_int 1 [0x1])
                        (const_int 2 [0x2])
                        (const_int 3 [0x3])
                        (const_int 4 [0x4])
                        (const_int 5 [0x5])
                        (const_int 6 [0x6])
                        (const_int 7 [0x7])
                    ])))) "pr110206.c":12:42 7471 {sse4_1_zero_extendv8qiv8hi2}
     (expr_list:REG_EQUAL (const_vector:V8HI [
                (const_int 204 [0xcc]) repeated x8
            ])
        (expr_list:REG_DEAD (reg:V4QI 98)
            (nil))))

We rely on the "undefined" vals to have a specific value (from the earlier
REG_EQUAL note) but actual code generation doesn't ensure this (it doesn't
need to).  That said, the issue isn't the constant folding per-se but that
we do not actually constant fold but register an equality that doesn't hold.

	PR target/110206

gcc/ChangeLog:

	* fwprop.cc (contains_paradoxical_subreg_p): Move to ...
	* rtlanal.cc (contains_paradoxical_subreg_p): ... here.
	* rtlanal.h (contains_paradoxical_subreg_p): Add prototype.
	* cprop.cc (try_replace_reg): Do not set REG_EQUAL note
	when the original source contains a paradoxical subreg.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr110206.c: New test.
---
 gcc/fwprop.cc | 16 +---------------
 1 file changed, 1 insertion(+), 15 deletions(-)

(limited to 'gcc/fwprop.cc')

diff --git a/gcc/fwprop.cc b/gcc/fwprop.cc
index ae342f5..0707a23 100644
--- a/gcc/fwprop.cc
+++ b/gcc/fwprop.cc
@@ -25,6 +25,7 @@ along with GCC; see the file COPYING3.  If not see
 #include "coretypes.h"
 #include "backend.h"
 #include "rtl.h"
+#include "rtlanal.h"
 #include "df.h"
 #include "rtl-ssa.h"
 
@@ -353,21 +354,6 @@ reg_single_def_p (rtx x)
   return REG_P (x) && crtl->ssa->single_dominating_def (REGNO (x));
 }
 
-/* Return true if X contains a paradoxical subreg.  */
-
-static bool
-contains_paradoxical_subreg_p (rtx x)
-{
-  subrtx_var_iterator::array_type array;
-  FOR_EACH_SUBRTX_VAR (iter, array, x, NONCONST)
-    {
-      x = *iter;
-      if (SUBREG_P (x) && paradoxical_subreg_p (x))
-	return true;
-    }
-  return false;
-}
-
 /* Try to substitute (set DEST SRC), which defines DEF, into note NOTE of
    USE_INSN.  Return the number of substitutions on success, otherwise return
    -1 and leave USE_INSN unchanged.
-- 
cgit v1.1