Hi All,
As reported in PR rtl-optimization/53352 CSE currently trips up on a
paradoxical subreg case. When compiling for ARM GNU/Linux with -O3
the expanded RTL of interest looks like:
(insn 12 11 13 3 (set (reg:SI 140)
(lshiftrt:SI (reg/v:SI 135 [ tmp1 ])
(const_int 16 [0x10])))
(nil))
(insn 13 12 14 3 (set (reg:QI 141)
(subreg:QI (reg:SI 140) 0))
(nil))
(insn 14 13 15 3 (set (reg:SI 142)
(subreg:SI (reg:QI 141) 0))
(nil))
(insn 15 14 16 3 (set (reg:SI 134 [ tmp1$2 ])
(and:SI (reg:SI 142)
(const_int 255 [0xff])))
(nil))
...
(insn 29 28 30 3 (set (reg:SI 0 r0)
(const_int 0 [0]))
(nil))
after "cse1" things look like:
(insn 12 11 13 2 (set (reg:SI 140)
(const_int 65280 [0xff00]))
(nil))
(insn 13 12 14 2 (set (reg:QI 141)
(subreg:QI (reg:SI 140) 0))
(expr_list:REG_EQUAL (const_int 0 [0])
(nil)))
;; This is *not* equal to zero because the upper
;; two bytes are undefined.
(insn 14 13 15 2 (set (reg:SI 142)
(subreg:SI (reg:QI 141) 0))
(expr_list:REG_EQUAL (const_int 0 [0])
(nil)))
(insn 15 14 16 2 (set (reg:SI 134 [ tmp1$2 ])
(reg:SI 142))
(expr_list:REG_EQUAL (const_int 0 [0])
(nil)))
...
(insn 29 28 30 2 (set (reg:SI 0 r0)
(reg:SI 142))
(expr_list:REG_EQUAL (const_int 0 [0])
(nil)))
I believe the REG_EQUAL note on the set involving a paradoxical subreg
is incorrect. It eventually causes 0xFF00 to be passed to the function
'foo'.
The attached patch fixes the issue by skipping the paradoxical subreg
in 'equiv_constant'. Compiler bootstrapped for i686-pc-linux-gnu and
full GCC test runs for i686-pc-linux-gnu and arm-none-linux-gnueabi (no
regressions). OK? (If this is OK, then can someone commit for me. I don't
have write access).
gcc/
2012-05-15 Meador Inge <mead...@codesourcery.com>
PR rtl-optimization/53352
* cse.c (equiv_constant): Ignore paradoxical subregs.
gcc/testsuite/
2012-05-15 Meador Inge <mead...@codesourcery.com>
PR rtl-optimization/53352
* gcc.dg/pr53352.c: New test.
--
Meador Inge
CodeSourcery / Mentor Embedded
http://www.mentor.com/embedded-software
Index: gcc/testsuite/gcc.dg/pr53352.c
===================================================================
--- gcc/testsuite/gcc.dg/pr53352.c (revision 0)
+++ gcc/testsuite/gcc.dg/pr53352.c (revision 0)
@@ -0,0 +1,41 @@
+/* { dg-do run } */
+/* { dg-options "-O1" } */
+
+#include <stdlib.h>
+
+typedef union
+{
+ struct
+ {
+ unsigned char a;
+ unsigned char b;
+ unsigned char c;
+ unsigned char d;
+ } parts;
+ unsigned long whole;
+} T;
+
+T *g_t;
+
+void bar (unsigned long x)
+{
+ if (x != 0)
+ abort ();
+}
+
+int main ()
+{
+ T one;
+ T two;
+ T tmp1, tmp2;
+
+ one.whole = 0xFFE0E0E0;
+ two.whole = 0xFF000000;
+ tmp1.parts = two.parts;
+ tmp2.parts = one.parts;
+ tmp2.parts.c = tmp1.parts.c;
+ one.parts = tmp2.parts;
+
+ g_t = &one;
+ bar (0);
+}
Index: gcc/cse.c
===================================================================
--- gcc/cse.c (revision 187470)
+++ gcc/cse.c (working copy)
@@ -3786,8 +3786,11 @@ equiv_constant (rtx x)
}
}
- /* Otherwise see if we already have a constant for the inner REG. */
+ /* Otherwise see if we already have a constant for the inner REG.
+ Don't bother with paradoxical subregs because we have no way
+ of knowing what the upper bytes are. */
if (REG_P (SUBREG_REG (x))
+ && (GET_MODE_SIZE (mode) <= GET_MODE_SIZE (imode))
&& (new_rtx = equiv_constant (SUBREG_REG (x))) != 0)
return simplify_subreg (mode, new_rtx, imode, SUBREG_BYTE (x));
