Re: [PATCH] Fix ICE in ia64 speculation support

[Maxim Kuvyrkov <maxim at codesourcery dot com>]

Eric Botcazou wrote:
> > Here is a patch implementing Paolo's approach.  At the moment I'm
> > bootstrapping / regtesting it on {x86_64 and ia64}-unknown-linux-gnu.
> >
> > OK for trunk?
>
> The middle-end part is OK if you add the proper documentation for the hook in 
> doc/tm.texi and get rid of the 'n' in default_unspec_may_trap_p (i.e. write 
> the loop like in may_trap_p_1).

Here is an updated patch.

Jim, sorry I missed to CC you on the original message.  Is ia64 part of 
the patch OK with you?


Thanks,

Maxim
2007-09-13  Paolo Bonzini  <bonzini@gnu.org>
	    Maxim Kuvyrkov  <maxim@codesourcery.com>

	* target.h (unspec_may_trap_p): New target hook.
	* target-def.h (TARGET_UNSPEC_MAY_TRAP_P): New macro.
	* targhooks.c (default_unspec_may_trap_p): Default implementation of
	the hook.
	* targhooks.h (default_unspec_may_trap_p): Declare it.
	* doc/tm.texi (TARGET_UNSPEC_MAY_TRAP_P): Document new hook.
	* rtlanal.c (may_trap_p_1): Use new hook.  Make global.
	* rtl.h (may_trap_p_1): Declare.
	
	* config/ia64/ia64.c (ia64_unspec_may_trap_p): New function to
	override default hook implementation.
	(TARGET_UNSPEC_MAY_TRAP_P): Override default implementation of the
	hook.
	
2007-09-13  Paolo Bonzini  <bonzini@gnu.org>
	    Maxim Kuvyrkov  <maxim@codesourcery.com>

	* gcc.c-torture/compile/20040709-2.c: New test.
	

Index: target.h
===================================================================
--- target.h	(revision 129295)
+++ target.h	(working copy)
@@ -652,6 +652,10 @@ struct gcc_target
      value.  */
   rtx (* allocate_initial_value) (rtx x);
 
+  /* Return nonzero if evaluating UNSPEC[_VOLATILE] X might cause a trap.
+     FLAGS has the same meaning as in rtlanal.c: may_trap_p_1.  */
+  int (* unspec_may_trap_p) (const_rtx x, unsigned flags);
+
   /* Given a register, this hook should return a parallel of registers
      to represent where to find the register pieces.  Define this hook
      if the register and its mode are represented in Dwarf in
Index: target-def.h
===================================================================
--- target-def.h	(revision 129295)
+++ target-def.h	(working copy)
@@ -480,6 +480,8 @@
 #define TARGET_MANGLE_TYPE hook_constcharptr_const_tree_null
 #define TARGET_ALLOCATE_INITIAL_VALUE NULL
 
+#define TARGET_UNSPEC_MAY_TRAP_P default_unspec_may_trap_p
+
 #ifndef TARGET_SET_CURRENT_FUNCTION
 #define TARGET_SET_CURRENT_FUNCTION hook_void_tree
 #endif
@@ -741,6 +743,7 @@
   TARGET_RTX_COSTS,				\
   TARGET_ADDRESS_COST,				\
   TARGET_ALLOCATE_INITIAL_VALUE,		\
+  TARGET_UNSPEC_MAY_TRAP_P,                     \
   TARGET_DWARF_REGISTER_SPAN,                   \
   TARGET_INIT_DWARF_REG_SIZES_EXTRA,		\
   TARGET_FIXED_CONDITION_CODE_REGS,		\
Index: targhooks.c
===================================================================
--- targhooks.c	(revision 129295)
+++ targhooks.c	(working copy)
@@ -75,6 +75,26 @@ default_external_libcall (rtx fun ATTRIB
 #endif
 }
 
+int
+default_unspec_may_trap_p (const_rtx x, unsigned flags)
+{
+  int i;
+
+  if (GET_CODE (x) == UNSPEC_VOLATILE
+      /* Any floating arithmetic may trap.  */
+      || (SCALAR_FLOAT_MODE_P (GET_MODE (x))
+	  && flag_trapping_math))
+    return 1;
+
+  for (i = 0; i < XVECLEN (x, 0); ++i)
+    {
+      if (may_trap_p_1 (XVECEXP (x, 0, i), flags))
+	return 1;
+    }
+
+  return 0;
+}
+
 enum machine_mode
 default_cc_modes_compatible (enum machine_mode m1, enum machine_mode m2)
 {
Index: targhooks.h
===================================================================
--- targhooks.h	(revision 129295)
+++ targhooks.h	(working copy)
@@ -19,6 +19,8 @@ along with GCC; see the file COPYING3.  
 
 extern void default_external_libcall (rtx);
 
+extern int default_unspec_may_trap_p (const_rtx, unsigned);
+
 extern enum machine_mode default_cc_modes_compatible (enum machine_mode,
 						      enum machine_mode);
 
Index: doc/tm.texi
===================================================================
--- doc/tm.texi	(revision 129295)
+++ doc/tm.texi	(working copy)
@@ -10151,6 +10151,13 @@ The default value of this hook is @code{
 allocation.
 @end deftypefn
 
+@deftypefn {Target Hook} int TARGET_UNSPEC_MAY_TRAP_P (const_rtx @var{x}, unsigned @var{flags})
+This target hook returns nonzero if unspec[_volatile] @var{x} might cause
+a trap.  Targets can use this hook to enhance precision of analysis
+for unspecs.  You may call @code{may_trap_p_1} to analyze inner elements
+of @var{x} in which case @var{flags} should be passed along.
+@end deftypefn
+
 @deftypefn {Target Hook} void TARGET_SET_CURRENT_FUNCTION (tree @var{decl})
 The compiler invokes this hook whenever it changes its current function 
 context (@code{cfun}).  You can define this function if
Index: rtlanal.c
===================================================================
--- rtlanal.c	(revision 129295)
+++ rtlanal.c	(working copy)
@@ -2182,7 +2182,7 @@ enum may_trap_p_flags
    cannot trap at its current location, but it might become trapping if moved
    elsewhere.  */
 
-static int
+int
 may_trap_p_1 (const_rtx x, unsigned flags)
 {
   int i;
@@ -2209,8 +2209,11 @@ may_trap_p_1 (const_rtx x, unsigned flag
     case SCRATCH:
       return 0;
 
-    case ASM_INPUT:
+    case UNSPEC:
     case UNSPEC_VOLATILE:
+      return targetm.unspec_may_trap_p (x, flags);
+
+    case ASM_INPUT:
     case TRAP_IF:
       return 1;
 
Index: rtl.h
===================================================================
--- rtl.h	(revision 129295)
+++ rtl.h	(working copy)
@@ -1739,6 +1739,7 @@ extern void remove_reg_equal_equiv_notes
 extern int side_effects_p (const_rtx);
 extern int volatile_refs_p (const_rtx);
 extern int volatile_insn_p (const_rtx);
+extern int may_trap_p_1 (const_rtx, unsigned);
 extern int may_trap_p (const_rtx);
 extern int may_trap_after_code_motion_p (const_rtx);
 extern int may_trap_or_fault_p (const_rtx);
Index: config/ia64/ia64.c
===================================================================
--- config/ia64/ia64.c	(revision 129295)
+++ config/ia64/ia64.c	(working copy)
@@ -203,6 +203,7 @@ static int ia64_arg_partial_bytes (CUMUL
 static bool ia64_function_ok_for_sibcall (tree, tree);
 static bool ia64_return_in_memory (const_tree, const_tree);
 static bool ia64_rtx_costs (rtx, int, int, int *);
+static int ia64_unspec_may_trap_p (const_rtx, unsigned);
 static void fix_range (const char *);
 static bool ia64_handle_option (size_t, const char *, int);
 static struct machine_function * ia64_init_machine_status (void);
@@ -409,6 +410,9 @@ static const struct attribute_spec ia64_
 #undef TARGET_ADDRESS_COST
 #define TARGET_ADDRESS_COST hook_int_rtx_0
 
+#undef TARGET_UNSPEC_MAY_TRAP_P
+#define TARGET_UNSPEC_MAY_TRAP_P ia64_unspec_may_trap_p
+
 #undef TARGET_MACHINE_DEPENDENT_REORG
 #define TARGET_MACHINE_DEPENDENT_REORG ia64_reorg
 
@@ -5073,6 +5077,29 @@ ia64_secondary_reload_class (enum reg_cl
 }
 
 
+/* Implement targetm.unspec_may_trap_p hook.  */
+static int
+ia64_unspec_may_trap_p (const_rtx x, unsigned flags)
+{
+  if (GET_CODE (x) == UNSPEC)
+    {
+      switch (XINT (x, 1))
+	{
+	case UNSPEC_LDA:
+	case UNSPEC_LDS:
+	case UNSPEC_LDSA:
+	case UNSPEC_LDCCLR:
+	case UNSPEC_CHKACLR:
+	case UNSPEC_CHKS:
+	  /* These unspecs are just wrappers.  */
+	  return may_trap_p_1 (XVECEXP (x, 0, 0), flags);
+	}
+    }
+
+  return default_unspec_may_trap_p (x, flags);
+}
+
+
 /* Parse the -mfixed-range= option string.  */
 
 static void
Index: testsuite/gcc.c-torture/compile/20040709-2.c
===================================================================
--- testsuite/gcc.c-torture/compile/20040709-2.c	(revision 0)
+++ testsuite/gcc.c-torture/compile/20040709-2.c	(revision 0)
@@ -0,0 +1,150 @@
+/* { dg-options "-funroll-loops -Wno-overflow" { target ia64-*-* } } */
+
+/* Check for ia64 data speculation failure with '-O2 -funroll-loops'.  */
+
+extern void abort (void);
+extern void exit (int);
+
+unsigned int
+myrnd (void)
+{
+  static unsigned int s = 1388815473;
+  s *= 1103515245;
+  s += 12345;
+  return (s / 65536) % 2048;
+}
+
+#define T(S)					\
+struct S s##S;					\
+struct S retme##S (struct S x)			\
+{						\
+  return x;					\
+}						\
+						\
+unsigned int fn1##S (unsigned int x)		\
+{						\
+  struct S y = s##S;				\
+  y.k += x;					\
+  y = retme##S (y);				\
+  return y.k;					\
+}						\
+						\
+unsigned int fn2##S (unsigned int x)		\
+{						\
+  struct S y = s##S;				\
+  y.k += x;					\
+  y.k %= 15;					\
+  return y.k;					\
+}						\
+						\
+unsigned int retit##S (void)			\
+{						\
+  return s##S.k;				\
+}						\
+						\
+unsigned int fn3##S (unsigned int x)		\
+{						\
+  s##S.k += x;					\
+  return retit##S ();				\
+}						\
+						\
+void test##S (void)				\
+{						\
+  int i;					\
+  unsigned int mask, v, a, r;			\
+  struct S x;					\
+  char *p = (char *) &s##S;			\
+  for (i = 0; i < sizeof (s##S); ++i)		\
+    *p++ = myrnd ();				\
+  if (__builtin_classify_type (s##S.l) == 8)	\
+    s##S.l = 5.25;				\
+  s##S.k = -1;					\
+  mask = s##S.k;				\
+  v = myrnd ();					\
+  a = myrnd ();					\
+  s##S.k = v;					\
+  x = s##S;					\
+  r = fn1##S (a);				\
+  if (x.i != s##S.i || x.j != s##S.j		\
+      || x.k != s##S.k || x.l != s##S.l		\
+      || ((v + a) & mask) != r)			\
+    abort ();					\
+  v = myrnd ();					\
+  a = myrnd ();					\
+  s##S.k = v;					\
+  x = s##S;					\
+  r = fn2##S (a);				\
+  if (x.i != s##S.i || x.j != s##S.j		\
+      || x.k != s##S.k || x.l != s##S.l		\
+      || ((((v + a) & mask) % 15) & mask) != r)	\
+    abort ();					\
+  v = myrnd ();					\
+  a = myrnd ();					\
+  s##S.k = v;					\
+  x = s##S;					\
+  r = fn3##S (a);				\
+  if (x.i != s##S.i || x.j != s##S.j		\
+      || s##S.k != r || x.l != s##S.l		\
+      || ((v + a) & mask) != r)			\
+    abort ();					\
+}
+
+#define pck __attribute__((packed))
+struct pck A { unsigned short i : 1, l : 1, j : 3, k : 11; }; T(A)
+struct pck B { unsigned short i : 4, j : 1, k : 11; unsigned int l; }; T(B)
+struct pck C { unsigned int l; unsigned short i : 4, j : 1, k : 11; }; T(C)
+struct pck D { unsigned long long l : 6, i : 6, j : 23, k : 29; }; T(D)
+struct pck E { unsigned long long l, i : 12, j : 23, k : 29; }; T(E)
+struct pck F { unsigned long long i : 12, j : 23, k : 29, l; }; T(F)
+struct pck G { unsigned short i : 1, j : 1, k : 6; unsigned long long l; }; T(G)
+struct pck H { unsigned short i : 6, j : 2, k : 8; unsigned long long l; }; T(H)
+struct pck I { unsigned short i : 1, j : 6, k : 1; unsigned long long l; }; T(I)
+struct pck J { unsigned short i : 1, j : 8, k : 7; unsigned short l; }; T(J)
+struct pck K { unsigned int k : 6, l : 1, j : 10, i : 15; }; T(K)
+struct pck L { unsigned int k : 6, j : 11, i : 15; unsigned int l; }; T(L)
+struct pck M { unsigned int l; unsigned short k : 6, j : 11, i : 15; }; T(M)
+struct pck N { unsigned long long l : 6, k : 6, j : 23, i : 29; }; T(N)
+struct pck O { unsigned long long l, k : 12, j : 23, i : 29; }; T(O)
+struct pck P { unsigned long long k : 12, j : 23, i : 29, l; }; T(P)
+struct pck Q { unsigned short k : 12, j : 1, i : 3; unsigned long long l; }; T(Q)
+struct pck R { unsigned short k : 2, j : 11, i : 3; unsigned long long l; }; T(R)
+struct pck S { unsigned short k : 1, j : 6, i : 9; unsigned long long l; }; T(S)
+struct pck T { unsigned short k : 1, j : 8, i : 7; unsigned short l; }; T(T)
+struct pck U { unsigned short j : 6, k : 1, i : 9; unsigned long long l; }; T(U)
+struct pck V { unsigned short j : 8, k : 1, i : 7; unsigned short l; }; T(V)
+struct pck W { long double l; unsigned int k : 12, j : 13, i : 7; }; T(W)
+struct pck X { unsigned int k : 12, j : 13, i : 7; long double l; }; T(X)
+struct pck Y { unsigned int k : 12, j : 11, i : 9; long double l; }; T(Y)
+struct pck Z { long double l; unsigned int j : 13, i : 7, k : 12; }; T(Z)
+
+int
+main (void)
+{
+  testA ();
+  testB ();
+  testC ();
+  testD ();
+  testE ();
+  testF ();
+  testG ();
+  testH ();
+  testI ();
+  testJ ();
+  testK ();
+  testL ();
+  testM ();
+  testN ();
+  testO ();
+  testP ();
+  testQ ();
+  testR ();
+  testS ();
+  testT ();
+  testU ();
+  testV ();
+  testW ();
+  testX ();
+  testY ();
+  testZ ();
+  exit (0);
+}