re PR rtl-optimization/77541 (wrong code with 512bit vectors of int128 @ -O1)

2016-11-24  Vladimir Makarov  <vmakarov@redhat.com>

	PR rtl-optimization/77541
	* lra-constraints.c (struct input_reload): Add field match_p.
	(get_reload_reg): Check modes of input reloads to generate unique
	value reload pseudo.
	(match_reload): Add input reload pseudo for the current insn.

2016-11-24  Vladimir Makarov  <vmakarov@redhat.com>

	PR rtl-optimization/77541
	* gcc.target/i386/pr77541.c: New.

From-SVN: r242848

4 files changed, 92 insertions, 31 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 7fb4826..a20c48a 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2016-11-24  Vladimir Makarov  <vmakarov@redhat.com>
+
+	PR rtl-optimization/77541
+	* lra-constraints.c (struct input_reload): Add field match_p.
+	(get_reload_reg): Check modes of input reloads to generate unique
+	value reload pseudo.
+	(match_reload): Add input reload pseudo for the current insn.
+
 2016-11-24  James Greenhalgh  <james.greenhalgh@arm.com>
 
 	* config/aarch64/aarch64-c.c (aarch64_update_cpp_builtins): Update
diff --git a/gcc/lra-constraints.c b/gcc/lra-constraints.c
index 56b65ef..133b55c 100644
--- a/gcc/lra-constraints.c
+++ b/gcc/lra-constraints.c
@@ -529,6 +529,8 @@ init_curr_operand_mode (void)
 /* Structure describes input reload of the current insns.  */
 struct input_reload
 {
+  /* True for input reload of matched operands.  */
+  bool match_p;
   /* Reloaded value.  */
   rtx input;
   /* Reload pseudo used.  */
@@ -563,6 +565,7 @@ get_reload_reg (enum op_type type, machine_mode mode, rtx original,
 {
   int i, regno;
   enum reg_class new_class;
+  bool unique_p = false;
 
   if (type == OP_OUT)
     {
@@ -574,39 +577,53 @@ get_reload_reg (enum op_type type, machine_mode mode, rtx original,
      e.g. volatile memory.  */
   if (! side_effects_p (original))
     for (i = 0; i < curr_insn_input_reloads_num; i++)
-      if (rtx_equal_p (curr_insn_input_reloads[i].input, original)
-	  && in_class_p (curr_insn_input_reloads[i].reg, rclass, &new_class))
-	{
-	  rtx reg = curr_insn_input_reloads[i].reg;
-	  regno = REGNO (reg);
-	  /* If input is equal to original and both are VOIDmode,
-	     GET_MODE (reg) might be still different from mode.
-	     Ensure we don't return *result_reg with wrong mode.  */
-	  if (GET_MODE (reg) != mode)
-	    {
-	      if (in_subreg_p)
-		continue;
-	      if (GET_MODE_SIZE (GET_MODE (reg)) < GET_MODE_SIZE (mode))
-		continue;
-	      reg = lowpart_subreg (mode, reg, GET_MODE (reg));
-	      if (reg == NULL_RTX || GET_CODE (reg) != SUBREG)
-		continue;
-	    }
-	  *result_reg = reg;
-	  if (lra_dump_file != NULL)
-	    {
-	      fprintf (lra_dump_file, "	 Reuse r%d for reload ", regno);
-	      dump_value_slim (lra_dump_file, original, 1);
-	    }
-	  if (new_class != lra_get_allocno_class (regno))
-	    lra_change_class (regno, new_class, ", change to", false);
-	  if (lra_dump_file != NULL)
-	    fprintf (lra_dump_file, "\n");
-	  return false;
-	}
-  *result_reg = lra_create_new_reg (mode, original, rclass, title);
+      {
+	if (! curr_insn_input_reloads[i].match_p
+	    && rtx_equal_p (curr_insn_input_reloads[i].input, original)
+	    && in_class_p (curr_insn_input_reloads[i].reg, rclass, &new_class))
+	  {
+	    rtx reg = curr_insn_input_reloads[i].reg;
+	    regno = REGNO (reg);
+	    /* If input is equal to original and both are VOIDmode,
+	       GET_MODE (reg) might be still different from mode.
+	       Ensure we don't return *result_reg with wrong mode.  */
+	    if (GET_MODE (reg) != mode)
+	      {
+		if (in_subreg_p)
+		  continue;
+		if (GET_MODE_SIZE (GET_MODE (reg)) < GET_MODE_SIZE (mode))
+		  continue;
+		reg = lowpart_subreg (mode, reg, GET_MODE (reg));
+		if (reg == NULL_RTX || GET_CODE (reg) != SUBREG)
+		  continue;
+	      }
+	    *result_reg = reg;
+	    if (lra_dump_file != NULL)
+	      {
+		fprintf (lra_dump_file, "	 Reuse r%d for reload ", regno);
+		dump_value_slim (lra_dump_file, original, 1);
+	      }
+	    if (new_class != lra_get_allocno_class (regno))
+	      lra_change_class (regno, new_class, ", change to", false);
+	    if (lra_dump_file != NULL)
+	      fprintf (lra_dump_file, "\n");
+	    return false;
+	  }
+	/* If we have an input reload with a different mode, make sure it
+	   will get a different hard reg.  */
+	else if (REG_P (original)
+		 && REG_P (curr_insn_input_reloads[i].input)
+		 && REGNO (original) == REGNO (curr_insn_input_reloads[i].input)
+		 && (GET_MODE (original)
+		     != GET_MODE (curr_insn_input_reloads[i].input)))
+	  unique_p = true;
+      }
+  *result_reg = (unique_p
+		 ? lra_create_new_reg_with_unique_value
+		 : lra_create_new_reg) (mode, original, rclass, title);
   lra_assert (curr_insn_input_reloads_num < LRA_MAX_INSN_RELOADS);
   curr_insn_input_reloads[curr_insn_input_reloads_num].input = original;
+  curr_insn_input_reloads[curr_insn_input_reloads_num].match_p = false;
   curr_insn_input_reloads[curr_insn_input_reloads_num++].reg = *result_reg;
   return true;
 }
@@ -1002,6 +1019,12 @@ match_reload (signed char out, signed char *ins, signed char *outs,
   lra_emit_move (copy_rtx (new_in_reg), in_rtx);
   *before = get_insns ();
   end_sequence ();
+  /* Add the new pseudo to consider values of subsequent input reload
+     pseudos.  */
+  lra_assert (curr_insn_input_reloads_num < LRA_MAX_INSN_RELOADS);
+  curr_insn_input_reloads[curr_insn_input_reloads_num].input = in_rtx;
+  curr_insn_input_reloads[curr_insn_input_reloads_num].match_p = true;
+  curr_insn_input_reloads[curr_insn_input_reloads_num++].reg = new_in_reg;
   for (i = 0; (in = ins[i]) >= 0; i++)
     {
       lra_assert
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 144cd3c..0994787 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2016-11-24  Vladimir Makarov  <vmakarov@redhat.com>
+
+	PR rtl-optimization/77541
+	* gcc.target/i386/pr77541.c: New.
+
 2016-11-24  Steven G. Kargl  <kargl@gcc.gnu.org>
 
 	PR fortran/78500
diff --git a/gcc/testsuite/gcc.target/i386/pr77541.c b/gcc/testsuite/gcc.target/i386/pr77541.c
new file mode 100644
index 0000000..2c533bb
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr77541.c
@@ -0,0 +1,25 @@
+/* { dg-do run } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -Wno-psabi" } */
+
+#define MAGIC 0x0706050403020100
+
+typedef unsigned long long u64;
+typedef unsigned __int128 v64u128 __attribute__ ((vector_size (64)));
+
+v64u128 __attribute__ ((noinline, noclone))
+foo (u64 x1, u64 x2, u64 x3, u64 x4, v64u128 x5)
+{
+  (void)x1, (void)x2;
+  x4 >>= x4 & 63;
+  return x3 + x4 + x5;
+}
+
+int
+main ()
+{
+  v64u128 x = foo (0, 0, 0, MAGIC, (v64u128) {});
+  if (x[0] != MAGIC || x[1] != MAGIC || x[2] != MAGIC || x[3] != MAGIC)
+    __builtin_abort();
+  return 0;
+}