re PR tree-optimization/79390 (10% performance drop in SciMark2 LU after r242550)

	PR tree-optimization/79390
	* optabs.c (emit_conditional_move): If the preferred op2/op3 operand
	order does not result in usable sequence, retry with reversed operand
	order.

	* gcc.target/i386/pr70465-2.c: Xfail the scan-assembler-not test.

From-SVN: r246882

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index efd66a6272a9ad78d226baf5f20c7d178b6a48b5..fd40a2a2f97d7824dd95c79f042662844813044c 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,10 @@
 2017-04-12  Jakub Jelinek  <jakub@redhat.com>
 
+       PR tree-optimization/79390
+       * optabs.c (emit_conditional_move): If the preferred op2/op3 operand
+       order does not result in usable sequence, retry with reversed operand
+       order.
+
        PR sanitizer/80403
        PR sanitizer/80404
        PR sanitizer/80405

diff --git a/gcc/optabs.c b/gcc/optabs.c
index 1afd593ae1520475b13c789ff6df2602b41be024..48e37f8bb40fe717487b36c11707da2c4652d20c 100644 (file)
--- a/gcc/optabs.c
+++ b/gcc/optabs.c
@@ -4258,12 +4258,15 @@ emit_conditional_move (rtx target, enum rtx_code code, rtx op0, rtx op1,
   if (cmode == VOIDmode)
     cmode = GET_MODE (op0);
 
+  enum rtx_code orig_code = code;
+  bool swapped = false;
   if (swap_commutative_operands_p (op2, op3)
       && ((reversed = reversed_comparison_code_parts (code, op0, op1, NULL))
           != UNKNOWN))
     {
       std::swap (op2, op3);
       code = reversed;
+      swapped = true;
     }
 
   if (mode == VOIDmode)
@@ -4272,45 +4275,62 @@ emit_conditional_move (rtx target, enum rtx_code code, rtx op0, rtx op1,
   icode = direct_optab_handler (movcc_optab, mode);
 
   if (icode == CODE_FOR_nothing)
-    return 0;
+    return NULL_RTX;
 
   if (!target)
     target = gen_reg_rtx (mode);
 
-  code = unsignedp ? unsigned_condition (code) : code;
-  comparison = simplify_gen_relational (code, VOIDmode, cmode, op0, op1);
-
-  /* We can get const0_rtx or const_true_rtx in some circumstances.  Just
-     return NULL and let the caller figure out how best to deal with this
-     situation.  */
-  if (!COMPARISON_P (comparison))
-    return NULL_RTX;
-
-  saved_pending_stack_adjust save;
-  save_pending_stack_adjust (&save);
-  last = get_last_insn ();
-  do_pending_stack_adjust ();
-  prepare_cmp_insn (XEXP (comparison, 0), XEXP (comparison, 1),
-                   GET_CODE (comparison), NULL_RTX, unsignedp, OPTAB_WIDEN,
-                   &comparison, &cmode);
-  if (comparison)
+  for (int pass = 0; ; pass++)
     {
-      struct expand_operand ops[4];
+      code = unsignedp ? unsigned_condition (code) : code;
+      comparison = simplify_gen_relational (code, VOIDmode, cmode, op0, op1);
 
-      create_output_operand (&ops[0], target, mode);
-      create_fixed_operand (&ops[1], comparison);
-      create_input_operand (&ops[2], op2, mode);
-      create_input_operand (&ops[3], op3, mode);
-      if (maybe_expand_insn (icode, 4, ops))
+      /* We can get const0_rtx or const_true_rtx in some circumstances.  Just
+        punt and let the caller figure out how best to deal with this
+        situation.  */
+      if (COMPARISON_P (comparison))
        {
-         if (ops[0].value != target)
-           convert_move (target, ops[0].value, false);
-         return target;
+         saved_pending_stack_adjust save;
+         save_pending_stack_adjust (&save);
+         last = get_last_insn ();
+         do_pending_stack_adjust ();
+         prepare_cmp_insn (XEXP (comparison, 0), XEXP (comparison, 1),
+                           GET_CODE (comparison), NULL_RTX, unsignedp,
+                           OPTAB_WIDEN, &comparison, &cmode);
+         if (comparison)
+           {
+             struct expand_operand ops[4];
+
+             create_output_operand (&ops[0], target, mode);
+             create_fixed_operand (&ops[1], comparison);
+             create_input_operand (&ops[2], op2, mode);
+             create_input_operand (&ops[3], op3, mode);
+             if (maybe_expand_insn (icode, 4, ops))
+               {
+                 if (ops[0].value != target)
+                   convert_move (target, ops[0].value, false);
+                 return target;
+               }
+           }
+         delete_insns_since (last);
+         restore_pending_stack_adjust (&save);
        }
+
+      if (pass == 1)
+       return NULL_RTX;
+
+      /* If the preferred op2/op3 order is not usable, retry with other
+        operand order, perhaps it will expand successfully.  */
+      if (swapped)
+       code = orig_code;
+      else if ((reversed = reversed_comparison_code_parts (orig_code, op0, op1,
+                                                          NULL))
+              != UNKNOWN)
+       code = reversed;
+      else
+       return NULL_RTX;
+      std::swap (op2, op3);
     }
-  delete_insns_since (last);
-  restore_pending_stack_adjust (&save);
-  return NULL_RTX;
 }
 
 

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 9dce05e31176a3e24b2ed22775abde3c4657bf79..b1594f22791507308e2150096f3749d291b488f7 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,5 +1,8 @@
 2017-04-12  Jakub Jelinek  <jakub@redhat.com>
 
+       PR tree-optimization/79390
+       * gcc.target/i386/pr70465-2.c: Xfail the scan-assembler-not test.
+
        PR sanitizer/80403
        PR sanitizer/80404
        PR sanitizer/80405

diff --git a/gcc/testsuite/gcc.target/i386/pr70465-2.c b/gcc/testsuite/gcc.target/i386/pr70465-2.c
index 71b683aad70ef304ca047faadea8cebad6897924..d60386d39ce639297ea93becfa480c046901a7aa 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/pr70465-2.c
+++ b/gcc/testsuite/gcc.target/i386/pr70465-2.c
@@ -1,7 +1,7 @@
 /* PR target/70465 */
 /* { dg-do compile } */
 /* { dg-options "-Ofast -mfpmath=387 -fomit-frame-pointer" } */
-/* { dg-final { scan-assembler-not "fxch\t%st.1" } } */
+/* { dg-final { scan-assembler-not "fxch\t%st.1" { xfail *-*-* } } } */
 
 extern float d[1024];