[LRA]: Don't reuse chosen insn alternative with special memory constraint

To speed up GCC, LRA reuses chosen alternative from previous
constraint subpass.  A spilled pseudo is considered ok for any memory
constraint although stack slot assigned to the pseudo later might not
satisfy the chosen alternative constraint.  As we don't consider all insn
alternatives on the subsequent LRA sub-passes, it might result in LRA failure
to generate the correct insn.  This patch solves the problem.

gcc/ChangeLog:

	PR target/111225
	* lra-constraints.cc (goal_reuse_alt_p): New global flag.
	(process_alt_operands): Set up the flag.  Clear flag for chosen
	alternative with special memory constraints.
	(process_alt_operands): Set up used insn alternative depending on the flag.

gcc/testsuite/ChangeLog:

	PR target/111225
	* gcc.target/i386/pr111225.c: New test.

diff --git a/gcc/lra-constraints.cc b/gcc/lra-constraints.cc
index c718bedff32a55e8b1d388de4f1e18e11d20dab7..3aaa49069997c1d771a0ced82c9be1f4bf23fed1 100644 (file)
--- a/gcc/lra-constraints.cc
+++ b/gcc/lra-constraints.cc
@@ -1462,6 +1462,9 @@ static int goal_alt_matches[MAX_RECOG_OPERANDS];
 static int goal_alt_dont_inherit_ops_num;
 /* Numbers of operands whose reload pseudos should not be inherited.  */
 static int goal_alt_dont_inherit_ops[MAX_RECOG_OPERANDS];
+/* True if we should try only this alternative for the next constraint sub-pass
+   to speed up the sub-pass.  */
+static bool goal_reuse_alt_p;
 /* True if the insn commutative operands should be swapped.  */
 static bool goal_alt_swapped;
 /* The chosen insn alternative.         */
@@ -2130,6 +2133,7 @@ process_alt_operands (int only_alternative)
   int curr_alt_dont_inherit_ops_num;
   /* Numbers of operands whose reload pseudos should not be inherited. */
   int curr_alt_dont_inherit_ops[MAX_RECOG_OPERANDS];
+  bool curr_reuse_alt_p;
   /* True if output stack pointer reload should be generated for the current
      alternative.  */
   bool curr_alt_out_sp_reload_p;
@@ -2217,6 +2221,7 @@ process_alt_operands (int only_alternative)
       reject += static_reject;
       early_clobbered_regs_num = 0;
       curr_alt_out_sp_reload_p = false;
+      curr_reuse_alt_p = true;
       
       for (nop = 0; nop < n_operands; nop++)
        {
@@ -2574,7 +2579,10 @@ process_alt_operands (int only_alternative)
                      if (satisfies_memory_constraint_p (op, cn))
                        win = true;
                      else if (spilled_pseudo_p (op))
-                       win = true;
+                       {
+                         curr_reuse_alt_p = false;
+                         win = true;
+                       }
                      break;
                    }
                  break;
@@ -3318,6 +3326,7 @@ process_alt_operands (int only_alternative)
              goal_alt_offmemok[nop] = curr_alt_offmemok[nop];
            }
          goal_alt_dont_inherit_ops_num = curr_alt_dont_inherit_ops_num;
+         goal_reuse_alt_p = curr_reuse_alt_p;
          for (nop = 0; nop < curr_alt_dont_inherit_ops_num; nop++)
            goal_alt_dont_inherit_ops[nop] = curr_alt_dont_inherit_ops[nop];
          goal_alt_swapped = curr_swapped;
@@ -4399,7 +4408,8 @@ curr_insn_transform (bool check_only_p)
     }
 
   lra_assert (goal_alt_number >= 0);
-  lra_set_used_insn_alternative (curr_insn, goal_alt_number);
+  lra_set_used_insn_alternative (curr_insn, goal_reuse_alt_p
+                                ? goal_alt_number : LRA_UNKNOWN_ALT);
 
   if (lra_dump_file != NULL)
     {

diff --git a/gcc/testsuite/gcc.target/i386/pr111225.c b/gcc/testsuite/gcc.target/i386/pr111225.c
new file mode 100644 (file)
index 0000000..5d92daf
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr111225.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O1 -fsanitize=thread -mforce-drap -mavx512cd" } */
+
+typedef long long __m256i __attribute__ ((__vector_size__ (32)));
+
+int foo (__m256i x, __m256i y)
+{
+  __m256i a = x & ~y;
+  return !__builtin_ia32_ptestz256 (a, a);
+}
+
+int bar (__m256i x, __m256i y)
+{
+  __m256i a = ~x & y;
+  return !__builtin_ia32_ptestz256 (a, a);
+}