re PR target/71663 (aarch64 Vector initialization can be improved slightly)

PR target/71663
gcc
	* config/aarch64/aarch64.c (aarch64_expand_vector_init):
	Improve vector initialization code gen for only variable case.

gcc/testsuite
	* gcc.target/aarch64/vect-init-1.c: Newtestcase.
	* gcc.target/aarch64/vect-init-2.c: Likewise.
	* gcc.target/aarch64/vect-init-3.c: Likewise.
	* gcc.target/aarch64/vect-init-4.c: Likewise.
	* gcc.target/aarch64/vect-init-5.c: Likewise.


Co-Authored-By: Naveen H.S <Naveen.Hurugalawadi@cavium.com>

From-SVN: r249187

gcc/ChangeLog

+2017-06-14  Andrew Pinski  <apinski@cavium.com>
+	    Naveen H.S  <Naveen.Hurugalawadi@cavium.com>
+
+	PR target/71663
+	* config/aarch64/aarch64.c (aarch64_expand_vector_init):
+	Improve vector initialization code gen for only variable case. 
+
 2017-06-14  Eric Botcazou  <ebotcazou@adacore.com>
 
 	* config/sparc/driver-sparc.c (cpu_names): Add SPARC-T5 entry.

gcc/config/aarch64/aarch64.c

@@ -11707,6 +11707,57 @@ aarch64_expand_vector_init (rtx target, rtx vals)
       return;
     }
 
+  enum insn_code icode = optab_handler (vec_set_optab, mode);
+  gcc_assert (icode != CODE_FOR_nothing);
+
+  /* If there are only variable elements, try to optimize
+     the insertion using dup for the most common element
+     followed by insertions.  */
+
+  /* The algorithm will fill matches[*][0] with the earliest matching element,
+     and matches[X][1] with the count of duplicate elements (if X is the
+     earliest element which has duplicates).  */
+
+  if (n_var == n_elts && n_elts <= 16)
+    {
+      int matches[16][2] = {0};
+      for (int i = 0; i < n_elts; i++)
+	{
+	  for (int j = 0; j <= i; j++)
+	    {
+	      if (rtx_equal_p (XVECEXP (vals, 0, i), XVECEXP (vals, 0, j)))
+		{
+		  matches[i][0] = j;
+		  matches[j][1]++;
+		  break;
+		}
+	    }
+	}
+      int maxelement = 0;
+      int maxv = 0;
+      for (int i = 0; i < n_elts; i++)
+	if (matches[i][1] > maxv)
+	  {
+	    maxelement = i;
+	    maxv = matches[i][1];
+	  }
+
+      /* Create a duplicate of the most common element.  */
+      rtx x = copy_to_mode_reg (inner_mode, XVECEXP (vals, 0, maxelement));
+      aarch64_emit_move (target, gen_rtx_VEC_DUPLICATE (mode, x));
+
+      /* Insert the rest.  */
+      for (int i = 0; i < n_elts; i++)
+	{
+	  rtx x = XVECEXP (vals, 0, i);
+	  if (matches[i][0] == maxelement)
+	    continue;
+	  x = copy_to_mode_reg (inner_mode, x);
+	  emit_insn (GEN_FCN (icode) (target, x, GEN_INT (i)));
+	}
+      return;
+    }
+
   /* Initialise a vector which is part-variable.  We want to first try
      to build those lanes which are constant in the most efficient way we
      can.  */
@@ -11740,10 +11791,6 @@ aarch64_expand_vector_init (rtx target, rtx vals)
     }
 
   /* Insert the variable lanes directly.  */
-
-  enum insn_code icode = optab_handler (vec_set_optab, mode);
-  gcc_assert (icode != CODE_FOR_nothing);
-
   for (int i = 0; i < n_elts; i++)
     {
       rtx x = XVECEXP (vals, 0, i);

gcc/testsuite/ChangeLog

+2017-06-14  Andrew Pinski  <apinski@cavium.com>
+	    Naveen H.S  <Naveen.Hurugalawadi@cavium.com>
+
+	PR target/71663
+	* gcc.target/aarch64/vect-init-1.c: Newtestcase.
+	* gcc.target/aarch64/vect-init-2.c: Likewise.
+	* gcc.target/aarch64/vect-init-3.c: Likewise.
+	* gcc.target/aarch64/vect-init-4.c: Likewise.
+	* gcc.target/aarch64/vect-init-5.c: Likewise.
+
 2017-06-14  Paolo Carlini  <paolo.carlini@oracle.com>
 
 	PR c++/58541

gcc/testsuite/gcc.target/aarch64/vect-init-1.c

+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+#define vector __attribute__((vector_size(16)))
+
+vector float combine (float a, float b, float c, float d)
+{
+  return (vector float) { a, b, c, d };
+}
+
+/* { dg-final { scan-assembler-not "movi\t" } } */
+/* { dg-final { scan-assembler-not "orr\t" } } */

gcc/testsuite/gcc.target/aarch64/vect-init-2.c

+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+#define vector __attribute__((vector_size(16)))
+
+vector float combine (float a, float b, float d)
+{
+  return (vector float) { a, b, a, d };
+}
+
+/* { dg-final { scan-assembler-not "movi\t" } } */
+/* { dg-final { scan-assembler-not "orr\t" } } */

gcc/testsuite/gcc.target/aarch64/vect-init-3.c

+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+#define vector __attribute__((vector_size(16)))
+
+vector float combine (float a, float b)
+{
+  return (vector float) { a, b, a, b };
+}
+
+/* { dg-final { scan-assembler-not "movi\t" } } */
+/* { dg-final { scan-assembler-not "orr\t" } } */

gcc/testsuite/gcc.target/aarch64/vect-init-4.c

+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+#define vector __attribute__((vector_size(16)))
+
+vector float combine (float a, float b)
+{
+  return (vector float) { a, b, b, a };
+}
+
+/* { dg-final { scan-assembler-not "movi\t" } } */
+/* { dg-final { scan-assembler-not "orr\t" } } */

gcc/testsuite/gcc.target/aarch64/vect-init-5.c

+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+#define vector __attribute__((vector_size(16)))
+
+vector float combine (float a, float b)
+{
+  return (vector float) { a, b, a, a };
+}
+
+/* { dg-final { scan-assembler-not "movi\t" } } */
+/* { dg-final { scan-assembler-not "orr\t" } } */