Generalise VEC_DUPLICATE folding for variable-length vectors

This patch uses the constant vector encoding scheme to handle
more cases of a VEC_DUPLICATE of another vector.  Duplicating
any fixed-length vector is fine, and duplicating a variable-length
vector is OK as long as that vector is also a duplicate of a
fixed-length sequence.

Other cases fell through to:

  if (VECTOR_MODE_P (mode) && GET_CODE (op) == CONST_VECTOR)

which was only expecting to deal with elementwise operations.

2019-07-29  Richard Sandiford  <richard.sandiford@arm.com>

gcc/
	* simplify-rtx.c (simplify_const_unary_operation): Fold a
	VEC_DUPLICATE of a fixed-length vector even if the result
	is variable-length.  Likewise fold a duplicate of a
	variable-length vector if the variable-length vector is
	itself a duplicate of a fixed-length sequence.
	(test_vector_ops_duplicate): Test more cases.

From-SVN: r273868

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index d80cd319bb65fbec37ea84e955384a11a7a230d3..706939c850dc9add4bd202168c64001cd2052018 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,12 @@
+2019-07-29  Richard Sandiford  <richard.sandiford@arm.com>
+
+       * simplify-rtx.c (simplify_const_unary_operation): Fold a
+       VEC_DUPLICATE of a fixed-length vector even if the result
+       is variable-length.  Likewise fold a duplicate of a
+       variable-length vector if the variable-length vector is
+       itself a duplicate of a fixed-length sequence.
+       (test_vector_ops_duplicate): Test more cases.
+
 2019-07-29  Richard Sandiford  <richard.sandiford@arm.com>
 
        * vector-builder.h (vector_builder): Add a shape template parameter.

diff --git a/gcc/simplify-rtx.c b/gcc/simplify-rtx.c
index 0a69c0503abec311aea987567b7e2dc8552d6f31..9359a3cdb4dc496600f0d624a61c1c75ed67f3a0 100644 (file)
--- a/gcc/simplify-rtx.c
+++ b/gcc/simplify-rtx.c
@@ -1736,23 +1736,24 @@ simplify_const_unary_operation (enum rtx_code code, machine_mode mode,
       }
       if (CONST_SCALAR_INT_P (op) || CONST_DOUBLE_AS_FLOAT_P (op))
        return gen_const_vec_duplicate (mode, op);
-      unsigned int n_elts;
       if (GET_CODE (op) == CONST_VECTOR
-         && GET_MODE_NUNITS (mode).is_constant (&n_elts))
-       {
-         /* This must be constant if we're duplicating it to a constant
-            number of elements.  */
-         unsigned int in_n_elts = CONST_VECTOR_NUNITS (op).to_constant ();
-         gcc_assert (in_n_elts < n_elts);
-         gcc_assert ((n_elts % in_n_elts) == 0);
-         rtvec v = rtvec_alloc (n_elts);
-         for (unsigned i = 0; i < n_elts; i++)
-           RTVEC_ELT (v, i) = CONST_VECTOR_ELT (op, i % in_n_elts);
-         return gen_rtx_CONST_VECTOR (mode, v);
+         && (CONST_VECTOR_DUPLICATE_P (op)
+             || CONST_VECTOR_NUNITS (op).is_constant ()))
+       {
+         unsigned int npatterns = (CONST_VECTOR_DUPLICATE_P (op)
+                                   ? CONST_VECTOR_NPATTERNS (op)
+                                   : CONST_VECTOR_NUNITS (op).to_constant ());
+         gcc_assert (multiple_p (GET_MODE_NUNITS (mode), npatterns));
+         rtx_vector_builder builder (mode, npatterns, 1);
+         for (unsigned i = 0; i < npatterns; i++)
+           builder.quick_push (CONST_VECTOR_ELT (op, i));
+         return builder.build ();
        }
     }
 
-  if (VECTOR_MODE_P (mode) && GET_CODE (op) == CONST_VECTOR)
+  if (VECTOR_MODE_P (mode)
+      && GET_CODE (op) == CONST_VECTOR
+      && known_eq (GET_MODE_NUNITS (mode), CONST_VECTOR_NUNITS (op)))
     {
       gcc_assert (GET_MODE (op) == op_mode);
 
@@ -6977,6 +6978,18 @@ test_vector_ops_duplicate (machine_mode mode, rtx scalar_reg)
       && mode_for_vector (inner_mode, 2).exists (&narrower_mode)
       && VECTOR_MODE_P (narrower_mode))
     {
+      /* Test VEC_DUPLICATE of a vector.  */
+      rtx_vector_builder nbuilder (narrower_mode, 2, 1);
+      nbuilder.quick_push (const0_rtx);
+      nbuilder.quick_push (const1_rtx);
+      rtx_vector_builder builder (mode, 2, 1);
+      builder.quick_push (const0_rtx);
+      builder.quick_push (const1_rtx);
+      ASSERT_RTX_EQ (builder.build (),
+                    simplify_unary_operation (VEC_DUPLICATE, mode,
+                                              nbuilder.build (),
+                                              narrower_mode));
+
       /* Test VEC_SELECT of a vector.  */
       rtx vec_par
        = gen_rtx_PARALLEL (VOIDmode, gen_rtvec (2, const1_rtx, const0_rtx));