While working on autovectorizing for the RISCV port I encountered an issue
where can_duplicate_and_interleave_p assumes that GET_MODE_NUNITS is a
power of two. The RISC-V target has vector modes (e.g. VNx1DImode) that
are not a power of two.

Tested on RISCV and x86_64-linux-gnu. Okay?

2023-03-09  Michael Collison  <colli...@rivosinc.com>

        * poly-int.h (exact_div_p): New function to
        verify that argument is a power of 2 poly_int.
        * tree-vect-slp.cc (can_duplicate_and_interleave_p):
        Check that GET_MODE_NUNITS is a power of 2.
---
 gcc/poly-int.h       | 17 +++++++++++++++++
 gcc/tree-vect-slp.cc |  3 ++-
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/gcc/poly-int.h b/gcc/poly-int.h
index 12571455081..d09632f341f 100644
--- a/gcc/poly-int.h
+++ b/gcc/poly-int.h
@@ -2219,6 +2219,23 @@ multiple_p (const poly_int_pod<N, Ca> &a, const 
poly_int_pod<N, Cb> &b,
   return constant_multiple_p (a, b, multiple);
 }
 
+/* Return true, if A is known to be a multiple of B.  */
+
+template<unsigned int N, typename Ca, typename Cb>
+inline bool
+exact_div_p (const poly_int_pod<N, Ca> &a, Cb b)
+{
+  typedef POLY_CONST_COEFF (Ca, Cb) C;
+  poly_int<N, C> r;
+  for (unsigned int i = 0; i < N; i++)
+    {
+      if ((a.coeffs[i] % b) != 0)
+       return false;
+
+    }
+  return true;
+}
+
 /* Return A / B, given that A is known to be a multiple of B.  */
 
 template<unsigned int N, typename Ca, typename Cb>
diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
index 9a4e000925e..6be2036a13a 100644
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -426,7 +426,8 @@ can_duplicate_and_interleave_p (vec_info *vinfo, unsigned 
int count,
          if (vector_type
              && VECTOR_MODE_P (TYPE_MODE (vector_type))
              && known_eq (GET_MODE_SIZE (TYPE_MODE (vector_type)),
-                          GET_MODE_SIZE (base_vector_mode)))
+                          GET_MODE_SIZE (base_vector_mode))
+             && exact_div_p (GET_MODE_NUNITS (TYPE_MODE (vector_type)), 2))
            {
              /* Try fusing consecutive sequences of COUNT / NVECTORS elements
                 together into elements of type INT_TYPE and using the result
-- 
2.34.1

Reply via email to