Since kind == vec_perm may not be a real vec_perm, just a broadcast or
simple load in BB vectorizer.
Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
Ready push to trunk.
gcc/ChangeLog:
* config/i386/i386.cc (ix86_vector_costs::finish_cost):
Restrict tune avx256_avoid_vec_perm to loop vectorization
only.
---
gcc/config/i386/i386.cc | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 55c9b16dd38..5a02e12d634 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -26305,15 +26305,15 @@ ix86_vector_costs::finish_cost (const vector_costs
*scalar_costs)
&& (exact_log2 (LOOP_VINFO_VECT_FACTOR (loop_vinfo).to_constant ())
> ceil_log2 (LOOP_VINFO_INT_NITERS (loop_vinfo))))
m_costs[vect_body] = INT_MAX;
+
+ for (int i = 0; i != 3; i++)
+ if (m_num_avx256_vec_perm[i]
+ && TARGET_AVX256_AVOID_VEC_PERM)
+ m_costs[i] = INT_MAX;
}
ix86_vect_estimate_reg_pressure ();
- for (int i = 0; i != 3; i++)
- if (m_num_avx256_vec_perm[i]
- && TARGET_AVX256_AVOID_VEC_PERM)
- m_costs[i] = INT_MAX;
-
/* When X86_TUNE_AVX512_TWO_EPILOGUES is enabled arrange for both
a AVX2 and a SSE epilogue for AVX512 vectorized loops. */
if (loop_vinfo
--
2.34.1
