aarch64: Add costs for storing one element of a vector

Storing one element of a vector is costed as a vec_to_scalar
followed by a scalar_store.  However, vec_to_scalar is also
used for reductions and for vector-to-GPR moves, which makes
it difficult to pick one cost for them all.

This patch therefore adds a cost for extracting one element
of a vector in preparation for storing it out.  The store
itself is still costed separately.

Like with the previous patches, this one only becomes active if
a CPU selects use_new_vector_costs.  It should therefore have
a very low impact on other CPUs.

gcc/
	* config/aarch64/aarch64-protos.h
	(simd_vec_cost::store_elt_extra_cost): New member variable.
	* config/aarch64/aarch64.c (generic_advsimd_vector_cost): Update
	accordingly, using the vec_to_scalar cost for the new field.
	(generic_sve_vector_cost, a64fx_advsimd_vector_cost): Likewise.
	(a64fx_sve_vector_cost, qdf24xx_advsimd_vector_cost): Likewise.
	(thunderx_advsimd_vector_cost, tsv110_advsimd_vector_cost): Likewise.
	(cortexa57_advsimd_vector_cost, exynosm1_advsimd_vector_cost)
	(xgene1_advsimd_vector_cost, thunderx2t99_advsimd_vector_cost)
	(thunderx3t110_advsimd_vector_cost): Likewise.
	(aarch64_detect_vector_stmt_subtype): Detect single-element stores.

2 files changed, 24 insertions, 0 deletions

diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
index 3d15275..fabe3df 100644
--- a/gcc/config/aarch64/aarch64-protos.h
+++ b/gcc/config/aarch64/aarch64-protos.h
@@ -224,6 +224,10 @@ struct simd_vec_cost
   const int reduc_f32_cost;
   const int reduc_f64_cost;
 
+  /* Additional cost of storing a single vector element, on top of the
+     normal cost of a scalar store.  */
+  const int store_elt_extra_cost;
+
   /* Cost of a vector-to-scalar operation.  */
   const int vec_to_scalar_cost;
 
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 8fb723d..20bb75b 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -601,6 +601,7 @@ static const advsimd_vec_cost generic_advsimd_vector_cost =
   2, /* reduc_f16_cost  */
   2, /* reduc_f32_cost  */
   2, /* reduc_f64_cost  */
+  2, /* store_elt_extra_cost  */
   2, /* vec_to_scalar_cost  */
   1, /* scalar_to_vec_cost  */
   1, /* align_load_cost  */
@@ -626,6 +627,7 @@ static const sve_vec_cost generic_sve_vector_cost =
     2, /* reduc_f16_cost  */
     2, /* reduc_f32_cost  */
     2, /* reduc_f64_cost  */
+    2, /* store_elt_extra_cost  */
     2, /* vec_to_scalar_cost  */
     1, /* scalar_to_vec_cost  */
     1, /* align_load_cost  */
@@ -667,6 +669,7 @@ static const advsimd_vec_cost a64fx_advsimd_vector_cost =
   13, /* reduc_f16_cost  */
   13, /* reduc_f32_cost  */
   13, /* reduc_f64_cost  */
+  13, /* store_elt_extra_cost  */
   13, /* vec_to_scalar_cost  */
   4, /* scalar_to_vec_cost  */
   6, /* align_load_cost  */
@@ -691,6 +694,7 @@ static const sve_vec_cost a64fx_sve_vector_cost =
     13, /* reduc_f16_cost  */
     13, /* reduc_f32_cost  */
     13, /* reduc_f64_cost  */
+    13, /* store_elt_extra_cost  */
     13, /* vec_to_scalar_cost  */
     4, /* scalar_to_vec_cost  */
     6, /* align_load_cost  */
@@ -731,6 +735,7 @@ static const advsimd_vec_cost qdf24xx_advsimd_vector_cost =
   1, /* reduc_f16_cost  */
   1, /* reduc_f32_cost  */
   1, /* reduc_f64_cost  */
+  1, /* store_elt_extra_cost  */
   1, /* vec_to_scalar_cost  */
   1, /* scalar_to_vec_cost  */
   1, /* align_load_cost  */
@@ -768,6 +773,7 @@ static const advsimd_vec_cost thunderx_advsimd_vector_cost =
   2, /* reduc_f16_cost  */
   2, /* reduc_f32_cost  */
   2, /* reduc_f64_cost  */
+  2, /* store_elt_extra_cost  */
   2, /* vec_to_scalar_cost  */
   2, /* scalar_to_vec_cost  */
   3, /* align_load_cost  */
@@ -804,6 +810,7 @@ static const advsimd_vec_cost tsv110_advsimd_vector_cost =
   3, /* reduc_f16_cost  */
   3, /* reduc_f32_cost  */
   3, /* reduc_f64_cost  */
+  3, /* store_elt_extra_cost  */
   3, /* vec_to_scalar_cost  */
   2, /* scalar_to_vec_cost  */
   5, /* align_load_cost  */
@@ -839,6 +846,7 @@ static const advsimd_vec_cost cortexa57_advsimd_vector_cost =
   8, /* reduc_f16_cost  */
   8, /* reduc_f32_cost  */
   8, /* reduc_f64_cost  */
+  8, /* store_elt_extra_cost  */
   8, /* vec_to_scalar_cost  */
   8, /* scalar_to_vec_cost  */
   4, /* align_load_cost  */
@@ -875,6 +883,7 @@ static const advsimd_vec_cost exynosm1_advsimd_vector_cost =
   3, /* reduc_f16_cost  */
   3, /* reduc_f32_cost  */
   3, /* reduc_f64_cost  */
+  3, /* store_elt_extra_cost  */
   3, /* vec_to_scalar_cost  */
   3, /* scalar_to_vec_cost  */
   5, /* align_load_cost  */
@@ -910,6 +919,7 @@ static const advsimd_vec_cost xgene1_advsimd_vector_cost =
   4, /* reduc_f16_cost  */
   4, /* reduc_f32_cost  */
   4, /* reduc_f64_cost  */
+  4, /* store_elt_extra_cost  */
   4, /* vec_to_scalar_cost  */
   4, /* scalar_to_vec_cost  */
   10, /* align_load_cost  */
@@ -946,6 +956,7 @@ static const advsimd_vec_cost thunderx2t99_advsimd_vector_cost =
   6, /* reduc_f16_cost  */
   6, /* reduc_f32_cost  */
   6, /* reduc_f64_cost  */
+  6, /* store_elt_extra_cost  */
   6, /* vec_to_scalar_cost  */
   5, /* scalar_to_vec_cost  */
   4, /* align_load_cost  */
@@ -982,6 +993,7 @@ static const advsimd_vec_cost thunderx3t110_advsimd_vector_cost =
   5, /* reduc_f16_cost  */
   5, /* reduc_f32_cost  */
   5, /* reduc_f64_cost  */
+  5, /* store_elt_extra_cost  */
   5, /* vec_to_scalar_cost  */
   5, /* scalar_to_vec_cost  */
   4, /* align_load_cost  */
@@ -14259,6 +14271,14 @@ aarch64_detect_vector_stmt_subtype (vec_info *vinfo, vect_cost_for_stmt kind,
   if (aarch64_sve_mode_p (TYPE_MODE (vectype)))
     sve_costs = aarch64_tune_params.vec_costs->sve;
 
+  /* Detect cases in which vec_to_scalar is describing the extraction of a
+     vector element in preparation for a scalar store.  The store itself is
+     costed separately.  */
+  if (kind == vec_to_scalar
+      && STMT_VINFO_DATA_REF (stmt_info)
+      && DR_IS_WRITE (STMT_VINFO_DATA_REF (stmt_info)))
+    return simd_costs->store_elt_extra_cost;
+
   /* Detect cases in which vec_to_scalar represents an in-loop reduction.  */
   if (kind == vec_to_scalar
       && where == vect_body