As part of the vector cost API cleanup this transitions
vect_model_simple_cost to only record costs with SLP node.
For this to work the patch adds an overload to record_stmt_cost
only passing in the SLP node.
The vect_prologue_cost_for_slp adjustment is one spot that
needs an eye with regard to re-doing the whole thing.
Bootstrapped and tested on x86_64-unknown-linux-gnu.
Richard.
* tree-vectorizer.h (record_stmt_cost): Add overload with
only SLP node and no vector type.
* tree-vect-stmts.cc (record_stmt_cost): Use
SLP_TREE_REPRESENTATIVE for stmt_vec_info.
(vect_model_simple_cost): Do not get stmt_vec_info argument
and adjust.
(vectorizable_call): Adjust.
(vectorizable_simd_clone_call): Likewise.
(vectorizable_conversion): Likewise.
(vectorizable_assignment): Likewise.
(vectorizable_shift): Likewise.
(vectorizable_operation): Likewise.
(vectorizable_condition): Likewise.
(vectorizable_comparison_1): Likewise.
* tree-vect-slp.cc (vect_prologue_cost_for_slp): Use
full-blown record_stmt_cost.
---
gcc/tree-vect-slp.cc | 2 +-
gcc/tree-vect-stmts.cc | 35 ++++++++++++++---------------------
gcc/tree-vectorizer.h | 11 +++++++++++
3 files changed, 26 insertions(+), 22 deletions(-)
diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
index 857517f5a86..fb2262a6137 100644
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -8036,7 +8036,7 @@ vect_prologue_cost_for_slp (slp_tree node,
we are costing so avoid passing it down more than once. Pass
it to the first vec_construct or scalar_to_vec part since for those
the x86 backend tries to account for GPR to XMM register moves. */
- record_stmt_cost (cost_vec, 1, kind,
+ record_stmt_cost (cost_vec, 1, kind, nullptr,
(kind != vector_load && !passed) ? node : nullptr,
vectype, 0, vect_prologue);
if (kind != vector_load)
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index bd390b26e0a..ec50f5098b5 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -130,7 +130,8 @@ record_stmt_cost (stmt_vector_for_cost *body_cost_vec, int
count,
tree vectype, int misalign,
enum vect_cost_model_location where)
{
- return record_stmt_cost (body_cost_vec, count, kind, NULL, node,
+ return record_stmt_cost (body_cost_vec, count, kind,
+ SLP_TREE_REPRESENTATIVE (node), node,
vectype, misalign, where);
}
@@ -905,11 +906,8 @@ vect_mark_stmts_to_be_vectorized (loop_vec_info
loop_vinfo, bool *fatal)
be generated for the single vector op. We will handle that shortly. */
static void
-vect_model_simple_cost (vec_info *,
- stmt_vec_info stmt_info, int ncopies,
- enum vect_def_type *dt,
- int ndts,
- slp_tree node,
+vect_model_simple_cost (vec_info *, int ncopies, enum vect_def_type *dt,
+ int ndts, slp_tree node,
stmt_vector_for_cost *cost_vec,
vect_cost_for_stmt kind = vector_stmt)
{
@@ -928,11 +926,11 @@ vect_model_simple_cost (vec_info *,
for (int i = 0; i < ndts; i++)
if (dt[i] == vect_constant_def || dt[i] == vect_external_def)
prologue_cost += record_stmt_cost (cost_vec, 1, scalar_to_vec,
- stmt_info, 0, vect_prologue);
+ node, 0, vect_prologue);
/* Pass the inside-of-loop statements to the target-specific cost model. */
inside_cost += record_stmt_cost (cost_vec, ncopies, kind,
- stmt_info, 0, vect_body);
+ node, 0, vect_body);
if (dump_enabled_p ())
dump_printf_loc (MSG_NOTE, vect_location,
@@ -3756,8 +3754,7 @@ vectorizable_call (vec_info *vinfo,
}
STMT_VINFO_TYPE (stmt_info) = call_vec_info_type;
DUMP_VECT_SCOPE ("vectorizable_call");
- vect_model_simple_cost (vinfo, stmt_info,
- ncopies, dt, ndts, slp_node, cost_vec);
+ vect_model_simple_cost (vinfo, ncopies, dt, ndts, slp_node, cost_vec);
if (ifn != IFN_LAST && modifier == NARROW && !slp_node)
record_stmt_cost (cost_vec, ncopies / 2,
vec_promote_demote, stmt_info, 0, vect_body);
@@ -4724,8 +4721,7 @@ vectorizable_simd_clone_call (vec_info *vinfo,
stmt_vec_info stmt_info,
STMT_VINFO_TYPE (stmt_info) = call_simd_clone_vec_info_type;
DUMP_VECT_SCOPE ("vectorizable_simd_clone_call");
-/* vect_model_simple_cost (vinfo, stmt_info, ncopies,
- dt, slp_node, cost_vec); */
+/* vect_model_simple_cost (vinfo, ncopies, dt, slp_node, cost_vec); */
return true;
}
@@ -5922,7 +5918,7 @@ vectorizable_conversion (vec_info *vinfo,
if (modifier == NONE)
{
STMT_VINFO_TYPE (stmt_info) = type_conversion_vec_info_type;
- vect_model_simple_cost (vinfo, stmt_info, (1 + multi_step_cvt),
+ vect_model_simple_cost (vinfo, (1 + multi_step_cvt),
dt, ndts, slp_node, cost_vec);
}
else if (modifier == NARROW_SRC || modifier == NARROW_DST)
@@ -6291,8 +6287,7 @@ vectorizable_assignment (vec_info *vinfo,
STMT_VINFO_TYPE (stmt_info) = assignment_vec_info_type;
DUMP_VECT_SCOPE ("vectorizable_assignment");
if (!vect_nop_conversion_p (stmt_info))
- vect_model_simple_cost (vinfo, stmt_info, ncopies, dt, ndts, slp_node,
- cost_vec);
+ vect_model_simple_cost (vinfo, ncopies, dt, ndts, slp_node, cost_vec);
return true;
}
@@ -6662,7 +6657,7 @@ vectorizable_shift (vec_info *vinfo,
}
STMT_VINFO_TYPE (stmt_info) = shift_vec_info_type;
DUMP_VECT_SCOPE ("vectorizable_shift");
- vect_model_simple_cost (vinfo, stmt_info, ncopies, dt,
+ vect_model_simple_cost (vinfo, ncopies, dt,
scalar_shift_arg ? 1 : ndts, slp_node, cost_vec);
return true;
}
@@ -7099,8 +7094,7 @@ vectorizable_operation (vec_info *vinfo,
STMT_VINFO_TYPE (stmt_info) = op_vec_info_type;
DUMP_VECT_SCOPE ("vectorizable_operation");
- vect_model_simple_cost (vinfo, stmt_info,
- 1, dt, ndts, slp_node, cost_vec);
+ vect_model_simple_cost (vinfo, 1, dt, ndts, slp_node, cost_vec);
if (using_emulated_vectors_p)
{
/* The above vect_model_simple_cost call handles constants
@@ -12931,7 +12925,7 @@ vectorizable_condition (vec_info *vinfo,
}
STMT_VINFO_TYPE (stmt_info) = condition_vec_info_type;
- vect_model_simple_cost (vinfo, stmt_info, ncopies, dts, ndts, slp_node,
+ vect_model_simple_cost (vinfo, ncopies, dts, ndts, slp_node,
cost_vec, kind);
return true;
}
@@ -13363,8 +13357,7 @@ vectorizable_comparison_1 (vec_info *vinfo, tree
vectype,
return false;
}
- vect_model_simple_cost (vinfo, stmt_info,
- ncopies * (1 + (bitop2 != NOP_EXPR)),
+ vect_model_simple_cost (vinfo, ncopies * (1 + (bitop2 != NOP_EXPR)),
dts, ndts, slp_node, cost_vec);
return true;
}
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index a2f33a5ecd6..118200ff4a8 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -2454,6 +2454,17 @@ record_stmt_cost (stmt_vector_for_cost *body_cost_vec,
int count,
STMT_VINFO_VECTYPE (stmt_info), misalign, where);
}
+/* Overload of record_stmt_cost with VECTYPE derived from SLP node. */
+
+inline unsigned
+record_stmt_cost (stmt_vector_for_cost *body_cost_vec, int count,
+ enum vect_cost_for_stmt kind, slp_tree node,
+ int misalign, enum vect_cost_model_location where)
+{
+ return record_stmt_cost (body_cost_vec, count, kind, node,
+ SLP_TREE_VECTYPE (node), misalign, where);
+}
+
extern void vect_finish_replace_stmt (vec_info *, stmt_vec_info, gimple *);
extern void vect_finish_stmt_generation (vec_info *, stmt_vec_info, gimple *,
gimple_stmt_iterator *);
--
2.43.0
