From: Robin Dapp <[email protected]>
This patch wants to change gather/scatter costing to use
vect_gather_load and vect_scatter_store instead of n
scalar_loads/stores. As far as I can tell, we haven't been using
vector_gather_load/scatter_store in a while because the
if ((kind == vector_load || kind == unaligned_load)
&& (stmt_info && STMT_VINFO_GATHER_SCATTER_P (stmt_info)))
guard wouldn't fire with kind = scalar_load.
Therefore, the patch removes it and passes the appropriate cost kind
directly, as well as the proper, potentially punned vectype.
Targets need to look at the vectype in order to determine the number of
gather/scatter elements now where they could rely on "count" before.
I had to adjust one x86 test case that expected vectorization with
gather. But haswell's gather costs are high at 44 and the "wrong"
scalar load costs before didn't inhibit vectorization in the same way.
I tried measuring a comparable test case on my x86 laptop and declining
to vectorize (i.e. gather is expensive) seems the right call, at least on my
machine.
gcc/ChangeLog:
* targhooks.cc (default_builtin_vectorization_cost): Use vector
subparts as cost estimate.
* tree-vect-stmts.cc (record_stmt_cost): Don't override cost
kind.
(vectorizable_store): Pass vector_scatter_store cost kind.
(vectorizable_load): Pass vector_gather_load cost kind.
gcc/testsuite/ChangeLog:
* gcc.target/i386/avx512vl-pr88464-11.c: Use no vect cost model.
---
gcc/targhooks.cc | 4 +++
.../gcc.target/i386/avx512vl-pr88464-11.c | 2 +-
gcc/tree-vect-stmts.cc | 27 ++++++-------------
3 files changed, 13 insertions(+), 20 deletions(-)
diff --git a/gcc/targhooks.cc b/gcc/targhooks.cc
index 88582e4fa51..57f9cefd3a1 100644
--- a/gcc/targhooks.cc
+++ b/gcc/targhooks.cc
@@ -779,6 +779,10 @@ default_builtin_vectorization_cost (enum
vect_cost_for_stmt type_of_cost,
case vec_deconstruct:
return estimated_poly_value (TYPE_VECTOR_SUBPARTS (vectype)) - 1;
+ case vector_gather_load:
+ case vector_scatter_store:
+ return estimated_poly_value (TYPE_VECTOR_SUBPARTS (vectype));
+
default:
gcc_unreachable ();
}
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-11.c
b/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-11.c
index 3a98108279a..7ade00d2a19 100644
--- a/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-11.c
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-11.c
@@ -1,6 +1,6 @@
/* PR tree-optimization/88464 */
/* { dg-do compile } */
-/* { dg-options "-O3 -mavx512vl -mprefer-vector-width=128 -mtune=haswell
-fdump-tree-vect-details" } */
+/* { dg-options "-O3 -mavx512vl -mprefer-vector-width=128 -mtune=haswell
-fvect-cost-model=unlimited -fdump-tree-vect-details" } */
/* { dg-final { scan-tree-dump-times "loop vectorized using 16 byte vectors" 4
"vect" } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 4 "vect"
} } */
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 7a4596c337c..0e73b02e356 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -95,13 +95,6 @@ record_stmt_cost (stmt_vector_for_cost *body_cost_vec, int
count,
tree vectype, int misalign,
enum vect_cost_model_location where)
{
- if ((kind == vector_load || kind == unaligned_load)
- && (stmt_info && STMT_VINFO_GATHER_SCATTER_P (stmt_info)))
- kind = vector_gather_load;
- if ((kind == vector_store || kind == unaligned_store)
- && (stmt_info && STMT_VINFO_GATHER_SCATTER_P (stmt_info)))
- kind = vector_scatter_store;
-
stmt_info_for_cost si
= { count, kind, where, stmt_info, node, vectype, misalign };
body_cost_vec->safe_push (si);
@@ -9073,10 +9066,9 @@ vectorizable_store (vec_info *vinfo,
+= record_stmt_cost (cost_vec, 1, vector_stmt,
slp_node, 0, vect_body);
- unsigned int cnunits = vect_nunits_for_cost (vectype);
inside_cost
- += record_stmt_cost (cost_vec, cnunits, scalar_store,
- slp_node, 0, vect_body);
+ += record_stmt_cost (cost_vec, 1, vector_scatter_store,
+ slp_node, vectype, 0, vect_body);
continue;
}
@@ -9189,10 +9181,9 @@ vectorizable_store (vec_info *vinfo,
(TYPE_MODE (TREE_TYPE (final_mask)))));
if (costing_p)
{
- unsigned int cnunits = vect_nunits_for_cost (vectype);
inside_cost
- += record_stmt_cost (cost_vec, cnunits, scalar_store,
- slp_node, 0, vect_body);
+ += record_stmt_cost (cost_vec, 1, vector_scatter_store,
+ slp_node, vectype, 0, vect_body);
continue;
}
@@ -11077,10 +11068,9 @@ vectorizable_load (vec_info *vinfo,
+= record_stmt_cost (cost_vec, 1, vector_stmt,
slp_node, 0, vect_body);
- unsigned int cnunits = vect_nunits_for_cost (vectype);
inside_cost
- = record_stmt_cost (cost_vec, cnunits, scalar_load,
- slp_node, 0, vect_body);
+ += record_stmt_cost (cost_vec, 1, vector_gather_load,
+ slp_node, vectype, 0, vect_body);
continue;
}
if (STMT_VINFO_GATHER_SCATTER_P (stmt_info))
@@ -11183,10 +11173,9 @@ vectorizable_load (vec_info *vinfo,
gcc_assert (!final_len && nunits.is_constant ());
if (costing_p)
{
- unsigned int cnunits = vect_nunits_for_cost (vectype);
inside_cost
- = record_stmt_cost (cost_vec, cnunits, scalar_load,
- slp_node, 0, vect_body);
+ += record_stmt_cost (cost_vec, 1, vector_gather_load,
+ slp_node, vectype, 0, vect_body);
continue;
}
tree offset_vectype = TREE_TYPE (vec_offsets[0]);
--
2.56.0
