aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--gcc/testsuite/gcc.dg/vect/bb-slp-conditional_store_1.c15
-rw-r--r--gcc/testsuite/gcc.dg/vect/vect-conditional_store_5.c28
-rw-r--r--gcc/testsuite/gcc.dg/vect/vect-conditional_store_6.c24
-rw-r--r--gcc/tree-vect-loop.cc12
-rw-r--r--gcc/tree-vect-patterns.cc39
-rw-r--r--gcc/tree-vect-slp.cc14
-rw-r--r--gcc/tree-vect-stmts.cc6
-rw-r--r--gcc/tree-vectorizer.cc3
-rw-r--r--gcc/tree-vectorizer.h7
9 files changed, 139 insertions, 9 deletions
diff --git a/gcc/testsuite/gcc.dg/vect/bb-slp-conditional_store_1.c b/gcc/testsuite/gcc.dg/vect/bb-slp-conditional_store_1.c
new file mode 100644
index 0000000..650a3bf
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/bb-slp-conditional_store_1.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-require-effective-target vect_float } */
+
+/* { dg-additional-options "-mavx2" { target avx2 } } */
+/* { dg-additional-options "-march=armv9-a" { target aarch64-*-* } } */
+
+void foo3 (float *restrict a, int *restrict c)
+{
+#pragma GCC unroll 8
+ for (int i = 0; i < 8; i++)
+ c[i] = a[i] > 1.0;
+}
+
+/* { dg-final { scan-tree-dump "vectorized using SLP" "slp1" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/vect-conditional_store_5.c b/gcc/testsuite/gcc.dg/vect/vect-conditional_store_5.c
new file mode 100644
index 0000000..37d60fa
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-conditional_store_5.c
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-require-effective-target vect_masked_store } */
+
+/* { dg-additional-options "-mavx2" { target avx2 } } */
+/* { dg-additional-options "-march=armv9-a" { target aarch64-*-* } } */
+
+#include <stdbool.h>
+
+void foo3 (float *restrict a, int *restrict b, int *restrict c, int n, int stride)
+{
+ if (stride <= 1)
+ return;
+
+ bool ai = a[0];
+
+ for (int i = 0; i < n; i++)
+ {
+ int res = c[i];
+ int t = b[i+stride];
+ if (ai)
+ t = res;
+ c[i] = t;
+ }
+}
+
+/* { dg-final { scan-tree-dump "LOOP VECTORIZED" "vect" } } */
+/* { dg-final { scan-tree-dump-not "VEC_COND_EXPR " "vect" { target aarch64-*-* } } } */
diff --git a/gcc/testsuite/gcc.dg/vect/vect-conditional_store_6.c b/gcc/testsuite/gcc.dg/vect/vect-conditional_store_6.c
new file mode 100644
index 0000000..5e1aedf
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-conditional_store_6.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-require-effective-target vect_masked_store } */
+
+/* { dg-additional-options "-mavx2" { target avx2 } } */
+/* { dg-additional-options "-march=armv9-a" { target aarch64-*-* } } */
+
+void foo3 (unsigned long long *restrict a, int *restrict b, int *restrict c, int n, int stride)
+{
+ if (stride <= 1)
+ return;
+
+ for (int i = 0; i < n; i++)
+ {
+ int res = c[i];
+ int t = b[i+stride];
+ if (a[i])
+ t = res;
+ c[i] = t;
+ }
+}
+
+/* { dg-final { scan-tree-dump "LOOP VECTORIZED" "vect" } } */
+/* { dg-final { scan-tree-dump-not "VEC_COND_EXPR " "vect" { target aarch64-*-* } } } */
diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index 0f54ebe..5cd4bdb 100644
--- a/gcc/tree-vect-loop.cc
+++ b/gcc/tree-vect-loop.cc
@@ -12356,6 +12356,18 @@ vect_transform_loop (loop_vec_info loop_vinfo, gimple *loop_vectorized_call)
vect_schedule_slp (loop_vinfo, LOOP_VINFO_SLP_INSTANCES (loop_vinfo));
}
+ /* Generate the loop invariant statements. */
+ if (!gimple_seq_empty_p (LOOP_VINFO_INV_PATTERN_DEF_SEQ (loop_vinfo)))
+ {
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_NOTE, vect_location,
+ "------>generating loop invariant statements\n");
+ gimple_stmt_iterator gsi;
+ gsi = gsi_after_labels (loop_preheader_edge (loop)->src);
+ gsi_insert_seq_before (&gsi, LOOP_VINFO_INV_PATTERN_DEF_SEQ (loop_vinfo),
+ GSI_CONTINUE_LINKING);
+ }
+
/* FORNOW: the vectorizer supports only loops which body consist
of one basic block (header + empty latch). When the vectorizer will
support more involved loop forms, the order by which the BBs are
diff --git a/gcc/tree-vect-patterns.cc b/gcc/tree-vect-patterns.cc
index a2bf90a..e7e877d 100644
--- a/gcc/tree-vect-patterns.cc
+++ b/gcc/tree-vect-patterns.cc
@@ -183,6 +183,17 @@ append_pattern_def_seq (vec_info *vinfo,
new_stmt);
}
+
+/* Add NEW_STMT to VINFO's invariant pattern definition statements. These
+ statements are not vectorized but are materialized as scalar in the loop
+ preheader. */
+
+static inline void
+append_inv_pattern_def_seq (vec_info *vinfo, gimple *new_stmt)
+{
+ gimple_seq_add_stmt_without_update (&vinfo->inv_pattern_def_seq, new_stmt);
+}
+
/* The caller wants to perform new operations on vect_external variable
VAR, so that the result of the operations would also be vect_external.
Return the edge on which the operations can be performed, if one exists.
@@ -6055,12 +6066,34 @@ vect_recog_bool_pattern (vec_info *vinfo,
var = adjust_bool_stmts (vinfo, bool_stmts, type, stmt_vinfo);
else if (integer_type_for_mask (var, vinfo))
return NULL;
+ else if (TREE_CODE (TREE_TYPE (var)) == BOOLEAN_TYPE
+ && !vect_get_internal_def (vinfo, var))
+ {
+ /* If the condition is already a boolean then manually convert it to a
+ mask of the given integer type but don't set a vectype. */
+ tree lhs_ivar = vect_recog_temp_ssa_var (type, NULL);
+ pattern_stmt = gimple_build_assign (lhs_ivar, COND_EXPR, var,
+ build_all_ones_cst (type),
+ build_zero_cst (type));
+ append_inv_pattern_def_seq (vinfo, pattern_stmt);
+ var = lhs_ivar;
+ }
+
+ tree lhs_var = vect_recog_temp_ssa_var (boolean_type_node, NULL);
+ pattern_stmt = gimple_build_assign (lhs_var, NE_EXPR, var,
+ build_zero_cst (TREE_TYPE (var)));
+
+ tree new_vectype = get_mask_type_for_scalar_type (vinfo, TREE_TYPE (var));
+ if (!new_vectype)
+ return NULL;
+
+ new_vectype = truth_type_for (new_vectype);
+ append_pattern_def_seq (vinfo, stmt_vinfo, pattern_stmt, new_vectype,
+ TREE_TYPE (var));
lhs = vect_recog_temp_ssa_var (TREE_TYPE (lhs), NULL);
pattern_stmt
- = gimple_build_assign (lhs, COND_EXPR,
- build2 (NE_EXPR, boolean_type_node,
- var, build_int_cst (TREE_TYPE (var), 0)),
+ = gimple_build_assign (lhs, COND_EXPR, lhs_var,
gimple_assign_rhs2 (last_stmt),
gimple_assign_rhs3 (last_stmt));
*type_out = vectype;
diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
index 9c817de..600987d 100644
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -9159,6 +9159,20 @@ vect_slp_region (vec<basic_block> bbs, vec<data_reference_p> datarefs,
vect_location = saved_vect_location;
}
+
+
+ /* Generate the invariant statements. */
+ if (!gimple_seq_empty_p (bb_vinfo->inv_pattern_def_seq))
+ {
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_NOTE, vect_location,
+ "------>generating invariant statements\n");
+
+ gimple_stmt_iterator gsi;
+ gsi = gsi_after_labels (bb_vinfo->bbs[0]);
+ gsi_insert_seq_after (&gsi, bb_vinfo->inv_pattern_def_seq,
+ GSI_CONTINUE_LINKING);
+ }
}
else
{
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 45003f7..b72b54d 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -12736,11 +12736,7 @@ vectorizable_comparison_1 (vec_info *vinfo, tree vectype,
/* Invariant comparison. */
if (!vectype)
{
- if (VECT_SCALAR_BOOLEAN_TYPE_P (TREE_TYPE (rhs1)))
- vectype = mask_type;
- else
- vectype = get_vectype_for_scalar_type (vinfo, TREE_TYPE (rhs1),
- slp_node);
+ vectype = get_vectype_for_scalar_type (vinfo, TREE_TYPE (rhs1), slp_node);
if (!vectype || maybe_ne (TYPE_VECTOR_SUBPARTS (vectype), nunits))
return false;
}
diff --git a/gcc/tree-vectorizer.cc b/gcc/tree-vectorizer.cc
index 4279b6d..d4ab473 100644
--- a/gcc/tree-vectorizer.cc
+++ b/gcc/tree-vectorizer.cc
@@ -466,7 +466,8 @@ vec_info::vec_info (vec_info::vec_kind kind_in, vec_info_shared *shared_)
shared (shared_),
stmt_vec_info_ro (false),
bbs (NULL),
- nbbs (0)
+ nbbs (0),
+ inv_pattern_def_seq (NULL)
{
stmt_vec_infos.create (50);
}
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index 53105f9..490061a 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -512,6 +512,12 @@ public:
/* The count of the basic blocks in the vectorization region. */
unsigned int nbbs;
+ /* Used to keep a sequence of def stmts of a pattern stmt that are loop
+ invariant if they exists.
+ The sequence is emitted in the loop preheader should the loop be vectorized
+ and are reset when undoing patterns. */
+ gimple_seq inv_pattern_def_seq;
+
private:
stmt_vec_info new_stmt_vec_info (gimple *stmt);
void set_vinfo_for_stmt (gimple *, stmt_vec_info, bool = true);
@@ -1042,6 +1048,7 @@ public:
#define LOOP_VINFO_ORIG_LOOP_INFO(L) (L)->orig_loop_info
#define LOOP_VINFO_SIMD_IF_COND(L) (L)->simd_if_cond
#define LOOP_VINFO_INNER_LOOP_COST_FACTOR(L) (L)->inner_loop_cost_factor
+#define LOOP_VINFO_INV_PATTERN_DEF_SEQ(L) (L)->inv_pattern_def_seq
#define LOOP_VINFO_FULLY_MASKED_P(L) \
(LOOP_VINFO_USING_PARTIAL_VECTORS_P (L) \
generated by cgit v1.1 at 2025-04-10 08:19:16 +0000