https://gcc.gnu.org/g:9c747183efa555e45200523c162021e385511be5
commit r15-903-g9c747183efa555e45200523c162021e385511be5
Author: Feng Xue <f...@os.amperecomputing.com>
Date: Thu May 16 11:08:38 2024 +0800
vect: Unify bbs in loop_vec_info and bb_vec_info
Both derived classes have their own "bbs" field, which have exactly same
purpose of recording all basic blocks inside the corresponding vect region,
while the fields are composed by different data type, one is normal array,
the other is auto_vec. This difference causes some duplicated code even
handling the same stuff, almost in tree-vect-patterns. One refinement is
lifting this field into the base class "vec_info", and reset its value to
the continuous memory area pointed by two old "bbs" in each constructor
of derived classes.
2024-05-16 Feng Xue <f...@os.amperecomputing.com>
gcc/
* tree-vect-loop.cc (_loop_vec_info::_loop_vec_info): Move
initialization of bbs to explicit construction code. Adjust the
definition of nbbs.
(update_epilogue_loop_vinfo): Update nbbs for epilog vinfo.
* tree-vect-patterns.cc (vect_determine_precisions): Make
loop_vec_info and bb_vec_info share same code.
(vect_pattern_recog): Remove duplicated vect_pattern_recog_1 loop.
* tree-vect-slp.cc (vect_get_and_check_slp_defs): Access to bbs[0]
via base vec_info class.
(_bb_vec_info::_bb_vec_info): Initialize bbs and nbbs using data
fields of input auto_vec<> bbs.
(vect_slp_region): Use access to nbbs to replace original
bbs.length().
(vect_schedule_slp_node): Access to bbs[0] via base vec_info class.
* tree-vectorizer.cc (vec_info::vec_info): Add initialization of
bbs and nbbs.
(vec_info::insert_seq_on_entry): Access to bbs[0] via base vec_info
class.
* tree-vectorizer.h (vec_info): Add new fields bbs and nbbs.
(LOOP_VINFO_NBBS): New macro.
(BB_VINFO_BBS): Rename BB_VINFO_BB to BB_VINFO_BBS.
(BB_VINFO_NBBS): New macro.
(_loop_vec_info): Remove field bbs.
(_bb_vec_info): Rename field bbs.
Diff:
---
gcc/tree-vect-loop.c | 0
gcc/tree-vect-loop.cc | 7 ++-
gcc/tree-vect-patterns.cc | 142 +++++++++++++---------------------------------
gcc/tree-vect-slp.cc | 23 +++++---
gcc/tree-vectorizer.cc | 7 ++-
gcc/tree-vectorizer.h | 23 ++++----
6 files changed, 74 insertions(+), 128 deletions(-)
diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index 3b94bb13a8b..04a9ac64df7 100644
--- a/gcc/tree-vect-loop.cc
+++ b/gcc/tree-vect-loop.cc
@@ -1028,7 +1028,6 @@ bb_in_loop_p (const_basic_block bb, const void *data)
_loop_vec_info::_loop_vec_info (class loop *loop_in, vec_info_shared *shared)
: vec_info (vec_info::loop, shared),
loop (loop_in),
- bbs (XCNEWVEC (basic_block, loop->num_nodes)),
num_itersm1 (NULL_TREE),
num_iters (NULL_TREE),
num_iters_unchanged (NULL_TREE),
@@ -1079,8 +1078,9 @@ _loop_vec_info::_loop_vec_info (class loop *loop_in,
vec_info_shared *shared)
case of the loop forms we allow, a dfs order of the BBs would the same
as reversed postorder traversal, so we are safe. */
- unsigned int nbbs = dfs_enumerate_from (loop->header, 0, bb_in_loop_p,
- bbs, loop->num_nodes, loop);
+ bbs = XCNEWVEC (basic_block, loop->num_nodes);
+ nbbs = dfs_enumerate_from (loop->header, 0, bb_in_loop_p, bbs,
+ loop->num_nodes, loop);
gcc_assert (nbbs == loop->num_nodes);
for (unsigned int i = 0; i < nbbs; i++)
@@ -11667,6 +11667,7 @@ update_epilogue_loop_vinfo (class loop *epilogue, tree
advance)
free (LOOP_VINFO_BBS (epilogue_vinfo));
LOOP_VINFO_BBS (epilogue_vinfo) = epilogue_bbs;
+ LOOP_VINFO_NBBS (epilogue_vinfo) = epilogue->num_nodes;
/* Advance data_reference's with the number of iterations of the previous
loop and its prologue. */
diff --git a/gcc/tree-vect-patterns.cc b/gcc/tree-vect-patterns.cc
index 8929e5aa7f3..88e7e34d78d 100644
--- a/gcc/tree-vect-patterns.cc
+++ b/gcc/tree-vect-patterns.cc
@@ -6925,81 +6925,41 @@ vect_determine_stmt_precisions (vec_info *vinfo,
stmt_vec_info stmt_info)
void
vect_determine_precisions (vec_info *vinfo)
{
+ basic_block *bbs = vinfo->bbs;
+ unsigned int nbbs = vinfo->nbbs;
+
DUMP_VECT_SCOPE ("vect_determine_precisions");
- if (loop_vec_info loop_vinfo = dyn_cast <loop_vec_info> (vinfo))
+ for (unsigned int i = 0; i < nbbs; i++)
{
- class loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
- basic_block *bbs = LOOP_VINFO_BBS (loop_vinfo);
- unsigned int nbbs = loop->num_nodes;
-
- for (unsigned int i = 0; i < nbbs; i++)
+ basic_block bb = bbs[i];
+ for (auto gsi = gsi_start_phis (bb); !gsi_end_p (gsi); gsi_next (&gsi))
{
- basic_block bb = bbs[i];
- for (auto gsi = gsi_start_phis (bb);
- !gsi_end_p (gsi); gsi_next (&gsi))
- {
- stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi.phi ());
- if (stmt_info)
- vect_determine_mask_precision (vinfo, stmt_info);
- }
- for (auto si = gsi_start_bb (bb); !gsi_end_p (si); gsi_next (&si))
- if (!is_gimple_debug (gsi_stmt (si)))
- vect_determine_mask_precision
- (vinfo, vinfo->lookup_stmt (gsi_stmt (si)));
+ stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi.phi ());
+ if (stmt_info && STMT_VINFO_VECTORIZABLE (stmt_info))
+ vect_determine_mask_precision (vinfo, stmt_info);
}
- for (unsigned int i = 0; i < nbbs; i++)
+ for (auto gsi = gsi_start_bb (bb); !gsi_end_p (gsi); gsi_next (&gsi))
{
- basic_block bb = bbs[nbbs - i - 1];
- for (gimple_stmt_iterator si = gsi_last_bb (bb);
- !gsi_end_p (si); gsi_prev (&si))
- if (!is_gimple_debug (gsi_stmt (si)))
- vect_determine_stmt_precisions
- (vinfo, vinfo->lookup_stmt (gsi_stmt (si)));
- for (auto gsi = gsi_start_phis (bb);
- !gsi_end_p (gsi); gsi_next (&gsi))
- {
- stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi.phi ());
- if (stmt_info)
- vect_determine_stmt_precisions (vinfo, stmt_info);
- }
+ stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi_stmt (gsi));
+ if (stmt_info && STMT_VINFO_VECTORIZABLE (stmt_info))
+ vect_determine_mask_precision (vinfo, stmt_info);
}
}
- else
+ for (unsigned int i = 0; i < nbbs; i++)
{
- bb_vec_info bb_vinfo = as_a <bb_vec_info> (vinfo);
- for (unsigned i = 0; i < bb_vinfo->bbs.length (); ++i)
+ basic_block bb = bbs[nbbs - i - 1];
+ for (auto gsi = gsi_last_bb (bb); !gsi_end_p (gsi); gsi_prev (&gsi))
{
- basic_block bb = bb_vinfo->bbs[i];
- for (auto gsi = gsi_start_phis (bb); !gsi_end_p (gsi); gsi_next
(&gsi))
- {
- stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi.phi ());
- if (stmt_info && STMT_VINFO_VECTORIZABLE (stmt_info))
- vect_determine_mask_precision (vinfo, stmt_info);
- }
- for (auto gsi = gsi_start_bb (bb); !gsi_end_p (gsi); gsi_next (&gsi))
- {
- stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi_stmt (gsi));
- if (stmt_info && STMT_VINFO_VECTORIZABLE (stmt_info))
- vect_determine_mask_precision (vinfo, stmt_info);
- }
+ stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi_stmt (gsi));
+ if (stmt_info && STMT_VINFO_VECTORIZABLE (stmt_info))
+ vect_determine_stmt_precisions (vinfo, stmt_info);
}
- for (int i = bb_vinfo->bbs.length () - 1; i != -1; --i)
+ for (auto gsi = gsi_start_phis (bb); !gsi_end_p (gsi); gsi_next (&gsi))
{
- for (gimple_stmt_iterator gsi = gsi_last_bb (bb_vinfo->bbs[i]);
- !gsi_end_p (gsi); gsi_prev (&gsi))
- {
- stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi_stmt (gsi));
- if (stmt_info && STMT_VINFO_VECTORIZABLE (stmt_info))
- vect_determine_stmt_precisions (vinfo, stmt_info);
- }
- for (auto gsi = gsi_start_phis (bb_vinfo->bbs[i]);
- !gsi_end_p (gsi); gsi_next (&gsi))
- {
- stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi.phi ());
- if (stmt_info && STMT_VINFO_VECTORIZABLE (stmt_info))
- vect_determine_stmt_precisions (vinfo, stmt_info);
- }
+ stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi.phi ());
+ if (stmt_info && STMT_VINFO_VECTORIZABLE (stmt_info))
+ vect_determine_stmt_precisions (vinfo, stmt_info);
}
}
}
@@ -7328,56 +7288,32 @@ vect_pattern_recog_1 (vec_info *vinfo,
void
vect_pattern_recog (vec_info *vinfo)
{
- class loop *loop;
- basic_block *bbs;
- unsigned int nbbs;
- gimple_stmt_iterator si;
- unsigned int i, j;
+ basic_block *bbs = vinfo->bbs;
+ unsigned int nbbs = vinfo->nbbs;
vect_determine_precisions (vinfo);
DUMP_VECT_SCOPE ("vect_pattern_recog");
- if (loop_vec_info loop_vinfo = dyn_cast <loop_vec_info> (vinfo))
+ /* Scan through the stmts in the region, applying the pattern recognition
+ functions starting at each stmt visited. */
+ for (unsigned i = 0; i < nbbs; i++)
{
- loop = LOOP_VINFO_LOOP (loop_vinfo);
- bbs = LOOP_VINFO_BBS (loop_vinfo);
- nbbs = loop->num_nodes;
+ basic_block bb = bbs[i];
- /* Scan through the loop stmts, applying the pattern recognition
- functions starting at each stmt visited: */
- for (i = 0; i < nbbs; i++)
+ for (auto si = gsi_start_bb (bb); !gsi_end_p (si); gsi_next (&si))
{
- basic_block bb = bbs[i];
- for (si = gsi_start_bb (bb); !gsi_end_p (si); gsi_next (&si))
- {
- if (is_gimple_debug (gsi_stmt (si)))
- continue;
- stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi_stmt (si));
- /* Scan over all generic vect_recog_xxx_pattern functions. */
- for (j = 0; j < NUM_PATTERNS; j++)
- vect_pattern_recog_1 (vinfo, &vect_vect_recog_func_ptrs[j],
- stmt_info);
- }
+ stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi_stmt (si));
+
+ if (!stmt_info || !STMT_VINFO_VECTORIZABLE (stmt_info))
+ continue;
+
+ /* Scan over all generic vect_recog_xxx_pattern functions. */
+ for (unsigned j = 0; j < NUM_PATTERNS; j++)
+ vect_pattern_recog_1 (vinfo, &vect_vect_recog_func_ptrs[j],
+ stmt_info);
}
}
- else
- {
- bb_vec_info bb_vinfo = as_a <bb_vec_info> (vinfo);
- for (unsigned i = 0; i < bb_vinfo->bbs.length (); ++i)
- for (gimple_stmt_iterator gsi = gsi_start_bb (bb_vinfo->bbs[i]);
- !gsi_end_p (gsi); gsi_next (&gsi))
- {
- stmt_vec_info stmt_info = bb_vinfo->lookup_stmt (gsi_stmt (gsi));
- if (!stmt_info || !STMT_VINFO_VECTORIZABLE (stmt_info))
- continue;
-
- /* Scan over all generic vect_recog_xxx_pattern functions. */
- for (j = 0; j < NUM_PATTERNS; j++)
- vect_pattern_recog_1 (vinfo,
- &vect_vect_recog_func_ptrs[j], stmt_info);
- }
- }
/* After this no more add_stmt calls are allowed. */
vinfo->stmt_vec_info_ro = true;
diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
index 7a963e28063..bc7a85d6bfc 100644
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -748,8 +748,7 @@ vect_get_and_check_slp_defs (vec_info *vinfo, unsigned char
swap,
&& is_a <bb_vec_info> (vinfo)
&& TREE_CODE (oprnd) == SSA_NAME
&& !SSA_NAME_IS_DEFAULT_DEF (oprnd)
- && !dominated_by_p (CDI_DOMINATORS,
- as_a <bb_vec_info> (vinfo)->bbs[0],
+ && !dominated_by_p (CDI_DOMINATORS, vinfo->bbs[0],
gimple_bb (SSA_NAME_DEF_STMT (oprnd))))
{
if (dump_enabled_p ())
@@ -6293,10 +6292,16 @@ vect_detect_hybrid_slp (loop_vec_info loop_vinfo)
_bb_vec_info::_bb_vec_info (vec<basic_block> _bbs, vec_info_shared *shared)
: vec_info (vec_info::bb, shared),
- bbs (_bbs),
roots (vNULL)
{
- for (unsigned i = 0; i < bbs.length (); ++i)
+ /* The region we are operating on. bbs[0] is the entry, excluding
+ its PHI nodes. In the future we might want to track an explicit
+ entry edge to cover bbs[0] PHI nodes and have a region entry
+ insert location. */
+ bbs = _bbs.address ();
+ nbbs = _bbs.length ();
+
+ for (unsigned i = 0; i < nbbs; ++i)
{
if (i != 0)
for (gphi_iterator si = gsi_start_phis (bbs[i]); !gsi_end_p (si);
@@ -6325,7 +6330,7 @@ _bb_vec_info::_bb_vec_info (vec<basic_block> _bbs,
vec_info_shared *shared)
_bb_vec_info::~_bb_vec_info ()
{
/* Reset region marker. */
- for (unsigned i = 0; i < bbs.length (); ++i)
+ for (unsigned i = 0; i < nbbs; ++i)
{
if (i != 0)
for (gphi_iterator si = gsi_start_phis (bbs[i]); !gsi_end_p (si);
@@ -7630,7 +7635,7 @@ vect_slp_is_lane_insert (gimple *use_stmt, tree vec,
unsigned *this_lane)
static void
vect_slp_check_for_roots (bb_vec_info bb_vinfo)
{
- for (unsigned i = 0; i < bb_vinfo->bbs.length (); ++i)
+ for (unsigned i = 0; i < bb_vinfo->nbbs; ++i)
for (gimple_stmt_iterator gsi = gsi_start_bb (bb_vinfo->bbs[i]);
!gsi_end_p (gsi); gsi_next (&gsi))
{
@@ -8114,7 +8119,7 @@ vect_slp_region (vec<basic_block> bbs,
vec<data_reference_p> datarefs,
we vectorized all if-converted code. */
if ((!profitable_subgraphs.is_empty () || force_clear) && orig_loop)
{
- gcc_assert (bb_vinfo->bbs.length () == 1);
+ gcc_assert (bb_vinfo->nbbs == 1);
for (gimple_stmt_iterator gsi = gsi_start_bb (bb_vinfo->bbs[0]);
!gsi_end_p (gsi); gsi_next (&gsi))
{
@@ -9618,14 +9623,14 @@ vect_schedule_slp_node (vec_info *vinfo,
if (!last_stmt)
{
gcc_assert (seen_vector_def);
- si = gsi_after_labels (as_a <bb_vec_info> (vinfo)->bbs[0]);
+ si = gsi_after_labels (vinfo->bbs[0]);
}
else if (is_ctrl_altering_stmt (last_stmt))
{
/* We split regions to vectorize at control altering stmts
with a definition so this must be an external which
we can insert at the start of the region. */
- si = gsi_after_labels (as_a <bb_vec_info> (vinfo)->bbs[0]);
+ si = gsi_after_labels (vinfo->bbs[0]);
}
else if (is_a <bb_vec_info> (vinfo)
&& gimple_bb (last_stmt) != gimple_bb (stmt_info->stmt)
diff --git a/gcc/tree-vectorizer.cc b/gcc/tree-vectorizer.cc
index 9001b738bf3..1fb4fb36ed4 100644
--- a/gcc/tree-vectorizer.cc
+++ b/gcc/tree-vectorizer.cc
@@ -463,7 +463,9 @@ shrink_simd_arrays
vec_info::vec_info (vec_info::vec_kind kind_in, vec_info_shared *shared_)
: kind (kind_in),
shared (shared_),
- stmt_vec_info_ro (false)
+ stmt_vec_info_ro (false),
+ bbs (NULL),
+ nbbs (0)
{
stmt_vec_infos.create (50);
}
@@ -660,9 +662,8 @@ vec_info::insert_seq_on_entry (stmt_vec_info context,
gimple_seq seq)
}
else
{
- bb_vec_info bb_vinfo = as_a <bb_vec_info> (this);
gimple_stmt_iterator gsi_region_begin
- = gsi_after_labels (bb_vinfo->bbs[0]);
+ = gsi_after_labels (bbs[0]);
gsi_insert_seq_before (&gsi_region_begin, seq, GSI_SAME_STMT);
}
}
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index 93bc30ef660..479823412fd 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -499,6 +499,16 @@ public:
made any decisions about which vector modes to use. */
machine_mode vector_mode;
+ /* The basic blocks in the vectorization region. For _loop_vec_info,
+ the memory is internally managed, while for _bb_vec_info, it points
+ to element space of an external auto_vec<>. This inconsistency is
+ not a good class design pattern. TODO: improve it with an unified
+ auto_vec<> whose lifetime is confined to vec_info object. */
+ basic_block *bbs;
+
+ /* The count of the basic blocks in the vectorization region. */
+ unsigned int nbbs;
+
private:
stmt_vec_info new_stmt_vec_info (gimple *stmt);
void set_vinfo_for_stmt (gimple *, stmt_vec_info, bool = true);
@@ -679,9 +689,6 @@ public:
/* The loop to which this info struct refers to. */
class loop *loop;
- /* The loop basic blocks. */
- basic_block *bbs;
-
/* Number of latch executions. */
tree num_itersm1;
/* Number of iterations. */
@@ -969,6 +976,7 @@ public:
#define LOOP_VINFO_EPILOGUE_IV_EXIT(L) (L)->vec_epilogue_loop_iv_exit
#define LOOP_VINFO_SCALAR_IV_EXIT(L) (L)->scalar_loop_iv_exit
#define LOOP_VINFO_BBS(L) (L)->bbs
+#define LOOP_VINFO_NBBS(L) (L)->nbbs
#define LOOP_VINFO_NITERSM1(L) (L)->num_itersm1
#define LOOP_VINFO_NITERS(L) (L)->num_iters
/* Since LOOP_VINFO_NITERS and LOOP_VINFO_NITERSM1 can change after
@@ -1094,16 +1102,11 @@ public:
_bb_vec_info (vec<basic_block> bbs, vec_info_shared *);
~_bb_vec_info ();
- /* The region we are operating on. bbs[0] is the entry, excluding
- its PHI nodes. In the future we might want to track an explicit
- entry edge to cover bbs[0] PHI nodes and have a region entry
- insert location. */
- vec<basic_block> bbs;
-
vec<slp_root> roots;
} *bb_vec_info;
-#define BB_VINFO_BB(B) (B)->bb
+#define BB_VINFO_BBS(B) (B)->bbs
+#define BB_VINFO_NBBS(B) (B)->nbbs
#define BB_VINFO_GROUPED_STORES(B) (B)->grouped_stores
#define BB_VINFO_SLP_INSTANCES(B) (B)->slp_instances
#define BB_VINFO_DATAREFS(B) (B)->shared->datarefs
