Hi,
Based on vect_peeling algorithm, we know for sure that vectorized loop must
iterates at least once.
This patch sets range information for niter bounds of vectorized loop. This
helps niter analysis,
so iv elimination too.
Is it OK?
Thanks,
bin
2017-04-11 Bin Cheng <bin.ch...@arm.com>
* tree-vect-loop-manip.c (vect_gen_vector_loop_niters): Refactor.
Set range information for vector loop bound variable.
(vect_do_peeling): Ditto.From 0962735526bf474591e410104d6c9576691e0a1f Mon Sep 17 00:00:00 2001
From: Bin Cheng <binch...@e108451-lin.cambridge.arm.com>
Date: Tue, 14 Mar 2017 17:46:55 +0000
Subject: [PATCH 31/33] range_info-for-vect_loop-niters-20170224.txt
---
gcc/tree-vect-loop-manip.c | 39 +++++++++++++++++++++++----------------
1 file changed, 23 insertions(+), 16 deletions(-)
diff --git a/gcc/tree-vect-loop-manip.c b/gcc/tree-vect-loop-manip.c
index faeaa6d..0fc8cd3 100644
--- a/gcc/tree-vect-loop-manip.c
+++ b/gcc/tree-vect-loop-manip.c
@@ -1177,22 +1177,21 @@ vect_gen_vector_loop_niters (loop_vec_info loop_vinfo,
tree niters,
tree *niters_vector_ptr, bool niters_no_overflow)
{
tree ni_minus_gap, var;
- tree niters_vector;
+ tree niters_vector, type = TREE_TYPE (niters);
int vf = LOOP_VINFO_VECT_FACTOR (loop_vinfo);
edge pe = loop_preheader_edge (LOOP_VINFO_LOOP (loop_vinfo));
- tree log_vf = build_int_cst (TREE_TYPE (niters), exact_log2 (vf));
+ tree log_vf = build_int_cst (type, exact_log2 (vf));
/* If epilogue loop is required because of data accesses with gaps, we
subtract one iteration from the total number of iterations here for
correct calculation of RATIO. */
if (LOOP_VINFO_PEELING_FOR_GAPS (loop_vinfo))
{
- ni_minus_gap = fold_build2 (MINUS_EXPR, TREE_TYPE (niters),
- niters,
- build_one_cst (TREE_TYPE (niters)));
+ ni_minus_gap = fold_build2 (MINUS_EXPR, type, niters,
+ build_one_cst (type));
if (!is_gimple_val (ni_minus_gap))
{
- var = create_tmp_var (TREE_TYPE (niters), "ni_gap");
+ var = create_tmp_var (type, "ni_gap");
gimple *stmts = NULL;
ni_minus_gap = force_gimple_operand (ni_minus_gap, &stmts,
true, var);
@@ -1208,25 +1207,28 @@ vect_gen_vector_loop_niters (loop_vec_info loop_vinfo,
tree niters,
(niters - vf) >> log2(vf) + 1 by using the fact that we know ratio
will be at least one. */
if (niters_no_overflow)
- niters_vector = fold_build2 (RSHIFT_EXPR, TREE_TYPE (niters),
- ni_minus_gap, log_vf);
+ niters_vector = fold_build2 (RSHIFT_EXPR, type, ni_minus_gap, log_vf);
else
niters_vector
- = fold_build2 (PLUS_EXPR, TREE_TYPE (niters),
- fold_build2 (RSHIFT_EXPR, TREE_TYPE (niters),
- fold_build2 (MINUS_EXPR, TREE_TYPE (niters),
- ni_minus_gap,
- build_int_cst
- (TREE_TYPE (niters), vf)),
+ = fold_build2 (PLUS_EXPR, type,
+ fold_build2 (RSHIFT_EXPR, type,
+ fold_build2 (MINUS_EXPR, type, ni_minus_gap,
+ build_int_cst (type, vf)),
log_vf),
- build_int_cst (TREE_TYPE (niters), 1));
+ build_int_cst (type, 1));
if (!is_gimple_val (niters_vector))
{
- var = create_tmp_var (TREE_TYPE (niters), "bnd");
+ var = create_tmp_var (type, "bnd");
gimple *stmts = NULL;
niters_vector = force_gimple_operand (niters_vector, &stmts, true, var);
gsi_insert_seq_on_edge_immediate (pe, stmts);
+ /* Peeling algorithm guarantees that vector loop bound is at least ONE,
+ we set range information to make niters analyzer's life easier. */
+ if (TREE_CODE (niters_vector) == SSA_NAME)
+ set_range_info (niters_vector, VR_RANGE, build_int_cst (type, 1),
+ fold_build2 (RSHIFT_EXPR, type,
+ TYPE_MAX_VALUE (type), log_vf));
}
*niters_vector_ptr = niters_vector;
@@ -1773,6 +1775,11 @@ vect_do_peeling (loop_vec_info loop_vinfo, tree niters,
tree nitersm1,
= fold_build2 (MINUS_EXPR, type,
LOOP_VINFO_NITERSM1 (loop_vinfo), niters_prolog);
niters = vect_build_loop_niters (loop_vinfo);
+ /* It's guaranteed that vector loop bound before vectorization is at
+ least VF, so set range information. */
+ if (TREE_CODE (niters) == SSA_NAME)
+ set_range_info (niters, VR_RANGE,
+ build_int_cst (type, vf), TYPE_MAX_VALUE (type));
/* Prolog iterates at most bound_prolog times, latch iterates at
most bound_prolog - 1 times. */
--
1.9.1
