Skip to content

R
riscv-gcc-1
Commit 14ac6aa2 by Richard Biener Committed by Richard Biener
Options

re PR tree-optimization/53342 (rnflow.f90 is ~5% slower after revision 187340) 

2013-02-05  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/53342
	PR tree-optimization/53185
	* tree-vectorizer.h (vect_check_strided_load): Remove.
	* tree-vect-data-refs.c (vect_enhance_data_refs_alignment): Do
	not disallow peeling for vectorized strided loads.
	(vect_check_strided_load): Make static and simplify.
	(vect_analyze_data_refs): Adjust.
	* tree-vect-stmts.c (vectorizable_load): Handle peeled loops
	correctly when vectorizing strided loads.

	* gcc.dg/vect/pr53185-2.c: New testcase.

From-SVN: r195759
parent 3654d3cf
Showing with 64 additions and 51 deletions
gcc/ChangeLog
2013-02-05 Richard Biener <rguenther@suse.de>
PR tree-optimization/53342
PR tree-optimization/53185
* tree-vectorizer.h (vect_check_strided_load): Remove.
* tree-vect-data-refs.c (vect_enhance_data_refs_alignment): Do
not disallow peeling for vectorized strided loads.
(vect_check_strided_load): Make static and simplify.
(vect_analyze_data_refs): Adjust.
* tree-vect-stmts.c (vectorizable_load): Handle peeled loops
correctly when vectorizing strided loads.
2013-02-05 Richard Biener <rguenther@suse.de>
* doc/install.texi: Refer to ISL, not PPL.
2013-02-05 Jan Hubicka <jh@suse.cz>
......
gcc/testsuite/ChangeLog
2013-02-05 Richard Biener <rguenther@suse.de>
PR tree-optimization/53342
PR tree-optimization/53185
* gcc.dg/vect/pr53185-2.c: New testcase.
2013-02-05 Jan Hubicka <jh@suse.cz>
PR tree-optimization/55789
......
gcc/testsuite/gcc.dg/vect/pr53185-2.c 0 → 100644
void __attribute__((noinline,noclone))
fn1 (int * __restrict f, int * __restrict d, unsigned short a, int c)
{
unsigned short e;
for (e = 0; e < a; ++e)
f[e] = d[e * c];
}
extern void abort (void);
int main ()
{
int a[32], b[3 * 32];
int i, off;
for (i = 0; i < 3 * 32; ++i)
b[i] = i;
for (off = 0; off < 8; ++off)
{
fn1 (&a[off], &b[off], 32 - off, 3);
for (i = 0; i < 32 - off; ++i)
if (a[off+i] != b[off+i*3])
abort ();
}
return 0;
}
/* { dg-final { cleanup-tree-dump "vect" } } */
gcc/tree-vect-data-refs.c
......@@ -1615,18 +1615,6 @@ vect_enhance_data_refs_alignment (loop_vec_info loop_vinfo)
&& GROUP_FIRST_ELEMENT (stmt_info) != stmt)
continue;
/* FORNOW: Any strided load prevents peeling. The induction
variable analysis will fail when the prologue loop is generated,
and so we can't generate the new base for the pointer. */
if (STMT_VINFO_STRIDE_LOAD_P (stmt_info))
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
"strided load prevents peeling");
do_peeling = false;
break;
}
/* For invariant accesses there is nothing to enhance. */
if (integer_zerop (DR_STEP (dr)))
continue;
......@@ -2890,9 +2878,8 @@ vect_check_gather (gimple stmt, loop_vec_info loop_vinfo, tree *basep,
This handles ARRAY_REFs (with variant index) and MEM_REFs (with variant
base pointer) only. */
bool
vect_check_strided_load (gimple stmt, loop_vec_info loop_vinfo, tree *basep,
tree *stepp)
static bool
vect_check_strided_load (gimple stmt, loop_vec_info loop_vinfo)
{
struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
......@@ -2925,10 +2912,6 @@ vect_check_strided_load (gimple stmt, loop_vec_info loop_vinfo, tree *basep,
|| !simple_iv (loop, loop_containing_stmt (stmt), off, &iv, true))
return false;
if (basep)
*basep = iv.base;
if (stepp)
*stepp = iv.step;
return true;
}
......@@ -3473,8 +3456,7 @@ vect_analyze_data_refs (loop_vec_info loop_vinfo,
{
bool strided_load = false;
if (!nested_in_vect_loop_p (loop, stmt))
strided_load
= vect_check_strided_load (stmt, loop_vinfo, NULL, NULL);
strided_load = vect_check_strided_load (stmt, loop_vinfo);
if (!strided_load)
{
if (dump_enabled_p ())
......
gcc/tree-vect-stmts.c
......@@ -4353,7 +4353,6 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
tree aggr_type;
tree gather_base = NULL_TREE, gather_off = NULL_TREE;
tree gather_off_vectype = NULL_TREE, gather_decl = NULL_TREE;
tree stride_base, stride_step;
int gather_scale = 1;
enum vect_def_type gather_dt = vect_unknown_def_type;
......@@ -4462,11 +4461,7 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
}
}
else if (STMT_VINFO_STRIDE_LOAD_P (stmt_info))
{
if (!vect_check_strided_load (stmt, loop_vinfo,
&stride_base, &stride_step))
return false;
}
;
else
{
negative = tree_int_cst_compare (nested_in_vect_loop
......@@ -4674,13 +4669,21 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
bool insert_after;
gimple incr;
tree offvar;
tree ref = DR_REF (dr);
tree ivstep;
tree running_off;
vec<constructor_elt, va_gc> *v = NULL;
gimple_seq stmts = NULL;
tree stride_base, stride_step, alias_off;
gcc_assert (!nested_in_vect_loop);
gcc_assert (stride_base && stride_step);
stride_base
= fold_build_pointer_plus
(unshare_expr (DR_BASE_ADDRESS (dr)),
size_binop (PLUS_EXPR,
convert_to_ptrofftype (unshare_expr (DR_OFFSET (dr))),
convert_to_ptrofftype (DR_INIT(dr))));
stride_step = fold_convert (sizetype, unshare_expr (DR_STEP (dr)));
/* For a load with loop-invariant (but other than power-of-2)
stride (i.e. not a grouped access) like so:
......@@ -4716,6 +4719,7 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
prev_stmt_info = NULL;
running_off = offvar;
alias_off = build_int_cst (reference_alias_ptr_type (DR_REF (dr)), 0);
for (j = 0; j < ncopies; j++)
{
tree vec_inv;
......@@ -4725,33 +4729,16 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
{
tree newref, newoff;
gimple incr;
if (TREE_CODE (ref) == ARRAY_REF)
{
newref = build4 (ARRAY_REF, TREE_TYPE (ref),
unshare_expr (TREE_OPERAND (ref, 0)),
running_off,
NULL_TREE, NULL_TREE);
if (!useless_type_conversion_p (TREE_TYPE (vectype),
TREE_TYPE (newref)))
newref = build1 (VIEW_CONVERT_EXPR, TREE_TYPE (vectype),
newref);
}
else
newref = build2 (MEM_REF, TREE_TYPE (vectype),
running_off,
TREE_OPERAND (ref, 1));
newref = build2 (MEM_REF, TREE_TYPE (vectype),
running_off, alias_off);
newref = force_gimple_operand_gsi (gsi, newref, true,
NULL_TREE, true,
GSI_SAME_STMT);
CONSTRUCTOR_APPEND_ELT (v, NULL_TREE, newref);
newoff = copy_ssa_name (running_off, NULL);
if (POINTER_TYPE_P (TREE_TYPE (newoff)))
incr = gimple_build_assign_with_ops (POINTER_PLUS_EXPR, newoff,
running_off, stride_step);
else
incr = gimple_build_assign_with_ops (PLUS_EXPR, newoff,
running_off, stride_step);
incr = gimple_build_assign_with_ops (POINTER_PLUS_EXPR, newoff,
running_off, stride_step);
vect_finish_stmt_generation (stmt, incr, gsi);
running_off = newoff;
......
gcc/tree-vectorizer.h
......@@ -923,7 +923,6 @@ extern bool vect_analyze_data_ref_accesses (loop_vec_info, bb_vec_info);
extern bool vect_prune_runtime_alias_test_list (loop_vec_info);
extern tree vect_check_gather (gimple, loop_vec_info, tree *, tree *,
int *);
extern bool vect_check_strided_load (gimple, loop_vec_info, tree *, tree *);
extern bool vect_analyze_data_refs (loop_vec_info, bb_vec_info, int *);
extern tree vect_create_data_ref_ptr (gimple, tree, struct loop *, tree,
tree *, gimple_stmt_iterator *,
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment