Skip to content
Projects
Groups
Snippets
Help
This project
Loading...
Sign in / Register
Toggle navigation
R
riscv-gcc-1
Overview
Overview
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
lvzhengyang
riscv-gcc-1
Commits
267d3070
Commit
267d3070
authored
Apr 20, 2011
by
Richard Sandiford
Committed by
Richard Sandiford
Apr 20, 2011
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Revert last patch.
From-SVN: r172763
parent
0b2ddd9c
Hide whitespace changes
Inline
Side-by-side
Showing
13 changed files
with
262 additions
and
630 deletions
+262
-630
gcc/ChangeLog
+7
-0
gcc/config/arm/t-linux-eabi
+2
-2
gcc/doc/md.texi
+0
-42
gcc/genopinit.c
+0
-2
gcc/internal-fn.c
+0
-67
gcc/internal-fn.def
+0
-3
gcc/optabs.h
+0
-5
gcc/tree-vect-data-refs.c
+8
-76
gcc/tree-vect-slp.c
+2
-3
gcc/tree-vect-stmts.c
+240
-414
gcc/tree-vectorizer.h
+3
-6
gcc/tree.c
+0
-9
gcc/tree.h
+0
-1
No files found.
gcc/ChangeLog
View file @
267d3070
2011-04-20 Richard Sandiford <richard.sandiford@linaro.org>
* doc/md.texi, optabs.h, genopinit.c, internal-fn.def
internal-fn.c, tree.h, tree.c, tree-vectorizer.h,
tree-vect-data-refs.c, tree-vect-stmts.c, tree-vect-slp.c: Revert
last patch.
2011-04-20 Richard Sandiford <richard.sandiford@linaro.org>
* doc/md.texi (vec_load_lanes, vec_store_lanes): Document.
* optabs.h (COI_vec_load_lanes, COI_vec_store_lanes): New
convert_optab_index values.
...
...
gcc/config/arm/t-linux-eabi
View file @
267d3070
...
...
@@ -21,8 +21,8 @@ TARGET_LIBGCC2_CFLAGS = -fPIC
# We do not build a Thumb multilib for Linux because the definition of
# CLEAR_INSN_CACHE in linux-gas.h does not work in Thumb mode.
MULTILIB_OPTIONS =
MULTILIB_DIRNAMES =
MULTILIB_OPTIONS =
mthumb
MULTILIB_DIRNAMES =
thumb
#MULTILIB_OPTIONS += mcpu=fa606te/mcpu=fa626te/mcpu=fmp626/mcpu=fa726te
#MULTILIB_DIRNAMES += fa606te fa626te fmp626 fa726te
...
...
gcc/doc/md.texi
View file @
267d3070
...
...
@@ -3846,48 +3846,6 @@ into consecutive memory locations. Operand 0 is the first of the
consecutive
memory
locations
,
operand
1
is
the
first
register
,
and
operand
2
is
a
constant
:
the
number
of
consecutive
registers
.
@cindex
@code
{
vec_load_lanes
@var
{
m
}
@var
{
n
}}
instruction
pattern
@item
@samp
{
vec_load_lanes
@var
{
m
}
@var
{
n
}}
Perform
an
interleaved
load
of
several
vectors
from
memory
operand
1
into
register
operand
0
.
Both
operands
have
mode
@var
{
m
}.
The
register
operand
is
viewed
as
holding
consecutive
vectors
of
mode
@var
{
n
},
while
the
memory
operand
is
a
flat
array
that
contains
the
same
number
of
elements
.
The
operation
is
equivalent
to
:
@smallexample
int
c
=
GET_MODE_SIZE
(
@var
{
m
})
/
GET_MODE_SIZE
(
@var
{
n
});
for
(
j
=
0
;
j
<
GET_MODE_NUNITS
(
@var
{
n
});
j
++
)
for
(
i
=
0
;
i
<
c
;
i
++
)
operand0
[
i
][
j
]
=
operand1
[
j
*
c
+
i
];
@end
smallexample
For
example
,
@samp
{
vec_load_lanestiv4hi
}
loads
8
16
-
bit
values
from
memory
into
a
register
of
mode
@samp
{
TI
}
@
.
The
register
contains
two
consecutive
vectors
of
mode
@samp
{
V4HI
}
@
.
This
pattern
can
only
be
used
if
:
@smallexample
TARGET_ARRAY_MODE_SUPPORTED_P
(
@var
{
n
},
@var
{
c
})
@end
smallexample
is
true
.
GCC
assumes
that
,
if
a
target
supports
this
kind
of
instruction
for
some
mode
@var
{
n
},
it
also
supports
unaligned
loads
for
vectors
of
mode
@var
{
n
}.
@cindex
@code
{
vec_store_lanes
@var
{
m
}
@var
{
n
}}
instruction
pattern
@item
@samp
{
vec_store_lanes
@var
{
m
}
@var
{
n
}}
Equivalent
to
@samp
{
vec_load_lanes
@var
{
m
}
@var
{
n
}},
with
the
memory
and
register
operands
reversed
.
That
is
,
the
instruction
is
equivalent
to
:
@smallexample
int
c
=
GET_MODE_SIZE
(
@var
{
m
})
/
GET_MODE_SIZE
(
@var
{
n
});
for
(
j
=
0
;
j
<
GET_MODE_NUNITS
(
@var
{
n
});
j
++
)
for
(
i
=
0
;
i
<
c
;
i
++
)
operand0
[
j
*
c
+
i
]
=
operand1
[
i
][
j
];
@end
smallexample
for
a
memory
operand
0
and
register
operand
1
.
@cindex
@code
{
vec_set
@var
{
m
}}
instruction
pattern
@item
@samp
{
vec_set
@var
{
m
}}
Set
given
field
in
the
vector
value
.
Operand
0
is
the
vector
to
modify
,
...
...
gcc/genopinit.c
View file @
267d3070
...
...
@@ -74,8 +74,6 @@ static const char * const optabs[] =
"set_convert_optab_handler (fractuns_optab, $B, $A, CODE_FOR_$(fractuns$Q$a$I$b2$))"
,
"set_convert_optab_handler (satfract_optab, $B, $A, CODE_FOR_$(satfract$a$Q$b2$))"
,
"set_convert_optab_handler (satfractuns_optab, $B, $A, CODE_FOR_$(satfractuns$I$a$Q$b2$))"
,
"set_convert_optab_handler (vec_load_lanes_optab, $A, $B, CODE_FOR_$(vec_load_lanes$a$b$))"
,
"set_convert_optab_handler (vec_store_lanes_optab, $A, $B, CODE_FOR_$(vec_store_lanes$a$b$))"
,
"set_optab_handler (add_optab, $A, CODE_FOR_$(add$P$a3$))"
,
"set_optab_handler (addv_optab, $A, CODE_FOR_$(add$F$a3$)),
\n
\
set_optab_handler (add_optab, $A, CODE_FOR_$(add$F$a3$))"
,
...
...
gcc/internal-fn.c
View file @
267d3070
...
...
@@ -42,73 +42,6 @@ const int internal_fn_flags_array[] = {
0
};
/* ARRAY_TYPE is an array of vector modes. Return the associated insn
for load-lanes-style optab OPTAB. The insn must exist. */
static
enum
insn_code
get_multi_vector_move
(
tree
array_type
,
convert_optab
optab
)
{
enum
insn_code
icode
;
enum
machine_mode
imode
;
enum
machine_mode
vmode
;
gcc_assert
(
TREE_CODE
(
array_type
)
==
ARRAY_TYPE
);
imode
=
TYPE_MODE
(
array_type
);
vmode
=
TYPE_MODE
(
TREE_TYPE
(
array_type
));
icode
=
convert_optab_handler
(
optab
,
imode
,
vmode
);
gcc_assert
(
icode
!=
CODE_FOR_nothing
);
return
icode
;
}
/* Expand LOAD_LANES call STMT. */
static
void
expand_LOAD_LANES
(
gimple
stmt
)
{
struct
expand_operand
ops
[
2
];
tree
type
,
lhs
,
rhs
;
rtx
target
,
mem
;
lhs
=
gimple_call_lhs
(
stmt
);
rhs
=
gimple_call_arg
(
stmt
,
0
);
type
=
TREE_TYPE
(
lhs
);
target
=
expand_expr
(
lhs
,
NULL_RTX
,
VOIDmode
,
EXPAND_WRITE
);
mem
=
expand_normal
(
rhs
);
gcc_assert
(
MEM_P
(
mem
));
PUT_MODE
(
mem
,
TYPE_MODE
(
type
));
create_output_operand
(
&
ops
[
0
],
target
,
TYPE_MODE
(
type
));
create_fixed_operand
(
&
ops
[
1
],
mem
);
expand_insn
(
get_multi_vector_move
(
type
,
vec_load_lanes_optab
),
2
,
ops
);
}
/* Expand STORE_LANES call STMT. */
static
void
expand_STORE_LANES
(
gimple
stmt
)
{
struct
expand_operand
ops
[
2
];
tree
type
,
lhs
,
rhs
;
rtx
target
,
reg
;
lhs
=
gimple_call_lhs
(
stmt
);
rhs
=
gimple_call_arg
(
stmt
,
0
);
type
=
TREE_TYPE
(
rhs
);
target
=
expand_expr
(
lhs
,
NULL_RTX
,
VOIDmode
,
EXPAND_WRITE
);
reg
=
expand_normal
(
rhs
);
gcc_assert
(
MEM_P
(
target
));
PUT_MODE
(
target
,
TYPE_MODE
(
type
));
create_fixed_operand
(
&
ops
[
0
],
target
);
create_input_operand
(
&
ops
[
1
],
reg
,
TYPE_MODE
(
type
));
expand_insn
(
get_multi_vector_move
(
type
,
vec_store_lanes_optab
),
2
,
ops
);
}
/* Routines to expand each internal function, indexed by function number.
Each routine has the prototype:
...
...
gcc/internal-fn.def
View file @
267d3070
...
...
@@ -37,6 +37,3 @@ along with GCC; see the file COPYING3. If not see
void expand_NAME (gimple stmt)
where STMT is the statement that performs the call. */
DEF_INTERNAL_FN (LOAD_LANES, ECF_CONST | ECF_LEAF)
DEF_INTERNAL_FN (STORE_LANES, ECF_CONST | ECF_LEAF)
gcc/optabs.h
View file @
267d3070
...
...
@@ -578,9 +578,6 @@ enum convert_optab_index
COI_satfract
,
COI_satfractuns
,
COI_vec_load_lanes
,
COI_vec_store_lanes
,
COI_MAX
};
...
...
@@ -601,8 +598,6 @@ enum convert_optab_index
#define fractuns_optab (&convert_optab_table[COI_fractuns])
#define satfract_optab (&convert_optab_table[COI_satfract])
#define satfractuns_optab (&convert_optab_table[COI_satfractuns])
#define vec_load_lanes_optab (&convert_optab_table[COI_vec_load_lanes])
#define vec_store_lanes_optab (&convert_optab_table[COI_vec_store_lanes])
/* Contains the optab used for each rtx code. */
extern
optab
code_to_optab
[
NUM_RTX_CODE
+
1
];
...
...
gcc/tree-vect-data-refs.c
View file @
267d3070
...
...
@@ -43,45 +43,6 @@ along with GCC; see the file COPYING3. If not see
#include "expr.h"
#include "optabs.h"
/* Return true if load- or store-lanes optab OPTAB is implemented for
COUNT vectors of type VECTYPE. NAME is the name of OPTAB. */
static
bool
vect_lanes_optab_supported_p
(
const
char
*
name
,
convert_optab
optab
,
tree
vectype
,
unsigned
HOST_WIDE_INT
count
)
{
enum
machine_mode
mode
,
array_mode
;
bool
limit_p
;
mode
=
TYPE_MODE
(
vectype
);
limit_p
=
!
targetm
.
array_mode_supported_p
(
mode
,
count
);
array_mode
=
mode_for_size
(
count
*
GET_MODE_BITSIZE
(
mode
),
MODE_INT
,
limit_p
);
if
(
array_mode
==
BLKmode
)
{
if
(
vect_print_dump_info
(
REPORT_DETAILS
))
fprintf
(
vect_dump
,
"no array mode for %s["
HOST_WIDE_INT_PRINT_DEC
"]"
,
GET_MODE_NAME
(
mode
),
count
);
return
false
;
}
if
(
convert_optab_handler
(
optab
,
array_mode
,
mode
)
==
CODE_FOR_nothing
)
{
if
(
vect_print_dump_info
(
REPORT_DETAILS
))
fprintf
(
vect_dump
,
"cannot use %s<%s><%s>"
,
name
,
GET_MODE_NAME
(
array_mode
),
GET_MODE_NAME
(
mode
));
return
false
;
}
if
(
vect_print_dump_info
(
REPORT_DETAILS
))
fprintf
(
vect_dump
,
"can use %s<%s><%s>"
,
name
,
GET_MODE_NAME
(
array_mode
),
GET_MODE_NAME
(
mode
));
return
true
;
}
/* Return the smallest scalar part of STMT.
This is used to determine the vectype of the stmt. We generally set the
vectype according to the type of the result (lhs). For stmts whose
...
...
@@ -3415,18 +3376,6 @@ vect_strided_store_supported (tree vectype, unsigned HOST_WIDE_INT count)
}
/* Return TRUE if vec_store_lanes is available for COUNT vectors of
type VECTYPE. */
bool
vect_store_lanes_supported
(
tree
vectype
,
unsigned
HOST_WIDE_INT
count
)
{
return
vect_lanes_optab_supported_p
(
"vec_store_lanes"
,
vec_store_lanes_optab
,
vectype
,
count
);
}
/* Function vect_permute_store_chain.
Given a chain of interleaved stores in DR_CHAIN of LENGTH that must be
...
...
@@ -3881,16 +3830,6 @@ vect_strided_load_supported (tree vectype, unsigned HOST_WIDE_INT count)
return
true
;
}
/* Return TRUE if vec_load_lanes is available for COUNT vectors of
type VECTYPE. */
bool
vect_load_lanes_supported
(
tree
vectype
,
unsigned
HOST_WIDE_INT
count
)
{
return
vect_lanes_optab_supported_p
(
"vec_load_lanes"
,
vec_load_lanes_optab
,
vectype
,
count
);
}
/* Function vect_permute_load_chain.
...
...
@@ -4038,28 +3977,19 @@ void
vect_transform_strided_load
(
gimple
stmt
,
VEC
(
tree
,
heap
)
*
dr_chain
,
int
size
,
gimple_stmt_iterator
*
gsi
)
{
stmt_vec_info
stmt_info
=
vinfo_for_stmt
(
stmt
);
gimple
first_stmt
=
DR_GROUP_FIRST_DR
(
stmt_info
);
gimple
next_stmt
,
new_stmt
;
VEC
(
tree
,
heap
)
*
result_chain
=
NULL
;
unsigned
int
i
,
gap_count
;
tree
tmp_data_ref
;
/* DR_CHAIN contains input data-refs that are a part of the interleaving.
RESULT_CHAIN is the output of vect_permute_load_chain, it contains permuted
vectors, that are ready for vector computation. */
result_chain
=
VEC_alloc
(
tree
,
heap
,
size
);
/* Permute. */
vect_permute_load_chain
(
dr_chain
,
size
,
stmt
,
gsi
,
&
result_chain
);
vect_record_strided_load_vectors
(
stmt
,
result_chain
);
VEC_free
(
tree
,
heap
,
result_chain
);
}
/* RESULT_CHAIN contains the output of a group of strided loads that were
generated as part of the vectorization of STMT. Assign the statement
for each vector to the associated scalar statement. */
void
vect_record_strided_load_vectors
(
gimple
stmt
,
VEC
(
tree
,
heap
)
*
result_chain
)
{
gimple
first_stmt
=
DR_GROUP_FIRST_DR
(
vinfo_for_stmt
(
stmt
));
gimple
next_stmt
,
new_stmt
;
unsigned
int
i
,
gap_count
;
tree
tmp_data_ref
;
/* Put a permuted data-ref in the VECTORIZED_STMT field.
Since we scan the chain starting from it's first node, their order
...
...
@@ -4121,6 +4051,8 @@ vect_record_strided_load_vectors (gimple stmt, VEC(tree,heap) *result_chain)
break
;
}
}
VEC_free
(
tree
,
heap
,
result_chain
);
}
/* Function vect_force_dr_alignment_p.
...
...
gcc/tree-vect-slp.c
View file @
267d3070
...
...
@@ -215,8 +215,7 @@ vect_get_and_check_slp_defs (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo,
vect_model_simple_cost
(
stmt_info
,
ncopies_for_cost
,
dt
,
slp_node
);
else
/* Store. */
vect_model_store_cost
(
stmt_info
,
ncopies_for_cost
,
false
,
dt
[
0
],
slp_node
);
vect_model_store_cost
(
stmt_info
,
ncopies_for_cost
,
dt
[
0
],
slp_node
);
}
else
...
...
@@ -580,7 +579,7 @@ vect_build_slp_tree (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo,
/* Analyze costs (for the first stmt in the group). */
vect_model_load_cost
(
vinfo_for_stmt
(
stmt
),
ncopies_for_cost
,
false
,
*
node
);
ncopies_for_cost
,
*
node
);
}
/* Store the place of this load in the interleaving chain. In
...
...
gcc/tree-vect-stmts.c
View file @
267d3070
...
...
@@ -42,82 +42,6 @@ along with GCC; see the file COPYING3. If not see
#include "langhooks.h"
/* Return a variable of type ELEM_TYPE[NELEMS]. */
static
tree
create_vector_array
(
tree
elem_type
,
unsigned
HOST_WIDE_INT
nelems
)
{
return
create_tmp_var
(
build_array_type_nelts
(
elem_type
,
nelems
),
"vect_array"
);
}
/* ARRAY is an array of vectors created by create_vector_array.
Return an SSA_NAME for the vector in index N. The reference
is part of the vectorization of STMT and the vector is associated
with scalar destination SCALAR_DEST. */
static
tree
read_vector_array
(
gimple
stmt
,
gimple_stmt_iterator
*
gsi
,
tree
scalar_dest
,
tree
array
,
unsigned
HOST_WIDE_INT
n
)
{
tree
vect_type
,
vect
,
vect_name
,
array_ref
;
gimple
new_stmt
;
gcc_assert
(
TREE_CODE
(
TREE_TYPE
(
array
))
==
ARRAY_TYPE
);
vect_type
=
TREE_TYPE
(
TREE_TYPE
(
array
));
vect
=
vect_create_destination_var
(
scalar_dest
,
vect_type
);
array_ref
=
build4
(
ARRAY_REF
,
vect_type
,
array
,
build_int_cst
(
size_type_node
,
n
),
NULL_TREE
,
NULL_TREE
);
new_stmt
=
gimple_build_assign
(
vect
,
array_ref
);
vect_name
=
make_ssa_name
(
vect
,
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
vect_name
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
mark_symbols_for_renaming
(
new_stmt
);
return
vect_name
;
}
/* ARRAY is an array of vectors created by create_vector_array.
Emit code to store SSA_NAME VECT in index N of the array.
The store is part of the vectorization of STMT. */
static
void
write_vector_array
(
gimple
stmt
,
gimple_stmt_iterator
*
gsi
,
tree
vect
,
tree
array
,
unsigned
HOST_WIDE_INT
n
)
{
tree
array_ref
;
gimple
new_stmt
;
array_ref
=
build4
(
ARRAY_REF
,
TREE_TYPE
(
vect
),
array
,
build_int_cst
(
size_type_node
,
n
),
NULL_TREE
,
NULL_TREE
);
new_stmt
=
gimple_build_assign
(
array_ref
,
vect
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
mark_symbols_for_renaming
(
new_stmt
);
}
/* PTR is a pointer to an array of type TYPE. Return a representation
of *PTR. The memory reference replaces those in FIRST_DR
(and its group). */
static
tree
create_array_ref
(
tree
type
,
tree
ptr
,
struct
data_reference
*
first_dr
)
{
struct
ptr_info_def
*
pi
;
tree
mem_ref
,
alias_ptr_type
;
alias_ptr_type
=
reference_alias_ptr_type
(
DR_REF
(
first_dr
));
mem_ref
=
build2
(
MEM_REF
,
type
,
ptr
,
build_int_cst
(
alias_ptr_type
,
0
));
/* Arrays have the same alignment as their type. */
pi
=
get_ptr_info
(
ptr
);
pi
->
align
=
TYPE_ALIGN_UNIT
(
type
);
pi
->
misalign
=
0
;
return
mem_ref
;
}
/* Utility functions used by vect_mark_stmts_to_be_vectorized. */
/* Function vect_mark_relevant.
...
...
@@ -724,8 +648,7 @@ vect_cost_strided_group_size (stmt_vec_info stmt_info)
void
vect_model_store_cost
(
stmt_vec_info
stmt_info
,
int
ncopies
,
bool
store_lanes_p
,
enum
vect_def_type
dt
,
slp_tree
slp_node
)
enum
vect_def_type
dt
,
slp_tree
slp_node
)
{
int
group_size
;
unsigned
int
inside_cost
=
0
,
outside_cost
=
0
;
...
...
@@ -762,11 +685,9 @@ vect_model_store_cost (stmt_vec_info stmt_info, int ncopies,
first_dr
=
STMT_VINFO_DATA_REF
(
stmt_info
);
}
/* We assume that the cost of a single store-lanes instruction is
equivalent to the cost of GROUP_SIZE separate stores. If a strided
access is instead being provided by a permute-and-store operation,
include the cost of the permutes. */
if
(
!
store_lanes_p
&&
group_size
>
1
)
/* Is this an access in a group of stores, which provide strided access?
If so, add in the cost of the permutes. */
if
(
group_size
>
1
)
{
/* Uses a high and low interleave operation for each needed permute. */
inside_cost
=
ncopies
*
exact_log2
(
group_size
)
*
group_size
...
...
@@ -842,8 +763,8 @@ vect_get_store_cost (struct data_reference *dr, int ncopies,
access scheme chosen. */
void
vect_model_load_cost
(
stmt_vec_info
stmt_info
,
int
ncopies
,
bool
load_lanes_p
,
slp_tree
slp_node
)
vect_model_load_cost
(
stmt_vec_info
stmt_info
,
int
ncopies
,
slp_tree
slp_node
)
{
int
group_size
;
gimple
first_stmt
;
...
...
@@ -868,11 +789,9 @@ vect_model_load_cost (stmt_vec_info stmt_info, int ncopies, bool load_lanes_p,
first_dr
=
dr
;
}
/* We assume that the cost of a single load-lanes instruction is
equivalent to the cost of GROUP_SIZE separate loads. If a strided
access is instead being provided by a load-and-permute operation,
include the cost of the permutes. */
if
(
!
load_lanes_p
&&
group_size
>
1
)
/* Is this an access in a group of loads providing strided access?
If so, add in the cost of the permutes. */
if
(
group_size
>
1
)
{
/* Uses an even and odd extract operations for each needed permute. */
inside_cost
=
ncopies
*
exact_log2
(
group_size
)
*
group_size
...
...
@@ -3410,7 +3329,6 @@ vectorizable_store (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
stmt_vec_info
stmt_info
=
vinfo_for_stmt
(
stmt
);
struct
data_reference
*
dr
=
STMT_VINFO_DATA_REF
(
stmt_info
),
*
first_dr
=
NULL
;
tree
vectype
=
STMT_VINFO_VECTYPE
(
stmt_info
);
tree
elem_type
;
loop_vec_info
loop_vinfo
=
STMT_VINFO_LOOP_VINFO
(
stmt_info
);
struct
loop
*
loop
=
NULL
;
enum
machine_mode
vec_mode
;
...
...
@@ -3426,7 +3344,6 @@ vectorizable_store (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
int
j
;
gimple
next_stmt
,
first_stmt
=
NULL
;
bool
strided_store
=
false
;
bool
store_lanes_p
=
false
;
unsigned
int
group_size
,
i
;
VEC
(
tree
,
heap
)
*
dr_chain
=
NULL
,
*
oprnds
=
NULL
,
*
result_chain
=
NULL
;
bool
inv_p
;
...
...
@@ -3434,7 +3351,6 @@ vectorizable_store (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
bool
slp
=
(
slp_node
!=
NULL
);
unsigned
int
vec_num
;
bb_vec_info
bb_vinfo
=
STMT_VINFO_BB_VINFO
(
stmt_info
);
tree
aggr_type
;
if
(
loop_vinfo
)
loop
=
LOOP_VINFO_LOOP
(
loop_vinfo
);
...
...
@@ -3488,8 +3404,7 @@ vectorizable_store (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
/* The scalar rhs type needs to be trivially convertible to the vector
component type. This should always be the case. */
elem_type
=
TREE_TYPE
(
vectype
);
if
(
!
useless_type_conversion_p
(
elem_type
,
TREE_TYPE
(
op
)))
if
(
!
useless_type_conversion_p
(
TREE_TYPE
(
vectype
),
TREE_TYPE
(
op
)))
{
if
(
vect_print_dump_info
(
REPORT_DETAILS
))
fprintf
(
vect_dump
,
"??? operands of different types"
);
...
...
@@ -3519,9 +3434,7 @@ vectorizable_store (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
if
(
!
slp
&&
!
PURE_SLP_STMT
(
stmt_info
))
{
group_size
=
DR_GROUP_SIZE
(
vinfo_for_stmt
(
first_stmt
));
if
(
vect_store_lanes_supported
(
vectype
,
group_size
))
store_lanes_p
=
true
;
else
if
(
!
vect_strided_store_supported
(
vectype
,
group_size
))
if
(
!
vect_strided_store_supported
(
vectype
,
group_size
))
return
false
;
}
...
...
@@ -3549,7 +3462,7 @@ vectorizable_store (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
if
(
!
vec_stmt
)
/* transformation not required. */
{
STMT_VINFO_TYPE
(
stmt_info
)
=
store_vec_info_type
;
vect_model_store_cost
(
stmt_info
,
ncopies
,
store_lanes_p
,
dt
,
NULL
);
vect_model_store_cost
(
stmt_info
,
ncopies
,
dt
,
NULL
);
return
true
;
}
...
...
@@ -3604,16 +3517,6 @@ vectorizable_store (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
alignment_support_scheme
=
vect_supportable_dr_alignment
(
first_dr
,
false
);
gcc_assert
(
alignment_support_scheme
);
/* Targets with store-lane instructions must not require explicit
realignment. */
gcc_assert
(
!
store_lanes_p
||
alignment_support_scheme
==
dr_aligned
||
alignment_support_scheme
==
dr_unaligned_supported
);
if
(
store_lanes_p
)
aggr_type
=
build_array_type_nelts
(
elem_type
,
vec_num
*
nunits
);
else
aggr_type
=
vectype
;
/* In case the vectorization factor (VF) is bigger than the number
of elements that we can fit in a vectype (nunits), we have to generate
...
...
@@ -3702,7 +3605,7 @@ vectorizable_store (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
/* We should have catched mismatched types earlier. */
gcc_assert
(
useless_type_conversion_p
(
vectype
,
TREE_TYPE
(
vec_oprnd
)));
dataref_ptr
=
vect_create_data_ref_ptr
(
first_stmt
,
aggr_
type
,
NULL
,
dataref_ptr
=
vect_create_data_ref_ptr
(
first_stmt
,
vec
type
,
NULL
,
NULL_TREE
,
&
dummy
,
gsi
,
&
ptr_incr
,
false
,
&
inv_p
);
gcc_assert
(
bb_vinfo
||
!
inv_p
);
...
...
@@ -3725,93 +3628,70 @@ vectorizable_store (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
VEC_replace
(
tree
,
dr_chain
,
i
,
vec_oprnd
);
VEC_replace
(
tree
,
oprnds
,
i
,
vec_oprnd
);
}
dataref_ptr
=
bump_vector_ptr
(
dataref_ptr
,
ptr_incr
,
gsi
,
stmt
,
TYPE_SIZE_UNIT
(
aggr_type
)
);
dataref_ptr
=
bump_vector_ptr
(
dataref_ptr
,
ptr_incr
,
gsi
,
stmt
,
NULL_TREE
);
}
if
(
store_lanes_p
)
new_stmt
=
NULL
;
if
(
strided_store
)
{
tree
vec_array
;
/* Combine all the vectors into an array. */
vec_array
=
create_vector_array
(
vectype
,
vec_num
);
for
(
i
=
0
;
i
<
vec_num
;
i
++
)
{
vec_oprnd
=
VEC_index
(
tree
,
dr_chain
,
i
);
write_vector_array
(
stmt
,
gsi
,
vec_oprnd
,
vec_array
,
i
);
}
/* Emit:
MEM_REF[...all elements...] = STORE_LANES (VEC_ARRAY). */
data_ref
=
create_array_ref
(
aggr_type
,
dataref_ptr
,
first_dr
);
new_stmt
=
gimple_build_call_internal
(
IFN_STORE_LANES
,
1
,
vec_array
);
gimple_call_set_lhs
(
new_stmt
,
data_ref
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
mark_symbols_for_renaming
(
new_stmt
);
result_chain
=
VEC_alloc
(
tree
,
heap
,
group_size
);
/* Permute. */
vect_permute_store_chain
(
dr_chain
,
group_size
,
stmt
,
gsi
,
&
result_chain
);
}
else
next_stmt
=
first_stmt
;
for
(
i
=
0
;
i
<
vec_num
;
i
++
)
{
new_stmt
=
NULL
;
if
(
strided_store
)
struct
ptr_info_def
*
pi
;
if
(
i
>
0
)
/* Bump the vector pointer. */
dataref_ptr
=
bump_vector_ptr
(
dataref_ptr
,
ptr_incr
,
gsi
,
stmt
,
NULL_TREE
);
if
(
slp
)
vec_oprnd
=
VEC_index
(
tree
,
vec_oprnds
,
i
);
else
if
(
strided_store
)
/* For strided stores vectorized defs are interleaved in
vect_permute_store_chain(). */
vec_oprnd
=
VEC_index
(
tree
,
result_chain
,
i
);
data_ref
=
build2
(
MEM_REF
,
TREE_TYPE
(
vec_oprnd
),
dataref_ptr
,
build_int_cst
(
reference_alias_ptr_type
(
DR_REF
(
first_dr
)),
0
));
pi
=
get_ptr_info
(
dataref_ptr
);
pi
->
align
=
TYPE_ALIGN_UNIT
(
vectype
);
if
(
aligned_access_p
(
first_dr
))
pi
->
misalign
=
0
;
else
if
(
DR_MISALIGNMENT
(
first_dr
)
==
-
1
)
{
result_chain
=
VEC_alloc
(
tree
,
heap
,
group_size
);
/* Permute. */
vect_permute_store_chain
(
dr_chain
,
group_size
,
stmt
,
gsi
,
&
result_chain
);
TREE_TYPE
(
data_ref
)
=
build_aligned_type
(
TREE_TYPE
(
data_ref
),
TYPE_ALIGN
(
TREE_TYPE
(
vectype
)));
pi
->
align
=
TYPE_ALIGN_UNIT
(
TREE_TYPE
(
vectype
));
pi
->
misalign
=
0
;
}
next_stmt
=
first_stmt
;
for
(
i
=
0
;
i
<
vec_num
;
i
++
)
else
{
struct
ptr_info_def
*
pi
;
if
(
i
>
0
)
/* Bump the vector pointer. */
dataref_ptr
=
bump_vector_ptr
(
dataref_ptr
,
ptr_incr
,
gsi
,
stmt
,
NULL_TREE
);
if
(
slp
)
vec_oprnd
=
VEC_index
(
tree
,
vec_oprnds
,
i
);
else
if
(
strided_store
)
/* For strided stores vectorized defs are interleaved in
vect_permute_store_chain(). */
vec_oprnd
=
VEC_index
(
tree
,
result_chain
,
i
);
data_ref
=
build2
(
MEM_REF
,
TREE_TYPE
(
vec_oprnd
),
dataref_ptr
,
build_int_cst
(
reference_alias_ptr_type
(
DR_REF
(
first_dr
)),
0
));
pi
=
get_ptr_info
(
dataref_ptr
);
pi
->
align
=
TYPE_ALIGN_UNIT
(
vectype
);
if
(
aligned_access_p
(
first_dr
))
pi
->
misalign
=
0
;
else
if
(
DR_MISALIGNMENT
(
first_dr
)
==
-
1
)
{
TREE_TYPE
(
data_ref
)
=
build_aligned_type
(
TREE_TYPE
(
data_ref
),
TYPE_ALIGN
(
elem_type
));
pi
->
align
=
TYPE_ALIGN_UNIT
(
elem_type
);
pi
->
misalign
=
0
;
}
else
{
TREE_TYPE
(
data_ref
)
=
build_aligned_type
(
TREE_TYPE
(
data_ref
),
TYPE_ALIGN
(
elem_type
));
pi
->
misalign
=
DR_MISALIGNMENT
(
first_dr
);
}
TREE_TYPE
(
data_ref
)
=
build_aligned_type
(
TREE_TYPE
(
data_ref
),
TYPE_ALIGN
(
TREE_TYPE
(
vectype
)));
pi
->
misalign
=
DR_MISALIGNMENT
(
first_dr
);
}
/* Arguments are ready. Create the new vector stmt. */
new_stmt
=
gimple_build_assign
(
data_ref
,
vec_oprnd
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
mark_symbols_for_renaming
(
new_stmt
);
/* Arguments are ready. Create the new vector stmt. */
new_stmt
=
gimple_build_assign
(
data_ref
,
vec_oprnd
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
mark_symbols_for_renaming
(
new_stmt
);
if
(
slp
)
continue
;
if
(
slp
)
continue
;
next_stmt
=
DR_GROUP_NEXT_DR
(
vinfo_for_stmt
(
next_stmt
));
if
(
!
next_stmt
)
break
;
}
next_stmt
=
DR_GROUP_NEXT_DR
(
vinfo_for_stmt
(
next_stmt
));
if
(
!
next_stmt
)
break
;
}
if
(
!
slp
)
{
...
...
@@ -3930,7 +3810,6 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
bool
nested_in_vect_loop
=
false
;
struct
data_reference
*
dr
=
STMT_VINFO_DATA_REF
(
stmt_info
),
*
first_dr
;
tree
vectype
=
STMT_VINFO_VECTYPE
(
stmt_info
);
tree
elem_type
;
tree
new_temp
;
enum
machine_mode
mode
;
gimple
new_stmt
=
NULL
;
...
...
@@ -3947,7 +3826,6 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
gimple
phi
=
NULL
;
VEC
(
tree
,
heap
)
*
dr_chain
=
NULL
;
bool
strided_load
=
false
;
bool
load_lanes_p
=
false
;
gimple
first_stmt
;
tree
scalar_type
;
bool
inv_p
;
...
...
@@ -3960,7 +3838,6 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
enum
tree_code
code
;
bb_vec_info
bb_vinfo
=
STMT_VINFO_BB_VINFO
(
stmt_info
);
int
vf
;
tree
aggr_type
;
if
(
loop_vinfo
)
{
...
...
@@ -4037,8 +3914,7 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
/* The vector component type needs to be trivially convertible to the
scalar lhs. This should always be the case. */
elem_type
=
TREE_TYPE
(
vectype
);
if
(
!
useless_type_conversion_p
(
TREE_TYPE
(
scalar_dest
),
elem_type
))
if
(
!
useless_type_conversion_p
(
TREE_TYPE
(
scalar_dest
),
TREE_TYPE
(
vectype
)))
{
if
(
vect_print_dump_info
(
REPORT_DETAILS
))
fprintf
(
vect_dump
,
"??? operands of different types"
);
...
...
@@ -4056,9 +3932,7 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
if
(
!
slp
&&
!
PURE_SLP_STMT
(
stmt_info
))
{
group_size
=
DR_GROUP_SIZE
(
vinfo_for_stmt
(
first_stmt
));
if
(
vect_load_lanes_supported
(
vectype
,
group_size
))
load_lanes_p
=
true
;
else
if
(
!
vect_strided_load_supported
(
vectype
,
group_size
))
if
(
!
vect_strided_load_supported
(
vectype
,
group_size
))
return
false
;
}
}
...
...
@@ -4085,7 +3959,7 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
if
(
!
vec_stmt
)
/* transformation not required. */
{
STMT_VINFO_TYPE
(
stmt_info
)
=
load_vec_info_type
;
vect_model_load_cost
(
stmt_info
,
ncopies
,
load_lanes_p
,
NULL
);
vect_model_load_cost
(
stmt_info
,
ncopies
,
NULL
);
return
true
;
}
...
...
@@ -4126,11 +4000,6 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
alignment_support_scheme
=
vect_supportable_dr_alignment
(
first_dr
,
false
);
gcc_assert
(
alignment_support_scheme
);
/* Targets with load-lane instructions must not require explicit
realignment. */
gcc_assert
(
!
load_lanes_p
||
alignment_support_scheme
==
dr_aligned
||
alignment_support_scheme
==
dr_unaligned_supported
);
/* In case the vectorization factor (VF) is bigger than the number
of elements that we can fit in a vectype (nunits), we have to generate
...
...
@@ -4262,250 +4131,208 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
if
(
negative
)
offset
=
size_int
(
-
TYPE_VECTOR_SUBPARTS
(
vectype
)
+
1
);
if
(
load_lanes_p
)
aggr_type
=
build_array_type_nelts
(
elem_type
,
vec_num
*
nunits
);
else
aggr_type
=
vectype
;
prev_stmt_info
=
NULL
;
for
(
j
=
0
;
j
<
ncopies
;
j
++
)
{
/* 1. Create the vector
or array
pointer update chain. */
/* 1. Create the vector pointer update chain. */
if
(
j
==
0
)
dataref_ptr
=
vect_create_data_ref_ptr
(
first_stmt
,
aggr_
type
,
at_loop
,
dataref_ptr
=
vect_create_data_ref_ptr
(
first_stmt
,
vec
type
,
at_loop
,
offset
,
&
dummy
,
gsi
,
&
ptr_incr
,
false
,
&
inv_p
);
else
dataref_ptr
=
bump_vector_ptr
(
dataref_ptr
,
ptr_incr
,
gsi
,
stmt
,
TYPE_SIZE_UNIT
(
aggr_type
)
);
dataref_ptr
=
bump_vector_ptr
(
dataref_ptr
,
ptr_incr
,
gsi
,
stmt
,
NULL_TREE
);
if
(
strided_load
||
slp_perm
)
dr_chain
=
VEC_alloc
(
tree
,
heap
,
vec_num
);
if
(
load_lanes_p
)
for
(
i
=
0
;
i
<
vec_num
;
i
++
)
{
tree
vec_array
;
vec_array
=
create_vector_array
(
vectype
,
vec_num
);
/* Emit:
VEC_ARRAY = LOAD_LANES (MEM_REF[...all elements...]). */
data_ref
=
create_array_ref
(
aggr_type
,
dataref_ptr
,
first_dr
);
new_stmt
=
gimple_build_call_internal
(
IFN_LOAD_LANES
,
1
,
data_ref
);
gimple_call_set_lhs
(
new_stmt
,
vec_array
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
mark_symbols_for_renaming
(
new_stmt
);
if
(
i
>
0
)
dataref_ptr
=
bump_vector_ptr
(
dataref_ptr
,
ptr_incr
,
gsi
,
stmt
,
NULL_TREE
);
/*
Extract each vector into an SSA_NAME
. */
for
(
i
=
0
;
i
<
vec_num
;
i
++
)
/*
2. Create the vector-load in the loop
. */
switch
(
alignment_support_scheme
)
{
new_temp
=
read_vector_array
(
stmt
,
gsi
,
scalar_dest
,
vec_array
,
i
);
VEC_quick_push
(
tree
,
dr_chain
,
new_temp
);
}
/* Record the mapping between SSA_NAMEs and statements. */
vect_record_strided_load_vectors
(
stmt
,
dr_chain
);
}
else
{
for
(
i
=
0
;
i
<
vec_num
;
i
++
)
{
if
(
i
>
0
)
dataref_ptr
=
bump_vector_ptr
(
dataref_ptr
,
ptr_incr
,
gsi
,
stmt
,
NULL_TREE
);
/* 2. Create the vector-load in the loop. */
switch
(
alignment_support_scheme
)
{
case
dr_aligned
:
case
dr_unaligned_supported
:
case
dr_aligned
:
case
dr_unaligned_supported
:
{
struct
ptr_info_def
*
pi
;
data_ref
=
build2
(
MEM_REF
,
vectype
,
dataref_ptr
,
build_int_cst
(
reference_alias_ptr_type
(
DR_REF
(
first_dr
)),
0
));
pi
=
get_ptr_info
(
dataref_ptr
);
pi
->
align
=
TYPE_ALIGN_UNIT
(
vectype
);
if
(
alignment_support_scheme
==
dr_aligned
)
{
struct
ptr_info_def
*
pi
;
data_ref
=
build2
(
MEM_REF
,
vectype
,
dataref_ptr
,
build_int_cst
(
reference_alias_ptr_type
(
DR_REF
(
first_dr
)),
0
));
pi
=
get_ptr_info
(
dataref_ptr
);
pi
->
align
=
TYPE_ALIGN_UNIT
(
vectype
);
if
(
alignment_support_scheme
==
dr_aligned
)
{
gcc_assert
(
aligned_access_p
(
first_dr
));
pi
->
misalign
=
0
;
}
else
if
(
DR_MISALIGNMENT
(
first_dr
)
==
-
1
)
{
TREE_TYPE
(
data_ref
)
=
build_aligned_type
(
TREE_TYPE
(
data_ref
),
TYPE_ALIGN
(
elem_type
));
pi
->
align
=
TYPE_ALIGN_UNIT
(
elem_type
);
pi
->
misalign
=
0
;
}
else
{
TREE_TYPE
(
data_ref
)
=
build_aligned_type
(
TREE_TYPE
(
data_ref
),
TYPE_ALIGN
(
elem_type
));
pi
->
misalign
=
DR_MISALIGNMENT
(
first_dr
);
}
break
;
gcc_assert
(
aligned_access_p
(
first_dr
));
pi
->
misalign
=
0
;
}
case
dr_explicit_realign
:
else
if
(
DR_MISALIGNMENT
(
first_dr
)
==
-
1
)
{
tree
ptr
,
bump
;
tree
vs_minus_1
;
vs_minus_1
=
size_int
(
TYPE_VECTOR_SUBPARTS
(
vectype
)
-
1
);
if
(
compute_in_loop
)
msq
=
vect_setup_realignment
(
first_stmt
,
gsi
,
&
realignment_token
,
dr_explicit_realign
,
dataref_ptr
,
NULL
);
new_stmt
=
gimple_build_assign_with_ops
(
BIT_AND_EXPR
,
NULL_TREE
,
dataref_ptr
,
build_int_cst
(
TREE_TYPE
(
dataref_ptr
),
-
(
HOST_WIDE_INT
)
TYPE_ALIGN_UNIT
(
vectype
)));
ptr
=
make_ssa_name
(
SSA_NAME_VAR
(
dataref_ptr
),
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
ptr
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
data_ref
=
build2
(
MEM_REF
,
vectype
,
ptr
,
build_int_cst
(
reference_alias_ptr_type
(
DR_REF
(
first_dr
)),
0
));
vec_dest
=
vect_create_destination_var
(
scalar_dest
,
vectype
);
new_stmt
=
gimple_build_assign
(
vec_dest
,
data_ref
);
new_temp
=
make_ssa_name
(
vec_dest
,
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
new_temp
);
gimple_set_vdef
(
new_stmt
,
gimple_vdef
(
stmt
));
gimple_set_vuse
(
new_stmt
,
gimple_vuse
(
stmt
));
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
msq
=
new_temp
;
bump
=
size_binop
(
MULT_EXPR
,
vs_minus_1
,
TYPE_SIZE_UNIT
(
scalar_type
));
ptr
=
bump_vector_ptr
(
dataref_ptr
,
NULL
,
gsi
,
stmt
,
bump
);
new_stmt
=
gimple_build_assign_with_ops
(
BIT_AND_EXPR
,
NULL_TREE
,
ptr
,
build_int_cst
(
TREE_TYPE
(
ptr
),
-
(
HOST_WIDE_INT
)
TYPE_ALIGN_UNIT
(
vectype
)));
ptr
=
make_ssa_name
(
SSA_NAME_VAR
(
dataref_ptr
),
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
ptr
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
data_ref
=
build2
(
MEM_REF
,
vectype
,
ptr
,
build_int_cst
(
reference_alias_ptr_type
(
DR_REF
(
first_dr
)),
0
));
break
;
TREE_TYPE
(
data_ref
)
=
build_aligned_type
(
TREE_TYPE
(
data_ref
),
TYPE_ALIGN
(
TREE_TYPE
(
vectype
)));
pi
->
align
=
TYPE_ALIGN_UNIT
(
TREE_TYPE
(
vectype
));
pi
->
misalign
=
0
;
}
case
dr_explicit_realign_optimized
:
new_stmt
=
gimple_build_assign_with_ops
(
BIT_AND_EXPR
,
NULL_TREE
,
dataref_ptr
,
build_int_cst
(
TREE_TYPE
(
dataref_ptr
),
-
(
HOST_WIDE_INT
)
TYPE_ALIGN_UNIT
(
vectype
)));
new_temp
=
make_ssa_name
(
SSA_NAME_VAR
(
dataref_ptr
),
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
new_temp
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
data_ref
=
build2
(
MEM_REF
,
vectype
,
new_temp
,
build_int_cst
(
reference_alias_ptr_type
(
DR_REF
(
first_dr
)),
0
));
break
;
default:
gcc_unreachable
();
}
else
{
TREE_TYPE
(
data_ref
)
=
build_aligned_type
(
TREE_TYPE
(
data_ref
),
TYPE_ALIGN
(
TREE_TYPE
(
vectype
)));
pi
->
misalign
=
DR_MISALIGNMENT
(
first_dr
);
}
break
;
}
case
dr_explicit_realign
:
{
tree
ptr
,
bump
;
tree
vs_minus_1
=
size_int
(
TYPE_VECTOR_SUBPARTS
(
vectype
)
-
1
);
if
(
compute_in_loop
)
msq
=
vect_setup_realignment
(
first_stmt
,
gsi
,
&
realignment_token
,
dr_explicit_realign
,
dataref_ptr
,
NULL
);
new_stmt
=
gimple_build_assign_with_ops
(
BIT_AND_EXPR
,
NULL_TREE
,
dataref_ptr
,
build_int_cst
(
TREE_TYPE
(
dataref_ptr
),
-
(
HOST_WIDE_INT
)
TYPE_ALIGN_UNIT
(
vectype
)));
ptr
=
make_ssa_name
(
SSA_NAME_VAR
(
dataref_ptr
),
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
ptr
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
data_ref
=
build2
(
MEM_REF
,
vectype
,
ptr
,
build_int_cst
(
reference_alias_ptr_type
(
DR_REF
(
first_dr
)),
0
));
vec_dest
=
vect_create_destination_var
(
scalar_dest
,
vectype
);
new_stmt
=
gimple_build_assign
(
vec_dest
,
data_ref
);
new_temp
=
make_ssa_name
(
vec_dest
,
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
new_temp
);
gimple_set_vdef
(
new_stmt
,
gimple_vdef
(
stmt
));
gimple_set_vuse
(
new_stmt
,
gimple_vuse
(
stmt
));
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
msq
=
new_temp
;
bump
=
size_binop
(
MULT_EXPR
,
vs_minus_1
,
TYPE_SIZE_UNIT
(
scalar_type
));
ptr
=
bump_vector_ptr
(
dataref_ptr
,
NULL
,
gsi
,
stmt
,
bump
);
new_stmt
=
gimple_build_assign_with_ops
(
BIT_AND_EXPR
,
NULL_TREE
,
ptr
,
build_int_cst
(
TREE_TYPE
(
ptr
),
-
(
HOST_WIDE_INT
)
TYPE_ALIGN_UNIT
(
vectype
)));
ptr
=
make_ssa_name
(
SSA_NAME_VAR
(
dataref_ptr
),
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
ptr
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
data_ref
=
build2
(
MEM_REF
,
vectype
,
ptr
,
build_int_cst
(
reference_alias_ptr_type
(
DR_REF
(
first_dr
)),
0
));
break
;
}
case
dr_explicit_realign_optimized
:
new_stmt
=
gimple_build_assign_with_ops
(
BIT_AND_EXPR
,
NULL_TREE
,
dataref_ptr
,
build_int_cst
(
TREE_TYPE
(
dataref_ptr
),
-
(
HOST_WIDE_INT
)
TYPE_ALIGN_UNIT
(
vectype
)));
new_temp
=
make_ssa_name
(
SSA_NAME_VAR
(
dataref_ptr
),
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
new_temp
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
data_ref
=
build2
(
MEM_REF
,
vectype
,
new_temp
,
build_int_cst
(
reference_alias_ptr_type
(
DR_REF
(
first_dr
)),
0
));
break
;
default:
gcc_unreachable
();
}
vec_dest
=
vect_create_destination_var
(
scalar_dest
,
vectype
);
new_stmt
=
gimple_build_assign
(
vec_dest
,
data_ref
);
new_temp
=
make_ssa_name
(
vec_dest
,
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
new_temp
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
mark_symbols_for_renaming
(
new_stmt
);
/* 3. Handle explicit realignment if necessary/supported. Create in
loop: vec_dest = realign_load (msq, lsq, realignment_token) */
if
(
alignment_support_scheme
==
dr_explicit_realign_optimized
||
alignment_support_scheme
==
dr_explicit_realign
)
{
lsq
=
gimple_assign_lhs
(
new_stmt
);
if
(
!
realignment_token
)
realignment_token
=
dataref_ptr
;
vec_dest
=
vect_create_destination_var
(
scalar_dest
,
vectype
);
new_stmt
=
gimple_build_assign
(
vec_dest
,
data_ref
);
new_stmt
=
gimple_build_assign_with_ops3
(
REALIGN_LOAD_EXPR
,
vec_dest
,
msq
,
lsq
,
realignment_token
);
new_temp
=
make_ssa_name
(
vec_dest
,
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
new_temp
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
mark_symbols_for_renaming
(
new_stmt
);
/* 3. Handle explicit realignment if necessary/supported.
Create in loop:
vec_dest = realign_load (msq, lsq, realignment_token) */
if
(
alignment_support_scheme
==
dr_explicit_realign_optimized
||
alignment_support_scheme
==
dr_explicit_realign
)
if
(
alignment_support_scheme
==
dr_explicit_realign_optimized
)
{
lsq
=
gimple_assign_lhs
(
new_stmt
);
if
(
!
realignment_token
)
realignment_token
=
dataref_ptr
;
vec_dest
=
vect_create_destination_var
(
scalar_dest
,
vectype
);
new_stmt
=
gimple_build_assign_with_ops3
(
REALIGN_LOAD_EXPR
,
vec_dest
,
msq
,
lsq
,
realignment_token
);
new_temp
=
make_ssa_name
(
vec_dest
,
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
new_temp
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
if
(
alignment_support_scheme
==
dr_explicit_realign_optimized
)
{
gcc_assert
(
phi
);
if
(
i
==
vec_num
-
1
&&
j
==
ncopies
-
1
)
add_phi_arg
(
phi
,
lsq
,
loop_latch_edge
(
containing_loop
),
UNKNOWN_LOCATION
);
msq
=
lsq
;
}
gcc_assert
(
phi
);
if
(
i
==
vec_num
-
1
&&
j
==
ncopies
-
1
)
add_phi_arg
(
phi
,
lsq
,
loop_latch_edge
(
containing_loop
),
UNKNOWN_LOCATION
);
msq
=
lsq
;
}
}
/* 4. Handle invariant-load. */
if
(
inv_p
&&
!
bb_vinfo
)
/* 4. Handle invariant-load. */
if
(
inv_p
&&
!
bb_vinfo
)
{
gcc_assert
(
!
strided_load
);
gcc_assert
(
nested_in_vect_loop_p
(
loop
,
stmt
));
if
(
j
==
0
)
{
gcc_assert
(
!
strided_load
);
gcc_assert
(
nested_in_vect_loop_p
(
loop
,
stmt
));
if
(
j
==
0
)
{
int
k
;
tree
t
=
NULL_TREE
;
tree
vec_inv
,
bitpos
,
bitsize
=
TYPE_SIZE
(
scalar_type
);
/* CHECKME: bitpos depends on endianess? */
bitpos
=
bitsize_zero_node
;
vec_inv
=
build3
(
BIT_FIELD_REF
,
scalar_type
,
new_temp
,
bitsize
,
bitpos
);
vec_dest
=
vect_create_destination_var
(
scalar_dest
,
NULL_TREE
);
new_stmt
=
gimple_build_assign
(
vec_dest
,
vec_inv
);
new_temp
=
make_ssa_name
(
vec_dest
,
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
new_temp
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
for
(
k
=
nunits
-
1
;
k
>=
0
;
--
k
)
t
=
tree_cons
(
NULL_TREE
,
new_temp
,
t
);
/* FIXME: use build_constructor directly. */
vec_inv
=
build_constructor_from_list
(
vectype
,
t
);
new_temp
=
vect_init_vector
(
stmt
,
vec_inv
,
vectype
,
gsi
);
new_stmt
=
SSA_NAME_DEF_STMT
(
new_temp
);
}
else
gcc_unreachable
();
/* FORNOW. */
}
int
k
;
tree
t
=
NULL_TREE
;
tree
vec_inv
,
bitpos
,
bitsize
=
TYPE_SIZE
(
scalar_type
);
/* CHECKME: bitpos depends on endianess? */
bitpos
=
bitsize_zero_node
;
vec_inv
=
build3
(
BIT_FIELD_REF
,
scalar_type
,
new_temp
,
bitsize
,
bitpos
);
vec_dest
=
vect_create_destination_var
(
scalar_dest
,
NULL_TREE
);
new_stmt
=
gimple_build_assign
(
vec_dest
,
vec_inv
);
new_temp
=
make_ssa_name
(
vec_dest
,
new_stmt
);
gimple_assign_set_lhs
(
new_stmt
,
new_temp
);
vect_finish_stmt_generation
(
stmt
,
new_stmt
,
gsi
);
if
(
negative
)
{
new_temp
=
reverse_vec_elements
(
new_temp
,
stmt
,
gsi
);
for
(
k
=
nunits
-
1
;
k
>=
0
;
--
k
)
t
=
tree_cons
(
NULL_TREE
,
new_temp
,
t
);
/* FIXME: use build_constructor directly. */
vec_inv
=
build_constructor_from_list
(
vectype
,
t
);
new_temp
=
vect_init_vector
(
stmt
,
vec_inv
,
vectype
,
gsi
);
new_stmt
=
SSA_NAME_DEF_STMT
(
new_temp
);
}
else
gcc_unreachable
();
/* FORNOW. */
}
/* Collect vector loads and later create their permutation in
vect_transform_strided_load (). */
if
(
strided_load
||
slp_perm
)
VEC_quick_push
(
tree
,
dr_chain
,
new_temp
);
/* Store vector loads in the corresponding SLP_NODE. */
if
(
slp
&&
!
slp_perm
)
VEC_quick_push
(
gimple
,
SLP_TREE_VEC_STMTS
(
slp_node
),
new_stmt
);
if
(
negative
)
{
new_temp
=
reverse_vec_elements
(
new_temp
,
stmt
,
gsi
);
new_stmt
=
SSA_NAME_DEF_STMT
(
new_temp
);
}
/* Collect vector loads and later create their permutation in
vect_transform_strided_load (). */
if
(
strided_load
||
slp_perm
)
VEC_quick_push
(
tree
,
dr_chain
,
new_temp
);
/* Store vector loads in the corresponding SLP_NODE. */
if
(
slp
&&
!
slp_perm
)
VEC_quick_push
(
gimple
,
SLP_TREE_VEC_STMTS
(
slp_node
),
new_stmt
);
}
if
(
slp
&&
!
slp_perm
)
...
...
@@ -4524,8 +4351,7 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
{
if
(
strided_load
)
{
if
(
!
load_lanes_p
)
vect_transform_strided_load
(
stmt
,
dr_chain
,
group_size
,
gsi
);
vect_transform_strided_load
(
stmt
,
dr_chain
,
group_size
,
gsi
);
*
vec_stmt
=
STMT_VINFO_VEC_STMT
(
stmt_info
);
}
else
...
...
gcc/tree-vectorizer.h
View file @
267d3070
...
...
@@ -788,9 +788,9 @@ extern void free_stmt_vec_info (gimple stmt);
extern
tree
vectorizable_function
(
gimple
,
tree
,
tree
);
extern
void
vect_model_simple_cost
(
stmt_vec_info
,
int
,
enum
vect_def_type
*
,
slp_tree
);
extern
void
vect_model_store_cost
(
stmt_vec_info
,
int
,
bool
,
enum
vect_def_type
,
slp_tree
);
extern
void
vect_model_load_cost
(
stmt_vec_info
,
int
,
bool
,
slp_tree
);
extern
void
vect_model_store_cost
(
stmt_vec_info
,
int
,
enum
vect_def_type
,
slp_tree
);
extern
void
vect_model_load_cost
(
stmt_vec_info
,
int
,
slp_tree
);
extern
void
vect_finish_stmt_generation
(
gimple
,
gimple
,
gimple_stmt_iterator
*
);
extern
bool
vect_mark_stmts_to_be_vectorized
(
loop_vec_info
);
...
...
@@ -829,9 +829,7 @@ extern tree vect_create_data_ref_ptr (gimple, tree, struct loop *, tree,
extern
tree
bump_vector_ptr
(
tree
,
gimple
,
gimple_stmt_iterator
*
,
gimple
,
tree
);
extern
tree
vect_create_destination_var
(
tree
,
tree
);
extern
bool
vect_strided_store_supported
(
tree
,
unsigned
HOST_WIDE_INT
);
extern
bool
vect_store_lanes_supported
(
tree
,
unsigned
HOST_WIDE_INT
);
extern
bool
vect_strided_load_supported
(
tree
,
unsigned
HOST_WIDE_INT
);
extern
bool
vect_load_lanes_supported
(
tree
,
unsigned
HOST_WIDE_INT
);
extern
void
vect_permute_store_chain
(
VEC
(
tree
,
heap
)
*
,
unsigned
int
,
gimple
,
gimple_stmt_iterator
*
,
VEC
(
tree
,
heap
)
**
);
extern
tree
vect_setup_realignment
(
gimple
,
gimple_stmt_iterator
*
,
tree
*
,
...
...
@@ -839,7 +837,6 @@ extern tree vect_setup_realignment (gimple, gimple_stmt_iterator *, tree *,
struct
loop
**
);
extern
void
vect_transform_strided_load
(
gimple
,
VEC
(
tree
,
heap
)
*
,
int
,
gimple_stmt_iterator
*
);
extern
void
vect_record_strided_load_vectors
(
gimple
,
VEC
(
tree
,
heap
)
*
);
extern
int
vect_get_place_in_interleaving_chain
(
gimple
,
gimple
);
extern
tree
vect_get_new_vect_var
(
tree
,
enum
vect_var_kind
,
const
char
*
);
extern
tree
vect_create_addr_base_for_vector_ref
(
gimple
,
gimple_seq
*
,
...
...
gcc/tree.c
View file @
267d3070
...
...
@@ -7340,15 +7340,6 @@ build_nonshared_array_type (tree elt_type, tree index_type)
return
build_array_type_1
(
elt_type
,
index_type
,
false
);
}
/* Return a representation of ELT_TYPE[NELTS], using indices of type
sizetype. */
tree
build_array_type_nelts
(
tree
elt_type
,
unsigned
HOST_WIDE_INT
nelts
)
{
return
build_array_type
(
elt_type
,
build_index_type
(
size_int
(
nelts
-
1
)));
}
/* Recursively examines the array elements of TYPE, until a non-array
element type is found. */
...
...
gcc/tree.h
View file @
267d3070
...
...
@@ -4247,7 +4247,6 @@ extern tree build_type_no_quals (tree);
extern
tree
build_index_type
(
tree
);
extern
tree
build_array_type
(
tree
,
tree
);
extern
tree
build_nonshared_array_type
(
tree
,
tree
);
extern
tree
build_array_type_nelts
(
tree
,
unsigned
HOST_WIDE_INT
);
extern
tree
build_function_type
(
tree
,
tree
);
extern
tree
build_function_type_list
(
tree
,
...);
extern
tree
build_function_type_skip_args
(
tree
,
bitmap
);
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment