Add support for masked load/store_lanes
Richard Sandiford
richard.sandiford@linaro.org
Wed Nov 8 16:46:00 GMT 2017
This patch adds support for vectorising groups of IFN_MASK_LOADs
and IFN_MASK_STOREs using conditional load/store-lanes instructions.
This requires new internal functions to represent the result
(IFN_MASK_{LOAD,STORE}_LANES), as well as associated optabs.
The normal IFN_{LOAD,STORE}_LANES functions are const operations
that logically just perform the permute: the load or store is
encoded as a MEM operand to the call statement. In contrast,
the IFN_MASK_{LOAD,STORE}_LANES functions use the same kind of
interface as IFN_MASK_{LOAD,STORE}, since the memory is only
conditionally accessed.
The AArch64 patterns were added as part of the main LD[234]/ST[234] patch.
Tested on aarch64-linux-gnu (both with and without SVE), x86_64-linux-gnu
and powerpc64le-linux-gnu. OK to install?
Thanks,
Richard
2017-11-08 Richard Sandiford <richard.sandiford@linaro.org>
Alan Hayward <alan.hayward@arm.com>
David Sherwood <david.sherwood@arm.com>
gcc/
* optabs.def (vec_mask_load_lanes_optab): New optab.
(vec_mask_store_lanes_optab): Likewise.
* internal-fn.def (MASK_LOAD_LANES): New internal function.
(MASK_STORE_LANES): Likewise.
* internal-fn.c (mask_load_lanes_direct): New macro.
(mask_store_lanes_direct): Likewise.
(expand_mask_load_optab_fn): Handle masked operations.
(expand_mask_load_lanes_optab_fn): New macro.
(expand_mask_store_optab_fn): Handle masked operations.
(expand_mask_store_lanes_optab_fn): New macro.
(direct_mask_load_lanes_optab_supported_p): Likewise.
(direct_mask_store_lanes_optab_supported_p): Likewise.
* tree-vectorizer.h (vect_store_lanes_supported): Take a masked_p
parameter.
(vect_load_lanes_supported): Likewise.
* tree-vect-data-refs.c (strip_conversion): New function.
(can_group_stmts_p): Likewise.
(vect_analyze_data_ref_accesses): Use it instead of checking
for a pair of assignments.
(vect_store_lanes_supported): Take a masked_p parameter.
(vect_load_lanes_supported): Likewise.
* tree-vect-loop.c (vect_analyze_loop_2): Update calls to
vect_store_lanes_supported and vect_load_lanes_supported.
* tree-vect-slp.c (vect_analyze_slp_instance): Likewise.
* tree-vect-stmts.c (replace_mask_load): New function, split
out from vectorizable_mask_load_store. Keep the group information
up-to-date.
(get_store_op): New function.
(get_group_load_store_type): Take a masked_p parameter. Don't
allow gaps for masked accesses. Use get_store_op. Update calls
to vect_store_lanes_supported and vect_load_lanes_supported.
(get_load_store_type): Take a masked_p parameter and update
call to get_group_load_store_type.
(init_stored_values, advance_stored_values): New functions,
split out from vectorizable_store.
(do_load_lanes, do_store_lanes): New functions.
(get_masked_group_alias_ptr_type): New function.
(vectorizable_mask_load_store): Update call to get_load_store_type.
Handle masked VMAT_LOAD_STORE_LANES. Update GROUP_STORE_COUNT
when vectorizing a group of stores and only vectorize when we
reach the last statement in the group. Vectorize the first
statement in a group of loads. Use an array aggregate type
rather than a vector type for load/store_lanes. Use
init_stored_values, advance_stored_values, do_load_lanes,
do_store_lanes, get_masked_group_alias_ptr_type and replace_mask_load.
(vectorizable_store): Update call to get_load_store_type.
Use init_stored_values, advance_stored_values and do_store_lanes.
(vectorizable_load): Update call to get_load_store_type.
Use do_load_lanes.
(vect_transform_stmt): Set grouped_store for grouped IFN_MASK_STOREs.
Only set is_store for the last element in the group.
gcc/testsuite/
* gcc.dg/vect/vect-ooo-group-1.c: New test.
* gcc.target/aarch64/sve_mask_struct_load_1.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_load_1_run.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_load_2.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_load_2_run.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_load_3.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_load_3_run.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_load_4.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_load_5.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_load_6.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_load_7.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_load_8.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_store_1.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_store_1_run.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_store_2.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_store_2_run.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_store_3.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_store_3_run.c: Likewise.
* gcc.target/aarch64/sve_mask_struct_store_4.c: Likewise.
Index: gcc/optabs.def
===================================================================
--- gcc/optabs.def 2017-11-08 15:05:55.697852337 +0000
+++ gcc/optabs.def 2017-11-08 16:35:04.763816035 +0000
@@ -80,6 +80,8 @@ OPTAB_CD(ssmsub_widen_optab, "ssmsub$b$a
OPTAB_CD(usmsub_widen_optab, "usmsub$a$b4")
OPTAB_CD(vec_load_lanes_optab, "vec_load_lanes$a$b")
OPTAB_CD(vec_store_lanes_optab, "vec_store_lanes$a$b")
+OPTAB_CD(vec_mask_load_lanes_optab, "vec_mask_load_lanes$a$b")
+OPTAB_CD(vec_mask_store_lanes_optab, "vec_mask_store_lanes$a$b")
OPTAB_CD(vcond_optab, "vcond$a$b")
OPTAB_CD(vcondu_optab, "vcondu$a$b")
OPTAB_CD(vcondeq_optab, "vcondeq$a$b")
Index: gcc/internal-fn.def
===================================================================
--- gcc/internal-fn.def 2017-11-01 08:07:13.340797708 +0000
+++ gcc/internal-fn.def 2017-11-08 16:35:04.763816035 +0000
@@ -45,9 +45,11 @@ along with GCC; see the file COPYING3.
- mask_load: currently just maskload
- load_lanes: currently just vec_load_lanes
+ - mask_load_lanes: currently just vec_mask_load_lanes
- mask_store: currently just maskstore
- store_lanes: currently just vec_store_lanes
+ - mask_store_lanes: currently just vec_mask_store_lanes
DEF_INTERNAL_FLT_FN is like DEF_INTERNAL_OPTAB_FN, but in addition,
the function implements the computational part of a built-in math
@@ -92,9 +94,13 @@ along with GCC; see the file COPYING3.
DEF_INTERNAL_OPTAB_FN (MASK_LOAD, ECF_PURE, maskload, mask_load)
DEF_INTERNAL_OPTAB_FN (LOAD_LANES, ECF_CONST, vec_load_lanes, load_lanes)
+DEF_INTERNAL_OPTAB_FN (MASK_LOAD_LANES, ECF_PURE,
+ vec_mask_load_lanes, mask_load_lanes)
DEF_INTERNAL_OPTAB_FN (MASK_STORE, 0, maskstore, mask_store)
DEF_INTERNAL_OPTAB_FN (STORE_LANES, ECF_CONST, vec_store_lanes, store_lanes)
+DEF_INTERNAL_OPTAB_FN (MASK_STORE_LANES, 0,
+ vec_mask_store_lanes, mask_store_lanes)
DEF_INTERNAL_OPTAB_FN (RSQRT, ECF_CONST, rsqrt, unary)
Index: gcc/internal-fn.c
===================================================================
--- gcc/internal-fn.c 2017-11-08 15:05:55.618852345 +0000
+++ gcc/internal-fn.c 2017-11-08 16:35:04.763816035 +0000
@@ -79,8 +79,10 @@ #define DEF_INTERNAL_FN(CODE, FLAGS, FNS
#define not_direct { -2, -2, false }
#define mask_load_direct { -1, 2, false }
#define load_lanes_direct { -1, -1, false }
+#define mask_load_lanes_direct { -1, -1, false }
#define mask_store_direct { 3, 2, false }
#define store_lanes_direct { 0, 0, false }
+#define mask_store_lanes_direct { 0, 0, false }
#define unary_direct { 0, 0, true }
#define binary_direct { 0, 0, true }
@@ -2277,7 +2279,7 @@ expand_LOOP_DIST_ALIAS (internal_fn, gca
gcc_unreachable ();
}
-/* Expand MASK_LOAD call STMT using optab OPTAB. */
+/* Expand MASK_LOAD{,_LANES} call STMT using optab OPTAB. */
static void
expand_mask_load_optab_fn (internal_fn, gcall *stmt, convert_optab optab)
@@ -2286,6 +2288,7 @@ expand_mask_load_optab_fn (internal_fn,
tree type, lhs, rhs, maskt, ptr;
rtx mem, target, mask;
unsigned align;
+ insn_code icode;
maskt = gimple_call_arg (stmt, 2);
lhs = gimple_call_lhs (stmt);
@@ -2298,6 +2301,12 @@ expand_mask_load_optab_fn (internal_fn,
type = build_aligned_type (type, align);
rhs = fold_build2 (MEM_REF, type, gimple_call_arg (stmt, 0), ptr);
+ if (optab == vec_mask_load_lanes_optab)
+ icode = get_multi_vector_move (type, optab);
+ else
+ icode = convert_optab_handler (optab, TYPE_MODE (type),
+ TYPE_MODE (TREE_TYPE (maskt)));
+
mem = expand_expr (rhs, NULL_RTX, VOIDmode, EXPAND_WRITE);
gcc_assert (MEM_P (mem));
mask = expand_normal (maskt);
@@ -2305,12 +2314,12 @@ expand_mask_load_optab_fn (internal_fn,
create_output_operand (&ops[0], target, TYPE_MODE (type));
create_fixed_operand (&ops[1], mem);
create_input_operand (&ops[2], mask, TYPE_MODE (TREE_TYPE (maskt)));
- expand_insn (convert_optab_handler (optab, TYPE_MODE (type),
- TYPE_MODE (TREE_TYPE (maskt))),
- 3, ops);
+ expand_insn (icode, 3, ops);
}
-/* Expand MASK_STORE call STMT using optab OPTAB. */
+#define expand_mask_load_lanes_optab_fn expand_mask_load_optab_fn
+
+/* Expand MASK_STORE{,_LANES} call STMT using optab OPTAB. */
static void
expand_mask_store_optab_fn (internal_fn, gcall *stmt, convert_optab optab)
@@ -2319,6 +2328,7 @@ expand_mask_store_optab_fn (internal_fn,
tree type, lhs, rhs, maskt, ptr;
rtx mem, reg, mask;
unsigned align;
+ insn_code icode;
maskt = gimple_call_arg (stmt, 2);
rhs = gimple_call_arg (stmt, 3);
@@ -2329,6 +2339,12 @@ expand_mask_store_optab_fn (internal_fn,
type = build_aligned_type (type, align);
lhs = fold_build2 (MEM_REF, type, gimple_call_arg (stmt, 0), ptr);
+ if (optab == vec_mask_store_lanes_optab)
+ icode = get_multi_vector_move (type, optab);
+ else
+ icode = convert_optab_handler (optab, TYPE_MODE (type),
+ TYPE_MODE (TREE_TYPE (maskt)));
+
mem = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE);
gcc_assert (MEM_P (mem));
mask = expand_normal (maskt);
@@ -2336,11 +2352,11 @@ expand_mask_store_optab_fn (internal_fn,
create_fixed_operand (&ops[0], mem);
create_input_operand (&ops[1], reg, TYPE_MODE (type));
create_input_operand (&ops[2], mask, TYPE_MODE (TREE_TYPE (maskt)));
- expand_insn (convert_optab_handler (optab, TYPE_MODE (type),
- TYPE_MODE (TREE_TYPE (maskt))),
- 3, ops);
+ expand_insn (icode, 3, ops);
}
+#define expand_mask_store_lanes_optab_fn expand_mask_store_optab_fn
+
static void
expand_ABNORMAL_DISPATCHER (internal_fn, gcall *)
{
@@ -2732,8 +2748,10 @@ #define direct_unary_optab_supported_p d
#define direct_binary_optab_supported_p direct_optab_supported_p
#define direct_mask_load_optab_supported_p direct_optab_supported_p
#define direct_load_lanes_optab_supported_p multi_vector_optab_supported_p
+#define direct_mask_load_lanes_optab_supported_p multi_vector_optab_supported_p
#define direct_mask_store_optab_supported_p direct_optab_supported_p
#define direct_store_lanes_optab_supported_p multi_vector_optab_supported_p
+#define direct_mask_store_lanes_optab_supported_p multi_vector_optab_supported_p
/* Return true if FN is supported for the types in TYPES when the
optimization type is OPT_TYPE. The types are those associated with
Index: gcc/tree-vectorizer.h
===================================================================
--- gcc/tree-vectorizer.h 2017-11-08 15:05:33.791822333 +0000
+++ gcc/tree-vectorizer.h 2017-11-08 16:35:04.771159765 +0000
@@ -1284,9 +1284,9 @@ extern tree bump_vector_ptr (tree, gimpl
tree);
extern tree vect_create_destination_var (tree, tree);
extern bool vect_grouped_store_supported (tree, unsigned HOST_WIDE_INT);
-extern bool vect_store_lanes_supported (tree, unsigned HOST_WIDE_INT);
+extern bool vect_store_lanes_supported (tree, unsigned HOST_WIDE_INT, bool);
extern bool vect_grouped_load_supported (tree, bool, unsigned HOST_WIDE_INT);
-extern bool vect_load_lanes_supported (tree, unsigned HOST_WIDE_INT);
+extern bool vect_load_lanes_supported (tree, unsigned HOST_WIDE_INT, bool);
extern void vect_permute_store_chain (vec<tree> ,unsigned int, gimple *,
gimple_stmt_iterator *, vec<tree> *);
extern tree vect_setup_realignment (gimple *, gimple_stmt_iterator *, tree *,
Index: gcc/tree-vect-data-refs.c
===================================================================
--- gcc/tree-vect-data-refs.c 2017-11-08 15:06:16.087850270 +0000
+++ gcc/tree-vect-data-refs.c 2017-11-08 16:35:04.768405866 +0000
@@ -2791,6 +2791,62 @@ dr_group_sort_cmp (const void *dra_, con
return cmp;
}
+/* If OP is the result of a conversion, return the unconverted value,
+ otherwise return null. */
+
+static tree
+strip_conversion (tree op)
+{
+ if (TREE_CODE (op) != SSA_NAME)
+ return NULL_TREE;
+ gimple *stmt = SSA_NAME_DEF_STMT (op);
+ if (!is_gimple_assign (stmt)
+ || !CONVERT_EXPR_CODE_P (gimple_assign_rhs_code (stmt)))
+ return NULL_TREE;
+ return gimple_assign_rhs1 (stmt);
+}
+
+/* Return true if vectorizable_* routines can handle statements STMT1
+ and STMT2 being in a single group. */
+
+static bool
+can_group_stmts_p (gimple *stmt1, gimple *stmt2)
+{
+ if (gimple_assign_single_p (stmt1))
+ return gimple_assign_single_p (stmt2);
+
+ if (is_gimple_call (stmt1) && gimple_call_internal_p (stmt1))
+ {
+ /* Check for two masked loads or two masked stores. */
+ if (!is_gimple_call (stmt2) || !gimple_call_internal_p (stmt2))
+ return false;
+ internal_fn ifn = gimple_call_internal_fn (stmt1);
+ if (ifn != IFN_MASK_LOAD && ifn != IFN_MASK_STORE)
+ return false;
+ if (ifn != gimple_call_internal_fn (stmt2))
+ return false;
+
+ /* Check that the masks are the same. Cope with casts of masks,
+ like those created by build_mask_conversion. */
+ tree mask1 = gimple_call_arg (stmt1, 2);
+ tree mask2 = gimple_call_arg (stmt2, 2);
+ if (!operand_equal_p (mask1, mask2, 0))
+ {
+ mask1 = strip_conversion (mask1);
+ if (!mask1)
+ return false;
+ mask2 = strip_conversion (mask2);
+ if (!mask2)
+ return false;
+ if (!operand_equal_p (mask1, mask2, 0))
+ return false;
+ }
+ return true;
+ }
+
+ return false;
+}
+
/* Function vect_analyze_data_ref_accesses.
Analyze the access pattern of all the data references in the loop.
@@ -2857,8 +2913,7 @@ vect_analyze_data_ref_accesses (vec_info
|| data_ref_compare_tree (DR_BASE_ADDRESS (dra),
DR_BASE_ADDRESS (drb)) != 0
|| data_ref_compare_tree (DR_OFFSET (dra), DR_OFFSET (drb)) != 0
- || !gimple_assign_single_p (DR_STMT (dra))
- || !gimple_assign_single_p (DR_STMT (drb)))
+ || !can_group_stmts_p (DR_STMT (dra), DR_STMT (drb)))
break;
/* Check that the data-refs have the same constant size. */
@@ -4662,15 +4717,21 @@ vect_grouped_store_supported (tree vecty
}
-/* Return TRUE if vec_store_lanes is available for COUNT vectors of
- type VECTYPE. */
+/* Return TRUE if vec_{mask_}store_lanes is available for COUNT vectors of
+ type VECTYPE. MASKED_P says whether the masked form is needed. */
bool
-vect_store_lanes_supported (tree vectype, unsigned HOST_WIDE_INT count)
+vect_store_lanes_supported (tree vectype, unsigned HOST_WIDE_INT count,
+ bool masked_p)
{
- return vect_lanes_optab_supported_p ("vec_store_lanes",
- vec_store_lanes_optab,
- vectype, count);
+ if (masked_p)
+ return vect_lanes_optab_supported_p ("vec_mask_store_lanes",
+ vec_mask_store_lanes_optab,
+ vectype, count);
+ else
+ return vect_lanes_optab_supported_p ("vec_store_lanes",
+ vec_store_lanes_optab,
+ vectype, count);
}
@@ -5238,15 +5299,21 @@ vect_grouped_load_supported (tree vectyp
return false;
}
-/* Return TRUE if vec_load_lanes is available for COUNT vectors of
- type VECTYPE. */
+/* Return TRUE if vec_{masked_}load_lanes is available for COUNT vectors of
+ type VECTYPE. MASKED_P says whether the masked form is needed. */
bool
-vect_load_lanes_supported (tree vectype, unsigned HOST_WIDE_INT count)
+vect_load_lanes_supported (tree vectype, unsigned HOST_WIDE_INT count,
+ bool masked_p)
{
- return vect_lanes_optab_supported_p ("vec_load_lanes",
- vec_load_lanes_optab,
- vectype, count);
+ if (masked_p)
+ return vect_lanes_optab_supported_p ("vec_mask_load_lanes",
+ vec_mask_load_lanes_optab,
+ vectype, count);
+ else
+ return vect_lanes_optab_supported_p ("vec_load_lanes",
+ vec_load_lanes_optab,
+ vectype, count);
}
/* Function vect_permute_load_chain.
Index: gcc/tree-vect-loop.c
===================================================================
--- gcc/tree-vect-loop.c 2017-11-08 15:05:36.349044117 +0000
+++ gcc/tree-vect-loop.c 2017-11-08 16:35:04.770241799 +0000
@@ -2247,7 +2247,7 @@ vect_analyze_loop_2 (loop_vec_info loop_
vinfo = vinfo_for_stmt (STMT_VINFO_GROUP_FIRST_ELEMENT (vinfo));
unsigned int size = STMT_VINFO_GROUP_SIZE (vinfo);
tree vectype = STMT_VINFO_VECTYPE (vinfo);
- if (! vect_store_lanes_supported (vectype, size)
+ if (! vect_store_lanes_supported (vectype, size, false)
&& ! vect_grouped_store_supported (vectype, size))
return false;
FOR_EACH_VEC_ELT (SLP_INSTANCE_LOADS (instance), j, node)
@@ -2257,7 +2257,7 @@ vect_analyze_loop_2 (loop_vec_info loop_
bool single_element_p = !STMT_VINFO_GROUP_NEXT_ELEMENT (vinfo);
size = STMT_VINFO_GROUP_SIZE (vinfo);
vectype = STMT_VINFO_VECTYPE (vinfo);
- if (! vect_load_lanes_supported (vectype, size)
+ if (! vect_load_lanes_supported (vectype, size, false)
&& ! vect_grouped_load_supported (vectype, single_element_p,
size))
return false;
Index: gcc/tree-vect-slp.c
===================================================================
--- gcc/tree-vect-slp.c 2017-11-08 15:05:34.296308263 +0000
+++ gcc/tree-vect-slp.c 2017-11-08 16:35:04.770241799 +0000
@@ -2175,7 +2175,7 @@ vect_analyze_slp_instance (vec_info *vin
instructions do not generate this SLP instance. */
if (is_a <loop_vec_info> (vinfo)
&& loads_permuted
- && dr && vect_store_lanes_supported (vectype, group_size))
+ && dr && vect_store_lanes_supported (vectype, group_size, false))
{
slp_tree load_node;
FOR_EACH_VEC_ELT (loads, i, load_node)
@@ -2188,7 +2188,7 @@ vect_analyze_slp_instance (vec_info *vin
if (STMT_VINFO_STRIDED_P (stmt_vinfo)
|| ! vect_load_lanes_supported
(STMT_VINFO_VECTYPE (stmt_vinfo),
- GROUP_SIZE (stmt_vinfo)))
+ GROUP_SIZE (stmt_vinfo), false))
break;
}
if (i == loads.length ())
Index: gcc/tree-vect-stmts.c
===================================================================
--- gcc/tree-vect-stmts.c 2017-11-08 15:05:36.350875282 +0000
+++ gcc/tree-vect-stmts.c 2017-11-08 16:35:04.771159765 +0000
@@ -1700,6 +1700,69 @@ vectorizable_internal_function (combined
static tree permute_vec_elements (tree, tree, tree, gimple *,
gimple_stmt_iterator *);
+/* Replace IFN_MASK_LOAD statement STMT with a dummy assignment, to ensure
+ that it won't be expanded even when there's no following DCE pass. */
+
+static void
+replace_mask_load (gimple *stmt, gimple_stmt_iterator *gsi)
+{
+ /* If this statement is part of a pattern created by the vectorizer,
+ get the original statement. */
+ stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
+ if (STMT_VINFO_RELATED_STMT (stmt_info))
+ {
+ stmt = STMT_VINFO_RELATED_STMT (stmt_info);
+ stmt_info = vinfo_for_stmt (stmt);
+ }
+
+ gcc_assert (gsi_stmt (*gsi) == stmt);
+ tree lhs = gimple_call_lhs (stmt);
+ tree zero = build_zero_cst (TREE_TYPE (lhs));
+ gimple *new_stmt = gimple_build_assign (lhs, zero);
+ set_vinfo_for_stmt (new_stmt, stmt_info);
+ set_vinfo_for_stmt (stmt, NULL);
+ STMT_VINFO_STMT (stmt_info) = new_stmt;
+
+ /* If STMT was the first statement in a group, redirect all
+ GROUP_FIRST_ELEMENT pointers to the new statement (which has the
+ same stmt_info as the old statement). */
+ if (GROUP_FIRST_ELEMENT (stmt_info) == stmt)
+ {
+ gimple *group_stmt = new_stmt;
+ do
+ {
+ GROUP_FIRST_ELEMENT (vinfo_for_stmt (group_stmt)) = new_stmt;
+ group_stmt = GROUP_NEXT_ELEMENT (vinfo_for_stmt (group_stmt));
+ }
+ while (group_stmt);
+ }
+ else if (GROUP_FIRST_ELEMENT (stmt_info))
+ {
+ /* Otherwise redirect the GROUP_NEXT_ELEMENT. It would be more
+ efficient if these pointers were to the stmt_vec_info rather
+ than the gimple statements themselves, but this is by no means
+ the only quadractic loop for groups. */
+ gimple *group_stmt = GROUP_FIRST_ELEMENT (stmt_info);
+ while (GROUP_NEXT_ELEMENT (vinfo_for_stmt (group_stmt)) != stmt)
+ group_stmt = GROUP_NEXT_ELEMENT (vinfo_for_stmt (group_stmt));
+ GROUP_NEXT_ELEMENT (vinfo_for_stmt (group_stmt)) = new_stmt;
+ }
+ gsi_replace (gsi, new_stmt, true);
+}
+
+/* STMT is either a masked or unconditional store. Return the value
+ being stored. */
+
+static tree
+get_store_op (gimple *stmt)
+{
+ if (gimple_assign_single_p (stmt))
+ return gimple_assign_rhs1 (stmt);
+ if (gimple_call_internal_p (stmt, IFN_MASK_STORE))
+ return gimple_call_arg (stmt, 3);
+ gcc_unreachable ();
+}
+
/* STMT is a non-strided load or store, meaning that it accesses
elements with a known constant step. Return -1 if that step
is negative, 0 if it is zero, and 1 if it is greater than zero. */
@@ -1744,7 +1807,7 @@ perm_mask_for_reverse (tree vectype)
static bool
get_group_load_store_type (gimple *stmt, tree vectype, bool slp,
- vec_load_store_type vls_type,
+ bool masked_p, vec_load_store_type vls_type,
vect_memory_access_type *memory_access_type)
{
stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
@@ -1765,7 +1828,10 @@ get_group_load_store_type (gimple *stmt,
/* True if we can cope with such overrun by peeling for gaps, so that
there is at least one final scalar iteration after the vector loop. */
- bool can_overrun_p = (vls_type == VLS_LOAD && loop_vinfo && !loop->inner);
+ bool can_overrun_p = (!masked_p
+ && vls_type == VLS_LOAD
+ && loop_vinfo
+ && !loop->inner);
/* There can only be a gap at the end of the group if the stride is
known at compile time. */
@@ -1828,6 +1894,7 @@ get_group_load_store_type (gimple *stmt,
and so we are guaranteed to access a non-gap element in the
same B-sized block. */
if (would_overrun_p
+ && !masked_p
&& gap < (vect_known_alignment_in_bytes (first_dr)
/ vect_get_scalar_dr_size (first_dr)))
would_overrun_p = false;
@@ -1838,8 +1905,8 @@ get_group_load_store_type (gimple *stmt,
{
/* First try using LOAD/STORE_LANES. */
if (vls_type == VLS_LOAD
- ? vect_load_lanes_supported (vectype, group_size)
- : vect_store_lanes_supported (vectype, group_size))
+ ? vect_load_lanes_supported (vectype, group_size, masked_p)
+ : vect_store_lanes_supported (vectype, group_size, masked_p))
{
*memory_access_type = VMAT_LOAD_STORE_LANES;
overrun_p = would_overrun_p;
@@ -1865,8 +1932,7 @@ get_group_load_store_type (gimple *stmt,
gimple *next_stmt = GROUP_NEXT_ELEMENT (stmt_info);
while (next_stmt)
{
- gcc_assert (gimple_assign_single_p (next_stmt));
- tree op = gimple_assign_rhs1 (next_stmt);
+ tree op = get_store_op (next_stmt);
gimple *def_stmt;
enum vect_def_type dt;
if (!vect_is_simple_use (op, vinfo, &def_stmt, &dt))
@@ -1950,11 +2016,12 @@ get_negative_load_store_type (gimple *st
or scatters, fill in GS_INFO accordingly.
SLP says whether we're performing SLP rather than loop vectorization.
+ MASKED_P is true if the statement is conditional on a vectorized mask.
VECTYPE is the vector type that the vectorized statements will use.
NCOPIES is the number of vector statements that will be needed. */
static bool
-get_load_store_type (gimple *stmt, tree vectype, bool slp,
+get_load_store_type (gimple *stmt, tree vectype, bool slp, bool masked_p,
vec_load_store_type vls_type, unsigned int ncopies,
vect_memory_access_type *memory_access_type,
gather_scatter_info *gs_info)
@@ -1982,7 +2049,7 @@ get_load_store_type (gimple *stmt, tree
}
else if (STMT_VINFO_GROUPED_ACCESS (stmt_info))
{
- if (!get_group_load_store_type (stmt, vectype, slp, vls_type,
+ if (!get_group_load_store_type (stmt, vectype, slp, masked_p, vls_type,
memory_access_type))
return false;
}
@@ -2031,6 +2098,174 @@ get_load_store_type (gimple *stmt, tree
return true;
}
+/* Set up the stored values for the first copy of a vectorized store.
+ GROUP_SIZE is the number of stores in the group (which is 1 for
+ ungrouped stores). FIRST_STMT is the first statement in the group.
+
+ On return, initialize OPERANDS to a new vector in which element I
+ is the value that the first copy of group member I should store.
+ The caller should free OPERANDS after use. */
+
+static void
+init_stored_values (unsigned int group_size, gimple *first_stmt,
+ vec<tree> *operands)
+{
+ operands->create (group_size);
+ gimple *next_stmt = first_stmt;
+ for (unsigned int i = 0; i < group_size; i++)
+ {
+ /* Since gaps are not supported for interleaved stores,
+ GROUP_SIZE is the exact number of stmts in the chain.
+ Therefore, NEXT_STMT can't be NULL_TREE. In case that
+ there is no interleaving, GROUP_SIZE is 1, and only one
+ iteration of the loop will be executed. */
+ gcc_assert (next_stmt);
+ tree op = get_store_op (next_stmt);
+ tree vec_op = vect_get_vec_def_for_operand (op, next_stmt);
+ operands->quick_push (vec_op);
+ next_stmt = GROUP_NEXT_ELEMENT (vinfo_for_stmt (next_stmt));
+ }
+}
+
+/* OPERANDS is a vector set up by init_stored_values. Update each element
+ for the next copy of each statement. GROUP_SIZE and FIRST_STMT are
+ as for init_stored_values. */
+
+static void
+advance_stored_values (unsigned int group_size, gimple *first_stmt,
+ vec<tree> operands)
+{
+ vec_info *vinfo = vinfo_for_stmt (first_stmt)->vinfo;
+ for (unsigned int i = 0; i < group_size; i++)
+ {
+ tree op = operands[i];
+ enum vect_def_type dt;
+ gimple *def_stmt;
+ vect_is_simple_use (op, vinfo, &def_stmt, &dt);
+ operands[i] = vect_get_vec_def_for_stmt_copy (dt, op);
+ }
+}
+
+/* Emit one copy of a vectorized LOAD_LANES for STMT. GROUP_SIZE is
+ the number of vectors being loaded and VECTYPE is the type of each
+ vector. AGGR_TYPE is the type that should be used to refer to the
+ memory source (which contains the same number of elements as
+ GROUP_SIZE copies of VECTYPE, but in a different order).
+ DATAREF_PTR points to the first element that should be loaded.
+ ALIAS_PTR_TYPE is the type of the accessed elements for aliasing
+ purposes. MASK, if nonnull, is a mask in which element I is true
+ if element I of each destination vector should be loaded. */
+
+static void
+do_load_lanes (gimple *stmt, gimple_stmt_iterator *gsi,
+ unsigned int group_size, tree vectype, tree aggr_type,
+ tree dataref_ptr, tree alias_ptr_type, tree mask)
+{
+ tree scalar_dest = gimple_get_lhs (stmt);
+ tree vec_array = create_vector_array (vectype, group_size);
+
+ gcall *new_stmt;
+ if (mask)
+ {
+ /* Emit: VEC_ARRAY = MASK_LOAD_LANES (DATAREF_PTR, ALIAS_PTR, MASK). */
+ tree alias_ptr = build_int_cst (alias_ptr_type,
+ TYPE_ALIGN_UNIT (TREE_TYPE (vectype)));
+ new_stmt = gimple_build_call_internal (IFN_MASK_LOAD_LANES, 3,
+ dataref_ptr, alias_ptr, mask);
+ }
+ else
+ {
+ /* Emit: VEC_ARRAY = LOAD_LANES (MEM_REF[...all elements...]). */
+ tree data_ref = create_array_ref (aggr_type, dataref_ptr,
+ alias_ptr_type);
+ new_stmt = gimple_build_call_internal (IFN_LOAD_LANES, 1, data_ref);
+ }
+ gimple_call_set_lhs (new_stmt, vec_array);
+ gimple_call_set_nothrow (new_stmt, true);
+ vect_finish_stmt_generation (stmt, new_stmt, gsi);
+
+ /* Extract each vector into an SSA_NAME. */
+ auto_vec<tree, 16> dr_chain;
+ dr_chain.reserve (group_size);
+ for (unsigned int i = 0; i < group_size; i++)
+ {
+ tree new_temp = read_vector_array (stmt, gsi, scalar_dest, vec_array, i);
+ dr_chain.quick_push (new_temp);
+ }
+
+ /* Record the mapping between SSA_NAMEs and statements. */
+ vect_record_grouped_load_vectors (stmt, dr_chain);
+}
+
+/* Emit one copy of a vectorized STORE_LANES for STMT. GROUP_SIZE is
+ the number of vectors being stored and OPERANDS[I] is the value
+ that group member I should store. AGGR_TYPE is the type that should
+ be used to refer to the memory destination (which contains the same
+ number of elements as the source vectors, but in a different order).
+ DATAREF_PTR points to the first store location. ALIAS_PTR_TYPE is
+ the type of the accessed elements for aliasing purposes. MASK,
+ if nonnull, is a mask in which element I is true if element I of
+ each source vector should be stored. */
+
+static gimple *
+do_store_lanes (gimple *stmt, gimple_stmt_iterator *gsi,
+ unsigned int group_size, tree aggr_type, tree dataref_ptr,
+ tree alias_ptr_type, vec<tree> operands, tree mask)
+{
+ /* Combine all the vectors into an array. */
+ tree vectype = TREE_TYPE (operands[0]);
+ tree vec_array = create_vector_array (vectype, group_size);
+ for (unsigned int i = 0; i < group_size; i++)
+ write_vector_array (stmt, gsi, operands[i], vec_array, i);
+
+ gcall *new_stmt;
+ if (mask)
+ {
+ /* Emit: MASK_STORE_LANES (DATAREF_PTR, ALIAS_PTR, MASK, VEC_ARRAY). */
+ tree alias_ptr = build_int_cst (alias_ptr_type,
+ TYPE_ALIGN_UNIT (TREE_TYPE (vectype)));
+ new_stmt = gimple_build_call_internal (IFN_MASK_STORE_LANES, 4,
+ dataref_ptr, alias_ptr,
+ mask, vec_array);
+ }
+ else
+ {
+ /* Emit: MEM_REF[...all elements...] = STORE_LANES (VEC_ARRAY). */
+ tree data_ref = create_array_ref (aggr_type, dataref_ptr, alias_ptr_type);
+ new_stmt = gimple_build_call_internal (IFN_STORE_LANES, 1, vec_array);
+ gimple_call_set_lhs (new_stmt, data_ref);
+ }
+ gimple_call_set_nothrow (new_stmt, true);
+ vect_finish_stmt_generation (stmt, new_stmt, gsi);
+ return new_stmt;
+}
+
+/* Return the alias pointer type for the group of masked loads or
+ stores starting at FIRST_STMT. */
+
+static tree
+get_masked_group_alias_ptr_type (gimple *first_stmt)
+{
+ tree type, next_type;
+ gimple *next_stmt;
+
+ type = TREE_TYPE (gimple_call_arg (first_stmt, 1));
+ next_stmt = GROUP_NEXT_ELEMENT (vinfo_for_stmt (first_stmt));
+ while (next_stmt)
+ {
+ next_type = TREE_TYPE (gimple_call_arg (next_stmt, 1));
+ if (get_alias_set (type) != get_alias_set (next_type))
+ {
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_NOTE, vect_location,
+ "conflicting alias set types.\n");
+ return ptr_type_node;
+ }
+ next_stmt = GROUP_NEXT_ELEMENT (vinfo_for_stmt (next_stmt));
+ }
+ return type;
+}
+
/* Function vectorizable_mask_load_store.
Check if STMT performs a conditional load or store that can be vectorized.
@@ -2053,6 +2288,7 @@ vectorizable_mask_load_store (gimple *st
tree rhs_vectype = NULL_TREE;
tree mask_vectype;
tree elem_type;
+ tree aggr_type;
gimple *new_stmt;
tree dummy;
tree dataref_ptr = NULL_TREE;
@@ -2066,6 +2302,8 @@ vectorizable_mask_load_store (gimple *st
tree mask;
gimple *def_stmt;
enum vect_def_type dt;
+ gimple *first_stmt = stmt;
+ unsigned int group_size = 1;
if (slp_node != NULL)
return false;
@@ -2127,7 +2365,7 @@ vectorizable_mask_load_store (gimple *st
vls_type = VLS_LOAD;
vect_memory_access_type memory_access_type;
- if (!get_load_store_type (stmt, vectype, false, vls_type, ncopies,
+ if (!get_load_store_type (stmt, vectype, false, true, vls_type, ncopies,
&memory_access_type, &gs_info))
return false;
@@ -2144,7 +2382,18 @@ vectorizable_mask_load_store (gimple *st
return false;
}
}
- else if (memory_access_type != VMAT_CONTIGUOUS)
+ else if (rhs_vectype
+ && !useless_type_conversion_p (vectype, rhs_vectype))
+ return false;
+ else if (memory_access_type == VMAT_CONTIGUOUS)
+ {
+ if (!VECTOR_MODE_P (TYPE_MODE (vectype))
+ || !can_vec_mask_load_store_p (TYPE_MODE (vectype),
+ TYPE_MODE (mask_vectype),
+ vls_type == VLS_LOAD))
+ return false;
+ }
+ else if (memory_access_type != VMAT_LOAD_STORE_LANES)
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -2152,13 +2401,6 @@ vectorizable_mask_load_store (gimple *st
vls_type == VLS_LOAD ? "load" : "store");
return false;
}
- else if (!VECTOR_MODE_P (TYPE_MODE (vectype))
- || !can_vec_mask_load_store_p (TYPE_MODE (vectype),
- TYPE_MODE (mask_vectype),
- vls_type == VLS_LOAD)
- || (rhs_vectype
- && !useless_type_conversion_p (vectype, rhs_vectype)))
- return false;
if (!vec_stmt) /* transformation not required. */
{
@@ -2176,6 +2418,14 @@ vectorizable_mask_load_store (gimple *st
/* Transform. */
+ if (STMT_VINFO_GROUPED_ACCESS (stmt_info))
+ {
+ first_stmt = GROUP_FIRST_ELEMENT (stmt_info);
+ group_size = GROUP_SIZE (vinfo_for_stmt (first_stmt));
+ if (vls_type != VLS_LOAD)
+ GROUP_STORE_COUNT (vinfo_for_stmt (first_stmt))++;
+ }
+
if (memory_access_type == VMAT_GATHER_SCATTER)
{
tree vec_oprnd0 = NULL_TREE, op;
@@ -2343,23 +2593,28 @@ vectorizable_mask_load_store (gimple *st
prev_stmt_info = vinfo_for_stmt (new_stmt);
}
- /* Ensure that even with -fno-tree-dce the scalar MASK_LOAD is removed
- from the IL. */
- if (STMT_VINFO_RELATED_STMT (stmt_info))
- {
- stmt = STMT_VINFO_RELATED_STMT (stmt_info);
- stmt_info = vinfo_for_stmt (stmt);
- }
- tree lhs = gimple_call_lhs (stmt);
- new_stmt = gimple_build_assign (lhs, build_zero_cst (TREE_TYPE (lhs)));
- set_vinfo_for_stmt (new_stmt, stmt_info);
- set_vinfo_for_stmt (stmt, NULL);
- STMT_VINFO_STMT (stmt_info) = new_stmt;
- gsi_replace (gsi, new_stmt, true);
+ replace_mask_load (stmt, gsi);
return true;
}
- else if (vls_type != VLS_LOAD)
+
+ if (memory_access_type == VMAT_LOAD_STORE_LANES)
+ aggr_type = build_array_type_nelts (elem_type, group_size * nunits);
+ else
+ aggr_type = vectype;
+
+ if (vls_type != VLS_LOAD)
{
+ /* Vectorize the whole group when we reach the final statement.
+ Replace all other statements with an empty sequence. */
+ if (STMT_VINFO_GROUPED_ACCESS (stmt_info)
+ && (GROUP_STORE_COUNT (vinfo_for_stmt (first_stmt))
+ < GROUP_SIZE (vinfo_for_stmt (first_stmt))))
+ {
+ *vec_stmt = NULL;
+ return true;
+ }
+
+ auto_vec<tree, 16> operands;
tree vec_rhs = NULL_TREE, vec_mask = NULL_TREE;
prev_stmt_info = NULL;
LOOP_VINFO_HAS_MASK_STORE (loop_vinfo) = true;
@@ -2369,48 +2624,62 @@ vectorizable_mask_load_store (gimple *st
if (i == 0)
{
- tree rhs = gimple_call_arg (stmt, 3);
- vec_rhs = vect_get_vec_def_for_operand (rhs, stmt);
+ init_stored_values (group_size, first_stmt, &operands);
+ vec_rhs = operands[0];
vec_mask = vect_get_vec_def_for_operand (mask, stmt,
mask_vectype);
- /* We should have catched mismatched types earlier. */
+ /* We should have caught mismatched types earlier. */
gcc_assert (useless_type_conversion_p (vectype,
TREE_TYPE (vec_rhs)));
- dataref_ptr = vect_create_data_ref_ptr (stmt, vectype, NULL,
- NULL_TREE, &dummy, gsi,
- &ptr_incr, false, &inv_p);
+ dataref_ptr = vect_create_data_ref_ptr (first_stmt, aggr_type,
+ NULL, NULL_TREE, &dummy,
+ gsi, &ptr_incr, false,
+ &inv_p);
gcc_assert (!inv_p);
}
else
{
- vect_is_simple_use (vec_rhs, loop_vinfo, &def_stmt, &dt);
- vec_rhs = vect_get_vec_def_for_stmt_copy (dt, vec_rhs);
+ advance_stored_values (group_size, first_stmt, operands);
+ vec_rhs = operands[0];
vect_is_simple_use (vec_mask, loop_vinfo, &def_stmt, &dt);
vec_mask = vect_get_vec_def_for_stmt_copy (dt, vec_mask);
- dataref_ptr = bump_vector_ptr (dataref_ptr, ptr_incr, gsi, stmt,
- TYPE_SIZE_UNIT (vectype));
+ dataref_ptr = bump_vector_ptr (dataref_ptr, ptr_incr,
+ gsi, first_stmt,
+ TYPE_SIZE_UNIT (aggr_type));
}
- align = DR_TARGET_ALIGNMENT (dr);
- if (aligned_access_p (dr))
- misalign = 0;
- else if (DR_MISALIGNMENT (dr) == -1)
+ if (memory_access_type == VMAT_LOAD_STORE_LANES)
{
- align = TYPE_ALIGN_UNIT (elem_type);
- misalign = 0;
+ tree ref_type = get_masked_group_alias_ptr_type (first_stmt);
+ new_stmt = do_store_lanes (stmt, gsi, group_size, aggr_type,
+ dataref_ptr, ref_type, operands,
+ vec_mask);
}
else
- misalign = DR_MISALIGNMENT (dr);
- set_ptr_info_alignment (get_ptr_info (dataref_ptr), align,
- misalign);
- tree ptr = build_int_cst (TREE_TYPE (gimple_call_arg (stmt, 1)),
- misalign ? least_bit_hwi (misalign) : align);
- gcall *call
- = gimple_build_call_internal (IFN_MASK_STORE, 4, dataref_ptr,
- ptr, vec_mask, vec_rhs);
- gimple_call_set_nothrow (call, true);
- new_stmt = call;
- vect_finish_stmt_generation (stmt, new_stmt, gsi);
+ {
+ align = DR_TARGET_ALIGNMENT (dr);
+ if (aligned_access_p (dr))
+ misalign = 0;
+ else if (DR_MISALIGNMENT (dr) == -1)
+ {
+ align = TYPE_ALIGN_UNIT (elem_type);
+ misalign = 0;
+ }
+ else
+ misalign = DR_MISALIGNMENT (dr);
+ set_ptr_info_alignment (get_ptr_info (dataref_ptr), align,
+ misalign);
+ tree ptr = build_int_cst (TREE_TYPE (gimple_call_arg (stmt, 1)),
+ misalign
+ ? least_bit_hwi (misalign)
+ : align);
+ gcall *call
+ = gimple_build_call_internal (IFN_MASK_STORE, 4, dataref_ptr,
+ ptr, vec_mask, vec_rhs);
+ gimple_call_set_nothrow (call, true);
+ new_stmt = call;
+ vect_finish_stmt_generation (stmt, new_stmt, gsi);
+ }
if (i == 0)
STMT_VINFO_VEC_STMT (stmt_info) = *vec_stmt = new_stmt;
else
@@ -2420,73 +2689,88 @@ vectorizable_mask_load_store (gimple *st
}
else
{
+ /* Vectorize the whole group when we reach the first statement.
+ For later statements we just need to return the cached
+ replacement. */
+ if (group_size > 1
+ && STMT_VINFO_VEC_STMT (vinfo_for_stmt (first_stmt)))
+ {
+ *vec_stmt = STMT_VINFO_VEC_STMT (stmt_info);
+ replace_mask_load (stmt, gsi);
+ return true;
+ }
+
tree vec_mask = NULL_TREE;
prev_stmt_info = NULL;
- vec_dest = vect_create_destination_var (gimple_call_lhs (stmt), vectype);
+ if (memory_access_type == VMAT_LOAD_STORE_LANES)
+ vec_dest = NULL_TREE;
+ else
+ vec_dest = vect_create_destination_var (gimple_call_lhs (stmt),
+ vectype);
for (i = 0; i < ncopies; i++)
{
unsigned align, misalign;
if (i == 0)
{
+ gcc_assert (mask == gimple_call_arg (first_stmt, 2));
vec_mask = vect_get_vec_def_for_operand (mask, stmt,
mask_vectype);
- dataref_ptr = vect_create_data_ref_ptr (stmt, vectype, NULL,
- NULL_TREE, &dummy, gsi,
- &ptr_incr, false, &inv_p);
+ dataref_ptr = vect_create_data_ref_ptr (first_stmt, aggr_type,
+ NULL, NULL_TREE, &dummy,
+ gsi, &ptr_incr, false,
+ &inv_p);
gcc_assert (!inv_p);
}
else
{
vect_is_simple_use (vec_mask, loop_vinfo, &def_stmt, &dt);
vec_mask = vect_get_vec_def_for_stmt_copy (dt, vec_mask);
- dataref_ptr = bump_vector_ptr (dataref_ptr, ptr_incr, gsi, stmt,
- TYPE_SIZE_UNIT (vectype));
+ dataref_ptr = bump_vector_ptr (dataref_ptr, ptr_incr,
+ gsi, first_stmt,
+ TYPE_SIZE_UNIT (aggr_type));
}
- align = DR_TARGET_ALIGNMENT (dr);
- if (aligned_access_p (dr))
- misalign = 0;
- else if (DR_MISALIGNMENT (dr) == -1)
+ if (memory_access_type == VMAT_LOAD_STORE_LANES)
{
- align = TYPE_ALIGN_UNIT (elem_type);
- misalign = 0;
+ tree ref_type = get_masked_group_alias_ptr_type (first_stmt);
+ do_load_lanes (stmt, gsi, group_size, vectype,
+ aggr_type, dataref_ptr, ref_type, vec_mask);
+ *vec_stmt = STMT_VINFO_VEC_STMT (stmt_info);
}
else
- misalign = DR_MISALIGNMENT (dr);
- set_ptr_info_alignment (get_ptr_info (dataref_ptr), align,
- misalign);
- tree ptr = build_int_cst (TREE_TYPE (gimple_call_arg (stmt, 1)),
- misalign ? least_bit_hwi (misalign) : align);
- gcall *call
- = gimple_build_call_internal (IFN_MASK_LOAD, 3, dataref_ptr,
- ptr, vec_mask);
- gimple_call_set_lhs (call, make_ssa_name (vec_dest));
- gimple_call_set_nothrow (call, true);
- vect_finish_stmt_generation (stmt, call, gsi);
- if (i == 0)
- STMT_VINFO_VEC_STMT (stmt_info) = *vec_stmt = call;
- else
- STMT_VINFO_RELATED_STMT (prev_stmt_info) = call;
- prev_stmt_info = vinfo_for_stmt (call);
+ {
+ align = DR_TARGET_ALIGNMENT (dr);
+ if (aligned_access_p (dr))
+ misalign = 0;
+ else if (DR_MISALIGNMENT (dr) == -1)
+ {
+ align = TYPE_ALIGN_UNIT (elem_type);
+ misalign = 0;
+ }
+ else
+ misalign = DR_MISALIGNMENT (dr);
+ set_ptr_info_alignment (get_ptr_info (dataref_ptr), align,
+ misalign);
+ tree ptr = build_int_cst (TREE_TYPE (gimple_call_arg (stmt, 1)),
+ misalign
+ ? least_bit_hwi (misalign)
+ : align);
+ gcall *call
+ = gimple_build_call_internal (IFN_MASK_LOAD, 3, dataref_ptr,
+ ptr, vec_mask);
+ gimple_call_set_lhs (call, make_ssa_name (vec_dest));
+ gimple_call_set_nothrow (call, true);
+ vect_finish_stmt_generation (stmt, call, gsi);
+ if (i == 0)
+ STMT_VINFO_VEC_STMT (stmt_info) = *vec_stmt = call;
+ else
+ STMT_VINFO_RELATED_STMT (prev_stmt_info) = call;
+ prev_stmt_info = vinfo_for_stmt (call);
+ }
}
- }
- if (vls_type == VLS_LOAD)
- {
- /* Ensure that even with -fno-tree-dce the scalar MASK_LOAD is removed
- from the IL. */
- if (STMT_VINFO_RELATED_STMT (stmt_info))
- {
- stmt = STMT_VINFO_RELATED_STMT (stmt_info);
- stmt_info = vinfo_for_stmt (stmt);
- }
- tree lhs = gimple_call_lhs (stmt);
- new_stmt = gimple_build_assign (lhs, build_zero_cst (TREE_TYPE (lhs)));
- set_vinfo_for_stmt (new_stmt, stmt_info);
- set_vinfo_for_stmt (stmt, NULL);
- STMT_VINFO_STMT (stmt_info) = new_stmt;
- gsi_replace (gsi, new_stmt, true);
+ replace_mask_load (stmt, gsi);
}
return true;
@@ -5818,7 +6102,7 @@ vectorizable_store (gimple *stmt, gimple
return false;
vect_memory_access_type memory_access_type;
- if (!get_load_store_type (stmt, vectype, slp, vls_type, ncopies,
+ if (!get_load_store_type (stmt, vectype, slp, false, vls_type, ncopies,
&memory_access_type, &gs_info))
return false;
@@ -6353,34 +6637,21 @@ vectorizable_store (gimple *stmt, gimple
vec_oprnd = vec_oprnds[0];
}
else
- {
- /* For interleaved stores we collect vectorized defs for all the
- stores in the group in DR_CHAIN and OPRNDS. DR_CHAIN is then
- used as an input to vect_permute_store_chain(), and OPRNDS as
- an input to vect_get_vec_def_for_stmt_copy() for the next copy.
-
- If the store is not grouped, GROUP_SIZE is 1, and DR_CHAIN and
- OPRNDS are of size 1. */
- next_stmt = first_stmt;
- for (i = 0; i < group_size; i++)
- {
- /* Since gaps are not supported for interleaved stores,
- GROUP_SIZE is the exact number of stmts in the chain.
- Therefore, NEXT_STMT can't be NULL_TREE. In case that
- there is no interleaving, GROUP_SIZE is 1, and only one
- iteration of the loop will be executed. */
- gcc_assert (next_stmt
- && gimple_assign_single_p (next_stmt));
- op = gimple_assign_rhs1 (next_stmt);
-
- vec_oprnd = vect_get_vec_def_for_operand (op, next_stmt);
- dr_chain.quick_push (vec_oprnd);
- oprnds.quick_push (vec_oprnd);
- next_stmt = GROUP_NEXT_ELEMENT (vinfo_for_stmt (next_stmt));
- }
+ {
+ /* For interleaved stores we collect vectorized defs
+ for all the stores in the group in DR_CHAIN and OPRNDS.
+ DR_CHAIN is then used as an input to
+ vect_permute_store_chain(), and OPRNDS as an input to
+ vect_get_vec_def_for_stmt_copy() for the next copy.
+
+ If the store is not grouped, GROUP_SIZE is 1, and DR_CHAIN
+ and OPRNDS are of size 1. */
+ init_stored_values (group_size, first_stmt, &oprnds);
+ dr_chain.safe_splice (oprnds);
+ vec_oprnd = oprnds[0];
}
- /* We should have catched mismatched types earlier. */
+ /* We should have caught mismatched types earlier. */
gcc_assert (useless_type_conversion_p (vectype,
TREE_TYPE (vec_oprnd)));
bool simd_lane_access_p
@@ -6414,14 +6685,10 @@ vectorizable_store (gimple *stmt, gimple
next copy.
If the store is not grouped, GROUP_SIZE is 1, and DR_CHAIN and
OPRNDS are of size 1. */
- for (i = 0; i < group_size; i++)
- {
- op = oprnds[i];
- vect_is_simple_use (op, vinfo, &def_stmt, &dt);
- vec_oprnd = vect_get_vec_def_for_stmt_copy (dt, op);
- dr_chain[i] = vec_oprnd;
- oprnds[i] = vec_oprnd;
- }
+ advance_stored_values (group_size, first_stmt, oprnds);
+ dr_chain.truncate (0);
+ dr_chain.splice (oprnds);
+ vec_oprnd = oprnds[0];
if (dataref_offset)
dataref_offset
= int_const_binop (PLUS_EXPR, dataref_offset,
@@ -6432,27 +6699,8 @@ vectorizable_store (gimple *stmt, gimple
}
if (memory_access_type == VMAT_LOAD_STORE_LANES)
- {
- 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 = 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, ref_type);
- gcall *call = gimple_build_call_internal (IFN_STORE_LANES, 1,
- vec_array);
- gimple_call_set_lhs (call, data_ref);
- gimple_call_set_nothrow (call, true);
- new_stmt = call;
- vect_finish_stmt_generation (stmt, new_stmt, gsi);
- }
+ new_stmt = do_store_lanes (stmt, gsi, vec_num, aggr_type,
+ dataref_ptr, ref_type, dr_chain, NULL_TREE);
else
{
new_stmt = NULL;
@@ -6859,7 +7107,7 @@ vectorizable_load (gimple *stmt, gimple_
}
vect_memory_access_type memory_access_type;
- if (!get_load_store_type (stmt, vectype, slp, VLS_LOAD, ncopies,
+ if (!get_load_store_type (stmt, vectype, slp, false, VLS_LOAD, ncopies,
&memory_access_type, &gs_info))
return false;
@@ -7553,32 +7801,8 @@ vectorizable_load (gimple *stmt, gimple_
dr_chain.create (vec_num);
if (memory_access_type == VMAT_LOAD_STORE_LANES)
- {
- 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, ref_type);
- gcall *call = gimple_build_call_internal (IFN_LOAD_LANES, 1,
- data_ref);
- gimple_call_set_lhs (call, vec_array);
- gimple_call_set_nothrow (call, true);
- new_stmt = call;
- vect_finish_stmt_generation (stmt, new_stmt, gsi);
-
- /* Extract each vector into an SSA_NAME. */
- for (i = 0; i < vec_num; i++)
- {
- new_temp = read_vector_array (stmt, gsi, scalar_dest,
- vec_array, i);
- dr_chain.quick_push (new_temp);
- }
-
- /* Record the mapping between SSA_NAMEs and statements. */
- vect_record_grouped_load_vectors (stmt, dr_chain);
- }
+ do_load_lanes (stmt, gsi, group_size, vectype, aggr_type,
+ dataref_ptr, ref_type, NULL_TREE);
else
{
for (i = 0; i < vec_num; i++)
@@ -8907,7 +9131,16 @@ vect_transform_stmt (gimple *stmt, gimpl
done = vectorizable_call (stmt, gsi, &vec_stmt, slp_node);
stmt = gsi_stmt (*gsi);
if (gimple_call_internal_p (stmt, IFN_MASK_STORE))
- is_store = true;
+ {
+ gcc_assert (!slp_node);
+ /* As with normal stores, we vectorize the whole group when
+ we reach the last call in the group. The other calls are
+ in the group are left with a null VEC_STMT. */
+ if (STMT_VINFO_GROUPED_ACCESS (stmt_info))
+ *grouped_store = true;
+ if (STMT_VINFO_VEC_STMT (stmt_info))
+ is_store = true;
+ }
break;
case call_simd_clone_vec_info_type:
Index: gcc/testsuite/gcc.dg/vect/vect-ooo-group-1.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.dg/vect/vect-ooo-group-1.c 2017-11-08 16:35:04.763816035 +0000
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+
+void
+f (int *restrict a, int *restrict b, int *restrict c)
+{
+ for (int i = 0; i < 100; ++i)
+ if (c[i])
+ {
+ a[i * 2] = b[i * 5 + 2];
+ a[i * 2 + 1] = b[i * 5];
+ }
+}
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_1.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_1.c 2017-11-08 16:35:04.763816035 +0000
@@ -0,0 +1,67 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ NAME##_2 (OUTTYPE *__restrict dest, INTYPE *__restrict src, \
+ MASKTYPE *__restrict cond, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ if (cond[i]) \
+ dest[i] = src[i * 2] + src[i * 2 + 1]; \
+ }
+
+#define TEST2(NAME, OUTTYPE, INTYPE) \
+ TEST_LOOP (NAME##_i8, OUTTYPE, INTYPE, signed char) \
+ TEST_LOOP (NAME##_i16, OUTTYPE, INTYPE, unsigned short) \
+ TEST_LOOP (NAME##_f32, OUTTYPE, INTYPE, float) \
+ TEST_LOOP (NAME##_f64, OUTTYPE, INTYPE, double)
+
+#define TEST1(NAME, OUTTYPE) \
+ TEST2 (NAME##_i8, OUTTYPE, signed char) \
+ TEST2 (NAME##_i16, OUTTYPE, unsigned short) \
+ TEST2 (NAME##_i32, OUTTYPE, int) \
+ TEST2 (NAME##_i64, OUTTYPE, unsigned long)
+
+#define TEST(NAME) \
+ TEST1 (NAME##_i8, signed char) \
+ TEST1 (NAME##_i16, unsigned short) \
+ TEST1 (NAME##_i32, int) \
+ TEST1 (NAME##_i64, unsigned long) \
+ TEST2 (NAME##_f16_f16, _Float16, _Float16) \
+ TEST2 (NAME##_f32_f32, float, float) \
+ TEST2 (NAME##_f64_f64, double, double)
+
+TEST (test)
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 1 1 1 1
+ 16 | 1 1 1 1
+ 32 | 1 1 1 1
+ 64 | 1 1 1 1. */
+/* { dg-final { scan-assembler-times {\tld2b\t.z[0-9]} 16 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 2 2 2 2
+ 16 | 2 1 1 1 x2 (for half float)
+ 32 | 2 1 1 1
+ 64 | 2 1 1 1. */
+/* { dg-final { scan-assembler-times {\tld2h\t.z[0-9]} 28 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 4 4 4 4
+ 16 | 4 2 2 2
+ 32 | 4 2 1 1 x2 (for float)
+ 64 | 4 2 1 1. */
+/* { dg-final { scan-assembler-times {\tld2w\t.z[0-9]} 50 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 8 8 8 8
+ 16 | 8 4 4 4
+ 32 | 8 4 2 2
+ 64 | 8 4 2 1 x2 (for double). */
+/* { dg-final { scan-assembler-times {\tld2d\t.z[0-9]} 98 } } */
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_1_run.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_1_run.c 2017-11-08 16:35:04.763816035 +0000
@@ -0,0 +1,38 @@
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#include "sve_mask_struct_load_1.c"
+
+#define N 100
+
+#undef TEST_LOOP
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ { \
+ OUTTYPE out[N]; \
+ INTYPE in[N * 2]; \
+ MASKTYPE mask[N]; \
+ for (int i = 0; i < N; ++i) \
+ { \
+ out[i] = i * 7 / 2; \
+ mask[i] = i % 5 <= i % 3; \
+ asm volatile ("" ::: "memory"); \
+ } \
+ for (int i = 0; i < N * 2; ++i) \
+ in[i] = i * 9 / 2; \
+ NAME##_2 (out, in, mask, N); \
+ for (int i = 0; i < N; ++i) \
+ { \
+ OUTTYPE if_true = in[i * 2] + in[i * 2 + 1]; \
+ OUTTYPE if_false = i * 7 / 2; \
+ if (out[i] != (mask[i] ? if_true : if_false)) \
+ __builtin_abort (); \
+ asm volatile ("" ::: "memory"); \
+ } \
+ }
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+ TEST (test);
+ return 0;
+}
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_2.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_2.c 2017-11-08 16:35:04.766569934 +0000
@@ -0,0 +1,69 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ NAME##_3 (OUTTYPE *__restrict dest, INTYPE *__restrict src, \
+ MASKTYPE *__restrict cond, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ if (cond[i]) \
+ dest[i] = (src[i * 3] \
+ + src[i * 3 + 1] \
+ + src[i * 3 + 2]); \
+ }
+
+#define TEST2(NAME, OUTTYPE, INTYPE) \
+ TEST_LOOP (NAME##_i8, OUTTYPE, INTYPE, signed char) \
+ TEST_LOOP (NAME##_i16, OUTTYPE, INTYPE, unsigned short) \
+ TEST_LOOP (NAME##_f32, OUTTYPE, INTYPE, float) \
+ TEST_LOOP (NAME##_f64, OUTTYPE, INTYPE, double)
+
+#define TEST1(NAME, OUTTYPE) \
+ TEST2 (NAME##_i8, OUTTYPE, signed char) \
+ TEST2 (NAME##_i16, OUTTYPE, unsigned short) \
+ TEST2 (NAME##_i32, OUTTYPE, int) \
+ TEST2 (NAME##_i64, OUTTYPE, unsigned long)
+
+#define TEST(NAME) \
+ TEST1 (NAME##_i8, signed char) \
+ TEST1 (NAME##_i16, unsigned short) \
+ TEST1 (NAME##_i32, int) \
+ TEST1 (NAME##_i64, unsigned long) \
+ TEST2 (NAME##_f16_f16, _Float16, _Float16) \
+ TEST2 (NAME##_f32_f32, float, float) \
+ TEST2 (NAME##_f64_f64, double, double)
+
+TEST (test)
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 1 1 1 1
+ 16 | 1 1 1 1
+ 32 | 1 1 1 1
+ 64 | 1 1 1 1. */
+/* { dg-final { scan-assembler-times {\tld3b\t.z[0-9]} 16 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 2 2 2 2
+ 16 | 2 1 1 1 x2 (for _Float16)
+ 32 | 2 1 1 1
+ 64 | 2 1 1 1. */
+/* { dg-final { scan-assembler-times {\tld3h\t.z[0-9]} 28 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 4 4 4 4
+ 16 | 4 2 2 2
+ 32 | 4 2 1 1 x2 (for float)
+ 64 | 4 2 1 1. */
+/* { dg-final { scan-assembler-times {\tld3w\t.z[0-9]} 50 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 8 8 8 8
+ 16 | 8 4 4 4
+ 32 | 8 4 2 2
+ 64 | 8 4 2 1 x2 (for double). */
+/* { dg-final { scan-assembler-times {\tld3d\t.z[0-9]} 98 } } */
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_2_run.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_2_run.c 2017-11-08 16:35:04.766569934 +0000
@@ -0,0 +1,40 @@
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#include "sve_mask_struct_load_2.c"
+
+#define N 100
+
+#undef TEST_LOOP
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ { \
+ OUTTYPE out[N]; \
+ INTYPE in[N * 3]; \
+ MASKTYPE mask[N]; \
+ for (int i = 0; i < N; ++i) \
+ { \
+ out[i] = i * 7 / 2; \
+ mask[i] = i % 5 <= i % 3; \
+ asm volatile ("" ::: "memory"); \
+ } \
+ for (int i = 0; i < N * 3; ++i) \
+ in[i] = i * 9 / 2; \
+ NAME##_3 (out, in, mask, N); \
+ for (int i = 0; i < N; ++i) \
+ { \
+ OUTTYPE if_true = (in[i * 3] \
+ + in[i * 3 + 1] \
+ + in[i * 3 + 2]); \
+ OUTTYPE if_false = i * 7 / 2; \
+ if (out[i] != (mask[i] ? if_true : if_false)) \
+ __builtin_abort (); \
+ asm volatile ("" ::: "memory"); \
+ } \
+ }
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+ TEST (test);
+ return 0;
+}
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_3.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_3.c 2017-11-08 16:35:04.766569934 +0000
@@ -0,0 +1,70 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ NAME##_4 (OUTTYPE *__restrict dest, INTYPE *__restrict src, \
+ MASKTYPE *__restrict cond, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ if (cond[i]) \
+ dest[i] = (src[i * 4] \
+ + src[i * 4 + 1] \
+ + src[i * 4 + 2] \
+ + src[i * 4 + 3]); \
+ }
+
+#define TEST2(NAME, OUTTYPE, INTYPE) \
+ TEST_LOOP (NAME##_i8, OUTTYPE, INTYPE, signed char) \
+ TEST_LOOP (NAME##_i16, OUTTYPE, INTYPE, unsigned short) \
+ TEST_LOOP (NAME##_f32, OUTTYPE, INTYPE, float) \
+ TEST_LOOP (NAME##_f64, OUTTYPE, INTYPE, double)
+
+#define TEST1(NAME, OUTTYPE) \
+ TEST2 (NAME##_i8, OUTTYPE, signed char) \
+ TEST2 (NAME##_i16, OUTTYPE, unsigned short) \
+ TEST2 (NAME##_i32, OUTTYPE, int) \
+ TEST2 (NAME##_i64, OUTTYPE, unsigned long)
+
+#define TEST(NAME) \
+ TEST1 (NAME##_i8, signed char) \
+ TEST1 (NAME##_i16, unsigned short) \
+ TEST1 (NAME##_i32, int) \
+ TEST1 (NAME##_i64, unsigned long) \
+ TEST2 (NAME##_f16_f16, _Float16, _Float16) \
+ TEST2 (NAME##_f32_f32, float, float) \
+ TEST2 (NAME##_f64_f64, double, double)
+
+TEST (test)
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 1 1 1 1
+ 16 | 1 1 1 1
+ 32 | 1 1 1 1
+ 64 | 1 1 1 1. */
+/* { dg-final { scan-assembler-times {\tld4b\t.z[0-9]} 16 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 2 2 2 2
+ 16 | 2 1 1 1 x2 (for half float)
+ 32 | 2 1 1 1
+ 64 | 2 1 1 1. */
+/* { dg-final { scan-assembler-times {\tld4h\t.z[0-9]} 28 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 4 4 4 4
+ 16 | 4 2 2 2
+ 32 | 4 2 1 1 x2 (for float)
+ 64 | 4 2 1 1. */
+/* { dg-final { scan-assembler-times {\tld4w\t.z[0-9]} 50 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 8 8 8 8
+ 16 | 8 4 4 4
+ 32 | 8 4 2 2
+ 64 | 8 4 2 1 x2 (for double). */
+/* { dg-final { scan-assembler-times {\tld4d\t.z[0-9]} 98 } } */
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_3_run.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_3_run.c 2017-11-08 16:35:04.766569934 +0000
@@ -0,0 +1,41 @@
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#include "sve_mask_struct_load_3.c"
+
+#define N 100
+
+#undef TEST_LOOP
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ { \
+ OUTTYPE out[N]; \
+ INTYPE in[N * 4]; \
+ MASKTYPE mask[N]; \
+ for (int i = 0; i < N; ++i) \
+ { \
+ out[i] = i * 7 / 2; \
+ mask[i] = i % 5 <= i % 3; \
+ asm volatile ("" ::: "memory"); \
+ } \
+ for (int i = 0; i < N * 4; ++i) \
+ in[i] = i * 9 / 2; \
+ NAME##_4 (out, in, mask, N); \
+ for (int i = 0; i < N; ++i) \
+ { \
+ OUTTYPE if_true = (in[i * 4] \
+ + in[i * 4 + 1] \
+ + in[i * 4 + 2] \
+ + in[i * 4 + 3]); \
+ OUTTYPE if_false = i * 7 / 2; \
+ if (out[i] != (mask[i] ? if_true : if_false)) \
+ __builtin_abort (); \
+ asm volatile ("" ::: "memory"); \
+ } \
+ }
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+ TEST (test);
+ return 0;
+}
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_4.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_4.c 2017-11-08 16:35:04.766569934 +0000
@@ -0,0 +1,67 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ NAME##_3 (OUTTYPE *__restrict dest, INTYPE *__restrict src, \
+ MASKTYPE *__restrict cond, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ if (cond[i]) \
+ dest[i] = src[i * 3] + src[i * 3 + 2]; \
+ }
+
+#define TEST2(NAME, OUTTYPE, INTYPE) \
+ TEST_LOOP (NAME##_i8, OUTTYPE, INTYPE, signed char) \
+ TEST_LOOP (NAME##_i16, OUTTYPE, INTYPE, unsigned short) \
+ TEST_LOOP (NAME##_f32, OUTTYPE, INTYPE, float) \
+ TEST_LOOP (NAME##_f64, OUTTYPE, INTYPE, double)
+
+#define TEST1(NAME, OUTTYPE) \
+ TEST2 (NAME##_i8, OUTTYPE, signed char) \
+ TEST2 (NAME##_i16, OUTTYPE, unsigned short) \
+ TEST2 (NAME##_i32, OUTTYPE, int) \
+ TEST2 (NAME##_i64, OUTTYPE, unsigned long)
+
+#define TEST(NAME) \
+ TEST1 (NAME##_i8, signed char) \
+ TEST1 (NAME##_i16, unsigned short) \
+ TEST1 (NAME##_i32, int) \
+ TEST1 (NAME##_i64, unsigned long) \
+ TEST2 (NAME##_f16_f16, _Float16, _Float16) \
+ TEST2 (NAME##_f32_f32, float, float) \
+ TEST2 (NAME##_f64_f64, double, double)
+
+TEST (test)
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 1 1 1 1
+ 16 | 1 1 1 1
+ 32 | 1 1 1 1
+ 64 | 1 1 1 1. */
+/* { dg-final { scan-assembler-times {\tld3b\t.z[0-9]} 16 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 2 2 2 2
+ 16 | 2 1 1 1 x2 (for half float)
+ 32 | 2 1 1 1
+ 64 | 2 1 1 1. */
+/* { dg-final { scan-assembler-times {\tld3h\t.z[0-9]} 28 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 4 4 4 4
+ 16 | 4 2 2 2
+ 32 | 4 2 1 1 x2 (for float)
+ 64 | 4 2 1 1. */
+/* { dg-final { scan-assembler-times {\tld3w\t.z[0-9]} 50 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 8 8 8 8
+ 16 | 8 4 4 4
+ 32 | 8 4 2 2
+ 64 | 8 4 2 1 x2 (for double). */
+/* { dg-final { scan-assembler-times {\tld3d\t.z[0-9]} 98 } } */
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_5.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_5.c 2017-11-08 16:35:04.766569934 +0000
@@ -0,0 +1,67 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ NAME##_4 (OUTTYPE *__restrict dest, INTYPE *__restrict src, \
+ MASKTYPE *__restrict cond, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ if (cond[i]) \
+ dest[i] = src[i * 4] + src[i * 4 + 3]; \
+ }
+
+#define TEST2(NAME, OUTTYPE, INTYPE) \
+ TEST_LOOP (NAME##_i8, OUTTYPE, INTYPE, signed char) \
+ TEST_LOOP (NAME##_i16, OUTTYPE, INTYPE, unsigned short) \
+ TEST_LOOP (NAME##_f32, OUTTYPE, INTYPE, float) \
+ TEST_LOOP (NAME##_f64, OUTTYPE, INTYPE, double)
+
+#define TEST1(NAME, OUTTYPE) \
+ TEST2 (NAME##_i8, OUTTYPE, signed char) \
+ TEST2 (NAME##_i16, OUTTYPE, unsigned short) \
+ TEST2 (NAME##_i32, OUTTYPE, int) \
+ TEST2 (NAME##_i64, OUTTYPE, unsigned long)
+
+#define TEST(NAME) \
+ TEST1 (NAME##_i8, signed char) \
+ TEST1 (NAME##_i16, unsigned short) \
+ TEST1 (NAME##_i32, int) \
+ TEST1 (NAME##_i64, unsigned long) \
+ TEST2 (NAME##_f16_f16, _Float16, _Float16) \
+ TEST2 (NAME##_f32_f32, float, float) \
+ TEST2 (NAME##_f64_f64, double, double)
+
+TEST (test)
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 1 1 1 1
+ 16 | 1 1 1 1
+ 32 | 1 1 1 1
+ 64 | 1 1 1 1. */
+/* { dg-final { scan-assembler-times {\tld4b\t.z[0-9]} 16 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 2 2 2 2
+ 16 | 2 1 1 1 x2 (for half float)
+ 32 | 2 1 1 1
+ 64 | 2 1 1 1. */
+/* { dg-final { scan-assembler-times {\tld4h\t.z[0-9]} 28 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 4 4 4 4
+ 16 | 4 2 2 2
+ 32 | 4 2 1 1 x2 (for float)
+ 64 | 4 2 1 1. */
+/* { dg-final { scan-assembler-times {\tld4w\t.z[0-9]} 50 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ Out 8 | 8 8 8 8
+ 16 | 8 4 4 4
+ 32 | 8 4 2 2
+ 64 | 8 4 2 1 x2 (for double). */
+/* { dg-final { scan-assembler-times {\tld4d\t.z[0-9]} 98 } } */
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_6.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_6.c 2017-11-08 16:35:04.766569934 +0000
@@ -0,0 +1,40 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ NAME##_2 (OUTTYPE *__restrict dest, INTYPE *__restrict src, \
+ MASKTYPE *__restrict cond, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ if (cond[i]) \
+ dest[i] = src[i * 2]; \
+ }
+
+#define TEST2(NAME, OUTTYPE, INTYPE) \
+ TEST_LOOP (NAME##_i8, OUTTYPE, INTYPE, signed char) \
+ TEST_LOOP (NAME##_i16, OUTTYPE, INTYPE, unsigned short) \
+ TEST_LOOP (NAME##_f32, OUTTYPE, INTYPE, float) \
+ TEST_LOOP (NAME##_f64, OUTTYPE, INTYPE, double)
+
+#define TEST1(NAME, OUTTYPE) \
+ TEST2 (NAME##_i8, OUTTYPE, signed char) \
+ TEST2 (NAME##_i16, OUTTYPE, unsigned short) \
+ TEST2 (NAME##_i32, OUTTYPE, int) \
+ TEST2 (NAME##_i64, OUTTYPE, unsigned long)
+
+#define TEST(NAME) \
+ TEST1 (NAME##_i8, signed char) \
+ TEST1 (NAME##_i16, unsigned short) \
+ TEST1 (NAME##_i32, int) \
+ TEST1 (NAME##_i64, unsigned long) \
+ TEST2 (NAME##_f16_f16, _Float16, _Float16) \
+ TEST2 (NAME##_f32_f32, float, float) \
+ TEST2 (NAME##_f64_f64, double, double)
+
+TEST (test)
+
+/* { dg-final { scan-assembler-not {\tld2b\t} } } */
+/* { dg-final { scan-assembler-not {\tld2h\t} } } */
+/* { dg-final { scan-assembler-not {\tld2w\t} } } */
+/* { dg-final { scan-assembler-not {\tld2d\t} } } */
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_7.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_7.c 2017-11-08 16:35:04.767487900 +0000
@@ -0,0 +1,40 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ NAME##_3 (OUTTYPE *__restrict dest, INTYPE *__restrict src, \
+ MASKTYPE *__restrict cond, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ if (cond[i]) \
+ dest[i] = src[i * 3] + src[i * 3 + 1]; \
+ }
+
+#define TEST2(NAME, OUTTYPE, INTYPE) \
+ TEST_LOOP (NAME##_i8, OUTTYPE, INTYPE, signed char) \
+ TEST_LOOP (NAME##_i16, OUTTYPE, INTYPE, unsigned short) \
+ TEST_LOOP (NAME##_f32, OUTTYPE, INTYPE, float) \
+ TEST_LOOP (NAME##_f64, OUTTYPE, INTYPE, double)
+
+#define TEST1(NAME, OUTTYPE) \
+ TEST2 (NAME##_i8, OUTTYPE, signed char) \
+ TEST2 (NAME##_i16, OUTTYPE, unsigned short) \
+ TEST2 (NAME##_i32, OUTTYPE, int) \
+ TEST2 (NAME##_i64, OUTTYPE, unsigned long)
+
+#define TEST(NAME) \
+ TEST1 (NAME##_i8, signed char) \
+ TEST1 (NAME##_i16, unsigned short) \
+ TEST1 (NAME##_i32, int) \
+ TEST1 (NAME##_i64, unsigned long) \
+ TEST2 (NAME##_f16_f16, _Float16, _Float16) \
+ TEST2 (NAME##_f32_f32, float, float) \
+ TEST2 (NAME##_f64_f64, double, double)
+
+TEST (test)
+
+/* { dg-final { scan-assembler-not {\tld3b\t} } } */
+/* { dg-final { scan-assembler-not {\tld3h\t} } } */
+/* { dg-final { scan-assembler-not {\tld3w\t} } } */
+/* { dg-final { scan-assembler-not {\tld3d\t} } } */
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_8.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_load_8.c 2017-11-08 16:35:04.767487900 +0000
@@ -0,0 +1,40 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ NAME##_4 (OUTTYPE *__restrict dest, INTYPE *__restrict src, \
+ MASKTYPE *__restrict cond, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ if (cond[i]) \
+ dest[i] = src[i * 4] + src[i * 4 + 2]; \
+ }
+
+#define TEST2(NAME, OUTTYPE, INTYPE) \
+ TEST_LOOP (NAME##_i8, OUTTYPE, INTYPE, signed char) \
+ TEST_LOOP (NAME##_i16, OUTTYPE, INTYPE, unsigned short) \
+ TEST_LOOP (NAME##_f32, OUTTYPE, INTYPE, float) \
+ TEST_LOOP (NAME##_f64, OUTTYPE, INTYPE, double)
+
+#define TEST1(NAME, OUTTYPE) \
+ TEST2 (NAME##_i8, OUTTYPE, signed char) \
+ TEST2 (NAME##_i16, OUTTYPE, unsigned short) \
+ TEST2 (NAME##_i32, OUTTYPE, int) \
+ TEST2 (NAME##_i64, OUTTYPE, unsigned long)
+
+#define TEST(NAME) \
+ TEST1 (NAME##_i8, signed char) \
+ TEST1 (NAME##_i16, unsigned short) \
+ TEST1 (NAME##_i32, int) \
+ TEST1 (NAME##_i64, unsigned long) \
+ TEST2 (NAME##_f16_f16, _Float16, _Float16) \
+ TEST2 (NAME##_f32_f32, float, float) \
+ TEST2 (NAME##_f64_f64, double, double)
+
+TEST (test)
+
+/* { dg-final { scan-assembler-not {\tld4b\t} } } */
+/* { dg-final { scan-assembler-not {\tld4h\t} } } */
+/* { dg-final { scan-assembler-not {\tld4w\t} } } */
+/* { dg-final { scan-assembler-not {\tld4d\t} } } */
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_1.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_1.c 2017-11-08 16:35:04.767487900 +0000
@@ -0,0 +1,70 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -ffast-math -march=armv8-a+sve" } */
+
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ NAME##_2 (OUTTYPE *__restrict dest, INTYPE *__restrict src, \
+ MASKTYPE *__restrict cond, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ if (cond[i]) \
+ { \
+ dest[i * 2] = src[i]; \
+ dest[i * 2 + 1] = src[i]; \
+ } \
+ }
+
+#define TEST2(NAME, OUTTYPE, INTYPE) \
+ TEST_LOOP (NAME##_i8, OUTTYPE, INTYPE, signed char) \
+ TEST_LOOP (NAME##_i16, OUTTYPE, INTYPE, unsigned short) \
+ TEST_LOOP (NAME##_f32, OUTTYPE, INTYPE, float) \
+ TEST_LOOP (NAME##_f64, OUTTYPE, INTYPE, double)
+
+#define TEST1(NAME, OUTTYPE) \
+ TEST2 (NAME##_i8, OUTTYPE, signed char) \
+ TEST2 (NAME##_i16, OUTTYPE, unsigned short) \
+ TEST2 (NAME##_i32, OUTTYPE, int) \
+ TEST2 (NAME##_i64, OUTTYPE, unsigned long)
+
+#define TEST(NAME) \
+ TEST1 (NAME##_i8, signed char) \
+ TEST1 (NAME##_i16, unsigned short) \
+ TEST1 (NAME##_i32, int) \
+ TEST1 (NAME##_i64, unsigned long) \
+ TEST2 (NAME##_f16_f16, _Float16, _Float16) \
+ TEST2 (NAME##_f32_f32, float, float) \
+ TEST2 (NAME##_f64_f64, double, double)
+
+TEST (test)
+
+/* Mask | 8 16 32 64
+ -------+------------
+ In 8 | 1 1 1 1
+ 16 | 1 1 1 1
+ 32 | 1 1 1 1
+ 64 | 1 1 1 1. */
+/* { dg-final { scan-assembler-times {\tst2b\t.z[0-9]} 16 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ In 8 | 2 2 2 2
+ 16 | 2 1 1 1 x2 (for _Float16)
+ 32 | 2 1 1 1
+ 64 | 2 1 1 1. */
+/* { dg-final { scan-assembler-times {\tst2h\t.z[0-9]} 28 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ In 8 | 4 4 4 4
+ 16 | 4 2 2 2
+ 32 | 4 2 1 1 x2 (for float)
+ 64 | 4 2 1 1. */
+/* { dg-final { scan-assembler-times {\tst2w\t.z[0-9]} 50 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ In 8 | 8 8 8 8
+ 16 | 8 4 4 4
+ 32 | 8 4 2 2
+ 64 | 8 4 2 1 x2 (for double). */
+/* { dg-final { scan-assembler-times {\tst2d\t.z[0-9]} 98 } } */
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_1_run.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_1_run.c 2017-11-08 16:35:04.767487900 +0000
@@ -0,0 +1,38 @@
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#include "sve_mask_struct_store_1.c"
+
+#define N 100
+
+#undef TEST_LOOP
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ { \
+ OUTTYPE out[N * 2]; \
+ INTYPE in[N]; \
+ MASKTYPE mask[N]; \
+ for (int i = 0; i < N; ++i) \
+ { \
+ in[i] = i * 7 / 2; \
+ mask[i] = i % 5 <= i % 3; \
+ asm volatile ("" ::: "memory"); \
+ } \
+ for (int i = 0; i < N * 2; ++i) \
+ out[i] = i * 9 / 2; \
+ NAME##_2 (out, in, mask, N); \
+ for (int i = 0; i < N * 2; ++i) \
+ { \
+ OUTTYPE if_true = in[i / 2]; \
+ OUTTYPE if_false = i * 9 / 2; \
+ if (out[i] != (mask[i / 2] ? if_true : if_false)) \
+ __builtin_abort (); \
+ asm volatile ("" ::: "memory"); \
+ } \
+ }
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+ TEST (test);
+ return 0;
+}
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_2.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_2.c 2017-11-08 16:35:04.767487900 +0000
@@ -0,0 +1,71 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -ffast-math -march=armv8-a+sve" } */
+
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ NAME##_3 (OUTTYPE *__restrict dest, INTYPE *__restrict src, \
+ MASKTYPE *__restrict cond, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ if (cond[i]) \
+ { \
+ dest[i * 3] = src[i]; \
+ dest[i * 3 + 1] = src[i]; \
+ dest[i * 3 + 2] = src[i]; \
+ } \
+ }
+
+#define TEST2(NAME, OUTTYPE, INTYPE) \
+ TEST_LOOP (NAME##_i8, OUTTYPE, INTYPE, signed char) \
+ TEST_LOOP (NAME##_i16, OUTTYPE, INTYPE, unsigned short) \
+ TEST_LOOP (NAME##_f32, OUTTYPE, INTYPE, float) \
+ TEST_LOOP (NAME##_f64, OUTTYPE, INTYPE, double)
+
+#define TEST1(NAME, OUTTYPE) \
+ TEST2 (NAME##_i8, OUTTYPE, signed char) \
+ TEST2 (NAME##_i16, OUTTYPE, unsigned short) \
+ TEST2 (NAME##_i32, OUTTYPE, int) \
+ TEST2 (NAME##_i64, OUTTYPE, unsigned long)
+
+#define TEST(NAME) \
+ TEST1 (NAME##_i8, signed char) \
+ TEST1 (NAME##_i16, unsigned short) \
+ TEST1 (NAME##_i32, int) \
+ TEST1 (NAME##_i64, unsigned long) \
+ TEST2 (NAME##_f16_f16, _Float16, _Float16) \
+ TEST2 (NAME##_f32_f32, float, float) \
+ TEST2 (NAME##_f64_f64, double, double)
+
+TEST (test)
+
+/* Mask | 8 16 32 64
+ -------+------------
+ In 8 | 1 1 1 1
+ 16 | 1 1 1 1
+ 32 | 1 1 1 1
+ 64 | 1 1 1 1. */
+/* { dg-final { scan-assembler-times {\tst3b\t.z[0-9]} 16 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ In 8 | 2 2 2 2
+ 16 | 2 1 1 1 x2 (for _Float16)
+ 32 | 2 1 1 1
+ 64 | 2 1 1 1. */
+/* { dg-final { scan-assembler-times {\tst3h\t.z[0-9]} 28 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ In 8 | 4 4 4 4
+ 16 | 4 2 2 2
+ 32 | 4 2 1 1 x2 (for float)
+ 64 | 4 2 1 1. */
+/* { dg-final { scan-assembler-times {\tst3w\t.z[0-9]} 50 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ In 8 | 8 8 8 8
+ 16 | 8 4 4 4
+ 32 | 8 4 2 2
+ 64 | 8 4 2 1 x2 (for double). */
+/* { dg-final { scan-assembler-times {\tst3d\t.z[0-9]} 98 } } */
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_2_run.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_2_run.c 2017-11-08 16:35:04.767487900 +0000
@@ -0,0 +1,38 @@
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#include "sve_mask_struct_store_2.c"
+
+#define N 100
+
+#undef TEST_LOOP
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ { \
+ OUTTYPE out[N * 3]; \
+ INTYPE in[N]; \
+ MASKTYPE mask[N]; \
+ for (int i = 0; i < N; ++i) \
+ { \
+ in[i] = i * 7 / 2; \
+ mask[i] = i % 5 <= i % 3; \
+ asm volatile ("" ::: "memory"); \
+ } \
+ for (int i = 0; i < N * 3; ++i) \
+ out[i] = i * 9 / 2; \
+ NAME##_3 (out, in, mask, N); \
+ for (int i = 0; i < N * 3; ++i) \
+ { \
+ OUTTYPE if_true = in[i / 3]; \
+ OUTTYPE if_false = i * 9 / 2; \
+ if (out[i] != (mask[i / 3] ? if_true : if_false)) \
+ __builtin_abort (); \
+ asm volatile ("" ::: "memory"); \
+ } \
+ }
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+ TEST (test);
+ return 0;
+}
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_3.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_3.c 2017-11-08 16:35:04.767487900 +0000
@@ -0,0 +1,72 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -fno-vect-cost-model -march=armv8-a+sve" } */
+
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ NAME##_4 (OUTTYPE *__restrict dest, INTYPE *__restrict src, \
+ MASKTYPE *__restrict cond, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ if (cond[i]) \
+ { \
+ dest[i * 4] = src[i]; \
+ dest[i * 4 + 1] = src[i]; \
+ dest[i * 4 + 2] = src[i]; \
+ dest[i * 4 + 3] = src[i]; \
+ } \
+ }
+
+#define TEST2(NAME, OUTTYPE, INTYPE) \
+ TEST_LOOP (NAME##_i8, OUTTYPE, INTYPE, signed char) \
+ TEST_LOOP (NAME##_i16, OUTTYPE, INTYPE, unsigned short) \
+ TEST_LOOP (NAME##_f32, OUTTYPE, INTYPE, float) \
+ TEST_LOOP (NAME##_f64, OUTTYPE, INTYPE, double)
+
+#define TEST1(NAME, OUTTYPE) \
+ TEST2 (NAME##_i8, OUTTYPE, signed char) \
+ TEST2 (NAME##_i16, OUTTYPE, unsigned short) \
+ TEST2 (NAME##_i32, OUTTYPE, int) \
+ TEST2 (NAME##_i64, OUTTYPE, unsigned long)
+
+#define TEST(NAME) \
+ TEST1 (NAME##_i8, signed char) \
+ TEST1 (NAME##_i16, unsigned short) \
+ TEST1 (NAME##_i32, int) \
+ TEST1 (NAME##_i64, unsigned long) \
+ TEST2 (NAME##_f16_f16, _Float16, _Float16) \
+ TEST2 (NAME##_f32_f32, float, float) \
+ TEST2 (NAME##_f64_f64, double, double)
+
+TEST (test)
+
+/* Mask | 8 16 32 64
+ -------+------------
+ In 8 | 1 1 1 1
+ 16 | 1 1 1 1
+ 32 | 1 1 1 1
+ 64 | 1 1 1 1. */
+/* { dg-final { scan-assembler-times {\tst4b\t.z[0-9]} 16 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ In 8 | 2 2 2 2
+ 16 | 2 1 1 1 x2 (for half float)
+ 32 | 2 1 1 1
+ 64 | 2 1 1 1. */
+/* { dg-final { scan-assembler-times {\tst4h\t.z[0-9]} 28 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ In 8 | 4 4 4 4
+ 16 | 4 2 2 2
+ 32 | 4 2 1 1 x2 (for float)
+ 64 | 4 2 1 1. */
+/* { dg-final { scan-assembler-times {\tst4w\t.z[0-9]} 50 } } */
+
+/* Mask | 8 16 32 64
+ -------+------------
+ In 8 | 8 8 8 8
+ 16 | 8 4 4 4
+ 32 | 8 4 2 2
+ 64 | 8 4 2 1 x2 (for double). */
+/* { dg-final { scan-assembler-times {\tst4d\t.z[0-9]} 98 } } */
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_3_run.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_3_run.c 2017-11-08 16:35:04.767487900 +0000
@@ -0,0 +1,38 @@
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-dce -ffast-math -march=armv8-a+sve" } */
+
+#include "sve_mask_struct_store_3.c"
+
+#define N 100
+
+#undef TEST_LOOP
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ { \
+ OUTTYPE out[N * 4]; \
+ INTYPE in[N]; \
+ MASKTYPE mask[N]; \
+ for (int i = 0; i < N; ++i) \
+ { \
+ in[i] = i * 7 / 2; \
+ mask[i] = i % 5 <= i % 3; \
+ asm volatile ("" ::: "memory"); \
+ } \
+ for (int i = 0; i < N * 4; ++i) \
+ out[i] = i * 9 / 2; \
+ NAME##_4 (out, in, mask, N); \
+ for (int i = 0; i < N * 4; ++i) \
+ { \
+ OUTTYPE if_true = in[i / 4]; \
+ OUTTYPE if_false = i * 9 / 2; \
+ if (out[i] != (mask[i / 4] ? if_true : if_false)) \
+ __builtin_abort (); \
+ asm volatile ("" ::: "memory"); \
+ } \
+ }
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+ TEST (test);
+ return 0;
+}
Index: gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_4.c
===================================================================
--- /dev/null 2017-11-08 11:04:45.353113300 +0000
+++ gcc/testsuite/gcc.target/aarch64/sve_mask_struct_store_4.c 2017-11-08 16:35:04.767487900 +0000
@@ -0,0 +1,44 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -ffast-math -march=armv8-a+sve" } */
+
+#define TEST_LOOP(NAME, OUTTYPE, INTYPE, MASKTYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ NAME##_2 (OUTTYPE *__restrict dest, INTYPE *__restrict src, \
+ MASKTYPE *__restrict cond, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ { \
+ if (cond[i] < 8) \
+ dest[i * 2] = src[i]; \
+ if (cond[i] > 2) \
+ dest[i * 2 + 1] = src[i]; \
+ } \
+ }
+
+#define TEST2(NAME, OUTTYPE, INTYPE) \
+ TEST_LOOP (NAME##_i8, OUTTYPE, INTYPE, signed char) \
+ TEST_LOOP (NAME##_i16, OUTTYPE, INTYPE, unsigned short) \
+ TEST_LOOP (NAME##_f32, OUTTYPE, INTYPE, float) \
+ TEST_LOOP (NAME##_f64, OUTTYPE, INTYPE, double)
+
+#define TEST1(NAME, OUTTYPE) \
+ TEST2 (NAME##_i8, OUTTYPE, signed char) \
+ TEST2 (NAME##_i16, OUTTYPE, unsigned short) \
+ TEST2 (NAME##_i32, OUTTYPE, int) \
+ TEST2 (NAME##_i64, OUTTYPE, unsigned long)
+
+#define TEST(NAME) \
+ TEST1 (NAME##_i8, signed char) \
+ TEST1 (NAME##_i16, unsigned short) \
+ TEST1 (NAME##_i32, int) \
+ TEST1 (NAME##_i64, unsigned long) \
+ TEST2 (NAME##_f16_f16, _Float16, _Float16) \
+ TEST2 (NAME##_f32_f32, float, float) \
+ TEST2 (NAME##_f64_f64, double, double)
+
+TEST (test)
+
+/* { dg-final { scan-assembler-not {\tst2b\t.z[0-9]} } } */
+/* { dg-final { scan-assembler-not {\tst2h\t.z[0-9]} } } */
+/* { dg-final { scan-assembler-not {\tst2w\t.z[0-9]} } } */
+/* { dg-final { scan-assembler-not {\tst2d\t.z[0-9]} } } */
More information about the Gcc-patches
mailing list