+2019-06-13 Kugan Vivekanandarajah <kugan.vivekanandarajah@linaro.org>
+
+ PR target/88838
+ * tree-vect-loop-manip.c (vect_set_loop_masks_directly): If the
+ compare_type is not with Pmode size, we will create an IV with
+ Pmode size with truncated use (i.e. converted to the correct type).
+ * tree-vect-loop.c (vect_verify_full_masking): Find IV type.
+ (vect_iv_limit_for_full_masking): New. Factored out of
+ vect_set_loop_condition_masked.
+ * tree-vectorizer.h (LOOP_VINFO_MASK_IV_TYPE): New.
+ (vect_iv_limit_for_full_masking): Declare.
+
2019-06-13 Kugan Vivekanandarajah <kugan.vivekanandarajah@linaro.org>
PR target/88834
+2019-06-13 Kugan Vivekanandarajah <kugan.vivekanandarajah@linaro.org>
+
+ PR target/88838
+ * gcc.target/aarch64/pr88838.c: New test.
+ * gcc.target/aarch64/sve/while_1.c: Adjust.
+
2019-06-13 Kugan Vivekanandarajah <kugan.vivekanandarajah@linaro.org>
PR target/88834
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-S -O3 -march=armv8.2-a+sve" } */
+
+void
+f (int *restrict x, int *restrict y, int *restrict z, int n)
+{
+ for (int i = 0; i < n; i += 1)
+ x[i] = y[i] + z[i];
+}
+
+/* { dg-final { scan-assembler-not "sxtw" } } */
TEST_ALL (ADD_LOOP)
/* { dg-final { scan-assembler-not {\tuqdec} } } */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.b, xzr,} 2 } } */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.b, x[0-9]+,} 2 } } */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.h, xzr,} 2 } } */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.h, x[0-9]+,} 2 } } */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.s, xzr,} 3 } } */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.s, x[0-9]+,} 3 } } */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.d, xzr,} 3 } } */
-/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.d, x[0-9]+,} 3 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.b, wzr,} 2 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.b, w[0-9]+,} 2 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.h, wzr,} 2 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.h, w[0-9]+,} 2 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.s, wzr,} 3 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.s, w[0-9]+,} 3 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.d, wzr,} 3 } } */
+/* { dg-final { scan-assembler-times {\twhilelo\tp[0-7]\.d, w[0-9]+,} 3 } } */
/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.b, p[0-7]/z, \[x0, x[0-9]+\]\n} 2 } } */
/* { dg-final { scan-assembler-times {\tst1b\tz[0-9]+\.b, p[0-7], \[x0, x[0-9]+\]\n} 2 } } */
/* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.h, p[0-7]/z, \[x0, x[0-9]+, lsl 1\]\n} 2 } } */
bool might_wrap_p)
{
tree compare_type = LOOP_VINFO_MASK_COMPARE_TYPE (loop_vinfo);
+ tree iv_type = LOOP_VINFO_MASK_IV_TYPE (loop_vinfo);
tree mask_type = rgm->mask_type;
unsigned int nscalars_per_iter = rgm->max_nscalars_per_iter;
poly_uint64 nscalars_per_mask = TYPE_VECTOR_SUBPARTS (mask_type);
tree index_before_incr, index_after_incr;
gimple_stmt_iterator incr_gsi;
bool insert_after;
- tree zero_index = build_int_cst (compare_type, 0);
standard_iv_increment_position (loop, &incr_gsi, &insert_after);
- create_iv (zero_index, nscalars_step, NULL_TREE, loop, &incr_gsi,
+
+ tree zero_index = build_int_cst (iv_type, 0);
+ tree step = build_int_cst (iv_type,
+ LOOP_VINFO_VECT_FACTOR (loop_vinfo));
+ /* Create IV of iv_type. */
+ create_iv (zero_index, step, NULL_TREE, loop, &incr_gsi,
insert_after, &index_before_incr, &index_after_incr);
+ zero_index = build_int_cst (compare_type, 0);
tree test_index, test_limit, first_limit;
gimple_stmt_iterator *test_gsi;
if (might_wrap_p)
tree next_mask = NULL_TREE;
tree mask;
unsigned int i;
+ gimple_seq test_seq = NULL;
+ test_index = gimple_convert (&test_seq, compare_type, test_index);
+ gsi_insert_seq_before (test_gsi, test_seq, GSI_SAME_STMT);
+
FOR_EACH_VEC_ELT_REVERSE (rgm->masks, i, mask)
{
/* Previous masks will cover BIAS scalars. This mask covers the
tree compare_type = LOOP_VINFO_MASK_COMPARE_TYPE (loop_vinfo);
unsigned int compare_precision = TYPE_PRECISION (compare_type);
- unsigned HOST_WIDE_INT max_vf = vect_max_vf (loop_vinfo);
tree orig_niters = niters;
/* Type of the initial value of NITERS. */
tree ni_actual_type = TREE_TYPE (niters);
unsigned int ni_actual_precision = TYPE_PRECISION (ni_actual_type);
+ tree niters_skip = LOOP_VINFO_MASK_SKIP_NITERS (loop_vinfo);
/* Convert NITERS to the same size as the compare. */
if (compare_precision > ni_actual_precision
else
niters = gimple_convert (&preheader_seq, compare_type, niters);
- /* Convert skip_niters to the right type. */
- tree niters_skip = LOOP_VINFO_MASK_SKIP_NITERS (loop_vinfo);
-
- /* Now calculate the value that the induction variable must be able
- to hit in order to ensure that we end the loop with an all-false mask.
- This involves adding the maximum number of inactive trailing scalar
- iterations. */
- widest_int iv_limit;
- bool known_max_iters = max_loop_iterations (loop, &iv_limit);
- if (known_max_iters)
- {
- if (niters_skip)
- {
- /* Add the maximum number of skipped iterations to the
- maximum iteration count. */
- if (TREE_CODE (niters_skip) == INTEGER_CST)
- iv_limit += wi::to_widest (niters_skip);
- else
- iv_limit += max_vf - 1;
- }
- /* IV_LIMIT is the maximum number of latch iterations, which is also
- the maximum in-range IV value. Round this value down to the previous
- vector alignment boundary and then add an extra full iteration. */
- poly_uint64 vf = LOOP_VINFO_VECT_FACTOR (loop_vinfo);
- iv_limit = (iv_limit & -(int) known_alignment (vf)) + max_vf;
- }
-
+ widest_int iv_limit = vect_iv_limit_for_full_masking (loop_vinfo);
/* Get the vectorization factor in tree form. */
tree vf = build_int_cst (compare_type,
LOOP_VINFO_VECT_FACTOR (loop_vinfo));
/* See whether zero-based IV would ever generate all-false masks
before wrapping around. */
bool might_wrap_p
- = (!known_max_iters
+ = (iv_limit == -1
|| (wi::min_precision (iv_limit * rgm->max_nscalars_per_iter,
UNSIGNED)
> compare_precision));
{
struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
unsigned int min_ni_width;
+ unsigned int max_nscalars_per_iter
+ = vect_get_max_nscalars_per_iter (loop_vinfo);
/* Use a normal loop if there are no statements that need masking.
This only happens in rare degenerate cases: it means that the loop
max_ni = wi::smin (max_ni, max_back_edges + 1);
/* Account for rgroup masks, in which each bit is replicated N times. */
- max_ni *= vect_get_max_nscalars_per_iter (loop_vinfo);
+ max_ni *= max_nscalars_per_iter;
/* Work out how many bits we need to represent the limit. */
min_ni_width = wi::min_precision (max_ni, UNSIGNED);
/* Find a scalar mode for which WHILE_ULT is supported. */
opt_scalar_int_mode cmp_mode_iter;
tree cmp_type = NULL_TREE;
+ tree iv_type = NULL_TREE;
+ widest_int iv_limit = vect_iv_limit_for_full_masking (loop_vinfo);
+ widest_int iv_precision = UINT_MAX;
+
+ if (iv_limit != -1)
+ iv_precision = wi::min_precision (iv_limit * max_nscalars_per_iter,
+ UNSIGNED);
+
FOR_EACH_MODE_IN_CLASS (cmp_mode_iter, MODE_INT)
{
unsigned int cmp_bits = GET_MODE_BITSIZE (cmp_mode_iter.require ());
&& can_produce_all_loop_masks_p (loop_vinfo, this_type))
{
/* Although we could stop as soon as we find a valid mode,
- it's often better to continue until we hit Pmode, since the
- operands to the WHILE are more likely to be reusable in
- address calculations. */
- cmp_type = this_type;
+ there are at least two reasons why that's not always the
+ best choice:
+
+ - An IV that's Pmode or wider is more likely to be reusable
+ in address calculations than an IV that's narrower than
+ Pmode.
+
+ - Doing the comparison in IV_PRECISION or wider allows
+ a natural 0-based IV, whereas using a narrower comparison
+ type requires mitigations against wrap-around.
+
+ Conversely, if the IV limit is variable, doing the comparison
+ in a wider type than the original type can introduce
+ unnecessary extensions, so picking the widest valid mode
+ is not always a good choice either.
+
+ Here we prefer the first IV type that's Pmode or wider,
+ and the first comparison type that's IV_PRECISION or wider.
+ (The comparison type must be no wider than the IV type,
+ to avoid extensions in the vector loop.)
+
+ ??? We might want to try continuing beyond Pmode for ILP32
+ targets if CMP_BITS < IV_PRECISION. */
+ iv_type = this_type;
+ if (!cmp_type || iv_precision > TYPE_PRECISION (cmp_type))
+ cmp_type = this_type;
if (cmp_bits >= GET_MODE_BITSIZE (Pmode))
break;
}
return false;
LOOP_VINFO_MASK_COMPARE_TYPE (loop_vinfo) = cmp_type;
+ LOOP_VINFO_MASK_IV_TYPE (loop_vinfo) = iv_type;
return true;
}
add_phi_arg (phi, gimple_vuse (last_store), e, UNKNOWN_LOCATION);
}
}
+
+/* Decide whether it is possible to use a zero-based induction variable
+ when vectorizing LOOP_VINFO with a fully-masked loop. If it is,
+ return the value that the induction variable must be able to hold
+ in order to ensure that the loop ends with an all-false mask.
+ Return -1 otherwise. */
+widest_int
+vect_iv_limit_for_full_masking (loop_vec_info loop_vinfo)
+{
+ tree niters_skip = LOOP_VINFO_MASK_SKIP_NITERS (loop_vinfo);
+ struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
+ unsigned HOST_WIDE_INT max_vf = vect_max_vf (loop_vinfo);
+
+ /* Calculate the value that the induction variable must be able
+ to hit in order to ensure that we end the loop with an all-false mask.
+ This involves adding the maximum number of inactive trailing scalar
+ iterations. */
+ widest_int iv_limit = -1;
+ if (max_loop_iterations (loop, &iv_limit))
+ {
+ if (niters_skip)
+ {
+ /* Add the maximum number of skipped iterations to the
+ maximum iteration count. */
+ if (TREE_CODE (niters_skip) == INTEGER_CST)
+ iv_limit += wi::to_widest (niters_skip);
+ else
+ iv_limit += max_vf - 1;
+ }
+ else if (LOOP_VINFO_PEELING_FOR_ALIGNMENT (loop_vinfo))
+ /* Make a conservatively-correct assumption. */
+ iv_limit += max_vf - 1;
+
+ /* IV_LIMIT is the maximum number of latch iterations, which is also
+ the maximum in-range IV value. Round this value down to the previous
+ vector alignment boundary and then add an extra full iteration. */
+ poly_uint64 vf = LOOP_VINFO_VECT_FACTOR (loop_vinfo);
+ iv_limit = (iv_limit & -(int) known_alignment (vf)) + max_vf;
+ }
+ return iv_limit;
+}
+
is false and vectorized loop otherwise. */
tree simd_if_cond;
+ /* Type of the IV to use in the WHILE_ULT call for fully-masked
+ loops. */
+ tree iv_type;
+
/* Unknown DRs according to which loop was peeled. */
struct dr_vec_info *unaligned_dr;
#define LOOP_VINFO_MASKS(L) (L)->masks
#define LOOP_VINFO_MASK_SKIP_NITERS(L) (L)->mask_skip_niters
#define LOOP_VINFO_MASK_COMPARE_TYPE(L) (L)->mask_compare_type
+#define LOOP_VINFO_MASK_IV_TYPE(L) (L)->iv_type
#define LOOP_VINFO_PTR_MASK(L) (L)->ptr_mask
#define LOOP_VINFO_LOOP_NEST(L) (L)->shared->loop_nest
#define LOOP_VINFO_DATAREFS(L) (L)->shared->datarefs
/* FORNOW: Used in tree-parloops.c. */
extern stmt_vec_info vect_force_simple_reduction (loop_vec_info, stmt_vec_info,
bool *, bool);
+extern widest_int vect_iv_limit_for_full_masking (loop_vec_info loop_vinfo);
/* Used in gimple-loop-interchange.c. */
extern bool check_reduction_path (dump_user_location_t, loop_p, gphi *, tree,
enum tree_code);
projects / gcc.git / commitdiff