This is a preliminary to patch 2, which wants functionality equivalent to
vect_gen_perm_mask (converting a char* to an RTL const_vector) but without the
check of can_vec_perm_p.
All existing calls to vect_gen_perm_mask barring that in perm_mask_for_reverse,
assert the return value is non-null. Hence, this patch splits the existing
vect_gen_perm_mask into two: a checked variant which makes the equivalent
assertion; and an unchecked variant, which just turns any char* into an
equivalent const_vector.
(An) alternative strategy would be merely to remove the check from
vect_gen_perm_mask (so equivalent to this patch's vect_gen_perm_mask_any), and
add a preceding assert at all callsites (i.e. changing the many
"gen_vect_perm_mask (...); assert (... != NULL);" into "assert (can_vec_perm_p
(...)); gen_vect_perm_mask (...);" - that would work just as well as far as this
patch series is concerned.
On its own, bootstrapped on x86-none-linux-gnu (more testing with patches 2+3).
gcc/ChangeLog:
* tree-vectorizer.h (vect_gen_perm_mask): Remove.
(vect_gen_perm_mask_checked, vect_gen_perm_mask_any): New.
tree_vec_data_refs.c (vect_permute_load_chain, vec_permute_store_chain,
vec_shift_permute_load_chain): Replace vect_gen_perm_mask & assert
with vect_gen_perm_mask_checked.
* tree-vect-stmts.c (vectorizable_mask_load_store, vectorizable_load):
Likewise.
(vect_gen_perm_mask_checked): New.
(vect_gen_perm_mask): Remove can_vec_perm_p check, rename to...
(vect_gen_perm_mask_any): ...this.
(perm_mask_for_reverse): Call can_vec_perm_p and
vect_gen_perm_mask_checked.diff --git a/gcc/tree-vect-data-refs.c b/gcc/tree-vect-data-refs.c
index 1d30bdf78cbd66874906c5f7444ce30c4c391feb..4c5b1394517bfcf5c4226143e53cbbe79e0c68b1 100644
--- a/gcc/tree-vect-data-refs.c
+++ b/gcc/tree-vect-data-refs.c
@@ -4623,8 +4623,7 @@ vect_permute_store_chain (vec<tree> dr_chain,
if (3 * i + nelt2 < nelt)
sel[3 * i + nelt2] = 0;
}
- perm3_mask_low = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm3_mask_low != NULL);
+ perm3_mask_low = vect_gen_perm_mask_checked (vectype, sel);
for (i = 0; i < nelt; i++)
{
@@ -4635,8 +4634,7 @@ vect_permute_store_chain (vec<tree> dr_chain,
if (3 * i + nelt2 < nelt)
sel[3 * i + nelt2] = nelt + j2++;
}
- perm3_mask_high = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm3_mask_high != NULL);
+ perm3_mask_high = vect_gen_perm_mask_checked (vectype, sel);
vect1 = dr_chain[0];
vect2 = dr_chain[1];
@@ -4675,13 +4673,11 @@ vect_permute_store_chain (vec<tree> dr_chain,
sel[i * 2] = i;
sel[i * 2 + 1] = i + nelt;
}
- perm_mask_high = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm_mask_high != NULL);
+ perm_mask_high = vect_gen_perm_mask_checked (vectype, sel);
for (i = 0; i < nelt; i++)
sel[i] += nelt / 2;
- perm_mask_low = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm_mask_low != NULL);
+ perm_mask_low = vect_gen_perm_mask_checked (vectype, sel);
for (i = 0, n = log_length; i < n; i++)
{
@@ -5184,8 +5180,7 @@ vect_permute_load_chain (vec<tree> dr_chain,
sel[i] = 3 * i + k;
else
sel[i] = 0;
- perm3_mask_low = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm3_mask_low != NULL);
+ perm3_mask_low = vect_gen_perm_mask_checked (vectype, sel);
for (i = 0, j = 0; i < nelt; i++)
if (3 * i + k < 2 * nelt)
@@ -5193,8 +5188,7 @@ vect_permute_load_chain (vec<tree> dr_chain,
else
sel[i] = nelt + ((nelt + k) % 3) + 3 * (j++);
- perm3_mask_high = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm3_mask_high != NULL);
+ perm3_mask_high = vect_gen_perm_mask_checked (vectype, sel);
first_vect = dr_chain[0];
second_vect = dr_chain[1];
@@ -5228,13 +5222,11 @@ vect_permute_load_chain (vec<tree> dr_chain,
for (i = 0; i < nelt; ++i)
sel[i] = i * 2;
- perm_mask_even = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm_mask_even != NULL);
+ perm_mask_even = vect_gen_perm_mask_checked (vectype, sel);
for (i = 0; i < nelt; ++i)
sel[i] = i * 2 + 1;
- perm_mask_odd = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm_mask_odd != NULL);
+ perm_mask_odd = vect_gen_perm_mask_checked (vectype, sel);
for (i = 0; i < log_length; i++)
{
@@ -5389,8 +5381,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
supported by target\n");
return false;
}
- perm2_mask1 = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm2_mask1 != NULL);
+ perm2_mask1 = vect_gen_perm_mask_checked (vectype, sel);
for (i = 0; i < nelt / 2; ++i)
sel[i] = i * 2 + 1;
@@ -5404,8 +5395,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
supported by target\n");
return false;
}
- perm2_mask2 = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm2_mask2 != NULL);
+ perm2_mask2 = vect_gen_perm_mask_checked (vectype, sel);
/* Generating permutation constant to shift all elements.
For vector length 8 it is {4 5 6 7 8 9 10 11}. */
@@ -5418,8 +5408,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
"shift permutation is not supported by target\n");
return false;
}
- shift1_mask = vect_gen_perm_mask (vectype, sel);
- gcc_assert (shift1_mask != NULL);
+ shift1_mask = vect_gen_perm_mask_checked (vectype, sel);
/* Generating permutation constant to select vector from 2.
For vector length 8 it is {0 1 2 3 12 13 14 15}. */
@@ -5434,8 +5423,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
"select is not supported by target\n");
return false;
}
- select_mask = vect_gen_perm_mask (vectype, sel);
- gcc_assert (select_mask != NULL);
+ select_mask = vect_gen_perm_mask_checked (vectype, sel);
first_vect = dr_chain[0];
second_vect = dr_chain[1];
@@ -5494,8 +5482,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
supported by target\n");
return false;
}
- perm3_mask = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm3_mask != NULL);
+ perm3_mask = vect_gen_perm_mask_checked (vectype, sel);
/* Generating permutation constant to shift all elements.
For vector length 8 it is {6 7 8 9 10 11 12 13}. */
@@ -5508,8 +5495,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
"shift permutation is not supported by target\n");
return false;
}
- shift1_mask = vect_gen_perm_mask (vectype, sel);
- gcc_assert (shift1_mask != NULL);
+ shift1_mask = vect_gen_perm_mask_checked (vectype, sel);
/* Generating permutation constant to shift all elements.
For vector length 8 it is {5 6 7 8 9 10 11 12}. */
@@ -5522,8 +5508,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
"shift permutation is not supported by target\n");
return false;
}
- shift2_mask = vect_gen_perm_mask (vectype, sel);
- gcc_assert (shift2_mask != NULL);
+ shift2_mask = vect_gen_perm_mask_checked (vectype, sel);
/* Generating permutation constant to shift all elements.
For vector length 8 it is {3 4 5 6 7 8 9 10}. */
@@ -5536,8 +5521,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
"shift permutation is not supported by target\n");
return false;
}
- shift3_mask = vect_gen_perm_mask (vectype, sel);
- gcc_assert (shift3_mask != NULL);
+ shift3_mask = vect_gen_perm_mask_checked (vectype, sel);
/* Generating permutation constant to shift all elements.
For vector length 8 it is {5 6 7 8 9 10 11 12}. */
@@ -5550,8 +5534,7 @@ vect_shift_permute_load_chain (vec<tree> dr_chain,
"shift permutation is not supported by target\n");
return false;
}
- shift4_mask = vect_gen_perm_mask (vectype, sel);
- gcc_assert (shift4_mask != NULL);
+ shift4_mask = vect_gen_perm_mask_checked (vectype, sel);
for (k = 0; k < 3; k++)
{
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index 681479ed911e9ff0fadc8d52576086ed3bbaca5a..3c2d7d7926e7aece6c0aca63210a2d6d591ac1fb 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -1913,8 +1913,7 @@ vectorizable_mask_load_store (gimple stmt, gimple_stmt_iterator *gsi,
for (i = 0; i < gather_off_nunits; ++i)
sel[i] = i | nunits;
- perm_mask = vect_gen_perm_mask (gather_off_vectype, sel);
- gcc_assert (perm_mask != NULL_TREE);
+ perm_mask = vect_gen_perm_mask_checked (gather_off_vectype, sel);
}
else if (nunits == gather_off_nunits * 2)
{
@@ -1925,13 +1924,11 @@ vectorizable_mask_load_store (gimple stmt, gimple_stmt_iterator *gsi,
sel[i] = i < gather_off_nunits
? i : i + nunits - gather_off_nunits;
- perm_mask = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm_mask != NULL_TREE);
+ perm_mask = vect_gen_perm_mask_checked (vectype, sel);
ncopies *= 2;
for (i = 0; i < nunits; ++i)
sel[i] = i | gather_off_nunits;
- mask_perm_mask = vect_gen_perm_mask (masktype, sel);
- gcc_assert (mask_perm_mask != NULL_TREE);
+ mask_perm_mask = vect_gen_perm_mask_checked (masktype, sel);
}
else
gcc_unreachable ();
@@ -4936,7 +4933,9 @@ perm_mask_for_reverse (tree vectype)
for (i = 0; i < nunits; ++i)
sel[i] = nunits - 1 - i;
- return vect_gen_perm_mask (vectype, sel);
+ if (!can_vec_perm_p (TYPE_MODE (vectype), false, sel))
+ return NULL_TREE;
+ return vect_gen_perm_mask_checked (vectype, sel);
}
/* Function vectorizable_store.
@@ -5467,21 +5466,19 @@ vectorizable_store (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
return true;
}
-/* Given a vector type VECTYPE and permutation SEL returns
- the VECTOR_CST mask that implements the permutation of the
- vector elements. If that is impossible to do, returns NULL. */
+/* Given a vector type VECTYPE, turns permutation SEL into the equivalent
+ VECTOR_CST mask. No checks are made that the target platform supports the
+ mask, so callers may wish to test can_vec_perm_p separately, or use
+ vect_gen_perm_mask_checked. */
tree
-vect_gen_perm_mask (tree vectype, unsigned char *sel)
+vect_gen_perm_mask_any (tree vectype, const unsigned char *sel)
{
tree mask_elt_type, mask_type, mask_vec, *mask_elts;
int i, nunits;
nunits = TYPE_VECTOR_SUBPARTS (vectype);
- if (!can_vec_perm_p (TYPE_MODE (vectype), false, sel))
- return NULL;
-
mask_elt_type = lang_hooks.types.type_for_mode
(int_mode_for_mode (TYPE_MODE (TREE_TYPE (vectype))), 1);
mask_type = get_vectype_for_scalar_type (mask_elt_type);
@@ -5494,6 +5491,15 @@ vect_gen_perm_mask (tree vectype, unsigned char *sel)
return mask_vec;
}
+/* Checked version of vect_gen_perm_mask_any. Asserts can_vec_perm_p. */
+
+tree
+vect_gen_perm_mask_checked (tree vectype, const unsigned char *sel)
+{
+ gcc_assert (can_vec_perm_p (TYPE_MODE (vectype), false, sel));
+ return vect_gen_perm_mask_any (vectype, sel);
+}
+
/* Given a vector variable X and Y, that was generated for the scalar
STMT, generate instructions to permute the vector elements of X and Y
using permutation mask MASK_VEC, insert them at *GSI and return the
@@ -5849,8 +5855,7 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
for (i = 0; i < gather_off_nunits; ++i)
sel[i] = i | nunits;
- perm_mask = vect_gen_perm_mask (gather_off_vectype, sel);
- gcc_assert (perm_mask != NULL_TREE);
+ perm_mask = vect_gen_perm_mask_checked (gather_off_vectype, sel);
}
else if (nunits == gather_off_nunits * 2)
{
@@ -5861,8 +5866,7 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
sel[i] = i < gather_off_nunits
? i : i + nunits - gather_off_nunits;
- perm_mask = vect_gen_perm_mask (vectype, sel);
- gcc_assert (perm_mask != NULL_TREE);
+ perm_mask = vect_gen_perm_mask_checked (vectype, sel);
ncopies *= 2;
}
else
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index 93aa73e59c6079dc95288979e15c1d47725391b7..d817f9f53a6ed8d88a305207f6f482ef7a30fea3 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -1040,7 +1040,8 @@ extern void vect_get_store_cost (struct data_reference *, int,
extern bool vect_supportable_shift (enum tree_code, tree);
extern void vect_get_vec_defs (tree, tree, gimple, vec<tree> *,
vec<tree> *, slp_tree, int);
-extern tree vect_gen_perm_mask (tree, unsigned char *);
+extern tree vect_gen_perm_mask_any (tree, const unsigned char *);
+extern tree vect_gen_perm_mask_checked (tree, const unsigned char *);
/* In tree-vect-data-refs.c. */
extern bool vect_can_force_dr_alignment_p (const_tree, unsigned int);
