--- /dev/null
+/* { dg-require-effective-target vect_int } */
+/* PR tree-optimization/67682. */
+
+#include "tree-vect.h"
+
+int __attribute__((__aligned__(8))) a[8];
+int __attribute__((__aligned__(8))) b[4];
+
+__attribute__ ((noinline)) void
+test ()
+{
+ a[0] = b[0];
+ a[1] = b[1];
+ a[2] = b[2];
+ a[3] = b[3];
+ a[4] = 0;
+ a[5] = 0;
+ a[6] = 0;
+ a[7] = 0;
+}
+
+int
+main (int argc, char **argv)
+{
+ check_vect ();
+
+ for (int i = 0; i < 8; i++)
+ a[i] = 1;
+ for (int i = 0; i < 4; i++)
+ b[i] = i + 4;
+ __asm__ volatile ("" : : : "memory");
+ test (a, b);
+ __asm__ volatile ("" : : : "memory");
+ for (int i = 0; i < 4; i++)
+ if (a[i] != i+4)
+ abort ();
+ for (int i = 4; i < 8; i++)
+ if (a[i] != 0)
+ abort ();
+ return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "Basic block will be vectorized using SLP" 1 "slp2" } } */
+/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp2" } } */
--- /dev/null
+/* { dg-require-effective-target vect_int } */
+/* PR tree-optimization/67682. */
+
+#include "tree-vect.h"
+
+int __attribute__((__aligned__(8))) a[8];
+int __attribute__((__aligned__(8))) b[4];
+
+__attribute__ ((noinline)) void
+test ()
+{
+ a[0] = b[2] + 1;
+ a[1] = b[0] + 2;
+ a[2] = b[1] + 3;
+ a[3] = b[1] + 4;
+ a[4] = b[3] * 3;
+ a[5] = b[0] * 4;
+ a[6] = b[2] * 5;
+ a[7] = b[1] * 7;
+}
+
+int
+main (int argc, char **argv)
+{
+ check_vect ();
+
+ for (int i = 0; i < 8; i++)
+ a[i] = 1;
+ for (int i = 0; i < 4; i++)
+ b[i] = i + 4;
+ __asm__ volatile ("" : : : "memory");
+ test (a, b);
+ __asm__ volatile ("" : : : "memory");
+ if ((a[0] != 7) || a[1] != 6 || (a[2] != 8) || (a[3] != 9)
+ || (a[4] != 21) || (a[5] != 16) || (a[6] != 30) || (a[7] != 35))
+ abort ();
+ return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "Basic block will be vectorized using SLP" 1 "slp2" } } */
+/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp2" } } */
--- /dev/null
+/* { dg-require-effective-target vect_int } */
+/* PR tree-optimization/67682. */
+
+#include "tree-vect.h"
+
+int __attribute__((__aligned__(8))) a[8];
+int __attribute__((__aligned__(8))) b[8];
+
+__attribute__ ((noinline)) void
+test ()
+{
+ a[0] = b[0] + 1;
+ a[1] = b[1] + 2;
+ a[2] = b[2] + 3;
+ a[3] = b[3] + 4;
+ a[4] = b[0] * 3;
+ a[5] = b[2] * 4;
+ a[6] = b[4] * 5;
+ a[7] = b[6] * 7;
+}
+
+int
+main (int argc, char **argv)
+{
+ check_vect ();
+
+ for (int i = 0; i < 8; i++)
+ a[i] = 1;
+ for (int i = 0; i < 8; i++)
+ b[i] = i + 4;
+ __asm__ volatile ("" : : : "memory");
+ test (a, b);
+ __asm__ volatile ("" : : : "memory");
+ if ((a[0] != 5) || (a[1] != 7) || (a[2] != 9) || (a[3] != 11)
+ || (a[4] != 12) || (a[5] != 24) || (a[6] != 40) || (a[7] != 70))
+ abort ();
+ return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "Basic block will be vectorized using SLP" 1 "slp2" } } */
+/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp2" } } */
body_cost_vec.release ();
}
+/* Splits a group of stores, currently beginning at FIRST_STMT, into two groups:
+ one (still beginning at FIRST_STMT) of size GROUP1_SIZE (also containing
+ the first GROUP1_SIZE stmts, since stores are consecutive), the second
+ containing the remainder.
+ Return the first stmt in the second group. */
+
+static gimple *
+vect_split_slp_store_group (gimple *first_stmt, unsigned group1_size)
+{
+ stmt_vec_info first_vinfo = vinfo_for_stmt (first_stmt);
+ gcc_assert (GROUP_FIRST_ELEMENT (first_vinfo) == first_stmt);
+ gcc_assert (group1_size > 0);
+ int group2_size = GROUP_SIZE (first_vinfo) - group1_size;
+ gcc_assert (group2_size > 0);
+ GROUP_SIZE (first_vinfo) = group1_size;
+
+ gimple *stmt = first_stmt;
+ for (unsigned i = group1_size; i > 1; i--)
+ {
+ stmt = GROUP_NEXT_ELEMENT (vinfo_for_stmt (stmt));
+ gcc_assert (GROUP_GAP (vinfo_for_stmt (stmt)) == 1);
+ }
+ /* STMT is now the last element of the first group. */
+ gimple *group2 = GROUP_NEXT_ELEMENT (vinfo_for_stmt (stmt));
+ GROUP_NEXT_ELEMENT (vinfo_for_stmt (stmt)) = 0;
+
+ GROUP_SIZE (vinfo_for_stmt (group2)) = group2_size;
+ for (stmt = group2; stmt; stmt = GROUP_NEXT_ELEMENT (vinfo_for_stmt (stmt)))
+ {
+ GROUP_FIRST_ELEMENT (vinfo_for_stmt (stmt)) = group2;
+ gcc_assert (GROUP_GAP (vinfo_for_stmt (stmt)) == 1);
+ }
+
+ /* For the second group, the GROUP_GAP is that before the original group,
+ plus skipping over the first vector. */
+ GROUP_GAP (vinfo_for_stmt (group2)) =
+ GROUP_GAP (first_vinfo) + group1_size;
+
+ /* GROUP_GAP of the first group now has to skip over the second group too. */
+ GROUP_GAP (first_vinfo) += group2_size;
+
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_NOTE, vect_location, "Split group into %d and %d\n",
+ group1_size, group2_size);
+
+ return group2;
+}
+
/* Analyze an SLP instance starting from a group of grouped stores. Call
vect_build_slp_tree to build a tree of packed stmts if possible.
Return FALSE if it's impossible to SLP any stmt in the loop. */
tree vectype, scalar_type = NULL_TREE;
gimple *next;
unsigned int vectorization_factor = 0;
- int i;
+ unsigned int i;
unsigned int max_nunits = 0;
vec<slp_tree> loads;
struct data_reference *dr = STMT_VINFO_DATA_REF (vinfo_for_stmt (stmt));
vect_free_slp_tree (node);
loads.release ();
+ /* For basic block SLP, try to break the group up into multiples of the
+ vectorization factor. */
+ if (is_a <bb_vec_info> (vinfo)
+ && GROUP_FIRST_ELEMENT (vinfo_for_stmt (stmt))
+ && STMT_VINFO_GROUPED_ACCESS (vinfo_for_stmt (stmt)))
+ {
+ /* We consider breaking the group only on VF boundaries from the existing
+ start. */
+ for (i = 0; i < group_size; i++)
+ if (!matches[i]) break;
+
+ if (i >= vectorization_factor && i < group_size)
+ {
+ /* Split into two groups at the first vector boundary before i. */
+ gcc_assert ((vectorization_factor & (vectorization_factor - 1)) == 0);
+ unsigned group1_size = i & ~(vectorization_factor - 1);
+
+ gimple *rest = vect_split_slp_store_group (stmt, group1_size);
+ bool res = vect_analyze_slp_instance (vinfo, stmt, max_tree_size);
+ /* If the first non-match was in the middle of a vector,
+ skip the rest of that vector. */
+ if (group1_size < i)
+ {
+ i = group1_size + vectorization_factor;
+ if (i < group_size)
+ rest = vect_split_slp_store_group (rest, vectorization_factor);
+ }
+ if (i < group_size)
+ res |= vect_analyze_slp_instance (vinfo, rest, max_tree_size);
+ return res;
+ }
+ /* Even though the first vector did not all match, we might be able to SLP
+ (some) of the remainder. FORNOW ignore this possibility. */
+ }
+
return false;
}
projects / gcc.git / commitdiff