Epilogue vectorization is not set up to re-use a vectorized
accumulator consisting of more than one vector. For non-SLP
we always reduce to a single but for SLP that isn't happening.
In such case we currenlty miscompile the epilog so avoid this.
PR tree-optimization/107160
* tree-vect-loop.cc (vect_create_epilog_for_reduction):
Do not register accumulator if we failed to reduce it
to a single vector.
* gcc.dg/vect/pr107160.c: New testcase.
--- /dev/null
+/* { dg-do run } */
+
+#include <math.h>
+
+#define N 128
+float fl[N];
+
+__attribute__ ((noipa)) void
+init ()
+{
+ for (int i = 0; i < N; i++)
+ fl[i] = i;
+}
+
+__attribute__ ((noipa)) float
+foo (int n1)
+{
+ float sum0, sum1, sum2, sum3;
+ sum0 = sum1 = sum2 = sum3 = 0.0f;
+
+ int n = (n1 / 4) * 4;
+ for (int i = 0; i < n; i += 4)
+ {
+ sum0 += fabs (fl[i]);
+ sum1 += fabs (fl[i + 1]);
+ sum2 += fabs (fl[i + 2]);
+ sum3 += fabs (fl[i + 3]);
+ }
+
+ return sum0 + sum1 + sum2 + sum3;
+}
+
+int
+main ()
+{
+ init ();
+ float res = foo (80);
+ if (res != 3160)
+ __builtin_abort ();
+ return 0;
+}
}
/* Record this operation if it could be reused by the epilogue loop. */
- if (STMT_VINFO_REDUC_TYPE (reduc_info) == TREE_CODE_REDUCTION)
+ if (STMT_VINFO_REDUC_TYPE (reduc_info) == TREE_CODE_REDUCTION
+ && vec_num == 1)
loop_vinfo->reusable_accumulators.put (scalar_results[0],
{ orig_reduc_input, reduc_info });