The following arranges for the pre-SLP vectorization scalar cleanup
to be run when predictive commoning was applied to a loop in the
function. This is similar to the complete unroll situation and
facilitating SLP vectorization. Avoiding the SSA copies in predictive
commoning itself isn't easy (and predcom also sometimes unrolls,
asking for scalar cleanup).
Bootstrapped and tested on x86_64-unknown-linux-gnu, pushed.
PR tree-optimization/114435
* tree-predcom.cc (tree_predictive_commoning): Queue
the next scalar cleanup sub-pipeline to be run when we
did something.
* gcc.dg/vect/bb-slp-pr114435.c: New testcase.
---
gcc/testsuite/gcc.dg/vect/bb-slp-pr114435.c | 37 +++++++++++++++++++++
gcc/tree-predcom.cc | 3 ++
2 files changed, 40 insertions(+)
create mode 100644 gcc/testsuite/gcc.dg/vect/bb-slp-pr114435.c
diff --git a/gcc/testsuite/gcc.dg/vect/bb-slp-pr114435.c
b/gcc/testsuite/gcc.dg/vect/bb-slp-pr114435.c
new file mode 100644
index 00000000000..d1eecf7979a
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/bb-slp-pr114435.c
@@ -0,0 +1,37 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_double } */
+/* Predictive commining is supposed to happen. */
+/* { dg-additional-options "-O3 -fdump-tree-pcom" } */
+
+struct res {
+ double r0;
+ double r1;
+ double r2;
+ double r3;
+};
+
+struct pxl {
+ double v0;
+ double v1;
+ double v2;
+ double v3;
+};
+
+#define IS_NAN(x) ((x) == (x))
+
+void fold(struct res *r, struct pxl *in, double k, int sz)
+{
+ int i;
+
+ for (i = 0; i < sz; i++) {
+ if (IS_NAN(k)) continue;
+ r->r0 += in[i].v0 * k;
+ r->r1 += in[i].v1 * k;
+ r->r2 += in[i].v2 * k;
+ r->r3 += in[i].v3 * k;
+ }
+}
+
+/* { dg-final { scan-tree-dump "# r__r0_lsm\[^\r\n\]* = PHI" "pcom" } } */
+/* { dg-final { scan-tree-dump "optimized: basic block part vectorized" "slp1"
} } */
+/* { dg-final { scan-tree-dump "# vect\[^\r\n\]* = PHI" "slp1" } } */
diff --git a/gcc/tree-predcom.cc b/gcc/tree-predcom.cc
index 75a4c85164c..9844fee1e97 100644
--- a/gcc/tree-predcom.cc
+++ b/gcc/tree-predcom.cc
@@ -3522,6 +3522,9 @@ tree_predictive_commoning (bool allow_unroll_p)
}
}
+ if (ret != 0)
+ cfun->pending_TODOs |= PENDING_TODO_force_next_scalar_cleanup;
+
return ret;
}
--
2.35.3
