tree-optimization/110221 - SLP and loop mask/len

The following fixes the issue that when SLP stmts are internal defs
but appear invariant because they end up only using invariant defs
then they get scheduled outside of the loop.  This nice optimization
breaks down when loop masks or lens are applied since those are not
explicitly tracked as dependences.  The following makes sure to never
schedule internal defs outside of the vectorized loop when the
loop uses masks/lens.

	PR tree-optimization/110221
	* tree-vect-slp.cc (vect_schedule_slp_node): When loop
	masking / len is applied make sure to not schedule
	intenal defs outside of the loop.

	* gfortran.dg/pr110221.f: New testcase.

(cherry picked from commit e5f1956498251a4973d52c8aad3faf34d0443169)

diff --git a/gcc/testsuite/gfortran.dg/pr110221.f b/gcc/testsuite/gfortran.dg/pr110221.f
new file mode 100644 (file)
index 0000000..8b57384
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/pr110221.f
@@ -0,0 +1,17 @@
+C PR middle-end/68146
+C { dg-do compile }
+C { dg-options "-O2 -w" }
+C { dg-additional-options "-mavx512f --param vect-partial-vector-usage=2" { target avx512f } }
+      SUBROUTINE CJYVB(V,Z,V0,CBJ,CDJ,CBY,CYY)
+      IMPLICIT DOUBLE PRECISION (A,B,G,O-Y)
+      IMPLICIT COMPLEX*16 (C,Z)
+      DIMENSION CBJ(0:*),CDJ(0:*),CBY(0:*)
+      N=INT(V)
+      CALL GAMMA2(VG,GA)
+      DO 65 K=1,N
+        CBY(K)=CYY
+65    CONTINUE
+      CDJ(0)=V0/Z*CBJ(0)-CBJ(1)
+      DO 70 K=1,N
+70      CDJ(K)=-(K+V0)/Z*CBJ(K)+CBJ(K-1)
+      END

diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
index 4b948c04499749bfbc6809b1847b0729c42cda4e..a6c03fe6442761edac2a1ebc34b6f7e87b0d5be3 100644 (file)
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -8833,6 +8833,16 @@ vect_schedule_slp_node (vec_info *vinfo,
       /* Emit other stmts after the children vectorized defs which is
         earliest possible.  */
       gimple *last_stmt = NULL;
+      if (auto loop_vinfo = dyn_cast <loop_vec_info> (vinfo))
+       if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo)
+           || LOOP_VINFO_FULLY_WITH_LENGTH_P (loop_vinfo))
+         {
+           /* But avoid scheduling internal defs outside of the loop when
+              we might have only implicitly tracked loop mask/len defs.  */
+           gimple_stmt_iterator si
+             = gsi_after_labels (LOOP_VINFO_LOOP (loop_vinfo)->header);
+           last_stmt = gsi_stmt (si);
+         }
       bool seen_vector_def = false;
       FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
        if (SLP_TREE_DEF_TYPE (child) == vect_internal_def)