From 90518c07dfb770b680fd8bdba76dd1b39103277d Mon Sep 17 00:00:00 2001
From: Richard Biener <rguenther@suse.de>
Date: Fri, 10 Nov 2023 12:39:11 +0100
Subject: [PATCH 151/157] [Backport][SME] tree-optimization/110221 - SLP and
 loop mask/len

Reference: https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=e5f1956498251a4973d52c8aad3faf34d0443169

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.
---
 gcc/testsuite/gfortran.dg/pr110221.f | 17 +++++++++++++++++
 gcc/tree-vect-slp.cc                 | 10 ++++++++++
 2 files changed, 27 insertions(+)
 create mode 100644 gcc/testsuite/gfortran.dg/pr110221.f

diff --git a/gcc/testsuite/gfortran.dg/pr110221.f b/gcc/testsuite/gfortran.dg/pr110221.f
new file mode 100644
index 000000000..8b5738431
--- /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 d02f0ce37..e3e246977 100644
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -8531,6 +8531,16 @@ 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 = *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)
-- 
2.33.0