re PR fortran/92094 (ice in vect_transform_stmt at tree-vect-stmts.c:10921)

2019-10-15  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/92094
	* tree-vect-loop.c (vectorizable_reduction): For nested cycles
	do not adjust the reduction definition def type.
	* tree-vect-stmts.c (vect_transform_stmt): Verify the scalar stmt
	defines the latch argument of the PHI.

	* gfortran.dg/pr92094.f90: New testcase.

From-SVN: r276987

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 40726e9635421ccc06531dd3f0a20a25ce033ca4..6e16ee81e5397ff69ae31c00e6b5c366c7dd9420 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2019-10-15  Richard Biener  <rguenther@suse.de>
+
+       PR tree-optimization/92094
+       * tree-vect-loop.c (vectorizable_reduction): For nested cycles
+       do not adjust the reduction definition def type.
+       * tree-vect-stmts.c (vect_transform_stmt): Verify the scalar stmt
+       defines the latch argument of the PHI.
+
 2019-10-15  Hongyu Wang  <hongtao.wang@intel.com>
 
        PR target/92035

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 34854d29cf75f60dbc3bf575fcee4688db81d8fe..7fbb8dd64e85f9efeaa3bfa466403f113c3d3d44 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2019-10-15  Richard Biener  <rguenther@suse.de>
+
+       PR tree-optimization/92094
+       * gfortran.dg/pr92094.f90: New testcase.
+
 2019-10-15  Hongyu Wang  <hongyu.wang@intel.com>
 
        PR target/92035

diff --git a/gcc/testsuite/gfortran.dg/pr92094.f90 b/gcc/testsuite/gfortran.dg/pr92094.f90
new file mode 100644 (file)
index 0000000..6793391
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/pr92094.f90
@@ -0,0 +1,28 @@
+! { dg-do compile }
+! { dg-options "-O3" }
+      subroutine hesfcn(n, x, h, ldh)
+      integer n,ldh
+      double precision x(n), h(ldh)
+
+      integer i,j,k,kj
+      double precision th,u1,u2,v2
+ 
+      kj = 0
+      do 770 j = 1, n
+         kj = kj - j
+         do 760 k = 1, j
+            kj = kj + 1
+            v2 = 2 * x(k) - 1
+            u1 = 0
+            u2 = 2
+            do 750 i = 1, n
+               h(kj) = h(kj) + u2
+               th = 4 * v2 + u2 - u1
+               u1 = u2
+               u2 = th
+               th = v2 - 1
+  750       continue
+  760    continue
+  770 continue
+
+      end

diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
index de018acefad382dfe7c7a2ef8dd24e1e0fd8fd56..455251070d081d11f5301f7178dc2d62f2f2bb0e 100644 (file)
--- a/gcc/tree-vect-loop.c
+++ b/gcc/tree-vect-loop.c
@@ -5742,20 +5742,9 @@ vectorizable_reduction (stmt_vec_info stmt_info, slp_tree slp_node,
   if (STMT_VINFO_DEF_TYPE (stmt_info) == vect_nested_cycle)
     {
       if (is_a <gphi *> (stmt_info->stmt))
-       {
-         /* Analysis for double-reduction is done on the outer
-            loop PHI, nested cycles have no further restrictions.  */
-         STMT_VINFO_TYPE (stmt_info) = cycle_phi_info_type;
-         /* For nested cycles we want to let regular vectorizable_*
-            routines handle code-generation.  */
-         if (STMT_VINFO_DEF_TYPE (reduc_info) != vect_double_reduction_def)
-           {
-             stmt_info = STMT_VINFO_REDUC_DEF (stmt_info);
-             STMT_VINFO_DEF_TYPE (stmt_info) = vect_internal_def;
-             STMT_VINFO_DEF_TYPE (vect_stmt_to_vectorize (stmt_info))
-               = vect_internal_def;
-           }
-       }
+       /* Analysis for double-reduction is done on the outer
+          loop PHI, nested cycles have no further restrictions.  */
+       STMT_VINFO_TYPE (stmt_info) = cycle_phi_info_type;
       else
        STMT_VINFO_TYPE (stmt_info) = reduc_vec_info_type;
       return true;

diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index e606945d536ad3353b2317aed5b504a89eec9fc3..ff9863f290f281a88f6a74a90f267815430a7e05 100644 (file)
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -10906,13 +10906,16 @@ vect_transform_stmt (stmt_vec_info stmt_info, gimple_stmt_iterator *gsi,
       && STMT_VINFO_REDUC_TYPE (reduc_info) != EXTRACT_LAST_REDUCTION)
     {
       gphi *phi;
+      edge e;
       if (!slp_node
          && (phi = dyn_cast <gphi *>
                      (STMT_VINFO_REDUC_DEF (orig_stmt_info)->stmt))
          && dominated_by_p (CDI_DOMINATORS,
-                            gimple_bb (orig_stmt_info->stmt), gimple_bb (phi)))
+                            gimple_bb (orig_stmt_info->stmt), gimple_bb (phi))
+         && (e = loop_latch_edge (gimple_bb (phi)->loop_father))
+         && (PHI_ARG_DEF_FROM_EDGE (phi, e)
+             == gimple_get_lhs (orig_stmt_info->stmt)))
        {
-         edge e = loop_latch_edge (gimple_bb (phi)->loop_father);
          stmt_vec_info phi_info
            = STMT_VINFO_VEC_STMT (STMT_VINFO_REDUC_DEF (orig_stmt_info));
          stmt_vec_info vec_stmt = STMT_VINFO_VEC_STMT (stmt_info);
@@ -10932,7 +10935,7 @@ vect_transform_stmt (stmt_vec_info stmt_info, gimple_stmt_iterator *gsi,
        {
          slp_tree phi_node = slp_node_instance->reduc_phis;
          gphi *phi = as_a <gphi *> (SLP_TREE_SCALAR_STMTS (phi_node)[0]->stmt);
-         edge e = loop_latch_edge (gimple_bb (phi)->loop_father);
+         e = loop_latch_edge (gimple_bb (phi)->loop_father);
          gcc_assert (SLP_TREE_VEC_STMTS (phi_node).length ()
                      == SLP_TREE_VEC_STMTS (slp_node).length ());
          for (unsigned i = 0; i < SLP_TREE_VEC_STMTS (phi_node).length (); ++i)