tree-optimization/39612 - avoid issueing loads in SM when possible

Currently store-motion emits a load of the value in the loop
preheader even when the original loop does not contain any read
of the reference.  This avoids doing this.  In the conditional
store-motion case we need to mark the sunk stores with no-warning
since the control dependence is too tricky to figure out for
the uninit warning.

2020-05-04  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/39612
	* tree-ssa-loop-im.c (im_mem_ref::loaded): New member.
	(set_ref_loaded_in_loop): New.
	(mark_ref_loaded): Likewise.
	(gather_mem_refs_stmt): Call mark_ref_loaded for loads.
	(execute_sm): Avoid issueing a load when it was not there.
	(execute_sm_if_changed): Avoid issueing warnings for the
	conditional store.

	* gcc.dg/tree-ssa/pr39612.c: New testcase.

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 42c4af762cdf270b2994d00afba8dd6c83ce2e11..61d5ce5ae1f1df673ebcdbce2dac03ebf71a45cf 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,14 @@
+2020-05-04  Richard Biener  <rguenther@suse.de>
+
+       PR tree-optimization/39612
+       * tree-ssa-loop-im.c (im_mem_ref::loaded): New member.
+       (set_ref_loaded_in_loop): New.
+       (mark_ref_loaded): Likewise.
+       (gather_mem_refs_stmt): Call mark_ref_loaded for loads.
+       (execute_sm): Avoid issueing a load when it was not there.
+       (execute_sm_if_changed): Avoid issueing warnings for the
+       conditional store.
+
 2020-05-04  Martin Jambor  <mjambor@suse.cz>
 
        PR ipa/93385

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index bbdd51a33f9b94c0d4566095d3cf129cf0d1394d..341b6741251554dbc432a5bb66a946fd126118ab 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2020-05-04  Richard Biener  <rguenther@suse.de>
+
+       PR tree-optimization/39612
+       * gcc.dg/tree-ssa/pr39612.c: New testcase.
+
 2020-05-04  Uroš Bizjak  <ubizjak@gmail.com>
 
        PR target/94650

diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr39612.c b/gcc/testsuite/gcc.dg/tree-ssa/pr39612.c
new file mode 100644 (file)
index 0000000..884f905
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr39612.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-lim2-details -Wuninitialized" } */
+
+void foo(int *);
+void f2(int dst[3], int R)
+{
+  int i, inter[2];
+
+  for (i = 1; i < R; i++) {
+    if (i & 8)
+      {
+       inter[0] = 1;
+       inter[1] = 1;
+      }
+  }
+
+  foo(inter);
+}
+
+/* { dg-final { scan-tree-dump-times "Executing store motion" 2 "lim2" } } */
+/* { dg-final { scan-tree-dump-not " = inter\\\[\[0-1\]\\\];" "lim2" } } */

diff --git a/gcc/tree-ssa-loop-im.c b/gcc/tree-ssa-loop-im.c
index abd5f702b91ad80f7038e69be7f1f71d19c20098..18e5c18c17eb7472e96a9252d60b5a50698f8f1a 100644 (file)
--- a/gcc/tree-ssa-loop-im.c
+++ b/gcc/tree-ssa-loop-im.c
@@ -127,6 +127,8 @@ public:
 
   bitmap stored;               /* The set of loops in that this memory location
                                   is stored to.  */
+  bitmap loaded;               /* The set of loops in that this memory location
+                                  is loaded from.  */
   vec<mem_ref_loc>             accesses_in_loop;
                                /* The locations of the accesses.  Vector
                                   indexed by the loop number.  */
@@ -1395,6 +1397,7 @@ mem_ref_alloc (ao_ref *mem, unsigned hash, unsigned id)
   ref->ref_decomposed = false;
   ref->hash = hash;
   ref->stored = NULL;
+  ref->loaded = NULL;
   bitmap_initialize (&ref->indep_loop, &lim_bitmap_obstack);
   bitmap_initialize (&ref->dep_loop, &lim_bitmap_obstack);
   ref->accesses_in_loop.create (1);
@@ -1435,6 +1438,27 @@ mark_ref_stored (im_mem_ref *ref, class loop *loop)
     loop = loop_outer (loop);
 }
 
+/* Set the LOOP bit in REF loaded bitmap and allocate that if
+   necessary.  Return whether a bit was changed.  */
+
+static bool
+set_ref_loaded_in_loop (im_mem_ref *ref, class loop *loop)
+{
+  if (!ref->loaded)
+    ref->loaded = BITMAP_ALLOC (&lim_bitmap_obstack);
+  return bitmap_set_bit (ref->loaded, loop->num);
+}
+
+/* Marks reference REF as loaded in LOOP.  */
+
+static void
+mark_ref_loaded (im_mem_ref *ref, class loop *loop)
+{
+  while (loop != current_loops->tree_root
+        && set_ref_loaded_in_loop (ref, loop))
+    loop = loop_outer (loop);
+}
+
 /* Gathers memory references in statement STMT in LOOP, storing the
    information about them in the memory_accesses structure.  Marks
    the vops accessed through unrecognized statements there as
@@ -1571,6 +1595,8 @@ gather_mem_refs_stmt (class loop *loop, gimple *stmt)
       bitmap_set_bit (&memory_accesses.refs_stored_in_loop[loop->num], ref->id);
       mark_ref_stored (ref, loop);
     }
+  else
+    mark_ref_loaded (ref, loop);
   init_lim_data (stmt)->ref = ref->id;
   return;
 }
@@ -1968,6 +1994,8 @@ execute_sm_if_changed (edge ex, tree mem, tree tmp_var, tree flag,
   gsi = gsi_start_bb (then_bb);
   /* Insert actual store.  */
   stmt = gimple_build_assign (unshare_expr (mem), tmp_var);
+  /* Make sure to not warn about maybe-uninit uses of tmp_var here.  */
+  gimple_set_no_warning (stmt, true);
   gsi_insert_after (&gsi, stmt, GSI_CONTINUE_LINKING);
 
   edge e1 = single_succ_edge (new_bb);
@@ -2115,14 +2143,17 @@ execute_sm (class loop *loop, vec<edge> exits, im_mem_ref *ref)
      by move_computations after all dependencies.  */
   gsi = gsi_for_stmt (first_mem_ref_loc (loop, ref)->stmt);
 
-  /* FIXME/TODO: For the multi-threaded variant, we could avoid this
-     load altogether, since the store is predicated by a flag.  We
-     could, do the load only if it was originally in the loop.  */
-  load = gimple_build_assign (tmp_var, unshare_expr (ref->mem.ref));
-  lim_data = init_lim_data (load);
-  lim_data->max_loop = loop;
-  lim_data->tgt_loop = loop;
-  gsi_insert_before (&gsi, load, GSI_SAME_STMT);
+  /* Avoid doing a load if there was no load of the ref in the loop.
+     Esp. when the ref is not always stored we cannot optimize it
+     away later.  */
+  if (ref->loaded && bitmap_bit_p (ref->loaded, loop->num))
+    {
+      load = gimple_build_assign (tmp_var, unshare_expr (ref->mem.ref));
+      lim_data = init_lim_data (load);
+      lim_data->max_loop = loop;
+      lim_data->tgt_loop = loop;
+      gsi_insert_before (&gsi, load, GSI_SAME_STMT);
+    }
 
   if (multi_threaded_model_p)
     {