tree-optimization/94949 - fix load eliding in SM

This fixes the case of not using the multithreaded model when
only conditionally storing to the destination.  We cannot elide
the load in this case.

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

	PR tree-optimization/94949
	* tree-ssa-loop-im.c (execute_sm): Check whether we use
	the multithreaded model or always compute the stored value
	before eliding a load.

	* gcc.dg/torture/pr94949.c: New testcase.

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 6a419757bf897f8ecaf3930062ca5d80b1c6aa41..2267a63bca13e7821ee2172bf1d019a04c5db21c 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,10 @@
+2020-05-05  Richard Biener  <rguenther@suse.de>
+
+       PR tree-optimization/94949
+       * tree-ssa-loop-im.c (execute_sm): Check whether we use
+       the multithreaded model or always compute the stored value
+       before eliding a load.
+
 2020-05-05  Alex Coplan  <alex.coplan@arm.com>
 
        * config/aarch64/aarch64.md (*one_cmpl_zero_extend): New.

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index e06bcf862123acda2bebcee804422aa22bc25050..2ffa0f8f43416fcc429c7babe41f3246b5c146df 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2020-05-05  Richard Biener  <rguenther@suse.de>
+
+       PR tree-optimization/94949
+       * gcc.dg/torture/pr94949.c: New testcase.
+
 2020-05-05  Alex Coplan  <alex.coplan@arm.com>
 
        * gcc.target/aarch64/mvn_zero_ext.c: New test.

diff --git a/gcc/testsuite/gcc.dg/torture/pr94949.c b/gcc/testsuite/gcc.dg/torture/pr94949.c
new file mode 100644 (file)
index 0000000..6182d77
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr94949.c
@@ -0,0 +1,17 @@
+/* { dg-do run } */
+/* { dg-additional-options "-fallow-store-data-races" } */
+
+static int x = 1;
+static volatile int y = -1;
+int
+main()
+{
+  for (int i = 0; i < 128; ++i)
+    {
+      if (i == y)
+       x = i;
+    }
+  if (x != 1)
+    __builtin_abort ();
+  return 0;
+}

diff --git a/gcc/tree-ssa-loop-im.c b/gcc/tree-ssa-loop-im.c
index 18e5c18c17eb7472e96a9252d60b5a50698f8f1a..554dd4be5bbcfb1496c8111e5cce1d61e23d98ab 100644 (file)
--- a/gcc/tree-ssa-loop-im.c
+++ b/gcc/tree-ssa-loop-im.c
@@ -2128,9 +2128,9 @@ execute_sm (class loop *loop, vec<edge> exits, im_mem_ref *ref)
   fmt_data.orig_loop = loop;
   for_each_index (&ref->mem.ref, force_move_till, &fmt_data);
 
+  bool always_stored = ref_always_accessed_p (loop, ref, true);
   if (bb_in_transaction (loop_preheader_edge (loop)->src)
-      || (! flag_store_data_races
-         && ! ref_always_accessed_p (loop, ref, true)))
+      || (! flag_store_data_races && ! always_stored))
     multi_threaded_model_p = true;
 
   if (multi_threaded_model_p)
@@ -2145,8 +2145,10 @@ execute_sm (class loop *loop, vec<edge> exits, im_mem_ref *ref)
 
   /* 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))
+     away later.  But when it is not always stored we must use a conditional
+     store then.  */
+  if ((!always_stored && !multi_threaded_model_p)
+      || (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);