bswap: Fix up recent vector CONSTRUCTOR optimization [PR98568]

As the testcase shows, bswap can match even byte-swapping or indentity
from low part of some wider SSA_NAME.
For bswap replacement other than for vector CONSTRUCTOR the code has been
using NOP_EXPR casts if the types weren't compatible, but for vectors
we need to use VIEW_CONVERT_EXPR.  The problem with the latter is that
we require that it has the same size, which isn't guaranteed, so this patch
in those cases first adds a narrowing NOP_EXPR cast and only afterwards
does a VIEW_CONVERT_EXPR.

2021-01-07  Jakub Jelinek  <jakub@redhat.com>

	PR tree-optimization/98568
	* gimple-ssa-store-merging.c (bswap_view_convert): New function.
	(bswap_replace): Use it.

	* g++.dg/torture/pr98568.C: New test.

2 files changed, 59 insertions, 3 deletions

diff --git a/gcc/gimple-ssa-store-merging.c b/gcc/gimple-ssa-store-merging.c
index 4577647c..f0f4a06 100644
--- a/gcc/gimple-ssa-store-merging.c
+++ b/gcc/gimple-ssa-store-merging.c
@@ -978,6 +978,25 @@ public:
 
 }; // class pass_optimize_bswap
 
+/* Helper function for bswap_replace.  Build VIEW_CONVERT_EXPR from
+   VAL to TYPE.  If VAL has different type size, emit a NOP_EXPR cast
+   first.  */
+
+static tree
+bswap_view_convert (gimple_stmt_iterator *gsi, tree type, tree val)
+{
+  gcc_assert (INTEGRAL_TYPE_P (TREE_TYPE (val)));
+  if (TYPE_SIZE (type) != TYPE_SIZE (TREE_TYPE (val)))
+    {
+      HOST_WIDE_INT prec = TREE_INT_CST_LOW (TYPE_SIZE (type));
+      tree itype = build_nonstandard_integer_type (prec, 1);
+      gimple *g = gimple_build_assign (make_ssa_name (itype), NOP_EXPR, val);
+      gsi_insert_before (gsi, g, GSI_SAME_STMT);
+      val = gimple_assign_lhs (g);
+    }
+  return build1 (VIEW_CONVERT_EXPR, type, val);
+}
+
 /* Perform the bswap optimization: replace the expression computed in the rhs
    of gsi_stmt (GSI) (or if NULL add instead of replace) by an equivalent
    bswap, load or load + bswap expression.
@@ -1100,7 +1119,7 @@ bswap_replace (gimple_stmt_iterator gsi, gimple *ins_stmt, tree fndecl,
 	      gimple_set_vuse (load_stmt, n->vuse);
 	      gsi_insert_before (&gsi, load_stmt, GSI_SAME_STMT);
 	      if (conv_code == VIEW_CONVERT_EXPR)
-		val_tmp = build1 (VIEW_CONVERT_EXPR, TREE_TYPE (tgt), val_tmp);
+		val_tmp = bswap_view_convert (&gsi, TREE_TYPE (tgt), val_tmp);
 	      gimple_assign_set_rhs_with_ops (&gsi, conv_code, val_tmp);
 	      update_stmt (cur_stmt);
 	    }
@@ -1144,7 +1163,7 @@ bswap_replace (gimple_stmt_iterator gsi, gimple *ins_stmt, tree fndecl,
 	  if (!is_gimple_val (src))
 	    return NULL_TREE;
 	  if (conv_code == VIEW_CONVERT_EXPR)
-	    src = build1 (VIEW_CONVERT_EXPR, TREE_TYPE (tgt), src);
+	    src = bswap_view_convert (&gsi, TREE_TYPE (tgt), src);
 	  g = gimple_build_assign (tgt, conv_code, src);
 	}
       else if (cur_stmt)
@@ -1227,7 +1246,7 @@ bswap_replace (gimple_stmt_iterator gsi, gimple *ins_stmt, tree fndecl,
       tmp = make_temp_ssa_name (bswap_type, NULL, "bswapdst");
       tree atmp = tmp;
       if (conv_code == VIEW_CONVERT_EXPR)
-	atmp = build1 (VIEW_CONVERT_EXPR, TREE_TYPE (tgt), tmp);
+	atmp = bswap_view_convert (&gsi, TREE_TYPE (tgt), tmp);
       convert_stmt = gimple_build_assign (tgt, conv_code, atmp);
       gsi_insert_after (&gsi, convert_stmt, GSI_SAME_STMT);
     }
diff --git a/gcc/testsuite/g++.dg/torture/pr98568.C b/gcc/testsuite/g++.dg/torture/pr98568.C
new file mode 100644
index 0000000..5c20223
--- /dev/null
+++ b/gcc/testsuite/g++.dg/torture/pr98568.C
@@ -0,0 +1,37 @@
+// PR tree-optimization/98568
+// { dg-do compile }
+
+char a[2];
+char b[4];
+
+void
+foo (int x)
+{
+  a[1] = x >> 8;
+  a[0] = x;
+}
+
+void
+bar (long long x)
+{
+  b[3] = x >> 24;
+  b[2] = x >> 16;
+  b[1] = x >> 8;
+  b[0] = x;
+}
+
+void
+baz (int x)
+{
+  a[0] = x >> 8;
+  a[1] = x;
+}
+
+void
+qux (long long x)
+{
+  b[0] = x >> 24;
+  b[1] = x >> 16;
+  b[2] = x >> 8;
+  b[3] = x;
+}