Optimize nested permutation to single VEC_PERM_EXPR [PR54346]

        This patch implemented the optimization in PR 54346, which Merges

	c = VEC_PERM_EXPR <a, b, VCST0>;
        d = VEC_PERM_EXPR <c, c, VCST1>;
                to
        d = VEC_PERM_EXPR <a, b, NEW_VCST>;

	Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}
        tree-ssa/forwprop-19.c fail to pass but I'm not sure whether it
        is ok to removed it.

gcc/ChangeLog:

	PR tree-optimization/54346
	* match.pd: Merge the index of VCST then generates the new vec_perm.

gcc/testsuite/ChangeLog:

	* gcc.dg/pr54346.c: New test.

Co-authored-by: liuhongt <hongtao.liu@intel.com>

2 files changed, 54 insertions, 0 deletions

diff --git a/gcc/match.pd b/gcc/match.pd
index 345bcb7..3550c16 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -8086,6 +8086,47 @@ and,
   (minus (mult (vec_perm @1 @1 @3) @2) @4)))
 
 
+/* Merge
+   c = VEC_PERM_EXPR <a, b, VCST0>;
+   d = VEC_PERM_EXPR <c, c, VCST1>;
+   to
+   d = VEC_PERM_EXPR <a, b, NEW_VCST>;  */
+
+(simplify
+ (vec_perm (vec_perm@0 @1 @2 VECTOR_CST@3) @0 VECTOR_CST@4)
+ (with
+  {
+    if (!TYPE_VECTOR_SUBPARTS (type).is_constant ())
+      return NULL_TREE;
+
+    tree op0;
+    machine_mode result_mode = TYPE_MODE (type);
+    machine_mode op_mode = TYPE_MODE (TREE_TYPE (@1));
+    int nelts = TYPE_VECTOR_SUBPARTS (type).to_constant ();
+    vec_perm_builder builder0;
+    vec_perm_builder builder1;
+    vec_perm_builder builder2 (nelts, nelts, 1);
+
+    if (!tree_to_vec_perm_builder (&builder0, @3)
+	|| !tree_to_vec_perm_builder (&builder1, @4))
+      return NULL_TREE;
+
+    vec_perm_indices sel0 (builder0, 2, nelts);
+    vec_perm_indices sel1 (builder1, 1, nelts);
+
+    for (int i = 0; i < nelts; i++)
+      builder2.quick_push (sel0[sel1[i].to_constant ()]);
+
+    vec_perm_indices sel2 (builder2, 2, nelts);
+
+    if (!can_vec_perm_const_p (result_mode, op_mode, sel2, false))
+      return NULL_TREE;
+
+    op0 = vec_perm_indices_to_tree (TREE_TYPE (@4), sel2);
+  }
+  (vec_perm @1 @2 { op0; })))
+
+
 /* Match count trailing zeroes for simplify_count_trailing_zeroes in fwprop.
    The canonical form is array[((x & -x) * C) >> SHIFT] where C is a magic
    constant which when multiplied by a power of 2 contains a unique value
diff --git a/gcc/testsuite/gcc.dg/pr54346.c b/gcc/testsuite/gcc.dg/pr54346.c
new file mode 100755
index 0000000..63611ab
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/pr54346.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-O -fdump-tree-dse1" } */
+
+typedef int veci __attribute__ ((vector_size (4 * sizeof (int))));
+
+void fun (veci a, veci b, veci *i)
+{
+  veci c = __builtin_shuffle (a, b, __extension__ (veci) {1, 4, 2, 7});
+  *i = __builtin_shuffle (c, __extension__ (veci) { 7, 2, 1, 5 });
+}
+
+/* { dg-final { scan-tree-dump "VEC_PERM_EXPR.*{ 3, 6, 0, 0 }" "dse1" } } */
+/* { dg-final { scan-tree-dump-times "VEC_PERM_EXPR" 1 "dse1" } } */