Optimize VEC_PERM_EXPR with same permutation index and operation

The sequence
     c1 = VEC_PERM_EXPR (a, a, mask)
     c2 = VEC_PERM_EXPR (b, b, mask)
     c3 = c1 op c2
can be optimized to
     c = a op b
     c3 = VEC_PERM_EXPR (c, c, mask)
for all integer vector operation, and float operation with
full permutation.

gcc/ChangeLog:

	PR target/98167
	* match.pd: New perm + vector op patterns for int and fp vector.

gcc/testsuite/ChangeLog:

	PR target/98167
	* gcc.target/i386/pr98167.c: New test.

2 files changed, 98 insertions, 0 deletions

diff --git a/gcc/match.pd b/gcc/match.pd
index 0476753..39edc89 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -8245,3 +8245,57 @@ and,
  (bit_and (negate @0) integer_onep@1)
  (if (!TYPE_OVERFLOW_SANITIZED (type))
   (bit_and @0 @1)))
+
+/* Optimize
+   c1 = VEC_PERM_EXPR (a, a, mask)
+   c2 = VEC_PERM_EXPR (b, b, mask)
+   c3 = c1 op c2
+   -->
+   c = a op b
+   c3 = VEC_PERM_EXPR (c, c, mask)
+   For all integer non-div operations.  */
+(for op (plus minus mult bit_and bit_ior bit_xor
+	 lshift rshift)
+ (simplify
+  (op (vec_perm @0 @0 @2) (vec_perm @1 @1 @2))
+   (if (VECTOR_INTEGER_TYPE_P (type))
+    (vec_perm (op @0 @1) (op @0 @1) @2))))
+
+/* Similar for float arithmetic when permutation constant covers
+   all vector elements.  */
+(for op (plus minus mult)
+ (simplify
+  (op (vec_perm @0 @0 VECTOR_CST@2) (vec_perm @1 @1 VECTOR_CST@2))
+   (if (VECTOR_FLOAT_TYPE_P (type)
+	&& TYPE_VECTOR_SUBPARTS (type).is_constant ())
+    (with
+     {
+       tree perm_cst = @2;
+       vec_perm_builder builder;
+       bool full_perm_p = false;
+       if (tree_to_vec_perm_builder (&builder, perm_cst))
+	 {
+	   unsigned HOST_WIDE_INT nelts;
+
+	   nelts = TYPE_VECTOR_SUBPARTS (type).to_constant ();
+	   /* Create a vec_perm_indices for the VECTOR_CST.  */
+	   vec_perm_indices sel (builder, 1, nelts);
+
+	   /* Check if perm indices covers all vector elements.  */
+	   if (sel.encoding ().encoded_full_vector_p ())
+	     {
+	       auto_sbitmap seen (nelts);
+	       unsigned HOST_WIDE_INT count = 0, i;
+
+	       for (i = 0; i < nelts; i++)
+		 {
+		   if (!bitmap_set_bit (seen, sel[i].to_constant ()))
+		    break;
+		   count++;
+		 }
+	       full_perm_p = count == nelts;
+	     }
+	 }
+      }
+      (if (full_perm_p)
+	(vec_perm (op @0 @1) (op @0 @1) @2))))))
diff --git a/gcc/testsuite/gcc.target/i386/pr98167.c b/gcc/testsuite/gcc.target/i386/pr98167.c
new file mode 100644
index 0000000..40e0ac1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr98167.c
@@ -0,0 +1,44 @@
+/* PR target/98167 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx2" } */
+
+/* { dg-final { scan-assembler-times "vpshufd\t" 8 } } */
+/* { dg-final { scan-assembler-times "vpermilps\t" 3 } } */
+
+#define VEC_PERM_4 \
+  2, 3, 1, 0
+#define VEC_PERM_8 \
+  4, 5, 6, 7, 3, 2, 1, 0
+#define VEC_PERM_16 \
+  8, 9, 10, 11, 12, 13, 14, 15, 7, 6, 5, 4, 3, 2, 1, 0
+
+#define TYPE_PERM_OP(type, size, op, name) \
+  typedef type v##size##s##type __attribute__ ((vector_size(4*size))); \
+  v##size##s##type type##foo##size##i_##name (v##size##s##type a, \
+					      v##size##s##type b) \
+  { \
+    v##size##s##type a1 = __builtin_shufflevector (a, a, \
+						   VEC_PERM_##size); \
+    v##size##s##type b1 = __builtin_shufflevector (b, b, \
+						   VEC_PERM_##size); \
+    return a1 op b1; \
+  }
+
+#define INT_PERMS(op, name) \
+  TYPE_PERM_OP (int, 4, op, name) \
+
+#define FP_PERMS(op, name) \
+  TYPE_PERM_OP (float, 4, op, name) \
+
+INT_PERMS (+, add)
+INT_PERMS (-, sub)
+INT_PERMS (*, mul)
+INT_PERMS (|, ior)
+INT_PERMS (^, xor)
+INT_PERMS (&, and)
+INT_PERMS (<<, shl)
+INT_PERMS (>>, shr)
+FP_PERMS (+, add)
+FP_PERMS (-, sub)
+FP_PERMS (*, mul)
+