[gcc r13-4497] aarch64: Use dup and zip1 for interleaving elements in vector initializer.

[gcc r13-4497] aarch64: Use dup and zip1 for interleaving elements in vector initializer.

[Prathamesh Kulkarni]

https://gcc.gnu.org/g:769370f3e2e04823c8a621d8ffa756dd83ebf21e

commit r13-4497-g769370f3e2e04823c8a621d8ffa756dd83ebf21e
Author: Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org>
Date:   Tue Dec 6 06:51:14 2022 +0530

    aarch64: Use dup and zip1 for interleaving elements in vector initializer.
    
    gcc/ChangeLog:
            * config/aarch64/aarch64.cc (aarch64_expand_vector_init): Use dup
            and zip1 for interleaving elements in vector initializer.
    
    gcc/testsuite/ChangeLog:
            * gcc.target/aarch64/interleave-init-1.c: New test.

Diff:
---
 gcc/config/aarch64/aarch64.cc                      | 32 +++++++++++++++++++
 .../gcc.target/aarch64/interleave-init-1.c         | 37 ++++++++++++++++++++++
 2 files changed, 69 insertions(+)

diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index e97f3b32f7c..dedda68261d 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -22058,6 +22058,38 @@ aarch64_expand_vector_init (rtx target, rtx vals)
       return;
     }
 
+  /* Check for interleaving case.
+     For eg if initializer is (int16x8_t) {x, y, x, y, x, y, x, y}.
+     Generate following code:
+     dup v0.h, x
+     dup v1.h, y
+     zip1 v0.h, v0.h, v1.h
+     for "large enough" initializer.  */
+
+  if (n_elts >= 8)
+    {
+      int i;
+      for (i = 2; i < n_elts; i++)
+	if (!rtx_equal_p (XVECEXP (vals, 0, i), XVECEXP (vals, 0, i % 2)))
+	  break;
+
+      if (i == n_elts)
+	{
+	  machine_mode mode = GET_MODE (target);
+	  rtx dest[2];
+
+	  for (int i = 0; i < 2; i++)
+	    {
+	      rtx x = expand_vector_broadcast (mode, XVECEXP (vals, 0, i));
+	      dest[i] = force_reg (mode, x);
+	    }
+
+	  rtvec v = gen_rtvec (2, dest[0], dest[1]);
+	  emit_set_insn (target, gen_rtx_UNSPEC (mode, v, UNSPEC_ZIP1));
+	  return;
+	}
+    }
+
   enum insn_code icode = optab_handler (vec_set_optab, mode);
   gcc_assert (icode != CODE_FOR_nothing);
 
diff --git a/gcc/testsuite/gcc.target/aarch64/interleave-init-1.c b/gcc/testsuite/gcc.target/aarch64/interleave-init-1.c
new file mode 100644
index 00000000000..ee775048589
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/interleave-init-1.c
@@ -0,0 +1,37 @@
+/* { dg-do compile } */
+/* { dg-options "-O3" } */
+/* { dg-final { check-function-bodies "**" "" "" } } */
+
+#include <arm_neon.h>
+
+/*
+** foo:
+**	...
+**	dup	v[0-9]+\.8h, w[0-9]+
+**	dup	v[0-9]+\.8h, w[0-9]+
+**	zip1	v[0-9]+\.8h, v[0-9]+\.8h, v[0-9]+\.8h
+**	...
+**	ret
+*/
+
+int16x8_t foo(int16_t x, int y)
+{
+  int16x8_t v = (int16x8_t) {x, y, x, y, x, y, x, y}; 
+  return v;
+}
+
+/*
+** foo2:
+**	...
+**	dup	v[0-9]+\.8h, w[0-9]+
+**	movi	v[0-9]+\.8h, 0x1
+**	zip1	v[0-9]+\.8h, v[0-9]+\.8h, v[0-9]+\.8h
+**	...
+**	ret
+*/
+
+int16x8_t foo2(int16_t x) 
+{
+  int16x8_t v = (int16x8_t) {x, 1, x, 1, x, 1, x, 1}; 
+  return v;
+}