RISC-V: Combine vec_duplicate + vxor.vv to vxor.vx on GR2VR cost

This patch would like to combine the vec_duplicate + vxor.vv to the
vxor.vx.  From example as below code.  The related pattern will depend
on the cost of vec_duplicate from GR2VR.  Then the late-combine will
take action if the cost of GR2VR is zero, and reject the combination
if the GR2VR cost is greater than zero.

Assume we have example code like below, GR2VR cost is 0.

  #define DEF_VX_BINARY(T, OP)                                        \
  void                                                                \
  test_vx_binary (T * restrict out, T * restrict in, T x, unsigned n) \
  {                                                                   \
    for (unsigned i = 0; i < n; i++)                                  \
      out[i] = in[i] OP x;                                            \
  }

  DEF_VX_BINARY(int32_t, |)

Before this patch:
  10   │ test_vx_binary_or_int32_t_case_0:
  11   │     beq a3,zero,.L8
  12   │     vsetvli a5,zero,e32,m1,ta,ma
  13   │     vmv.v.x v2,a2
  14   │     slli    a3,a3,32
  15   │     srli    a3,a3,32
  16   │ .L3:
  17   │     vsetvli a5,a3,e32,m1,ta,ma
  18   │     vle32.v v1,0(a1)
  19   │     slli    a4,a5,2
  20   │     sub a3,a3,a5
  21   │     add a1,a1,a4
  22   │     vxor.vv v1,v1,v2
  23   │     vse32.v v1,0(a0)
  24   │     add a0,a0,a4
  25   │     bne a3,zero,.L3

After this patch:
  10   │ test_vx_binary_or_int32_t_case_0:
  11   │     beq a3,zero,.L8
  12   │     slli    a3,a3,32
  13   │     srli    a3,a3,32
  14   │ .L3:
  15   │     vsetvli a5,a3,e32,m1,ta,ma
  16   │     vle32.v v1,0(a1)
  17   │     slli    a4,a5,2
  18   │     sub a3,a3,a5
  19   │     add a1,a1,a4
  20   │     vxor.vx v1,v1,a2
  21   │     vse32.v v1,0(a0)
  22   │     add a0,a0,a4
  23   │     bne a3,zero,.L3

The below test suites are passed for this patch.
* The rv64gcv fully regression test.

gcc/ChangeLog:

	* config/riscv/riscv-v.cc (expand_vx_binary_vec_dup_vec): Add
	new case for XOR op.
	(expand_vx_binary_vec_vec_dup): Diito.
	* config/riscv/riscv.cc (riscv_rtx_costs): Ditto.
	* config/riscv/vector-iterators.md: Add new op or to no_shift_vx_ops.

Signed-off-by: Pan Li <pan2.li@intel.com>

3 files changed, 4 insertions, 1 deletions

diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index a6ee582..eedcda2 100644
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -5535,6 +5535,7 @@ expand_vx_binary_vec_dup_vec (rtx op_0, rtx op_1, rtx op_2,
     case PLUS:
     case AND:
     case IOR:
+    case XOR:
       icode = code_for_pred_scalar (code, mode);
       break;
     case MINUS:
@@ -5563,6 +5564,7 @@ expand_vx_binary_vec_vec_dup (rtx op_0, rtx op_1, rtx op_2,
     case MINUS:
     case AND:
     case IOR:
+    case XOR:
       icode = code_for_pred_scalar (code, mode);
       break;
     default:
diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index eaaca36..87f2052 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -3918,6 +3918,7 @@ riscv_rtx_costs (rtx x, machine_mode mode, int outer_code, int opno ATTRIBUTE_UN
 	      case MINUS:
 	      case AND:
 	      case IOR:
+	      case XOR:
 		{
 		  rtx op_0 = XEXP (x, 0);
 		  rtx op_1 = XEXP (x, 1);
diff --git a/gcc/config/riscv/vector-iterators.md b/gcc/config/riscv/vector-iterators.md
index a50b7fd..77d72a7 100644
--- a/gcc/config/riscv/vector-iterators.md
+++ b/gcc/config/riscv/vector-iterators.md
@@ -4042,7 +4042,7 @@
 ])
 
 (define_code_iterator any_int_binop_no_shift_vx [
-  plus minus and ior
+  plus minus and ior xor
 ])
 
 (define_code_iterator any_int_unop [neg not])