aarch64: Add __builtin_aarch64_chkfeat

Builtin for chkfeat: the input argument is used to initialize x16 then
execute chkfeat and return the updated x16.

Note: the ACLE __chkfeat(x) will flip the bits to be more intuitive
(xor the input to output), but for the builtin that seems unnecessary
complication.

gcc/ChangeLog:

	* config/aarch64/aarch64-builtins.cc (enum aarch64_builtins):
	Define AARCH64_BUILTIN_CHKFEAT.
	(aarch64_general_init_builtins): Handle chkfeat.
	(aarch64_general_expand_builtin): Handle chkfeat.
	Co-authored-by: Richard Sandiford <richard.sandiford@arm.com>

diff --git a/gcc/config/aarch64/aarch64-builtins.cc b/gcc/config/aarch64/aarch64-builtins.cc
index 97bde7c15d3bcb9cca6ff69567007060670cc568..e693a14f4f3c3b6faef7b898a07dd493a8469ad7 100644 (file)
--- a/gcc/config/aarch64/aarch64-builtins.cc
+++ b/gcc/config/aarch64/aarch64-builtins.cc
@@ -876,6 +876,8 @@ enum aarch64_builtins
   AARCH64_PLDX,
   AARCH64_PLI,
   AARCH64_PLIX,
+  /* Armv8.9-A / Armv9.4-A builtins.  */
+  AARCH64_BUILTIN_CHKFEAT,
   AARCH64_BUILTIN_MAX
 };
 
@@ -2279,6 +2281,12 @@ aarch64_general_init_builtins (void)
   if (!TARGET_ILP32)
     aarch64_init_pauth_hint_builtins ();
 
+  tree ftype_chkfeat
+    = build_function_type_list (uint64_type_node, uint64_type_node, NULL);
+  aarch64_builtin_decls[AARCH64_BUILTIN_CHKFEAT]
+    = aarch64_general_add_builtin ("__builtin_aarch64_chkfeat", ftype_chkfeat,
+                                  AARCH64_BUILTIN_CHKFEAT);
+
   if (in_lto_p)
     handle_arm_acle_h ();
 }
@@ -3498,6 +3506,15 @@ aarch64_general_expand_builtin (unsigned int fcode, tree exp, rtx target,
     case AARCH64_PLIX:
       aarch64_expand_prefetch_builtin (exp, fcode);
       return target;
+
+    case AARCH64_BUILTIN_CHKFEAT:
+      {
+       rtx x16_reg = gen_rtx_REG (DImode, R16_REGNUM);
+       op0 = expand_normal (CALL_EXPR_ARG (exp, 0));
+       emit_move_insn (x16_reg, op0);
+       expand_insn (CODE_FOR_aarch64_chkfeat, 0, 0);
+       return copy_to_reg (x16_reg);
+      }
     }
 
   if (fcode >= AARCH64_SIMD_BUILTIN_BASE && fcode <= AARCH64_SIMD_BUILTIN_MAX)