arm: [MVE intrinsics] add viddup shape

This patch adds the viddup shape description for vidup and vddup.

This requires the addition of report_not_one_of and
function_checker::require_immediate_one_of to
gcc/config/arm/arm-mve-builtins.cc (they are copies of the aarch64 SVE
counterpart).

This patch also introduces MODE_wb.

2024-08-21  Christophe Lyon  <christophe.lyon@linaro.org>

	gcc/

	* config/arm/arm-mve-builtins-shapes.cc (viddup): New.
	* config/arm/arm-mve-builtins-shapes.h (viddup): New.
	* config/arm/arm-mve-builtins.cc (report_not_one_of): New.
	(function_checker::require_immediate_one_of): New.
	* config/arm/arm-mve-builtins.def (wb): New mode.
	* config/arm/arm-mve-builtins.h (function_checker) Add
	require_immediate_one_of.

gcc/config/arm/arm-mve-builtins-shapes.cc

@@ -2191,6 +2191,91 @@ struct vcvtx_def : public overloaded_base<0>
 };
 SHAPE (vcvtx)
 
+/* <T0>_t vfoo[_n]_t0(uint32_t, const int)
+   <T0>_t vfoo[_wb]_t0(uint32_t *, const int)
+
+   Shape for vector increment or decrement and duplicate operations that take
+   an integer or pointer to integer first argument and an immediate, and
+   produce a vector.
+
+   Check that 'imm' is one of 1, 2, 4 or 8.
+
+   Example: vddupq.
+   uint8x16_t [__arm_]vddupq[_n]_u8(uint32_t a, const int imm)
+   uint8x16_t [__arm_]vddupq[_wb]_u8(uint32_t *a, const int imm)
+   uint8x16_t [__arm_]vddupq_m[_n_u8](uint8x16_t inactive, uint32_t a, const int imm, mve_pred16_t p)
+   uint8x16_t [__arm_]vddupq_m[_wb_u8](uint8x16_t inactive, uint32_t *a, const int imm, mve_pred16_t p)
+   uint8x16_t [__arm_]vddupq_x[_n]_u8(uint32_t a, const int imm, mve_pred16_t p)
+   uint8x16_t [__arm_]vddupq_x[_wb]_u8(uint32_t *a, const int imm, mve_pred16_t p)  */
+struct viddup_def : public overloaded_base<0>
+{
+  bool
+  explicit_type_suffix_p (unsigned int i, enum predication_index pred,
+			  enum mode_suffix_index,
+			  type_suffix_info) const override
+  {
+    return ((i == 0) && (pred != PRED_m));
+  }
+
+  bool
+  skip_overload_p (enum predication_index, enum mode_suffix_index mode) const override
+  {
+    /* For MODE_wb, share the overloaded instance with MODE_n.  */
+    if (mode == MODE_wb)
+      return true;
+
+    return false;
+  }
+
+  void
+  build (function_builder &b, const function_group_info &group,
+	 bool preserve_user_namespace) const override
+  {
+    b.add_overloaded_functions (group, MODE_none, preserve_user_namespace);
+    build_all (b, "v0,su32,su64", group, MODE_n, preserve_user_namespace);
+    build_all (b, "v0,as,su64", group, MODE_wb, preserve_user_namespace);
+  }
+
+  tree
+  resolve (function_resolver &r) const override
+  {
+    unsigned int i, nargs;
+    type_suffix_index type_suffix = NUM_TYPE_SUFFIXES;
+    if (!r.check_gp_argument (2, i, nargs))
+      return error_mark_node;
+
+    type_suffix = r.type_suffix_ids[0];
+    /* With PRED_m, ther is no type suffix, so infer it from the first (inactive)
+       argument.  */
+    if (type_suffix == NUM_TYPE_SUFFIXES)
+      type_suffix = r.infer_vector_type (0);
+
+    unsigned int last_arg = i - 1;
+    /* Check that last_arg is either scalar or pointer.  */
+    if (!r.scalar_argument_p (last_arg))
+      return error_mark_node;
+
+    if (!r.require_integer_immediate (last_arg + 1))
+      return error_mark_node;
+
+    /* With MODE_n we expect a scalar, with MODE_wb we expect a pointer.  */
+    mode_suffix_index mode_suffix;
+    if (POINTER_TYPE_P (r.get_argument_type (last_arg)))
+      mode_suffix = MODE_wb;
+    else
+      mode_suffix = MODE_n;
+
+    return r.resolve_to (mode_suffix, type_suffix);
+  }
+
+  bool
+  check (function_checker &c) const override
+  {
+    return c.require_immediate_one_of (1, 1, 2, 4, 8);
+  }
+};
+SHAPE (viddup)
+
 /* <T0>_t vfoo[_t0](<T0>_t, <T0>_t, mve_pred16_t)
 
    i.e. a version of the standard ternary shape in which

gcc/config/arm/arm-mve-builtins-shapes.h

@@ -82,6 +82,7 @@ namespace arm_mve
     extern const function_shape *const vcvt_f16_f32;
     extern const function_shape *const vcvt_f32_f16;
     extern const function_shape *const vcvtx;
+    extern const function_shape *const viddup;
     extern const function_shape *const vpsel;
 
   } /* end namespace arm_mve::shapes */

gcc/config/arm/arm-mve-builtins.cc

@@ -630,6 +630,20 @@ report_not_enum (location_t location, tree fndecl, unsigned int argno,
 	    " a valid %qT value", actual, argno + 1, fndecl, enumtype);
 }
 
+/* Report that LOCATION has a call to FNDECL in which argument ARGNO has
+   the value ACTUAL, whereas the function requires one of VALUE0..3.
+   ARGNO counts from zero.  */
+static void
+report_not_one_of (location_t location, tree fndecl, unsigned int argno,
+		   HOST_WIDE_INT actual, HOST_WIDE_INT value0,
+		   HOST_WIDE_INT value1, HOST_WIDE_INT value2,
+		   HOST_WIDE_INT value3)
+{
+  error_at (location, "passing %wd to argument %d of %qE, which expects"
+	    " %wd, %wd, %wd or %wd", actual, argno + 1, fndecl, value0, value1,
+	    value2, value3);
+}
+
 /* Checks that the mve.fp extension is enabled, given that REQUIRES_FLOAT
    indicates whether it is required or not for function FNDECL.
    Report an error against LOCATION if not.  */
@@ -1969,6 +1983,36 @@ function_checker::require_immediate_enum (unsigned int rel_argno, tree type)
   return false;
 }
 
+/* Check that argument REL_ARGNO is an integer constant expression that
+   has one of the given values.  */
+bool
+function_checker::require_immediate_one_of (unsigned int rel_argno,
+					    HOST_WIDE_INT value0,
+					    HOST_WIDE_INT value1,
+					    HOST_WIDE_INT value2,
+					    HOST_WIDE_INT value3)
+{
+  unsigned int argno = m_base_arg + rel_argno;
+  if (!argument_exists_p (argno))
+    return true;
+
+  HOST_WIDE_INT actual;
+  if (!require_immediate (argno, actual))
+    return false;
+
+  if (actual != value0
+      && actual != value1
+      && actual != value2
+      && actual != value3)
+    {
+      report_not_one_of (location, fndecl, argno, actual,
+			 value0, value1, value2, value3);
+      return false;
+    }
+
+  return true;
+}
+
 /* Check that argument REL_ARGNO is an integer constant expression in the
    range [MIN, MAX].  REL_ARGNO counts from the end of the predication
    arguments.  */

gcc/config/arm/arm-mve-builtins.def

@@ -36,6 +36,7 @@
 DEF_MVE_MODE (n, none, none, none)
 DEF_MVE_MODE (offset, none, none, bytes)
 DEF_MVE_MODE (r, none, none, none)
+DEF_MVE_MODE (wb, none, none, none)
 
 #define REQUIRES_FLOAT false
 DEF_MVE_TYPE (mve_pred16_t, boolean_type_node)

gcc/config/arm/arm-mve-builtins.h

@@ -433,6 +433,8 @@ class function_checker : public function_call_info
 
   bool require_immediate_enum (unsigned int, tree);
   bool require_immediate_lane_index (unsigned int, unsigned int = 1);
+  bool require_immediate_one_of (unsigned int, HOST_WIDE_INT, HOST_WIDE_INT,
+				 HOST_WIDE_INT, HOST_WIDE_INT);
   bool require_immediate_range (unsigned int, HOST_WIDE_INT, HOST_WIDE_INT);
 
   bool check ();