[OpenCL] Add cl_khr_subgroup_rotate builtins

[svenvh]

Summary

Add the builtins for the new OpenCL extension. The specification is at: https://www.khronos.org/registry/OpenCL/specs/3.0-unified/html/OpenCL_Ext.html#cl_khr_subgroup_rotate

[Anastasia]

LGTM! I imagine tablegen side is being tested automatically?

Btw do we need to set the feature macro for SPIR/SPIR-V target and then test it too?

[svenvh]

Added macro and macro test. Added reference to Extension spec section.

[svenvh]

In D124256#3474043, @Anastasia wrote:

LGTM! I imagine tablegen side is being tested automatically?

The TableGen definitions are tested by clang/test/Headers/opencl-builtins.cl

Btw do we need to set the feature macro for SPIR/SPIR-V target and then test it too?

Good point! Added.

clang/lib/Headers/opencl-c-base.h

 #if defined(__SPIR__) || defined(__SPIRV__)
 #define cl_khr_subgroup_extended_types 1
 #define cl_khr_subgroup_non_uniform_vote 1
 #define cl_khr_subgroup_ballot 1
 #define cl_khr_subgroup_non_uniform_arithmetic 1
 #define cl_khr_subgroup_shuffle 1
 #define cl_khr_subgroup_shuffle_relative 1
 #define cl_khr_subgroup_clustered_reduce 1
+#define cl_khr_subgroup_rotate 1
 #define cl_khr_extended_bit_ops 1
 #define cl_khr_integer_dot_product 1
 #define __opencl_c_integer_dot_product_input_4x8bit 1
 #define __opencl_c_integer_dot_product_input_4x8bit_packed 1
 #define cl_ext_float_atomics 1
 #ifdef cl_khr_fp16
 #define __opencl_c_ext_fp16_global_atomic_load_store 1
 #define __opencl_c_ext_fp16_local_atomic_load_store 1

clang/lib/Headers/opencl-c.h

 int __ovld __cnfn dot_4x8packed_su_int(uint, uint);
 
 uint __ovld __cnfn dot_acc_sat_4x8packed_uu_uint(uint, uint, uint);
 int __ovld __cnfn dot_acc_sat_4x8packed_ss_int(uint, uint, int);
 int __ovld __cnfn dot_acc_sat_4x8packed_us_int(uint, uint, int);
 int __ovld __cnfn dot_acc_sat_4x8packed_su_int(uint, uint, int);
 #endif // __opencl_c_integer_dot_product_input_4x8bit_packed
 
+#if defined(cl_khr_subgroup_rotate)
+char __ovld __conv sub_group_rotate(char, int);
+uchar __ovld __conv sub_group_rotate(uchar, int);
+short __ovld __conv sub_group_rotate(short, int);
+ushort __ovld __conv sub_group_rotate(ushort, int);
+int __ovld __conv sub_group_rotate(int, int);
+uint __ovld __conv sub_group_rotate(uint, int);
+long __ovld __conv sub_group_rotate(long, int);
+ulong __ovld __conv sub_group_rotate(ulong, int);
+float __ovld __conv sub_group_rotate(float, int);
+#if defined(cl_khr_fp64)
+double __ovld __conv sub_group_rotate(double, int);
+#endif // cl_khr_fp64
+#if defined(cl_khr_fp16)
+half __ovld __conv sub_group_rotate(half, int);
+#endif // cl_khr_fp16
+
+char __ovld __conv sub_group_clustered_rotate(char, int, uint);
+uchar __ovld __conv sub_group_clustered_rotate(uchar, int, uint);
+short __ovld __conv sub_group_clustered_rotate(short, int, uint);
+ushort __ovld __conv sub_group_clustered_rotate(ushort, int, uint);
+int __ovld __conv sub_group_clustered_rotate(int, int, uint);
+uint __ovld __conv sub_group_clustered_rotate(uint, int, uint);
+long __ovld __conv sub_group_clustered_rotate(long, int, uint);
+ulong __ovld __conv sub_group_clustered_rotate(ulong, int, uint);
+float __ovld __conv sub_group_clustered_rotate(float, int, uint);
+#if defined(cl_khr_fp64)
+double __ovld __conv sub_group_clustered_rotate(double, int, uint);
+#endif // cl_khr_fp64
+#if defined(cl_khr_fp16)
+half __ovld __conv sub_group_clustered_rotate(half, int, uint);
+#endif // cl_khr_fp16
+#endif // cl_khr_subgroup_rotate
+
 #if defined(cl_intel_subgroups)
 // Intel-Specific Sub Group Functions
 float   __ovld __conv intel_sub_group_shuffle( float , uint );
 float2  __ovld __conv intel_sub_group_shuffle( float2, uint );
 float3  __ovld __conv intel_sub_group_shuffle( float3, uint );
 float4  __ovld __conv intel_sub_group_shuffle( float4, uint );
 float8  __ovld __conv intel_sub_group_shuffle( float8, uint );
 float16 __ovld __conv intel_sub_group_shuffle( float16, uint );

clang/lib/Sema/OpenCLBuiltins.td

let Extension = FunctionExtension<"__opencl_c_integer_dot_product_input_4x8bit_packed"> in {
   def : Builtin<"dot_4x8packed_su_int", [Int, UInt, UInt], Attr.Const>;
 
   def : Builtin<"dot_acc_sat_4x8packed_uu_uint", [UInt, UInt, UInt, UInt], Attr.Const>;
   def : Builtin<"dot_acc_sat_4x8packed_ss_int", [Int, UInt, UInt, Int], Attr.Const>;
   def : Builtin<"dot_acc_sat_4x8packed_us_int", [Int, UInt, UInt, Int], Attr.Const>;
   def : Builtin<"dot_acc_sat_4x8packed_su_int", [Int, UInt, UInt, Int], Attr.Const>;
 }
 
+// Section 48.3 - cl_khr_subgroup_rotate
+let Extension = FunctionExtension<"cl_khr_subgroup_rotate"> in {
+  def : Builtin<"sub_group_rotate", [AGenType1, AGenType1, Int], Attr.Convergent>;
+  def : Builtin<"sub_group_clustered_rotate", [AGenType1, AGenType1, Int, UInt], Attr.Convergent>;
+}
+
 //--------------------------------------------------------------------
 // Arm extensions.
 let Extension = ArmIntegerDotProductInt8 in {
   foreach name = ["arm_dot"] in {
     def : Builtin<name, [UInt, VectorType<UChar, 4>, VectorType<UChar, 4>]>;
     def : Builtin<name, [Int, VectorType<Char, 4>, VectorType<Char, 4>]>;
   }
 }

clang/test/Headers/opencl-c-header.cl

 #error "Incorrectly defined cl_khr_subgroup_shuffle"
 #endif
 #if cl_khr_subgroup_shuffle_relative != 1
 #error "Incorrectly defined cl_khr_subgroup_shuffle_relative"
 #endif
 #if cl_khr_subgroup_clustered_reduce != 1
 #error "Incorrectly defined cl_khr_subgroup_clustered_reduce"
 #endif
+#if cl_khr_subgroup_rotate != 1
+#error "Incorrectly defined cl_khr_subgroup_rotate"
+#endif
 #if cl_khr_extended_bit_ops != 1
 #error "Incorrectly defined cl_khr_extended_bit_ops"
 #endif
 #if cl_khr_integer_dot_product != 1
 #error "Incorrectly defined cl_khr_integer_dot_product"
 #endif
 #if __opencl_c_integer_dot_product_input_4x8bit != 1
 #error "Incorrectly defined __opencl_c_integer_dot_product_input_4x8bit"

 #error "Incorrect cl_khr_subgroup_shuffle define"
 #endif
 #ifdef cl_khr_subgroup_shuffle_relative
 #error "Incorrect cl_khr_subgroup_shuffle_relative define"
 #endif
 #ifdef cl_khr_subgroup_clustered_reduce
 #error "Incorrect cl_khr_subgroup_clustered_reduce define"
 #endif
+#ifdef cl_khr_subgroup_rotate
+#error "Incorrect cl_khr_subgroup_rotate define"
+#endif
 #ifdef cl_khr_extended_bit_ops
 #error "Incorrect cl_khr_extended_bit_ops define"
 #endif
 #ifdef cl_khr_integer_dot_product
 #error "Incorrect cl_khr_integer_dot_product define"
 #endif
 #ifdef __opencl_c_integer_dot_product_input_4x8bit
 #error "Incorrect __opencl_c_integer_dot_product_input_4x8bit define"