[clang] 21c29a8 - [OpenCL] Add cl_khr_subgroup_rotate builtins

[Sven van Haastregt via cfe-commits]

Author: Sven van Haastregt
Date: 2022-05-18T13:02:17+01:00
New Revision: 21c29a8ae053cb436141ee636333c4f816cc20c4

URL: https://github.com/llvm/llvm-project/commit/21c29a8ae053cb436141ee636333c4f816cc20c4
DIFF: https://github.com/llvm/llvm-project/commit/21c29a8ae053cb436141ee636333c4f816cc20c4.diff

LOG: [OpenCL] Add cl_khr_subgroup_rotate builtins

Differential Revision: https://reviews.llvm.org/D124256

Added: 
    

Modified: 
    clang/lib/Headers/opencl-c-base.h
    clang/lib/Headers/opencl-c.h
    clang/lib/Sema/OpenCLBuiltins.td
    clang/test/Headers/opencl-c-header.cl

Removed: 
    


################################################################################
diff  --git a/clang/lib/Headers/opencl-c-base.h b/clang/lib/Headers/opencl-c-base.h
index 4e87afad84bf..20048d97bc74 100644
--- a/clang/lib/Headers/opencl-c-base.h
+++ b/clang/lib/Headers/opencl-c-base.h
@@ -21,6 +21,7 @@
 #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

diff  --git a/clang/lib/Headers/opencl-c.h b/clang/lib/Headers/opencl-c.h
index 8d9af5248195..69e2c85610ba 100644
--- a/clang/lib/Headers/opencl-c.h
+++ b/clang/lib/Headers/opencl-c.h
@@ -17275,6 +17275,40 @@ 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 );

diff  --git a/clang/lib/Sema/OpenCLBuiltins.td b/clang/lib/Sema/OpenCLBuiltins.td
index 220daf05acf9..75cea2ffc19c 100644
--- a/clang/lib/Sema/OpenCLBuiltins.td
+++ b/clang/lib/Sema/OpenCLBuiltins.td
@@ -1845,6 +1845,12 @@ let Extension = FunctionExtension<"__opencl_c_integer_dot_product_input_4x8bit_p
   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 {

diff  --git a/clang/test/Headers/opencl-c-header.cl b/clang/test/Headers/opencl-c-header.cl
index be185ff8dcf1..455842412fd0 100644
--- a/clang/test/Headers/opencl-c-header.cl
+++ b/clang/test/Headers/opencl-c-header.cl
@@ -127,6 +127,9 @@ global atomic_int z = ATOMIC_VAR_INIT(99);
 #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
@@ -208,6 +211,9 @@ global atomic_int z = ATOMIC_VAR_INIT(99);
 #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