[Clang] Add support for missing OpenCL extensions

This patch adds handling for the following OpenCL extensions, passed as
`-cl-ext` arguments to Clang:
- cl_khr_extended_bit_ops
- cl_khr_integer_dot_product
- cl_khr_subgroup_ballot
- cl_khr_subgroup_clustered_reduce
- cl_khr_subgroup_extended_types
- cl_khr_subgroup_named_barrier
- cl_khr_subgroup_non_uniform_arithmetic
- cl_khr_subgroup_non_uniform_vote
- cl_khr_subgroup_rotate
- cl_khr_subgroup_shuffle
- cl_khr_subgroup_shuffle_relative
- cl_khr_work_group_uniform_arithmetic
- cl_intel_subgroups_char
- cl_intel_subgroups_long

Author: vmustya

clang/include/clang/Basic/OpenCLExtensions.def

@@ -90,13 +90,29 @@ OPENCL_EXTENSION(__cl_clang_variadic_functions, true, 100)
 OPENCL_EXTENSION(__cl_clang_non_portable_kernel_param_types, true, 100)
 OPENCL_EXTENSION(__cl_clang_bitfields, true, 100)
 
+// Khronos OpenCL extensions
+OPENCL_EXTENSION(cl_khr_extended_bit_ops, true, 100)
+OPENCL_EXTENSION(cl_khr_integer_dot_product, true, 100)
+OPENCL_EXTENSION(cl_khr_subgroup_ballot, true, 100)
+OPENCL_EXTENSION(cl_khr_subgroup_clustered_reduce, true, 100)
+OPENCL_EXTENSION(cl_khr_subgroup_extended_types, true, 100)
+OPENCL_EXTENSION(cl_khr_subgroup_named_barrier, true, 100)
+OPENCL_EXTENSION(cl_khr_subgroup_non_uniform_arithmetic, true, 100)
+OPENCL_EXTENSION(cl_khr_subgroup_non_uniform_vote, true, 100)
+OPENCL_EXTENSION(cl_khr_subgroup_rotate, true, 100)
+OPENCL_EXTENSION(cl_khr_subgroup_shuffle, true, 100)
+OPENCL_EXTENSION(cl_khr_subgroup_shuffle_relative, true, 100)
+OPENCL_EXTENSION(cl_khr_work_group_uniform_arithmetic, true, 200)
+
 // AMD OpenCL extensions
 OPENCL_EXTENSION(cl_amd_media_ops, true, 100)
 OPENCL_EXTENSION(cl_amd_media_ops2, true, 100)
 
 // Intel OpenCL extensions
 OPENCL_EXTENSION(cl_intel_subgroups, true, 120)
+OPENCL_EXTENSION(cl_intel_subgroups_char, true, 120)
 OPENCL_EXTENSION(cl_intel_subgroups_short, true, 120)
+OPENCL_EXTENSION(cl_intel_subgroups_long, true, 120)
 OPENCL_EXTENSION(cl_intel_device_side_avc_motion_estimation, true, 120)
 
 // OpenCL C 3.0 features (6.2.1. Features)
@@ -112,6 +128,11 @@ OPENCL_OPTIONALCOREFEATURE(__opencl_c_program_scope_global_variables, false, 300
 OPENCL_OPTIONALCOREFEATURE(__opencl_c_fp64, false, 300, OCL_C_30)
 OPENCL_OPTIONALCOREFEATURE(__opencl_c_images, false, 300, OCL_C_30)
 
+// Features enabled by the Khronos extensions
+OPENCL_GENERIC_EXTENSION(__opencl_c_work_group_collective_functions, false, 300, 0)
+OPENCL_GENERIC_EXTENSION(__opencl_c_integer_dot_product_input_4x8bit, false, 300, 0)
+OPENCL_GENERIC_EXTENSION(__opencl_c_integer_dot_product_input_4x8bit_packed, false, 300, 0)
+
 #undef OPENCL_OPTIONALCOREFEATURE
 #undef OPENCL_COREFEATURE
 #undef OPENCL_GENERIC_EXTENSION

clang/lib/Basic/OpenCLOptions.cpp

@@ -18,7 +18,14 @@ static const std::pair<StringRef, StringRef> DependentFeaturesList[] = {
     {"__opencl_c_3d_image_writes", "__opencl_c_images"},
     {"__opencl_c_pipes", "__opencl_c_generic_address_space"},
     {"__opencl_c_device_enqueue", "__opencl_c_generic_address_space"},
-    {"__opencl_c_device_enqueue", "__opencl_c_program_scope_global_variables"}};
+    {"__opencl_c_device_enqueue", "__opencl_c_program_scope_global_variables"},
+    {"__opencl_c_work_group_collective_functions",
+     "cl_khr_work_group_uniform_arithmetic"},
+    {"__opencl_c_integer_dot_product_input_4x8bit",
+     "cl_khr_integer_dot_product"},
+    {"__opencl_c_integer_dot_product_input_4x8bit_packed",
+     "cl_khr_integer_dot_product"},
+};
 
 // Extensions and equivalent feature pairs.
 static const std::pair<StringRef, StringRef> FeatureExtensionMap[] = {