diff --git a/clang/lib/Sema/OpenCLBuiltins.td b/clang/lib/Sema/OpenCLBuiltins.td
--- a/clang/lib/Sema/OpenCLBuiltins.td
+++ b/clang/lib/Sema/OpenCLBuiltins.td
@@ -53,6 +53,7 @@
 // FunctionExtension definitions.
 def FuncExtNone                          : FunctionExtension<"">;
 def FuncExtKhrSubgroups                  : FunctionExtension<"cl_khr_subgroups">;
+def FuncExtKhrSubgroupBallot             : FunctionExtension<"cl_khr_subgroup_ballot">;
 def FuncExtKhrGlobalInt32BaseAtomics     : FunctionExtension<"cl_khr_global_int32_base_atomics">;
 def FuncExtKhrGlobalInt32ExtendedAtomics : FunctionExtension<"cl_khr_global_int32_extended_atomics">;
 def FuncExtKhrLocalInt32BaseAtomics      : FunctionExtension<"cl_khr_local_int32_base_atomics">;
@@ -344,6 +345,7 @@
 // GenType definitions for multiple base types (e.g. all floating point types,
 // or all integer types).
 // All types
+def AGenType1              : GenericType<"AGenType1", TLAll, Vec1>;
 def AGenTypeN              : GenericType<"AGenTypeN", TLAll, VecAndScalar>;
 def AGenTypeNNoScalar      : GenericType<"AGenTypeNNoScalar", TLAll, VecNoScalar>;
 // All integer
@@ -1486,6 +1488,44 @@
   }
 }
 
+// OpenCL Extension v3.0 s38 - Extended Subgroup Functions
+
+// Section 38.4.1 - cl_khr_subgroup_extended_types
+// TODO
+
+// Section 38.5.1 - cl_khr_subgroup_non_uniform_vote
+// TODO
+
+// Section 38.6.1 - cl_khr_subgroup_ballot
+let Extension = FuncExtKhrSubgroupBallot in {
+  def : Builtin<"sub_group_non_uniform_broadcast", [AGenTypeN, AGenTypeN, UInt]>;
+  def : Builtin<"sub_group_broadcast_first", [AGenType1, AGenType1]>;
+  def : Builtin<"sub_group_ballot", [VectorType<UInt, 4>, Int]>;
+  def : Builtin<"sub_group_inverse_ballot", [Int, VectorType<UInt, 4>], Attr.Const>;
+  def : Builtin<"sub_group_ballot_bit_extract", [Int, VectorType<UInt, 4>, UInt], Attr.Const>;
+  def : Builtin<"sub_group_ballot_bit_count", [UInt, VectorType<UInt, 4>], Attr.Const>;
+  def : Builtin<"sub_group_ballot_inclusive_scan", [UInt, VectorType<UInt, 4>]>;
+  def : Builtin<"sub_group_ballot_exclusive_scan", [UInt, VectorType<UInt, 4>]>;
+  def : Builtin<"sub_group_ballot_find_lsb", [UInt, VectorType<UInt, 4>]>;
+  def : Builtin<"sub_group_ballot_find_msb", [UInt, VectorType<UInt, 4>]>;
+
+  foreach op = ["eq", "ge", "gt", "le", "lt"] in {
+    def : Builtin<"get_sub_group_" # op # "_mask", [VectorType<UInt, 4>], Attr.Const>;
+  }
+}
+
+// Section 38.7.1 - cl_khr_subgroup_non_uniform_arithmetic
+// TODO
+
+// Section 38.8.1 - cl_khr_subgroup_shuffle
+// TODO
+
+// Section 38.9.1 - cl_khr_subgroup_shuffle_relative
+// TODO
+
+// Section 38.10.1 - cl_khr_subgroup_clustered_reduce
+// TODO
+
 //--------------------------------------------------------------------
 // Arm extensions.
 let Extension = ArmIntegerDotProductInt8 in {
diff --git a/clang/test/SemaOpenCL/fdeclare-opencl-builtins.cl b/clang/test/SemaOpenCL/fdeclare-opencl-builtins.cl
--- a/clang/test/SemaOpenCL/fdeclare-opencl-builtins.cl
+++ b/clang/test/SemaOpenCL/fdeclare-opencl-builtins.cl
@@ -7,7 +7,10 @@
 // RUN: %clang_cc1 %s -triple spir -verify -pedantic -Wconversion -Werror -fsyntax-only -cl-std=CLC++ -fdeclare-opencl-builtins -DNO_HEADER
 // RUN: %clang_cc1 %s -triple spir -verify -pedantic -Wconversion -Werror -fsyntax-only -cl-std=CLC++ -fdeclare-opencl-builtins -finclude-default-header
 
-// Test the -fdeclare-opencl-builtins option.
+// Test the -fdeclare-opencl-builtins option.  This is not a completeness
+// test, so it should not test for all builtins defined by OpenCL.  Instead
+// this test should cover different functional aspects of the TableGen builtin
+// function machinery.
 
 #pragma OPENCL EXTENSION cl_khr_fp16 : enable
 #if __OPENCL_C_VERSION__ < CL_VERSION_1_2
@@ -30,6 +33,11 @@
 typedef int int4 __attribute__((ext_vector_type(4)));
 typedef uint uint4 __attribute__((ext_vector_type(4)));
 typedef long long2 __attribute__((ext_vector_type(2)));
+
+// Enable extensions that are enabled in opencl-c-base.h.
+#if (defined(__OPENCL_CPP_VERSION__) || __OPENCL_C_VERSION__ >= 200)
+#define cl_khr_subgroup_ballot 1
+#endif
 #endif
 
 kernel void test_pointers(volatile global void *global_p, global const int4 *a) {
@@ -132,6 +140,14 @@
 #endif
 }
 
+kernel void extended_subgroup(global uint4 *out) {
+  out[0] = get_sub_group_eq_mask();
+#if __OPENCL_C_VERSION__ < CL_VERSION_2_0 && !defined(__OPENCL_CPP_VERSION__)
+  // expected-error@-2{{implicit declaration of function 'get_sub_group_eq_mask' is invalid in OpenCL}}
+  // expected-error@-3{{implicit conversion changes signedness}}
+#endif
+}
+
 kernel void basic_vector_data() {
 #if __OPENCL_C_VERSION__ >= CL_VERSION_2_0
   generic void *generic_p;