[OpenCL] Add cl_khr_kernel_clock builtins

[svenvh]

Provisional extension description: https://registry.khronos.org/OpenCL/specs/3.0-unified/html/OpenCL_API.html#cl_khr_kernel_clock and
https://registry.khronos.org/OpenCL/specs/3.0-unified/html/OpenCL_C.html#kernel-clock-functions .

[llvmbot]

@llvm/pr-subscribers-backend-x86

@llvm/pr-subscribers-clang

Author: Sven van Haastregt (svenvh)

Changes

Provisional extension description: https://registry.khronos.org/OpenCL/specs/3.0-unified/html/OpenCL_API.html#cl_khr_kernel_clock and
https://registry.khronos.org/OpenCL/specs/3.0-unified/html/OpenCL_C.html#kernel-clock-functions .

---

Full diff: https://github.com/llvm/llvm-project/pull/91950.diff

3 Files Affected:

• (modified) clang/lib/Headers/opencl-c-base.h (+4)
• (modified) clang/lib/Headers/opencl-c.h (+15)
• (modified) clang/lib/Sema/OpenCLBuiltins.td (+14)

diff --git a/clang/lib/Headers/opencl-c-base.h b/clang/lib/Headers/opencl-c-base.h
index 2494f6213fc56..786678b9d8a75 100644
--- a/clang/lib/Headers/opencl-c-base.h
+++ b/clang/lib/Headers/opencl-c-base.h
@@ -46,6 +46,10 @@
 #define __opencl_c_ext_fp32_global_atomic_min_max 1
 #define __opencl_c_ext_fp32_local_atomic_min_max 1
 #define __opencl_c_ext_image_raw10_raw12 1
+#define cl_khr_kernel_clock 1
+#define __opencl_c_kernel_clock_scope_device 1
+#define __opencl_c_kernel_clock_scope_work_group 1
+#define __opencl_c_kernel_clock_scope_sub_group 1
 
 #endif // defined(__SPIR__) || defined(__SPIRV__)
 #endif // (defined(__OPENCL_CPP_VERSION__) || __OPENCL_C_VERSION__ >= 200)
diff --git a/clang/lib/Headers/opencl-c.h b/clang/lib/Headers/opencl-c.h
index 288bb18bc654e..20719b74b6b8d 100644
--- a/clang/lib/Headers/opencl-c.h
+++ b/clang/lib/Headers/opencl-c.h
@@ -17314,6 +17314,21 @@ half __ovld __conv sub_group_clustered_rotate(half, int, uint);
 #endif // cl_khr_fp16
 #endif // cl_khr_subgroup_rotate
 
+#if defined(cl_khr_kernel_clock)
+#if defined(__opencl_c_kernel_clock_scope_device)
+ulong __ovld clock_read_device();
+uint2 __ovld clock_read_hilo_device();
+#endif // __opencl_c_kernel_clock_scope_device
+#if defined(__opencl_c_kernel_clock_scope_work_group)
+ulong __ovld clock_read_work_group();
+uint2 __ovld clock_read_hilo_work_group();
+#endif // __opencl_c_kernel_clock_scope_work_group
+#if defined(__opencl_c_kernel_clock_scope_sub_group)
+ulong __ovld clock_read_sub_group();
+uint2 __ovld clock_read_hilo_sub_group();
+#endif // __opencl_c_kernel_clock_scope_sub_group
+#endif // cl_khr_kernel_clock
+
 #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 a7bdfe20b9828..4da61429fcce7 100644
--- a/clang/lib/Sema/OpenCLBuiltins.td
+++ b/clang/lib/Sema/OpenCLBuiltins.td
@@ -1852,6 +1852,20 @@ let Extension = FunctionExtension<"cl_khr_subgroup_rotate"> in {
   def : Builtin<"sub_group_clustered_rotate", [AGenType1, AGenType1, Int, UInt], Attr.Convergent>;
 }
 
+// cl_khr_kernel_clock
+let Extension = FunctionExtension<"cl_khr_kernel_clock __opencl_c_kernel_clock_scope_device"> in {
+  def : Builtin<"clock_read_device", [ULong]>;
+  def : Builtin<"clock_read_hilo_device", [VectorType<UInt, 2>]>;
+}
+let Extension = FunctionExtension<"cl_khr_kernel_clock __opencl_c_kernel_clock_scope_work_group"> in {
+  def : Builtin<"clock_read_work_group", [ULong]>;
+  def : Builtin<"clock_read_hilo_work_group", [VectorType<UInt, 2>]>;
+}
+let Extension = FunctionExtension<"cl_khr_kernel_clock __opencl_c_kernel_clock_scope_sub_group"> in {
+  def : Builtin<"clock_read_sub_group", [ULong]>;
+  def : Builtin<"clock_read_hilo_sub_group", [VectorType<UInt, 2>]>;
+}
+
 //--------------------------------------------------------------------
 // Arm extensions.
 let Extension = ArmIntegerDotProductInt8 in {

[cdai2]

LGTM. Compilation is verified.