[clang] aa9c2d1 - [OpenCL] Align subgroup builtin guards

[Sven van Haastregt via cfe-commits]

Author: Sven van Haastregt
Date: 2022-02-23T12:22:09Z
New Revision: aa9c2d19d9b73589d72114d6e0a4fb4ce42b922b

URL: https://github.com/llvm/llvm-project/commit/aa9c2d19d9b73589d72114d6e0a4fb4ce42b922b
DIFF: https://github.com/llvm/llvm-project/commit/aa9c2d19d9b73589d72114d6e0a4fb4ce42b922b.diff

LOG: [OpenCL] Align subgroup builtin guards

Until now, subgroup builtins are available with `opencl-c.h` when at
least one of `cl_intel_subgroups`, `cl_khr_subgroups`, or
`__opencl_c_subgroups` is defined.  With `-fdeclare-opencl-builtins`,
subgroup builtins are conditionalized on `cl_khr_subgroups` only.

Align `-fdeclare-opencl-builtins` to `opencl-c.h` by introducing the
internal `__opencl_subgroup_builtins` macro.

Differential Revision: https://reviews.llvm.org/D120254

Added: 
    

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

Removed: 
    


################################################################################
diff  --git a/clang/lib/Headers/opencl-c-base.h b/clang/lib/Headers/opencl-c-base.h
index 5191c41bcd057..d0a0d5bdbf4f5 100644
--- a/clang/lib/Headers/opencl-c-base.h
+++ b/clang/lib/Headers/opencl-c-base.h
@@ -80,6 +80,11 @@
 #define __opencl_c_named_address_space_builtins 1
 #endif // !defined(__opencl_c_generic_address_space)
 
+#if defined(cl_intel_subgroups) || defined(cl_khr_subgroups) || defined(__opencl_c_subgroups)
+// Internal feature macro to provide subgroup builtins.
+#define __opencl_subgroup_builtins 1
+#endif
+
 // built-in scalar data types:
 
 /**

diff  --git a/clang/lib/Headers/opencl-c.h b/clang/lib/Headers/opencl-c.h
index 18c1c317e100f..172b2c192709f 100644
--- a/clang/lib/Headers/opencl-c.h
+++ b/clang/lib/Headers/opencl-c.h
@@ -16282,7 +16282,7 @@ queue_t __ovld get_default_queue(void);
 
 // OpenCL Extension v2.0 s9.17 - Sub-groups
 
-#if defined(cl_intel_subgroups) || defined(cl_khr_subgroups) || defined(__opencl_c_subgroups)
+#if defined(__opencl_subgroup_builtins)
 // Shared Sub Group Functions
 uint    __ovld get_sub_group_size(void);
 uint    __ovld get_max_sub_group_size(void);
@@ -16381,7 +16381,7 @@ double  __ovld __conv sub_group_scan_inclusive_min(double x);
 double  __ovld __conv sub_group_scan_inclusive_max(double x);
 #endif //cl_khr_fp64
 
-#endif //cl_khr_subgroups cl_intel_subgroups __opencl_c_subgroups
+#endif // __opencl_subgroup_builtins
 
 #if defined(cl_khr_subgroup_extended_types)
 char __ovld __conv sub_group_broadcast( char value, uint index );

diff  --git a/clang/lib/Sema/OpenCLBuiltins.td b/clang/lib/Sema/OpenCLBuiltins.td
index e6da5e34f7091..ff23a1c52ff38 100644
--- a/clang/lib/Sema/OpenCLBuiltins.td
+++ b/clang/lib/Sema/OpenCLBuiltins.td
@@ -83,7 +83,7 @@ def AtomicFp64TypeExt : TypeExtension<"cl_khr_int64_base_atomics cl_khr_int64_ex
 
 // FunctionExtension definitions.
 def FuncExtNone                          : FunctionExtension<"">;
-def FuncExtKhrSubgroups                  : FunctionExtension<"cl_khr_subgroups">;
+def FuncExtKhrSubgroups                  : FunctionExtension<"__opencl_subgroup_builtins">;
 def FuncExtKhrSubgroupExtendedTypes      : FunctionExtension<"cl_khr_subgroup_extended_types">;
 def FuncExtKhrSubgroupNonUniformVote     : FunctionExtension<"cl_khr_subgroup_non_uniform_vote">;
 def FuncExtKhrSubgroupBallot             : FunctionExtension<"cl_khr_subgroup_ballot">;

diff  --git a/clang/test/SemaOpenCL/fdeclare-opencl-builtins.cl b/clang/test/SemaOpenCL/fdeclare-opencl-builtins.cl
index d2d7fff02efaa..89a4646839acb 100644
--- a/clang/test/SemaOpenCL/fdeclare-opencl-builtins.cl
+++ b/clang/test/SemaOpenCL/fdeclare-opencl-builtins.cl
@@ -1,7 +1,7 @@
 // RUN: %clang_cc1 %s -triple spir -verify -pedantic -Wconversion -Werror -fsyntax-only -cl-std=CL -fdeclare-opencl-builtins -DNO_HEADER
 // RUN: %clang_cc1 %s -triple spir -verify -pedantic -Wconversion -Werror -fsyntax-only -cl-std=CL -fdeclare-opencl-builtins -finclude-default-header
-// RUN: %clang_cc1 %s -triple spir -verify -pedantic -Wconversion -Werror -fsyntax-only -cl-std=CL1.2 -fdeclare-opencl-builtins -DNO_HEADER
-// RUN: %clang_cc1 %s -triple spir -verify -pedantic -Wconversion -Werror -fsyntax-only -cl-std=CL1.2 -fdeclare-opencl-builtins -finclude-default-header
+// RUN: %clang_cc1 %s -triple spir -verify -pedantic -Wconversion -Werror -fsyntax-only -cl-std=CL1.2 -fdeclare-opencl-builtins -DNO_HEADER -cl-ext=-cl_intel_subgroups
+// RUN: %clang_cc1 %s -triple spir -verify -pedantic -Wconversion -Werror -fsyntax-only -cl-std=CL1.2 -fdeclare-opencl-builtins -finclude-default-header -cl-ext=-cl_intel_subgroups
 // RUN: %clang_cc1 %s -triple spir -verify -pedantic -Wconversion -Werror -fsyntax-only -cl-std=CL2.0 -fdeclare-opencl-builtins -DNO_HEADER
 // RUN: %clang_cc1 %s -triple spir -verify -pedantic -Wconversion -Werror -fsyntax-only -cl-std=CL2.0 -fdeclare-opencl-builtins -finclude-default-header
 // RUN: %clang_cc1 %s -triple spir -verify -pedantic -Wconversion -Werror -fsyntax-only -cl-std=CL3.0 -fdeclare-opencl-builtins -finclude-default-header
@@ -79,6 +79,7 @@ typedef struct {int a;} ndrange_t;
 #define cl_khr_subgroup_non_uniform_arithmetic 1
 #define cl_khr_subgroup_clustered_reduce 1
 #define __opencl_c_read_write_images 1
+#define __opencl_subgroup_builtins 1
 #endif
 
 #if (__OPENCL_CPP_VERSION__ == 100 || __OPENCL_C_VERSION__ == 200)