CUDA/HIP programs use __noinline__ like a keyword e.g.
__noinline__ void foo() {} since __noinline__ is defined
as a macro __attribute__((noinline)) in CUDA/HIP runtime
header files.
However, gcc and clang supports __attribute__((__noinline__))
the same as __attribute__((noinline)). Some C++ libraries
use __attribute__((__noinline__)) in their header files.
When CUDA/HIP programs include such header files,
clang will emit error about invalid attributes.
This patch fixes this issue by supporting __noinline__ as
a keyword, so that CUDA/HIP runtime could remove
the macro definition.
Reviewed by: Aaron Ballman, Artem Belevich
Differential Revision: https://reviews.llvm.org/D124866
- Implemented `P0849R8: auto(x): decay-copy in the language <https://wg21.link/P0849R8>`_.
- Implemented `P2242R3: Non-literal variables (and labels and gotos) in constexpr functions <https://wg21.link/P2242R3>`_.
-CUDA Language Changes in Clang
-------------------------------
+CUDA/HIP Language Changes in Clang
+----------------------------------
+
+- Added `__noinline__` as a keyword to avoid diagnostics due to usage of
+ `__attribute__((__noinline__))` in CUDA/HIP programs.
Objective-C Language Changes in Clang
-------------------------------------
}
def NoInline : DeclOrStmtAttr {
- let Spellings = [GCC<"noinline">, CXX11<"clang", "noinline">,
- C2x<"clang", "noinline">, Declspec<"noinline">];
+ let Spellings = [Keyword<"__noinline__">, GCC<"noinline">,
+ CXX11<"clang", "noinline">, C2x<"clang", "noinline">,
+ Declspec<"noinline">];
let Accessors = [Accessor<"isClangNoInline", [CXX11<"clang", "noinline">,
C2x<"clang", "noinline">]>];
let Documentation = [NoInlineDocs];
marked ``[[clang::noinline]]`` and contains calls, those calls inside the
statement will not be inlined by the compiler.
+``__noinline__`` can be used as a keyword in CUDA/HIP languages. This is to
+avoid diagnostics due to usage of ``__attribute__((__noinline__))``
+with ``__noinline__`` defined as a macro as ``__attribute__((noinline))``.
+
.. code-block:: c
int example(void) {
FEATURE(cxx_abi_relative_vtable, LangOpts.CPlusPlus && LangOpts.RelativeCXXABIVTables)
+// CUDA/HIP Features
+FEATURE(cuda_noinline_keyword, LangOpts.CUDA)
+
#undef EXTENSION
#undef FEATURE
// C++ for OpenCL s2.3.1: addrspace_cast operator
KEYWORD(addrspace_cast , KEYOPENCLCXX)
+// CUDA/HIP function attributes
+KEYWORD(__noinline__ , KEYCUDA)
+
// OpenMP Type Traits
UNARY_EXPR_OR_TYPE_TRAIT(__builtin_omp_required_simd_align, OpenMPRequiredSimdAlign, KEYALL)
void ParseOpenCLKernelAttributes(ParsedAttributes &attrs);
void ParseOpenCLQualifiers(ParsedAttributes &Attrs);
void ParseNullabilityTypeSpecifiers(ParsedAttributes &attrs);
+ void ParseCUDAFunctionAttributes(ParsedAttributes &attrs);
VersionTuple ParseVersionTuple(SourceRange &Range);
void ParseAvailabilityAttribute(IdentifierInfo &Availability,
KEYOPENCLCXX = 0x400000,
KEYMSCOMPAT = 0x800000,
KEYSYCL = 0x1000000,
+ KEYCUDA = 0x2000000,
KEYALLCXX = KEYCXX | KEYCXX11 | KEYCXX20,
KEYALL = (0x1ffffff & ~KEYNOMS18 &
~KEYNOOPENCL) // KEYNOMS18 and KEYNOOPENCL are used to exclude.
return KS_Future;
if (LangOpts.isSYCL() && (Flags & KEYSYCL))
return KS_Enabled;
+ if (LangOpts.CUDA && (Flags & KEYCUDA))
+ return KS_Enabled;
return KS_Disabled;
}
}
}
+void Parser::ParseCUDAFunctionAttributes(ParsedAttributes &attrs) {
+ while (Tok.is(tok::kw___noinline__)) {
+ IdentifierInfo *AttrName = Tok.getIdentifierInfo();
+ SourceLocation AttrNameLoc = ConsumeToken();
+ attrs.addNew(AttrName, AttrNameLoc, nullptr, AttrNameLoc, nullptr, 0,
+ ParsedAttr::AS_Keyword);
+ }
+}
+
void Parser::ParseOpenCLQualifiers(ParsedAttributes &Attrs) {
IdentifierInfo *AttrName = Tok.getIdentifierInfo();
SourceLocation AttrNameLoc = Tok.getLocation();
ParseOpenCLKernelAttributes(DS.getAttributes());
continue;
+ // CUDA/HIP single token adornments.
+ case tok::kw___noinline__:
+ ParseCUDAFunctionAttributes(DS.getAttributes());
+ continue;
+
// Nullability type specifiers.
case tok::kw__Nonnull:
case tok::kw__Nullable:
--- /dev/null
+// Uses -O2 since the defalt -O0 option adds noinline to all functions.
+
+// RUN: %clang_cc1 -triple nvptx-nvidia-cuda -fcuda-is-device \
+// RUN: -O2 -disable-llvm-passes -emit-llvm -o - %s | FileCheck %s
+
+// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -fcuda-is-device \
+// RUN: -O2 -disable-llvm-passes -emit-llvm -o - -x hip %s | FileCheck %s
+
+// RUN: %clang_cc1 -triple x86_64-unknown-gnu-linux \
+// RUN: -O2 -disable-llvm-passes -emit-llvm -o - %s | FileCheck %s
+
+#include "Inputs/cuda.h"
+
+__noinline__ __device__ __host__ void fun1() {}
+
+__attribute__((noinline)) __device__ __host__ void fun2() {}
+
+__attribute__((__noinline__)) __device__ __host__ void fun3() {}
+
+[[gnu::__noinline__]] __device__ __host__ void fun4() {}
+
+#define __noinline__ __attribute__((__noinline__))
+__noinline__ __device__ __host__ void fun5() {}
+
+__device__ __host__ void fun6() {}
+
+// CHECK: define{{.*}}@_Z4fun1v{{.*}}#[[ATTR1:[0-9]*]]
+// CHECK: define{{.*}}@_Z4fun2v{{.*}}#[[ATTR1:[0-9]*]]
+// CHECK: define{{.*}}@_Z4fun3v{{.*}}#[[ATTR1:[0-9]*]]
+// CHECK: define{{.*}}@_Z4fun4v{{.*}}#[[ATTR1:[0-9]*]]
+// CHECK: define{{.*}}@_Z4fun5v{{.*}}#[[ATTR1:[0-9]*]]
+// CHECK: define{{.*}}@_Z4fun6v{{.*}}#[[ATTR2:[0-9]*]]
+// CHECK: attributes #[[ATTR1]] = {{.*}}noinline
+// CHECK-NOT: attributes #[[ATTR2]] = {{.*}}noinline
--- /dev/null
+// RUN: %clang_cc1 -E -triple x86_64-linux-gnu %s -o - | FileCheck %s
+
+// CHECK: has_noinline_keyword
+#if __has_feature(cuda_noinline_keyword)
+int has_noinline_keyword();
+#else
+int no_noinine_keyword();
+#endif
--- /dev/null
+// RUN: %clang_cc1 -fsyntax-only -verify=cuda %s
+// RUN: %clang_cc1 -fsyntax-only -verify=cuda -pedantic %s
+// RUN: %clang_cc1 -fsyntax-only -verify=cpp -x c++ %s
+
+// cuda-no-diagnostics
+
+__noinline__ void fun1() { } // cpp-error {{unknown type name '__noinline__'}}
+
+__attribute__((noinline)) void fun2() { }
+__attribute__((__noinline__)) void fun3() { }
+[[gnu::__noinline__]] void fun4() { }
+
+#define __noinline__ __attribute__((__noinline__))
+__noinline__ void fun5() {}
+
+#undef __noinline__
+#10 "cuda.h" 3
+#define __noinline__ __attribute__((__noinline__))
+__noinline__ void fun6() {}