diff options
| -rw-r--r-- | clang/lib/AST/Decl.cpp | 7 | ||||
| -rw-r--r-- | clang/test/CodeGenCUDA/library-builtin.cu | 22 |
2 files changed, 29 insertions, 0 deletions
diff --git a/clang/lib/AST/Decl.cpp b/clang/lib/AST/Decl.cpp index 918466236bf..f8010695c90 100644 --- a/clang/lib/AST/Decl.cpp +++ b/clang/lib/AST/Decl.cpp @@ -2901,6 +2901,13 @@ unsigned FunctionDecl::getBuiltinID() const { Context.BuiltinInfo.isPredefinedLibFunction(BuiltinID)) return 0; + // CUDA does not have device-side standard library. printf and malloc are the + // only special cases that are supported by device-side runtime. + if (Context.getLangOpts().CUDA && hasAttr<CUDADeviceAttr>() && + !hasAttr<CUDAHostAttr>() && + !(BuiltinID == Builtin::BIprintf || BuiltinID == Builtin::BImalloc)) + return 0; + return BuiltinID; } diff --git a/clang/test/CodeGenCUDA/library-builtin.cu b/clang/test/CodeGenCUDA/library-builtin.cu new file mode 100644 index 00000000000..4804c75cde3 --- /dev/null +++ b/clang/test/CodeGenCUDA/library-builtin.cu @@ -0,0 +1,22 @@ +// REQUIRES: x86-registered-target +// REQUIRES: nvptx-registered-target + +// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -emit-llvm -o - %s | \ +// RUN: FileCheck --check-prefixes=HOST,BOTH %s +// RUN: %clang_cc1 -fcuda-is-device -triple nvptx64-nvidia-cuda \ +// RUN: -emit-llvm -o - %s | FileCheck %s --check-prefixes=DEVICE,BOTH + +// BOTH-LABEL: define float @logf(float + +// logf() should be calling itself recursively as we don't have any standard +// library on device side. +// DEVICE: call float @logf(float +extern "C" __attribute__((device)) float logf(float __x) { return logf(__x); } + +// NOTE: this case is to illustrate the expected differences in behavior between +// the host and device. In general we do not mess with host-side standard +// library. +// +// Host is assumed to have standard library, so logf() calls LLVM intrinsic. +// HOST: call float @llvm.log.f32(float +extern "C" float logf(float __x) { return logf(__x); } |
