Author: tra Date: Tue Jan 23 11:08:18 2018 New Revision: 323239 URL: http://llvm.org/viewvc/llvm-project?rev=323239&view=rev Log: [CUDA] CUDA has no device-side library builtins.
We should (almost) never consider a device-side declaration to match a library builtin functio. Otherwise clang may ignore the implementation provided by the CUDA headers and emit clang's idea of the builtin. Differential Revision: https://reviews.llvm.org/D42319 Added: cfe/trunk/test/CodeGenCUDA/library-builtin.cu Modified: cfe/trunk/lib/AST/Decl.cpp Modified: cfe/trunk/lib/AST/Decl.cpp URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/AST/Decl.cpp?rev=323239&r1=323238&r2=323239&view=diff ============================================================================== --- cfe/trunk/lib/AST/Decl.cpp (original) +++ cfe/trunk/lib/AST/Decl.cpp Tue Jan 23 11:08:18 2018 @@ -2901,6 +2901,13 @@ unsigned FunctionDecl::getBuiltinID() co 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; } Added: cfe/trunk/test/CodeGenCUDA/library-builtin.cu URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/CodeGenCUDA/library-builtin.cu?rev=323239&view=auto ============================================================================== --- cfe/trunk/test/CodeGenCUDA/library-builtin.cu (added) +++ cfe/trunk/test/CodeGenCUDA/library-builtin.cu Tue Jan 23 11:08:18 2018 @@ -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); } _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits