From fc6245cf9dc945c35d7b1be78c92b970a1c5199d Mon Sep 17 00:00:00 2001 From: Justin Lebar Date: Fri, 9 Sep 2016 20:35:43 +0000 Subject: [PATCH] [CUDA] Make __GCC_ATOMIC_XXX_LOCK_FREE macros the same on host/device. Summary: This fixes a bug where we were unable to compile the following CUDA file with libstdc++ (didn't try libc++): #include void foo() { std::shared_future x; } The problem is that only defines std::shared_future if __GCC_ATOMIC_INT_LOCK_FREE > 1. When we compiled this file for device, the macro was set to 1, and then the class didn't exist at all. Reviewers: tra Subscribers: cfe-commits, jhen Differential Revision: https://reviews.llvm.org/D24407 git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@281089 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/Basic/Targets.cpp | 6 +++++ test/Preprocessor/cuda-types.cu | 39 ++++++++++++++++++++------------- 2 files changed, 30 insertions(+), 15 deletions(-) diff --git a/lib/Basic/Targets.cpp b/lib/Basic/Targets.cpp index 535b681035..15190594fc 100644 --- a/lib/Basic/Targets.cpp +++ b/lib/Basic/Targets.cpp @@ -1768,6 +1768,12 @@ public: UseExplicitBitFieldAlignment = HostTarget->useExplicitBitFieldAlignment(); ZeroLengthBitfieldBoundary = HostTarget->getZeroLengthBitfieldBoundary(); + // This is a bit of a lie, but it controls __GCC_ATOMIC_XXX_LOCK_FREE, and + // we need those macros to be identical on host and device, because (among + // other things) they affect which standard library classes are defined, and + // we need all classes to be defined on both the host and device. + MaxAtomicInlineWidth = HostTarget->getMaxAtomicInlineWidth(); + // Properties intentionally not copied from host: // - LargeArrayMinWidth, LargeArrayAlign: Not visible across the // host/device boundary. diff --git a/test/Preprocessor/cuda-types.cu b/test/Preprocessor/cuda-types.cu index 32aa928596..2b6160b8d6 100644 --- a/test/Preprocessor/cuda-types.cu +++ b/test/Preprocessor/cuda-types.cu @@ -1,21 +1,30 @@ -// Check that types, widths, etc. match on the host and device sides of CUDA -// compilations. Note that we filter out long double, as this is intentionally -// different on host and device. +// Check that types, widths, __GCC_ATOMIC* macros, etc. match on the host and +// device sides of CUDA compilations. Note that we filter out long double, as +// this is intentionally different on host and device. +// +// FIXME: We really should make __GCC_HAVE_SYNC_COMPARE_AND_SWAP identical on +// host and device, but architecturally this is difficult at the moment. -// RUN: %clang --cuda-host-only -nocudainc -target i386-unknown-linux-gnu -x cuda -E -dM -o - /dev/null > %T/i386-host-defines -// RUN: %clang --cuda-device-only -nocudainc -nocudalib -target i386-unknown-linux-gnu -x cuda -E -dM -o - /dev/null > %T/i386-device-defines -// RUN: grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF|WIDTH\)' %T/i386-host-defines | grep -v '__LDBL\|_LONG_DOUBLE' > %T/i386-host-defines-filtered -// RUN: grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF|WIDTH\)' %T/i386-device-defines | grep -v '__LDBL\|_LONG_DOUBLE' > %T/i386-device-defines-filtered +// RUN: %clang --cuda-host-only -nocudainc -target i386-unknown-linux-gnu -x cuda -E -dM -o - /dev/null \ +// RUN: | grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF|WIDTH\)\|define __GCC_ATOMIC' \ +// RUN: | grep -v '__LDBL\|_LONG_DOUBLE' > %T/i386-host-defines-filtered +// RUN: %clang --cuda-device-only -nocudainc -nocudalib -target i386-unknown-linux-gnu -x cuda -E -dM -o - /dev/null \ +// RUN: | grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF|WIDTH\)\|define __GCC_ATOMIC' \ +// RUN: | grep -v '__LDBL\|_LONG_DOUBLE' > %T/i386-device-defines-filtered // RUN: diff %T/i386-host-defines-filtered %T/i386-device-defines-filtered -// RUN: %clang --cuda-host-only -nocudainc -target x86_64-unknown-linux-gnu -x cuda -E -dM -o - /dev/null > %T/x86_64-host-defines -// RUN: %clang --cuda-device-only -nocudainc -nocudalib -target x86_64-unknown-linux-gnu -x cuda -E -dM -o - /dev/null > %T/x86_64-device-defines -// RUN: grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF\|WIDTH\)' %T/x86_64-host-defines | grep -v '__LDBL\|_LONG_DOUBLE' > %T/x86_64-host-defines-filtered -// RUN: grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF\|WIDTH\)' %T/x86_64-device-defines | grep -v '__LDBL\|_LONG_DOUBLE' > %T/x86_64-device-defines-filtered +// RUN: %clang --cuda-host-only -nocudainc -target x86_64-unknown-linux-gnu -x cuda -E -dM -o - /dev/null \ +// RUN: | grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF|WIDTH\)\|define __GCC_ATOMIC' \ +// RUN: | grep -v '__LDBL\|_LONG_DOUBLE' > %T/x86_64-host-defines-filtered +// RUN: %clang --cuda-device-only -nocudainc -nocudalib -target x86_64-unknown-linux-gnu -x cuda -E -dM -o - /dev/null \ +// RUN: | grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF|WIDTH\)\|define __GCC_ATOMIC' \ +// RUN: | grep -v '__LDBL\|_LONG_DOUBLE' > %T/x86_64-device-defines-filtered // RUN: diff %T/x86_64-host-defines-filtered %T/x86_64-device-defines-filtered -// RUN: %clang --cuda-host-only -nocudainc -target powerpc64-unknown-linux-gnu -x cuda -E -dM -o - /dev/null > %T/powerpc64-host-defines -// RUN: %clang --cuda-device-only -nocudainc -nocudalib -target powerpc64-unknown-linux-gnu -x cuda -E -dM -o - /dev/null > %T/powerpc64-device-defines -// RUN: grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF\|WIDTH\)' %T/powerpc64-host-defines | grep -v '__LDBL\|_LONG_DOUBLE' > %T/powerpc64-host-defines-filtered -// RUN: grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF\|WIDTH\)' %T/powerpc64-device-defines | grep -v '__LDBL\|_LONG_DOUBLE' > %T/powerpc64-device-defines-filtered +// RUN: %clang --cuda-host-only -nocudainc -target powerpc64-unknown-linux-gnu -x cuda -E -dM -o - /dev/null \ +// RUN: | grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF|WIDTH\)\|define __GCC_ATOMIC' \ +// RUN: | grep -v '__LDBL\|_LONG_DOUBLE' > %T/powerpc64-host-defines-filtered +// RUN: %clang --cuda-device-only -nocudainc -nocudalib -target powerpc64-unknown-linux-gnu -x cuda -E -dM -o - /dev/null \ +// RUN: | grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF|WIDTH\)\|define __GCC_ATOMIC' \ +// RUN: | grep -v '__LDBL\|_LONG_DOUBLE' > %T/powerpc64-device-defines-filtered // RUN: diff %T/powerpc64-host-defines-filtered %T/powerpc64-device-defines-filtered -- 2.40.0