maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[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 <future>
  void foo() { std::shared_future<int> x; }

The problem is that <future> 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

llvm-svn: 281089
This commit is contained in:
Justin Lebar 2016-09-09 20:35:43 +00:00
parent 92e33a3ebc
commit 5057f17716
2 changed files with 30 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
clang/lib/Basic/Targets.cpp
View File

@ -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.

39
clang/test/Preprocessor/cuda-types.cu
View File

@ -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