r325136 - [CUDA] Allow external variables in separate compilation
Jonas Hahnfeld via cfe-commits
cfe-commits at lists.llvm.org
Wed Feb 14 08:04:04 PST 2018
Author: hahnfeld
Date: Wed Feb 14 08:04:03 2018
New Revision: 325136
URL: http://llvm.org/viewvc/llvm-project?rev=325136&view=rev
Log:
[CUDA] Allow external variables in separate compilation
According to the CUDA Programming Guide this is prohibited in
whole program compilation mode. This makes sense because external
references cannot be satisfied in that mode anyway. However,
such variables are allowed in separate compilation mode which
is a valid use case.
Differential Revision: https://reviews.llvm.org/D42923
Modified:
cfe/trunk/lib/Sema/SemaDeclAttr.cpp
cfe/trunk/test/SemaCUDA/extern-shared.cu
Modified: cfe/trunk/lib/Sema/SemaDeclAttr.cpp
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Sema/SemaDeclAttr.cpp?rev=325136&r1=325135&r2=325136&view=diff
==============================================================================
--- cfe/trunk/lib/Sema/SemaDeclAttr.cpp (original)
+++ cfe/trunk/lib/Sema/SemaDeclAttr.cpp Wed Feb 14 08:04:03 2018
@@ -4112,7 +4112,8 @@ static void handleSharedAttr(Sema &S, De
auto *VD = cast<VarDecl>(D);
// extern __shared__ is only allowed on arrays with no length (e.g.
// "int x[]").
- if (VD->hasExternalStorage() && !isa<IncompleteArrayType>(VD->getType())) {
+ if (!S.getLangOpts().CUDARelocatableDeviceCode && VD->hasExternalStorage() &&
+ !isa<IncompleteArrayType>(VD->getType())) {
S.Diag(Attr.getLoc(), diag::err_cuda_extern_shared) << VD;
return;
}
Modified: cfe/trunk/test/SemaCUDA/extern-shared.cu
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/SemaCUDA/extern-shared.cu?rev=325136&r1=325135&r2=325136&view=diff
==============================================================================
--- cfe/trunk/test/SemaCUDA/extern-shared.cu (original)
+++ cfe/trunk/test/SemaCUDA/extern-shared.cu Wed Feb 14 08:04:03 2018
@@ -1,6 +1,11 @@
// RUN: %clang_cc1 -fsyntax-only -verify %s
// RUN: %clang_cc1 -fsyntax-only -fcuda-is-device -verify %s
+// RUN: %clang_cc1 -fsyntax-only -fcuda-rdc -verify=rdc %s
+// RUN: %clang_cc1 -fsyntax-only -fcuda-is-device -fcuda-rdc -verify=rdc %s
+// These declarations are fine in separate compilation mode:
+// rdc-no-diagnostics
+
#include "Inputs/cuda.h"
__device__ void foo() {
More information about the cfe-commits
mailing list