summaryrefslogtreecommitdiff
path: root/clang/lib/CodeGen/CodeGenModule.cpp
diff options
context:
space:
mode:
authorYaxun (Sam) Liu <yaxun.liu@amd.com>2021-01-26 17:11:01 -0500
committerYaxun (Sam) Liu <yaxun.liu@amd.com>2021-02-03 14:29:51 -0500
commit0b2af1a2889423bb797856841ac81cf10d01c696 (patch)
tree3fd03338b91695155d7bf9cc7ecf2ff9a6870e17 /clang/lib/CodeGen/CodeGenModule.cpp
parent4a35941dbde63964240d30309e2b72d8be8fabb6 (diff)
[NFC][CUDA] Refactor registering device variable
Extract registering device variable to CUDA runtime codegen function since it will be called in multiple places. Reviewed by: Artem Belevich Differential Revision: https://reviews.llvm.org/D95558
Diffstat (limited to 'clang/lib/CodeGen/CodeGenModule.cpp')
-rw-r--r--clang/lib/CodeGen/CodeGenModule.cpp55
1 files changed, 2 insertions, 53 deletions
diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index c9cf4076579b..b133d2a84a59 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -4297,59 +4297,8 @@ void CodeGenModule::EmitGlobalVarDefinition(const VarDecl *D,
(D->hasAttr<CUDADeviceAttr>() || D->hasAttr<CUDAConstantAttr>()))
GV->setExternallyInitialized(true);
} else {
- // Host-side shadows of external declarations of device-side
- // global variables become internal definitions. These have to
- // be internal in order to prevent name conflicts with global
- // host variables with the same name in a different TUs.
- if (D->hasAttr<CUDADeviceAttr>() || D->hasAttr<CUDAConstantAttr>()) {
- Linkage = llvm::GlobalValue::InternalLinkage;
- // Shadow variables and their properties must be registered with CUDA
- // runtime. Skip Extern global variables, which will be registered in
- // the TU where they are defined.
- //
- // Don't register a C++17 inline variable. The local symbol can be
- // discarded and referencing a discarded local symbol from outside the
- // comdat (__cuda_register_globals) is disallowed by the ELF spec.
- // TODO: Reject __device__ constexpr and __device__ inline in Sema.
- if (!D->hasExternalStorage() && !D->isInline())
- getCUDARuntime().registerDeviceVar(D, *GV, !D->hasDefinition(),
- D->hasAttr<CUDAConstantAttr>());
- } else if (D->hasAttr<CUDASharedAttr>()) {
- // __shared__ variables are odd. Shadows do get created, but
- // they are not registered with the CUDA runtime, so they
- // can't really be used to access their device-side
- // counterparts. It's not clear yet whether it's nvcc's bug or
- // a feature, but we've got to do the same for compatibility.
- Linkage = llvm::GlobalValue::InternalLinkage;
- } else if (D->getType()->isCUDADeviceBuiltinSurfaceType() ||
- D->getType()->isCUDADeviceBuiltinTextureType()) {
- // Builtin surfaces and textures and their template arguments are
- // also registered with CUDA runtime.
- Linkage = llvm::GlobalValue::InternalLinkage;
- const ClassTemplateSpecializationDecl *TD =
- cast<ClassTemplateSpecializationDecl>(
- D->getType()->getAs<RecordType>()->getDecl());
- const TemplateArgumentList &Args = TD->getTemplateArgs();
- if (TD->hasAttr<CUDADeviceBuiltinSurfaceTypeAttr>()) {
- assert(Args.size() == 2 &&
- "Unexpected number of template arguments of CUDA device "
- "builtin surface type.");
- auto SurfType = Args[1].getAsIntegral();
- if (!D->hasExternalStorage())
- getCUDARuntime().registerDeviceSurf(D, *GV, !D->hasDefinition(),
- SurfType.getSExtValue());
- } else {
- assert(Args.size() == 3 &&
- "Unexpected number of template arguments of CUDA device "
- "builtin texture type.");
- auto TexType = Args[1].getAsIntegral();
- auto Normalized = Args[2].getAsIntegral();
- if (!D->hasExternalStorage())
- getCUDARuntime().registerDeviceTex(D, *GV, !D->hasDefinition(),
- TexType.getSExtValue(),
- Normalized.getZExtValue());
- }
- }
+ getCUDARuntime().internalizeDeviceSideVar(D, Linkage);
+ getCUDARuntime().handleVarRegistration(D, *GV);
}
}