[CUDA] Fix emission of constant strings in sections

[Hahnfeld]

Summary

CGM.GetAddrOfConstantCString() sets the adress of the created GlobalValue
to unnamed. When emitting the object file LLVM will mark the surrounding
section as SHF_MERGE iff the string is nul-terminated and contains no
other nuls (see IsNullTerminatedString). This results in problems when
saving temporaries because LLVM doesn't set an EntrySize, so reading in
the serialized assembly file fails.
This never happened for the GPU binaries because they usually contain
a nul-character somewhere. Instead this only affected the module ID
when compiling relocatable device code.

However, this points to a potentially larger problem: If we put a
constant string into a named section, we really want the data to end
up in that section in the object file. To avoid LLVM merging sections
this patch unmarks the GlobalVariable's address as unnamed which also
fixes the problem of invalid serialized assembly files when saving
temporaries.

cfe/trunk/lib/CodeGen/CGCUDANV.cpp

llvm::Constant *makeConstantString(const std::string &Str,
                                      const std::string &Name = "",
                                      const std::string &SectionName = "",
                                      unsigned Alignment = 0) {
     llvm::Constant *Zeros[] = {llvm::ConstantInt::get(SizeTy, 0),
                                llvm::ConstantInt::get(SizeTy, 0)};
     auto ConstStr = CGM.GetAddrOfConstantCString(Str, Name.c_str());
     llvm::GlobalVariable *GV =
         cast<llvm::GlobalVariable>(ConstStr.getPointer());
-    if (!SectionName.empty())
+    if (!SectionName.empty()) {
       GV->setSection(SectionName);
+      // Mark the address as used which make sure that this section isn't
+      // merged and we will really have it in the object file.
+      GV->setUnnamedAddr(llvm::GlobalValue::UnnamedAddr::None);
+    }
     if (Alignment)
       GV->setAlignment(Alignment);
 
     return llvm::ConstantExpr::getGetElementPtr(ConstStr.getElementType(),
                                                 ConstStr.getPointer(), Zeros);
   }
 
   /// Helper function that generates an empty dummy function returning void.

cfe/trunk/test/CodeGenCUDA/device-stub.cu

void use_pointers() {
   p = &ext_host_var;
 }
 
 // Make sure that all parts of GPU code init/cleanup are there:
 // * constant unnamed string with the kernel name
 // ALL: private unnamed_addr constant{{.*}}kernelfunc{{.*}}\00"
 // * constant unnamed string with GPU binary
 // HIP: @[[FATBIN:__hip_fatbin]] = external constant i8, section ".hip_fatbin"
-// CUDA: @[[FATBIN:.*]] = private unnamed_addr constant{{.*GPU binary would be here.*}}\00",
+// CUDA: @[[FATBIN:.*]] = private constant{{.*GPU binary would be here.*}}\00",
 // CUDANORDC-SAME: section ".nv_fatbin", align 8
 // CUDARDC-SAME: section "__nv_relfatbin", align 8
 // * constant struct that wraps GPU binary
 // ALL: @__[[PREFIX:cuda|hip]]_fatbin_wrapper = internal constant
 // ALL-SAME: { i32, i32, i8*, i8* }
 // CUDA-SAME: { i32 1180844977, i32 1,
 // HIP-SAME: { i32 1212764230, i32 1,
 // CUDA-SAME: i8* getelementptr inbounds ({{.*}}@[[FATBIN]], i64 0, i64 0),
 // HIP-SAME:  i8* @[[FATBIN]],
 // ALL-SAME: i8* null }
 // CUDA-SAME: section ".nvFatBinSegment"
 // HIP-SAME: section ".hipFatBinSegment"
 // * variable to save GPU binary handle after initialization
 // NORDC: @__[[PREFIX]]_gpubin_handle = internal global i8** null
 // * constant unnamed string with NVModuleID
-// RDC: [[MODULE_ID_GLOBAL:@.*]] = private unnamed_addr constant
+// RDC: [[MODULE_ID_GLOBAL:@.*]] = private constant
 // CUDARDC-SAME: c"[[MODULE_ID:.+]]\00", section "__nv_module_id", align 32
 // HIPRDC-SAME: c"[[MODULE_ID:.+]]\00", section "__hip_module_id", align 32
 // * Make sure our constructor was added to global ctor list.
 // ALL: @llvm.global_ctors = appending global {{.*}}@__[[PREFIX]]_module_ctor
 // * In separate mode we also register a destructor.
 // NORDC: @llvm.global_dtors = appending global {{.*}}@__[[PREFIX]]_module_dtor
 // * Alias to global symbol containing the NVModuleID.
 // RDC: @__fatbinwrap[[MODULE_ID]] = alias { i32, i32, i8*, i8* }

 // Test that we've created destructor.
 // NORDC: define internal void @__[[PREFIX]]_module_dtor
 // NORDC: load{{.*}}__[[PREFIX]]_gpubin_handle
 // NORDC-NEXT: call void @__[[PREFIX]]UnregisterFatBinary
 
 // There should be no __[[PREFIX]]_register_globals if we have no
 // device-side globals, but we still need to register GPU binary.
 // Skip GPU binary string first.
-// CUDANOGLOBALS: @{{.*}} = private unnamed_addr constant{{.*}}
+// CUDANOGLOBALS: @{{.*}} = private constant{{.*}}
 // HIPNOGLOBALS: @{{.*}} = external constant{{.*}}
 // NOGLOBALS-NOT: define internal void @__{{.*}}_register_globals
 // NOGLOBALS: define internal void @__[[PREFIX:cuda|hip]]_module_ctor
 // NOGLOBALS: call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
 // NOGLOBALS-NOT: call void @__[[PREFIX]]_register_globals
 // NOGLOBALS: define internal void @__[[PREFIX]]_module_dtor
 // NOGLOBALS: call void @__[[PREFIX]]UnregisterFatBinary
 
 // There should be no constructors/destructors if we have no GPU binary.
 // NOGPUBIN-NOT: define internal void @__[[PREFIX]]_register_globals
 // NOGPUBIN-NOT: define internal void @__[[PREFIX]]_module_ctor
 // NOGPUBIN-NOT: define internal void @__[[PREFIX]]_module_dtor