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

[CUDA] Place GPU binary into .nv_fatbin section and align it by 8. 

This matches the way nvcc encapsulates GPU binaries into host object file.
Now cuobjdump can deal with clang-compiled object files.

Differential Revision: https://reviews.llvm.org/D23429

llvm-svn: 278549
This commit is contained in:
Artem Belevich 2016-08-12 18:44:01 +00:00
parent dc698c3e91
commit 4c09318be2
2 changed files with 14 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
clang/lib/CodeGen/CGCUDANV.cpp
View File

@ -55,10 +55,18 @@ private:
/// where the C code specifies const char*.
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())
GV->setSection(SectionName);
if (Alignment)
GV->setAlignment(Alignment);
return llvm::ConstantExpr::getGetElementPtr(ConstStr.getElementType(),
ConstStr.getPointer(), Zeros);
}
@ -285,7 +293,8 @@ llvm::Function *CGNVCUDARuntime::makeModuleCtorFunction() {
llvm::Constant *Values[] = {
llvm::ConstantInt::get(IntTy, 0x466243b1), // Fatbin wrapper magic.
llvm::ConstantInt::get(IntTy, 1), // Fatbin version.
makeConstantString(GpuBinaryOrErr.get()->getBuffer(), "", 16), // Data.
makeConstantString(GpuBinaryOrErr.get()->getBuffer(), // Data.
"", ".nv_fatbin", 8), //
llvm::ConstantPointerNull::get(VoidPtrTy)}; // Unused in fatbin v1.
llvm::GlobalVariable *FatbinWrapper = new llvm::GlobalVariable(
TheModule, FatbinWrapperTy, true, llvm::GlobalValue::InternalLinkage,

6
clang/test/CodeGenCUDA/device-stub.cu
View File

@ -45,10 +45,12 @@ void use_pointers() {
// * constant unnamed string with the kernel name
// CHECK: private unnamed_addr constant{{.*}}kernelfunc{{.*}}\00"
// * constant unnamed string with GPU binary
// CHECK: private unnamed_addr constant{{.*}}\00"
// CHECK: private unnamed_addr constant{{.*GPU binary would be here.*}}\00"
// CHECK-SAME: section ".nv_fatbin", align 8
// * constant struct that wraps GPU binary
// CHECK: @__cuda_fatbin_wrapper = internal constant { i32, i32, i8*, i8* }
// CHECK: { i32 1180844977, i32 1, {{.*}}, i8* null }
// CHECK-SAME: { i32 1180844977, i32 1, {{.*}}, i8* null }
// CHECK-SAME: section ".nvFatBinSegment"
// * variable to save GPU binary handle after initialization
// CHECK: @__cuda_gpubin_handle = internal global i8** null
// * Make sure our constructor/destructor was added to global ctor/dtor list.