本文整理汇总了C++中IRBuilder::CreateConstInBoundsGEP1_64方法的典型用法代码示例。如果您正苦于以下问题：C++ IRBuilder::CreateConstInBoundsGEP1_64方法的具体用法？C++ IRBuilder::CreateConstInBoundsGEP1_64怎么用？C++ IRBuilder::CreateConstInBoundsGEP1_64使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类IRBuilder的用法示例。
在下文中一共展示了IRBuilder::CreateConstInBoundsGEP1_64方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的C++代码示例。
示例1: make_pair
std::pair<Value *, Value *>
AMDGPUPromoteAlloca::getLocalSizeYZ(IRBuilder<> &Builder) {
if (!IsAMDHSA) {
Function *LocalSizeYFn
= Intrinsic::getDeclaration(Mod, Intrinsic::r600_read_local_size_y);
Function *LocalSizeZFn
= Intrinsic::getDeclaration(Mod, Intrinsic::r600_read_local_size_z);
CallInst *LocalSizeY = Builder.CreateCall(LocalSizeYFn, {});
CallInst *LocalSizeZ = Builder.CreateCall(LocalSizeZFn, {});
LocalSizeY->setMetadata(LLVMContext::MD_range, MaxWorkGroupSizeRange);
LocalSizeZ->setMetadata(LLVMContext::MD_range, MaxWorkGroupSizeRange);
return std::make_pair(LocalSizeY, LocalSizeZ);
}
// We must read the size out of the dispatch pointer.
assert(IsAMDGCN);
// We are indexing into this struct, and want to extract the workgroup_size_*
// fields.
//
// typedef struct hsa_kernel_dispatch_packet_s {
// uint16_t header;
// uint16_t setup;
// uint16_t workgroup_size_x ;
// uint16_t workgroup_size_y;
// uint16_t workgroup_size_z;
// uint16_t reserved0;
// uint32_t grid_size_x ;
// uint32_t grid_size_y ;
// uint32_t grid_size_z;
//
// uint32_t private_segment_size;
// uint32_t group_segment_size;
// uint64_t kernel_object;
//
// #ifdef HSA_LARGE_MODEL
// void *kernarg_address;
// #elif defined HSA_LITTLE_ENDIAN
// void *kernarg_address;
// uint32_t reserved1;
// #else
// uint32_t reserved1;
// void *kernarg_address;
// #endif
// uint64_t reserved2;
// hsa_signal_t completion_signal; // uint64_t wrapper
// } hsa_kernel_dispatch_packet_t
//
Function *DispatchPtrFn
= Intrinsic::getDeclaration(Mod, Intrinsic::amdgcn_dispatch_ptr);
CallInst *DispatchPtr = Builder.CreateCall(DispatchPtrFn, {});
DispatchPtr->addAttribute(AttributeSet::ReturnIndex, Attribute::NoAlias);
DispatchPtr->addAttribute(AttributeSet::ReturnIndex, Attribute::NonNull);
// Size of the dispatch packet struct.
DispatchPtr->addDereferenceableAttr(AttributeSet::ReturnIndex, 64);
Type *I32Ty = Type::getInt32Ty(Mod->getContext());
Value *CastDispatchPtr = Builder.CreateBitCast(
DispatchPtr, PointerType::get(I32Ty, AMDGPUAS::CONSTANT_ADDRESS));
// We could do a single 64-bit load here, but it's likely that the basic
// 32-bit and extract sequence is already present, and it is probably easier
// to CSE this. The loads should be mergable later anyway.
Value *GEPXY = Builder.CreateConstInBoundsGEP1_64(CastDispatchPtr, 1);
LoadInst *LoadXY = Builder.CreateAlignedLoad(GEPXY, 4);
Value *GEPZU = Builder.CreateConstInBoundsGEP1_64(CastDispatchPtr, 2);
LoadInst *LoadZU = Builder.CreateAlignedLoad(GEPZU, 4);
MDNode *MD = llvm::MDNode::get(Mod->getContext(), None);
LoadXY->setMetadata(LLVMContext::MD_invariant_load, MD);
LoadZU->setMetadata(LLVMContext::MD_invariant_load, MD);
LoadZU->setMetadata(LLVMContext::MD_range, MaxWorkGroupSizeRange);
// Extract y component. Upper half of LoadZU should be zero already.
Value *Y = Builder.CreateLShr(LoadXY, 16);
return std::make_pair(Y, LoadZU);
}