[MLIR][OpenMP] Refactoring createTargetData in OMPIRBuilder

Key changes:
  - Refactor the createTargetData function to make use of the emitOffloadingArrays and emitOffloadingArraysArgument functions to generate code.
  - Added a new emitIfClause helper function to allow handling if clauses in a similar fashion to Clang.
  - Updated the MLIR side of code to account for changes to createTargetData.

Depends on D149872

Reviewed By: jdoerfert

Differential Revision: https://reviews.llvm.org/D146557
This commit is contained in:
Akash Banerjee 2023-06-19 12:46:15 +01:00
parent 7e229217f4
commit a032dc139d
5 changed files with 422 additions and 339 deletions

View File

@ -1478,6 +1478,25 @@ public:
/// Computes the size of type in bytes.
Value *getSizeInBytes(Value *BasePtr);
// Emit a branch from the current block to the Target block only if
// the current block has a terminator.
void emitBranch(BasicBlock *Target);
// If BB has no use then delete it and return. Else place BB after the current
// block, if possible, or else at the end of the function. Also add a branch
// from current block to BB if current block does not have a terminator.
void emitBlock(BasicBlock *BB, Function *CurFn, bool IsFinished = false);
/// Emits code for OpenMP 'if' clause using specified \a BodyGenCallbackTy
/// Here is the logic:
/// if (Cond) {
/// ThenGen();
/// } else {
/// ElseGen();
/// }
void emitIfClause(Value *Cond, BodyGenCallbackTy ThenGen,
BodyGenCallbackTy ElseGen, InsertPointTy AllocaIP = {});
/// Create the global variable holding the offload mappings information.
GlobalVariable *createOffloadMaptypes(SmallVectorImpl<uint64_t> &Mappings,
std::string VarName);
@ -1987,29 +2006,41 @@ public:
StringRef EntryFnName,
StringRef EntryFnIDName,
int32_t NumTeams, int32_t NumThreads);
/// Type of BodyGen to use for region codegen
///
/// Priv: If device pointer privatization is required, emit the body of the
/// region here. It will have to be duplicated: with and without
/// privatization.
/// DupNoPriv: If we need device pointer privatization, we need
/// to emit the body of the region with no privatization in the 'else' branch
/// of the conditional.
/// NoPriv: If we don't require privatization of device
/// pointers, we emit the body in between the runtime calls. This avoids
/// duplicating the body code.
enum BodyGenTy { Priv, DupNoPriv, NoPriv };
/// Generator for '#omp target data'
///
/// \param Loc The location where the target data construct was encountered.
/// \param AllocaIP The insertion points to be used for alloca instructions.
/// \param CodeGenIP The insertion point at which the target directive code
/// should be placed.
/// \param MapTypeFlags BitVector storing the mapType flags for the
/// mapOperands.
/// \param MapNames Names for the mapOperands.
/// \param MapperAllocas Pointers to the AllocInsts for the map clause.
/// \param IsBegin If true then emits begin mapper call otherwise emits
/// end mapper call.
/// \param DeviceID Stores the DeviceID from the device clause.
/// \param IfCond Value which corresponds to the if clause condition.
/// \param ProcessMapOpCB Callback that generates code for the map clause.
/// \param BodyGenCB Callback that will generate the region code.
/// \param Info Stores all information realted to the Target Data directive.
/// \param GenMapInfoCB Callback that populates the MapInfos and returns.
/// \param BodyGenCB Optional Callback to generate the region code.
OpenMPIRBuilder::InsertPointTy createTargetData(
const LocationDescription &Loc, OpenMPIRBuilder::InsertPointTy CodeGenIP,
SmallVectorImpl<uint64_t> &MapTypeFlags,
SmallVectorImpl<Constant *> &MapNames,
struct MapperAllocas &MapperAllocas, bool IsBegin, int64_t DeviceID,
Value *IfCond, BodyGenCallbackTy ProcessMapOpCB,
BodyGenCallbackTy BodyGenCB = {});
const LocationDescription &Loc, InsertPointTy AllocaIP,
InsertPointTy CodeGenIP, Value *DeviceID, Value *IfCond,
TargetDataInfo &Info,
function_ref<MapInfosTy &(InsertPointTy CodeGenIP)> GenMapInfoCB,
omp::RuntimeFunction *MapperFunc = nullptr,
function_ref<InsertPointTy(InsertPointTy CodeGenIP,
BodyGenTy BodyGenType)>
BodyGenCB = nullptr);
using TargetBodyGenCallbackTy = function_ref<InsertPointTy(
InsertPointTy AllocaIP, InsertPointTy CodeGenIP)>;

View File

@ -4078,73 +4078,121 @@ Constant *OpenMPIRBuilder::registerTargetRegionFunction(
}
OpenMPIRBuilder::InsertPointTy OpenMPIRBuilder::createTargetData(
const LocationDescription &Loc, OpenMPIRBuilder::InsertPointTy CodeGenIP,
SmallVectorImpl<uint64_t> &MapTypeFlags,
SmallVectorImpl<Constant *> &MapNames, struct MapperAllocas &MapperAllocas,
bool IsBegin, int64_t DeviceID, Value *IfCond,
BodyGenCallbackTy ProcessMapOpCB, BodyGenCallbackTy BodyGenCB) {
const LocationDescription &Loc, InsertPointTy AllocaIP,
InsertPointTy CodeGenIP, Value *DeviceID, Value *IfCond,
TargetDataInfo &Info,
function_ref<MapInfosTy &(InsertPointTy CodeGenIP)> GenMapInfoCB,
omp::RuntimeFunction *MapperFunc,
function_ref<InsertPointTy(InsertPointTy CodeGenIP, BodyGenTy BodyGenType)>
BodyGenCB) {
if (!updateToLocation(Loc))
return InsertPointTy();
Builder.restoreIP(CodeGenIP);
bool IsStandAlone = !BodyGenCB;
// LLVM utilities like blocks with terminators.
// The UI acts as a resume point for code insertion after the BodyGen
auto *UI = Builder.CreateUnreachable();
if (IfCond) {
auto *ThenTI =
SplitBlockAndInsertIfThen(IfCond, UI, /* Unreachable */ false);
ThenTI->getParent()->setName("omp_if.then");
Builder.SetInsertPoint(ThenTI);
} else {
Builder.SetInsertPoint(UI);
}
// Generate the code for the opening of the data environment. Capture all the
// arguments of the runtime call by reference because they are used in the
// closing of the region.
auto BeginThenGen = [&](InsertPointTy AllocaIP, InsertPointTy CodeGenIP) {
emitOffloadingArrays(AllocaIP, Builder.saveIP(),
GenMapInfoCB(Builder.saveIP()), Info,
/*IsNonContiguous=*/true);
ProcessMapOpCB(Builder.saveIP(), Builder.saveIP());
TargetDataRTArgs RTArgs;
emitOffloadingArraysArgument(Builder, RTArgs, Info);
uint32_t SrcLocStrSize;
Constant *SrcLocStr = getOrCreateSrcLocStr(Loc, SrcLocStrSize);
Value *srcLocInfo = getOrCreateIdent(SrcLocStr, SrcLocStrSize);
// Emit the number of elements in the offloading arrays.
Value *PointerNum = Builder.getInt32(Info.NumberOfPtrs);
GlobalVariable *MapTypesGV =
createOffloadMaptypes(MapTypeFlags, ".offload_maptypes");
Value *MapTypesArg = Builder.CreateConstInBoundsGEP2_32(
ArrayType::get(Builder.getInt64Ty(), MapTypeFlags.size()), MapTypesGV,
/*Idx0=*/0, /*Idx1=*/0);
// Source location for the ident struct
uint32_t SrcLocStrSize;
Constant *SrcLocStr = getOrCreateSrcLocStr(Loc, SrcLocStrSize);
Value *SrcLocInfo = getOrCreateIdent(SrcLocStr, SrcLocStrSize);
GlobalVariable *MapNamesGV =
createOffloadMapnames(MapNames, ".offload_mapnames");
Value *MapNamesArg = Builder.CreateConstInBoundsGEP2_32(
ArrayType::get(Builder.getInt8PtrTy(), MapNames.size()), MapNamesGV,
/*Idx0=*/0, /*Idx1=*/0);
Value *OffloadingArgs[] = {SrcLocInfo, DeviceID,
PointerNum, RTArgs.BasePointersArray,
RTArgs.PointersArray, RTArgs.SizesArray,
RTArgs.MapTypesArray, RTArgs.MapNamesArray,
RTArgs.MappersArray};
Function *beginMapperFunc =
getOrCreateRuntimeFunctionPtr(omp::OMPRTL___tgt_target_data_begin_mapper);
Function *endMapperFunc =
getOrCreateRuntimeFunctionPtr(omp::OMPRTL___tgt_target_data_end_mapper);
if (IsStandAlone) {
assert(MapperFunc && "MapperFunc missing for standalone target data");
Builder.CreateCall(getOrCreateRuntimeFunctionPtr(*MapperFunc),
OffloadingArgs);
} else {
Function *BeginMapperFunc = getOrCreateRuntimeFunctionPtr(
omp::OMPRTL___tgt_target_data_begin_mapper);
Builder.CreateCall(BeginMapperFunc, OffloadingArgs);
// If device pointer privatization is required, emit the body of the
// region here. It will have to be duplicated: with and without
// privatization.
Builder.restoreIP(BodyGenCB(Builder.saveIP(), BodyGenTy::Priv));
}
};
// If we need device pointer privatization, we need to emit the body of the
// region with no privatization in the 'else' branch of the conditional.
// Otherwise, we don't have to do anything.
auto BeginElseGen = [&](InsertPointTy AllocaIP, InsertPointTy CodeGenIP) {
Builder.restoreIP(BodyGenCB(Builder.saveIP(), BodyGenTy::DupNoPriv));
};
// Generate code for the closing of the data region.
auto EndThenGen = [&](InsertPointTy AllocaIP, InsertPointTy CodeGenIP) {
TargetDataRTArgs RTArgs;
emitOffloadingArraysArgument(Builder, RTArgs, Info, /*EmitDebug=*/false,
/*ForEndCall=*/true);
// Emit the number of elements in the offloading arrays.
Value *PointerNum = Builder.getInt32(Info.NumberOfPtrs);
// Source location for the ident struct
uint32_t SrcLocStrSize;
Constant *SrcLocStr = getOrCreateSrcLocStr(Loc, SrcLocStrSize);
Value *SrcLocInfo = getOrCreateIdent(SrcLocStr, SrcLocStrSize);
Value *OffloadingArgs[] = {SrcLocInfo, DeviceID,
PointerNum, RTArgs.BasePointersArray,
RTArgs.PointersArray, RTArgs.SizesArray,
RTArgs.MapTypesArray, RTArgs.MapNamesArray,
RTArgs.MappersArray};
Function *EndMapperFunc =
getOrCreateRuntimeFunctionPtr(omp::OMPRTL___tgt_target_data_end_mapper);
Builder.CreateCall(EndMapperFunc, OffloadingArgs);
};
// We don't have to do anything to close the region if the if clause evaluates
// to false.
auto EndElseGen = [&](InsertPointTy AllocaIP, InsertPointTy CodeGenIP) {};
if (BodyGenCB) {
// Create call to start the data region.
emitMapperCall(Builder.saveIP(), beginMapperFunc, srcLocInfo, MapTypesArg,
MapNamesArg, MapperAllocas, DeviceID, MapTypeFlags.size());
if (IfCond) {
emitIfClause(IfCond, BeginThenGen, BeginElseGen, AllocaIP);
} else {
BeginThenGen(AllocaIP, Builder.saveIP());
}
BodyGenCB(Builder.saveIP(), Builder.saveIP());
// If we don't require privatization of device pointers, we emit the body in
// between the runtime calls. This avoids duplicating the body code.
Builder.restoreIP(BodyGenCB(Builder.saveIP(), BodyGenTy::NoPriv));
Builder.SetInsertPoint(UI->getParent());
// Create call to end the data region.
emitMapperCall(Builder.saveIP(), endMapperFunc, srcLocInfo, MapTypesArg,
MapNamesArg, MapperAllocas, DeviceID, MapTypeFlags.size());
if (IfCond) {
emitIfClause(IfCond, EndThenGen, EndElseGen, AllocaIP);
} else {
EndThenGen(AllocaIP, Builder.saveIP());
}
} else {
emitMapperCall(Builder.saveIP(), IsBegin ? beginMapperFunc : endMapperFunc,
srcLocInfo, MapTypesArg, MapNamesArg, MapperAllocas,
DeviceID, MapTypeFlags.size());
if (IfCond) {
emitIfClause(IfCond, BeginThenGen, EndElseGen, AllocaIP);
} else {
BeginThenGen(AllocaIP, Builder.saveIP());
}
}
// Update the insertion point and remove the terminator we introduced.
Builder.SetInsertPoint(UI->getParent());
if (IfCond)
UI->getParent()->setName("omp_if.end");
UI->eraseFromParent();
return Builder.saveIP();
}
@ -4668,6 +4716,77 @@ void OpenMPIRBuilder::emitOffloadingArrays(
emitNonContiguousDescriptor(AllocaIP, CodeGenIP, CombinedInfo, Info);
}
void OpenMPIRBuilder::emitBranch(BasicBlock *Target) {
BasicBlock *CurBB = Builder.GetInsertBlock();
if (!CurBB || CurBB->getTerminator()) {
// If there is no insert point or the previous block is already
// terminated, don't touch it.
} else {
// Otherwise, create a fall-through branch.
Builder.CreateBr(Target);
}
Builder.ClearInsertionPoint();
}
void OpenMPIRBuilder::emitBlock(BasicBlock *BB, Function *CurFn,
bool IsFinished) {
BasicBlock *CurBB = Builder.GetInsertBlock();
// Fall out of the current block (if necessary).
emitBranch(BB);
if (IsFinished && BB->use_empty()) {
BB->eraseFromParent();
return;
}
// Place the block after the current block, if possible, or else at
// the end of the function.
if (CurBB && CurBB->getParent())
CurFn->insert(std::next(CurBB->getIterator()), BB);
else
CurFn->insert(CurFn->end(), BB);
Builder.SetInsertPoint(BB);
}
void OpenMPIRBuilder::emitIfClause(Value *Cond, BodyGenCallbackTy ThenGen,
BodyGenCallbackTy ElseGen,
InsertPointTy AllocaIP) {
// If the condition constant folds and can be elided, try to avoid emitting
// the condition and the dead arm of the if/else.
if (auto *CI = dyn_cast<ConstantInt>(Cond)) {
auto CondConstant = CI->getSExtValue();
if (CondConstant)
ThenGen(AllocaIP, Builder.saveIP());
else
ElseGen(AllocaIP, Builder.saveIP());
return;
}
Function *CurFn = Builder.GetInsertBlock()->getParent();
// Otherwise, the condition did not fold, or we couldn't elide it. Just
// emit the conditional branch.
BasicBlock *ThenBlock = BasicBlock::Create(M.getContext(), "omp_if.then");
BasicBlock *ElseBlock = BasicBlock::Create(M.getContext(), "omp_if.else");
BasicBlock *ContBlock = BasicBlock::Create(M.getContext(), "omp_if.end");
Builder.CreateCondBr(Cond, ThenBlock, ElseBlock);
// Emit the 'then' code.
emitBlock(ThenBlock, CurFn);
ThenGen(AllocaIP, Builder.saveIP());
emitBranch(ContBlock);
// Emit the 'else' code if present.
// There is no need to emit line number for unconditional branch.
emitBlock(ElseBlock, CurFn);
ElseGen(AllocaIP, Builder.saveIP());
// There is no need to emit line number for unconditional branch.
emitBranch(ContBlock);
// Emit the continuation block for code after the if.
emitBlock(ContBlock, CurFn, /*IsFinished=*/true);
}
bool OpenMPIRBuilder::checkAndEmitFlushAfterAtomic(
const LocationDescription &Loc, llvm::AtomicOrdering AO, AtomicKind AK) {
assert(!(AO == AtomicOrdering::NotAtomic ||

View File

@ -4886,18 +4886,9 @@ TEST_F(OpenMPIRBuilderTest, TargetEnterData) {
OMPBuilder.initialize();
F->setName("func");
IRBuilder<> Builder(BB);
OpenMPIRBuilder::LocationDescription Loc({Builder.saveIP(), DL});
unsigned NumDataOperands = 1;
int64_t DeviceID = 2;
struct OpenMPIRBuilder::MapperAllocas MapperAllocas;
SmallVector<uint64_t> MapTypeFlagsTo = {1};
SmallVector<Constant *> MapNames;
auto *I8PtrTy = Builder.getInt8PtrTy();
auto *ArrI8PtrTy = ArrayType::get(I8PtrTy, NumDataOperands);
auto *I64Ty = Builder.getInt64Ty();
auto *ArrI64Ty = ArrayType::get(I64Ty, NumDataOperands);
AllocaInst *Val1 =
Builder.CreateAlloca(Builder.getInt32Ty(), Builder.getInt64(1));
@ -4905,44 +4896,34 @@ TEST_F(OpenMPIRBuilderTest, TargetEnterData) {
IRBuilder<>::InsertPoint AllocaIP(&F->getEntryBlock(),
F->getEntryBlock().getFirstInsertionPt());
OMPBuilder.createMapperAllocas(Builder.saveIP(), AllocaIP, NumDataOperands,
MapperAllocas);
llvm::OpenMPIRBuilder::MapInfosTy CombinedInfo;
using InsertPointTy = OpenMPIRBuilder::InsertPointTy;
auto ProcessMapOpCB = [&](InsertPointTy AllocaIP, InsertPointTy CodeGenIP) {
Value *DataValue = Val1;
Value *DataPtrBase;
Value *DataPtr;
DataPtrBase = DataValue;
DataPtr = DataValue;
Builder.restoreIP(CodeGenIP);
auto GenMapInfoCB =
[&](InsertPointTy codeGenIP) -> llvm::OpenMPIRBuilder::MapInfosTy & {
// Get map clause information.
Builder.restoreIP(codeGenIP);
Value *Null = Constant::getNullValue(DataValue->getType()->getPointerTo());
Value *SizeGep =
Builder.CreateGEP(DataValue->getType(), Null, Builder.getInt32(1));
Value *SizePtrToInt = Builder.CreatePtrToInt(SizeGep, I64Ty);
Value *PtrBaseGEP =
Builder.CreateInBoundsGEP(ArrI8PtrTy, MapperAllocas.ArgsBase,
{Builder.getInt32(0), Builder.getInt32(0)});
Value *PtrBaseCast = Builder.CreateBitCast(
PtrBaseGEP, DataPtrBase->getType()->getPointerTo());
Builder.CreateStore(DataPtrBase, PtrBaseCast);
Value *PtrGEP =
Builder.CreateInBoundsGEP(ArrI8PtrTy, MapperAllocas.Args,
{Builder.getInt32(0), Builder.getInt32(0)});
Value *PtrCast =
Builder.CreateBitCast(PtrGEP, DataPtr->getType()->getPointerTo());
Builder.CreateStore(DataPtr, PtrCast);
Value *SizeGEP =
Builder.CreateInBoundsGEP(ArrI64Ty, MapperAllocas.ArgSizes,
{Builder.getInt32(0), Builder.getInt32(0)});
Builder.CreateStore(SizePtrToInt, SizeGEP);
CombinedInfo.BasePointers.emplace_back(Val1);
CombinedInfo.Pointers.emplace_back(Val1);
CombinedInfo.Sizes.emplace_back(Builder.getInt64(4));
CombinedInfo.Types.emplace_back(llvm::omp::OpenMPOffloadMappingFlags(1));
uint32_t temp;
CombinedInfo.Names.emplace_back(
OMPBuilder.getOrCreateSrcLocStr("unknown", temp));
return CombinedInfo;
};
llvm::OpenMPIRBuilder::TargetDataInfo Info(
/*RequiresDevicePointerInfo=*/false,
/*SeparateBeginEndCalls=*/true);
OMPBuilder.Config.setIsTargetCodegen(true);
llvm::omp::RuntimeFunction RTLFunc = OMPRTL___tgt_target_data_begin_mapper;
Builder.restoreIP(OMPBuilder.createTargetData(
Loc, Builder.saveIP(), MapTypeFlagsTo, MapNames, MapperAllocas,
/* IsBegin= */ true, DeviceID, /* IfCond= */ nullptr, ProcessMapOpCB));
Loc, AllocaIP, Builder.saveIP(), Builder.getInt64(DeviceID),
/* IfCond= */ nullptr, Info, GenMapInfoCB, &RTLFunc));
CallInst *TargetDataCall = dyn_cast<CallInst>(&BB->back());
EXPECT_NE(TargetDataCall, nullptr);
@ -4962,18 +4943,9 @@ TEST_F(OpenMPIRBuilderTest, TargetExitData) {
OMPBuilder.initialize();
F->setName("func");
IRBuilder<> Builder(BB);
OpenMPIRBuilder::LocationDescription Loc({Builder.saveIP(), DL});
unsigned NumDataOperands = 1;
int64_t DeviceID = 2;
struct OpenMPIRBuilder::MapperAllocas MapperAllocas;
SmallVector<uint64_t> MapTypeFlagsFrom = {2};
SmallVector<Constant *> MapNames;
auto *I8PtrTy = Builder.getInt8PtrTy();
auto *ArrI8PtrTy = ArrayType::get(I8PtrTy, NumDataOperands);
auto *I64Ty = Builder.getInt64Ty();
auto *ArrI64Ty = ArrayType::get(I64Ty, NumDataOperands);
AllocaInst *Val1 =
Builder.CreateAlloca(Builder.getInt32Ty(), Builder.getInt64(1));
@ -4981,44 +4953,34 @@ TEST_F(OpenMPIRBuilderTest, TargetExitData) {
IRBuilder<>::InsertPoint AllocaIP(&F->getEntryBlock(),
F->getEntryBlock().getFirstInsertionPt());
OMPBuilder.createMapperAllocas(Builder.saveIP(), AllocaIP, NumDataOperands,
MapperAllocas);
llvm::OpenMPIRBuilder::MapInfosTy CombinedInfo;
using InsertPointTy = OpenMPIRBuilder::InsertPointTy;
auto ProcessMapOpCB = [&](InsertPointTy AllocaIP, InsertPointTy CodeGenIP) {
Value *DataValue = Val1;
Value *DataPtrBase;
Value *DataPtr;
DataPtrBase = DataValue;
DataPtr = DataValue;
Builder.restoreIP(CodeGenIP);
auto GenMapInfoCB =
[&](InsertPointTy codeGenIP) -> llvm::OpenMPIRBuilder::MapInfosTy & {
// Get map clause information.
Builder.restoreIP(codeGenIP);
Value *Null = Constant::getNullValue(DataValue->getType()->getPointerTo());
Value *SizeGep =
Builder.CreateGEP(DataValue->getType(), Null, Builder.getInt32(1));
Value *SizePtrToInt = Builder.CreatePtrToInt(SizeGep, I64Ty);
Value *PtrBaseGEP =
Builder.CreateInBoundsGEP(ArrI8PtrTy, MapperAllocas.ArgsBase,
{Builder.getInt32(0), Builder.getInt32(0)});
Value *PtrBaseCast = Builder.CreateBitCast(
PtrBaseGEP, DataPtrBase->getType()->getPointerTo());
Builder.CreateStore(DataPtrBase, PtrBaseCast);
Value *PtrGEP =
Builder.CreateInBoundsGEP(ArrI8PtrTy, MapperAllocas.Args,
{Builder.getInt32(0), Builder.getInt32(0)});
Value *PtrCast =
Builder.CreateBitCast(PtrGEP, DataPtr->getType()->getPointerTo());
Builder.CreateStore(DataPtr, PtrCast);
Value *SizeGEP =
Builder.CreateInBoundsGEP(ArrI64Ty, MapperAllocas.ArgSizes,
{Builder.getInt32(0), Builder.getInt32(0)});
Builder.CreateStore(SizePtrToInt, SizeGEP);
CombinedInfo.BasePointers.emplace_back(Val1);
CombinedInfo.Pointers.emplace_back(Val1);
CombinedInfo.Sizes.emplace_back(Builder.getInt64(4));
CombinedInfo.Types.emplace_back(llvm::omp::OpenMPOffloadMappingFlags(2));
uint32_t temp;
CombinedInfo.Names.emplace_back(
OMPBuilder.getOrCreateSrcLocStr("unknown", temp));
return CombinedInfo;
};
llvm::OpenMPIRBuilder::TargetDataInfo Info(
/*RequiresDevicePointerInfo=*/false,
/*SeparateBeginEndCalls=*/true);
OMPBuilder.Config.setIsTargetCodegen(true);
llvm::omp::RuntimeFunction RTLFunc = OMPRTL___tgt_target_data_end_mapper;
Builder.restoreIP(OMPBuilder.createTargetData(
Loc, Builder.saveIP(), MapTypeFlagsFrom, MapNames, MapperAllocas,
/* IsBegin= */ false, DeviceID, /* IfCond= */ nullptr, ProcessMapOpCB));
Loc, AllocaIP, Builder.saveIP(), Builder.getInt64(DeviceID),
/* IfCond= */ nullptr, Info, GenMapInfoCB, &RTLFunc));
CallInst *TargetDataCall = dyn_cast<CallInst>(&BB->back());
EXPECT_NE(TargetDataCall, nullptr);
@ -5038,18 +5000,9 @@ TEST_F(OpenMPIRBuilderTest, TargetDataRegion) {
OMPBuilder.initialize();
F->setName("func");
IRBuilder<> Builder(BB);
OpenMPIRBuilder::LocationDescription Loc({Builder.saveIP(), DL});
unsigned NumDataOperands = 1;
int64_t DeviceID = 2;
struct OpenMPIRBuilder::MapperAllocas MapperAllocas;
SmallVector<uint64_t> MapTypeFlagsToFrom = {3};
SmallVector<Constant *> MapNames;
auto *I8PtrTy = Builder.getInt8PtrTy();
auto *ArrI8PtrTy = ArrayType::get(I8PtrTy, NumDataOperands);
auto *I64Ty = Builder.getInt64Ty();
auto *ArrI64Ty = ArrayType::get(I64Ty, NumDataOperands);
AllocaInst *Val1 =
Builder.CreateAlloca(Builder.getInt32Ty(), Builder.getInt64(1));
@ -5057,57 +5010,52 @@ TEST_F(OpenMPIRBuilderTest, TargetDataRegion) {
IRBuilder<>::InsertPoint AllocaIP(&F->getEntryBlock(),
F->getEntryBlock().getFirstInsertionPt());
OMPBuilder.createMapperAllocas(Builder.saveIP(), AllocaIP, NumDataOperands,
MapperAllocas);
llvm::OpenMPIRBuilder::MapInfosTy CombinedInfo;
using InsertPointTy = OpenMPIRBuilder::InsertPointTy;
auto ProcessMapOpCB = [&](InsertPointTy AllocaIP, InsertPointTy CodeGenIP) {
Value *DataValue = Val1;
Value *DataPtrBase;
Value *DataPtr;
DataPtrBase = DataValue;
DataPtr = DataValue;
Builder.restoreIP(CodeGenIP);
auto GenMapInfoCB =
[&](InsertPointTy codeGenIP) -> llvm::OpenMPIRBuilder::MapInfosTy & {
// Get map clause information.
Builder.restoreIP(codeGenIP);
Value *Null = Constant::getNullValue(DataValue->getType()->getPointerTo());
Value *SizeGep =
Builder.CreateGEP(DataValue->getType(), Null, Builder.getInt32(1));
Value *SizePtrToInt = Builder.CreatePtrToInt(SizeGep, I64Ty);
Value *PtrBaseGEP =
Builder.CreateInBoundsGEP(ArrI8PtrTy, MapperAllocas.ArgsBase,
{Builder.getInt32(0), Builder.getInt32(0)});
Value *PtrBaseCast = Builder.CreateBitCast(
PtrBaseGEP, DataPtrBase->getType()->getPointerTo());
Builder.CreateStore(DataPtrBase, PtrBaseCast);
Value *PtrGEP =
Builder.CreateInBoundsGEP(ArrI8PtrTy, MapperAllocas.Args,
{Builder.getInt32(0), Builder.getInt32(0)});
Value *PtrCast =
Builder.CreateBitCast(PtrGEP, DataPtr->getType()->getPointerTo());
Builder.CreateStore(DataPtr, PtrCast);
Value *SizeGEP =
Builder.CreateInBoundsGEP(ArrI64Ty, MapperAllocas.ArgSizes,
{Builder.getInt32(0), Builder.getInt32(0)});
Builder.CreateStore(SizePtrToInt, SizeGEP);
CombinedInfo.BasePointers.emplace_back(Val1);
CombinedInfo.Pointers.emplace_back(Val1);
CombinedInfo.Sizes.emplace_back(Builder.getInt64(4));
CombinedInfo.Types.emplace_back(llvm::omp::OpenMPOffloadMappingFlags(3));
uint32_t temp;
CombinedInfo.Names.emplace_back(
OMPBuilder.getOrCreateSrcLocStr("unknown", temp));
return CombinedInfo;
};
auto BodyCB = [&](InsertPointTy allocaIP, InsertPointTy codeGenIP) {
Builder.restoreIP(codeGenIP);
auto *SI = Builder.CreateStore(Builder.getInt32(99), Val1);
auto *newBB = SplitBlock(Builder.GetInsertBlock(), SI);
Builder.SetInsertPoint(newBB);
auto *UI = &Builder.GetInsertBlock()->back();
SplitBlock(Builder.GetInsertBlock(), UI);
llvm::OpenMPIRBuilder::TargetDataInfo Info(
/*RequiresDevicePointerInfo=*/false,
/*SeparateBeginEndCalls=*/true);
OMPBuilder.Config.setIsTargetCodegen(true);
auto BodyCB = [&](InsertPointTy CodeGenIP, int BodyGenType) {
if (BodyGenType == 3) {
Builder.restoreIP(CodeGenIP);
CallInst *TargetDataCall = dyn_cast<CallInst>(&BB->back());
EXPECT_NE(TargetDataCall, nullptr);
EXPECT_EQ(TargetDataCall->arg_size(), 9U);
EXPECT_EQ(TargetDataCall->getCalledFunction()->getName(),
"__tgt_target_data_begin_mapper");
EXPECT_TRUE(TargetDataCall->getOperand(1)->getType()->isIntegerTy(64));
EXPECT_TRUE(TargetDataCall->getOperand(2)->getType()->isIntegerTy(32));
EXPECT_TRUE(TargetDataCall->getOperand(8)->getType()->isPointerTy());
Builder.restoreIP(CodeGenIP);
Builder.CreateStore(Builder.getInt32(99), Val1);
}
return Builder.saveIP();
};
Builder.restoreIP(OMPBuilder.createTargetData(
Loc, Builder.saveIP(), MapTypeFlagsToFrom, MapNames, MapperAllocas,
/* IsBegin= */ false, DeviceID, /* IfCond= */ nullptr, ProcessMapOpCB,
BodyCB));
Loc, AllocaIP, Builder.saveIP(), Builder.getInt64(DeviceID),
/* IfCond= */ nullptr, Info, GenMapInfoCB, nullptr, BodyCB));
CallInst *TargetDataCall =
dyn_cast<CallInst>(&Builder.GetInsertBlock()->back());
CallInst *TargetDataCall = dyn_cast<CallInst>(&BB->back());
EXPECT_NE(TargetDataCall, nullptr);
EXPECT_EQ(TargetDataCall->arg_size(), 9U);
EXPECT_EQ(TargetDataCall->getCalledFunction()->getName(),

View File

@ -1361,78 +1361,55 @@ convertOmpThreadprivate(Operation &opInst, llvm::IRBuilderBase &builder,
return success();
}
/// Process MapOperands for Target Data directives.
static LogicalResult processMapOperand(
llvm::IRBuilderBase &builder, LLVM::ModuleTranslation &moduleTranslation,
const SmallVector<Value> &mapOperands, const ArrayAttr &mapTypes,
SmallVector<uint64_t> &mapTypeFlags,
SmallVectorImpl<llvm::Constant *> &mapNames,
struct llvm::OpenMPIRBuilder::MapperAllocas &mapperAllocas) {
auto numMapOperands = mapOperands.size();
llvm::OpenMPIRBuilder *ompBuilder = moduleTranslation.getOpenMPBuilder();
llvm::PointerType *i8PtrTy = builder.getInt8PtrTy();
llvm::ArrayType *arrI8PtrTy = llvm::ArrayType::get(i8PtrTy, numMapOperands);
llvm::IntegerType *i64Ty = builder.getInt64Ty();
llvm::ArrayType *arrI64Ty = llvm::ArrayType::get(i64Ty, numMapOperands);
int64_t getSizeInBytes(DataLayout &DL, const mlir::Type &type) {
if (isa<LLVM::LLVMPointerType>(type))
return DL.getTypeSize(cast<LLVM::LLVMPointerType>(type).getElementType());
return 0;
}
static void genMapInfos(llvm::IRBuilderBase &builder,
LLVM::ModuleTranslation &moduleTranslation,
DataLayout &DL,
llvm::OpenMPIRBuilder::MapInfosTy &combinedInfo,
const SmallVector<Value> &mapOperands,
const ArrayAttr &mapTypes) {
// Get map clause information.
llvm::OpenMPIRBuilder *ompBuilder = moduleTranslation.getOpenMPBuilder();
unsigned index = 0;
for (const auto &mapOp : mapOperands) {
const auto &mapTypeOp = mapTypes[index];
llvm::Value *mapOpValue = moduleTranslation.lookupValue(mapOp);
llvm::Value *mapOpPtrBase;
llvm::Value *mapOpPtr;
llvm::Value *mapOpSize;
if (isa<LLVM::LLVMPointerType>(mapOp.getType())) {
mapOpPtrBase = mapOpValue;
mapOpPtr = mapOpValue;
mapOpSize = ompBuilder->getSizeInBytes(mapOpValue);
} else {
return failure();
if (!mapOp.getType().isa<LLVM::LLVMPointerType>()) {
// TODO: Only LLVMPointerTypes are handled.
combinedInfo.BasePointers.clear();
combinedInfo.Pointers.clear();
combinedInfo.Sizes.clear();
combinedInfo.Types.clear();
combinedInfo.Names.clear();
return;
}
// Store base pointer extracted from operand into the i-th position of
// argBase.
llvm::Value *ptrBaseGEP = builder.CreateInBoundsGEP(
arrI8PtrTy, mapperAllocas.ArgsBase,
{builder.getInt32(0), builder.getInt32(index)});
llvm::Value *ptrBaseCast = builder.CreateBitCast(
ptrBaseGEP, mapOpPtrBase->getType()->getPointerTo());
builder.CreateStore(mapOpPtrBase, ptrBaseCast);
// Store pointer extracted from operand into the i-th position of args.
llvm::Value *ptrGEP = builder.CreateInBoundsGEP(
arrI8PtrTy, mapperAllocas.Args,
{builder.getInt32(0), builder.getInt32(index)});
llvm::Value *ptrCast =
builder.CreateBitCast(ptrGEP, mapOpPtr->getType()->getPointerTo());
builder.CreateStore(mapOpPtr, ptrCast);
// Store size extracted from operand into the i-th position of argSizes.
llvm::Value *sizeGEP = builder.CreateInBoundsGEP(
arrI64Ty, mapperAllocas.ArgSizes,
{builder.getInt32(0), builder.getInt32(index)});
builder.CreateStore(mapOpSize, sizeGEP);
mapTypeFlags.push_back(dyn_cast<mlir::IntegerAttr>(mapTypeOp).getInt());
llvm::Constant *mapName =
mlir::LLVM::createMappingInformation(mapOp.getLoc(), *ompBuilder);
mapNames.push_back(mapName);
++index;
llvm::Value *mapOpValue = moduleTranslation.lookupValue(mapOp);
combinedInfo.BasePointers.emplace_back(mapOpValue);
combinedInfo.Pointers.emplace_back(mapOpValue);
combinedInfo.Names.emplace_back(
mlir::LLVM::createMappingInformation(mapOp.getLoc(), *ompBuilder));
combinedInfo.Types.emplace_back(llvm::omp::OpenMPOffloadMappingFlags(
mapTypes[index].dyn_cast<mlir::IntegerAttr>().getInt()));
combinedInfo.Sizes.emplace_back(
builder.getInt64(getSizeInBytes(DL, mapOp.getType())));
index++;
}
return success();
}
static LogicalResult
convertOmpTargetData(Operation *op, llvm::IRBuilderBase &builder,
LLVM::ModuleTranslation &moduleTranslation) {
unsigned numMapOperands;
llvm::Value *ifCond = nullptr;
int64_t deviceID = llvm::omp::OMP_DEVICEID_UNDEF;
SmallVector<Value> mapOperands;
ArrayAttr mapTypes;
llvm::omp::RuntimeFunction RTLFn;
DataLayout DL = DataLayout(op->getParentOfType<ModuleOp>());
llvm::OpenMPIRBuilder *ompBuilder = moduleTranslation.getOpenMPBuilder();
@ -1453,7 +1430,6 @@ convertOmpTargetData(Operation *op, llvm::IRBuilderBase &builder,
dyn_cast<mlir::IntegerAttr>(constOp.getValue()))
deviceID = intAttr.getInt();
numMapOperands = dataOp.getMapOperands().size();
mapOperands = dataOp.getMapOperands();
mapTypes = dataOp.getMapTypes();
return success();
@ -1471,8 +1447,7 @@ convertOmpTargetData(Operation *op, llvm::IRBuilderBase &builder,
if (auto intAttr =
dyn_cast<mlir::IntegerAttr>(constOp.getValue()))
deviceID = intAttr.getInt();
numMapOperands = enterDataOp.getMapOperands().size();
RTLFn = llvm::omp::OMPRTL___tgt_target_data_begin_mapper;
mapOperands = enterDataOp.getMapOperands();
mapTypes = enterDataOp.getMapTypes();
return success();
@ -1491,7 +1466,7 @@ convertOmpTargetData(Operation *op, llvm::IRBuilderBase &builder,
dyn_cast<mlir::IntegerAttr>(constOp.getValue()))
deviceID = intAttr.getInt();
numMapOperands = exitDataOp.getMapOperands().size();
RTLFn = llvm::omp::OMPRTL___tgt_target_data_end_mapper;
mapOperands = exitDataOp.getMapOperands();
mapTypes = exitDataOp.getMapTypes();
return success();
@ -1504,46 +1479,55 @@ convertOmpTargetData(Operation *op, llvm::IRBuilderBase &builder,
if (failed(result))
return failure();
using InsertPointTy = llvm::OpenMPIRBuilder::InsertPointTy;
// Fill up the arrays with all the mapped variables.
llvm::OpenMPIRBuilder::MapInfosTy combinedInfo;
auto genMapInfoCB =
[&](InsertPointTy codeGenIP) -> llvm::OpenMPIRBuilder::MapInfosTy & {
builder.restoreIP(codeGenIP);
genMapInfos(builder, moduleTranslation, DL, combinedInfo, mapOperands,
mapTypes);
return combinedInfo;
};
LogicalResult bodyGenStatus = success();
using BodyGenTy = llvm::OpenMPIRBuilder::BodyGenTy;
auto bodyGenCB = [&](InsertPointTy codeGenIP, BodyGenTy bodyGenType) {
switch (bodyGenType) {
case BodyGenTy::Priv:
break;
case BodyGenTy::DupNoPriv:
break;
case BodyGenTy::NoPriv: {
// DataOp has only one region associated with it.
auto &region = cast<omp::DataOp>(op).getRegion();
builder.restoreIP(codeGenIP);
bodyGenStatus = inlineConvertOmpRegions(region, "omp.data.region",
builder, moduleTranslation);
}
}
return builder.saveIP();
};
llvm::OpenMPIRBuilder::LocationDescription ompLoc(builder);
llvm::OpenMPIRBuilder::InsertPointTy allocaIP =
findAllocaInsertPoint(builder, moduleTranslation);
struct llvm::OpenMPIRBuilder::MapperAllocas mapperAllocas;
SmallVector<uint64_t> mapTypeFlags;
SmallVector<llvm::Constant *> mapNames;
ompBuilder->createMapperAllocas(builder.saveIP(), allocaIP, numMapOperands,
mapperAllocas);
using InsertPointTy = llvm::OpenMPIRBuilder::InsertPointTy;
LogicalResult processMapOpStatus = success();
auto processMapOpCB = [&](InsertPointTy allocaIP, InsertPointTy codeGenIP) {
builder.restoreIP(codeGenIP);
processMapOpStatus =
processMapOperand(builder, moduleTranslation, mapOperands, mapTypes,
mapTypeFlags, mapNames, mapperAllocas);
};
LogicalResult bodyGenStatus = success();
auto bodyCB = [&](InsertPointTy allocaIP, InsertPointTy codeGenIP) {
// DataOp has only one region associated with it.
auto &region = cast<omp::DataOp>(op).getRegion();
builder.restoreIP(codeGenIP);
bodyGenStatus = inlineConvertOmpRegions(region, "omp.data.region", builder,
moduleTranslation);
};
// TODO: Add support for DevicePointerInfo
llvm::OpenMPIRBuilder::TargetDataInfo info(
/*RequiresDevicePointerInfo=*/false,
/*SeparateBeginEndCalls=*/true);
if (isa<omp::DataOp>(op)) {
builder.restoreIP(ompBuilder->createTargetData(
ompLoc, builder.saveIP(), mapTypeFlags, mapNames, mapperAllocas,
/*IsBegin=*/false, deviceID, ifCond, processMapOpCB, bodyCB));
ompLoc, allocaIP, builder.saveIP(), builder.getInt64(deviceID), ifCond,
info, genMapInfoCB, nullptr, bodyGenCB));
} else {
builder.restoreIP(ompBuilder->createTargetData(
ompLoc, builder.saveIP(), mapTypeFlags, mapNames, mapperAllocas,
isa<omp::EnterDataOp>(op), deviceID, ifCond, processMapOpCB));
ompLoc, allocaIP, builder.saveIP(), builder.getInt64(deviceID), ifCond,
info, genMapInfoCB, &RTLFn));
}
if (failed(processMapOpStatus))
return processMapOpStatus;
return bodyGenStatus;
}
@ -1554,7 +1538,7 @@ LogicalResult convertFlagsAttr(Operation *op, mlir::omp::FlagsAttr attribute,
LLVM::ModuleTranslation &moduleTranslation) {
if (!cast<mlir::ModuleOp>(op))
return failure();
llvm::OpenMPIRBuilder *ompBuilder = moduleTranslation.getOpenMPBuilder();
ompBuilder->createGlobalFlag(

View File

@ -11,29 +11,28 @@ llvm.func @_QPopenmp_target_data() {
llvm.return
}
// CHECK: @.offload_sizes = private unnamed_addr constant [1 x i64] [i64 4]
// CHECK: @.offload_maptypes = private unnamed_addr constant [1 x i64] [i64 3]
// CHECK-LABEL: define void @_QPopenmp_target_data() {
// CHECK: %[[VAL_0:.*]] = alloca [1 x ptr], align 8
// CHECK: %[[VAL_1:.*]] = alloca [1 x ptr], align 8
// CHECK: %[[VAL_2:.*]] = alloca [1 x i64], align 8
// CHECK: %[[VAL_2:.*]] = alloca [1 x ptr], align 8
// CHECK: %[[VAL_3:.*]] = alloca i32, i64 1, align 4
// CHECK: br label %[[VAL_4:.*]]
// CHECK: [[VAL_4]]:
// CHECK: %[[VAL_5:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_0]], i32 0, i32 0
// CHECK: store ptr %[[VAL_3]], ptr %[[VAL_5]], align 8
// CHECK: %[[VAL_6:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_1]], i32 0, i32 0
// CHECK: entry: ; preds = %[[VAL_5:.*]]
// CHECK: %[[VAL_6:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_0]], i32 0, i32 0
// CHECK: store ptr %[[VAL_3]], ptr %[[VAL_6]], align 8
// CHECK: %[[VAL_7:.*]] = getelementptr inbounds [1 x i64], ptr %[[VAL_2]], i32 0, i32 0
// CHECK: store i64 ptrtoint (ptr getelementptr (ptr, ptr null, i32 1) to i64), ptr %[[VAL_7]], align 4
// CHECK: %[[VAL_8:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_0]], i32 0, i32 0
// CHECK: %[[VAL_9:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_1]], i32 0, i32 0
// CHECK: %[[VAL_10:.*]] = getelementptr inbounds [1 x i64], ptr %[[VAL_2]], i32 0, i32 0
// CHECK: call void @__tgt_target_data_begin_mapper(ptr @2, i64 -1, i32 1, ptr %[[VAL_8]], ptr %[[VAL_9]], ptr %[[VAL_10]], ptr @.offload_maptypes, ptr @.offload_mapnames, ptr null)
// CHECK: %[[VAL_7:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_1]], i32 0, i32 0
// CHECK: store ptr %[[VAL_3]], ptr %[[VAL_7]], align 8
// CHECK: %[[VAL_8:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_2]], i64 0, i64 0
// CHECK: store ptr null, ptr %[[VAL_8]], align 8
// CHECK: %[[VAL_9:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_0]], i32 0, i32 0
// CHECK: %[[VAL_10:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_1]], i32 0, i32 0
// CHECK: call void @__tgt_target_data_begin_mapper(ptr @2, i64 -1, i32 1, ptr %[[VAL_9]], ptr %[[VAL_10]], ptr @.offload_sizes, ptr @.offload_maptypes, ptr null, ptr null)
// CHECK: store i32 99, ptr %[[VAL_3]], align 4
// CHECK: %[[VAL_11:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_0]], i32 0, i32 0
// CHECK: %[[VAL_12:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_1]], i32 0, i32 0
// CHECK: %[[VAL_13:.*]] = getelementptr inbounds [1 x i64], ptr %[[VAL_2]], i32 0, i32 0
// CHECK: call void @__tgt_target_data_end_mapper(ptr @2, i64 -1, i32 1, ptr %[[VAL_11]], ptr %[[VAL_12]], ptr %[[VAL_13]], ptr @.offload_maptypes, ptr @.offload_mapnames, ptr null)
// CHECK: call void @__tgt_target_data_end_mapper(ptr @2, i64 -1, i32 1, ptr %[[VAL_11]], ptr %[[VAL_12]], ptr @.offload_sizes, ptr @.offload_maptypes, ptr null, ptr null)
// CHECK: ret void
// -----
@ -51,35 +50,34 @@ llvm.func @_QPopenmp_target_data_region(%1 : !llvm.ptr<array<1024 x i32>>) {
llvm.return
}
// CHECK: @.offload_sizes = private unnamed_addr constant [1 x i64] [i64 4096]
// CHECK: @.offload_maptypes = private unnamed_addr constant [1 x i64] [i64 2]
// CHECK-LABEL: define void @_QPopenmp_target_data_region
// CHECK: (ptr %[[ARG_0:.*]]) {
// CHECK: %[[VAL_0:.*]] = alloca [1 x ptr], align 8
// CHECK: %[[VAL_1:.*]] = alloca [1 x ptr], align 8
// CHECK: %[[VAL_2:.*]] = alloca [1 x i64], align 8
// CHECK: %[[VAL_2:.*]] = alloca [1 x ptr], align 8
// CHECK: br label %[[VAL_3:.*]]
// CHECK: [[VAL_3]]:
// CHECK: %[[VAL_4:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_0]], i32 0, i32 0
// CHECK: store ptr %[[VAL_5:.*]], ptr %[[VAL_4]], align 8
// CHECK: %[[VAL_6:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_1]], i32 0, i32 0
// CHECK: store ptr %[[VAL_5]], ptr %[[VAL_6]], align 8
// CHECK: %[[VAL_7:.*]] = getelementptr inbounds [1 x i64], ptr %[[VAL_2]], i32 0, i32 0
// CHECK: store i64 ptrtoint (ptr getelementptr (ptr, ptr null, i32 1) to i64), ptr %[[VAL_7]], align 4
// CHECK: %[[VAL_8:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_0]], i32 0, i32 0
// CHECK: %[[VAL_9:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_1]], i32 0, i32 0
// CHECK: %[[VAL_10:.*]] = getelementptr inbounds [1 x i64], ptr %[[VAL_2]], i32 0, i32 0
// CHECK: call void @__tgt_target_data_begin_mapper(ptr @2, i64 -1, i32 1, ptr %[[VAL_8]], ptr %[[VAL_9]], ptr %[[VAL_10]], ptr @.offload_maptypes, ptr @.offload_mapnames, ptr null)
// CHECK: %[[VAL_11:.*]] = getelementptr [1024 x i32], ptr %[[VAL_5]], i32 0, i64 0
// CHECK: entry: ; preds = %[[VAL_4:.*]]
// CHECK: %[[VAL_5:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_0]], i32 0, i32 0
// CHECK: store ptr %[[VAL_6:.*]], ptr %[[VAL_5]], align 8
// CHECK: %[[VAL_7:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_1]], i32 0, i32 0
// CHECK: store ptr %[[VAL_6]], ptr %[[VAL_7]], align 8
// CHECK: %[[VAL_8:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_2]], i64 0, i64 0
// CHECK: store ptr null, ptr %[[VAL_8]], align 8
// CHECK: %[[VAL_9:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_0]], i32 0, i32 0
// CHECK: %[[VAL_10:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_1]], i32 0, i32 0
// CHECK: call void @__tgt_target_data_begin_mapper(ptr @2, i64 -1, i32 1, ptr %[[VAL_9]], ptr %[[VAL_10]], ptr @.offload_sizes, ptr @.offload_maptypes, ptr null, ptr null)
// CHECK: %[[VAL_11:.*]] = getelementptr [1024 x i32], ptr %[[VAL_6]], i32 0, i64 0
// CHECK: store i32 99, ptr %[[VAL_11]], align 4
// CHECK: %[[VAL_12:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_0]], i32 0, i32 0
// CHECK: %[[VAL_13:.*]] = getelementptr inbounds [1 x ptr], ptr %[[VAL_1]], i32 0, i32 0
// CHECK: %[[VAL_14:.*]] = getelementptr inbounds [1 x i64], ptr %[[VAL_2]], i32 0, i32 0
// CHECK: call void @__tgt_target_data_end_mapper(ptr @2, i64 -1, i32 1, ptr %[[VAL_12]], ptr %[[VAL_13]], ptr %[[VAL_14]], ptr @.offload_maptypes, ptr @.offload_mapnames, ptr null)
// CHECK: call void @__tgt_target_data_end_mapper(ptr @2, i64 -1, i32 1, ptr %[[VAL_12]], ptr %[[VAL_13]], ptr @.offload_sizes, ptr @.offload_maptypes, ptr null, ptr null)
// CHECK: ret void
// -----
llvm.func @_QPomp_target_enter_exit(%1 : !llvm.ptr<array<1024 x i32>>, %3 : !llvm.ptr<array<1024 x i32>>) {
llvm.func @_QPomp_target_enter_exit(%1 : !llvm.ptr<array<1024 x i32>>, %3 : !llvm.ptr<array<512 x i32>>) {
%4 = llvm.mlir.constant(1 : i64) : i64
%5 = llvm.alloca %4 x i32 {bindc_name = "dvc", in_type = i32, operand_segment_sizes = array<i32: 0, 0>, uniq_name = "_QFomp_target_enter_exitEdvc"} : (i64) -> !llvm.ptr<i32>
%6 = llvm.mlir.constant(1 : i64) : i64
@ -92,25 +90,27 @@ llvm.func @_QPomp_target_enter_exit(%1 : !llvm.ptr<array<1024 x i32>>, %3 : !llv
%11 = llvm.mlir.constant(10 : i32) : i32
%12 = llvm.icmp "slt" %10, %11 : i32
%13 = llvm.load %5 : !llvm.ptr<i32>
omp.target_enter_data if(%12 : i1) device(%13 : i32) map((to -> %1 : !llvm.ptr<array<1024 x i32>>), (alloc -> %3 : !llvm.ptr<array<1024 x i32>>))
omp.target_enter_data if(%12 : i1) device(%13 : i32) map((to -> %1 : !llvm.ptr<array<1024 x i32>>), (alloc -> %3 : !llvm.ptr<array<512 x i32>>))
%14 = llvm.load %7 : !llvm.ptr<i32>
%15 = llvm.mlir.constant(10 : i32) : i32
%16 = llvm.icmp "sgt" %14, %15 : i32
%17 = llvm.load %5 : !llvm.ptr<i32>
omp.target_exit_data if(%16 : i1) device(%17 : i32) map((from -> %1 : !llvm.ptr<array<1024 x i32>>), (release -> %3 : !llvm.ptr<array<1024 x i32>>))
omp.target_exit_data if(%16 : i1) device(%17 : i32) map((from -> %1 : !llvm.ptr<array<1024 x i32>>), (release -> %3 : !llvm.ptr<array<512 x i32>>))
llvm.return
}
// CHECK: @.offload_sizes = private unnamed_addr constant [2 x i64] [i64 4096, i64 2048]
// CHECK: @.offload_maptypes = private unnamed_addr constant [2 x i64] [i64 1, i64 0]
// CHECK: @.offload_maptypes.1 = private unnamed_addr constant [2 x i64] [i64 2, i64 0]
// CHECK: @.offload_sizes.1 = private unnamed_addr constant [2 x i64] [i64 4096, i64 2048]
// CHECK: @.offload_maptypes.2 = private unnamed_addr constant [2 x i64] [i64 2, i64 0]
// CHECK-LABEL: define void @_QPomp_target_enter_exit
// CHECK: (ptr %[[ARG_0:.*]], ptr %[[ARG_1:.*]]) {
// CHECK: %[[VAL_0:.*]] = alloca [2 x ptr], align 8
// CHECK: %[[VAL_1:.*]] = alloca [2 x ptr], align 8
// CHECK: %[[VAL_2:.*]] = alloca [2 x i64], align 8
// CHECK: %[[VAL_2:.*]] = alloca [2 x ptr], align 8
// CHECK: %[[VAL_3:.*]] = alloca [2 x ptr], align 8
// CHECK: %[[VAL_4:.*]] = alloca [2 x ptr], align 8
// CHECK: %[[VAL_5:.*]] = alloca [2 x i64], align 8
// CHECK: %[[VAL_5:.*]] = alloca [2 x ptr], align 8
// CHECK: %[[VAL_6:.*]] = alloca i32, i64 1, align 4
// CHECK: %[[VAL_7:.*]] = alloca i32, i64 1, align 4
// CHECK: store i32 5, ptr %[[VAL_7]], align 4
@ -126,44 +126,45 @@ llvm.func @_QPomp_target_enter_exit(%1 : !llvm.ptr<array<1024 x i32>>, %3 : !llv
// CHECK: store ptr %[[VAL_16:.*]], ptr %[[VAL_15]], align 8
// CHECK: %[[VAL_17:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_4]], i32 0, i32 0
// CHECK: store ptr %[[VAL_16]], ptr %[[VAL_17]], align 8
// CHECK: %[[VAL_18:.*]] = getelementptr inbounds [2 x i64], ptr %[[VAL_5]], i32 0, i32 0
// CHECK: store i64 ptrtoint (ptr getelementptr (ptr, ptr null, i32 1) to i64), ptr %[[VAL_18]], align 4
// CHECK: %[[VAL_18:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_5]], i64 0, i64 0
// CHECK: store ptr null, ptr %[[VAL_18]], align 8
// CHECK: %[[VAL_19:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_3]], i32 0, i32 1
// CHECK: store ptr %[[VAL_20:.*]], ptr %[[VAL_19]], align 8
// CHECK: %[[VAL_21:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_4]], i32 0, i32 1
// CHECK: store ptr %[[VAL_20]], ptr %[[VAL_21]], align 8
// CHECK: %[[VAL_22:.*]] = getelementptr inbounds [2 x i64], ptr %[[VAL_5]], i32 0, i32 1
// CHECK: store i64 ptrtoint (ptr getelementptr (ptr, ptr null, i32 1) to i64), ptr %[[VAL_22]], align 4
// CHECK: %[[VAL_22:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_5]], i64 0, i64 1
// CHECK: store ptr null, ptr %[[VAL_22]], align 8
// CHECK: %[[VAL_23:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_3]], i32 0, i32 0
// CHECK: %[[VAL_24:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_4]], i32 0, i32 0
// CHECK: %[[VAL_25:.*]] = getelementptr inbounds [2 x i64], ptr %[[VAL_5]], i32 0, i32 0
// CHECK: call void @__tgt_target_data_begin_mapper(ptr @3, i64 -1, i32 2, ptr %[[VAL_23]], ptr %[[VAL_24]], ptr %[[VAL_25]], ptr @.offload_maptypes, ptr @.offload_mapnames, ptr null)
// CHECK: br label %[[VAL_14]]
// CHECK: omp_if.end: ; preds = %[[VAL_11]], %[[VAL_13]]
// CHECK: call void @__tgt_target_data_begin_mapper(ptr @3, i64 -1, i32 2, ptr %[[VAL_23]], ptr %[[VAL_24]], ptr @.offload_sizes, ptr @.offload_maptypes, ptr null, ptr null)
// CHECK: br label %[[VAL_25:.*]]
// CHECK: omp_if.else: ; preds = %[[VAL_11]]
// CHECK: br label %[[VAL_25]]
// CHECK: omp_if.end: ; preds = %[[VAL_14]], %[[VAL_13]]
// CHECK: %[[VAL_26:.*]] = load i32, ptr %[[VAL_7]], align 4
// CHECK: %[[VAL_27:.*]] = icmp sgt i32 %[[VAL_26]], 10
// CHECK: %[[VAL_28:.*]] = load i32, ptr %[[VAL_6]], align 4
// CHECK: br i1 %[[VAL_27]], label %[[VAL_29:.*]], label %[[VAL_30:.*]]
// CHECK: omp_if.then4: ; preds = %[[VAL_14]]
// CHECK: omp_if.then1: ; preds = %[[VAL_25]]
// CHECK: %[[VAL_31:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_0]], i32 0, i32 0
// CHECK: store ptr %[[VAL_16]], ptr %[[VAL_31]], align 8
// CHECK: %[[VAL_32:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_1]], i32 0, i32 0
// CHECK: store ptr %[[VAL_16]], ptr %[[VAL_32]], align 8
// CHECK: %[[VAL_33:.*]] = getelementptr inbounds [2 x i64], ptr %[[VAL_2]], i32 0, i32 0
// CHECK: store i64 ptrtoint (ptr getelementptr (ptr, ptr null, i32 1) to i64), ptr %[[VAL_33]], align 4
// CHECK: %[[VAL_33:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_2]], i64 0, i64 0
// CHECK: store ptr null, ptr %[[VAL_33]], align 8
// CHECK: %[[VAL_34:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_0]], i32 0, i32 1
// CHECK: store ptr %[[VAL_20]], ptr %[[VAL_34]], align 8
// CHECK: %[[VAL_35:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_1]], i32 0, i32 1
// CHECK: store ptr %[[VAL_20]], ptr %[[VAL_35]], align 8
// CHECK: %[[VAL_36:.*]] = getelementptr inbounds [2 x i64], ptr %[[VAL_2]], i32 0, i32 1
// CHECK: store i64 ptrtoint (ptr getelementptr (ptr, ptr null, i32 1) to i64), ptr %[[VAL_36]], align 4
// CHECK: %[[VAL_36:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_2]], i64 0, i64 1
// CHECK: store ptr null, ptr %[[VAL_36]], align 8
// CHECK: %[[VAL_37:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_0]], i32 0, i32 0
// CHECK: %[[VAL_38:.*]] = getelementptr inbounds [2 x ptr], ptr %[[VAL_1]], i32 0, i32 0
// CHECK: %[[VAL_39:.*]] = getelementptr inbounds [2 x i64], ptr %[[VAL_2]], i32 0, i32 0
// CHECK: call void @__tgt_target_data_end_mapper(ptr @3, i64 -1, i32 2, ptr %[[VAL_37]], ptr %[[VAL_38]], ptr %[[VAL_39]], ptr @.offload_maptypes.1, ptr @.offload_mapnames.2, ptr null)
// CHECK: br label %[[VAL_30]]
// CHECK: omp_if.end5: ; preds = %[[VAL_14]], %[[VAL_29]]
// CHECK: call void @__tgt_target_data_end_mapper(ptr @3, i64 -1, i32 2, ptr %[[VAL_37]], ptr %[[VAL_38]], ptr @.offload_sizes.1, ptr @.offload_maptypes.2, ptr null, ptr null)
// CHECK: br label %[[VAL_39:.*]]
// CHECK: omp_if.else5: ; preds = %[[VAL_25]]
// CHECK: br label %[[VAL_39]]
// CHECK: omp_if.end6: ; preds = %[[VAL_30]], %[[VAL_29]]
// CHECK: ret void
// -----