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

CodeGen: clang-format goodness 

The changed files are not yet clang-format clean, but we are getting close.

llvm-svn: 174403
This commit is contained in:
Tobias Grosser 2013-02-05 18:01:29 +00:00
parent dc69f6fbca
commit c14582f276
7 changed files with 415 additions and 516 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

208
polly/lib/CodeGen/BlockGenerators.cpp
View File

@ -31,15 +31,13 @@ using namespace llvm;
using namespace polly;
static cl::opt<bool>
Aligned("enable-polly-aligned",
cl::desc("Assumed aligned memory accesses."), cl::Hidden,
cl::value_desc("OpenMP code generation enabled if true"),
cl::init(false), cl::ZeroOrMore);
Aligned("enable-polly-aligned", cl::desc("Assumed aligned memory accesses."),
cl::Hidden, cl::value_desc("OpenMP code generation enabled if true"),
cl::init(false), cl::ZeroOrMore);
static cl::opt<bool>
SCEVCodegen("polly-codegen-scev",
cl::desc("Use SCEV based code generation."), cl::Hidden,
cl::init(false), cl::ZeroOrMore);
SCEVCodegen("polly-codegen-scev", cl::desc("Use SCEV based code generation."),
cl::Hidden, cl::init(false), cl::ZeroOrMore);
/// The SCEVRewriter takes a scalar evolution expression and updates the
/// following components:
@ -81,7 +79,7 @@ SCEVCodegen("polly-codegen-scev",
/// - Instructions that reference operands already calculated within the
/// basic block.
/// - Store instructions
struct SCEVRewriter : public SCEVVisitor<SCEVRewriter, const SCEV*> {
struct SCEVRewriter : public SCEVVisitor<SCEVRewriter, const SCEV *> {
public:
static const SCEV *rewrite(const SCEV *scev, Scop &S, ScalarEvolution &SE,
ValueMapT &GlobalMap, ValueMapT &BBMap) {
@ -114,13 +112,10 @@ public:
return Expr;
}
return SCEVVisitor<SCEVRewriter, const SCEV*>::visit(Expr);
return SCEVVisitor<SCEVRewriter, const SCEV *>::visit(Expr);
}
const SCEV *visitConstant(const SCEVConstant *Constant) {
return Constant;
}
const SCEV *visitConstant(const SCEVConstant *Constant) { return Constant; }
const SCEV *visitTruncateExpr(const SCEVTruncateExpr *Expr) {
const SCEV *Operand = visit(Expr->getOperand());
@ -364,13 +359,13 @@ Value *BlockGenerator::getNewValue(const Value *Old, ValueMapT &BBMap,
// We assume constants never change.
// This avoids map lookups for many calls to this function.
if (isa<Constant>(Old))
return const_cast<Value*>(Old);
return const_cast<Value *>(Old);
if (GlobalMap.count(Old)) {
Value *New = GlobalMap[Old];
if (Old->getType()->getScalarSizeInBits()
< New->getType()->getScalarSizeInBits())
if (Old->getType()->getScalarSizeInBits() <
New->getType()->getScalarSizeInBits())
New = Builder.CreateTruncOrBitCast(New, Old->getType());
return New;
@ -381,11 +376,10 @@ Value *BlockGenerator::getNewValue(const Value *Old, ValueMapT &BBMap,
}
if (SCEVCodegen && SE.isSCEVable(Old->getType()))
if (const SCEV *Scev = SE.getSCEV(const_cast<Value*>(Old)))
if (const SCEV *Scev = SE.getSCEV(const_cast<Value *>(Old)))
if (!isa<SCEVCouldNotCompute>(Scev)) {
const SCEV *NewScev = SCEVRewriter::rewrite(Scev,
*Statement.getParent(), SE,
GlobalMap, BBMap);
const SCEV *NewScev = SCEVRewriter::rewrite(
Scev, *Statement.getParent(), SE, GlobalMap, BBMap);
SCEVExpander Expander(SE, "polly");
Value *Expanded = Expander.expandCodeFor(NewScev, Old->getType(),
Builder.GetInsertPoint());
@ -405,7 +399,7 @@ Value *BlockGenerator::getNewValue(const Value *Old, ValueMapT &BBMap,
// Everything else is probably a scop-constant value defined as global,
// function parameter or an instruction not within the scop.
return const_cast<Value*>(Old);
return const_cast<Value *>(Old);
}
void BlockGenerator::copyInstScalar(const Instruction *Inst, ValueMapT &BBMap,
@ -414,13 +408,14 @@ void BlockGenerator::copyInstScalar(const Instruction *Inst, ValueMapT &BBMap,
// Replace old operands with the new ones.
for (Instruction::const_op_iterator OI = Inst->op_begin(),
OE = Inst->op_end(); OI != OE; ++OI) {
OE = Inst->op_end();
OI != OE; ++OI) {
Value *OldOperand = *OI;
Value *NewOperand = getNewValue(OldOperand, BBMap, GlobalMap);
if (!NewOperand) {
assert(!isa<StoreInst>(NewInst)
&& "Store instructions are always needed!");
assert(!isa<StoreInst>(NewInst) &&
"Store instructions are always needed!");
delete NewInst;
return;
}
@ -435,9 +430,9 @@ void BlockGenerator::copyInstScalar(const Instruction *Inst, ValueMapT &BBMap,
NewInst->setName("p_" + Inst->getName());
}
std::vector<Value*> BlockGenerator::getMemoryAccessIndex(
__isl_keep isl_map *AccessRelation, Value *BaseAddress,
ValueMapT &BBMap, ValueMapT &GlobalMap) {
std::vector<Value *> BlockGenerator::getMemoryAccessIndex(
__isl_keep isl_map *AccessRelation, Value *BaseAddress, ValueMapT &BBMap,
ValueMapT &GlobalMap) {
assert((isl_map_dim(AccessRelation, isl_dim_out) == 1) &&
"Only single dimensional access functions supported");
@ -456,7 +451,7 @@ std::vector<Value*> BlockGenerator::getMemoryAccessIndex(
Type *Ty = Builder.getInt64Ty();
OffsetValue = Builder.CreateIntCast(OffsetValue, Ty, true);
std::vector<Value*> IndexArray;
std::vector<Value *> IndexArray;
Value *NullValue = Constant::getNullValue(Ty);
IndexArray.push_back(NullValue);
IndexArray.push_back(OffsetValue);
@ -464,20 +459,18 @@ std::vector<Value*> BlockGenerator::getMemoryAccessIndex(
}
Value *BlockGenerator::getNewAccessOperand(
__isl_keep isl_map *NewAccessRelation, Value *BaseAddress,
ValueMapT &BBMap, ValueMapT &GlobalMap) {
std::vector<Value*> IndexArray = getMemoryAccessIndex(NewAccessRelation,
BaseAddress,
BBMap, GlobalMap);
Value *NewOperand = Builder.CreateGEP(BaseAddress, IndexArray,
"p_newarrayidx_");
__isl_keep isl_map *NewAccessRelation, Value *BaseAddress, ValueMapT &BBMap,
ValueMapT &GlobalMap) {
std::vector<Value *> IndexArray =
getMemoryAccessIndex(NewAccessRelation, BaseAddress, BBMap, GlobalMap);
Value *NewOperand =
Builder.CreateGEP(BaseAddress, IndexArray, "p_newarrayidx_");
return NewOperand;
}
Value *BlockGenerator::generateLocationAccessed(const Instruction *Inst,
const Value *Pointer,
ValueMapT &BBMap,
ValueMapT &GlobalMap) {
Value *BlockGenerator::generateLocationAccessed(
const Instruction *Inst, const Value *Pointer, ValueMapT &BBMap,
ValueMapT &GlobalMap) {
MemoryAccess &Access = Statement.getAccessFor(Inst);
isl_map *CurrentAccessRelation = Access.getAccessRelation();
isl_map *NewAccessRelation = Access.getNewAccessRelation();
@ -490,9 +483,9 @@ Value *BlockGenerator::generateLocationAccessed(const Instruction *Inst,
if (!NewAccessRelation) {
NewPointer = getNewValue(Pointer, BBMap, GlobalMap);
} else {
Value *BaseAddress = const_cast<Value*>(Access.getBaseAddr());
NewPointer = getNewAccessOperand(NewAccessRelation, BaseAddress,
BBMap, GlobalMap);
Value *BaseAddress = const_cast<Value *>(Access.getBaseAddr());
NewPointer =
getNewAccessOperand(NewAccessRelation, BaseAddress, BBMap, GlobalMap);
}
isl_map_free(CurrentAccessRelation);
@ -500,23 +493,21 @@ Value *BlockGenerator::generateLocationAccessed(const Instruction *Inst,
return NewPointer;
}
Value *BlockGenerator::generateScalarLoad(const LoadInst *Load,
ValueMapT &BBMap,
ValueMapT &GlobalMap) {
Value *BlockGenerator::generateScalarLoad(
const LoadInst *Load, ValueMapT &BBMap, ValueMapT &GlobalMap) {
const Value *Pointer = Load->getPointerOperand();
const Instruction *Inst = dyn_cast<Instruction>(Load);
Value *NewPointer = generateLocationAccessed(Inst, Pointer, BBMap, GlobalMap);
Value *ScalarLoad = Builder.CreateLoad(NewPointer,
Load->getName() + "_p_scalar_");
Value *ScalarLoad =
Builder.CreateLoad(NewPointer, Load->getName() + "_p_scalar_");
return ScalarLoad;
}
Value *BlockGenerator::generateScalarStore(const StoreInst *Store,
ValueMapT &BBMap,
ValueMapT &GlobalMap) {
Value *BlockGenerator::generateScalarStore(
const StoreInst *Store, ValueMapT &BBMap, ValueMapT &GlobalMap) {
const Value *Pointer = Store->getPointerOperand();
Value *NewPointer = generateLocationAccessed(Store, Pointer, BBMap,
GlobalMap);
Value *NewPointer =
generateLocationAccessed(Store, Pointer, BBMap, GlobalMap);
Value *ValueOperand = getNewValue(Store->getValueOperand(), BBMap, GlobalMap);
return Builder.CreateStore(ValueOperand, NewPointer);
@ -547,8 +538,8 @@ void BlockGenerator::copyInstruction(const Instruction *Inst, ValueMapT &BBMap,
void BlockGenerator::copyBB(ValueMapT &GlobalMap) {
BasicBlock *BB = Statement.getBasicBlock();
BasicBlock *CopyBB = SplitBlock(Builder.GetInsertBlock(),
Builder.GetInsertPoint(), P);
BasicBlock *CopyBB =
SplitBlock(Builder.GetInsertBlock(), Builder.GetInsertPoint(), P);
CopyBB->setName("polly.stmt." + BB->getName());
Builder.SetInsertPoint(CopyBB->begin());
@ -556,22 +547,19 @@ void BlockGenerator::copyBB(ValueMapT &GlobalMap) {
for (BasicBlock::const_iterator II = BB->begin(), IE = BB->end(); II != IE;
++II)
copyInstruction(II, BBMap, GlobalMap);
copyInstruction(II, BBMap, GlobalMap);
}
VectorBlockGenerator::VectorBlockGenerator(IRBuilder<> &B,
VectorValueMapT &GlobalMaps,
ScopStmt &Stmt,
__isl_keep isl_map *Schedule,
Pass *P)
: BlockGenerator(B, Stmt, P), GlobalMaps(GlobalMaps), Schedule(Schedule) {
VectorBlockGenerator::VectorBlockGenerator(
IRBuilder<> &B, VectorValueMapT &GlobalMaps, ScopStmt &Stmt,
__isl_keep isl_map *Schedule, Pass *P)
: BlockGenerator(B, Stmt, P), GlobalMaps(GlobalMaps), Schedule(Schedule) {
assert(GlobalMaps.size() > 1 && "Only one vector lane found");
assert(Schedule && "No statement domain provided");
}
Value *VectorBlockGenerator::getVectorValue(const Value *Old,
ValueMapT &VectorMap,
VectorValueMapT &ScalarMaps) {
Value *VectorBlockGenerator::getVectorValue(
const Value *Old, ValueMapT &VectorMap, VectorValueMapT &ScalarMaps) {
if (VectorMap.count(Old))
return VectorMap[Old];
@ -580,11 +568,9 @@ Value *VectorBlockGenerator::getVectorValue(const Value *Old,
Value *Vector = UndefValue::get(VectorType::get(Old->getType(), Width));
for (int Lane = 0; Lane < Width; Lane++)
Vector = Builder.CreateInsertElement(Vector,
getNewValue(Old,
ScalarMaps[Lane],
GlobalMaps[Lane]),
Builder.getInt32(Lane));
Vector = Builder.CreateInsertElement(
Vector, getNewValue(Old, ScalarMaps[Lane], GlobalMaps[Lane]),
Builder.getInt32(Lane));
VectorMap[Old] = Vector;
@ -606,10 +592,10 @@ Value *VectorBlockGenerator::generateStrideOneLoad(const LoadInst *Load,
const Value *Pointer = Load->getPointerOperand();
Type *VectorPtrType = getVectorPtrTy(Pointer, getVectorWidth());
Value *NewPointer = getNewValue(Pointer, BBMap, GlobalMaps[0]);
Value *VectorPtr = Builder.CreateBitCast(NewPointer, VectorPtrType,
"vector_ptr");
LoadInst *VecLoad = Builder.CreateLoad(VectorPtr,
Load->getName() + "_p_vec_full");
Value *VectorPtr =
Builder.CreateBitCast(NewPointer, VectorPtrType, "vector_ptr");
LoadInst *VecLoad =
Builder.CreateLoad(VectorPtr, Load->getName() + "_p_vec_full");
if (!Aligned)
VecLoad->setAlignment(8);
@ -623,52 +609,47 @@ Value *VectorBlockGenerator::generateStrideZeroLoad(const LoadInst *Load,
Value *NewPointer = getNewValue(Pointer, BBMap, GlobalMaps[0]);
Value *VectorPtr = Builder.CreateBitCast(NewPointer, VectorPtrType,
Load->getName() + "_p_vec_p");
LoadInst *ScalarLoad= Builder.CreateLoad(VectorPtr,
Load->getName() + "_p_splat_one");
LoadInst *ScalarLoad =
Builder.CreateLoad(VectorPtr, Load->getName() + "_p_splat_one");
if (!Aligned)
ScalarLoad->setAlignment(8);
Constant *SplatVector =
Constant::getNullValue(VectorType::get(Builder.getInt32Ty(),
getVectorWidth()));
Constant *SplatVector = Constant::getNullValue(
VectorType::get(Builder.getInt32Ty(), getVectorWidth()));
Value *VectorLoad = Builder.CreateShuffleVector(ScalarLoad, ScalarLoad,
SplatVector,
Load->getName()
+ "_p_splat");
Value *VectorLoad = Builder.CreateShuffleVector(
ScalarLoad, ScalarLoad, SplatVector, Load->getName() + "_p_splat");
return VectorLoad;
}
Value *VectorBlockGenerator::generateUnknownStrideLoad(const LoadInst *Load,
VectorValueMapT &ScalarMaps) {
Value *VectorBlockGenerator::generateUnknownStrideLoad(
const LoadInst *Load, VectorValueMapT &ScalarMaps) {
int VectorWidth = getVectorWidth();
const Value *Pointer = Load->getPointerOperand();
VectorType *VectorType = VectorType::get(
dyn_cast<PointerType>(Pointer->getType())->getElementType(), VectorWidth);
dyn_cast<PointerType>(Pointer->getType())->getElementType(), VectorWidth);
Value *Vector = UndefValue::get(VectorType);
for (int i = 0; i < VectorWidth; i++) {
Value *NewPointer = getNewValue(Pointer, ScalarMaps[i], GlobalMaps[i]);
Value *ScalarLoad = Builder.CreateLoad(NewPointer,
Load->getName() + "_p_scalar_");
Vector = Builder.CreateInsertElement(Vector, ScalarLoad,
Builder.getInt32(i),
Load->getName() + "_p_vec_");
Value *ScalarLoad =
Builder.CreateLoad(NewPointer, Load->getName() + "_p_scalar_");
Vector = Builder.CreateInsertElement(
Vector, ScalarLoad, Builder.getInt32(i), Load->getName() + "_p_vec_");
}
return Vector;
}
void VectorBlockGenerator::generateLoad(const LoadInst *Load,
ValueMapT &VectorMap,
VectorValueMapT &ScalarMaps) {
void VectorBlockGenerator::generateLoad(
const LoadInst *Load, ValueMapT &VectorMap, VectorValueMapT &ScalarMaps) {
if (PollyVectorizerChoice >= VECTORIZER_FIRST_NEED_GROUPED_UNROLL ||
!VectorType::isValidElementType(Load->getType())) {
for (int i = 0; i < getVectorWidth(); i++)
ScalarMaps[i][Load] = generateScalarLoad(Load, ScalarMaps[i],
GlobalMaps[i]);
ScalarMaps[i][Load] =
generateScalarLoad(Load, ScalarMaps[i], GlobalMaps[i]);
return;
}
@ -689,8 +670,8 @@ void VectorBlockGenerator::copyUnaryInst(const UnaryInstruction *Inst,
ValueMapT &VectorMap,
VectorValueMapT &ScalarMaps) {
int VectorWidth = getVectorWidth();
Value *NewOperand = getVectorValue(Inst->getOperand(0), VectorMap,
ScalarMaps);
Value *NewOperand =
getVectorValue(Inst->getOperand(0), VectorMap, ScalarMaps);
assert(isa<CastInst>(Inst) && "Can not generate vector code for instruction");
@ -714,23 +695,22 @@ void VectorBlockGenerator::copyBinaryInst(const BinaryOperator *Inst,
VectorMap[Inst] = NewInst;
}
void VectorBlockGenerator::copyStore(const StoreInst *Store,
ValueMapT &VectorMap,
VectorValueMapT &ScalarMaps) {
void VectorBlockGenerator::copyStore(
const StoreInst *Store, ValueMapT &VectorMap, VectorValueMapT &ScalarMaps) {
int VectorWidth = getVectorWidth();
MemoryAccess &Access = Statement.getAccessFor(Store);
const Value *Pointer = Store->getPointerOperand();
Value *Vector = getVectorValue(Store->getValueOperand(), VectorMap,
ScalarMaps);
Value *Vector =
getVectorValue(Store->getValueOperand(), VectorMap, ScalarMaps);
if (Access.isStrideOne(isl_map_copy(Schedule))) {
Type *VectorPtrType = getVectorPtrTy(Pointer, VectorWidth);
Value *NewPointer = getNewValue(Pointer, ScalarMaps[0], GlobalMaps[0]);
Value *VectorPtr = Builder.CreateBitCast(NewPointer, VectorPtrType,
"vector_ptr");
Value *VectorPtr =
Builder.CreateBitCast(NewPointer, VectorPtrType, "vector_ptr");
StoreInst *Store = Builder.CreateStore(Vector, VectorPtr);
if (!Aligned)
@ -747,7 +727,8 @@ void VectorBlockGenerator::copyStore(const StoreInst *Store,
bool VectorBlockGenerator::hasVectorOperands(const Instruction *Inst,
ValueMapT &VectorMap) {
for (Instruction::const_op_iterator OI = Inst->op_begin(),
OE = Inst->op_end(); OI != OE; ++OI)
OE = Inst->op_end();
OI != OE; ++OI)
if (VectorMap.count(*OI))
return true;
return false;
@ -760,7 +741,8 @@ bool VectorBlockGenerator::extractScalarValues(const Instruction *Inst,
int VectorWidth = getVectorWidth();
for (Instruction::const_op_iterator OI = Inst->op_begin(),
OE = Inst->op_end(); OI != OE; ++OI) {
OE = Inst->op_end();
OI != OE; ++OI) {
ValueMapT::iterator VecOp = VectorMap.find(*OI);
if (VecOp == VectorMap.end())
@ -810,9 +792,7 @@ void VectorBlockGenerator::copyInstScalarized(const Instruction *Inst,
VectorMap[Inst] = Vector;
}
int VectorBlockGenerator::getVectorWidth() {
return GlobalMaps.size();
}
int VectorBlockGenerator::getVectorWidth() { return GlobalMaps.size(); }
void VectorBlockGenerator::copyInstruction(const Instruction *Inst,
ValueMapT &VectorMap,
@ -855,8 +835,8 @@ void VectorBlockGenerator::copyInstruction(const Instruction *Inst,
void VectorBlockGenerator::copyBB() {
BasicBlock *BB = Statement.getBasicBlock();
BasicBlock *CopyBB = SplitBlock(Builder.GetInsertBlock(),
Builder.GetInsertPoint(), P);
BasicBlock *CopyBB =
SplitBlock(Builder.GetInsertBlock(), Builder.GetInsertPoint(), P);
CopyBB->setName("polly.stmt." + BB->getName());
Builder.SetInsertPoint(CopyBB->begin());
@ -877,7 +857,7 @@ void VectorBlockGenerator::copyBB() {
VectorValueMapT ScalarBlockMap(getVectorWidth());
ValueMapT VectorBlockMap;
for (BasicBlock::const_iterator II = BB->begin(), IE = BB->end();
II != IE; ++II)
copyInstruction(II, VectorBlockMap, ScalarBlockMap);
for (BasicBlock::const_iterator II = BB->begin(), IE = BB->end(); II != IE;
++II)
copyInstruction(II, VectorBlockMap, ScalarBlockMap);
}

50
polly/lib/CodeGen/Cloog.cpp
View File

@ -97,9 +97,7 @@ public:
//close(FD[1]);
}
FILE *getInputFile() {
return input;
}
FILE *getInputFile() { return input; }
void closeInput() {
fclose(input);
@ -141,9 +139,7 @@ void Cloog::pprint(raw_ostream &OS) {
}
/// Create the Cloog AST from this program.
struct clast_root *Cloog::getClast() {
return (clast_root*)ClastRoot;
}
struct clast_root *Cloog::getClast() { return (clast_root *)ClastRoot; }
void Cloog::buildCloogOptions() {
Options = cloog_options_malloc(State);
@ -217,7 +213,7 @@ CloogInput *Cloog::buildCloogInput() {
}
void ClastVisitor::visit(const clast_stmt *stmt) {
if (CLAST_STMT_IS_A(stmt, stmt_root))
if (CLAST_STMT_IS_A(stmt, stmt_root))
assert(false && "No second root statement expected");
else if (CLAST_STMT_IS_A(stmt, stmt_ass))
return visitAssignment((const clast_assignment *)stmt);
@ -234,20 +230,13 @@ void ClastVisitor::visit(const clast_stmt *stmt) {
visit(stmt->next);
}
void ClastVisitor::visitAssignment(const clast_assignment *stmt) {
}
void ClastVisitor::visitAssignment(const clast_assignment *stmt) {}
void ClastVisitor::visitBlock(const clast_block *stmt) {
visit(stmt->body);
}
void ClastVisitor::visitBlock(const clast_block *stmt) { visit(stmt->body); }
void ClastVisitor::visitFor(const clast_for *stmt) {
visit(stmt->body);
}
void ClastVisitor::visitFor(const clast_for *stmt) { visit(stmt->body); }
void ClastVisitor::visitGuard(const clast_guard *stmt) {
visit(stmt->then);
}
void ClastVisitor::visitGuard(const clast_guard *stmt) { visit(stmt->then); }
} // End namespace polly.
@ -295,7 +284,7 @@ bool CloogExporter::runOnScop(Scop &S) {
std::string Filename = getFileName(&R);
errs() << "Writing Scop '" << R.getNameStr() << "' in function '"
<< FunctionName << "' to '" << Filename << "'...\n";
<< FunctionName << "' to '" << Filename << "'...\n";
FILE *F = fopen(Filename.c_str(), "w");
C.dump(F);
@ -310,29 +299,20 @@ void CloogExporter::getAnalysisUsage(AnalysisUsage &AU) const {
AU.addRequired<CloogInfo>();
}
static RegisterPass<CloogExporter> A("polly-export-cloog",
"Polly - Export the Cloog input file"
" (Writes a .cloog file for each Scop)"
);
static RegisterPass<CloogExporter>
A("polly-export-cloog", "Polly - Export the Cloog input file"
" (Writes a .cloog file for each Scop)");
llvm::Pass *polly::createCloogExporterPass() {
return new CloogExporter();
}
llvm::Pass *polly::createCloogExporterPass() { return new CloogExporter(); }
/// Write a .cloog input file
void CloogInfo::dump(FILE *F) {
C->dump(F);
}
void CloogInfo::dump(FILE *F) { C->dump(F); }
/// Print a source code representation of the program.
void CloogInfo::pprint(llvm::raw_ostream &OS) {
C->pprint(OS);
}
void CloogInfo::pprint(llvm::raw_ostream &OS) { C->pprint(OS); }
/// Create the Cloog AST from this program.
const struct clast_root *CloogInfo::getClast() {
return C->getClast();
}
const struct clast_root *CloogInfo::getClast() { return C->getClast(); }
void CloogInfo::releaseMemory() {
if (C) {

219
polly/lib/CodeGen/CodeGeneration.cpp
View File

@ -61,25 +61,22 @@ struct isl_set;
namespace polly {
static cl::opt<bool>
OpenMP("enable-polly-openmp",
cl::desc("Generate OpenMP parallel code"), cl::Hidden,
cl::value_desc("OpenMP code generation enabled if true"),
OpenMP("enable-polly-openmp", cl::desc("Generate OpenMP parallel code"),
cl::Hidden, cl::value_desc("OpenMP code generation enabled if true"),
cl::init(false), cl::ZeroOrMore);
#ifdef GPU_CODEGEN
static cl::opt<bool>
GPGPU("enable-polly-gpgpu",
cl::desc("Generate GPU parallel code"), cl::Hidden,
cl::value_desc("GPGPU code generation enabled if true"),
cl::init(false), cl::ZeroOrMore);
GPGPU("enable-polly-gpgpu", cl::desc("Generate GPU parallel code"), cl::Hidden,
cl::value_desc("GPGPU code generation enabled if true"), cl::init(false),
cl::ZeroOrMore);
static cl::opt<std::string>
GPUTriple("polly-gpgpu-triple",
cl::desc("Target triple for GPU code generation"),
cl::Hidden, cl::init(""));
static cl::opt<std::string> GPUTriple(
"polly-gpgpu-triple", cl::desc("Target triple for GPU code generation"),
cl::Hidden, cl::init(""));
#endif /* GPU_CODEGEN */
typedef DenseMap<const char*, Value*> CharMapT;
typedef DenseMap<const char *, Value *> CharMapT;
/// Class to generate LLVM-IR that calculates the value of a clast_expr.
class ClastExpCodeGen {
@ -140,58 +137,52 @@ Value *ClastExpCodeGen::codegen(const clast_binary *e, Type *Ty) {
switch (e->type) {
case clast_bin_mod:
return Builder.CreateSRem(LHS, RHS);
case clast_bin_fdiv:
{
// floord(n,d) ((n < 0) ? (n - d + 1) : n) / d
Value *One = ConstantInt::get(Ty, 1);
Value *Zero = ConstantInt::get(Ty, 0);
Value *Sum1 = Builder.CreateSub(LHS, RHS);
Value *Sum2 = Builder.CreateAdd(Sum1, One);
Value *isNegative = Builder.CreateICmpSLT(LHS, Zero);
Value *Dividend = Builder.CreateSelect(isNegative, Sum2, LHS);
return Builder.CreateSDiv(Dividend, RHS);
}
case clast_bin_cdiv:
{
// ceild(n,d) ((n < 0) ? n : (n + d - 1)) / d
Value *One = ConstantInt::get(Ty, 1);
Value *Zero = ConstantInt::get(Ty, 0);
Value *Sum1 = Builder.CreateAdd(LHS, RHS);
Value *Sum2 = Builder.CreateSub(Sum1, One);
Value *isNegative = Builder.CreateICmpSLT(LHS, Zero);
Value *Dividend = Builder.CreateSelect(isNegative, LHS, Sum2);
return Builder.CreateSDiv(Dividend, RHS);
}
case clast_bin_fdiv: {
// floord(n,d) ((n < 0) ? (n - d + 1) : n) / d
Value *One = ConstantInt::get(Ty, 1);
Value *Zero = ConstantInt::get(Ty, 0);
Value *Sum1 = Builder.CreateSub(LHS, RHS);
Value *Sum2 = Builder.CreateAdd(Sum1, One);
Value *isNegative = Builder.CreateICmpSLT(LHS, Zero);
Value *Dividend = Builder.CreateSelect(isNegative, Sum2, LHS);
return Builder.CreateSDiv(Dividend, RHS);
}
case clast_bin_cdiv: {
// ceild(n,d) ((n < 0) ? n : (n + d - 1)) / d
Value *One = ConstantInt::get(Ty, 1);
Value *Zero = ConstantInt::get(Ty, 0);
Value *Sum1 = Builder.CreateAdd(LHS, RHS);
Value *Sum2 = Builder.CreateSub(Sum1, One);
Value *isNegative = Builder.CreateICmpSLT(LHS, Zero);
Value *Dividend = Builder.CreateSelect(isNegative, LHS, Sum2);
return Builder.CreateSDiv(Dividend, RHS);
}
case clast_bin_div:
return Builder.CreateSDiv(LHS, RHS);
};
}
llvm_unreachable("Unknown clast binary expression type");
}
Value *ClastExpCodeGen::codegen(const clast_reduction *r, Type *Ty) {
assert(( r->type == clast_red_min
|| r->type == clast_red_max
|| r->type == clast_red_sum)
&& "Clast reduction type not supported");
assert((r->type == clast_red_min || r->type == clast_red_max ||
r->type == clast_red_sum) && "Clast reduction type not supported");
Value *old = codegen(r->elts[0], Ty);
for (int i = 1; i < r->n; ++i) {
Value *exprValue = codegen(r->elts[i], Ty);
switch (r->type) {
case clast_red_min:
{
Value *cmp = Builder.CreateICmpSLT(old, exprValue);
old = Builder.CreateSelect(cmp, old, exprValue);
break;
}
case clast_red_max:
{
Value *cmp = Builder.CreateICmpSGT(old, exprValue);
old = Builder.CreateSelect(cmp, old, exprValue);
break;
}
case clast_red_min: {
Value *cmp = Builder.CreateICmpSLT(old, exprValue);
old = Builder.CreateSelect(cmp, old, exprValue);
break;
}
case clast_red_max: {
Value *cmp = Builder.CreateICmpSGT(old, exprValue);
old = Builder.CreateSelect(cmp, old, exprValue);
break;
}
case clast_red_sum:
old = Builder.CreateAdd(old, exprValue);
break;
@ -205,7 +196,7 @@ ClastExpCodeGen::ClastExpCodeGen(IRBuilder<> &B, CharMapT &IVMap)
: Builder(B), IVS(IVMap) {}
Value *ClastExpCodeGen::codegen(const clast_expr *e, Type *Ty) {
switch(e->type) {
switch (e->type) {
case clast_expr_name:
return codegen((const clast_name *)e, Ty);
case clast_expr_term:
@ -260,11 +251,11 @@ private:
unsigned Dimension, int vectorDim,
std::vector<ValueMapT> *VectorVMap = 0);
void codegenSubstitutions(const clast_stmt *Assignment,
ScopStmt *Statement, int vectorDim = 0,
void codegenSubstitutions(const clast_stmt *Assignment, ScopStmt *Statement,
int vectorDim = 0,
std::vector<ValueMapT> *VectorVMap = 0);
void codegen(const clast_user_stmt *u, std::vector<Value*> *IVS = NULL,
void codegen(const clast_user_stmt *u, std::vector<Value *> *IVS = NULL,
const char *iterator = NULL, isl_set *scatteringDomain = 0);
void codegen(const clast_block *b);
@ -276,7 +267,7 @@ private:
///
/// Create a list of values that has to be stored into the OpenMP subfuncition
/// structure.
SetVector<Value*> getOMPValues(const clast_stmt *Body);
SetVector<Value *> getOMPValues(const clast_stmt *Body);
/// @brief Update ClastVars and ValueMap according to a value map.
///
@ -295,7 +286,7 @@ private:
/// Create a list of values that will be set to be parameters of the GPGPU
/// subfunction. These parameters represent device memory base addresses
/// and the size in bytes.
SetVector<Value*> getGPUValues(unsigned &OutputBytes);
SetVector<Value *> getGPUValues(unsigned &OutputBytes);
/// @brief Create a GPU parallel for loop.
///
@ -304,10 +295,9 @@ private:
void codegenForGPGPU(const clast_for *F);
/// @brief Get innermost for loop.
const clast_stmt *getScheduleInfo(const clast_for *F,
std::vector<int> &NumIters,
unsigned &LoopDepth,
unsigned &NonPLoopDepth);
const clast_stmt *
getScheduleInfo(const clast_for *F, std::vector<int> &NumIters,
unsigned &LoopDepth, unsigned &NonPLoopDepth);
#endif /* GPU_CODEGEN */
/// @brief Check if a loop is parallel
@ -379,15 +369,15 @@ void ClastStmtCodeGen::codegen(const clast_assignment *A, ScopStmt *Stmt,
ValueMap[PN] = RHS;
}
void ClastStmtCodeGen::codegenSubstitutions(const clast_stmt *Assignment,
ScopStmt *Statement, int vectorDim,
std::vector<ValueMapT> *VectorVMap) {
void ClastStmtCodeGen::codegenSubstitutions(
const clast_stmt *Assignment, ScopStmt *Statement, int vectorDim,
std::vector<ValueMapT> *VectorVMap) {
int Dimension = 0;
while (Assignment) {
assert(CLAST_STMT_IS_A(Assignment, stmt_ass) &&
"Substitions are expected to be assignments");
codegen((const clast_assignment *) Assignment, Statement, Dimension,
codegen((const clast_assignment *)Assignment, Statement, Dimension,
vectorDim, VectorVMap);
Assignment = Assignment->next;
Dimension++;
@ -397,18 +387,19 @@ void ClastStmtCodeGen::codegenSubstitutions(const clast_stmt *Assignment,
// Takes the cloog specific domain and translates it into a map Statement ->
// PartialSchedule, where the PartialSchedule contains all the dimensions that
// have been code generated up to this point.
static __isl_give isl_map *extractPartialSchedule(ScopStmt *Statement,
isl_set *Domain) {
static __isl_give isl_map *
extractPartialSchedule(ScopStmt *Statement, isl_set *Domain) {
isl_map *Schedule = Statement->getScattering();
int ScheduledDimensions = isl_set_dim(Domain, isl_dim_set);
int UnscheduledDimensions = isl_map_dim(Schedule, isl_dim_out) - ScheduledDimensions;
int UnscheduledDimensions =
isl_map_dim(Schedule, isl_dim_out) - ScheduledDimensions;
return isl_map_project_out(Schedule, isl_dim_out, ScheduledDimensions,
UnscheduledDimensions);
}
void ClastStmtCodeGen::codegen(const clast_user_stmt *u,
std::vector<Value*> *IVS , const char *iterator,
std::vector<Value *> *IVS, const char *iterator,
isl_set *Domain) {
ScopStmt *Statement = (ScopStmt *)u->statement->usr;
@ -427,7 +418,7 @@ void ClastStmtCodeGen::codegen(const clast_user_stmt *u,
if (IVS) {
assert(u->substitutions && "Substitutions expected!");
int i = 0;
for (std::vector<Value*>::iterator II = IVS->begin(), IE = IVS->end();
for (std::vector<Value *>::iterator II = IVS->begin(), IE = IVS->end();
II != IE; ++II) {
ClastVars[iterator] = *II;
codegenSubstitutions(u->substitutions, Statement, i, &VectorMap);
@ -473,7 +464,7 @@ void ClastStmtCodeGen::codegenForSequential(const clast_for *f) {
class ParameterVisitor : public ClastVisitor {
std::set<Value *> Values;
public:
ParameterVisitor() : ClastVisitor(), Values() { }
ParameterVisitor() : ClastVisitor(), Values() {}
void visitUser(const clast_user_stmt *Stmt) {
const ScopStmt *S = static_cast<const ScopStmt *>(Stmt->statement->usr);
@ -484,7 +475,8 @@ public:
++BI) {
const Instruction &Inst = *BI;
for (Instruction::const_op_iterator II = Inst.op_begin(),
IE = Inst.op_end(); II != IE; ++II) {
IE = Inst.op_end();
II != IE; ++II) {
Value *SrcVal = *II;
if (Instruction *OpInst = dyn_cast<Instruction>(SrcVal))
@ -500,15 +492,15 @@ public:
// Iterator to iterate over the values found.
typedef std::set<Value *>::const_iterator const_iterator;
inline const_iterator begin() const { return Values.begin(); }
inline const_iterator end() const { return Values.end(); }
inline const_iterator end() const { return Values.end(); }
};
SetVector<Value*> ClastStmtCodeGen::getOMPValues(const clast_stmt *Body) {
SetVector<Value*> Values;
SetVector<Value *> ClastStmtCodeGen::getOMPValues(const clast_stmt *Body) {
SetVector<Value *> Values;
// The clast variables
for (CharMapT::iterator I = ClastVars.begin(), E = ClastVars.end();
I != E; I++)
for (CharMapT::iterator I = ClastVars.begin(), E = ClastVars.end(); I != E;
I++)
Values.insert(I->second);
// Find the temporaries that are referenced in the clast statements'
@ -529,17 +521,18 @@ SetVector<Value*> ClastStmtCodeGen::getOMPValues(const clast_stmt *Body) {
}
void ClastStmtCodeGen::updateWithValueMap(
OMPGenerator::ValueToValueMapTy &VMap) {
std::set<Value*> Inserted;
OMPGenerator::ValueToValueMapTy &VMap) {
std::set<Value *> Inserted;
for (CharMapT::iterator I = ClastVars.begin(), E = ClastVars.end();
I != E; I++) {
for (CharMapT::iterator I = ClastVars.begin(), E = ClastVars.end(); I != E;
I++) {
ClastVars[I->first] = VMap[I->second];
Inserted.insert(I->second);
}
for (OMPGenerator::ValueToValueMapTy::iterator I = VMap.begin(),
E = VMap.end(); I != E; ++I) {
E = VMap.end();
I != E; ++I) {
if (Inserted.count(I->first))
continue;
@ -549,11 +542,11 @@ void ClastStmtCodeGen::updateWithValueMap(
static void clearDomtree(Function *F, DominatorTree &DT) {
DomTreeNode *N = DT.getNode(&F->getEntryBlock());
std::vector<BasicBlock*> Nodes;
for (po_iterator<DomTreeNode*> I = po_begin(N), E = po_end(N); I != E; ++I)
std::vector<BasicBlock *> Nodes;
for (po_iterator<DomTreeNode *> I = po_begin(N), E = po_end(N); I != E; ++I)
Nodes.push_back(I->getBlock());
for (std::vector<BasicBlock*>::iterator I = Nodes.begin(), E = Nodes.end();
for (std::vector<BasicBlock *>::iterator I = Nodes.begin(), E = Nodes.end();
I != E; ++I)
DT.eraseNode(*I);
}
@ -562,7 +555,7 @@ void ClastStmtCodeGen::codegenForOpenMP(const clast_for *For) {
Value *Stride, *LB, *UB, *IV;
BasicBlock::iterator LoopBody;
IntegerType *IntPtrTy = getIntPtrTy();
SetVector<Value*> Values;
SetVector<Value *> Values;
OMPGenerator::ValueToValueMapTy VMap;
OMPGenerator OMPGen(Builder, P);
@ -608,16 +601,17 @@ static unsigned getArraySizeInBytes(const ArrayType *AT) {
return Bytes;
}
SetVector<Value*> ClastStmtCodeGen::getGPUValues(unsigned &OutputBytes) {
SetVector<Value*> Values;
SetVector<Value *> ClastStmtCodeGen::getGPUValues(unsigned &OutputBytes) {
SetVector<Value *> Values;
OutputBytes = 0;
// Record the memory reference base addresses.
for (Scop::iterator SI = S->begin(), SE = S->end(); SI != SE; ++SI) {
ScopStmt *Stmt = *SI;
for (SmallVector<MemoryAccess*, 8>::iterator I = Stmt->memacc_begin(),
E = Stmt->memacc_end(); I != E; ++I) {
Value *BaseAddr = const_cast<Value*>((*I)->getBaseAddr());
for (SmallVector<MemoryAccess *, 8>::iterator I = Stmt->memacc_begin(),
E = Stmt->memacc_end();
I != E; ++I) {
Value *BaseAddr = const_cast<Value *>((*I)->getBaseAddr());
Values.insert((BaseAddr));
// FIXME: we assume that there is one and only one array to be written
@ -627,8 +621,8 @@ SetVector<Value*> ClastStmtCodeGen::getGPUValues(unsigned &OutputBytes) {
++NumWrites;
assert(NumWrites <= 1 &&
"We support at most one array to be written in a SCoP.");
if (const PointerType * PT =
dyn_cast<PointerType>(BaseAddr->getType())) {
if (const PointerType *PT =
dyn_cast<PointerType>(BaseAddr->getType())) {
Type *T = PT->getArrayElementType();
const ArrayType *ATy = dyn_cast<ArrayType>(T);
OutputBytes = getArraySizeInBytes(ATy);
@ -640,10 +634,9 @@ SetVector<Value*> ClastStmtCodeGen::getGPUValues(unsigned &OutputBytes) {
return Values;
}
const clast_stmt *ClastStmtCodeGen::getScheduleInfo(const clast_for *F,
std::vector<int> &NumIters,
unsigned &LoopDepth,
unsigned &NonPLoopDepth) {
const clast_stmt *ClastStmtCodeGen::getScheduleInfo(
const clast_for *F, std::vector<int> &NumIters, unsigned &LoopDepth,
unsigned &NonPLoopDepth) {
clast_stmt *Stmt = (clast_stmt *)F;
const clast_for *Result;
bool NonParaFlag = false;
@ -652,7 +645,7 @@ const clast_stmt *ClastStmtCodeGen::getScheduleInfo(const clast_for *F,
while (Stmt) {
if (CLAST_STMT_IS_A(Stmt, stmt_for)) {
const clast_for *T = (clast_for *) Stmt;
const clast_for *T = (clast_for *)Stmt;
if (isParallelFor(T)) {
if (!NonParaFlag) {
NumIters.push_back(getNumberOfIterations(T));
@ -672,8 +665,8 @@ const clast_stmt *ClastStmtCodeGen::getScheduleInfo(const clast_for *F,
"The loops should be tiled into 4-depth parallel loops and an "
"innermost non-parallel one (if exist).");
NonPLoopDepth = LoopDepth - NumIters.size();
assert(NonPLoopDepth <= 1
&& "We support only one innermost non-parallel loop currently.");
assert(NonPLoopDepth <= 1 &&
"We support only one innermost non-parallel loop currently.");
return (const clast_stmt *)Result->body;
}
@ -690,8 +683,8 @@ void ClastStmtCodeGen::codegenForGPGPU(const clast_for *F) {
// Get original IVS and ScopStmt
unsigned TiledLoopDepth, NonPLoopDepth;
const clast_stmt *InnerStmt = getScheduleInfo(F, NumIterations,
TiledLoopDepth, NonPLoopDepth);
const clast_stmt *InnerStmt =
getScheduleInfo(F, NumIterations, TiledLoopDepth, NonPLoopDepth);
const clast_stmt *TmpStmt;
const clast_user_stmt *U;
const clast_for *InnerFor;
@ -700,8 +693,8 @@ void ClastStmtCodeGen::codegenForGPGPU(const clast_for *F) {
TmpStmt = InnerFor->body;
} else
TmpStmt = InnerStmt;
U = (const clast_user_stmt *) TmpStmt;
ScopStmt *Statement = (ScopStmt *) U->statement->usr;
U = (const clast_user_stmt *)TmpStmt;
ScopStmt *Statement = (ScopStmt *)U->statement->usr;
for (unsigned i = 0; i < Statement->getNumIterators() - NonPLoopDepth; i++) {
const Value *IV = Statement->getInductionVariableForDimension(i);
IVS.insert(const_cast<Value *>(IV));
@ -726,7 +719,7 @@ void ClastStmtCodeGen::codegenForGPGPU(const clast_for *F) {
CmpInst::ICMP_SLE);
const Value *OldIV_ = Statement->getInductionVariableForDimension(2);
Value *OldIV = const_cast<Value *>(OldIV_);
VMap.insert(std::make_pair<Value*, Value*>(OldIV, IV));
VMap.insert(std::make_pair<Value *, Value *>(OldIV, IV));
}
updateWithValueMap(VMap);
@ -787,11 +780,11 @@ void ClastStmtCodeGen::codegenForVector(const clast_for *F) {
Stride = Stride.zext(LoopIVType->getBitWidth());
Value *StrideValue = ConstantInt::get(LoopIVType, Stride);
std::vector<Value*> IVS(VectorWidth);
std::vector<Value *> IVS(VectorWidth);
IVS[0] = LB;
for (int i = 1; i < VectorWidth; i++)
IVS[i] = Builder.CreateAdd(IVS[i-1], StrideValue, "p_vector_iv");
IVS[i] = Builder.CreateAdd(IVS[i - 1], StrideValue, "p_vector_iv");
isl_set *Domain = isl_set_from_cloog_domain(F->domain);
@ -872,8 +865,8 @@ void ClastStmtCodeGen::codegen(const clast_guard *g) {
Function *F = Builder.GetInsertBlock()->getParent();
LLVMContext &Context = F->getContext();
BasicBlock *CondBB = SplitBlock(Builder.GetInsertBlock(),
Builder.GetInsertPoint(), P);
BasicBlock *CondBB =
SplitBlock(Builder.GetInsertBlock(), Builder.GetInsertPoint(), P);
CondBB->setName("polly.cond");
BasicBlock *MergeBB = SplitBlock(CondBB, CondBB->begin(), P);
MergeBB->setName("polly.merge");
@ -905,7 +898,7 @@ void ClastStmtCodeGen::codegen(const clast_guard *g) {
}
void ClastStmtCodeGen::codegen(const clast_stmt *stmt) {
if (CLAST_STMT_IS_A(stmt, stmt_root))
if (CLAST_STMT_IS_A(stmt, stmt_root))
assert(false && "No second root statement expected");
else if (CLAST_STMT_IS_A(stmt, stmt_ass))
codegen((const clast_assignment *)stmt);
@ -946,7 +939,7 @@ void ClastStmtCodeGen::codegen(const clast_root *r) {
parallelCodeGeneration = false;
const clast_stmt *stmt = (const clast_stmt*) r;
const clast_stmt *stmt = (const clast_stmt *)r;
if (stmt->next)
codegen(stmt->next);
}
@ -964,7 +957,6 @@ public:
CodeGeneration() : ScopPass(ID) {}
bool runOnScop(Scop &S) {
ParallelLoops.clear();
@ -986,7 +978,8 @@ public:
virtual void printScop(raw_ostream &OS) const {
for (std::vector<std::string>::const_iterator PI = ParallelLoops.begin(),
PE = ParallelLoops.end(); PI != PE; ++PI)
PE = ParallelLoops.end();
PI != PE; ++PI)
OS << "Parallel loop with iterator '" << *PI << "' generated\n";
}

54
polly/lib/CodeGen/IslAst.cpp
View File

@ -78,10 +78,9 @@ struct AstBuildUserInfo {
};
// Print a loop annotated with OpenMP or vector pragmas.
static __isl_give isl_printer *
printParallelFor(__isl_keep isl_ast_node *Node, __isl_take isl_printer *Printer,
__isl_take isl_ast_print_options *PrintOptions,
IslAstUser *Info) {
static __isl_give isl_printer *printParallelFor(
__isl_keep isl_ast_node *Node, __isl_take isl_printer *Printer,
__isl_take isl_ast_print_options *PrintOptions, IslAstUser *Info) {
if (Info) {
if (Info->IsInnermostParallel) {
Printer = isl_printer_start_line(Printer);
@ -106,7 +105,7 @@ printFor(__isl_take isl_printer *Printer,
if (!Id)
return isl_ast_node_for_print(Node, Printer, PrintOptions);
struct IslAstUser *Info = (struct IslAstUser *) isl_id_get_user(Id);
struct IslAstUser *Info = (struct IslAstUser *)isl_id_get_user(Id);
Printer = printParallelFor(Node, Printer, PrintOptions, Info);
isl_id_free(Id);
return Printer;
@ -115,7 +114,7 @@ printFor(__isl_take isl_printer *Printer,
// Allocate an AstNodeInfo structure and initialize it with default values.
static struct IslAstUser *allocateIslAstUser() {
struct IslAstUser *NodeInfo;
NodeInfo = (struct IslAstUser *) malloc(sizeof(struct IslAstUser));
NodeInfo = (struct IslAstUser *)malloc(sizeof(struct IslAstUser));
NodeInfo->PMA = 0;
NodeInfo->Context = 0;
NodeInfo->IsOutermostParallel = 0;
@ -125,7 +124,7 @@ static struct IslAstUser *allocateIslAstUser() {
// Free the AstNodeInfo structure.
static void freeIslAstUser(void *Ptr) {
struct IslAstUser *UserStruct = (struct IslAstUser *) Ptr;
struct IslAstUser *UserStruct = (struct IslAstUser *)Ptr;
isl_ast_build_free(UserStruct->Context);
isl_pw_multi_aff_free(UserStruct->PMA);
free(UserStruct);
@ -202,9 +201,9 @@ static void markOpenmpParallel(__isl_keep isl_ast_build *Build,
//
// - Detection of openmp parallel loops
//
static __isl_give isl_id *astBuildBeforeFor(__isl_keep isl_ast_build *Build,
void *User) {
struct AstBuildUserInfo *BuildInfo = (struct AstBuildUserInfo *) User;
static __isl_give isl_id *
astBuildBeforeFor(__isl_keep isl_ast_build *Build, void *User) {
struct AstBuildUserInfo *BuildInfo = (struct AstBuildUserInfo *)User;
struct IslAstUser *NodeInfo = allocateIslAstUser();
isl_id *Id = isl_id_alloc(isl_ast_build_get_ctx(Build), "", NodeInfo);
Id = isl_id_set_free_user(Id, freeIslAstUser);
@ -262,13 +261,13 @@ static bool containsLoops(__isl_take isl_ast_node *Node) {
// that is marked as openmp parallel.
//
static __isl_give isl_ast_node *
astBuildAfterFor(__isl_take isl_ast_node *Node,
__isl_keep isl_ast_build *Build, void *User) {
astBuildAfterFor(__isl_take isl_ast_node *Node, __isl_keep isl_ast_build *Build,
void *User) {
isl_id *Id = isl_ast_node_get_annotation(Node);
if (!Id)
return Node;
struct IslAstUser *Info = (struct IslAstUser *) isl_id_get_user(Id);
struct AstBuildUserInfo *BuildInfo = (struct AstBuildUserInfo *) User;
struct IslAstUser *Info = (struct IslAstUser *)isl_id_get_user(Id);
struct AstBuildUserInfo *BuildInfo = (struct AstBuildUserInfo *)User;
if (Info) {
if (Info->IsOutermostParallel)
@ -285,14 +284,13 @@ astBuildAfterFor(__isl_take isl_ast_node *Node,
}
static __isl_give isl_ast_node *
AtEachDomain(__isl_take isl_ast_node *Node,
__isl_keep isl_ast_build *Context, void *User)
{
AtEachDomain(__isl_take isl_ast_node *Node, __isl_keep isl_ast_build *Context,
void *User) {
struct IslAstUser *Info = NULL;
isl_id *Id = isl_ast_node_get_annotation(Node);
if (Id)
Info = (struct IslAstUser *) isl_id_get_user(Id);
Info = (struct IslAstUser *)isl_id_get_user(Id);
if (!Info) {
// Allocate annotations once: parallel for detection might have already
@ -360,16 +358,14 @@ __isl_give isl_union_map *IslAst::getSchedule() {
isl_map *StmtSchedule = Stmt->getScattering();
StmtSchedule = isl_map_intersect_domain(StmtSchedule, Stmt->getDomain());
Schedule = isl_union_map_union(Schedule,
isl_union_map_from_map(StmtSchedule));
Schedule =
isl_union_map_union(Schedule, isl_union_map_from_map(StmtSchedule));
}
return Schedule;
}
IslAst::~IslAst() {
isl_ast_node_free(Root);
}
IslAst::~IslAst() { isl_ast_node_free(Root); }
/// Print a C like representation of the program.
void IslAst::pprint(llvm::raw_ostream &OS) {
@ -390,13 +386,9 @@ void IslAst::pprint(llvm::raw_ostream &OS) {
}
/// Create the isl_ast from this program.
__isl_give isl_ast_node *IslAst::getAst() {
return isl_ast_node_copy(Root);
}
__isl_give isl_ast_node *IslAst::getAst() { return isl_ast_node_copy(Root); }
void IslAstInfo::pprint(llvm::raw_ostream &OS) {
Ast->pprint(OS);
}
void IslAstInfo::pprint(llvm::raw_ostream &OS) { Ast->pprint(OS); }
void IslAstInfo::releaseMemory() {
if (Ast) {
@ -418,9 +410,7 @@ bool IslAstInfo::runOnScop(Scop &Scop) {
return false;
}
__isl_give isl_ast_node *IslAstInfo::getAst() {
return Ast->getAst();
}
__isl_give isl_ast_node *IslAstInfo::getAst() { return Ast->getAst(); }
void IslAstInfo::printScop(raw_ostream &OS) const {
Function *F = S->getRegion().getEntry()->getParent();

151
polly/lib/CodeGen/IslCodeGeneration.cpp
View File

@ -93,8 +93,8 @@ Function *RuntimeDebugBuilder::getPrintF() {
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
FunctionType *Ty = FunctionType::get(Builder.getInt32Ty(),
Builder.getInt8PtrTy(), true);
FunctionType *Ty =
FunctionType::get(Builder.getInt32Ty(), Builder.getInt8PtrTy(), true);
F = Function::Create(Ty, Linkage, Name, M);
}
@ -108,8 +108,8 @@ void RuntimeDebugBuilder::createFlush() {
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
FunctionType *Ty = FunctionType::get(Builder.getInt32Ty(),
Builder.getInt8PtrTy(), false);
FunctionType *Ty =
FunctionType::get(Builder.getInt32Ty(), Builder.getInt8PtrTy(), false);
F = Function::Create(Ty, Linkage, Name, M);
}
@ -148,7 +148,7 @@ public:
private:
IRBuilder<> &Builder;
std::map<isl_id *, Value*> &IDToValue;
std::map<isl_id *, Value *> &IDToValue;
Value *createOp(__isl_take isl_ast_expr *Expr);
Value *createOpUnary(__isl_take isl_ast_expr *Expr);
@ -213,18 +213,16 @@ Value *IslExprBuilder::createOpNAry(__isl_take isl_ast_expr *Expr) {
default:
llvm_unreachable("This is no n-ary isl ast expression");
case isl_ast_op_max:
{
Value *Cmp = Builder.CreateICmpSGT(V, OpV);
V = Builder.CreateSelect(Cmp, V, OpV);
continue;
}
case isl_ast_op_min:
{
Value *Cmp = Builder.CreateICmpSLT(V, OpV);
V = Builder.CreateSelect(Cmp, V, OpV);
continue;
}
case isl_ast_op_max: {
Value *Cmp = Builder.CreateICmpSGT(V, OpV);
V = Builder.CreateSelect(Cmp, V, OpV);
continue;
}
case isl_ast_op_min: {
Value *Cmp = Builder.CreateICmpSLT(V, OpV);
V = Builder.CreateSelect(Cmp, V, OpV);
continue;
}
}
}
@ -299,21 +297,20 @@ Value *IslExprBuilder::createOpBin(__isl_take isl_ast_expr *Expr) {
case isl_ast_op_pdiv_q: // Dividend is non-negative
Res = Builder.CreateSDiv(LHS, RHS);
break;
case isl_ast_op_fdiv_q: // Round towards -infty
{
// TODO: Review code and check that this calculation does not yield
// incorrect overflow in some bordercases.
//
// floord(n,d) ((n < 0) ? (n - d + 1) : n) / d
Value *One = ConstantInt::get(MaxType, 1);
Value *Zero = ConstantInt::get(MaxType, 0);
Value *Sum1 = Builder.CreateSub(LHS, RHS);
Value *Sum2 = Builder.CreateAdd(Sum1, One);
Value *isNegative = Builder.CreateICmpSLT(LHS, Zero);
Value *Dividend = Builder.CreateSelect(isNegative, Sum2, LHS);
Res = Builder.CreateSDiv(Dividend, RHS);
break;
}
case isl_ast_op_fdiv_q: { // Round towards -infty
// TODO: Review code and check that this calculation does not yield
// incorrect overflow in some bordercases.
//
// floord(n,d) ((n < 0) ? (n - d + 1) : n) / d
Value *One = ConstantInt::get(MaxType, 1);
Value *Zero = ConstantInt::get(MaxType, 0);
Value *Sum1 = Builder.CreateSub(LHS, RHS);
Value *Sum2 = Builder.CreateAdd(Sum1, One);
Value *isNegative = Builder.CreateICmpSLT(LHS, Zero);
Value *Dividend = Builder.CreateSelect(isNegative, Sum2, LHS);
Res = Builder.CreateSDiv(Dividend, RHS);
break;
}
case isl_ast_op_pdiv_r: // Dividend is non-negative
Res = Builder.CreateSRem(LHS, RHS);
break;
@ -556,7 +553,7 @@ private:
// This maps an isl_id* to the Value* it has in the generated program. For now
// on, the only isl_ids that are stored here are the newly calculated loop
// ivs.
std::map<isl_id *, Value*> IDToValue;
std::map<isl_id *, Value *> IDToValue;
// Extract the upper bound of this loop
//
@ -577,8 +574,8 @@ private:
// of loop iterations.
//
// 3. With the existing code, upper bounds have been easier to implement.
__isl_give isl_ast_expr *getUpperBound(__isl_keep isl_ast_node *For,
CmpInst::Predicate &Predicate);
__isl_give isl_ast_expr *
getUpperBound(__isl_keep isl_ast_node *For, CmpInst::Predicate &Predicate);
unsigned getNumberOfIterations(__isl_keep isl_ast_node *For);
@ -586,23 +583,22 @@ private:
void createForVector(__isl_take isl_ast_node *For, int VectorWidth);
void createForSequential(__isl_take isl_ast_node *For);
void createSubstitutions(__isl_take isl_pw_multi_aff *PMA,
__isl_take isl_ast_build *Context,
ScopStmt *Stmt, ValueMapT &VMap);
void createSubstitutionsVector(__isl_take isl_pw_multi_aff *PMA,
__isl_take isl_ast_build *Context,
ScopStmt *Stmt, VectorValueMapT &VMap,
std::vector<Value*> &IVS,
__isl_take isl_id *IteratorID);
__isl_take isl_ast_build *Context, ScopStmt *Stmt,
ValueMapT &VMap);
void createSubstitutionsVector(
__isl_take isl_pw_multi_aff *PMA, __isl_take isl_ast_build *Context,
ScopStmt *Stmt, VectorValueMapT &VMap, std::vector<Value *> &IVS,
__isl_take isl_id *IteratorID);
void createIf(__isl_take isl_ast_node *If);
void createUserVector(__isl_take isl_ast_node *User,
std::vector<Value*> &IVS, __isl_take isl_id *IteratorID,
__isl_take isl_union_map *Schedule);
void createUserVector(
__isl_take isl_ast_node *User, std::vector<Value *> &IVS,
__isl_take isl_id *IteratorID, __isl_take isl_union_map *Schedule);
void createUser(__isl_take isl_ast_node *User);
void createBlock(__isl_take isl_ast_node *Block);
};
__isl_give isl_ast_expr *IslNodeBuilder::getUpperBound(
__isl_keep isl_ast_node *For, ICmpInst::Predicate &Predicate) {
__isl_keep isl_ast_node *For, ICmpInst::Predicate &Predicate) {
isl_id *UBID, *IteratorID;
isl_ast_expr *Cond, *Iterator, *UB, *Arg0;
isl_ast_op_type Type;
@ -615,14 +611,14 @@ __isl_give isl_ast_expr *IslNodeBuilder::getUpperBound(
"conditional expression is not an atomic upper bound");
switch (Type) {
case isl_ast_op_le:
Predicate = ICmpInst::ICMP_SLE;
break;
case isl_ast_op_lt:
Predicate = ICmpInst::ICMP_SLT;
break;
default:
llvm_unreachable("Unexpected comparision type in loop conditon");
case isl_ast_op_le:
Predicate = ICmpInst::ICMP_SLE;
break;
case isl_ast_op_lt:
Predicate = ICmpInst::ICMP_SLT;
break;
default:
llvm_unreachable("Unexpected comparision type in loop conditon");
}
Arg0 = isl_ast_expr_get_op_arg(Cond, 0);
@ -656,7 +652,7 @@ unsigned IslNodeBuilder::getNumberOfIterations(__isl_keep isl_ast_node *For) {
if (!Annotation)
return -1;
struct IslAstUser *Info = (struct IslAstUser *) isl_id_get_user(Annotation);
struct IslAstUser *Info = (struct IslAstUser *)isl_id_get_user(Annotation);
if (!Info) {
isl_id_free(Annotation);
return -1;
@ -671,18 +667,17 @@ unsigned IslNodeBuilder::getNumberOfIterations(__isl_keep isl_ast_node *For) {
return NumberOfIterations + 1;
}
void IslNodeBuilder::createUserVector(__isl_take isl_ast_node *User,
std::vector<Value*> &IVS,
__isl_take isl_id *IteratorID,
__isl_take isl_union_map *Schedule) {
void IslNodeBuilder::createUserVector(
__isl_take isl_ast_node *User, std::vector<Value *> &IVS,
__isl_take isl_id *IteratorID, __isl_take isl_union_map *Schedule) {
isl_id *Annotation = isl_ast_node_get_annotation(User);
assert(Annotation && "Vector user statement is not annotated");
struct IslAstUser *Info = (struct IslAstUser *) isl_id_get_user(Annotation);
struct IslAstUser *Info = (struct IslAstUser *)isl_id_get_user(Annotation);
assert(Info && "Vector user statement annotation does not contain info");
isl_id *Id = isl_pw_multi_aff_get_tuple_id(Info->PMA, isl_dim_out);
ScopStmt *Stmt = (ScopStmt *) isl_id_get_user(Id);
ScopStmt *Stmt = (ScopStmt *)isl_id_get_user(Id);
VectorValueMapT VectorMap(IVS.size());
isl_union_set *Domain = isl_union_set_from_set(Stmt->getDomain());
@ -726,16 +721,16 @@ void IslNodeBuilder::createForVector(__isl_take isl_ast_node *For,
if (MaxType != ValueInc->getType())
ValueInc = Builder.CreateSExt(ValueInc, MaxType);
std::vector<Value*> IVS(VectorWidth);
std::vector<Value *> IVS(VectorWidth);
IVS[0] = ValueLB;
for (int i = 1; i < VectorWidth; i++)
IVS[i] = Builder.CreateAdd(IVS[i-1], ValueInc, "p_vector_iv");
IVS[i] = Builder.CreateAdd(IVS[i - 1], ValueInc, "p_vector_iv");
isl_id *Annotation = isl_ast_node_get_annotation(For);
assert(Annotation && "For statement is not annotated");
struct IslAstUser *Info = (struct IslAstUser *) isl_id_get_user(Annotation);
struct IslAstUser *Info = (struct IslAstUser *)isl_id_get_user(Annotation);
assert(Info && "For statement annotation does not contain info");
isl_union_map *Schedule = isl_ast_build_get_schedule(Info->Context);
@ -819,8 +814,8 @@ void IslNodeBuilder::createForSequential(__isl_take isl_ast_node *For) {
// executed at least once, which will enable a lot of loop invariant
// code motion.
IV = createLoop(ValueLB, ValueUB, ValueInc, Builder, P, AfterBlock,
Predicate);
IV =
createLoop(ValueLB, ValueUB, ValueInc, Builder, P, AfterBlock, Predicate);
IDToValue[IteratorID] = IV;
create(Body);
@ -853,8 +848,8 @@ void IslNodeBuilder::createIf(__isl_take isl_ast_node *If) {
Function *F = Builder.GetInsertBlock()->getParent();
LLVMContext &Context = F->getContext();
BasicBlock *CondBB = SplitBlock(Builder.GetInsertBlock(),
Builder.GetInsertPoint(), P);
BasicBlock *CondBB =
SplitBlock(Builder.GetInsertBlock(), Builder.GetInsertPoint(), P);
CondBB->setName("polly.cond");
BasicBlock *MergeBB = SplitBlock(CondBB, CondBB->begin(), P);
MergeBB->setName("polly.merge");
@ -914,14 +909,15 @@ void IslNodeBuilder::createSubstitutions(__isl_take isl_pw_multi_aff *PMA,
isl_ast_build_free(Context);
}
void IslNodeBuilder::createSubstitutionsVector(__isl_take isl_pw_multi_aff *PMA,
__isl_take isl_ast_build *Context, ScopStmt *Stmt, VectorValueMapT &VMap,
std::vector<Value*> &IVS, __isl_take isl_id *IteratorID) {
void IslNodeBuilder::createSubstitutionsVector(
__isl_take isl_pw_multi_aff *PMA, __isl_take isl_ast_build *Context,
ScopStmt *Stmt, VectorValueMapT &VMap, std::vector<Value *> &IVS,
__isl_take isl_id *IteratorID) {
int i = 0;
Value *OldValue = IDToValue[IteratorID];
for (std::vector<Value*>::iterator II = IVS.begin(), IE = IVS.end();
II != IE; ++II) {
for (std::vector<Value *>::iterator II = IVS.begin(), IE = IVS.end();
II != IE; ++II) {
IDToValue[IteratorID] = *II;
createSubstitutions(isl_pw_multi_aff_copy(PMA), isl_ast_build_copy(Context),
Stmt, VMap[i]);
@ -943,11 +939,11 @@ void IslNodeBuilder::createUser(__isl_take isl_ast_node *User) {
Annotation = isl_ast_node_get_annotation(User);
assert(Annotation && "Scalar user statement is not annotated");
Info = (struct IslAstUser *) isl_id_get_user(Annotation);
Info = (struct IslAstUser *)isl_id_get_user(Annotation);
assert(Info && "Scalar user statement annotation does not contain info");
Id = isl_pw_multi_aff_get_tuple_id(Info->PMA, isl_dim_out);
Stmt = (ScopStmt *) isl_id_get_user(Id);
Stmt = (ScopStmt *)isl_id_get_user(Id);
createSubstitutions(isl_pw_multi_aff_copy(Info->PMA),
isl_ast_build_copy(Info->Context), Stmt, VMap);
@ -1000,7 +996,7 @@ void IslNodeBuilder::addParameters(__isl_take isl_set *Context) {
Instruction *InsertLocation;
Id = isl_set_get_dim_id(Context, isl_dim_param, i);
Scev = (const SCEV*) isl_id_get_user(Id);
Scev = (const SCEV *)isl_id_get_user(Id);
T = dyn_cast<IntegerType>(Scev->getType());
InsertLocation = --(Builder.GetInsertBlock()->end());
Value *V = Rewriter.expandCodeFor(Scev, T, InsertLocation);
@ -1033,8 +1029,7 @@ public:
return true;
}
virtual void printScop(raw_ostream &OS) const {
}
virtual void printScop(raw_ostream &OS) const {}
virtual void getAnalysisUsage(AnalysisUsage &AU) const {
AU.addRequired<DominatorTree>();

92
polly/lib/CodeGen/LoopGenerators.cpp
View File

@ -73,12 +73,9 @@ Value *polly::createLoop(Value *LB, Value *UB, Value *Stride,
return IV;
}
void OMPGenerator::createCallParallelLoopStart(Value *SubFunction,
Value *SubfunctionParam,
Value *NumberOfThreads,
Value *LowerBound,
Value *UpperBound,
Value *Stride) {
void OMPGenerator::createCallParallelLoopStart(
Value *SubFunction, Value *SubfunctionParam, Value *NumberOfThreads,
Value *LowerBound, Value *UpperBound, Value *Stride) {
Module *M = getModule();
const char *Name = "GOMP_parallel_loop_runtime_start";
Function *F = M->getFunction(Name);
@ -88,35 +85,23 @@ void OMPGenerator::createCallParallelLoopStart(Value *SubFunction,
Type *LongTy = getIntPtrTy();
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
Type *Params[] = {
PointerType::getUnqual(FunctionType::get(Builder.getVoidTy(),
Builder.getInt8PtrTy(),
false)),
Builder.getInt8PtrTy(),
Builder.getInt32Ty(),
LongTy,
LongTy,
LongTy,
};
Type *Params[] = { PointerType::getUnqual(FunctionType::get(
Builder.getVoidTy(), Builder.getInt8PtrTy(), false)),
Builder.getInt8PtrTy(), Builder.getInt32Ty(), LongTy,
LongTy, LongTy, };
FunctionType *Ty = FunctionType::get(Builder.getVoidTy(), Params, false);
F = Function::Create(Ty, Linkage, Name, M);
}
Value *Args[] = {
SubFunction,
SubfunctionParam,
NumberOfThreads,
LowerBound,
UpperBound,
Stride,
};
Value *Args[] = { SubFunction, SubfunctionParam, NumberOfThreads, LowerBound,
UpperBound, Stride, };
Builder.CreateCall(F, Args);
}
Value *OMPGenerator::createCallLoopNext(Value *LowerBoundPtr,
Value *UpperBoundPtr) {
Value *
OMPGenerator::createCallLoopNext(Value *LowerBoundPtr, Value *UpperBoundPtr) {
Module *M = getModule();
const char *Name = "GOMP_loop_runtime_next";
Function *F = M->getFunction(Name);
@ -126,23 +111,17 @@ Value *OMPGenerator::createCallLoopNext(Value *LowerBoundPtr,
Type *LongPtrTy = PointerType::getUnqual(getIntPtrTy());
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
Type *Params[] = {
LongPtrTy,
LongPtrTy,
};
Type *Params[] = { LongPtrTy, LongPtrTy, };
FunctionType *Ty = FunctionType::get(Builder.getInt8Ty(), Params, false);
F = Function::Create(Ty, Linkage, Name, M);
}
Value *Args[] = {
LowerBoundPtr,
UpperBoundPtr,
};
Value *Args[] = { LowerBoundPtr, UpperBoundPtr, };
Value *Return = Builder.CreateCall(F, Args);
Return = Builder.CreateICmpNE(Return, Builder.CreateZExt(Builder.getFalse(),
Return->getType()));
Return = Builder.CreateICmpNE(
Return, Builder.CreateZExt(Builder.getFalse(), Return->getType()));
return Return;
}
@ -189,7 +168,7 @@ Module *OMPGenerator::getModule() {
Function *OMPGenerator::createSubfunctionDefinition() {
Module *M = getModule();
Function *F = Builder.GetInsertBlock()->getParent();
std::vector<Type*> Arguments(1, Builder.getInt8PtrTy());
std::vector<Type *> Arguments(1, Builder.getInt8PtrTy());
FunctionType *FT = FunctionType::get(Builder.getVoidTy(), Arguments, false);
Function *FN = Function::Create(FT, Function::InternalLinkage,
F->getName() + ".omp_subfn", M);
@ -202,8 +181,8 @@ Function *OMPGenerator::createSubfunctionDefinition() {
return FN;
}
Value *OMPGenerator::loadValuesIntoStruct(SetVector<Value*> &Values) {
std::vector<Type*> Members;
Value *OMPGenerator::loadValuesIntoStruct(SetVector<Value *> &Values) {
std::vector<Type *> Members;
for (unsigned i = 0; i < Values.size(); i++)
Members.push_back(Values[i]->getType());
@ -219,26 +198,24 @@ Value *OMPGenerator::loadValuesIntoStruct(SetVector<Value*> &Values) {
return Struct;
}
void OMPGenerator::extractValuesFromStruct(SetVector<Value*> OldValues,
Value *Struct,
ValueToValueMapTy &Map) {
void OMPGenerator::extractValuesFromStruct(
SetVector<Value *> OldValues, Value *Struct, ValueToValueMapTy &Map) {
for (unsigned i = 0; i < OldValues.size(); i++) {
Value *Address = Builder.CreateStructGEP(Struct, i);
Value *NewValue = Builder.CreateLoad(Address);
Map.insert(std::make_pair<Value*, Value*>(OldValues[i], NewValue));
Map.insert(std::make_pair<Value *, Value *>(OldValues[i], NewValue));
}
}
Value *OMPGenerator::createSubfunction(Value *Stride, Value *StructData,
SetVector<Value*> Data,
ValueToValueMapTy &Map,
Function **SubFunction) {
Value *OMPGenerator::createSubfunction(
Value *Stride, Value *StructData, SetVector<Value *> Data,
ValueToValueMapTy &Map, Function **SubFunction) {
Function *FN = createSubfunctionDefinition();
BasicBlock *PrevBB, *HeaderBB, *ExitBB, *CheckNextBB, *LoadIVBoundsBB,
*AfterBB;
*AfterBB;
Value *LowerBoundPtr, *UpperBoundPtr, *UserContext, *Ret1, *HasNextSchedule,
*LowerBound, *UpperBound, *IV;
*LowerBound, *UpperBound, *IV;
Type *IntPtrTy = getIntPtrTy();
LLVMContext &Context = FN->getContext();
@ -303,11 +280,10 @@ Value *OMPGenerator::createSubfunction(Value *Stride, Value *StructData,
return IV;
}
Value *OMPGenerator::createParallelLoop(Value *LowerBound, Value *UpperBound,
Value *Stride,
SetVector<Value*> &Values,
ValueToValueMapTy &Map,
BasicBlock::iterator *LoopBody) {
Value *OMPGenerator::createParallelLoop(
Value *LowerBound, Value *UpperBound, Value *Stride,
SetVector<Value *> &Values, ValueToValueMapTy &Map,
BasicBlock::iterator *LoopBody) {
Value *Struct, *IV, *SubfunctionParam, *NumberOfThreads;
Function *SubFunction;
@ -319,15 +295,15 @@ Value *OMPGenerator::createParallelLoop(Value *LowerBound, Value *UpperBound,
Builder.SetInsertPoint(PrevInsertPoint);
// Create call for GOMP_parallel_loop_runtime_start.
SubfunctionParam = Builder.CreateBitCast(Struct, Builder.getInt8PtrTy(),
"omp_data");
SubfunctionParam =
Builder.CreateBitCast(Struct, Builder.getInt8PtrTy(), "omp_data");
NumberOfThreads = Builder.getInt32(0);
// Add one as the upper bound provided by openmp is a < comparison
// whereas the codegenForSequential function creates a <= comparison.
UpperBound = Builder.CreateAdd(UpperBound,
ConstantInt::get(getIntPtrTy(), 1));
UpperBound =
Builder.CreateAdd(UpperBound, ConstantInt::get(getIntPtrTy(), 1));
createCallParallelLoopStart(SubFunction, SubfunctionParam, NumberOfThreads,
LowerBound, UpperBound, Stride);

157
polly/lib/CodeGen/PTXGenerator.cpp
View File

@ -34,9 +34,9 @@ using namespace llvm;
using namespace polly;
PTXGenerator::PTXGenerator(IRBuilder<> &Builder, Pass *P,
const std::string &Triple):
Builder(Builder), P(P), GPUTriple(Triple), GridWidth(1), GridHeight(1),
BlockWidth(1), BlockHeight(1), OutputBytes(0) {
const std::string &Triple)
: Builder(Builder), P(P), GPUTriple(Triple), GridWidth(1), GridHeight(1),
BlockWidth(1), BlockHeight(1), OutputBytes(0) {
InitializeGPUDataTypes();
}
@ -50,12 +50,12 @@ Function *PTXGenerator::createSubfunctionDefinition(int NumArgs) {
Module *M = getModule();
Function *F = Builder.GetInsertBlock()->getParent();
std::vector<Type*> Arguments;
std::vector<Type *> Arguments;
for (int i = 0; i < NumArgs; i++)
Arguments.push_back(Builder.getInt8PtrTy());
FunctionType *FT = FunctionType::get(Builder.getVoidTy(), Arguments, false);
Function *FN = Function::Create(FT, Function::InternalLinkage,
F->getName() + "_ptx_subfn", M);
F->getName() + "_ptx_subfn", M);
FN->setCallingConv(CallingConv::PTX_Kernel);
// Do not run any optimization pass on the new function.
@ -67,10 +67,9 @@ Function *PTXGenerator::createSubfunctionDefinition(int NumArgs) {
return FN;
}
void PTXGenerator::createSubfunction(SetVector<Value*> &UsedValues,
SetVector<Value*> &OriginalIVS,
PTXGenerator::ValueToValueMapTy &VMap,
Function **SubFunction) {
void PTXGenerator::createSubfunction(
SetVector<Value *> &UsedValues, SetVector<Value *> &OriginalIVS,
PTXGenerator::ValueToValueMapTy &VMap, Function **SubFunction) {
Function *FN = createSubfunctionDefinition(UsedValues.size());
Module *M = getModule();
LLVMContext &Context = FN->getContext();
@ -98,20 +97,20 @@ void PTXGenerator::createSubfunction(SetVector<Value*> &UsedValues,
Value *BaseAddr = UsedValues[j];
Type *ArrayTy = BaseAddr->getType();
Value *Param = Builder.CreateBitCast(AI, ArrayTy);
VMap.insert(std::make_pair<Value*, Value*>(BaseAddr, Param));
VMap.insert(std::make_pair<Value *, Value *>(BaseAddr, Param));
AI++;
}
// FIXME: These intrinsics should be inserted on-demand. However, we insert
// them all currently for simplicity.
Function *GetNctaidX =
Intrinsic::getDeclaration(M, Intrinsic::ptx_read_nctaid_x);
Intrinsic::getDeclaration(M, Intrinsic::ptx_read_nctaid_x);
Function *GetNctaidY =
Intrinsic::getDeclaration(M, Intrinsic::ptx_read_nctaid_y);
Intrinsic::getDeclaration(M, Intrinsic::ptx_read_nctaid_y);
Function *GetCtaidX =
Intrinsic::getDeclaration(M, Intrinsic::ptx_read_ctaid_x);
Intrinsic::getDeclaration(M, Intrinsic::ptx_read_ctaid_x);
Function *GetCtaidY =
Intrinsic::getDeclaration(M, Intrinsic::ptx_read_ctaid_y);
Intrinsic::getDeclaration(M, Intrinsic::ptx_read_ctaid_y);
Function *GetNtidX = Intrinsic::getDeclaration(M, Intrinsic::ptx_read_ntid_x);
Function *GetNtidY = Intrinsic::getDeclaration(M, Intrinsic::ptx_read_ntid_y);
Function *GetTidX = Intrinsic::getDeclaration(M, Intrinsic::ptx_read_tid_x);
@ -142,8 +141,8 @@ void PTXGenerator::createSubfunction(SetVector<Value*> &UsedValues,
Value *BlockID, *ThreadID;
switch (NumDims) {
case 1: {
Value *BlockSize = Builder.CreateMul(BlockWidth, BlockHeight,
"p_gpu_blocksize");
Value *BlockSize =
Builder.CreateMul(BlockWidth, BlockHeight, "p_gpu_blocksize");
BlockID = Builder.CreateMul(BIDy, GridWidth, "p_gpu_index_i");
BlockID = Builder.CreateAdd(BlockID, BIDx);
BlockID = Builder.CreateMul(BlockID, BlockSize);
@ -183,11 +182,11 @@ void PTXGenerator::createSubfunction(SetVector<Value*> &UsedValues,
return;
}
assert(OriginalIVS.size() == Substitutions.size()
&& "The size of IVS should be equal to the size of substitutions.");
assert(OriginalIVS.size() == Substitutions.size() &&
"The size of IVS should be equal to the size of substitutions.");
for (unsigned i = 0; i < OriginalIVS.size(); ++i) {
VMap.insert(std::make_pair<Value*, Value*>(OriginalIVS[i],
Substitutions[i]));
VMap.insert(
std::make_pair<Value *, Value *>(OriginalIVS[i], Substitutions[i]));
}
Builder.CreateBr(ExitBB);
@ -202,10 +201,9 @@ void PTXGenerator::createSubfunction(SetVector<Value*> &UsedValues,
*SubFunction = FN;
}
void PTXGenerator::startGeneration(SetVector<Value*> &UsedValues,
SetVector<Value*> &OriginalIVS,
ValueToValueMapTy &VMap,
BasicBlock::iterator *LoopBody) {
void PTXGenerator::startGeneration(
SetVector<Value *> &UsedValues, SetVector<Value *> &OriginalIVS,
ValueToValueMapTy &VMap, BasicBlock::iterator *LoopBody) {
Function *SubFunction;
BasicBlock::iterator PrevInsertPoint = Builder.GetInsertPoint();
createSubfunction(UsedValues, OriginalIVS, VMap, &SubFunction);
@ -213,9 +211,7 @@ void PTXGenerator::startGeneration(SetVector<Value*> &UsedValues,
Builder.SetInsertPoint(PrevInsertPoint);
}
IntegerType *PTXGenerator::getInt64Type() {
return Builder.getInt64Ty();
}
IntegerType *PTXGenerator::getInt64Type() { return Builder.getInt64Ty(); }
PointerType *PTXGenerator::getI8PtrType() {
return PointerType::getUnqual(Builder.getInt8Ty());
@ -260,7 +256,7 @@ void PTXGenerator::InitializeGPUDataTypes() {
ModuleTy = StructType::create(Context, "struct.PollyGPUModuleT");
KernelTy = StructType::create(Context, "struct.PollyGPUFunctionT");
DeviceTy = StructType::create(Context, "struct.PollyGPUDeviceT");
DevDataTy = StructType::create(Context,"struct.PollyGPUDevicePtrT");
DevDataTy = StructType::create(Context, "struct.PollyGPUDevicePtrT");
EventTy = StructType::create(Context, "struct.PollyGPUEventT");
}
@ -272,7 +268,7 @@ void PTXGenerator::createCallInitDevice(Value *Context, Value *Device) {
// If F is not available, declare it.
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
std::vector<Type*> Args;
std::vector<Type *> Args;
Args.push_back(PointerType::getUnqual(getGPUContextPtrType()));
Args.push_back(PointerType::getUnqual(getGPUDevicePtrType()));
FunctionType *Ty = FunctionType::get(Builder.getVoidTy(), Args, false);
@ -290,7 +286,7 @@ void PTXGenerator::createCallGetPTXModule(Value *Buffer, Value *Module) {
// If F is not available, declare it.
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
std::vector<Type*> Args;
std::vector<Type *> Args;
Args.push_back(getI8PtrType());
Args.push_back(PointerType::getUnqual(getGPUModulePtrType()));
FunctionType *Ty = FunctionType::get(Builder.getVoidTy(), Args, false);
@ -309,7 +305,7 @@ void PTXGenerator::createCallGetPTXKernelEntry(Value *Entry, Value *Module,
// If F is not available, declare it.
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
std::vector<Type*> Args;
std::vector<Type *> Args;
Args.push_back(getI8PtrType());
Args.push_back(getGPUModulePtrType());
Args.push_back(PointerType::getUnqual(getGPUFunctionPtrType()));
@ -320,9 +316,8 @@ void PTXGenerator::createCallGetPTXKernelEntry(Value *Entry, Value *Module,
Builder.CreateCall3(F, Entry, Module, Kernel);
}
void PTXGenerator::createCallAllocateMemoryForHostAndDevice(Value *HostData,
Value *DeviceData,
Value *Size) {
void PTXGenerator::createCallAllocateMemoryForHostAndDevice(
Value *HostData, Value *DeviceData, Value *Size) {
const char *Name = "polly_allocateMemoryForHostAndDevice";
Module *M = getModule();
Function *F = M->getFunction(Name);
@ -330,7 +325,7 @@ void PTXGenerator::createCallAllocateMemoryForHostAndDevice(Value *HostData,
// If F is not available, declare it.
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
std::vector<Type*> Args;
std::vector<Type *> Args;
Args.push_back(getPtrI8PtrType());
Args.push_back(PointerType::getUnqual(getPtrGPUDevicePtrType()));
Args.push_back(getInt64Type());
@ -341,9 +336,8 @@ void PTXGenerator::createCallAllocateMemoryForHostAndDevice(Value *HostData,
Builder.CreateCall3(F, HostData, DeviceData, Size);
}
void PTXGenerator::createCallCopyFromHostToDevice(Value *DeviceData,
Value *HostData,
Value *Size) {
void PTXGenerator::createCallCopyFromHostToDevice(
Value *DeviceData, Value *HostData, Value *Size) {
const char *Name = "polly_copyFromHostToDevice";
Module *M = getModule();
Function *F = M->getFunction(Name);
@ -351,7 +345,7 @@ void PTXGenerator::createCallCopyFromHostToDevice(Value *DeviceData,
// If F is not available, declare it.
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
std::vector<Type*> Args;
std::vector<Type *> Args;
Args.push_back(getPtrGPUDevicePtrType());
Args.push_back(getI8PtrType());
Args.push_back(getInt64Type());
@ -362,9 +356,8 @@ void PTXGenerator::createCallCopyFromHostToDevice(Value *DeviceData,
Builder.CreateCall3(F, DeviceData, HostData, Size);
}
void PTXGenerator::createCallCopyFromDeviceToHost(Value *HostData,
Value *DeviceData,
Value *Size) {
void PTXGenerator::createCallCopyFromDeviceToHost(
Value *HostData, Value *DeviceData, Value *Size) {
const char *Name = "polly_copyFromDeviceToHost";
Module *M = getModule();
Function *F = M->getFunction(Name);
@ -372,7 +365,7 @@ void PTXGenerator::createCallCopyFromDeviceToHost(Value *HostData,
// If F is not available, declare it.
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
std::vector<Type*> Args;
std::vector<Type *> Args;
Args.push_back(getI8PtrType());
Args.push_back(getPtrGPUDevicePtrType());
Args.push_back(getInt64Type());
@ -383,10 +376,8 @@ void PTXGenerator::createCallCopyFromDeviceToHost(Value *HostData,
Builder.CreateCall3(F, HostData, DeviceData, Size);
}
void PTXGenerator::createCallSetKernelParameters(Value *Kernel,
Value *BlockWidth,
Value *BlockHeight,
Value *DeviceData) {
void PTXGenerator::createCallSetKernelParameters(
Value *Kernel, Value *BlockWidth, Value *BlockHeight, Value *DeviceData) {
const char *Name = "polly_setKernelParameters";
Module *M = getModule();
Function *F = M->getFunction(Name);
@ -394,7 +385,7 @@ void PTXGenerator::createCallSetKernelParameters(Value *Kernel,
// If F is not available, declare it.
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
std::vector<Type*> Args;
std::vector<Type *> Args;
Args.push_back(getGPUFunctionPtrType());
Args.push_back(getInt64Type());
Args.push_back(getInt64Type());
@ -415,7 +406,7 @@ void PTXGenerator::createCallLaunchKernel(Value *Kernel, Value *GridWidth,
// If F is not available, declare it.
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
std::vector<Type*> Args;
std::vector<Type *> Args;
Args.push_back(getGPUFunctionPtrType());
Args.push_back(getInt64Type());
Args.push_back(getInt64Type());
@ -435,7 +426,7 @@ void PTXGenerator::createCallStartTimerByCudaEvent(Value *StartEvent,
// If F is not available, declare it.
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
std::vector<Type*> Args;
std::vector<Type *> Args;
Args.push_back(PointerType::getUnqual(getGPUEventPtrType()));
Args.push_back(PointerType::getUnqual(getGPUEventPtrType()));
FunctionType *Ty = FunctionType::get(Builder.getVoidTy(), Args, false);
@ -445,9 +436,8 @@ void PTXGenerator::createCallStartTimerByCudaEvent(Value *StartEvent,
Builder.CreateCall2(F, StartEvent, StopEvent);
}
void PTXGenerator::createCallStopTimerByCudaEvent(Value *StartEvent,
Value *StopEvent,
Value *Timer) {
void PTXGenerator::createCallStopTimerByCudaEvent(
Value *StartEvent, Value *StopEvent, Value *Timer) {
const char *Name = "polly_stopTimerByCudaEvent";
Module *M = getModule();
Function *F = M->getFunction(Name);
@ -455,7 +445,7 @@ void PTXGenerator::createCallStopTimerByCudaEvent(Value *StartEvent,
// If F is not available, declare it.
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
std::vector<Type*> Args;
std::vector<Type *> Args;
Args.push_back(getGPUEventPtrType());
Args.push_back(getGPUEventPtrType());
Args.push_back(getFloatPtrType());
@ -466,11 +456,9 @@ void PTXGenerator::createCallStopTimerByCudaEvent(Value *StartEvent,
Builder.CreateCall3(F, StartEvent, StopEvent, Timer);
}
void PTXGenerator::createCallCleanupGPGPUResources(Value *HostData,
Value *DeviceData,
Value *Module,
Value *Context,
Value *Kernel) {
void PTXGenerator::createCallCleanupGPGPUResources(
Value *HostData, Value *DeviceData, Value *Module, Value *Context,
Value *Kernel) {
const char *Name = "polly_cleanupGPGPUResources";
llvm::Module *M = getModule();
Function *F = M->getFunction(Name);
@ -478,7 +466,7 @@ void PTXGenerator::createCallCleanupGPGPUResources(Value *HostData,
// If F is not available, declare it.
if (!F) {
GlobalValue::LinkageTypes Linkage = Function::ExternalLinkage;
std::vector<Type*> Args;
std::vector<Type *> Args;
Args.push_back(getI8PtrType());
Args.push_back(getPtrGPUDevicePtrType());
Args.push_back(getGPUModulePtrType());
@ -516,11 +504,11 @@ Value *PTXGenerator::createPTXKernelFunction(Function *SubFunction) {
std::string LLVMKernelStr;
raw_string_ostream NameROS(LLVMKernelStr);
formatted_raw_ostream FOS(NameROS);
FOS << "target triple = \"" << GPUTriple <<"\"\n";
FOS << "target triple = \"" << GPUTriple << "\"\n";
SubFunction->print(FOS);
// Insert ptx intrinsics into the kernel string.
for (Module::iterator I = M->begin(), E = M->end(); I != E; ) {
for (Module::iterator I = M->begin(), E = M->end(); I != E;) {
Function *F = I++;
// Function must be a prototype and unused.
if (F->isDeclaration() && F->isIntrinsic()) {
@ -541,13 +529,12 @@ Value *PTXGenerator::createPTXKernelFunction(Function *SubFunction) {
}
}
Value *LLVMKernel = Builder.CreateGlobalStringPtr(LLVMKernelStr,
"llvm_kernel");
Value *LLVMKernel =
Builder.CreateGlobalStringPtr(LLVMKernelStr, "llvm_kernel");
Value *MCPU = Builder.CreateGlobalStringPtr("sm_10", "mcpu");
Value *Features = Builder.CreateGlobalStringPtr("", "cpu_features");
Function *GetDeviceKernel = Intrinsic::getDeclaration(M,
Intrinsic::codegen);
Function *GetDeviceKernel = Intrinsic::getDeclaration(M, Intrinsic::codegen);
return Builder.CreateCall3(GetDeviceKernel, LLVMKernel, MCPU, Features);
}
@ -596,22 +583,22 @@ void PTXGenerator::eraseUnusedFunctions(Function *SubFunction) {
void PTXGenerator::finishGeneration(Function *F) {
// Define data used by the GPURuntime library.
AllocaInst *PtrCUContext = Builder.CreateAlloca(getGPUContextPtrType(), 0,
"phcontext");
AllocaInst *PtrCUDevice = Builder.CreateAlloca(getGPUDevicePtrType(), 0,
"phdevice");
AllocaInst *PtrCUModule = Builder.CreateAlloca(getGPUModulePtrType(), 0,
"phmodule");
AllocaInst *PtrCUKernel = Builder.CreateAlloca(getGPUFunctionPtrType(), 0,
"phkernel");
AllocaInst *PtrCUStartEvent = Builder.CreateAlloca(getGPUEventPtrType(), 0,
"pstart_timer");
AllocaInst *PtrCUStopEvent = Builder.CreateAlloca(getGPUEventPtrType(), 0,
"pstop_timer");
AllocaInst *PtrDevData = Builder.CreateAlloca(getPtrGPUDevicePtrType(), 0,
"pdevice_data");
AllocaInst *PtrHostData = Builder.CreateAlloca(getI8PtrType(), 0,
"phost_data");
AllocaInst *PtrCUContext =
Builder.CreateAlloca(getGPUContextPtrType(), 0, "phcontext");
AllocaInst *PtrCUDevice =
Builder.CreateAlloca(getGPUDevicePtrType(), 0, "phdevice");
AllocaInst *PtrCUModule =
Builder.CreateAlloca(getGPUModulePtrType(), 0, "phmodule");
AllocaInst *PtrCUKernel =
Builder.CreateAlloca(getGPUFunctionPtrType(), 0, "phkernel");
AllocaInst *PtrCUStartEvent =
Builder.CreateAlloca(getGPUEventPtrType(), 0, "pstart_timer");
AllocaInst *PtrCUStopEvent =
Builder.CreateAlloca(getGPUEventPtrType(), 0, "pstop_timer");
AllocaInst *PtrDevData =
Builder.CreateAlloca(getPtrGPUDevicePtrType(), 0, "pdevice_data");
AllocaInst *PtrHostData =
Builder.CreateAlloca(getI8PtrType(), 0, "phost_data");
Type *FloatTy = llvm::Type::getFloatTy(getModule()->getContext());
AllocaInst *PtrElapsedTimes = Builder.CreateAlloca(FloatTy, 0, "ptimer");
@ -648,13 +635,11 @@ void PTXGenerator::finishGeneration(Function *F) {
// Record the end time.
LoadInst *CUStartEvent = Builder.CreateLoad(PtrCUStartEvent, "start_timer");
LoadInst *CUStopEvent = Builder.CreateLoad(PtrCUStopEvent, "stop_timer");
createCallStopTimerByCudaEvent(CUStartEvent, CUStopEvent,
PtrElapsedTimes);
createCallStopTimerByCudaEvent(CUStartEvent, CUStopEvent, PtrElapsedTimes);
// Cleanup all the resources used.
LoadInst *CUContext = Builder.CreateLoad(PtrCUContext, "cucontext");
createCallCleanupGPGPUResources(HData, DData, CUModule, CUContext,
CUKernel);
createCallCleanupGPGPUResources(HData, DData, CUModule, CUContext, CUKernel);
// Erase the ptx kernel and device subfunctions and ptx intrinsics from
// current module.