forked from OSchip/llvm-project
270 lines
8.6 KiB
C++
270 lines
8.6 KiB
C++
//===---- CGLoopInfo.cpp - LLVM CodeGen for loop metadata -*- C++ -*-------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "CGLoopInfo.h"
|
|
#include "clang/AST/ASTContext.h"
|
|
#include "clang/AST/Attr.h"
|
|
#include "clang/Sema/LoopHint.h"
|
|
#include "llvm/IR/BasicBlock.h"
|
|
#include "llvm/IR/Constants.h"
|
|
#include "llvm/IR/InstrTypes.h"
|
|
#include "llvm/IR/Instructions.h"
|
|
#include "llvm/IR/Metadata.h"
|
|
using namespace clang::CodeGen;
|
|
using namespace llvm;
|
|
|
|
static MDNode *createMetadata(LLVMContext &Ctx, const LoopAttributes &Attrs) {
|
|
|
|
if (!Attrs.IsParallel && Attrs.VectorizeWidth == 0 &&
|
|
Attrs.InterleaveCount == 0 && Attrs.UnrollCount == 0 &&
|
|
Attrs.VectorizeEnable == LoopAttributes::Unspecified &&
|
|
Attrs.UnrollEnable == LoopAttributes::Unspecified)
|
|
return nullptr;
|
|
|
|
SmallVector<Metadata *, 4> Args;
|
|
// Reserve operand 0 for loop id self reference.
|
|
auto TempNode = MDNode::getTemporary(Ctx, None);
|
|
Args.push_back(TempNode.get());
|
|
|
|
// Setting vectorize.width
|
|
if (Attrs.VectorizeWidth > 0) {
|
|
Metadata *Vals[] = {MDString::get(Ctx, "llvm.loop.vectorize.width"),
|
|
ConstantAsMetadata::get(ConstantInt::get(
|
|
Type::getInt32Ty(Ctx), Attrs.VectorizeWidth))};
|
|
Args.push_back(MDNode::get(Ctx, Vals));
|
|
}
|
|
|
|
// Setting interleave.count
|
|
if (Attrs.InterleaveCount > 0) {
|
|
Metadata *Vals[] = {MDString::get(Ctx, "llvm.loop.interleave.count"),
|
|
ConstantAsMetadata::get(ConstantInt::get(
|
|
Type::getInt32Ty(Ctx), Attrs.InterleaveCount))};
|
|
Args.push_back(MDNode::get(Ctx, Vals));
|
|
}
|
|
|
|
// Setting interleave.count
|
|
if (Attrs.UnrollCount > 0) {
|
|
Metadata *Vals[] = {MDString::get(Ctx, "llvm.loop.unroll.count"),
|
|
ConstantAsMetadata::get(ConstantInt::get(
|
|
Type::getInt32Ty(Ctx), Attrs.UnrollCount))};
|
|
Args.push_back(MDNode::get(Ctx, Vals));
|
|
}
|
|
|
|
// Setting vectorize.enable
|
|
if (Attrs.VectorizeEnable != LoopAttributes::Unspecified) {
|
|
Metadata *Vals[] = {MDString::get(Ctx, "llvm.loop.vectorize.enable"),
|
|
ConstantAsMetadata::get(ConstantInt::get(
|
|
Type::getInt1Ty(Ctx), (Attrs.VectorizeEnable ==
|
|
LoopAttributes::Enable)))};
|
|
Args.push_back(MDNode::get(Ctx, Vals));
|
|
}
|
|
|
|
// Setting unroll.full or unroll.disable
|
|
if (Attrs.UnrollEnable != LoopAttributes::Unspecified) {
|
|
std::string Name;
|
|
if (Attrs.UnrollEnable == LoopAttributes::Enable)
|
|
Name = "llvm.loop.unroll.enable";
|
|
else if (Attrs.UnrollEnable == LoopAttributes::Full)
|
|
Name = "llvm.loop.unroll.full";
|
|
else
|
|
Name = "llvm.loop.unroll.disable";
|
|
Metadata *Vals[] = {MDString::get(Ctx, Name)};
|
|
Args.push_back(MDNode::get(Ctx, Vals));
|
|
}
|
|
|
|
// Set the first operand to itself.
|
|
MDNode *LoopID = MDNode::get(Ctx, Args);
|
|
LoopID->replaceOperandWith(0, LoopID);
|
|
return LoopID;
|
|
}
|
|
|
|
LoopAttributes::LoopAttributes(bool IsParallel)
|
|
: IsParallel(IsParallel), VectorizeEnable(LoopAttributes::Unspecified),
|
|
UnrollEnable(LoopAttributes::Unspecified), VectorizeWidth(0),
|
|
InterleaveCount(0), UnrollCount(0) {}
|
|
|
|
void LoopAttributes::clear() {
|
|
IsParallel = false;
|
|
VectorizeWidth = 0;
|
|
InterleaveCount = 0;
|
|
UnrollCount = 0;
|
|
VectorizeEnable = LoopAttributes::Unspecified;
|
|
UnrollEnable = LoopAttributes::Unspecified;
|
|
}
|
|
|
|
LoopInfo::LoopInfo(BasicBlock *Header, const LoopAttributes &Attrs)
|
|
: LoopID(nullptr), Header(Header), Attrs(Attrs) {
|
|
LoopID = createMetadata(Header->getContext(), Attrs);
|
|
}
|
|
|
|
void LoopInfoStack::push(BasicBlock *Header) {
|
|
Active.push_back(LoopInfo(Header, StagedAttrs));
|
|
// Clear the attributes so nested loops do not inherit them.
|
|
StagedAttrs.clear();
|
|
}
|
|
|
|
void LoopInfoStack::push(BasicBlock *Header, clang::ASTContext &Ctx,
|
|
ArrayRef<const clang::Attr *> Attrs) {
|
|
|
|
// Identify loop hint attributes from Attrs.
|
|
for (const auto *Attr : Attrs) {
|
|
const LoopHintAttr *LH = dyn_cast<LoopHintAttr>(Attr);
|
|
const OpenCLUnrollHintAttr *OpenCLHint =
|
|
dyn_cast<OpenCLUnrollHintAttr>(Attr);
|
|
|
|
// Skip non loop hint attributes
|
|
if (!LH && !OpenCLHint) {
|
|
continue;
|
|
}
|
|
|
|
LoopHintAttr::OptionType Option = LoopHintAttr::Unroll;
|
|
LoopHintAttr::LoopHintState State = LoopHintAttr::Disable;
|
|
unsigned ValueInt = 1;
|
|
// Translate opencl_unroll_hint attribute argument to
|
|
// equivalent LoopHintAttr enums.
|
|
// OpenCL v2.0 s6.11.5:
|
|
// 0 - full unroll (no argument).
|
|
// 1 - disable unroll.
|
|
// other positive integer n - unroll by n.
|
|
if (OpenCLHint) {
|
|
ValueInt = OpenCLHint->getUnrollHint();
|
|
if (ValueInt == 0) {
|
|
State = LoopHintAttr::Full;
|
|
} else if (ValueInt != 1) {
|
|
Option = LoopHintAttr::UnrollCount;
|
|
State = LoopHintAttr::Numeric;
|
|
}
|
|
} else if (LH) {
|
|
auto *ValueExpr = LH->getValue();
|
|
if (ValueExpr) {
|
|
llvm::APSInt ValueAPS = ValueExpr->EvaluateKnownConstInt(Ctx);
|
|
ValueInt = ValueAPS.getSExtValue();
|
|
}
|
|
|
|
Option = LH->getOption();
|
|
State = LH->getState();
|
|
}
|
|
switch (State) {
|
|
case LoopHintAttr::Disable:
|
|
switch (Option) {
|
|
case LoopHintAttr::Vectorize:
|
|
// Disable vectorization by specifying a width of 1.
|
|
setVectorizeWidth(1);
|
|
break;
|
|
case LoopHintAttr::Interleave:
|
|
// Disable interleaving by speciyfing a count of 1.
|
|
setInterleaveCount(1);
|
|
break;
|
|
case LoopHintAttr::Unroll:
|
|
setUnrollState(LoopAttributes::Disable);
|
|
break;
|
|
case LoopHintAttr::UnrollCount:
|
|
case LoopHintAttr::VectorizeWidth:
|
|
case LoopHintAttr::InterleaveCount:
|
|
llvm_unreachable("Options cannot be disabled.");
|
|
break;
|
|
}
|
|
break;
|
|
case LoopHintAttr::Enable:
|
|
switch (Option) {
|
|
case LoopHintAttr::Vectorize:
|
|
case LoopHintAttr::Interleave:
|
|
setVectorizeEnable(true);
|
|
break;
|
|
case LoopHintAttr::Unroll:
|
|
setUnrollState(LoopAttributes::Enable);
|
|
break;
|
|
case LoopHintAttr::UnrollCount:
|
|
case LoopHintAttr::VectorizeWidth:
|
|
case LoopHintAttr::InterleaveCount:
|
|
llvm_unreachable("Options cannot enabled.");
|
|
break;
|
|
}
|
|
break;
|
|
case LoopHintAttr::AssumeSafety:
|
|
switch (Option) {
|
|
case LoopHintAttr::Vectorize:
|
|
case LoopHintAttr::Interleave:
|
|
// Apply "llvm.mem.parallel_loop_access" metadata to load/stores.
|
|
setParallel(true);
|
|
setVectorizeEnable(true);
|
|
break;
|
|
case LoopHintAttr::Unroll:
|
|
case LoopHintAttr::UnrollCount:
|
|
case LoopHintAttr::VectorizeWidth:
|
|
case LoopHintAttr::InterleaveCount:
|
|
llvm_unreachable("Options cannot be used to assume mem safety.");
|
|
break;
|
|
}
|
|
break;
|
|
case LoopHintAttr::Full:
|
|
switch (Option) {
|
|
case LoopHintAttr::Unroll:
|
|
setUnrollState(LoopAttributes::Full);
|
|
break;
|
|
case LoopHintAttr::Vectorize:
|
|
case LoopHintAttr::Interleave:
|
|
case LoopHintAttr::UnrollCount:
|
|
case LoopHintAttr::VectorizeWidth:
|
|
case LoopHintAttr::InterleaveCount:
|
|
llvm_unreachable("Options cannot be used with 'full' hint.");
|
|
break;
|
|
}
|
|
break;
|
|
case LoopHintAttr::Numeric:
|
|
switch (Option) {
|
|
case LoopHintAttr::VectorizeWidth:
|
|
setVectorizeWidth(ValueInt);
|
|
break;
|
|
case LoopHintAttr::InterleaveCount:
|
|
setInterleaveCount(ValueInt);
|
|
break;
|
|
case LoopHintAttr::UnrollCount:
|
|
setUnrollCount(ValueInt);
|
|
break;
|
|
case LoopHintAttr::Unroll:
|
|
case LoopHintAttr::Vectorize:
|
|
case LoopHintAttr::Interleave:
|
|
llvm_unreachable("Options cannot be assigned a value.");
|
|
break;
|
|
}
|
|
break;
|
|
}
|
|
}
|
|
|
|
/// Stage the attributes.
|
|
push(Header);
|
|
}
|
|
|
|
void LoopInfoStack::pop() {
|
|
assert(!Active.empty() && "No active loops to pop");
|
|
Active.pop_back();
|
|
}
|
|
|
|
void LoopInfoStack::InsertHelper(Instruction *I) const {
|
|
if (!hasInfo())
|
|
return;
|
|
|
|
const LoopInfo &L = getInfo();
|
|
if (!L.getLoopID())
|
|
return;
|
|
|
|
if (TerminatorInst *TI = dyn_cast<TerminatorInst>(I)) {
|
|
for (unsigned i = 0, ie = TI->getNumSuccessors(); i < ie; ++i)
|
|
if (TI->getSuccessor(i) == L.getHeader()) {
|
|
TI->setMetadata("llvm.loop", L.getLoopID());
|
|
break;
|
|
}
|
|
return;
|
|
}
|
|
|
|
if (L.getAttributes().IsParallel && I->mayReadOrWriteMemory())
|
|
I->setMetadata("llvm.mem.parallel_loop_access", L.getLoopID());
|
|
}
|