mirror of
https://github.com/llvm/llvm-project.git
synced 2025-05-17 19:56:04 +00:00
2de463ece3
Summary:
This is similar to other loop pragmas like 'vectorize'. Currently it
only has state values: distribute(enable) and distribute(disable). When
one of these is specified the corresponding loop metadata is generated:
!{!"llvm.loop.distribute.enable", i1 true/false}
As a result, loop distribution will be attempted on the loop even if
Loop Distribution in not enabled globally. Analogously, with 'disable'
distribution can be turned off for an individual loop even when the pass
is otherwise enabled.
There are some slight differences compared to the existing loop pragmas.
1. There is no 'assume_safety' variant which makes its handling slightly
different from 'vectorize'/'interleave'.
2. Unlike the existing loop pragmas, it does not have a corresponding
numeric pragma like 'vectorize' -> 'vectorize_width'. So for the
consistency checks in CheckForIncompatibleAttributes we don't need to
check it against other pragmas. We just need to check for duplicates of
the same pragma.
Reviewers: rsmith, dexonsmith, aaron.ballman
Subscribers: bob.wilson, cfe-commits, hfinkel
Differential Revision: http://reviews.llvm.org/D19403
llvm-svn: 272656
297 lines
9.7 KiB
C++
297 lines
9.7 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,
|
|
llvm::DebugLoc Location) {
|
|
|
|
if (!Attrs.IsParallel && Attrs.VectorizeWidth == 0 &&
|
|
Attrs.InterleaveCount == 0 && Attrs.UnrollCount == 0 &&
|
|
Attrs.VectorizeEnable == LoopAttributes::Unspecified &&
|
|
Attrs.UnrollEnable == LoopAttributes::Unspecified &&
|
|
Attrs.DistributeEnable == LoopAttributes::Unspecified &&
|
|
!Location)
|
|
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());
|
|
|
|
// If we have a valid debug location for the loop, add it.
|
|
if (Location)
|
|
Args.push_back(Location.getAsMDNode());
|
|
|
|
// 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));
|
|
}
|
|
|
|
if (Attrs.DistributeEnable != LoopAttributes::Unspecified) {
|
|
Metadata *Vals[] = {MDString::get(Ctx, "llvm.loop.distribute.enable"),
|
|
ConstantAsMetadata::get(ConstantInt::get(
|
|
Type::getInt1Ty(Ctx), (Attrs.DistributeEnable ==
|
|
LoopAttributes::Enable)))};
|
|
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),
|
|
DistributeEnable(LoopAttributes::Unspecified) {}
|
|
|
|
void LoopAttributes::clear() {
|
|
IsParallel = false;
|
|
VectorizeWidth = 0;
|
|
InterleaveCount = 0;
|
|
UnrollCount = 0;
|
|
VectorizeEnable = LoopAttributes::Unspecified;
|
|
UnrollEnable = LoopAttributes::Unspecified;
|
|
}
|
|
|
|
LoopInfo::LoopInfo(BasicBlock *Header, const LoopAttributes &Attrs,
|
|
llvm::DebugLoc Location)
|
|
: LoopID(nullptr), Header(Header), Attrs(Attrs) {
|
|
LoopID = createMetadata(Header->getContext(), Attrs, Location);
|
|
}
|
|
|
|
void LoopInfoStack::push(BasicBlock *Header, llvm::DebugLoc Location) {
|
|
Active.push_back(LoopInfo(Header, StagedAttrs, Location));
|
|
// 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,
|
|
llvm::DebugLoc Location) {
|
|
|
|
// 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::Distribute:
|
|
setDistributeState(false);
|
|
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::Distribute:
|
|
setDistributeState(true);
|
|
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:
|
|
case LoopHintAttr::Distribute:
|
|
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:
|
|
case LoopHintAttr::Distribute:
|
|
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:
|
|
case LoopHintAttr::Distribute:
|
|
llvm_unreachable("Options cannot be assigned a value.");
|
|
break;
|
|
}
|
|
break;
|
|
}
|
|
}
|
|
|
|
/// Stage the attributes.
|
|
push(Header, Location);
|
|
}
|
|
|
|
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::LLVMContext::MD_loop, L.getLoopID());
|
|
break;
|
|
}
|
|
return;
|
|
}
|
|
|
|
if (L.getAttributes().IsParallel && I->mayReadOrWriteMemory())
|
|
I->setMetadata("llvm.mem.parallel_loop_access", L.getLoopID());
|
|
}
|