Annotate LLVM-IR for all parallel loops

This change allows to annotate all parallel loops with loop id metadata.
  Furthermore, it will annotate memory instructions with
  llvm.mem.parallel_loop_access metadata for all surrounding parallel loops.
  This is especially usefull if an external paralleliser is used.

  This also removes the PollyLoopInfo class and comments the
  LoopAnnotator.

  A test case for multiple parallel loops is attached.

llvm-svn: 218793
This commit is contained in:
Johannes Doerfert 2014-10-01 20:10:44 +00:00
parent e3c513a965
commit c7b719fc03
5 changed files with 150 additions and 83 deletions

View File

@ -16,54 +16,35 @@
#define POLLY_CODEGEN_IRBUILDER_H
#include "llvm/IR/IRBuilder.h"
#include "llvm/Analysis/LoopInfo.h"
namespace polly {
/// @brief Keeps information about generated loops.
class PollyLoopInfo {
public:
PollyLoopInfo(llvm::BasicBlock *Header)
: LoopID(0), Header(Header), Parallel(false) {}
/// @brief Get the loop id metadata node.
///
/// Each loop is identified by a self referencing metadata node of the form:
///
/// '!n = metadata !{metadata !n}'
///
/// This functions creates such metadata on demand if not yet available.
///
/// @return The loop id metadata node.
llvm::MDNode *GetLoopID() const;
/// @brief Get the head basic block of this loop.
llvm::BasicBlock *GetHeader() const { return Header; }
/// @brief Check if the loop is parallel.
///
/// @return True, if the loop is parallel.
bool IsParallel() const { return Parallel; }
/// @brief Set a loop as parallel.
///
/// @IsParallel True, if the loop is to be marked as parallel. False, if the
// loop should be marked sequential.
void SetParallel(bool IsParallel = true) { Parallel = IsParallel; }
private:
mutable llvm::MDNode *LoopID;
llvm::BasicBlock *Header;
bool Parallel;
};
/// @brief Helper class to annotate newly generated loops with metadata.
///
/// This stack-like structure will keep track of all loops, and annotate
/// memory instructions and loop headers according to all parallel loops.
class LoopAnnotator {
public:
void Begin(llvm::BasicBlock *Header);
void SetCurrentParallel();
void End();
void Annotate(llvm::Instruction *I);
/// @brief Add a new loop @p L which is parallel if @p IsParallel is true.
void pushLoop(llvm::Loop *L, bool IsParallel);
/// @brief Remove the last added loop.
void popLoop(bool isParallel);
/// @brief Annotate the new instruction @p I for all parallel loops.
void annotate(llvm::Instruction *I);
/// @brief Annotate the loop latch @p B wrt. @p L.
void annotateLoopLatch(llvm::BranchInst *B, llvm::Loop *L,
bool IsParallel) const;
private:
std::vector<PollyLoopInfo> Active;
/// @brief All loops currently under construction.
llvm::SmallVector<llvm::Loop *, 8> ActiveLoops;
/// @brief Metadata pointing to parallel loops currently under construction.
llvm::SmallVector<llvm::MDNode *, 8> ParallelLoops;
};
/// @brief Add Polly specifics when running IRBuilder.
@ -84,7 +65,7 @@ protected:
llvm::IRBuilderDefaultInserter<PreserveNames>::InsertHelper(I, Name, BB,
InsertPt);
if (Annotator)
Annotator->Annotate(I);
Annotator->annotate(I);
}
private:

View File

@ -13,48 +13,66 @@
//===----------------------------------------------------------------------===//
#include "polly/CodeGen/IRBuilder.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/IR/Metadata.h"
#include "llvm/Support/Debug.h"
using namespace llvm;
using namespace polly;
llvm::MDNode *polly::PollyLoopInfo::GetLoopID() const {
if (LoopID)
return LoopID;
llvm::Value *Args[] = {0};
LoopID = llvm::MDNode::get(Header->getContext(), Args);
/// @brief Get the loop id metadata node.
///
/// Each loop is identified by a self referencing metadata node of the form:
///
/// '!n = metadata !{metadata !n}'
///
/// This functions creates such metadata on demand if not yet available.
///
/// @return The loop id metadata node.
static MDNode *getLoopID(Loop *L) {
Value *Args[] = {0};
MDNode *LoopID = MDNode::get(L->getHeader()->getContext(), Args);
LoopID->replaceOperandWith(0, LoopID);
return LoopID;
}
void polly::LoopAnnotator::Begin(llvm::BasicBlock *Header) {
Active.push_back(PollyLoopInfo(Header));
}
void polly::LoopAnnotator::End() { Active.pop_back(); }
void polly::LoopAnnotator::SetCurrentParallel() {
Active.back().SetParallel(true);
}
void polly::LoopAnnotator::Annotate(llvm::Instruction *Inst) {
if (Active.empty())
void polly::LoopAnnotator::pushLoop(Loop *L, bool IsParallel) {
ActiveLoops.push_back(L);
if (!IsParallel)
return;
const PollyLoopInfo &L = Active.back();
if (!L.IsParallel())
BasicBlock *Header = L->getHeader();
MDNode *Id = getLoopID(L);
Value *Args[] = {Id};
MDNode *Ids = ParallelLoops.empty()
? MDNode::get(Header->getContext(), Args)
: MDNode::concatenate(ParallelLoops.back(), Id);
ParallelLoops.push_back(Ids);
}
void polly::LoopAnnotator::popLoop(bool IsParallel) {
ActiveLoops.pop_back();
if (!IsParallel)
return;
if (TerminatorInst *TI = dyn_cast<llvm::TerminatorInst>(Inst)) {
for (unsigned i = 0, ie = TI->getNumSuccessors(); i != ie; ++i)
if (TI->getSuccessor(i) == L.GetHeader()) {
TI->setMetadata("llvm.loop", L.GetLoopID());
break;
}
} else if (Inst->mayReadOrWriteMemory()) {
Inst->setMetadata("llvm.mem.parallel_loop_access", L.GetLoopID());
}
assert(!ParallelLoops.empty() && "Expected a parallel loop to pop");
ParallelLoops.pop_back();
}
void polly::LoopAnnotator::annotateLoopLatch(BranchInst *B, Loop *L,
bool IsParallel) const {
if (!IsParallel)
return;
assert(!ParallelLoops.empty() && "Expected a parallel loop to annotate");
MDNode *Ids = ParallelLoops.back();
MDNode *Id = cast<MDNode>(Ids->getOperand(Ids->getNumOperands() - 1));
B->setMetadata("llvm.loop", Id);
}
void polly::LoopAnnotator::annotate(Instruction *Inst) {
if (!Inst->mayReadOrWriteMemory() || ParallelLoops.empty())
return;
Inst->setMetadata("llvm.mem.parallel_loop_access", ParallelLoops.back());
}

View File

@ -319,8 +319,8 @@ void IslNodeBuilder::createForSequential(__isl_take isl_ast_node *For) {
CmpInst::Predicate Predicate;
bool Parallel;
Parallel = IslAstInfo::isInnermostParallel(For) &&
!IslAstInfo::isReductionParallel(For);
Parallel =
IslAstInfo::isParallel(For) && !IslAstInfo::isReductionParallel(For);
Body = isl_ast_node_for_get_body(For);
@ -362,7 +362,7 @@ void IslNodeBuilder::createForSequential(__isl_take isl_ast_node *For) {
create(Body);
Annotator.End();
Annotator.popLoop(Parallel);
IDToValue.erase(IteratorID);

View File

@ -64,12 +64,6 @@ Value *polly::createLoop(Value *LB, Value *UB, Value *Stride,
BasicBlock *PreHeaderBB =
BasicBlock::Create(Context, "polly.loop_preheader", F);
if (Annotator) {
Annotator->Begin(HeaderBB);
if (Parallel)
Annotator->SetCurrentParallel();
}
// Update LoopInfo
Loop *OuterLoop = LI.getLoopFor(BeforeBB);
Loop *NewLoop = new Loop();
@ -86,6 +80,11 @@ Value *polly::createLoop(Value *LB, Value *UB, Value *Stride,
NewLoop->addBasicBlockToLoop(HeaderBB, LI.getBase());
// Notify the annotator (if present) that we have a new loop, but only
// after the header block is set.
if (Annotator)
Annotator->pushLoop(NewLoop, Parallel);
// ExitBB
ExitBB = SplitBlock(BeforeBB, Builder.GetInsertPoint()++, P);
ExitBB->setName("polly.loop_exit");
@ -122,7 +121,12 @@ Value *polly::createLoop(Value *LB, Value *UB, Value *Stride,
UB = Builder.CreateSub(UB, Stride, "polly.adjust_ub");
LoopCondition = Builder.CreateICmp(Predicate, IV, UB);
LoopCondition->setName("polly.loop_cond");
Builder.CreateCondBr(LoopCondition, HeaderBB, ExitBB);
// Create the loop latch and annotate it as such.
BranchInst *B = Builder.CreateCondBr(LoopCondition, HeaderBB, ExitBB);
if (Annotator)
Annotator->annotateLoopLatch(B, NewLoop, Parallel);
IV->addIncoming(IncrementedIV, HeaderBB);
if (GuardBB)
DT.changeImmediateDominator(ExitBB, GuardBB);

View File

@ -0,0 +1,64 @@
; RUN: opt %loadPolly -polly-codegen-isl -polly-ast-detect-parallel -S < %s | FileCheck %s
;
; Check that we mark multiple parallel loops correctly including the memory instructions.
;
; CHECK-DAG: %polly.loop_cond[[COuter:[0-9]*]] = icmp sle i64 %polly.indvar{{[0-9]*}}, 1022
; CHECK-DAG: br i1 %polly.loop_cond[[COuter]], label %polly.loop_header{{[0-9]*}}, label %polly.loop_exit{{[0-9]*}}, !llvm.loop !0
;
; CHECK-DAG: %polly.loop_cond[[CInner:[0-9]*]] = icmp sle i64 %polly.indvar{{[0-9]*}}, 510
; CHECK-DAG: br i1 %polly.loop_cond[[CInner]], label %polly.loop_header{{[0-9]*}}, label %polly.loop_exit{{[0-9]*}}, !llvm.loop !2
;
; CHECK-DAG: store i32 %p_tmp{{[0-9]*}}, i32* %p_arrayidx{{[0-9]*}}, !llvm.mem.parallel_loop_access !1
;
; CHECK: !0 = metadata !{metadata !0}
; CHECK: !1 = metadata !{metadata !0, metadata !2}
; CHECK: !2 = metadata !{metadata !2}
;
; void jd(int *A) {
; for (int i = 0; i < 1024; i++)
; for (int j = 0; j < 512; j++)
; A[i * 512 + j] = i + j;
; }
;
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
define void @jd(i32* %A) {
entry:
br label %for.cond
for.cond: ; preds = %for.inc5, %entry
%indvars.iv3 = phi i64 [ %indvars.iv.next4, %for.inc5 ], [ 0, %entry ]
%exitcond6 = icmp ne i64 %indvars.iv3, 1024
br i1 %exitcond6, label %for.body, label %for.end7
for.body: ; preds = %for.cond
br label %for.cond1
for.cond1: ; preds = %for.inc, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %for.body ]
%exitcond = icmp ne i64 %indvars.iv, 512
br i1 %exitcond, label %for.body3, label %for.end
for.body3: ; preds = %for.cond1
%tmp = add nsw i64 %indvars.iv3, %indvars.iv
%tmp7 = shl nsw i64 %indvars.iv3, 9
%tmp8 = add nsw i64 %tmp7, %indvars.iv
%arrayidx = getelementptr inbounds i32* %A, i64 %tmp8
%tmp9 = trunc i64 %tmp to i32
store i32 %tmp9, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body3
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
br label %for.cond1
for.end: ; preds = %for.cond1
br label %for.inc5
for.inc5: ; preds = %for.end
%indvars.iv.next4 = add nuw nsw i64 %indvars.iv3, 1
br label %for.cond
for.end7: ; preds = %for.cond
ret void
}