OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 2
Code Issues Packages Projects Releases Wiki Activity

Revert "[LoopUnrollAndJam] Change LoopUnrollAndJamPass to LoopNest pass" 

This reverts commit d65c32fb41.
This commit is contained in:
maekawatoshiki 2021-05-25 11:39:49 +09:00
parent 96d70f4d28
commit e77d24f70a
7 changed files with 59 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/include/llvm/Transforms/Scalar/LoopUnrollAndJamPass.h
View File

@ -10,7 +10,6 @@
#define LLVM_TRANSFORMS_SCALAR_LOOPUNROLLANDJAMPASS_H
#include "llvm/IR/PassManager.h"
#include "llvm/Transforms/Scalar/LoopPassManager.h"
namespace llvm {
class Function;
@ -21,8 +20,7 @@ class LoopUnrollAndJamPass : public PassInfoMixin<LoopUnrollAndJamPass> {
public:
explicit LoopUnrollAndJamPass(int OptLevel = 2) : OptLevel(OptLevel) {}
PreservedAnalyses run(LoopNest &L, LoopAnalysisManager &AM,
LoopStandardAnalysisResults &AR, LPMUpdater &U);
PreservedAnalyses run(Function &F, FunctionAnalysisManager &AM);
};
} // end namespace llvm

3
llvm/include/llvm/Transforms/Utils/UnrollLoop.h
View File

@ -17,7 +17,6 @@
#include "llvm/ADT/DenseMap.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Transforms/Scalar/LoopPassManager.h"
namespace llvm {
@ -98,7 +97,7 @@ LoopUnrollResult UnrollAndJamLoop(Loop *L, unsigned Count, unsigned TripCount,
LoopInfo *LI, ScalarEvolution *SE,
DominatorTree *DT, AssumptionCache *AC,
const TargetTransformInfo *TTI,
OptimizationRemarkEmitter *ORE, LPMUpdater *U,
OptimizationRemarkEmitter *ORE,
Loop **EpilogueLoop = nullptr);
bool isSafeToUnrollAndJam(Loop *L, ScalarEvolution &SE, DominatorTree &DT,

6
llvm/lib/Passes/PassBuilder.cpp
View File

@ -1207,8 +1207,7 @@ void PassBuilder::addVectorPasses(OptimizationLevel Level,
// across the loop nests.
// We do UnrollAndJam in a separate LPM to ensure it happens before unroll
if (EnableUnrollAndJam && PTO.LoopUnrolling)
FPM.addPass(createFunctionToLoopPassAdaptor(
LoopUnrollAndJamPass(Level.getSpeedupLevel())));
FPM.addPass(LoopUnrollAndJamPass(Level.getSpeedupLevel()));
FPM.addPass(LoopUnrollPass(LoopUnrollOptions(
Level.getSpeedupLevel(), /*OnlyWhenForced=*/!PTO.LoopUnrolling,
PTO.ForgetAllSCEVInLoopUnroll)));
@ -1291,8 +1290,7 @@ void PassBuilder::addVectorPasses(OptimizationLevel Level,
// across the loop nests.
// We do UnrollAndJam in a separate LPM to ensure it happens before unroll
if (EnableUnrollAndJam && PTO.LoopUnrolling) {
FPM.addPass(createFunctionToLoopPassAdaptor(
LoopUnrollAndJamPass(Level.getSpeedupLevel())));
FPM.addPass(LoopUnrollAndJamPass(Level.getSpeedupLevel()));
}
FPM.addPass(LoopUnrollPass(LoopUnrollOptions(
Level.getSpeedupLevel(), /*OnlyWhenForced=*/!PTO.LoopUnrolling,

2
llvm/lib/Passes/PassRegistry.def
View File

@ -247,6 +247,7 @@ FUNCTION_PASS("guard-widening", GuardWideningPass())
FUNCTION_PASS("load-store-vectorizer", LoadStoreVectorizerPass())
FUNCTION_PASS("loop-simplify", LoopSimplifyPass())
FUNCTION_PASS("loop-sink", LoopSinkPass())
FUNCTION_PASS("loop-unroll-and-jam", LoopUnrollAndJamPass())
FUNCTION_PASS("loop-flatten", LoopFlattenPass())
FUNCTION_PASS("lowerinvoke", LowerInvokePass())
FUNCTION_PASS("lowerswitch", LowerSwitchPass())
@ -398,7 +399,6 @@ LOOP_PASS("loop-deletion", LoopDeletionPass())
LOOP_PASS("loop-simplifycfg", LoopSimplifyCFGPass())
LOOP_PASS("loop-reduce", LoopStrengthReducePass())
LOOP_PASS("indvars", IndVarSimplifyPass())
LOOP_PASS("loop-unroll-and-jam", LoopUnrollAndJamPass())
LOOP_PASS("loop-unroll-full", LoopFullUnrollPass())
LOOP_PASS("print-access-info", LoopAccessInfoPrinterPass(dbgs()))
LOOP_PASS("print<ddg>", DDGAnalysisPrinterPass(dbgs()))

92
llvm/lib/Transforms/Scalar/LoopUnrollAndJamPass.cpp
View File

@ -22,7 +22,6 @@
#include "llvm/Analysis/DependenceAnalysis.h"
#include "llvm/Analysis/LoopAnalysisManager.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/LoopPass.h"
#include "llvm/Analysis/OptimizationRemarkEmitter.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/TargetTransformInfo.h"
@ -279,10 +278,11 @@ static bool computeUnrollAndJamCount(
return false;
}
static LoopUnrollResult tryToUnrollAndJamLoop(
Loop *L, DominatorTree &DT, LoopInfo *LI, ScalarEvolution &SE,
const TargetTransformInfo &TTI, AssumptionCache &AC, DependenceInfo &DI,
OptimizationRemarkEmitter &ORE, int OptLevel, LPMUpdater *U) {
static LoopUnrollResult
tryToUnrollAndJamLoop(Loop *L, DominatorTree &DT, LoopInfo *LI,
ScalarEvolution &SE, const TargetTransformInfo &TTI,
AssumptionCache &AC, DependenceInfo &DI,
OptimizationRemarkEmitter &ORE, int OptLevel) {
TargetTransformInfo::UnrollingPreferences UP =
gatherUnrollingPreferences(L, SE, TTI, nullptr, nullptr, OptLevel, None,
None, None, None, None, None);
@ -385,7 +385,7 @@ static LoopUnrollResult tryToUnrollAndJamLoop(
Loop *EpilogueOuterLoop = nullptr;
LoopUnrollResult UnrollResult = UnrollAndJamLoop(
L, UP.Count, OuterTripCount, OuterTripMultiple, UP.UnrollRemainder, LI,
&SE, &DT, &AC, &TTI, &ORE, U, &EpilogueOuterLoop);
&SE, &DT, &AC, &TTI, &ORE, &EpilogueOuterLoop);
// Assign new loop attributes.
if (EpilogueOuterLoop) {
@ -424,23 +424,33 @@ static LoopUnrollResult tryToUnrollAndJamLoop(
return UnrollResult;
}
static bool tryToUnrollAndJamLoop(LoopNest &LN, DominatorTree &DT, LoopInfo &LI,
static bool tryToUnrollAndJamLoop(Function &F, DominatorTree &DT, LoopInfo &LI,
ScalarEvolution &SE,
const TargetTransformInfo &TTI,
AssumptionCache &AC, DependenceInfo &DI,
OptimizationRemarkEmitter &ORE, int OptLevel,
LPMUpdater &U) {
OptimizationRemarkEmitter &ORE,
int OptLevel) {
bool DidSomething = false;
ArrayRef<Loop *> Loops = LN.getLoops();
// Add the loop nests in the reverse order of LN. See method
// The loop unroll and jam pass requires loops to be in simplified form, and
// also needs LCSSA. Since simplification may add new inner loops, it has to
// run before the legality and profitability checks. This means running the
// loop unroll and jam pass will simplify all loops, regardless of whether
// anything end up being unroll and jammed.
for (auto &L : LI) {
DidSomething |=
simplifyLoop(L, &DT, &LI, &SE, &AC, nullptr, false /* PreserveLCSSA */);
DidSomething |= formLCSSARecursively(*L, DT, &LI, &SE);
}
// Add the loop nests in the reverse order of LoopInfo. See method
// declaration.
SmallPriorityWorklist<Loop *, 4> Worklist;
appendLoopsToWorklist(Loops, Worklist);
appendLoopsToWorklist(LI, Worklist);
while (!Worklist.empty()) {
Loop *L = Worklist.pop_back_val();
LoopUnrollResult Result =
tryToUnrollAndJamLoop(L, DT, &LI, SE, TTI, AC, DI, ORE, OptLevel, &U);
tryToUnrollAndJamLoop(L, DT, &LI, SE, TTI, AC, DI, ORE, OptLevel);
if (Result != LoopUnrollResult::Unmodified)
DidSomething = true;
}
@ -450,35 +460,29 @@ static bool tryToUnrollAndJamLoop(LoopNest &LN, DominatorTree &DT, LoopInfo &LI,
namespace {
class LoopUnrollAndJam : public LoopPass {
class LoopUnrollAndJam : public FunctionPass {
public:
static char ID; // Pass ID, replacement for typeid
unsigned OptLevel;
LoopUnrollAndJam(int OptLevel = 2) : LoopPass(ID), OptLevel(OptLevel) {
LoopUnrollAndJam(int OptLevel = 2) : FunctionPass(ID), OptLevel(OptLevel) {
initializeLoopUnrollAndJamPass(*PassRegistry::getPassRegistry());
}
bool runOnLoop(Loop *L, LPPassManager &LPM) override {
if (skipLoop(L))
bool runOnFunction(Function &F) override {
if (skipFunction(F))
return false;
auto *F = L->getHeader()->getParent();
auto &SE = getAnalysis<ScalarEvolutionWrapperPass>().getSE();
auto *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
auto &DI = getAnalysis<DependenceAnalysisWrapperPass>().getDI();
auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
auto &TTI = getAnalysis<TargetTransformInfoWrapperPass>().getTTI(*F);
LoopInfo &LI = getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
ScalarEvolution &SE = getAnalysis<ScalarEvolutionWrapperPass>().getSE();
const TargetTransformInfo &TTI =
getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
auto &DI = getAnalysis<DependenceAnalysisWrapperPass>().getDI();
auto &ORE = getAnalysis<OptimizationRemarkEmitterWrapperPass>().getORE();
auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(*F);
LoopUnrollResult Result = tryToUnrollAndJamLoop(L, DT, LI, SE, TTI, AC, DI,
ORE, OptLevel, nullptr);
if (Result == LoopUnrollResult::FullyUnrolled)
LPM.markLoopAsDeleted(*L);
return Result != LoopUnrollResult::Unmodified;
return tryToUnrollAndJamLoop(F, DT, LI, SE, TTI, AC, DI, ORE, OptLevel);
}
/// This transformation requires natural loop information & requires that
@ -501,10 +505,7 @@ char LoopUnrollAndJam::ID = 0;
INITIALIZE_PASS_BEGIN(LoopUnrollAndJam, "loop-unroll-and-jam",
"Unroll and Jam loops", false, false)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopPass)
INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopSimplify)
INITIALIZE_PASS_DEPENDENCY(LCSSAWrapperPass)
INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
@ -517,20 +518,19 @@ Pass *llvm::createLoopUnrollAndJamPass(int OptLevel) {
return new LoopUnrollAndJam(OptLevel);
}
PreservedAnalyses LoopUnrollAndJamPass::run(LoopNest &LN,
LoopAnalysisManager &AM,
LoopStandardAnalysisResults &AR,
LPMUpdater &U) {
Function &F = *LN.getParent();
PreservedAnalyses LoopUnrollAndJamPass::run(Function &F,
FunctionAnalysisManager &AM) {
ScalarEvolution &SE = AM.getResult<ScalarEvolutionAnalysis>(F);
LoopInfo &LI = AM.getResult<LoopAnalysis>(F);
TargetTransformInfo &TTI = AM.getResult<TargetIRAnalysis>(F);
AssumptionCache &AC = AM.getResult<AssumptionAnalysis>(F);
DominatorTree &DT = AM.getResult<DominatorTreeAnalysis>(F);
DependenceInfo &DI = AM.getResult<DependenceAnalysis>(F);
OptimizationRemarkEmitter &ORE =
AM.getResult<OptimizationRemarkEmitterAnalysis>(F);
DependenceInfo DI(&F, &AR.AA, &AR.SE, &AR.LI);
OptimizationRemarkEmitter ORE(&F);
if (!tryToUnrollAndJamLoop(LN, AR.DT, AR.LI, AR.SE, AR.TTI, AR.AC, DI, ORE,
OptLevel, U))
if (!tryToUnrollAndJamLoop(F, DT, LI, SE, TTI, AC, DI, ORE, OptLevel))
return PreservedAnalyses::all();
auto PA = getLoopPassPreservedAnalyses();
PA.preserve<LoopNestAnalysis>();
return PA;
return getLoopPassPreservedAnalyses();
}

17
llvm/lib/Transforms/Utils/LoopUnrollAndJam.cpp
View File

@ -49,7 +49,6 @@
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/GenericDomTree.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Scalar/LoopPassManager.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/Cloning.h"
#include "llvm/Transforms/Utils/LoopUtils.h"
@ -222,11 +221,12 @@ static void moveHeaderPhiOperandsToForeBlocks(BasicBlock *Header,
If EpilogueLoop is non-null, it receives the epilogue loop (if it was
necessary to create one and not fully unrolled).
*/
LoopUnrollResult llvm::UnrollAndJamLoop(
Loop *L, unsigned Count, unsigned TripCount, unsigned TripMultiple,
bool UnrollRemainder, LoopInfo *LI, ScalarEvolution *SE, DominatorTree *DT,
AssumptionCache *AC, const TargetTransformInfo *TTI,
OptimizationRemarkEmitter *ORE, LPMUpdater *U, Loop **EpilogueLoop) {
LoopUnrollResult
llvm::UnrollAndJamLoop(Loop *L, unsigned Count, unsigned TripCount,
unsigned TripMultiple, bool UnrollRemainder,
LoopInfo *LI, ScalarEvolution *SE, DominatorTree *DT,
AssumptionCache *AC, const TargetTransformInfo *TTI,
OptimizationRemarkEmitter *ORE, Loop **EpilogueLoop) {
// When we enter here we should have already checked that it is safe
BasicBlock *Header = L->getHeader();
@ -605,11 +605,8 @@ LoopUnrollResult llvm::UnrollAndJamLoop(
++NumUnrolledAndJammed;
// Update LoopInfo if the loop is completely removed.
if (CompletelyUnroll) {
if (U)
U->markLoopAsDeleted(*L, std::string(L->getName()));
if (CompletelyUnroll)
LI->erase(L);
}
#ifndef NDEBUG
// We shouldn't have done anything to break loop simplify form or LCSSA.

2
llvm/test/Transforms/LoopUnrollAndJam/innerloop.ll
View File

@ -1,5 +1,5 @@
; RUN: opt -loop-unroll-and-jam -allow-unroll-and-jam -verify-loop-info < %s -S | FileCheck %s
; RUN: opt -passes='loop(loop-unroll-and-jam),verify<loops>' -allow-unroll-and-jam < %s -S | FileCheck %s
; RUN: opt -passes='loop-unroll-and-jam,verify<loops>' -allow-unroll-and-jam < %s -S | FileCheck %s
; Check that the newly created loops to not fail to be added to LI
; This test deliberately disables UnJ on the middle loop, performing it instead on the