This revision was automatically updated to reflect the committed changes.
Closed by commit rG2ea4c2c598b7: [BFI] Make BFI information available through
loop passes inside… (authored by wenlei).
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D86156/new/
https://reviews.llvm.org/D86156
Files:
llvm/include/llvm/Analysis/LoopAnalysisManager.h
llvm/include/llvm/Transforms/Scalar/LoopPassManager.h
llvm/lib/Passes/PassBuilder.cpp
llvm/lib/Transforms/Scalar/LICM.cpp
llvm/lib/Transforms/Scalar/LoopDistribute.cpp
llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
llvm/lib/Transforms/Scalar/LoopUnswitch.cpp
llvm/lib/Transforms/Utils/LoopVersioning.cpp
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
llvm/test/Other/opt-O2-pipeline.ll
llvm/test/Other/opt-O3-pipeline-enable-matrix.ll
llvm/test/Other/opt-O3-pipeline.ll
llvm/test/Other/opt-Os-pipeline.ll
llvm/unittests/Transforms/Scalar/LoopPassManagerTest.cpp
Index: llvm/unittests/Transforms/Scalar/LoopPassManagerTest.cpp
===================================================================
--- llvm/unittests/Transforms/Scalar/LoopPassManagerTest.cpp
+++ llvm/unittests/Transforms/Scalar/LoopPassManagerTest.cpp
@@ -9,7 +9,10 @@
#include "llvm/Transforms/Scalar/LoopPassManager.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/AssumptionCache.h"
+#include "llvm/Analysis/BlockFrequencyInfo.h"
+#include "llvm/Analysis/BranchProbabilityInfo.h"
#include "llvm/Analysis/MemorySSA.h"
+#include "llvm/Analysis/PostDominators.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
@@ -294,6 +297,9 @@
// those.
FAM.registerPass([&] { return AAManager(); });
FAM.registerPass([&] { return AssumptionAnalysis(); });
+ FAM.registerPass([&] { return BlockFrequencyAnalysis(); });
+ FAM.registerPass([&] { return BranchProbabilityAnalysis(); });
+ FAM.registerPass([&] { return PostDominatorTreeAnalysis(); });
FAM.registerPass([&] { return MemorySSAAnalysis(); });
FAM.registerPass([&] { return ScalarEvolutionAnalysis(); });
FAM.registerPass([&] { return TargetLibraryAnalysis(); });
Index: llvm/test/Other/opt-Os-pipeline.ll
===================================================================
--- llvm/test/Other/opt-Os-pipeline.ll
+++ llvm/test/Other/opt-Os-pipeline.ll
@@ -97,6 +97,8 @@
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Rotate Loops
; CHECK-NEXT: Memory SSA
+; CHECK-NEXT: Lazy Branch Probability Analysis
+; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Unswitch loops
@@ -154,6 +156,8 @@
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
+; CHECK-NEXT: Lazy Branch Probability Analysis
+; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Post-Dominator Tree Construction
@@ -256,10 +260,10 @@
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
-; CHECK-NEXT: Loop Pass Manager
-; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Lazy Branch Probability Analysis
; CHECK-NEXT: Lazy Block Frequency Analysis
+; CHECK-NEXT: Loop Pass Manager
+; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Optimization Remark Emitter
; CHECK-NEXT: Warn about non-applied transformations
; CHECK-NEXT: Alignment from assumptions
Index: llvm/test/Other/opt-O3-pipeline.ll
===================================================================
--- llvm/test/Other/opt-O3-pipeline.ll
+++ llvm/test/Other/opt-O3-pipeline.ll
@@ -116,6 +116,8 @@
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Rotate Loops
; CHECK-NEXT: Memory SSA
+; CHECK-NEXT: Lazy Branch Probability Analysis
+; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Unswitch loops
@@ -173,6 +175,8 @@
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
+; CHECK-NEXT: Lazy Branch Probability Analysis
+; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Post-Dominator Tree Construction
@@ -275,10 +279,10 @@
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
-; CHECK-NEXT: Loop Pass Manager
-; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Lazy Branch Probability Analysis
; CHECK-NEXT: Lazy Block Frequency Analysis
+; CHECK-NEXT: Loop Pass Manager
+; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Optimization Remark Emitter
; CHECK-NEXT: Warn about non-applied transformations
; CHECK-NEXT: Alignment from assumptions
Index: llvm/test/Other/opt-O3-pipeline-enable-matrix.ll
===================================================================
--- llvm/test/Other/opt-O3-pipeline-enable-matrix.ll
+++ llvm/test/Other/opt-O3-pipeline-enable-matrix.ll
@@ -116,6 +116,8 @@
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Rotate Loops
; CHECK-NEXT: Memory SSA
+; CHECK-NEXT: Lazy Branch Probability Analysis
+; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Unswitch loops
@@ -173,6 +175,8 @@
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
+; CHECK-NEXT: Lazy Branch Probability Analysis
+; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Post-Dominator Tree Construction
@@ -282,10 +286,10 @@
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
-; CHECK-NEXT: Loop Pass Manager
-; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Lazy Branch Probability Analysis
; CHECK-NEXT: Lazy Block Frequency Analysis
+; CHECK-NEXT: Loop Pass Manager
+; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Optimization Remark Emitter
; CHECK-NEXT: Warn about non-applied transformations
; CHECK-NEXT: Alignment from assumptions
Index: llvm/test/Other/opt-O2-pipeline.ll
===================================================================
--- llvm/test/Other/opt-O2-pipeline.ll
+++ llvm/test/Other/opt-O2-pipeline.ll
@@ -111,6 +111,8 @@
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Rotate Loops
; CHECK-NEXT: Memory SSA
+; CHECK-NEXT: Lazy Branch Probability Analysis
+; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Unswitch loops
@@ -168,6 +170,8 @@
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
+; CHECK-NEXT: Lazy Branch Probability Analysis
+; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Post-Dominator Tree Construction
@@ -270,10 +274,10 @@
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
-; CHECK-NEXT: Loop Pass Manager
-; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Lazy Branch Probability Analysis
; CHECK-NEXT: Lazy Block Frequency Analysis
+; CHECK-NEXT: Loop Pass Manager
+; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Optimization Remark Emitter
; CHECK-NEXT: Warn about non-applied transformations
; CHECK-NEXT: Alignment from assumptions
Index: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -8621,7 +8621,8 @@
auto &LAM = AM.getResult<LoopAnalysisManagerFunctionProxy>(F).getManager();
std::function<const LoopAccessInfo &(Loop &)> GetLAA =
[&](Loop &L) -> const LoopAccessInfo & {
- LoopStandardAnalysisResults AR = {AA, AC, DT, LI, SE, TLI, TTI, MSSA};
+ LoopStandardAnalysisResults AR = {AA, AC, DT, LI, SE,
+ TLI, TTI, nullptr, MSSA};
return LAM.getResult<LoopAccessAnalysis>(L, AR);
};
auto &MAMProxy = AM.getResult<ModuleAnalysisManagerFunctionProxy>(F);
Index: llvm/lib/Transforms/Utils/LoopVersioning.cpp
===================================================================
--- llvm/lib/Transforms/Utils/LoopVersioning.cpp
+++ llvm/lib/Transforms/Utils/LoopVersioning.cpp
@@ -357,7 +357,8 @@
auto &LAM = AM.getResult<LoopAnalysisManagerFunctionProxy>(F).getManager();
auto GetLAA = [&](Loop &L) -> const LoopAccessInfo & {
- LoopStandardAnalysisResults AR = {AA, AC, DT, LI, SE, TLI, TTI, MSSA};
+ LoopStandardAnalysisResults AR = {AA, AC, DT, LI, SE,
+ TLI, TTI, nullptr, MSSA};
return LAM.getResult<LoopAccessAnalysis>(L, AR);
};
Index: llvm/lib/Transforms/Scalar/LoopUnswitch.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/LoopUnswitch.cpp
+++ llvm/lib/Transforms/Scalar/LoopUnswitch.cpp
@@ -32,6 +32,7 @@
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/CodeMetrics.h"
#include "llvm/Analysis/InstructionSimplify.h"
+#include "llvm/Analysis/LazyBlockFrequencyInfo.h"
#include "llvm/Analysis/LegacyDivergenceAnalysis.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/LoopIterator.h"
@@ -217,6 +218,10 @@
/// loop preheaders be inserted into the CFG.
///
void getAnalysisUsage(AnalysisUsage &AU) const override {
+ // Lazy BFI and BPI are marked as preserved here so Loop Unswitching
+ // can remain part of the same loop pass as LICM
+ AU.addPreserved<LazyBlockFrequencyInfoPass>();
+ AU.addPreserved<LazyBranchProbabilityInfoPass>();
AU.addRequired<AssumptionCacheTracker>();
AU.addRequired<TargetTransformInfoWrapperPass>();
if (EnableMSSALoopDependency) {
Index: llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
+++ llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
@@ -720,7 +720,8 @@
auto &LAM = AM.getResult<LoopAnalysisManagerFunctionProxy>(F).getManager();
bool Changed = eliminateLoadsAcrossLoops(
F, LI, DT, BFI, PSI, [&](Loop &L) -> const LoopAccessInfo & {
- LoopStandardAnalysisResults AR = {AA, AC, DT, LI, SE, TLI, TTI, MSSA};
+ LoopStandardAnalysisResults AR = {AA, AC, DT, LI, SE,
+ TLI, TTI, nullptr, MSSA};
return LAM.getResult<LoopAccessAnalysis>(L, AR);
});
Index: llvm/lib/Transforms/Scalar/LoopDistribute.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/LoopDistribute.cpp
+++ llvm/lib/Transforms/Scalar/LoopDistribute.cpp
@@ -1058,7 +1058,8 @@
auto &LAM = AM.getResult<LoopAnalysisManagerFunctionProxy>(F).getManager();
std::function<const LoopAccessInfo &(Loop &)> GetLAA =
[&](Loop &L) -> const LoopAccessInfo & {
- LoopStandardAnalysisResults AR = {AA, AC, DT, LI, SE, TLI, TTI, nullptr};
+ LoopStandardAnalysisResults AR = {AA, AC, DT, LI, SE,
+ TLI, TTI, nullptr, nullptr};
return LAM.getResult<LoopAccessAnalysis>(L, AR);
};
Index: llvm/lib/Transforms/Scalar/LICM.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/LICM.cpp
+++ llvm/lib/Transforms/Scalar/LICM.cpp
@@ -39,6 +39,7 @@
#include "llvm/Analysis/ConstantFolding.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/GuardUtils.h"
+#include "llvm/Analysis/LazyBlockFrequencyInfo.h"
#include "llvm/Analysis/Loads.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/LoopIterator.h"
@@ -171,8 +172,8 @@
namespace {
struct LoopInvariantCodeMotion {
bool runOnLoop(Loop *L, AAResults *AA, LoopInfo *LI, DominatorTree *DT,
- TargetLibraryInfo *TLI, TargetTransformInfo *TTI,
- ScalarEvolution *SE, MemorySSA *MSSA,
+ BlockFrequencyInfo *BFI, TargetLibraryInfo *TLI,
+ TargetTransformInfo *TTI, ScalarEvolution *SE, MemorySSA *MSSA,
OptimizationRemarkEmitter *ORE);
LoopInvariantCodeMotion(unsigned LicmMssaOptCap,
@@ -208,19 +209,23 @@
MemorySSA *MSSA = EnableMSSALoopDependency
? (&getAnalysis<MemorySSAWrapperPass>().getMSSA())
: nullptr;
+ bool hasProfileData = L->getHeader()->getParent()->hasProfileData();
+ BlockFrequencyInfo *BFI =
+ hasProfileData ? &getAnalysis<LazyBlockFrequencyInfoPass>().getBFI()
+ : nullptr;
// For the old PM, we can't use OptimizationRemarkEmitter as an analysis
- // pass. Function analyses need to be preserved across loop transformations
+ // pass. Function analyses need to be preserved across loop transformations
// but ORE cannot be preserved (see comment before the pass definition).
OptimizationRemarkEmitter ORE(L->getHeader()->getParent());
- return LICM.runOnLoop(L,
- &getAnalysis<AAResultsWrapperPass>().getAAResults(),
- &getAnalysis<LoopInfoWrapperPass>().getLoopInfo(),
- &getAnalysis<DominatorTreeWrapperPass>().getDomTree(),
- &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(
- *L->getHeader()->getParent()),
- &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(
- *L->getHeader()->getParent()),
- SE ? &SE->getSE() : nullptr, MSSA, &ORE);
+ return LICM.runOnLoop(
+ L, &getAnalysis<AAResultsWrapperPass>().getAAResults(),
+ &getAnalysis<LoopInfoWrapperPass>().getLoopInfo(),
+ &getAnalysis<DominatorTreeWrapperPass>().getDomTree(), BFI,
+ &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(
+ *L->getHeader()->getParent()),
+ &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(
+ *L->getHeader()->getParent()),
+ SE ? &SE->getSE() : nullptr, MSSA, &ORE);
}
/// This transformation requires natural loop information & requires that
@@ -236,6 +241,9 @@
}
AU.addRequired<TargetTransformInfoWrapperPass>();
getLoopAnalysisUsage(AU);
+ LazyBlockFrequencyInfoPass::getLazyBFIAnalysisUsage(AU);
+ AU.addPreserved<LazyBlockFrequencyInfoPass>();
+ AU.addPreserved<LazyBranchProbabilityInfoPass>();
}
private:
@@ -251,8 +259,8 @@
OptimizationRemarkEmitter ORE(L.getHeader()->getParent());
LoopInvariantCodeMotion LICM(LicmMssaOptCap, LicmMssaNoAccForPromotionCap);
- if (!LICM.runOnLoop(&L, &AR.AA, &AR.LI, &AR.DT, &AR.TLI, &AR.TTI, &AR.SE,
- AR.MSSA, &ORE))
+ if (!LICM.runOnLoop(&L, &AR.AA, &AR.LI, &AR.DT, AR.BFI, &AR.TLI, &AR.TTI,
+ &AR.SE, AR.MSSA, &ORE))
return PreservedAnalyses::all();
auto PA = getLoopPassPreservedAnalyses();
@@ -272,6 +280,7 @@
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(MemorySSAWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(LazyBFIPass)
INITIALIZE_PASS_END(LegacyLICMPass, "licm", "Loop Invariant Code Motion", false,
false)
@@ -286,8 +295,8 @@
/// times on one loop.
bool LoopInvariantCodeMotion::runOnLoop(
Loop *L, AAResults *AA, LoopInfo *LI, DominatorTree *DT,
- TargetLibraryInfo *TLI, TargetTransformInfo *TTI, ScalarEvolution *SE,
- MemorySSA *MSSA, OptimizationRemarkEmitter *ORE) {
+ BlockFrequencyInfo *BFI, TargetLibraryInfo *TLI, TargetTransformInfo *TTI,
+ ScalarEvolution *SE, MemorySSA *MSSA, OptimizationRemarkEmitter *ORE) {
bool Changed = false;
assert(L->isLCSSAForm(*DT) && "Loop is not in LCSSA form.");
Index: llvm/lib/Passes/PassBuilder.cpp
===================================================================
--- llvm/lib/Passes/PassBuilder.cpp
+++ llvm/lib/Passes/PassBuilder.cpp
@@ -520,13 +520,15 @@
FPM.addPass(
RequireAnalysisPass<OptimizationRemarkEmitterAnalysis, Function>());
FPM.addPass(createFunctionToLoopPassAdaptor(
- std::move(LPM1), EnableMSSALoopDependency, DebugLogging));
+ std::move(LPM1), EnableMSSALoopDependency, /*UseBlockFrequencyInfo=*/true,
+ DebugLogging));
FPM.addPass(SimplifyCFGPass());
FPM.addPass(InstCombinePass());
// The loop passes in LPM2 (LoopFullUnrollPass) do not preserve MemorySSA.
// *All* loop passes must preserve it, in order to be able to use it.
FPM.addPass(createFunctionToLoopPassAdaptor(
- std::move(LPM2), /*UseMemorySSA=*/false, DebugLogging));
+ std::move(LPM2), /*UseMemorySSA=*/false, /*UseBlockFrequencyInfo=*/false,
+ DebugLogging));
// Delete small array after loop unroll.
FPM.addPass(SROA());
@@ -677,14 +679,16 @@
FPM.addPass(
RequireAnalysisPass<OptimizationRemarkEmitterAnalysis, Function>());
FPM.addPass(createFunctionToLoopPassAdaptor(
- std::move(LPM1), EnableMSSALoopDependency, DebugLogging));
+ std::move(LPM1), EnableMSSALoopDependency, /*UseBlockFrequencyInfo=*/true,
+ DebugLogging));
FPM.addPass(SimplifyCFGPass());
FPM.addPass(InstCombinePass());
// The loop passes in LPM2 (IndVarSimplifyPass, LoopIdiomRecognizePass,
// LoopDeletionPass and LoopFullUnrollPass) do not preserve MemorySSA.
// *All* loop passes must preserve it, in order to be able to use it.
FPM.addPass(createFunctionToLoopPassAdaptor(
- std::move(LPM2), /*UseMemorySSA=*/false, DebugLogging));
+ std::move(LPM2), /*UseMemorySSA=*/false, /*UseBlockFrequencyInfo=*/false,
+ DebugLogging));
// Delete small array after loop unroll.
FPM.addPass(SROA());
@@ -721,7 +725,7 @@
FPM.addPass(DSEPass());
FPM.addPass(createFunctionToLoopPassAdaptor(
LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap),
- EnableMSSALoopDependency, DebugLogging));
+ EnableMSSALoopDependency, /*UseBlockFrequencyInfo=*/true, DebugLogging));
if (PTO.Coroutines)
FPM.addPass(CoroElidePass());
@@ -799,7 +803,8 @@
FunctionPassManager FPM;
FPM.addPass(createFunctionToLoopPassAdaptor(
- LoopRotatePass(), EnableMSSALoopDependency, DebugLogging));
+ LoopRotatePass(), EnableMSSALoopDependency,
+ /*UseBlockFrequencyInfo=*/false, DebugLogging));
MPM.addPass(createModuleToFunctionPassAdaptor(std::move(FPM)));
// Add the profile lowering pass.
@@ -1129,7 +1134,8 @@
// First rotate loops that may have been un-rotated by prior passes.
OptimizePM.addPass(createFunctionToLoopPassAdaptor(
- LoopRotatePass(), EnableMSSALoopDependency, DebugLogging));
+ LoopRotatePass(), EnableMSSALoopDependency,
+ /*UseBlockFrequencyInfo=*/false, DebugLogging));
// Distribute loops to allow partial vectorization. I.e. isolate dependences
// into separate loop that would otherwise inhibit vectorization. This is
@@ -1196,7 +1202,7 @@
OptimizePM.addPass(RequireAnalysisPass<OptimizationRemarkEmitterAnalysis, Function>());
OptimizePM.addPass(createFunctionToLoopPassAdaptor(
LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap),
- EnableMSSALoopDependency, DebugLogging));
+ EnableMSSALoopDependency, /*UseBlockFrequencyInfo=*/true, DebugLogging));
// Now that we've vectorized and unrolled loops, we may have more refined
// alignment information, try to re-derive it here.
@@ -2261,8 +2267,9 @@
}
#define LOOP_PASS(NAME, CREATE_PASS) \
if (Name == NAME) { \
- MPM.addPass(createModuleToFunctionPassAdaptor( \
- createFunctionToLoopPassAdaptor(CREATE_PASS, false, DebugLogging))); \
+ MPM.addPass( \
+ createModuleToFunctionPassAdaptor(createFunctionToLoopPassAdaptor( \
+ CREATE_PASS, false, false, DebugLogging))); \
return Error::success(); \
}
#define LOOP_PASS_WITH_PARAMS(NAME, CREATE_PASS, PARSER) \
@@ -2272,7 +2279,7 @@
return Params.takeError(); \
MPM.addPass( \
createModuleToFunctionPassAdaptor(createFunctionToLoopPassAdaptor( \
- CREATE_PASS(Params.get()), false, DebugLogging))); \
+ CREATE_PASS(Params.get()), false, false, DebugLogging))); \
return Error::success(); \
}
#include "PassRegistry.def"
@@ -2373,8 +2380,9 @@
}
#define LOOP_PASS(NAME, CREATE_PASS) \
if (Name == NAME) { \
- CGPM.addPass(createCGSCCToFunctionPassAdaptor( \
- createFunctionToLoopPassAdaptor(CREATE_PASS, false, DebugLogging))); \
+ CGPM.addPass( \
+ createCGSCCToFunctionPassAdaptor(createFunctionToLoopPassAdaptor( \
+ CREATE_PASS, false, false, DebugLogging))); \
return Error::success(); \
}
#define LOOP_PASS_WITH_PARAMS(NAME, CREATE_PASS, PARSER) \
@@ -2384,7 +2392,7 @@
return Params.takeError(); \
CGPM.addPass( \
createCGSCCToFunctionPassAdaptor(createFunctionToLoopPassAdaptor( \
- CREATE_PASS(Params.get()), false, DebugLogging))); \
+ CREATE_PASS(Params.get()), false, false, DebugLogging))); \
return Error::success(); \
}
#include "PassRegistry.def"
@@ -2421,8 +2429,9 @@
return Err;
// Add the nested pass manager with the appropriate adaptor.
bool UseMemorySSA = (Name == "loop-mssa");
- FPM.addPass(createFunctionToLoopPassAdaptor(std::move(LPM), UseMemorySSA,
- DebugLogging));
+ FPM.addPass(createFunctionToLoopPassAdaptor(
+ std::move(LPM), UseMemorySSA, /*UseBlockFrequencyInfo=*/false,
+ DebugLogging));
return Error::success();
}
if (auto Count = parseRepeatPassName(Name)) {
@@ -2476,8 +2485,8 @@
// The risk is that it may become obsolete if we're not careful.
#define LOOP_PASS(NAME, CREATE_PASS) \
if (Name == NAME) { \
- FPM.addPass( \
- createFunctionToLoopPassAdaptor(CREATE_PASS, false, DebugLogging)); \
+ FPM.addPass(createFunctionToLoopPassAdaptor(CREATE_PASS, false, false, \
+ DebugLogging)); \
return Error::success(); \
}
#define LOOP_PASS_WITH_PARAMS(NAME, CREATE_PASS, PARSER) \
@@ -2486,7 +2495,7 @@
if (!Params) \
return Params.takeError(); \
FPM.addPass(createFunctionToLoopPassAdaptor(CREATE_PASS(Params.get()), \
- false, DebugLogging)); \
+ false, false, DebugLogging)); \
return Error::success(); \
}
#include "PassRegistry.def"
Index: llvm/include/llvm/Transforms/Scalar/LoopPassManager.h
===================================================================
--- llvm/include/llvm/Transforms/Scalar/LoopPassManager.h
+++ llvm/include/llvm/Transforms/Scalar/LoopPassManager.h
@@ -41,6 +41,7 @@
#include "llvm/ADT/STLExtras.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/BasicAliasAnalysis.h"
+#include "llvm/Analysis/BlockFrequencyInfo.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/LoopAnalysisManager.h"
#include "llvm/Analysis/LoopInfo.h"
@@ -233,9 +234,11 @@
: public PassInfoMixin<FunctionToLoopPassAdaptor<LoopPassT>> {
public:
explicit FunctionToLoopPassAdaptor(LoopPassT Pass, bool UseMemorySSA = false,
+ bool UseBlockFrequencyInfo = false,
bool DebugLogging = false)
: Pass(std::move(Pass)), LoopCanonicalizationFPM(DebugLogging),
- UseMemorySSA(UseMemorySSA) {
+ UseMemorySSA(UseMemorySSA),
+ UseBlockFrequencyInfo(UseBlockFrequencyInfo) {
LoopCanonicalizationFPM.addPass(LoopSimplifyPass());
LoopCanonicalizationFPM.addPass(LCSSAPass());
}
@@ -267,6 +270,9 @@
MemorySSA *MSSA = UseMemorySSA
? (&AM.getResult<MemorySSAAnalysis>(F).getMSSA())
: nullptr;
+ BlockFrequencyInfo *BFI = UseBlockFrequencyInfo && F.hasProfileData()
+ ? (&AM.getResult<BlockFrequencyAnalysis>(F))
+ : nullptr;
LoopStandardAnalysisResults LAR = {AM.getResult<AAManager>(F),
AM.getResult<AssumptionAnalysis>(F),
AM.getResult<DominatorTreeAnalysis>(F),
@@ -274,6 +280,7 @@
AM.getResult<ScalarEvolutionAnalysis>(F),
AM.getResult<TargetLibraryAnalysis>(F),
AM.getResult<TargetIRAnalysis>(F),
+ BFI,
MSSA};
// Setup the loop analysis manager from its proxy. It is important that
@@ -370,6 +377,8 @@
PA.preserve<DominatorTreeAnalysis>();
PA.preserve<LoopAnalysis>();
PA.preserve<ScalarEvolutionAnalysis>();
+ if (UseBlockFrequencyInfo && F.hasProfileData())
+ PA.preserve<BlockFrequencyAnalysis>();
if (UseMemorySSA)
PA.preserve<MemorySSAAnalysis>();
// FIXME: What we really want to do here is preserve an AA category, but
@@ -389,6 +398,7 @@
FunctionPassManager LoopCanonicalizationFPM;
bool UseMemorySSA = false;
+ bool UseBlockFrequencyInfo = false;
};
/// A function to deduce a loop pass type and wrap it in the templated
@@ -396,9 +406,10 @@
template <typename LoopPassT>
FunctionToLoopPassAdaptor<LoopPassT>
createFunctionToLoopPassAdaptor(LoopPassT Pass, bool UseMemorySSA = false,
+ bool UseBlockFrequencyInfo = false,
bool DebugLogging = false) {
- return FunctionToLoopPassAdaptor<LoopPassT>(std::move(Pass), UseMemorySSA,
- DebugLogging);
+ return FunctionToLoopPassAdaptor<LoopPassT>(
+ std::move(Pass), UseMemorySSA, UseBlockFrequencyInfo, DebugLogging);
}
/// Pass for printing a loop's contents as textual IR.
Index: llvm/include/llvm/Analysis/LoopAnalysisManager.h
===================================================================
--- llvm/include/llvm/Analysis/LoopAnalysisManager.h
+++ llvm/include/llvm/Analysis/LoopAnalysisManager.h
@@ -57,6 +57,7 @@
ScalarEvolution &SE;
TargetLibraryInfo &TLI;
TargetTransformInfo &TTI;
+ BlockFrequencyInfo *BFI;
MemorySSA *MSSA;
};
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
