[polly] df89564 - [SimpleLoopUnswitch] Don't use BlockFrequencyInfo to skip cold loops (#159522)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Oct 17 16:33:53 PDT 2025
Author: Luke Lau
Date: 2025-10-17T23:33:49Z
New Revision: df8956442feda0171fda79393778f698eb0385cf
URL: https://github.com/llvm/llvm-project/commit/df8956442feda0171fda79393778f698eb0385cf
DIFF: https://github.com/llvm/llvm-project/commit/df8956442feda0171fda79393778f698eb0385cf.diff
LOG: [SimpleLoopUnswitch] Don't use BlockFrequencyInfo to skip cold loops (#159522)
In https://reviews.llvm.org/D129599, non-trivial switching was disabled
for cold loops in the interest of code size. This added a dependency on
BlockFrequencyInfo with PGO, but in loop passes this is only available
on a lossy basis: see https://reviews.llvm.org/D86156
LICM moved away from BFI so as of today SimpleLoopUnswitch is the only
remaining loop pass that uses BFI, for the sole reason to prevent code
size increases in PGO builds. It doesn't use BFI if there's no profile
summary available.
After some investigation on llvm-test-suite it turns out that the lossy
BFI causes very significant deviations in block frequency, since when
new loops are deleted/created during the loop pass manager it can return
frequencies for different loops altogether.
This results in unswitchable loops being mistakenly skipped because they
are thought to be cold.
This patch removes the use of BFI from SimpleLoopUnswitch and thus the
last remaining use of BFI in a loop pass.
To recover the original intent of not unswitching cold code,
PGOForceFunctionAttrs can be used to annotate functions which can be
optimized for code size, since SimpleLoopUnswitch will respect OptSize:
https://reviews.llvm.org/D94559
This isn't 100% the same behaviour since the previous behaviour checked
for coldness at the loop level and this is now at the function level. We
could expand PGOForceFunctionAttrs to be more granular at the loop
level, https://github.com/llvm/llvm-project/issues/159595 tracks this
idea.
Added:
llvm/test/Transforms/PhaseOrdering/unswitch-cold-func.ll
Modified:
llvm/include/llvm/Analysis/LoopAnalysisManager.h
llvm/include/llvm/Transforms/Scalar/LoopPassManager.h
llvm/lib/Passes/PassBuilder.cpp
llvm/lib/Passes/PassBuilderPipelines.cpp
llvm/lib/Transforms/Scalar/LoopPassManager.cpp
llvm/lib/Transforms/Scalar/SimpleLoopUnswitch.cpp
llvm/test/Other/loop-pm-invalidation.ll
llvm/test/Other/new-pm-defaults.ll
llvm/test/Other/new-pm-thinlto-postlink-defaults.ll
llvm/test/Other/new-pm-thinlto-postlink-pgo-defaults.ll
llvm/test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll
llvm/test/Other/new-pm-thinlto-prelink-defaults.ll
llvm/test/Other/new-pm-thinlto-prelink-pgo-defaults.ll
llvm/test/Other/new-pm-thinlto-prelink-samplepgo-defaults.ll
llvm/test/Transforms/SimpleLoopUnswitch/nontrivial-unswitch-markloopasdeleted.ll
polly/lib/Transform/Canonicalization.cpp
Removed:
llvm/test/Transforms/LoopPredication/preserve-bpi.ll
llvm/test/Transforms/SimpleLoopUnswitch/PGO-nontrivial-unswitch.ll
################################################################################
diff --git a/llvm/include/llvm/Analysis/LoopAnalysisManager.h b/llvm/include/llvm/Analysis/LoopAnalysisManager.h
index fc69cb03849c6..1755257fe6c89 100644
--- a/llvm/include/llvm/Analysis/LoopAnalysisManager.h
+++ b/llvm/include/llvm/Analysis/LoopAnalysisManager.h
@@ -36,7 +36,6 @@ namespace llvm {
class AAResults;
class AssumptionCache;
-class BlockFrequencyInfo;
class DominatorTree;
class Function;
class Loop;
@@ -58,7 +57,6 @@ struct LoopStandardAnalysisResults {
ScalarEvolution &SE;
TargetLibraryInfo &TLI;
TargetTransformInfo &TTI;
- BlockFrequencyInfo *BFI;
MemorySSA *MSSA;
};
diff --git a/llvm/include/llvm/Transforms/Scalar/LoopPassManager.h b/llvm/include/llvm/Transforms/Scalar/LoopPassManager.h
index 750f9546625a2..1842d2dc5f05a 100644
--- a/llvm/include/llvm/Transforms/Scalar/LoopPassManager.h
+++ b/llvm/include/llvm/Transforms/Scalar/LoopPassManager.h
@@ -404,10 +404,8 @@ class FunctionToLoopPassAdaptor
explicit FunctionToLoopPassAdaptor(std::unique_ptr<PassConceptT> Pass,
bool UseMemorySSA = false,
- bool UseBlockFrequencyInfo = false,
bool LoopNestMode = false)
: Pass(std::move(Pass)), UseMemorySSA(UseMemorySSA),
- UseBlockFrequencyInfo(UseBlockFrequencyInfo),
LoopNestMode(LoopNestMode) {
LoopCanonicalizationFPM.addPass(LoopSimplifyPass());
LoopCanonicalizationFPM.addPass(LCSSAPass());
@@ -429,7 +427,6 @@ class FunctionToLoopPassAdaptor
FunctionPassManager LoopCanonicalizationFPM;
bool UseMemorySSA = false;
- bool UseBlockFrequencyInfo = false;
const bool LoopNestMode;
};
@@ -442,8 +439,7 @@ class FunctionToLoopPassAdaptor
/// \c LoopPassManager and the returned adaptor will be in loop-nest mode.
template <typename LoopPassT>
inline FunctionToLoopPassAdaptor
-createFunctionToLoopPassAdaptor(LoopPassT &&Pass, bool UseMemorySSA = false,
- bool UseBlockFrequencyInfo = false) {
+createFunctionToLoopPassAdaptor(LoopPassT &&Pass, bool UseMemorySSA = false) {
if constexpr (is_detected<HasRunOnLoopT, LoopPassT>::value) {
using PassModelT =
detail::PassModel<Loop, LoopPassT, LoopAnalysisManager,
@@ -453,7 +449,7 @@ createFunctionToLoopPassAdaptor(LoopPassT &&Pass, bool UseMemorySSA = false,
return FunctionToLoopPassAdaptor(
std::unique_ptr<FunctionToLoopPassAdaptor::PassConceptT>(
new PassModelT(std::forward<LoopPassT>(Pass))),
- UseMemorySSA, UseBlockFrequencyInfo, false);
+ UseMemorySSA, false);
} else {
LoopPassManager LPM;
LPM.addPass(std::forward<LoopPassT>(Pass));
@@ -465,7 +461,7 @@ createFunctionToLoopPassAdaptor(LoopPassT &&Pass, bool UseMemorySSA = false,
return FunctionToLoopPassAdaptor(
std::unique_ptr<FunctionToLoopPassAdaptor::PassConceptT>(
new PassModelT(std::move(LPM))),
- UseMemorySSA, UseBlockFrequencyInfo, true);
+ UseMemorySSA, true);
}
}
@@ -474,8 +470,7 @@ createFunctionToLoopPassAdaptor(LoopPassT &&Pass, bool UseMemorySSA = false,
template <>
inline FunctionToLoopPassAdaptor
createFunctionToLoopPassAdaptor<LoopPassManager>(LoopPassManager &&LPM,
- bool UseMemorySSA,
- bool UseBlockFrequencyInfo) {
+ bool UseMemorySSA) {
// Check if LPM contains any loop pass and if it does not, returns an adaptor
// in loop-nest mode.
using PassModelT =
@@ -487,7 +482,7 @@ createFunctionToLoopPassAdaptor<LoopPassManager>(LoopPassManager &&LPM,
return FunctionToLoopPassAdaptor(
std::unique_ptr<FunctionToLoopPassAdaptor::PassConceptT>(
new PassModelT(std::move(LPM))),
- UseMemorySSA, UseBlockFrequencyInfo, LoopNestMode);
+ UseMemorySSA, LoopNestMode);
}
/// Pass for printing a loop's contents as textual IR.
diff --git a/llvm/lib/Passes/PassBuilder.cpp b/llvm/lib/Passes/PassBuilder.cpp
index 53cf0046bd858..e45cac848d0a2 100644
--- a/llvm/lib/Passes/PassBuilder.cpp
+++ b/llvm/lib/Passes/PassBuilder.cpp
@@ -2027,13 +2027,13 @@ Error PassBuilder::parseModulePass(ModulePassManager &MPM,
#define LOOPNEST_PASS(NAME, CREATE_PASS) \
if (Name == NAME) { \
MPM.addPass(createModuleToFunctionPassAdaptor( \
- createFunctionToLoopPassAdaptor(CREATE_PASS, false, false))); \
+ createFunctionToLoopPassAdaptor(CREATE_PASS, false))); \
return Error::success(); \
}
#define LOOP_PASS(NAME, CREATE_PASS) \
if (Name == NAME) { \
MPM.addPass(createModuleToFunctionPassAdaptor( \
- createFunctionToLoopPassAdaptor(CREATE_PASS, false, false))); \
+ createFunctionToLoopPassAdaptor(CREATE_PASS, false))); \
return Error::success(); \
}
#define LOOP_PASS_WITH_PARAMS(NAME, CLASS, CREATE_PASS, PARSER, PARAMS) \
@@ -2041,9 +2041,8 @@ Error PassBuilder::parseModulePass(ModulePassManager &MPM,
auto Params = parsePassParameters(PARSER, Name, NAME); \
if (!Params) \
return Params.takeError(); \
- MPM.addPass( \
- createModuleToFunctionPassAdaptor(createFunctionToLoopPassAdaptor( \
- CREATE_PASS(Params.get()), false, false))); \
+ MPM.addPass(createModuleToFunctionPassAdaptor( \
+ createFunctionToLoopPassAdaptor(CREATE_PASS(Params.get()), false))); \
return Error::success(); \
}
#include "PassRegistry.def"
@@ -2142,13 +2141,13 @@ Error PassBuilder::parseCGSCCPass(CGSCCPassManager &CGPM,
#define LOOPNEST_PASS(NAME, CREATE_PASS) \
if (Name == NAME) { \
CGPM.addPass(createCGSCCToFunctionPassAdaptor( \
- createFunctionToLoopPassAdaptor(CREATE_PASS, false, false))); \
+ createFunctionToLoopPassAdaptor(CREATE_PASS, false))); \
return Error::success(); \
}
#define LOOP_PASS(NAME, CREATE_PASS) \
if (Name == NAME) { \
CGPM.addPass(createCGSCCToFunctionPassAdaptor( \
- createFunctionToLoopPassAdaptor(CREATE_PASS, false, false))); \
+ createFunctionToLoopPassAdaptor(CREATE_PASS, false))); \
return Error::success(); \
}
#define LOOP_PASS_WITH_PARAMS(NAME, CLASS, CREATE_PASS, PARSER, PARAMS) \
@@ -2156,9 +2155,8 @@ Error PassBuilder::parseCGSCCPass(CGSCCPassManager &CGPM,
auto Params = parsePassParameters(PARSER, Name, NAME); \
if (!Params) \
return Params.takeError(); \
- CGPM.addPass( \
- createCGSCCToFunctionPassAdaptor(createFunctionToLoopPassAdaptor( \
- CREATE_PASS(Params.get()), false, false))); \
+ CGPM.addPass(createCGSCCToFunctionPassAdaptor( \
+ createFunctionToLoopPassAdaptor(CREATE_PASS(Params.get()), false))); \
return Error::success(); \
}
#include "PassRegistry.def"
@@ -2191,11 +2189,8 @@ Error PassBuilder::parseFunctionPass(FunctionPassManager &FPM,
return Err;
// Add the nested pass manager with the appropriate adaptor.
bool UseMemorySSA = (Name == "loop-mssa");
- bool UseBFI = llvm::any_of(InnerPipeline, [](auto Pipeline) {
- return Pipeline.Name.contains("simple-loop-unswitch");
- });
- FPM.addPass(createFunctionToLoopPassAdaptor(std::move(LPM), UseMemorySSA,
- UseBFI));
+ FPM.addPass(
+ createFunctionToLoopPassAdaptor(std::move(LPM), UseMemorySSA));
return Error::success();
}
if (Name == "machine-function") {
@@ -2248,12 +2243,12 @@ Error PassBuilder::parseFunctionPass(FunctionPassManager &FPM,
// The risk is that it may become obsolete if we're not careful.
#define LOOPNEST_PASS(NAME, CREATE_PASS) \
if (Name == NAME) { \
- FPM.addPass(createFunctionToLoopPassAdaptor(CREATE_PASS, false, false)); \
+ FPM.addPass(createFunctionToLoopPassAdaptor(CREATE_PASS, false)); \
return Error::success(); \
}
#define LOOP_PASS(NAME, CREATE_PASS) \
if (Name == NAME) { \
- FPM.addPass(createFunctionToLoopPassAdaptor(CREATE_PASS, false, false)); \
+ FPM.addPass(createFunctionToLoopPassAdaptor(CREATE_PASS, false)); \
return Error::success(); \
}
#define LOOP_PASS_WITH_PARAMS(NAME, CLASS, CREATE_PASS, PARSER, PARAMS) \
@@ -2261,8 +2256,8 @@ Error PassBuilder::parseFunctionPass(FunctionPassManager &FPM,
auto Params = parsePassParameters(PARSER, Name, NAME); \
if (!Params) \
return Params.takeError(); \
- FPM.addPass(createFunctionToLoopPassAdaptor(CREATE_PASS(Params.get()), \
- false, false)); \
+ FPM.addPass( \
+ createFunctionToLoopPassAdaptor(CREATE_PASS(Params.get()), false)); \
return Error::success(); \
}
#include "PassRegistry.def"
diff --git a/llvm/lib/Passes/PassBuilderPipelines.cpp b/llvm/lib/Passes/PassBuilderPipelines.cpp
index 3f3939eaf0eb0..bd03ac090721c 100644
--- a/llvm/lib/Passes/PassBuilderPipelines.cpp
+++ b/llvm/lib/Passes/PassBuilderPipelines.cpp
@@ -519,16 +519,14 @@ PassBuilder::buildO1FunctionSimplificationPipeline(OptimizationLevel Level,
invokeLoopOptimizerEndEPCallbacks(LPM2, Level);
FPM.addPass(createFunctionToLoopPassAdaptor(std::move(LPM1),
- /*UseMemorySSA=*/true,
- /*UseBlockFrequencyInfo=*/true));
+ /*UseMemorySSA=*/true));
FPM.addPass(
SimplifyCFGPass(SimplifyCFGOptions().convertSwitchRangeToICmp(true)));
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,
- /*UseBlockFrequencyInfo=*/false));
+ /*UseMemorySSA=*/false));
// Delete small array after loop unroll.
FPM.addPass(SROAPass(SROAOptions::ModifyCFG));
@@ -710,8 +708,7 @@ PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
invokeLoopOptimizerEndEPCallbacks(LPM2, Level);
FPM.addPass(createFunctionToLoopPassAdaptor(std::move(LPM1),
- /*UseMemorySSA=*/true,
- /*UseBlockFrequencyInfo=*/true));
+ /*UseMemorySSA=*/true));
FPM.addPass(
SimplifyCFGPass(SimplifyCFGOptions().convertSwitchRangeToICmp(true)));
FPM.addPass(InstCombinePass());
@@ -719,8 +716,7 @@ PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
// 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,
- /*UseBlockFrequencyInfo=*/false));
+ /*UseMemorySSA=*/false));
// Delete small array after loop unroll.
FPM.addPass(SROAPass(SROAOptions::ModifyCFG));
@@ -773,7 +769,7 @@ PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
FPM.addPass(createFunctionToLoopPassAdaptor(
LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap,
/*AllowSpeculation=*/true),
- /*UseMemorySSA=*/true, /*UseBlockFrequencyInfo=*/false));
+ /*UseMemorySSA=*/true));
FPM.addPass(CoroElidePass());
@@ -842,8 +838,7 @@ void PassBuilder::addPostPGOLoopRotation(ModulePassManager &MPM,
createFunctionToLoopPassAdaptor(
LoopRotatePass(EnableLoopHeaderDuplication ||
Level != OptimizationLevel::Oz),
- /*UseMemorySSA=*/false,
- /*UseBlockFrequencyInfo=*/false),
+ /*UseMemorySSA=*/false),
PTO.EagerlyInvalidateAnalyses));
}
}
@@ -1358,8 +1353,7 @@ void PassBuilder::addVectorPasses(OptimizationLevel Level,
LPM.addPass(SimpleLoopUnswitchPass(/* NonTrivial */ Level ==
OptimizationLevel::O3));
ExtraPasses.addPass(
- createFunctionToLoopPassAdaptor(std::move(LPM), /*UseMemorySSA=*/true,
- /*UseBlockFrequencyInfo=*/true));
+ createFunctionToLoopPassAdaptor(std::move(LPM), /*UseMemorySSA=*/true));
ExtraPasses.addPass(
SimplifyCFGPass(SimplifyCFGOptions().convertSwitchRangeToICmp(true)));
ExtraPasses.addPass(InstCombinePass());
@@ -1438,7 +1432,7 @@ void PassBuilder::addVectorPasses(OptimizationLevel Level,
FPM.addPass(createFunctionToLoopPassAdaptor(
LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap,
/*AllowSpeculation=*/true),
- /*UseMemorySSA=*/true, /*UseBlockFrequencyInfo=*/false));
+ /*UseMemorySSA=*/true));
// Now that we've vectorized and unrolled loops, we may have more refined
// alignment information, try to re-derive it here.
@@ -1520,7 +1514,7 @@ PassBuilder::buildModuleOptimizationPipeline(OptimizationLevel Level,
OptimizePM.addPass(createFunctionToLoopPassAdaptor(
LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap,
/*AllowSpeculation=*/true),
- /*USeMemorySSA=*/true, /*UseBlockFrequencyInfo=*/false));
+ /*USeMemorySSA=*/true));
}
OptimizePM.addPass(Float2IntPass());
@@ -1560,8 +1554,8 @@ PassBuilder::buildModuleOptimizationPipeline(OptimizationLevel Level,
if (PTO.LoopInterchange)
LPM.addPass(LoopInterchangePass());
- OptimizePM.addPass(createFunctionToLoopPassAdaptor(
- std::move(LPM), /*UseMemorySSA=*/false, /*UseBlockFrequencyInfo=*/false));
+ OptimizePM.addPass(
+ createFunctionToLoopPassAdaptor(std::move(LPM), /*UseMemorySSA=*/false));
// FIXME: This may not be the right place in the pipeline.
// We need to have the data to support the right place.
@@ -2133,7 +2127,7 @@ PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level,
MainFPM.addPass(createFunctionToLoopPassAdaptor(
LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap,
/*AllowSpeculation=*/true),
- /*USeMemorySSA=*/true, /*UseBlockFrequencyInfo=*/false));
+ /*USeMemorySSA=*/true));
if (RunNewGVN)
MainFPM.addPass(NewGVNPass());
@@ -2163,8 +2157,8 @@ PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level,
PTO.ForgetAllSCEVInLoopUnroll));
// The loop passes in LPM (LoopFullUnrollPass) do not preserve MemorySSA.
// *All* loop passes must preserve it, in order to be able to use it.
- MainFPM.addPass(createFunctionToLoopPassAdaptor(
- std::move(LPM), /*UseMemorySSA=*/false, /*UseBlockFrequencyInfo=*/true));
+ MainFPM.addPass(
+ createFunctionToLoopPassAdaptor(std::move(LPM), /*UseMemorySSA=*/false));
MainFPM.addPass(LoopDistributePass());
diff --git a/llvm/lib/Transforms/Scalar/LoopPassManager.cpp b/llvm/lib/Transforms/Scalar/LoopPassManager.cpp
index 7da85868588b1..d827e649d0842 100644
--- a/llvm/lib/Transforms/Scalar/LoopPassManager.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopPassManager.cpp
@@ -8,7 +8,6 @@
#include "llvm/Transforms/Scalar/LoopPassManager.h"
#include "llvm/Analysis/AssumptionCache.h"
-#include "llvm/Analysis/BlockFrequencyInfo.h"
#include "llvm/Analysis/MemorySSA.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
@@ -217,9 +216,6 @@ PreservedAnalyses FunctionToLoopPassAdaptor::run(Function &F,
// Get the analysis results needed by loop passes.
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),
@@ -227,7 +223,6 @@ PreservedAnalyses FunctionToLoopPassAdaptor::run(Function &F,
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
diff --git a/llvm/lib/Transforms/Scalar/SimpleLoopUnswitch.cpp b/llvm/lib/Transforms/Scalar/SimpleLoopUnswitch.cpp
index e4ba70d1bce16..5af6c96c56a06 100644
--- a/llvm/lib/Transforms/Scalar/SimpleLoopUnswitch.cpp
+++ b/llvm/lib/Transforms/Scalar/SimpleLoopUnswitch.cpp
@@ -27,7 +27,6 @@
#include "llvm/Analysis/MemorySSA.h"
#include "llvm/Analysis/MemorySSAUpdater.h"
#include "llvm/Analysis/MustExecute.h"
-#include "llvm/Analysis/ProfileSummaryInfo.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Analysis/ValueTracking.h"
@@ -3611,8 +3610,7 @@ static bool unswitchLoop(Loop &L, DominatorTree &DT, LoopInfo &LI,
AssumptionCache &AC, AAResults &AA,
TargetTransformInfo &TTI, bool Trivial,
bool NonTrivial, ScalarEvolution *SE,
- MemorySSAUpdater *MSSAU, ProfileSummaryInfo *PSI,
- BlockFrequencyInfo *BFI, LPMUpdater &LoopUpdater) {
+ MemorySSAUpdater *MSSAU, LPMUpdater &LoopUpdater) {
assert(L.isRecursivelyLCSSAForm(DT, LI) &&
"Loops must be in LCSSA form before unswitching.");
@@ -3652,35 +3650,6 @@ static bool unswitchLoop(Loop &L, DominatorTree &DT, LoopInfo &LI,
if (F->hasOptSize())
return false;
- // Returns true if Loop L's loop nest is cold, i.e. if the headers of L,
- // of the loops L is nested in, and of the loops nested in L are all cold.
- auto IsLoopNestCold = [&](const Loop *L) {
- // Check L and all of its parent loops.
- auto *Parent = L;
- while (Parent) {
- if (!PSI->isColdBlock(Parent->getHeader(), BFI))
- return false;
- Parent = Parent->getParentLoop();
- }
- // Next check all loops nested within L.
- SmallVector<const Loop *, 4> Worklist;
- llvm::append_range(Worklist, L->getSubLoops());
- while (!Worklist.empty()) {
- auto *CurLoop = Worklist.pop_back_val();
- if (!PSI->isColdBlock(CurLoop->getHeader(), BFI))
- return false;
- llvm::append_range(Worklist, CurLoop->getSubLoops());
- }
- return true;
- };
-
- // Skip cold loops in cold loop nests, as unswitching them brings little
- // benefit but increases the code size
- if (PSI && PSI->hasProfileSummary() && BFI && IsLoopNestCold(&L)) {
- LLVM_DEBUG(dbgs() << " Skip cold loop: " << L << "\n");
- return false;
- }
-
// Perform legality checks.
if (!isSafeForNoNTrivialUnswitching(L, LI))
return false;
@@ -3705,11 +3674,6 @@ PreservedAnalyses SimpleLoopUnswitchPass::run(Loop &L, LoopAnalysisManager &AM,
LPMUpdater &U) {
Function &F = *L.getHeader()->getParent();
(void)F;
- ProfileSummaryInfo *PSI = nullptr;
- if (auto OuterProxy =
- AM.getResult<FunctionAnalysisManagerLoopProxy>(L, AR)
- .getCachedResult<ModuleAnalysisManagerFunctionProxy>(F))
- PSI = OuterProxy->getCachedResult<ProfileSummaryAnalysis>(*F.getParent());
LLVM_DEBUG(dbgs() << "Unswitching loop in " << F.getName() << ": " << L
<< "\n");
@@ -3720,7 +3684,7 @@ PreservedAnalyses SimpleLoopUnswitchPass::run(Loop &L, LoopAnalysisManager &AM,
AR.MSSA->verifyMemorySSA();
}
if (!unswitchLoop(L, AR.DT, AR.LI, AR.AC, AR.AA, AR.TTI, Trivial, NonTrivial,
- &AR.SE, MSSAU ? &*MSSAU : nullptr, PSI, AR.BFI, U))
+ &AR.SE, MSSAU ? &*MSSAU : nullptr, U))
return PreservedAnalyses::all();
if (AR.MSSA && VerifyMemorySSA)
diff --git a/llvm/test/Other/loop-pm-invalidation.ll b/llvm/test/Other/loop-pm-invalidation.ll
index 4bead0b734eae..25552f7f139fd 100644
--- a/llvm/test/Other/loop-pm-invalidation.ll
+++ b/llvm/test/Other/loop-pm-invalidation.ll
@@ -16,11 +16,6 @@
; RUN: opt -disable-output -disable-verify -verify-analysis-invalidation=0 -debug-pass-manager %s -aa-pipeline= 2>&1 \
; RUN: -passes='loop(no-op-loop,loop-deletion),invalidate<scalar-evolution>,loop(no-op-loop)' \
; RUN: | FileCheck %s --check-prefix=CHECK-SCEV-INV-AFTER-DELETE
-;
-; Test that BFI is invalidated after the loop adapter if any of the loop passes
-; invalidated it.
-; RUN: opt -disable-output -disable-verify -verify-analysis-invalidation=0 -debug-pass-manager %s -aa-pipeline= 2>&1 \
-; RUN: -O1 | FileCheck %s --check-prefix=CHECK-BFI-INV
define void @no_loops() {
; CHECK-LOOP-INV: Running pass: LoopSimplifyPass
@@ -247,28 +242,3 @@ l0.header:
exit:
ret void
}
-
-; CHECK-BFI-INV-LABEL: Running analysis: OuterAnalysisManagerProxy<{{.*}}> on loop %l0.header in function simplifiable_loop
-; CHECK-BFI-INV-NEXT: Running pass: LoopInstSimplifyPass on loop %l0.header in function simplifiable_loop
-; CHECK-BFI-INV-NEXT: Running pass: LoopSimplifyCFGPass on loop %l0.header in function simplifiable_loop
-; CHECK-BFI-INV-NEXT: Running pass: LICMPass on loop %l0.header in function simplifiable_loop
-; CHECK-BFI-INV-NEXT: Running pass: LoopRotatePass on loop %l0.header in function simplifiable_loop
-; CHECK-BFI-INV-NEXT: Running pass: LICMPass on loop %l0.header in function simplifiable_loop
-; CHECK-BFI-INV-NEXT: Running pass: SimpleLoopUnswitchPass on loop %l0.header in function simplifiable_loop
-; CHECK-BFI-INV-NEXT: Invalidating analysis: PostDominatorTreeAnalysis on simplifiable_loop
-; CHECK-BFI-INV-NEXT: Invalidating analysis: BranchProbabilityAnalysis on simplifiable_loop
-; CHECK-BFI-INV-NEXT: Invalidating analysis: BlockFrequencyAnalysis on simplifiable_loop
-; CHECK-BFI-INV-NEXT: Running pass: SimplifyCFGPass on simplifiable_loop (5 instructions)
-
-define void @simplifiable_loop(i1 %c) !prof !0 {
-entry:
- br label %l0.header
-
-l0.header:
- br label %l0.latch
-
-l0.latch:
- br i1 %c, label %l0.header, label %l0.latch
-}
-
-!0 = !{!"function_entry_count", i64 1}
diff --git a/llvm/test/Other/new-pm-defaults.ll b/llvm/test/Other/new-pm-defaults.ll
index 94e860b8ce304..65b96c8b8ef5d 100644
--- a/llvm/test/Other/new-pm-defaults.ll
+++ b/llvm/test/Other/new-pm-defaults.ll
@@ -186,7 +186,6 @@
; CHECK-O-NEXT: Running pass: LoopRotatePass
; CHECK-O-NEXT: Running pass: LICM
; CHECK-O-NEXT: Running pass: SimpleLoopUnswitchPass
-; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running pass: LoopSimplifyPass
diff --git a/llvm/test/Other/new-pm-thinlto-postlink-defaults.ll b/llvm/test/Other/new-pm-thinlto-postlink-defaults.ll
index a08a140a35166..3a0fffe426da1 100644
--- a/llvm/test/Other/new-pm-thinlto-postlink-defaults.ll
+++ b/llvm/test/Other/new-pm-thinlto-postlink-defaults.ll
@@ -114,7 +114,6 @@
; CHECK-O-NEXT: Running pass: LoopRotatePass
; CHECK-O-NEXT: Running pass: LICM
; CHECK-O-NEXT: Running pass: SimpleLoopUnswitchPass
-; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running pass: LoopSimplifyPass
diff --git a/llvm/test/Other/new-pm-thinlto-postlink-pgo-defaults.ll b/llvm/test/Other/new-pm-thinlto-postlink-pgo-defaults.ll
index d9e2dd37a7985..4623edcaf6656 100644
--- a/llvm/test/Other/new-pm-thinlto-postlink-pgo-defaults.ll
+++ b/llvm/test/Other/new-pm-thinlto-postlink-pgo-defaults.ll
@@ -100,7 +100,6 @@
; CHECK-O-NEXT: Running pass: LoopRotatePass
; CHECK-O-NEXT: Running pass: LICM
; CHECK-O-NEXT: Running pass: SimpleLoopUnswitchPass
-; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running pass: LoopSimplifyPass
diff --git a/llvm/test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll b/llvm/test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll
index 2f6fa4b27d354..590afd925e841 100644
--- a/llvm/test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll
+++ b/llvm/test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll
@@ -109,7 +109,6 @@
; CHECK-O-NEXT: Running pass: LoopRotatePass
; CHECK-O-NEXT: Running pass: LICM
; CHECK-O-NEXT: Running pass: SimpleLoopUnswitchPass
-; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running pass: LoopSimplifyPass
diff --git a/llvm/test/Other/new-pm-thinlto-prelink-defaults.ll b/llvm/test/Other/new-pm-thinlto-prelink-defaults.ll
index 5aacd26def2be..dd6acd2c51ee7 100644
--- a/llvm/test/Other/new-pm-thinlto-prelink-defaults.ll
+++ b/llvm/test/Other/new-pm-thinlto-prelink-defaults.ll
@@ -146,7 +146,6 @@
; CHECK-O-NEXT: Running pass: LoopRotatePass
; CHECK-O-NEXT: Running pass: LICM
; CHECK-O-NEXT: Running pass: SimpleLoopUnswitchPass
-; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running pass: LoopSimplifyPass
diff --git a/llvm/test/Other/new-pm-thinlto-prelink-pgo-defaults.ll b/llvm/test/Other/new-pm-thinlto-prelink-pgo-defaults.ll
index f6a9406596803..ee054527e20bd 100644
--- a/llvm/test/Other/new-pm-thinlto-prelink-pgo-defaults.ll
+++ b/llvm/test/Other/new-pm-thinlto-prelink-pgo-defaults.ll
@@ -149,7 +149,6 @@
; CHECK-O-NEXT: Running pass: LoopRotatePass
; CHECK-O-NEXT: Running pass: LICM
; CHECK-O-NEXT: Running pass: SimpleLoopUnswitchPass
-; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running pass: LoopSimplifyPass
diff --git a/llvm/test/Other/new-pm-thinlto-prelink-samplepgo-defaults.ll b/llvm/test/Other/new-pm-thinlto-prelink-samplepgo-defaults.ll
index 48a9433d24999..fd95e94f3c8b9 100644
--- a/llvm/test/Other/new-pm-thinlto-prelink-samplepgo-defaults.ll
+++ b/llvm/test/Other/new-pm-thinlto-prelink-samplepgo-defaults.ll
@@ -114,7 +114,6 @@
; CHECK-O-NEXT: Running pass: LoopRotatePass
; CHECK-O-NEXT: Running pass: LICM
; CHECK-O-NEXT: Running pass: SimpleLoopUnswitchPass
-; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-O-NEXT: Running pass: SimplifyCFGPass
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running pass: LoopSimplifyPass
diff --git a/llvm/test/Transforms/LoopPredication/preserve-bpi.ll b/llvm/test/Transforms/LoopPredication/preserve-bpi.ll
deleted file mode 100644
index 7fbb19783f464..0000000000000
--- a/llvm/test/Transforms/LoopPredication/preserve-bpi.ll
+++ /dev/null
@@ -1,60 +0,0 @@
-; RUN: opt -mtriple=x86_64 -passes='loop-mssa(loop-predication,licm,simple-loop-unswitch<nontrivial>,loop-simplifycfg)' -debug-pass-manager -debug-only=branch-prob -S < %s 2>&1 | FileCheck %s
-
-; REQUIRES: asserts
-
-; This test is to solely check that we do not run BPI every single time loop
-; predication is invoked (since BPI is preserved as part of
-; LoopStandardAnalysisResults).
-declare void @llvm.experimental.guard(i1, ...)
-
-; CHECK: Running pass: LoopPredicationPass on loop
-; CHECK-NEXT: Running pass: LICMPass on loop
-; CHECK-NEXT: Running pass: SimpleLoopUnswitchPass on loop
-; CHECK-NEXT: Running analysis: OuterAnalysisManagerProxy
-; CHECK-NEXT: Running pass: LoopPredicationPass on loop
-; CHECK-NEXT: Running pass: LICMPass on loop
-; CHECK-NEXT: Running pass: SimpleLoopUnswitchPass on loop
-; CHECK-NEXT: Running pass: LoopSimplifyCFGPass on loop
-
-define i32 @unsigned_loop_0_to_n_ult_check(ptr %array, i32 %length, i32 %n) {
-entry:
- %tmp5 = icmp eq i32 %n, 0
- br i1 %tmp5, label %exit, label %loop.preheader
-
-loop.preheader: ; preds = %entry
- br label %loop
-
-loop: ; preds = %guarded, %loop.preheader
- %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
- %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
- %within.bounds = icmp ult i32 %i, %length
- %widenable_cond = call i1 @llvm.experimental.widenable.condition()
- %exiplicit_guard_cond = and i1 %within.bounds, %widenable_cond
- br i1 %exiplicit_guard_cond, label %guarded, label %deopt, !prof !0
-
-deopt: ; preds = %loop
- %deoptcall = call i32 (...) @llvm.experimental.deoptimize.i32(i32 9) [ "deopt"() ]
- ret i32 %deoptcall
-
-guarded: ; preds = %loop
- %i.i64 = zext i32 %i to i64
- %array.i.ptr = getelementptr inbounds i32, ptr %array, i64 %i.i64
- %array.i = load i32, ptr %array.i.ptr, align 4
- %loop.acc.next = add i32 %loop.acc, %array.i
- %i.next = add nuw i32 %i, 1
- %continue = icmp ult i32 %i.next, %n
- br i1 %continue, label %loop, label %exit, !prof !2
-
-exit: ; preds = %guarded, %entry
- %result = phi i32 [ 0, %entry ], [ %loop.acc.next, %guarded ]
- ret i32 %result
-}
-
-declare i32 @llvm.experimental.deoptimize.i32(...)
-declare i1 @llvm.experimental.widenable.condition() #0
-
-attributes #0 = { inaccessiblememonly nounwind }
-
-!0 = !{!"branch_weights", i32 1048576, i32 1}
-!1 = !{i32 1, i32 -2147483648}
-!2 = !{!"branch_weights", i32 1024, i32 1}
diff --git a/llvm/test/Transforms/SimpleLoopUnswitch/PGO-nontrivial-unswitch.ll b/llvm/test/Transforms/PhaseOrdering/unswitch-cold-func.ll
similarity index 89%
rename from llvm/test/Transforms/SimpleLoopUnswitch/PGO-nontrivial-unswitch.ll
rename to llvm/test/Transforms/PhaseOrdering/unswitch-cold-func.ll
index 239397bb652ca..a6ebdf052411d 100644
--- a/llvm/test/Transforms/SimpleLoopUnswitch/PGO-nontrivial-unswitch.ll
+++ b/llvm/test/Transforms/PhaseOrdering/unswitch-cold-func.ll
@@ -1,13 +1,14 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
-; RUN: opt < %s -passes='require<profile-summary>,function(loop-mssa(simple-loop-unswitch<nontrivial>))' -S | FileCheck %s
+; RUN: opt < %s -passes='pgo-force-function-attrs,function(loop-mssa(simple-loop-unswitch<nontrivial>))' -pgo-kind=pgo-instr-use-pipeline -pgo-cold-func-opt=optsize -S | FileCheck %s
+; RUN: opt < %s -passes='pgo-force-function-attrs,function(loop-mssa(simple-loop-unswitch<nontrivial>))' -pgo-kind=pgo-instr-use-pipeline -pgo-cold-func-opt=minsize -S | FileCheck %s
;; Check that non-trivial loop unswitching is not applied to a cold loop in a
;; cold loop nest.
;; IR was generated from the following loop nest, profiled when called
;; with M=0 and N=0.
-;; void hotFunction(bool cond, int M, int N, int * A, int *B, int *C) {
+;; void function(bool cond, int M, int N, int * A, int *B, int *C) {
;; for (unsigned j = 0; j < M; j++)
;; for (unsigned i=0; i < N; i++) {
;; A[i] = B[i] + C[i];
@@ -15,8 +16,8 @@
;; }
;; }
-define void @_Z11hotFunctionbiiPiS_S_(i1 %cond, i32 %M, i32 %N, ptr %A, ptr %B, ptr %C) !prof !36 {
-; CHECK-LABEL: define void @_Z11hotFunctionbiiPiS_S_
+define void @_Z11functionbiiPiS_S_(i1 %cond, i32 %M, i32 %N, ptr %A, ptr %B, ptr %C) !prof !36 {
+; CHECK-LABEL: define void @_Z11functionbiiPiS_S_
; CHECK-SAME: (i1 [[COND:%.*]], i32 [[M:%.*]], i32 [[N:%.*]], ptr [[A:%.*]], ptr [[B:%.*]], ptr [[C:%.*]]) {{.*}}{
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP19_NOT:%.*]] = icmp eq i32 [[M]], 0
diff --git a/llvm/test/Transforms/SimpleLoopUnswitch/nontrivial-unswitch-markloopasdeleted.ll b/llvm/test/Transforms/SimpleLoopUnswitch/nontrivial-unswitch-markloopasdeleted.ll
index 9ab713cc8a4f5..383407b371da0 100644
--- a/llvm/test/Transforms/SimpleLoopUnswitch/nontrivial-unswitch-markloopasdeleted.ll
+++ b/llvm/test/Transforms/SimpleLoopUnswitch/nontrivial-unswitch-markloopasdeleted.ll
@@ -18,7 +18,6 @@
; the analysis caches.
;
; CHECK: Running pass: SimpleLoopUnswitchPass on loop %loop_begin in function test6
-; CHECK-NEXT: Running analysis: OuterAnalysisManagerProxy
; CHECK-NEXT: Clearing all analysis results for: loop_a_inner
diff --git a/polly/lib/Transform/Canonicalization.cpp b/polly/lib/Transform/Canonicalization.cpp
index 748d710dd08c1..1be560e64af40 100644
--- a/polly/lib/Transform/Canonicalization.cpp
+++ b/polly/lib/Transform/Canonicalization.cpp
@@ -104,8 +104,7 @@ polly::buildCanonicalicationPassesForNPM(llvm::ModulePassManager &MPM,
LoopPassManager LPM;
LPM.addPass(LoopRotatePass(Level != OptimizationLevel::Oz));
FPM.addPass(createFunctionToLoopPassAdaptor<LoopPassManager>(
- std::move(LPM), /*UseMemorySSA=*/false,
- /*UseBlockFrequencyInfo=*/false));
+ std::move(LPM), /*UseMemorySSA=*/false));
}
if (PollyInliner) {
MPM.addPass(createModuleToFunctionPassAdaptor(std::move(FPM)));
@@ -121,8 +120,7 @@ polly::buildCanonicalicationPassesForNPM(llvm::ModulePassManager &MPM,
LoopPassManager LPM;
LPM.addPass(IndVarSimplifyPass());
FPM.addPass(createFunctionToLoopPassAdaptor<LoopPassManager>(
- std::move(LPM), /*UseMemorySSA=*/false,
- /*UseBlockFrequencyInfo=*/true));
+ std::move(LPM), /*UseMemorySSA=*/false));
}
return FPM;
More information about the llvm-commits
mailing list