[LoopUnroll] Include hotness of region in opt remark
LoopUnroll is a loop pass, so the analysis of OptimizationRemarkEmitter
is added to the common function analysis passes that loop passes
depend on.
The BFI and indirectly BPI used in this pass is computed lazily so no
overhead should be observed unless -pass-remarks-with-hotness is used.
This is how the patch affects the O3 pipeline:
Dominator Tree Construction
Natural Loop Information
Canonicalize natural loops
Loop-Closed SSA Form Pass
Basic Alias Analysis (stateless AA impl)
Function Alias Analysis Results
Scalar Evolution Analysis
+ Lazy Branch Probability Analysis
+ Lazy Block Frequency Analysis
+ Optimization Remark Emitter
Loop Pass Manager
Rotate Loops
Loop Invariant Code Motion
Unswitch loops
Simplify the CFG
Dominator Tree Construction
Basic Alias Analysis (stateless AA impl)
Function Alias Analysis Results
Combine redundant instructions
Natural Loop Information
Canonicalize natural loops
Loop-Closed SSA Form Pass
Scalar Evolution Analysis
+ Lazy Branch Probability Analysis
+ Lazy Block Frequency Analysis
+ Optimization Remark Emitter
Loop Pass Manager
Induction Variable Simplification
Recognize loop idioms
Delete dead loops
Unroll loops
...
llvm-svn: 277203
diff --git a/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp b/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
index cc4e061..5c95bee 100644
--- a/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
@@ -21,11 +21,11 @@
#include "llvm/Analysis/LoopPass.h"
#include "llvm/Analysis/LoopPassManager.h"
#include "llvm/Analysis/LoopUnrollAnalyzer.h"
+#include "llvm/Analysis/OptimizationDiagnosticInfo.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/ScalarEvolutionExpressions.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/DataLayout.h"
-#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/InstVisitor.h"
#include "llvm/IR/IntrinsicInst.h"
@@ -693,8 +693,10 @@
// Calculates unroll count and writes it to UP.Count.
static bool computeUnrollCount(Loop *L, const TargetTransformInfo &TTI,
DominatorTree &DT, LoopInfo *LI,
- ScalarEvolution *SE, unsigned TripCount,
- unsigned TripMultiple, unsigned LoopSize,
+ ScalarEvolution *SE,
+ OptimizationRemarkEmitter *ORE,
+ unsigned TripCount, unsigned TripMultiple,
+ unsigned LoopSize,
TargetTransformInfo::UnrollingPreferences &UP) {
// BEInsns represents number of instructions optimized when "back edge"
// becomes "fall through" in unrolled loop.
@@ -736,9 +738,6 @@
PragmaEnableUnroll || UserUnrollCount;
uint64_t UnrolledSize;
- DebugLoc LoopLoc = L->getStartLoc();
- Function *F = L->getHeader()->getParent();
- LLVMContext &Ctx = F->getContext();
if (ExplicitUnroll && TripCount != 0) {
// If the loop has an unrolling pragma, we want to be more aggressive with
@@ -813,8 +812,8 @@
}
if (UP.Count < 2) {
if (PragmaEnableUnroll)
- emitOptimizationRemarkMissed(
- Ctx, DEBUG_TYPE, *F, LoopLoc,
+ ORE->emitOptimizationRemarkMissed(
+ DEBUG_TYPE, L,
"Unable to unroll loop as directed by unroll(enable) pragma "
"because unrolled size is too large.");
UP.Count = 0;
@@ -824,8 +823,8 @@
}
if ((PragmaFullUnroll || PragmaEnableUnroll) && TripCount &&
UP.Count != TripCount)
- emitOptimizationRemarkMissed(
- Ctx, DEBUG_TYPE, *F, LoopLoc,
+ ORE->emitOptimizationRemarkMissed(
+ DEBUG_TYPE, L,
"Unable to fully unroll loop as directed by unroll pragma because "
"unrolled size is too large.");
return ExplicitUnroll;
@@ -833,8 +832,8 @@
assert(TripCount == 0 &&
"All cases when TripCount is constant should be covered here.");
if (PragmaFullUnroll)
- emitOptimizationRemarkMissed(
- Ctx, DEBUG_TYPE, *F, LoopLoc,
+ ORE->emitOptimizationRemarkMissed(
+ DEBUG_TYPE, L,
"Unable to fully unroll loop as directed by unroll(full) pragma "
"because loop has a runtime trip count.");
@@ -877,8 +876,8 @@
<< TripMultiple << ". Reducing unroll count from "
<< OrigCount << " to " << UP.Count << ".\n");
if (PragmaCount > 0 && !UP.AllowRemainder)
- emitOptimizationRemarkMissed(
- Ctx, DEBUG_TYPE, *F, LoopLoc,
+ ORE->emitOptimizationRemarkMissed(
+ DEBUG_TYPE, L,
Twine("Unable to unroll loop the number of times directed by "
"unroll_count pragma because remainder loop is restricted "
"(that could architecture specific or because the loop "
@@ -898,7 +897,8 @@
static bool tryToUnrollLoop(Loop *L, DominatorTree &DT, LoopInfo *LI,
ScalarEvolution *SE, const TargetTransformInfo &TTI,
- AssumptionCache &AC, bool PreserveLCSSA,
+ AssumptionCache &AC, OptimizationRemarkEmitter &ORE,
+ bool PreserveLCSSA,
Optional<unsigned> ProvidedCount,
Optional<unsigned> ProvidedThreshold,
Optional<bool> ProvidedAllowPartial,
@@ -963,8 +963,8 @@
if (Convergent)
UP.AllowRemainder = false;
- bool IsCountSetExplicitly = computeUnrollCount(L, TTI, DT, LI, SE, TripCount,
- TripMultiple, LoopSize, UP);
+ bool IsCountSetExplicitly = computeUnrollCount(
+ L, TTI, DT, LI, SE, &ORE, TripCount, TripMultiple, LoopSize, UP);
if (!UP.Count)
return false;
// Unroll factor (Count) must be less or equal to TripCount.
@@ -974,7 +974,7 @@
// Unroll the loop.
if (!UnrollLoop(L, UP.Count, TripCount, UP.Force, UP.Runtime,
UP.AllowExpensiveTripCount, TripMultiple, LI, SE, &DT, &AC,
- PreserveLCSSA))
+ &ORE, PreserveLCSSA))
return false;
// If loop has an unroll count pragma or unrolled by explicitly set count
@@ -1014,11 +1014,12 @@
const TargetTransformInfo &TTI =
getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
+ auto &ORE = getAnalysis<OptimizationRemarkEmitterWrapperPass>().getORE();
bool PreserveLCSSA = mustPreserveAnalysisID(LCSSAID);
- return tryToUnrollLoop(L, DT, LI, SE, TTI, AC, PreserveLCSSA, ProvidedCount,
- ProvidedThreshold, ProvidedAllowPartial,
- ProvidedRuntime);
+ return tryToUnrollLoop(L, DT, LI, SE, TTI, AC, ORE, PreserveLCSSA,
+ ProvidedCount, ProvidedThreshold,
+ ProvidedAllowPartial, ProvidedRuntime);
}
/// This transformation requires natural loop information & requires that
@@ -1068,6 +1069,7 @@
ScalarEvolution *SE = FAM.getCachedResult<ScalarEvolutionAnalysis>(*F);
auto *TTI = FAM.getCachedResult<TargetIRAnalysis>(*F);
auto *AC = FAM.getCachedResult<AssumptionAnalysis>(*F);
+ auto *ORE = FAM.getCachedResult<OptimizationRemarkEmitterAnalysis>(*F);
if (!DT)
report_fatal_error("LoopUnrollPass: DominatorTreeAnalysis not cached at a higher level");
if (!LI)
@@ -1078,9 +1080,12 @@
report_fatal_error("LoopUnrollPass: TargetIRAnalysis not cached at a higher level");
if (!AC)
report_fatal_error("LoopUnrollPass: AssumptionAnalysis not cached at a higher level");
+ if (!ORE)
+ report_fatal_error("LoopUnrollPass: OptimizationRemarkEmitterAnalysis not "
+ "cached at a higher level");
bool Changed = tryToUnrollLoop(
- &L, *DT, LI, SE, *TTI, *AC, /*PreserveLCSSA*/ true, ProvidedCount,
+ &L, *DT, LI, SE, *TTI, *AC, *ORE, /*PreserveLCSSA*/ true, ProvidedCount,
ProvidedThreshold, ProvidedAllowPartial, ProvidedRuntime);
if (!Changed)