[llvm] r346483 - [CallSiteSplitting] Only record conditions up to the IDom(call site).
Florian Hahn via llvm-commits
llvm-commits at lists.llvm.org
Fri Nov 9 02:23:46 PST 2018
Author: fhahn
Date: Fri Nov 9 02:23:46 2018
New Revision: 346483
URL: http://llvm.org/viewvc/llvm-project?rev=346483&view=rev
Log:
[CallSiteSplitting] Only record conditions up to the IDom(call site).
We can stop recording conditions once we reached the immediate dominator
for the block containing the call site. Conditions in predecessors of the
that node will be the same for all paths to the call site and splitting
is not beneficial.
This patch makes CallSiteSplitting dependent on the DT anlysis. because
the immediate dominators seem to be the easiest way of finding the node
to stop at.
I had to update some exiting tests, because they were checking for
conditions that were true/false on all paths to the call site. Those
should now be handled by instcombine/ipsccp.
Reviewers: davide, junbuml
Reviewed By: junbuml
Differential Revision: https://reviews.llvm.org/D44627
Modified:
llvm/trunk/lib/Transforms/Scalar/CallSiteSplitting.cpp
llvm/trunk/test/Other/new-pm-lto-defaults.ll
llvm/trunk/test/Other/opt-O3-pipeline.ll
llvm/trunk/test/Transforms/CallSiteSplitting/callsite-split-or-phi.ll
Modified: llvm/trunk/lib/Transforms/Scalar/CallSiteSplitting.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Scalar/CallSiteSplitting.cpp?rev=346483&r1=346482&r2=346483&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Scalar/CallSiteSplitting.cpp (original)
+++ llvm/trunk/lib/Transforms/Scalar/CallSiteSplitting.cpp Fri Nov 9 02:23:46 2018
@@ -149,14 +149,14 @@ static void recordCondition(CallSite CS,
/// Record ICmp conditions relevant to any argument in CS following Pred's
/// single predecessors. If there are conflicting conditions along a path, like
-/// x == 1 and x == 0, the first condition will be used.
+/// x == 1 and x == 0, the first condition will be used. We stop once we reach
+/// an edge to StopAt.
static void recordConditions(CallSite CS, BasicBlock *Pred,
- ConditionsTy &Conditions) {
- recordCondition(CS, Pred, CS.getInstruction()->getParent(), Conditions);
+ ConditionsTy &Conditions, BasicBlock *StopAt) {
BasicBlock *From = Pred;
BasicBlock *To = Pred;
SmallPtrSet<BasicBlock *, 4> Visited;
- while (!Visited.count(From->getSinglePredecessor()) &&
+ while (To != StopAt && !Visited.count(From->getSinglePredecessor()) &&
(From = From->getSinglePredecessor())) {
recordCondition(CS, From, To, Conditions);
Visited.insert(From);
@@ -302,7 +302,7 @@ static void copyMustTailReturn(BasicBloc
static void splitCallSite(
CallSite CS,
const SmallVectorImpl<std::pair<BasicBlock *, ConditionsTy>> &Preds,
- DominatorTree *DT) {
+ DominatorTree &DT) {
Instruction *Instr = CS.getInstruction();
BasicBlock *TailBB = Instr->getParent();
bool IsMustTailCall = CS.isMustTailCall();
@@ -327,7 +327,7 @@ static void splitCallSite(
BasicBlock *PredBB = Preds[i].first;
BasicBlock *SplitBlock = DuplicateInstructionsInSplitBetween(
TailBB, PredBB, &*std::next(Instr->getIterator()), ValueToValueMaps[i],
- DT);
+ &DT);
assert(SplitBlock && "Unexpected new basic block split.");
Instruction *NewCI =
@@ -438,7 +438,7 @@ static bool isPredicatedOnPHI(CallSite C
return false;
}
-static bool tryToSplitOnPHIPredicatedArgument(CallSite CS, DominatorTree *DT) {
+static bool tryToSplitOnPHIPredicatedArgument(CallSite CS, DominatorTree &DT) {
if (!isPredicatedOnPHI(CS))
return false;
@@ -449,15 +449,25 @@ static bool tryToSplitOnPHIPredicatedArg
return true;
}
-static bool tryToSplitOnPredicatedArgument(CallSite CS, DominatorTree *DT) {
+static bool tryToSplitOnPredicatedArgument(CallSite CS, DominatorTree &DT) {
auto Preds = getTwoPredecessors(CS.getInstruction()->getParent());
if (Preds[0] == Preds[1])
return false;
+ // We can stop recording conditions once we reached the immediate dominator
+ // for the block containing the call site. Conditions in predecessors of the
+ // that node will be the same for all paths to the call site and splitting
+ // is not beneficial.
+ auto *CSDTNode = DT.getNode(CS.getInstruction()->getParent());
+ BasicBlock *StopAt = CSDTNode ? CSDTNode->getIDom()->getBlock() : nullptr;
+
SmallVector<std::pair<BasicBlock *, ConditionsTy>, 2> PredsCS;
for (auto *Pred : make_range(Preds.rbegin(), Preds.rend())) {
ConditionsTy Conditions;
- recordConditions(CS, Pred, Conditions);
+ // Record condition on edge BB(CS) <- Pred
+ recordCondition(CS, Pred, CS.getInstruction()->getParent(), Conditions);
+ // Record conditions followng Pred's single predecessors.
+ recordConditions(CS, Pred, Conditions, StopAt);
PredsCS.push_back({Pred, Conditions});
}
@@ -466,12 +476,24 @@ static bool tryToSplitOnPredicatedArgume
}))
return false;
+ // Record common conditions starting from StopAt. Those conditions hold for
+ // all paths to CS. Adding them gives the inliner a better chance at inlining
+ // CS.
+ ConditionsTy CommonConditions;
+ if (StopAt)
+ recordConditions(CS, StopAt, CommonConditions, nullptr);
+ if (!CommonConditions.empty())
+ for (auto &Pred : PredsCS) {
+ Pred.second.insert(Pred.second.end(), CommonConditions.begin(),
+ CommonConditions.end());
+ }
+
splitCallSite(CS, PredsCS, DT);
return true;
}
static bool tryToSplitCallSite(CallSite CS, TargetTransformInfo &TTI,
- DominatorTree *DT) {
+ DominatorTree &DT) {
if (!CS.arg_size() || !canSplitCallSite(CS, TTI))
return false;
return tryToSplitOnPredicatedArgument(CS, DT) ||
@@ -479,7 +501,7 @@ static bool tryToSplitCallSite(CallSite
}
static bool doCallSiteSplitting(Function &F, TargetLibraryInfo &TLI,
- TargetTransformInfo &TTI, DominatorTree *DT) {
+ TargetTransformInfo &TTI, DominatorTree &DT) {
bool Changed = false;
for (Function::iterator BI = F.begin(), BE = F.end(); BI != BE;) {
BasicBlock &BB = *BI++;
@@ -524,6 +546,7 @@ struct CallSiteSplittingLegacyPass : pub
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<TargetLibraryInfoWrapperPass>();
AU.addRequired<TargetTransformInfoWrapperPass>();
+ AU.addRequired<DominatorTreeWrapperPass>();
AU.addPreserved<DominatorTreeWrapperPass>();
FunctionPass::getAnalysisUsage(AU);
}
@@ -534,9 +557,8 @@ struct CallSiteSplittingLegacyPass : pub
auto &TLI = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
auto &TTI = getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
- auto *DTWP = getAnalysisIfAvailable<DominatorTreeWrapperPass>();
- return doCallSiteSplitting(F, TLI, TTI,
- DTWP ? &DTWP->getDomTree() : nullptr);
+ auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
+ return doCallSiteSplitting(F, TLI, TTI, DT);
}
};
} // namespace
@@ -546,6 +568,7 @@ INITIALIZE_PASS_BEGIN(CallSiteSplittingL
"Call-site splitting", false, false)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_END(CallSiteSplittingLegacyPass, "callsite-splitting",
"Call-site splitting", false, false)
FunctionPass *llvm::createCallSiteSplittingPass() {
@@ -556,7 +579,7 @@ PreservedAnalyses CallSiteSplittingPass:
FunctionAnalysisManager &AM) {
auto &TLI = AM.getResult<TargetLibraryAnalysis>(F);
auto &TTI = AM.getResult<TargetIRAnalysis>(F);
- auto *DT = AM.getCachedResult<DominatorTreeAnalysis>(F);
+ auto &DT = AM.getResult<DominatorTreeAnalysis>(F);
if (!doCallSiteSplitting(F, TLI, TTI, DT))
return PreservedAnalyses::all();
Modified: llvm/trunk/test/Other/new-pm-lto-defaults.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Other/new-pm-lto-defaults.ll?rev=346483&r1=346482&r2=346483&view=diff
==============================================================================
--- llvm/trunk/test/Other/new-pm-lto-defaults.ll (original)
+++ llvm/trunk/test/Other/new-pm-lto-defaults.ll Fri Nov 9 02:23:46 2018
@@ -38,13 +38,13 @@
; CHECK-O2-NEXT: Running pass: CallSiteSplittingPass on foo
; CHECK-O2-NEXT: Running analysis: TargetLibraryAnalysis on foo
; CHECK-O2-NEXT: Running analysis: TargetIRAnalysis on foo
+; CHECK-O2-NEXT: Running analysis: DominatorTreeAnalysis on foo
; CHECK-O2-NEXT: Finished llvm::Function pass manager run.
; CHECK-O2-NEXT: PGOIndirectCallPromotion
; CHECK-O2-NEXT: Running analysis: ProfileSummaryAnalysis
; CHECK-O2-NEXT: Running analysis: OptimizationRemarkEmitterAnalysis
; CHECK-O2-NEXT: Running pass: IPSCCPPass
-; CHECK-O2-DAG: Running analysis: AssumptionAnalysis on foo
-; CHECK-O2-DAG: Running analysis: DominatorTreeAnalysis on foo
+; CHECK-O2-NEXT: Running analysis: AssumptionAnalysis on foo
; CHECK-O2-NEXT: Running pass: CalledValuePropagationPass
; CHECK-O-NEXT: Running pass: ModuleToPostOrderCGSCCPassAdaptor<{{.*}}PostOrderFunctionAttrsPass>
; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy<{{.*}}SCC
Modified: llvm/trunk/test/Other/opt-O3-pipeline.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Other/opt-O3-pipeline.ll?rev=346483&r1=346482&r2=346483&view=diff
==============================================================================
--- llvm/trunk/test/Other/opt-O3-pipeline.ll (original)
+++ llvm/trunk/test/Other/opt-O3-pipeline.ll Fri Nov 9 02:23:46 2018
@@ -28,6 +28,7 @@
; CHECK-NEXT: Force set function attributes
; CHECK-NEXT: Infer set function attributes
; CHECK-NEXT: FunctionPass Manager
+; CHECK-NEXT: Dominator Tree Construction
; CHECK-NEXT: Call-site splitting
; CHECK-NEXT: Interprocedural Sparse Conditional Constant Propagation
; CHECK-NEXT: Unnamed pass: implement Pass::getPassName()
Modified: llvm/trunk/test/Transforms/CallSiteSplitting/callsite-split-or-phi.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/CallSiteSplitting/callsite-split-or-phi.ll?rev=346483&r1=346482&r2=346483&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/CallSiteSplitting/callsite-split-or-phi.ll (original)
+++ llvm/trunk/test/Transforms/CallSiteSplitting/callsite-split-or-phi.ll Fri Nov 9 02:23:46 2018
@@ -123,14 +123,14 @@ End:
;CHECK-LABEL: Header2.split:
;CHECK: %[[CALL1:.*]] = call i32 @callee(i32* nonnull %a, i32 %v, i32 10)
;CHECK-LABEL: TBB.split:
-;CHECK: %[[CALL2:.*]] = call i32 @callee(i32* nonnull %a, i32 %v, i32 %p)
+;CHECK: %[[CALL2:.*]] = call i32 @callee(i32* %a, i32 %v, i32 %p)
;CHECK-LABEL: Tail
;CHECK: %[[MERGED:.*]] = phi i32 [ %[[CALL1]], %Header2.split ], [ %[[CALL2]], %TBB.split ]
;CHECK: ret i32 %[[MERGED]]
define i32 @test_ne_eq_ne(i32* %a, i32 %v, i32 %p) {
Header:
%tobool1 = icmp ne i32* %a, null
- br i1 %tobool1, label %Header2, label %End
+ br i1 %tobool1, label %Header2, label %TBB
Header2:
%tobool2 = icmp eq i32 %p, 10
@@ -178,14 +178,14 @@ End:
;CHECK-LABEL: Header2.split:
;CHECK: %[[CALL1:.*]] = call i32 @callee(i32* nonnull %a, i32 %v, i32 %p)
;CHECK-LABEL: TBB.split:
-;CHECK: %[[CALL2:.*]] = call i32 @callee(i32* nonnull %a, i32 %v, i32 %p)
+;CHECK: %[[CALL2:.*]] = call i32 @callee(i32* %a, i32 %v, i32 %p)
;CHECK-LABEL: Tail
;CHECK: %[[MERGED:.*]] = phi i32 [ %[[CALL1]], %Header2.split ], [ %[[CALL2]], %TBB.split ]
;CHECK: ret i32 %[[MERGED]]
define i32 @test_ne_ne_ne_constrain_same_pointer_arg(i32* %a, i32 %v, i32 %p, i32* %a2, i32* %a3) {
Header:
%tobool1 = icmp ne i32* %a, null
- br i1 %tobool1, label %Header2, label %End
+ br i1 %tobool1, label %Header2, label %TBB
Header2:
%tobool2 = icmp ne i32* %a, %a2
@@ -235,14 +235,14 @@ End:
;CHECK-LABEL: Header2.split:
;CHECK: %[[CALL1:.*]] = call i32 @callee(i32* nonnull %a, i32 %v, i32 10)
;CHECK-LABEL: TBB.split:
-;CHECK: %[[CALL2:.*]] = call i32 @callee(i32* nonnull %a, i32 1, i32 %p)
+;CHECK: %[[CALL2:.*]] = call i32 @callee(i32* %a, i32 1, i32 %p)
;CHECK-LABEL: Tail
;CHECK: %[[MERGED:.*]] = phi i32 [ %[[CALL1]], %Header2.split ], [ %[[CALL2]], %TBB.split ]
;CHECK: ret i32 %[[MERGED]]
define i32 @test_eq_eq_eq_untaken(i32* %a, i32 %v, i32 %p) {
Header:
%tobool1 = icmp eq i32* %a, null
- br i1 %tobool1, label %End, label %Header2
+ br i1 %tobool1, label %TBB, label %Header2
Header2:
%tobool2 = icmp eq i32 %p, 10
@@ -290,14 +290,14 @@ End:
;CHECK-LABEL: Header2.split:
;CHECK: %[[CALL1:.*]] = call i32 @callee(i32* null, i32 %v, i32 10)
;CHECK-LABEL: TBB.split:
-;CHECK: %[[CALL2:.*]] = call i32 @callee(i32* null, i32 %v, i32 %p)
+;CHECK: %[[CALL2:.*]] = call i32 @callee(i32* %a, i32 %v, i32 %p)
;CHECK-LABEL: Tail
;CHECK: %[[MERGED:.*]] = phi i32 [ %[[CALL1]], %Header2.split ], [ %[[CALL2]], %TBB.split ]
;CHECK: ret i32 %[[MERGED]]
define i32 @test_ne_eq_ne_untaken(i32* %a, i32 %v, i32 %p) {
Header:
%tobool1 = icmp ne i32* %a, null
- br i1 %tobool1, label %End, label %Header2
+ br i1 %tobool1, label %TBB, label %Header2
Header2:
%tobool2 = icmp eq i32 %p, 10
@@ -486,6 +486,31 @@ Tail:
ret i32 %r
End:
+ ret i32 %v
+}
+
+;CHECK-LABEL: @test_cond_no_effect
+;CHECK-NOT: Header.split:
+;CHECK-NOT: TBB.split:
+;CHECK-LABEL: Tail:
+;CHECK: %r = call i32 @callee(i32* %a, i32 %v, i32 0)
+;CHECK: ret i32 %r
+define i32 @test_cond_no_effect(i32* %a, i32 %v) {
+Entry:
+ %tobool1 = icmp eq i32* %a, null
+ br i1 %tobool1, label %Header, label %End
+
+Header:
+ br i1 undef, label %Tail, label %TBB
+
+TBB:
+ br i1 undef, label %Tail, label %End
+
+Tail:
+ %r = call i32 @callee(i32* %a, i32 %v, i32 0)
+ ret i32 %r
+
+End:
ret i32 %v
}
More information about the llvm-commits
mailing list