Add some shortcuts in LazyValueInfo to reduce compile time of Correlated Value Propagation.

The patch is to partially fix PR10584. Correlated Value Propagation queries LVI
to check non-null for pointer params of each callsite. If we know the def of
param is an alloca instruction, we know it is non-null and can return early from
LVI. Similarly, CVP queries LVI to check whether pointer for each mem access is
constant. If the def of the pointer is an alloca instruction, we know it is not
a constant pointer. These shortcuts can reduce the cost of CVP significantly.

Differential Revision: https://reviews.llvm.org/D18066

llvm-svn: 281586

llvm/lib/Analysis/LazyValueInfo.cpp

@@ -1601,8 +1601,26 @@ LazyValueInfo LazyValueAnalysis::run(Function &F, FunctionAnalysisManager &FAM)
   return LazyValueInfo(&AC, &TLI, DT);
 }
 
+/// Returns true if we can statically tell that this value will never be a
+/// "useful" constant.  In practice, this means we've got something like an
+/// alloca or a malloc call for which a comparison against a constant can
+/// only be guarding dead code.  Note that we are potentially giving up some
+/// precision in dead code (a constant result) in favour of avoiding a
+/// expensive search for a easily answered common query.
+static bool isKnownNonConstant(Value *V) {
+  V = V->stripPointerCasts();
+  // The return val of alloc cannot be a Constant.
+  if (isa<AllocaInst>(V))
+    return true;
+  return false;
+}
+
 Constant *LazyValueInfo::getConstant(Value *V, BasicBlock *BB,
                                      Instruction *CxtI) {
+  // Bail out early if V is known not to be a Constant.
+  if (isKnownNonConstant(V))
+    return nullptr;
+
   const DataLayout &DL = BB->getModule()->getDataLayout();
   LVILatticeVal Result =
       getImpl(PImpl, AC, &DL, DT).getValueInBlock(V, BB, CxtI);
@@ -1738,6 +1756,17 @@ LazyValueInfo::getPredicateOnEdge(unsigned Pred, Value *V, Constant *C,
 LazyValueInfo::Tristate
 LazyValueInfo::getPredicateAt(unsigned Pred, Value *V, Constant *C,
                               Instruction *CxtI) {
+  // Is or is not NonNull are common predicates being queried. If
+  // isKnownNonNull can tell us the result of the predicate, we can
+  // return it quickly. But this is only a fastpath, and falling
+  // through would still be correct.
+  if (V->getType()->isPointerTy() && C->isNullValue() &&
+      isKnownNonNull(V->stripPointerCasts())) {
+    if (Pred == ICmpInst::ICMP_EQ)
+      return LazyValueInfo::False;
+    else if (Pred == ICmpInst::ICMP_NE)
+      return LazyValueInfo::True;
+  }
   const DataLayout &DL = CxtI->getModule()->getDataLayout();
   LVILatticeVal Result = getImpl(PImpl, AC, &DL, DT).getValueAt(V, CxtI);
   Tristate Ret = getPredicateResult(Pred, C, Result, DL, TLI);

llvm/test/Transforms/CorrelatedValuePropagation/alloca.ll

@@ -0,0 +1,48 @@
+; RUN: opt -S -correlated-propagation -debug-only=lazy-value-info <%s 2>&1 | FileCheck %s
+;
+; Shortcut in Correlated Value Propagation ensures not to take Lazy Value Info
+; analysis for %a.i and %tmp because %a.i is defined by alloca and %tmp is
+; defined by alloca + bitcast. We know the ret value of alloca is nonnull.
+;
+; CHECK-NOT: LVI Getting edge value   %a.i = alloca i64, align 8 at 'for.body'
+; CHECK-NOT: LVI Getting edge value   %tmp = bitcast i64* %a.i to i8* from 'for.cond' to 'for.body'
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@.str = private unnamed_addr constant [8 x i8] c"a = %l\0A\00", align 1
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.lifetime.start(i64, i8* nocapture)
+
+declare void @hoo(i64*)
+
+declare i32 @printf(i8* nocapture readonly, ...)
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.lifetime.end(i64, i8* nocapture)
+
+define void @goo(i32 %N, i64* %b) {
+entry:
+  %a.i = alloca i64, align 8
+  %tmp = bitcast i64* %a.i to i8*
+  %c = getelementptr inbounds i64, i64* %b, i64 0
+  br label %for.cond
+
+for.cond:                                         ; preds = %for.body, %entry
+  %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
+  %cmp = icmp slt i32 %i.0, %N
+  br i1 %cmp, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.cond
+  call void @llvm.lifetime.start(i64 8, i8* %tmp)
+  call void @hoo(i64* %a.i)
+  call void @hoo(i64* %c)
+  %tmp1 = load volatile i64, i64* %a.i, align 8
+  %call.i = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i64 %tmp1)
+  call void @llvm.lifetime.end(i64 8, i8* %tmp)
+  %inc = add nsw i32 %i.0, 1
+  br label %for.cond
+
+for.end:                                          ; preds = %for.cond
+  ret void
+}