[ValueTracking,VectorCombine] Allow passing DT to computeConstantRange.

[fhahn]

Summary

isValidAssumeForContext can provide better results with access to the
dominator tree in some cases. This patch adjusts computeConstantRange to
allow passing through a dominator tree.

The use VectorCombine is updated to pass through the DT to enable
additional scalarization.

Note that similar APIs like computeKnownBits already accept optional dominator
tree arguments.

[lebedev.ri]

LG with nit.

llvm/include/llvm/Analysis/ValueTracking.h

552

I think Depth should always stay the last parameter

[RKSimon]

llvm/include/llvm/Analysis/ValueTracking.h

552

+1

[fhahn]

Thanks, moved DT argument before Depth.

[fhahn]

llvm/include/llvm/Analysis/ValueTracking.h

552

There weren't too many users that needed updating. Fixed!

llvm/include/llvm/Analysis/ValueTracking.h

bool isOverflowIntrinsicNoWrap(const WithOverflowInst *WO,
                                  const DominatorTree &DT);
 
 
   /// Determine the possible constant range of an integer or vector of integer
   /// value. This is intended as a cheap, non-recursive check.
   ConstantRange computeConstantRange(const Value *V, bool UseInstrInfo = true,
                                      AssumptionCache *AC = nullptr,
                                      const Instruction *CtxI = nullptr,
-                                     unsigned Depth = 0);
+                                     unsigned Depth = 0,
+                                     const DominatorTree *DT = nullptr);
 
   /// Return true if this function can prove that the instruction I will
   /// always transfer execution to one of its successors (including the next
   /// instruction that follows within a basic block). E.g. this is not
   /// guaranteed for function calls that could loop infinitely.
   ///
   /// In other words, this function returns false for instructions that may
   /// transfer execution or fail to transfer execution in a way that is not

llvm/lib/Analysis/ValueTracking.cpp

switch (R.Flavor) {
     default:
       break;
   }
 }
 
 ConstantRange llvm::computeConstantRange(const Value *V, bool UseInstrInfo,
                                          AssumptionCache *AC,
                                          const Instruction *CtxI,
-                                         unsigned Depth) {
+                                         unsigned Depth,
+                                         const DominatorTree *DT) {
   assert(V->getType()->isIntOrIntVectorTy() && "Expected integer instruction");
 
   if (Depth == MaxAnalysisRecursionDepth)
     return ConstantRange::getFull(V->getType()->getScalarSizeInBits());
 
   const APInt *C;
   if (match(V, m_APInt(C)))
     return ConstantRange(*C);
for (auto &AssumeVH : AC->assumptionsFor(V)) {
       if (!AssumeVH)
         continue;
       CallInst *I = cast<CallInst>(AssumeVH);
       assert(I->getParent()->getParent() == CtxI->getParent()->getParent() &&
              "Got assumption for the wrong function!");
       assert(I->getCalledFunction()->getIntrinsicID() == Intrinsic::assume &&
              "must be an assume intrinsic");
 
-      if (!isValidAssumeForContext(I, CtxI, nullptr))
+      if (!isValidAssumeForContext(I, CtxI, DT))
         continue;
       Value *Arg = I->getArgOperand(0);
       ICmpInst *Cmp = dyn_cast<ICmpInst>(Arg);
       // Currently we just use information from comparisons.
       if (!Cmp || Cmp->getOperand(0) != V)
         continue;
       ConstantRange RHS = computeConstantRange(Cmp->getOperand(1), UseInstrInfo,
                                                AC, I, Depth + 1);

llvm/lib/Transforms/Vectorize/VectorCombine.cpp

void freeze(IRBuilder<> &Builder, Instruction &UserI) {
     ToFreeze = nullptr;
   }
 };
 
 /// Check if it is legal to scalarize a memory access to \p VecTy at index \p
 /// Idx. \p Idx must access a valid vector element.
 static ScalarizationResult canScalarizeAccess(FixedVectorType *VecTy,
                                               Value *Idx, Instruction *CtxI,
-                                              AssumptionCache &AC) {
+                                              AssumptionCache &AC,
+                                              const DominatorTree &DT) {
   if (auto *C = dyn_cast<ConstantInt>(Idx)) {
     if (C->getValue().ult(VecTy->getNumElements()))
       return ScalarizationResult::safe();
     return ScalarizationResult::unsafe();
   }
 
   unsigned IntWidth = Idx->getType()->getScalarSizeInBits();
   APInt Zero(IntWidth, 0);
   APInt MaxElts(IntWidth, VecTy->getNumElements());
   ConstantRange ValidIndices(Zero, MaxElts);
   ConstantRange IdxRange(IntWidth, true);
 
   if (isGuaranteedNotToBePoison(Idx, &AC)) {
-    if (ValidIndices.contains(computeConstantRange(Idx, true, &AC, CtxI, 0)))
+    if (ValidIndices.contains(
+            computeConstantRange(Idx, true, &AC, CtxI, 0, &DT)))
       return ScalarizationResult::safe();
     return ScalarizationResult::unsafe();
   }
 
   // If the index may be poison, check if we can insert a freeze before the
   // range of the index is restricted.
   Value *IdxBase;
   ConstantInt *CI;
if (auto *Load = dyn_cast<LoadInst>(Source)) {
     Value *SrcAddr = Load->getPointerOperand()->stripPointerCasts();
     // Don't optimize for atomic/volatile load or store. Ensure memory is not
     // modified between, vector type matches store size, and index is inbounds.
     if (!Load->isSimple() || Load->getParent() != SI->getParent() ||
         !DL.typeSizeEqualsStoreSize(Load->getType()) ||
         SrcAddr != SI->getPointerOperand()->stripPointerCasts())
       return false;
 
-    auto ScalarizableIdx = canScalarizeAccess(VecTy, Idx, Load, AC);
+    auto ScalarizableIdx = canScalarizeAccess(VecTy, Idx, Load, AC, DT);
     if (ScalarizableIdx.isUnsafe() ||
         isMemModifiedBetween(Load->getIterator(), SI->getIterator(),
                              MemoryLocation::get(SI), AA))
       return false;
 
     if (ScalarizableIdx.isSafeWithFreeze())
       ScalarizableIdx.freeze(Builder, *cast<Instruction>(Idx));
     Value *GEP = Builder.CreateInBoundsGEP(
if (LastCheckedInst->comesBefore(UI)) {
       }
     }
 
     if (!LastCheckedInst)
       LastCheckedInst = UI;
     else if (LastCheckedInst->comesBefore(UI))
       LastCheckedInst = UI;
 
-    auto ScalarIdx = canScalarizeAccess(FixedVT, UI->getOperand(1), &I, AC);
+    auto ScalarIdx = canScalarizeAccess(FixedVT, UI->getOperand(1), &I, AC, DT);
     if (!ScalarIdx.isSafe()) {
       // TODO: Freeze index if it is safe to do so.
       return false;
     }
 
     auto *Index = dyn_cast<ConstantInt>(UI->getOperand(1));
     OriginalCost +=
         TTI.getVectorInstrCost(Instruction::ExtractElement, LI->getType(),

llvm/test/Transforms/VectorCombine/AArch64/load-extract-insert-store-scalarization.ll

 ; CHECK-NEXT:    call void @llvm.assume(i1 [[CMP_2]])
 ; CHECK-NEXT:    br i1 [[C_1:%.*]], label [[LOOP:%.*]], label [[EXIT:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[LV:%.*]] = load <225 x double>, <225 x double>* [[A:%.*]], align 8
 ; CHECK-NEXT:    [[EXT_0:%.*]] = extractelement <225 x double> [[LV]], i64 [[IDX_1]]
 ; CHECK-NEXT:    [[MUL:%.*]] = fmul double 2.000000e+01, [[EXT_0]]
 ; CHECK-NEXT:    [[EXT_1:%.*]] = extractelement <225 x double> [[LV]], i64 [[IDX_2]]
 ; CHECK-NEXT:    [[SUB:%.*]] = fsub double [[EXT_1]], [[MUL]]
-; CHECK-NEXT:    [[INS:%.*]] = insertelement <225 x double> [[LV]], double [[SUB]], i64 [[IDX_1]]
-; CHECK-NEXT:    store <225 x double> [[INS]], <225 x double>* [[A]], align 8
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds <225 x double>, <225 x double>* [[A]], i64 0, i64 [[IDX_1]]
+; CHECK-NEXT:    store double [[SUB]], double* [[TMP0]], align 8
 ; CHECK-NEXT:    [[C_2:%.*]] = call i1 @cond()
 ; CHECK-NEXT:    br i1 [[C_2]], label [[LOOP]], label [[EXIT]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret void
 ;
 entry:
   %cmp.1 = icmp ult i64 %idx.1, 225
   call void @llvm.assume(i1 %cmp.1)

llvm/test/Transforms/VectorCombine/AArch64/load-extractelement-scalarization.ll

 
 define i32 @load_extract_idx_var_i64_known_valid_by_assume_in_dominating_block(<4 x i32>* %x, i64 %idx, i1 %c.1) {
 ; CHECK-LABEL: @load_extract_idx_var_i64_known_valid_by_assume_in_dominating_block(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i64 [[IDX:%.*]], 4
 ; CHECK-NEXT:    call void @llvm.assume(i1 [[CMP]])
 ; CHECK-NEXT:    br i1 [[C_1:%.*]], label [[LOOP:%.*]], label [[EXIT:%.*]]
 ; CHECK:       loop:
-; CHECK-NEXT:    [[LV:%.*]] = load <4 x i32>, <4 x i32>* [[X:%.*]], align 16
 ; CHECK-NEXT:    call void @maythrow()
-; CHECK-NEXT:    [[R:%.*]] = extractelement <4 x i32> [[LV]], i64 [[IDX]]
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds <4 x i32>, <4 x i32>* [[X:%.*]], i32 0, i64 [[IDX]]
+; CHECK-NEXT:    [[R:%.*]] = load i32, i32* [[TMP0]], align 4
 ; CHECK-NEXT:    [[C_2:%.*]] = call i1 @cond()
 ; CHECK-NEXT:    br i1 [[C_2]], label [[LOOP]], label [[EXIT]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    [[P:%.*]] = phi i32 [ [[R]], [[LOOP]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    ret i32 [[P]]
 ;
 entry:
   %cmp = icmp ult i64 %idx, 4