[llvm] [InstCombine] Fold icmp(constants[x]) when the range of x is given (PR #67093)

[via llvm-commits]

================
@@ -110,55 +112,34 @@ static bool isSignTest(ICmpInst::Predicate &Pred, const APInt &C) {
 Instruction *InstCombinerImpl::foldCmpLoadFromIndexedGlobal(
     LoadInst *LI, GetElementPtrInst *GEP, GlobalVariable *GV, CmpInst &ICI,
     ConstantInt *AndCst) {
-  if (LI->isVolatile() || LI->getType() != GEP->getResultElementType() ||
-      GV->getValueType() != GEP->getSourceElementType() ||
-      !GV->isConstant() || !GV->hasDefinitiveInitializer())
+  if (LI->isVolatile() || !GV->isConstant() || !GV->hasDefinitiveInitializer())
     return nullptr;
 
   Constant *Init = GV->getInitializer();
-  if (!isa<ConstantArray>(Init) && !isa<ConstantDataArray>(Init))
-    return nullptr;
+  uint64_t DataSize = DL.getTypeAllocSize(Init->getType());
 
-  uint64_t ArrayElementCount = Init->getType()->getArrayNumElements();
   // Don't blow up on huge arrays.
-  if (ArrayElementCount > MaxArraySizeForCombine)
-    return nullptr;
-
-  // There are many forms of this optimization we can handle, for now, just do
-  // the simple index into a single-dimensional array.
-  //
-  // Require: GEP GV, 0, i {{, constant indices}}
-  if (GEP->getNumOperands() < 3 ||
-      !isa<ConstantInt>(GEP->getOperand(1)) ||
-      !cast<ConstantInt>(GEP->getOperand(1))->isZero() ||
-      isa<Constant>(GEP->getOperand(2)))
+  if (DataSize > MaxDataSizeForCombine)
     return nullptr;
 
-  // Check that indices after the variable are constants and in-range for the
-  // type they index.  Collect the indices.  This is typically for arrays of
-  // structs.
-  SmallVector<unsigned, 4> LaterIndices;
+  Type *LoadedTy = LI->getType();
+  uint64_t LoadedTySize = DL.getTypeAllocSize(LoadedTy);
+  uint64_t PtrBitwidth = DL.getIndexSizeInBits(GEP->getPointerAddressSpace());
+  Type *PtrIdxTy = DL.getIndexType(GEP->getType());
 
-  Type *EltTy = Init->getType()->getArrayElementType();
-  for (unsigned i = 3, e = GEP->getNumOperands(); i != e; ++i) {
-    ConstantInt *Idx = dyn_cast<ConstantInt>(GEP->getOperand(i));
-    if (!Idx) return nullptr;  // Variable index.
-
-    uint64_t IdxVal = Idx->getZExtValue();
-    if ((unsigned)IdxVal != IdxVal) return nullptr; // Too large array index.
-
-    if (StructType *STy = dyn_cast<StructType>(EltTy))
-      EltTy = STy->getElementType(IdxVal);
-    else if (ArrayType *ATy = dyn_cast<ArrayType>(EltTy)) {
-      if (IdxVal >= ATy->getNumElements()) return nullptr;
-      EltTy = ATy->getElementType();
-    } else {
-      return nullptr; // Unknown type.
-    }
+  MapVector<Value *, APInt> VariableOffsets;
+  APInt ConstantOffset(PtrBitwidth, 0);
+  GEP->collectOffset(GEP->getModule()->getDataLayout(), PtrBitwidth,
----------------
XChy wrote:

Done.

https://github.com/llvm/llvm-project/pull/67093