remove useless MaterializeHostConstantsPass.cpp and fix lowering before instead

avoid spammy pim codegen diagnostics

src/PIM/Conversion/SpatialToPim/ReturnPathNormalization.cpp

@@ -375,6 +375,57 @@ static void cloneHelperChain(Value sourceValue,
   }
 }
 
+static bool isHostStaticReturnValue(Value value) {
+  llvm::SmallPtrSet<Operation*, 8> visited;
+  while (Operation* definingOp = value.getDefiningOp()) {
+    if (!visited.insert(definingOp).second)
+      return false;
+    if (isa<arith::ConstantOp>(definingOp) || definingOp->hasTrait<OpTrait::ConstantLike>())
+      return true;
+    if (!isReturnHelperChainOp(definingOp) || definingOp->getNumOperands() != 1)
+      return false;
+    value = definingOp->getOperand(0);
+  }
+  return false;
+}
+
+static FailureOr<Value>
+materializeHostStaticReturnValue(IRRewriter& rewriter, Value value, OperationFolder& constantFolder) {
+  llvm::SmallVector<Operation*> chain;
+  llvm::SmallPtrSet<Operation*, 8> visited;
+  while (Operation* definingOp = value.getDefiningOp()) {
+    if (!visited.insert(definingOp).second)
+      return failure();
+    chain.push_back(definingOp);
+    if (isa<arith::ConstantOp>(definingOp) || definingOp->hasTrait<OpTrait::ConstantLike>())
+      break;
+    if (!isReturnHelperChainOp(definingOp) || definingOp->getNumOperands() != 1)
+      return failure();
+    value = definingOp->getOperand(0);
+  }
+
+  if (chain.empty())
+    return failure();
+
+  IRMapping mapping;
+  Value clonedValue;
+  for (Operation* op : llvm::reverse(chain)) {
+    if (auto constantOp = dyn_cast<arith::ConstantOp>(op)) {
+      clonedValue = getOrCreateConstantLike(constantFolder, constantOp);
+      mapping.map(op->getResult(0), clonedValue);
+      continue;
+    }
+
+    Operation* clonedOp = rewriter.clone(*op, mapping);
+    for (auto [originalResult, newResult] : llvm::zip(op->getResults(), clonedOp->getResults()))
+      mapping.map(originalResult, newResult);
+    clonedValue = clonedOp->getResult(0);
+    rewriter.setInsertionPointAfter(clonedOp);
+  }
+
+  return clonedValue;
+}
+
 static FailureOr<Value> emitHostCopy(IRRewriter& rewriter,
                                      Location loc,
                                      Value outputTensor,
@@ -444,7 +495,30 @@ raptor::SpatialToPimPass::ReturnPathLoweringResult raptor::SpatialToPimPass::low
   OperationFolder constantFolder(producerOp->getContext());
   auto storedTensorType = cast<TensorType>(storedValue.getType());
 
+  auto materializeDirectHostReturn = [&](size_t returnIndex,
+                                         Value sourceValue,
+                                         ArrayRef<Operation*> helperChain) -> ReturnPathLoweringResult {
+    rewriter.setInsertionPointAfter(producerOp);
+    auto hostStaticValue = materializeHostStaticReturnValue(rewriter, sourceValue, constantFolder);
+    if (failed(hostStaticValue))
+      return ReturnPathLoweringResult::Failure;
+
+    Value hostReturnValue = *hostStaticValue;
+    if (!helperChain.empty())
+      cloneHelperChain(hostReturnValue, helperChain, rewriter, constantFolder, hostReturnValue);
+
+    outputTensors[returnIndex] =
+      [hostReturnValue](IRRewriter& rewriter, Location loc) -> Value { return hostReturnValue; };
+    return ReturnPathLoweringResult::Handled;
+  };
+
   if (auto returnUse = analyzeReturnUse(producedValue)) {
+    if (isHostStaticReturnValue(storedValue)) {
+      for (Operation* op : returnUse->helperChain)
+        markOpToRemove(op);
+      return materializeDirectHostReturn(returnUse->returnIndex, storedValue, returnUse->helperChain);
+    }
+
     Value currentStoredValue = storedValue;
     cloneHelperChain(storedValue, returnUse->helperChain, rewriter, constantFolder, currentStoredValue);
     for (Operation* op : returnUse->helperChain)
@@ -470,6 +544,8 @@ raptor::SpatialToPimPass::ReturnPathLoweringResult raptor::SpatialToPimPass::low
 
     if (isa<func::ReturnOp>(resultUser)) {
       size_t resultIndexInReturn = resultUse.getOperandNumber();
+      if (isHostStaticReturnValue(storedValue))
+        return materializeDirectHostReturn(resultIndexInReturn, storedValue, {});
       auto byteSize =
         pim::getCheckedShapedTypeSizeInBytes(storedTensorType, producerOp, "return-path host copy byte size");
       if (failed(byteSize))