better MaterializeMergeSchedule.cpp with %lane indexed batch computes

support for tensors of index values

src/PIM/Common/IR/ShapeUtils.cpp

@@ -1,4 +1,5 @@
 #include "llvm/ADT/STLExtras.h"
+#include "llvm/Support/ErrorHandling.h"
 
 #include "src/Accelerators/PIM/Common/IR/ShapeUtils.hpp"
 
@@ -35,6 +36,30 @@ int64_t getNumElements(llvm::ArrayRef<int64_t> shape) {
   return numElements;
 }
 
+bool hasByteSizedElementType(mlir::Type elementType) {
+  if (mlir::isa<mlir::IndexType>(elementType))
+    return true;
+  if (auto intType = mlir::dyn_cast<mlir::IntegerType>(elementType))
+    return intType.getWidth() > 0 && intType.getWidth() % 8 == 0;
+  if (auto floatType = mlir::dyn_cast<mlir::FloatType>(elementType))
+    return floatType.getWidth() > 0 && floatType.getWidth() % 8 == 0;
+  return false;
+}
+
+size_t getElementTypeSizeInBytes(mlir::Type elementType) {
+  if (mlir::isa<mlir::IndexType>(elementType))
+    return mlir::IndexType::kInternalStorageBitWidth / 8;
+  if (auto intType = mlir::dyn_cast<mlir::IntegerType>(elementType))
+    return static_cast<size_t>(intType.getWidth() / 8);
+  if (auto floatType = mlir::dyn_cast<mlir::FloatType>(elementType))
+    return static_cast<size_t>(floatType.getWidth() / 8);
+  llvm_unreachable("expected byte-sized integer, float, or index element type");
+}
+
+size_t getShapedTypeSizeInBytes(mlir::ShapedType shapedType) {
+  return static_cast<size_t>(shapedType.getNumElements()) * getElementTypeSizeInBytes(shapedType.getElementType());
+}
+
 bool isMemoryContiguous(llvm::ArrayRef<int64_t> srcShape,
                         llvm::ArrayRef<int64_t> offsets,
                         llvm::ArrayRef<int64_t> sizes,