[mlir][sparse] support iteration over compressed-hi dimension level in loop emitter

Reviewed By: aartbik

Differential Revision: https://reviews.llvm.org/D148668

mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorCodegen.cpp

@@ -532,6 +532,8 @@ static void genEndInsert(OpBuilder &builder, Location loc,
   const Level lvlRank = stt.getLvlRank();
   for (Level l = 0; l < lvlRank; l++) {
     const auto dlt = stt.getLvlType(l);
+    if (isCompressedWithHiDLT(dlt))
+      llvm_unreachable("TODO: Not yet implemented");
     if (isCompressedDLT(dlt)) {
       // Compressed dimensions need a position cleanup for all entries
       // that were not visited during the insertion pass.