diff --git a/.travis/openfpga_vpr8_reg_test.sh b/.travis/openfpga_vpr8_reg_test.sh
index 8c07480cd..c48959e58 100755
--- a/.travis/openfpga_vpr8_reg_test.sh
+++ b/.travis/openfpga_vpr8_reg_test.sh
@@ -99,6 +99,9 @@ python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/generate_fabric --
 echo -e "Testing Verilog testbench generation only";
 python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/generate_testbench --debug --show_thread_logs
 
+echo -e "Testing bitstream generation only";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/generate_bitstream --debug --show_thread_logs
+
 echo -e "Testing SDC generation with time units";
 python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/sdc_time_unit --debug --show_thread_logs
 
diff --git a/libopenfpga/libfpgabitstream/src/bitstream_manager.cpp b/libopenfpga/libfpgabitstream/src/bitstream_manager.cpp
index 66b4d1f23..990423802 100644
--- a/libopenfpga/libfpgabitstream/src/bitstream_manager.cpp
+++ b/libopenfpga/libfpgabitstream/src/bitstream_manager.cpp
@@ -9,17 +9,37 @@
 /* begin namespace openfpga */
 namespace openfpga {
 
+/**************************************************
+ * Public Constructors
+ *************************************************/
+BitstreamManager::BitstreamManager() {
+  num_blocks_ = 0;
+  num_bits_ = 0;
+  invalid_block_ids_.clear();
+  invalid_bit_ids_.clear();
+}
+
 /**************************************************
  * Public Accessors : Aggregates
  *************************************************/
 /* Find all the configuration bits */
+size_t BitstreamManager::num_bits() const {
+  return num_bits_;
+}
+
 BitstreamManager::config_bit_range BitstreamManager::bits() const {
-  return vtr::make_range(bit_ids_.begin(), bit_ids_.end());
+  return vtr::make_range(config_bit_iterator(ConfigBitId(0), invalid_bit_ids_),
+                         config_bit_iterator(ConfigBitId(num_bits_), invalid_bit_ids_));
+}
+
+size_t BitstreamManager::num_blocks() const {
+  return num_blocks_;
 }
 
 /* Find all the configuration blocks */
 BitstreamManager::config_block_range BitstreamManager::blocks() const {
-  return vtr::make_range(block_ids_.begin(), block_ids_.end());
+  return vtr::make_range(config_block_iterator(ConfigBlockId(0), invalid_block_ids_),
+                         config_block_iterator(ConfigBlockId(num_blocks_), invalid_block_ids_));
 }
 
 /******************************************************************************
@@ -29,7 +49,7 @@ bool BitstreamManager::bit_value(const ConfigBitId& bit_id) const {
   /* Ensure a valid id */
   VTR_ASSERT(true == valid_bit_id(bit_id));
 
-  return bit_values_[bit_id];
+  return '1' == bit_values_[bit_id];
 }
 
 std::string BitstreamManager::block_name(const ConfigBlockId& block_id) const {
@@ -57,32 +77,20 @@ std::vector<ConfigBitId> BitstreamManager::block_bits(const ConfigBlockId& block
   /* Ensure the input ids are valid */
   VTR_ASSERT(true == valid_block_id(block_id));
 
-  return block_bit_ids_[block_id];
-}
+  size_t lsb = block_bit_id_lsbs_[block_id]; 
+  size_t length = block_bit_lengths_[block_id]; 
 
-ConfigBlockId BitstreamManager::bit_parent_block(const ConfigBitId& bit_id) const {
-  /* Ensure the input ids are valid */
-  VTR_ASSERT(true == valid_bit_id(bit_id));
+  std::vector<ConfigBitId> bits(length, ConfigBitId::INVALID());
 
-  return bit_parent_block_ids_[bit_id];
-}
-
-size_t BitstreamManager::bit_index_in_parent_block(const ConfigBitId& bit_id) const {
-  /* Ensure the input ids are valid */
-  VTR_ASSERT(true == valid_bit_id(bit_id));
-
-  ConfigBlockId bit_parent_block = bit_parent_block_ids_[bit_id];
-
-  VTR_ASSERT(true == valid_block_id(bit_parent_block));
-
-  for (size_t index = 0; index < block_bits(bit_parent_block).size(); ++index) {
-    if (bit_id == block_bits(bit_parent_block)[index]) {
-      return index;
-    }
+  if (0 == length) {
+    return bits;
   }
 
-  /* Not found, return in valid value */
-  return size_t(-1); 
+  for (size_t i = lsb; i < lsb + length; ++i) {
+    bits[i - lsb] = ConfigBitId(i);
+  }
+
+  return bits;
 }
 
 /* Find the child block in a bitstream manager with a given name */
@@ -133,20 +141,22 @@ std::vector<std::string> BitstreamManager::block_output_net_ids(const ConfigBloc
  * Public Mutators
  ******************************************************************************/
 ConfigBitId BitstreamManager::add_bit(const bool& bit_value) {
-  ConfigBitId bit = ConfigBitId(bit_ids_.size());
+  ConfigBitId bit = ConfigBitId(num_bits_);
   /* Add a new bit, and allocate associated data structures */
-  bit_ids_.push_back(bit);
-  bit_values_.push_back(bit_value);
-  shared_config_bit_values_.emplace_back();
-  bit_parent_block_ids_.push_back(ConfigBlockId::INVALID());
+  num_bits_++;
+  if (true == bit_value) {
+    bit_values_.push_back('1');
+  } else {
+    bit_values_.push_back('0');
+  }
 
   return bit; 
 }
 
 void BitstreamManager::reserve_blocks(const size_t& num_blocks) {
-  block_ids_.reserve(num_blocks);
   block_names_.reserve(num_blocks);
-  block_bit_ids_.reserve(num_blocks);
+  block_bit_id_lsbs_.reserve(num_blocks);
+  block_bit_lengths_.reserve(num_blocks);
   block_path_ids_.reserve(num_blocks);
   block_input_net_ids_.reserve(num_blocks);
   block_output_net_ids_.reserve(num_blocks);
@@ -154,12 +164,17 @@ void BitstreamManager::reserve_blocks(const size_t& num_blocks) {
   child_block_ids_.reserve(num_blocks);
 }
 
+void BitstreamManager::reserve_bits(const size_t& num_bits) {
+  bit_values_.reserve(num_bits);
+}
+
 ConfigBlockId BitstreamManager::create_block() {
-  ConfigBlockId block = ConfigBlockId(block_ids_.size());
+  ConfigBlockId block = ConfigBlockId(num_blocks_);
   /* Add a new bit, and allocate associated data structures */
-  block_ids_.push_back(block);
+  num_blocks_++;
   block_names_.emplace_back();
-  block_bit_ids_.emplace_back();
+  block_bit_id_lsbs_.emplace_back(-1);
+  block_bit_lengths_.emplace_back(0);
   block_path_ids_.push_back(-2);
   block_input_net_ids_.emplace_back();
   block_output_net_ids_.emplace_back();
@@ -183,6 +198,15 @@ void BitstreamManager::set_block_name(const ConfigBlockId& block_id,
   block_names_[block_id] = block_name;
 }
 
+void BitstreamManager::reserve_child_blocks(const ConfigBlockId& parent_block,
+                                            const size_t& num_children) {
+  /* Ensure the input ids are valid */
+  VTR_ASSERT(true == valid_block_id(parent_block));
+
+  /* Add the child_block to the parent_block */
+  child_block_ids_[parent_block].reserve(num_children);
+}
+
 void BitstreamManager::add_child_block(const ConfigBlockId& parent_block, const ConfigBlockId& child_block) {
   /* Ensure the input ids are valid */
   VTR_ASSERT(true == valid_block_id(parent_block));
@@ -201,18 +225,17 @@ void BitstreamManager::add_child_block(const ConfigBlockId& parent_block, const
   parent_block_ids_[child_block] = parent_block;
 }
 
-void BitstreamManager::add_bit_to_block(const ConfigBlockId& block, const ConfigBitId& bit) {
+void BitstreamManager::add_block_bits(const ConfigBlockId& block,
+                                      const std::vector<bool>& block_bitstream) {
   /* Ensure the input ids are valid */
   VTR_ASSERT(true == valid_block_id(block));
-  VTR_ASSERT(true == valid_bit_id(bit));
 
-  /* We should have only a parent block for each bit! */
-  VTR_ASSERT(ConfigBlockId::INVALID() == bit_parent_block_ids_[bit]);
-
-  /* Add the bit to the block */
-  block_bit_ids_[block].push_back(bit);
-  /* Register the block in the parent of the bit */
-  bit_parent_block_ids_[bit] = block;
+  /* Add the bit to the block, record anchors in bit indexing for block-level searching */
+  block_bit_id_lsbs_[block] = num_bits_;
+  block_bit_lengths_[block] = block_bitstream.size();
+  for (const bool& bit : block_bitstream) {
+    add_bit(bit);
+  }
 }
 
 void BitstreamManager::add_path_id_to_block(const ConfigBlockId& block, const int& path_id) {
@@ -223,6 +246,14 @@ void BitstreamManager::add_path_id_to_block(const ConfigBlockId& block, const in
   block_path_ids_[block] = path_id;
 }
 
+void BitstreamManager::reserve_block_input_net_ids(const ConfigBlockId& block,
+                                                   const size_t& num_input_net_ids) {
+  /* Ensure the input ids are valid */
+  VTR_ASSERT(true == valid_block_id(block));
+
+  block_input_net_ids_[block].reserve(num_input_net_ids);
+}
+
 void BitstreamManager::add_input_net_id_to_block(const ConfigBlockId& block,
                                                  const std::string& input_net_id) {
   /* Ensure the input ids are valid */
@@ -232,6 +263,14 @@ void BitstreamManager::add_input_net_id_to_block(const ConfigBlockId& block,
   block_input_net_ids_[block].push_back(input_net_id);
 }
 
+void BitstreamManager::reserve_block_output_net_ids(const ConfigBlockId& block,
+                                                    const size_t& num_output_net_ids) {
+  /* Ensure the input ids are valid */
+  VTR_ASSERT(true == valid_block_id(block));
+
+  block_output_net_ids_[block].reserve(num_output_net_ids);
+}
+
 void BitstreamManager::add_output_net_id_to_block(const ConfigBlockId& block,
                                                   const std::string& output_net_id) {
   /* Ensure the input ids are valid */
@@ -241,22 +280,15 @@ void BitstreamManager::add_output_net_id_to_block(const ConfigBlockId& block,
   block_output_net_ids_[block].push_back(output_net_id);
 }
 
-void BitstreamManager::add_shared_config_bit_values(const ConfigBitId& bit, const std::vector<bool>& shared_config_bits) {
-  /* Ensure the input ids are valid */
-  VTR_ASSERT(true == valid_bit_id(bit));
- 
-  shared_config_bit_values_[bit] = shared_config_bits;
-}
-
 /******************************************************************************
  * Public Validators
  ******************************************************************************/
 bool BitstreamManager::valid_bit_id(const ConfigBitId& bit_id) const {
-  return (size_t(bit_id) < bit_ids_.size()) && (bit_id == bit_ids_[bit_id]);
+  return (size_t(bit_id) < num_bits_);
 }
 
 bool BitstreamManager::valid_block_id(const ConfigBlockId& block_id) const {
-  return (size_t(block_id) < block_ids_.size()) && (block_id == block_ids_[block_id]);
+  return (size_t(block_id) < num_blocks_);
 }
 
 bool BitstreamManager::valid_block_path_id(const ConfigBlockId& block_id) const {
diff --git a/libopenfpga/libfpgabitstream/src/bitstream_manager.h b/libopenfpga/libfpgabitstream/src/bitstream_manager.h
index 71bd63b43..6f2e56c38 100644
--- a/libopenfpga/libfpgabitstream/src/bitstream_manager.h
+++ b/libopenfpga/libfpgabitstream/src/bitstream_manager.h
@@ -36,6 +36,8 @@
 
 #include <vector>
 #include <map>
+#include <unordered_set>
+#include <unordered_map>
 #include "vtr_vector.h"
 
 #include "bitstream_manager_fwd.h"
@@ -44,17 +46,73 @@
 namespace openfpga {
 
 class BitstreamManager {
+  public: /* Type implementations */
+    /*
+     * This class (forward delcared above) is a template used to represent a lazily calculated 
+     * iterator of the specified ID type. The key assumption made is that the ID space is 
+     * contiguous and can be walked by incrementing the underlying ID value. To account for 
+     * invalid IDs, it keeps a reference to the invalid ID set and returns ID::INVALID() for
+     * ID values in the set.
+     *
+     * It is used to lazily create an iteration range (e.g. as returned by RRGraph::edges() RRGraph::nodes())
+     * just based on the count of allocated elements (i.e. RRGraph::num_nodes_ or RRGraph::num_edges_),
+     * and the set of any invalid IDs (i.e. RRGraph::invalid_node_ids_, RRGraph::invalid_edge_ids_).
+     */
+    template<class ID>
+    class lazy_id_iterator : public std::iterator<std::bidirectional_iterator_tag, ID> {
+      public:
+        //Since we pass ID as a template to std::iterator we need to use an explicit 'typename'
+        //to bring the value_type and iterator names into scope
+        typedef typename std::iterator<std::bidirectional_iterator_tag, ID>::value_type value_type;
+        typedef typename std::iterator<std::bidirectional_iterator_tag, ID>::iterator iterator;
+
+        lazy_id_iterator(value_type init, const std::unordered_set<ID>& invalid_ids)
+            : value_(init)
+            , invalid_ids_(invalid_ids) {}
+
+        //Advance to the next ID value
+        iterator operator++() {
+            value_ = ID(size_t(value_) + 1);
+            return *this;
+        }
+
+        //Advance to the previous ID value
+        iterator operator--() {
+            value_ = ID(size_t(value_) - 1);
+            return *this;
+        }
+
+        //Dereference the iterator
+        value_type operator*() const { return (invalid_ids_.count(value_)) ? ID::INVALID() : value_; }
+
+        friend bool operator==(const lazy_id_iterator<ID> lhs, const lazy_id_iterator<ID> rhs) { return lhs.value_ == rhs.value_; }
+        friend bool operator!=(const lazy_id_iterator<ID> lhs, const lazy_id_iterator<ID> rhs) { return !(lhs == rhs); }
+
+      private:
+        value_type value_;
+        const std::unordered_set<ID>& invalid_ids_;
+    };
+
+  public: /* Public constructor */
+    BitstreamManager();
+
   public: /* Types and ranges */
-    typedef vtr::vector<ConfigBitId, ConfigBitId>::const_iterator config_bit_iterator;
-    typedef vtr::vector<ConfigBlockId, ConfigBlockId>::const_iterator config_block_iterator;
+    //Lazy iterator utility forward declaration
+    template<class ID>
+    class lazy_id_iterator;
+
+    typedef lazy_id_iterator<ConfigBitId> config_bit_iterator;
+    typedef lazy_id_iterator<ConfigBlockId> config_block_iterator;
 
     typedef vtr::Range<config_bit_iterator> config_bit_range;
     typedef vtr::Range<config_block_iterator> config_block_range;
 
   public: /* Public aggregators */
     /* Find all the configuration bits */
+    size_t num_bits() const;
     config_bit_range bits() const;
 
+    size_t num_blocks() const;
     config_block_range blocks() const;
 
   public:  /* Public Accessors */
@@ -73,12 +131,6 @@ class BitstreamManager {
     /* Find all the bits that belong to a block */
     std::vector<ConfigBitId> block_bits(const ConfigBlockId& block_id) const;
 
-    /* Find the parent block of a bit */
-    ConfigBlockId bit_parent_block(const ConfigBitId& bit_id) const;
-
-    /* Find the index of a configuration bit in its parent block */
-    size_t bit_index_in_parent_block(const ConfigBitId& bit_id) const; 
-
     /* Find the child block in a bitstream manager with a given name */
     ConfigBlockId find_child_block(const ConfigBlockId& block_id, const std::string& child_block_name) const;
 
@@ -98,6 +150,9 @@ class BitstreamManager {
     /* Reserve memory for a number of clocks */
     void reserve_blocks(const size_t& num_blocks);
 
+    /* Reserve memory for a number of bits */
+    void reserve_bits(const size_t& num_bits);
+
     /* Create a new block of configuration bits */
     ConfigBlockId create_block();
 
@@ -108,24 +163,32 @@ class BitstreamManager {
     void set_block_name(const ConfigBlockId& block_id,
                         const std::string& block_name);
 
+    /* Reserve child blocks for a block to be memory efficient */
+    void reserve_child_blocks(const ConfigBlockId& parent_block,
+                              const size_t& num_children);
+
     /* Set a block as a child block of another */
     void add_child_block(const ConfigBlockId& parent_block, const ConfigBlockId& child_block);
 
-    /* Add a configuration bit to a block */
-    void add_bit_to_block(const ConfigBlockId& block, const ConfigBitId& bit);
+    /* Add a bitstream to a block */
+    void add_block_bits(const ConfigBlockId& block,
+                        const std::vector<bool>& block_bitstream);
 
     /* Add a path id to a block */
     void add_path_id_to_block(const ConfigBlockId& block, const int& path_id);
+ 
+    /* Reserve input net ids for a block */
+    void reserve_block_input_net_ids(const ConfigBlockId& block, const size_t& num_input_net_ids);
 
     /* Add an input net id to a block */
     void add_input_net_id_to_block(const ConfigBlockId& block, const std::string& input_net_id);
 
+    /* Reserve output net ids for a block */
+    void reserve_block_output_net_ids(const ConfigBlockId& block, const size_t& num_output_net_ids);
+
     /* Add an output net id to a block */
     void add_output_net_id_to_block(const ConfigBlockId& block, const std::string& output_net_id);
 
-    /* Add share configuration bits to a configuration bit */
-    void add_shared_config_bit_values(const ConfigBitId& bit, const std::vector<bool>& shared_config_bits);
-
   public:  /* Public Validators */
     bool valid_bit_id(const ConfigBitId& bit_id) const;
 
@@ -135,8 +198,10 @@ class BitstreamManager {
 
   private: /* Internal data */
     /* Unique id of a block of bits in the Bitstream */
-    vtr::vector<ConfigBlockId, ConfigBlockId> block_ids_; 
-    vtr::vector<ConfigBlockId, std::vector<ConfigBitId>> block_bit_ids_; 
+    size_t num_blocks_; 
+    std::unordered_set<ConfigBlockId> invalid_block_ids_;
+    vtr::vector<ConfigBlockId, size_t> block_bit_id_lsbs_; 
+    vtr::vector<ConfigBlockId, short> block_bit_lengths_; 
 
     /* Back-annotation for the bits */
     /* Parent block of a bit in the Bitstream 
@@ -160,7 +225,7 @@ class BitstreamManager {
      *   -Bitstream manager will NOT check if the id is good for bitstream builders
      *    It just store the results
      */
-    vtr::vector<ConfigBlockId, int> block_path_ids_; 
+    vtr::vector<ConfigBlockId, short> block_path_ids_; 
 
     /* Net ids that are mapped to inputs and outputs of this block
      * 
@@ -172,12 +237,10 @@ class BitstreamManager {
     vtr::vector<ConfigBlockId, std::vector<std::string>> block_output_net_ids_; 
 
     /* Unique id of a bit in the Bitstream */
-    vtr::vector<ConfigBitId, ConfigBitId> bit_ids_; 
-    vtr::vector<ConfigBitId, ConfigBlockId> bit_parent_block_ids_;
+    size_t num_bits_; 
+    std::unordered_set<ConfigBitId> invalid_bit_ids_; 
     /* value of a bit in the Bitstream */
-    vtr::vector<ConfigBitId, bool> bit_values_;
-    /* value of a shared configuration bits in the Bitstream */
-    vtr::vector<ConfigBitId, std::vector<bool>> shared_config_bit_values_;
+    vtr::vector<ConfigBitId, char> bit_values_;
 };
 
 } /* end namespace openfpga */
diff --git a/libopenfpga/libfpgabitstream/src/read_xml_arch_bitstream.cpp b/libopenfpga/libfpgabitstream/src/read_xml_arch_bitstream.cpp
index 3895b85b6..04e0918f1 100644
--- a/libopenfpga/libfpgabitstream/src/read_xml_arch_bitstream.cpp
+++ b/libopenfpga/libfpgabitstream/src/read_xml_arch_bitstream.cpp
@@ -101,16 +101,17 @@ void rec_read_xml_bitstream_block(pugi::xml_node& xml_bitstream_block,
     }
 
     /* Find the child paths/nets */
+    std::vector<bool> block_bits;
     for (pugi::xml_node xml_bit : xml_bitstream.children()) {
       /* We only care child bitstream blocks here */
       if (xml_bit.name() != std::string("bit")) {
         bad_tag(xml_bit, loc_data, xml_bitstream, {"bit"});
       }
       const int& bit_value = get_attribute(xml_bit, "value", loc_data).as_int();
-      ConfigBitId bit = bitstream_manager.add_bit(1 == bit_value);
-      /* Link the bit to parent block */
-      bitstream_manager.add_bit_to_block(curr_block, bit);
-    } 
+      block_bits.push_back(1 == bit_value);
+    }
+    /* Link the bit to parent block */
+    bitstream_manager.add_block_bits(curr_block, block_bits);
   }
   
   /* Go recursively: find all the child blocks and parse */
diff --git a/libopenfpga/libopenfpgashell/src/shell.h b/libopenfpga/libopenfpgashell/src/shell.h
index 1a49b313c..67dd4356d 100644
--- a/libopenfpga/libopenfpgashell/src/shell.h
+++ b/libopenfpga/libopenfpgashell/src/shell.h
@@ -5,6 +5,7 @@
 #include <map>
 #include <vector>
 #include <functional>
+#include <ctime>
 
 #include "vtr_vector.h"
 #include "vtr_range.h"
@@ -211,6 +212,9 @@ class Shell {
     std::map<std::string, ShellCommandId> command_name2ids_;
     std::map<std::string, ShellCommandClassId> command_class2ids_;
     vtr::vector<ShellCommandClassId, std::vector<ShellCommandId>> commands_by_classes_;  
+
+    /* Timer */
+    std::clock_t time_start_;
 };
 
 } /* End namespace openfpga */
diff --git a/libopenfpga/libopenfpgashell/src/shell.tpp b/libopenfpga/libopenfpgashell/src/shell.tpp
index 219287ee1..7c0ff7ce6 100644
--- a/libopenfpga/libopenfpgashell/src/shell.tpp
+++ b/libopenfpga/libopenfpgashell/src/shell.tpp
@@ -28,6 +28,7 @@ namespace openfpga {
 template<class T>
 Shell<T>::Shell(const char* name) {
   name_ = std::string(name);
+  time_start_ = 0;
 }
 
 /************************************************************************
@@ -241,6 +242,9 @@ ShellCommandClassId Shell<T>::add_command_class(const char* name) {
 template <class T>
 void Shell<T>::run_interactive_mode(T& context, const bool& quiet_mode) {
   if (false == quiet_mode) {
+    /* Reset timer since it does not come from another mode */
+    time_start_ = std::clock();
+
     VTR_LOG("Start interactive mode of %s...\n",
             name().c_str());
 
@@ -270,6 +274,8 @@ void Shell<T>::run_interactive_mode(T& context, const bool& quiet_mode) {
 template <class T>
 void Shell<T>::run_script_mode(const char* script_file_name, T& context) {
 
+  time_start_ = std::clock();
+
   VTR_LOG("Reading script file %s...\n", script_file_name);
 
   /* Print the title of the shell */
@@ -419,6 +425,9 @@ void Shell<T>::exit() const {
   VTR_LOG("\nFinish execution with %d errors\n",
             num_err);
 
+  VTR_LOG("\nThe entire OpenFPGA flow took %g seconds\n",
+          (double)(std::clock() - time_start_) / (double)CLOCKS_PER_SEC);
+
   VTR_LOG("\nThank you for using %s!\n",
           name().c_str());
 
diff --git a/libopenfpga/libopenfpgautil/src/openfpga_decode.cpp b/libopenfpga/libopenfpgautil/src/openfpga_decode.cpp
index 06b3487b0..168f98e42 100644
--- a/libopenfpga/libopenfpgautil/src/openfpga_decode.cpp
+++ b/libopenfpga/libopenfpgautil/src/openfpga_decode.cpp
@@ -73,4 +73,59 @@ std::vector<size_t> itobin_vec(const size_t& in_int,
   return ret;
 }
 
+/******************************************************************** 
+ * Converter an integer to a binary vector 
+ * For example: 
+ *   Input integer: 4
+ *   Binary length : 3
+ *   Output:
+ *     index | 0 | 1 | 2
+ *     ret   | 0 | 0 | 1 
+ *
+ * This function is optimized to return a vector of char
+ * which has a smaller memory footprint than size_t
+ ********************************************************************/
+std::vector<char> itobin_charvec(const size_t& in_int,
+                                 const size_t& bin_len) {
+  std::vector<char> ret(bin_len, '0');
+
+  /* Make sure we do not have any overflow! */
+  VTR_ASSERT ( (in_int < pow(2., bin_len)) );
+  
+  size_t temp = in_int;
+  for (size_t i = 0; i < bin_len; i++) {
+    if (1 == temp % 2) { 
+      ret[i] = '1'; /* Keep a good sequence of bits */
+    }
+    temp = temp / 2;
+  }
+ 
+  return ret;
+}
+
+/******************************************************************** 
+ * Converter a binary vector to an integer
+ * For example: 
+ *   Binary length : 3
+ *   Input:
+ *     index | 0 | 1 | 2
+ *     ret   | 0 | 0 | 1 
+ *
+ *   Output integer: 4
+ *
+ * This function is optimized to return a vector of char
+ * which has a smaller memory footprint than size_t
+ ********************************************************************/
+size_t bintoi_charvec(const std::vector<char>& bin) {
+  size_t ret = 0;
+
+  for (size_t i = 0; i < bin.size(); ++i) {
+    if ('1' == bin[i]) {
+      ret += pow(2., i);
+    }
+  }
+
+  return ret;
+}
+
 } /* end namespace openfpga */
diff --git a/libopenfpga/libopenfpgautil/src/openfpga_decode.h b/libopenfpga/libopenfpgautil/src/openfpga_decode.h
index c79254f63..ab6778c86 100644
--- a/libopenfpga/libopenfpgautil/src/openfpga_decode.h
+++ b/libopenfpga/libopenfpgautil/src/openfpga_decode.h
@@ -18,6 +18,11 @@ std::vector<size_t> ito1hot_vec(const size_t& in_int,
 std::vector<size_t> itobin_vec(const size_t& in_int,
                                const size_t& bin_len);
 
+std::vector<char> itobin_charvec(const size_t& in_int,
+                                 const size_t& bin_len);
+
+size_t bintoi_charvec(const std::vector<char>& bin);
+
 } /* namespace openfpga ends */
 
 #endif
diff --git a/openfpga/src/base/openfpga_build_fabric.cpp b/openfpga/src/base/openfpga_build_fabric.cpp
index adbe8fce6..df407e949 100644
--- a/openfpga/src/base/openfpga_build_fabric.cpp
+++ b/openfpga/src/base/openfpga_build_fabric.cpp
@@ -67,6 +67,7 @@ void compress_routing_hierarchy(OpenfpgaContext& openfpga_ctx,
 int build_fabric(OpenfpgaContext& openfpga_ctx,
                  const Command& cmd, const CommandContext& cmd_context) { 
 
+  CommandOptionId opt_frame_view = cmd.option("frame_view");
   CommandOptionId opt_compress_routing = cmd.option("compress_routing");
   CommandOptionId opt_duplicate_grid_pin = cmd.option("duplicate_grid_pin");
   CommandOptionId opt_gen_random_fabric_key = cmd.option("generate_random_fabric_key");
@@ -96,6 +97,7 @@ int build_fabric(OpenfpgaContext& openfpga_ctx,
                                                                   openfpga_ctx.mutable_decoder_lib(),
                                                                   const_cast<const OpenfpgaContext&>(openfpga_ctx),
                                                                   g_vpr_ctx.device(),
+                                                                  cmd_context.option_enable(cmd, opt_frame_view),
                                                                   cmd_context.option_enable(cmd, opt_compress_routing),
                                                                   cmd_context.option_enable(cmd, opt_duplicate_grid_pin),
                                                                   predefined_fabric_key,
diff --git a/openfpga/src/base/openfpga_naming.cpp b/openfpga/src/base/openfpga_naming.cpp
index 84366b1ab..f4a72ff61 100644
--- a/openfpga/src/base/openfpga_naming.cpp
+++ b/openfpga/src/base/openfpga_naming.cpp
@@ -134,7 +134,7 @@ std::string generate_mux_branch_subckt_name(const CircuitLibrary& circuit_lib,
  ***********************************************/
 std::string generate_mux_local_decoder_subckt_name(const size_t& addr_size, 
                                                    const size_t& data_size) {
-  std::string subckt_name = "decoder";
+  std::string subckt_name = "local_encoder";
   subckt_name += std::to_string(addr_size);
   subckt_name += "to";
   subckt_name += std::to_string(data_size);
diff --git a/openfpga/src/base/openfpga_setup_command.cpp b/openfpga/src/base/openfpga_setup_command.cpp
index ca5864b2e..eb0e0430d 100644
--- a/openfpga/src/base/openfpga_setup_command.cpp
+++ b/openfpga/src/base/openfpga_setup_command.cpp
@@ -267,6 +267,9 @@ ShellCommandId add_openfpga_build_fabric_command(openfpga::Shell<OpenfpgaContext
 
   Command shell_cmd("build_fabric");
 
+  /* Add an option '--frame_view' */
+  shell_cmd.add_option("frame_view", false, "Build only frame view of the fabric (nets are skipped)");
+
   /* Add an option '--compress_routing' */
   shell_cmd.add_option("compress_routing", false, "Compress the number of unique routing modules by identifying the unique GSBs");
 
diff --git a/openfpga/src/fabric/build_device_module.cpp b/openfpga/src/fabric/build_device_module.cpp
index b988e1e29..4c877cb86 100644
--- a/openfpga/src/fabric/build_device_module.cpp
+++ b/openfpga/src/fabric/build_device_module.cpp
@@ -30,6 +30,7 @@ ModuleManager build_device_module_graph(IoLocationMap& io_location_map,
                                         DecoderLibrary& decoder_lib,
                                         const OpenfpgaContext& openfpga_ctx,
                                         const DeviceContext& vpr_device_ctx,
+                                        const bool& frame_view,
                                         const bool& compress_routing,
                                         const bool& duplicate_grid_pin,
                                         const FabricKey& fabric_key,
@@ -118,7 +119,7 @@ ModuleManager build_device_module_graph(IoLocationMap& io_location_map,
                    openfpga_ctx.arch().arch_direct, 
                    openfpga_ctx.arch().config_protocol.type(),
                    sram_model,
-                   compress_routing, duplicate_grid_pin,
+                   frame_view, compress_routing, duplicate_grid_pin,
                    fabric_key, generate_random_fabric_key);
 
   /* Now a critical correction has to be done!
diff --git a/openfpga/src/fabric/build_device_module.h b/openfpga/src/fabric/build_device_module.h
index 34d30b997..641cfe779 100644
--- a/openfpga/src/fabric/build_device_module.h
+++ b/openfpga/src/fabric/build_device_module.h
@@ -19,6 +19,7 @@ ModuleManager build_device_module_graph(IoLocationMap& io_location_map,
                                         DecoderLibrary& decoder_lib,
                                         const OpenfpgaContext& openfpga_ctx,
                                         const DeviceContext& vpr_device_ctx,
+                                        const bool& frame_view,
                                         const bool& compress_routing,
                                         const bool& duplicate_grid_pin,
                                         const FabricKey& fabric_key,
diff --git a/openfpga/src/fabric/build_top_module.cpp b/openfpga/src/fabric/build_top_module.cpp
index edb25941e..e83ccae95 100644
--- a/openfpga/src/fabric/build_top_module.cpp
+++ b/openfpga/src/fabric/build_top_module.cpp
@@ -329,6 +329,7 @@ void build_top_module(ModuleManager& module_manager,
                       const ArchDirect& arch_direct,
                       const e_config_protocol_type& sram_orgz_type,
                       const CircuitModelId& sram_model,
+                      const bool& frame_view,
                       const bool& compact_routing_hierarchy,
                       const bool& duplicate_grid_pin,
                       const FabricKey& fabric_key,
@@ -351,18 +352,23 @@ void build_top_module(ModuleManager& module_manager,
   cb_instance_ids[CHANX] = add_top_module_connection_block_instances(module_manager, top_module, device_rr_gsb, CHANX, compact_routing_hierarchy);
   cb_instance_ids[CHANY] = add_top_module_connection_block_instances(module_manager, top_module, device_rr_gsb, CHANY, compact_routing_hierarchy);
 
-  /* Reserve nets to be memory efficient */
-  reserve_module_manager_module_nets(module_manager, top_module);
+  /* Add nets when we need a complete fabric modeling,
+   * which is required by downstream functions
+   */
+  if (false == frame_view) {
+    /* Reserve nets to be memory efficient */
+    reserve_module_manager_module_nets(module_manager, top_module);
 
-  /* Add module nets to connect the sub modules */
-  add_top_module_nets_connect_grids_and_gsbs(module_manager, top_module, 
-                                             grids, grid_instance_ids, 
-                                             rr_graph, device_rr_gsb, sb_instance_ids, cb_instance_ids,
-                                             compact_routing_hierarchy, duplicate_grid_pin);
-  /* Add inter-CLB direct connections */
-  add_top_module_nets_tile_direct_connections(module_manager, top_module, circuit_lib, 
-                                              grids, grid_instance_ids,
-                                              tile_direct, arch_direct);
+    /* Add module nets to connect the sub modules */
+    add_top_module_nets_connect_grids_and_gsbs(module_manager, top_module, 
+                                               grids, grid_instance_ids, 
+                                               rr_graph, device_rr_gsb, sb_instance_ids, cb_instance_ids,
+                                               compact_routing_hierarchy, duplicate_grid_pin);
+    /* Add inter-CLB direct connections */
+    add_top_module_nets_tile_direct_connections(module_manager, top_module, circuit_lib, 
+                                                grids, grid_instance_ids,
+                                                tile_direct, arch_direct);
+  }
 
   /* Add global ports to the pb_module:
    * This is a much easier job after adding sub modules (instances), 
diff --git a/openfpga/src/fabric/build_top_module.h b/openfpga/src/fabric/build_top_module.h
index 50bf6e611..2dcda9e74 100644
--- a/openfpga/src/fabric/build_top_module.h
+++ b/openfpga/src/fabric/build_top_module.h
@@ -36,6 +36,7 @@ void build_top_module(ModuleManager& module_manager,
                       const ArchDirect& arch_direct,
                       const e_config_protocol_type& sram_orgz_type,
                       const CircuitModelId& sram_model,
+                      const bool& frame_view,
                       const bool& compact_routing_hierarchy,
                       const bool& duplicate_grid_pin,
                       const FabricKey& fabric_key,
diff --git a/openfpga/src/fpga_bitstream/build_device_bitstream.cpp b/openfpga/src/fpga_bitstream/build_device_bitstream.cpp
index 6d13dfe6f..3f38e03a7 100644
--- a/openfpga/src/fpga_bitstream/build_device_bitstream.cpp
+++ b/openfpga/src/fpga_bitstream/build_device_bitstream.cpp
@@ -20,6 +20,82 @@
 /* begin namespace openfpga */
 namespace openfpga {
 
+/********************************************************************
+ * Estimate the number of blocks to be added to the whole device bitstream
+ * This function will recursively walk through the module graph 
+ * from the specified top module and count the number of configurable children
+ * which are the blocks that will be added to the bitstream manager
+ *******************************************************************/
+static 
+size_t rec_estimate_device_bitstream_num_blocks(const ModuleManager& module_manager,
+                                                const ModuleId& top_module) {
+  size_t num_blocks = 0;
+
+  /* Those child modules which have no children are
+   * actually configurable memory elements
+   * We skip them in couting
+   */
+  if (0 == module_manager.configurable_children(top_module).size()) {
+    return 0;
+  }
+
+  size_t num_configurable_children = module_manager.configurable_children(top_module).size();
+  for (size_t ichild = 0; ichild < num_configurable_children; ++ichild) {
+    ModuleId child_module = module_manager.configurable_children(top_module)[ichild];
+    num_blocks += rec_estimate_device_bitstream_num_blocks(module_manager, child_module);
+  }
+
+  /* Add the number of blocks at current level */
+  num_blocks++;
+
+  return num_blocks;
+}
+
+/********************************************************************
+ * Estimate the number of configuration bits to be added to the whole device bitstream
+ * This function will recursively walk through the module graph 
+ * from the specified top module and count the number of leaf configurable children
+ * which are the bits that will be added to the bitstream manager
+ *******************************************************************/
+static 
+size_t rec_estimate_device_bitstream_num_bits(const ModuleManager& module_manager,
+                                              const ModuleId& top_module,
+                                              const e_config_protocol_type& config_protocol_type) {
+  size_t num_bits = 0;
+
+  /* If a child module has no configurable children, this is a leaf node 
+   * We can count it in. Otherwise, we should go recursively.
+   */
+  if (0 == module_manager.configurable_children(top_module).size()) {
+    return 1;
+  }
+
+  size_t num_configurable_children = module_manager.configurable_children(top_module).size();
+  /* Frame-based configuration protocol will have 1 decoder
+   * if there are more than 1 configurable children
+   */
+  if ( (CONFIG_MEM_FRAME_BASED == config_protocol_type)
+    && (2 <= num_configurable_children)) {
+    num_configurable_children--;
+  }
+
+  /* Memory configuration protocol will have 2 decoders
+   * at the top-level
+   */
+  if (CONFIG_MEM_MEMORY_BANK == config_protocol_type) {
+    std::string top_block_name = generate_fpga_top_module_name();
+    if (top_module == module_manager.find_module(top_block_name)) {
+      num_configurable_children -= 2;
+    }
+  }
+  for (size_t ichild = 0; ichild < num_configurable_children; ++ichild) {
+    ModuleId child_module = module_manager.configurable_children(top_module)[ichild];
+    num_bits += rec_estimate_device_bitstream_num_bits(module_manager, child_module, config_protocol_type);
+  }
+
+  return num_bits;
+}
+
 /********************************************************************
  * A top-level function to build a bistream from the FPGA device
  * 1. It will organize the bitstream w.r.t. the hierarchy of module graphs 
@@ -52,6 +128,25 @@ BitstreamManager build_device_bitstream(const VprContext& vpr_ctx,
    */
   std::string top_block_name = generate_fpga_top_module_name();
   ConfigBlockId top_block = bitstream_manager.add_block(top_block_name);
+  const ModuleId& top_module = openfpga_ctx.module_graph().find_module(top_block_name);
+  VTR_ASSERT(true == openfpga_ctx.module_graph().valid_module_id(top_module));
+
+  /* Estimate the number of blocks to be added to the database */
+  size_t num_blocks_to_reserve = rec_estimate_device_bitstream_num_blocks(openfpga_ctx.module_graph(),
+                                                                          top_module);
+  bitstream_manager.reserve_blocks(num_blocks_to_reserve);
+  VTR_LOGV(verbose, "Reserved %lu configurable blocks\n", num_blocks_to_reserve);
+
+  /* Estimate the number of bits to be added to the database */
+  size_t num_bits_to_reserve = rec_estimate_device_bitstream_num_bits(openfpga_ctx.module_graph(),
+                                                                      top_module,
+                                                                      openfpga_ctx.arch().config_protocol.type());
+  bitstream_manager.reserve_bits(num_bits_to_reserve);
+  VTR_LOGV(verbose, "Reserved %lu configuration bits\n", num_bits_to_reserve);
+
+  /* Reserve child blocks for the top level block */
+  bitstream_manager.reserve_child_blocks(top_block,
+                                         openfpga_ctx.module_graph().configurable_children(top_module).size());
 
   /* Create bitstream from grids */
   VTR_LOGV(verbose, "Building grid bitstream...\n");
@@ -80,7 +175,13 @@ BitstreamManager build_device_bitstream(const VprContext& vpr_ctx,
                           openfpga_ctx.device_rr_gsb());
   VTR_LOGV(verbose, "Done\n");
 
-  VTR_LOGV(verbose, "Decoded %lu configuration bits\n", bitstream_manager.bits().size());
+  VTR_LOGV(verbose,
+           "Decoded %lu configuration bits into %lu blocks\n",
+           bitstream_manager.num_bits(),
+           bitstream_manager.num_blocks());
+
+  //VTR_ASSERT(num_blocks_to_reserve == bitstream_manager.num_blocks());
+  //VTR_ASSERT(num_bits_to_reserve == bitstream_manager.num_bits());
 
   return bitstream_manager;
 }
diff --git a/openfpga/src/fpga_bitstream/build_fabric_bitstream.cpp b/openfpga/src/fpga_bitstream/build_fabric_bitstream.cpp
index 240f19028..05e93d22a 100644
--- a/openfpga/src/fpga_bitstream/build_fabric_bitstream.cpp
+++ b/openfpga/src/fpga_bitstream/build_fabric_bitstream.cpp
@@ -158,11 +158,11 @@ void rec_build_module_fabric_dependent_memory_bank_bitstream(const BitstreamMana
   
     /* Find BL address */
     size_t cur_bl_index = std::floor(cur_mem_index / num_bls);
-    std::vector<size_t> bl_addr_bits_vec = itobin_vec(cur_bl_index, bl_addr_size);
+    std::vector<char> bl_addr_bits_vec = itobin_charvec(cur_bl_index, bl_addr_size);
 
     /* Find WL address */
     size_t cur_wl_index = cur_mem_index % num_wls;
-    std::vector<size_t> wl_addr_bits_vec = itobin_vec(cur_wl_index, wl_addr_size);
+    std::vector<char> wl_addr_bits_vec = itobin_charvec(cur_wl_index, wl_addr_size);
 
     /* Set BL address */
     fabric_bitstream.set_bit_bl_address(fabric_bit, bl_addr_bits_vec);
@@ -206,7 +206,7 @@ void rec_build_module_fabric_dependent_frame_bitstream(const BitstreamManager& b
                                                        const std::vector<ConfigBlockId>& parent_blocks,
                                                        const ModuleManager& module_manager,
                                                        const std::vector<ModuleId>& parent_modules,
-                                                       const std::vector<size_t>& addr_code,
+                                                       const std::vector<char>& addr_code,
                                                        FabricBitstream& fabric_bitstream) {
 
   /* Depth-first search: if we have any children in the parent_block, 
@@ -272,13 +272,13 @@ void rec_build_module_fabric_dependent_frame_bitstream(const BitstreamManager& b
       child_modules.push_back(child_module);
 
       /* Set address, apply binary conversion from the first to the last element in the address list */
-      std::vector<size_t> child_addr_code = addr_code;
+      std::vector<char> child_addr_code = addr_code;
 
       if (true == add_addr_code) { 
         /* Find the address port from the decoder module */
         const ModulePortId& decoder_addr_port_id = module_manager.find_module_port(decoder_module, std::string(DECODER_ADDRESS_PORT_NAME));
         const BasicPort& decoder_addr_port = module_manager.module_port(decoder_module, decoder_addr_port_id);
-        std::vector<size_t> addr_bits_vec = itobin_vec(child_id, decoder_addr_port.get_width());
+        std::vector<char> addr_bits_vec = itobin_charvec(child_id, decoder_addr_port.get_width());
 
         child_addr_code.insert(child_addr_code.begin(), addr_bits_vec.begin(), addr_bits_vec.end());
 
@@ -316,7 +316,7 @@ void rec_build_module_fabric_dependent_frame_bitstream(const BitstreamManager& b
         const ModulePortId& child_addr_port_id = module_manager.find_module_port(child_module, std::string(DECODER_ADDRESS_PORT_NAME));
         const BasicPort& child_addr_port = module_manager.module_port(child_module, child_addr_port_id);
         if (0 < max_child_addr_code_size - child_addr_port.get_width()) {
-          std::vector<size_t> dummy_codes(max_child_addr_code_size - child_addr_port.get_width(), 0);
+          std::vector<char> dummy_codes(max_child_addr_code_size - child_addr_port.get_width(), '0');
           child_addr_code.insert(child_addr_code.begin(), dummy_codes.begin(), dummy_codes.end());
         }
       }
@@ -349,9 +349,9 @@ void rec_build_module_fabric_dependent_frame_bitstream(const BitstreamManager& b
   for (size_t ibit = 0; ibit < bitstream_manager.block_bits(parent_blocks.back()).size(); ++ibit) {
     
     ConfigBitId config_bit = bitstream_manager.block_bits(parent_blocks.back())[ibit];
-    std::vector<size_t> addr_bits_vec = itobin_vec(ibit, decoder_addr_port.get_width());
+    std::vector<char> addr_bits_vec = itobin_charvec(ibit, decoder_addr_port.get_width());
 
-    std::vector<size_t> child_addr_code = addr_code;
+    std::vector<char> child_addr_code = addr_code;
 
     child_addr_code.insert(child_addr_code.begin(), addr_bits_vec.begin(), addr_bits_vec.end());
 
@@ -379,12 +379,18 @@ void build_module_fabric_dependent_bitstream(const ConfigProtocol& config_protoc
 
   switch (config_protocol.type()) {
   case CONFIG_MEM_STANDALONE: {
+    /* Reserve bits before build-up */
+    fabric_bitstream.reserve_bits(bitstream_manager.num_bits());
+
     rec_build_module_fabric_dependent_chain_bitstream(bitstream_manager, top_block,
                                                       module_manager, top_module, 
                                                       fabric_bitstream);
     break;
   }
   case CONFIG_MEM_SCAN_CHAIN: { 
+    /* Reserve bits before build-up */
+    fabric_bitstream.reserve_bits(bitstream_manager.num_bits());
+
     rec_build_module_fabric_dependent_chain_bitstream(bitstream_manager, top_block,
                                                       module_manager, top_module, 
                                                       fabric_bitstream);
@@ -392,6 +398,7 @@ void build_module_fabric_dependent_bitstream(const ConfigProtocol& config_protoc
     break;
   }
   case CONFIG_MEM_MEMORY_BANK: { 
+
     size_t cur_mem_index = 0;
     /* Find BL address port size */
     ModulePortId bl_addr_port = module_manager.find_module_port(top_module, std::string(DECODER_BL_ADDRESS_PORT_NAME));
@@ -415,6 +422,13 @@ void build_module_fabric_dependent_bitstream(const ConfigProtocol& config_protoc
     ModulePortId wl_port = module_manager.find_module_port(wl_decoder_module, std::string(DECODER_DATA_OUT_PORT_NAME));
     BasicPort wl_port_info = module_manager.module_port(wl_decoder_module, wl_port);
 
+    /* Reserve bits before build-up */
+    fabric_bitstream.set_use_address(true);
+    fabric_bitstream.set_use_wl_address(true);
+    fabric_bitstream.set_bl_address_length(bl_addr_port_info.get_width());
+    fabric_bitstream.set_wl_address_length(wl_addr_port_info.get_width());
+    fabric_bitstream.reserve_bits(bitstream_manager.num_bits());
+
     rec_build_module_fabric_dependent_memory_bank_bitstream(bitstream_manager, top_block,
                                                             module_manager, top_module, top_module, 
                                                             bl_addr_port_info.get_width(),
@@ -425,11 +439,21 @@ void build_module_fabric_dependent_bitstream(const ConfigProtocol& config_protoc
     break;
   }
   case CONFIG_MEM_FRAME_BASED: {
+
+    /* Find address port size */
+    ModulePortId addr_port = module_manager.find_module_port(top_module, std::string(DECODER_ADDRESS_PORT_NAME));
+    BasicPort addr_port_info = module_manager.module_port(top_module, addr_port);
+
+    /* Reserve bits before build-up */
+    fabric_bitstream.set_use_address(true);
+    fabric_bitstream.reserve_bits(bitstream_manager.num_bits());
+    fabric_bitstream.set_address_length(addr_port_info.get_width());
+
     rec_build_module_fabric_dependent_frame_bitstream(bitstream_manager,
                                                       std::vector<ConfigBlockId>(1, top_block),
                                                       module_manager,
                                                       std::vector<ModuleId>(1, top_module),
-                                                      std::vector<size_t>(),
+													  std::vector<char>(),
                                                       fabric_bitstream);
     break;
   }
@@ -459,7 +483,7 @@ void build_module_fabric_dependent_bitstream(const ConfigProtocol& config_protoc
    */
 
   /* Ensure our fabric bitstream is in the same size as device bistream */
-  VTR_ASSERT(bitstream_manager.bits().size() == fabric_bitstream.bits().size());
+  VTR_ASSERT(bitstream_manager.num_bits() == fabric_bitstream.num_bits());
 }
 
 /********************************************************************
@@ -495,6 +519,7 @@ FabricBitstream build_fabric_dependent_bitstream(const BitstreamManager& bitstre
   VTR_ASSERT(1 == top_block.size());
   VTR_ASSERT(0 == top_module_name.compare(bitstream_manager.block_name(top_block[0])));
 
+  /* Start build-up formally */
   build_module_fabric_dependent_bitstream(config_protocol,
                                           bitstream_manager, top_block[0],
                                           module_manager, top_module, 
@@ -502,7 +527,7 @@ FabricBitstream build_fabric_dependent_bitstream(const BitstreamManager& bitstre
 
   VTR_LOGV(verbose,
            "Built %lu configuration bits for fabric\n",
-           fabric_bitstream.bits().size());
+           fabric_bitstream.num_bits());
 
   return fabric_bitstream;
 }
diff --git a/openfpga/src/fpga_bitstream/build_grid_bitstream.cpp b/openfpga/src/fpga_bitstream/build_grid_bitstream.cpp
index c3de6cbfe..436c04697 100644
--- a/openfpga/src/fpga_bitstream/build_grid_bitstream.cpp
+++ b/openfpga/src/fpga_bitstream/build_grid_bitstream.cpp
@@ -106,11 +106,7 @@ void build_primitive_bitstream(BitstreamManager& bitstream_manager,
   bitstream_manager.add_child_block(parent_configurable_block, mem_block);
 
   /* Add the bitstream to the bitstream manager */
-  for (const bool& bit : mode_select_bitstream) {
-    ConfigBitId config_bit = bitstream_manager.add_bit(bit);
-    /* Link the memory bits to the mux mem block */
-    bitstream_manager.add_bit_to_block(mem_block, config_bit);
-  }
+  bitstream_manager.add_block_bits(mem_block, mode_select_bitstream);
 }
 
 /********************************************************************
@@ -214,13 +210,10 @@ void build_physical_block_pin_interc_bitstream(BitstreamManager& bitstream_manag
     VTR_ASSERT(mux_bitstream.size() == module_manager.module_port(mux_mem_module, mux_mem_out_port_id).get_width());
   
     /* Add the bistream to the bitstream manager */
-    for (const bool& bit : mux_bitstream) {
-      ConfigBitId config_bit = bitstream_manager.add_bit(bit);
-      /* Link the memory bits to the mux mem block */
-      bitstream_manager.add_bit_to_block(mux_mem_block, config_bit);
-    }
+    bitstream_manager.add_block_bits(mux_mem_block, mux_bitstream);
     /* Record path ids, input and output nets */
     bitstream_manager.add_path_id_to_block(mux_mem_block, mux_input_pin_id);
+    bitstream_manager.reserve_block_input_net_ids(mux_mem_block, input_nets.size());
     for (const AtomNetId& input_net : input_nets) {
       if (true == atom_ctx.nlist.valid_net_id(input_net)) {
         bitstream_manager.add_input_net_id_to_block(mux_mem_block, atom_ctx.nlist.net_name(input_net));
@@ -229,6 +222,7 @@ void build_physical_block_pin_interc_bitstream(BitstreamManager& bitstream_manag
       }
     }
     if (true == atom_ctx.nlist.valid_net_id(output_net)) {
+    bitstream_manager.reserve_block_output_net_ids(mux_mem_block, 1);
       bitstream_manager.add_output_net_id_to_block(mux_mem_block, atom_ctx.nlist.net_name(output_net));
     } else {
       bitstream_manager.add_output_net_id_to_block(mux_mem_block, std::string("unmapped"));
@@ -465,11 +459,7 @@ void build_lut_bitstream(BitstreamManager& bitstream_manager,
   bitstream_manager.add_child_block(parent_configurable_block, mem_block);
 
   /* Add the bitstream to the bitstream manager */
-  for (const bool& bit : lut_bitstream) {
-    ConfigBitId config_bit = bitstream_manager.add_bit(bit);
-    /* Link the memory bits to the mux mem block */
-    bitstream_manager.add_bit_to_block(mem_block, config_bit);
-  }
+  bitstream_manager.add_block_bits(mem_block, lut_bitstream);
 }
 
 /********************************************************************
diff --git a/openfpga/src/fpga_bitstream/build_routing_bitstream.cpp b/openfpga/src/fpga_bitstream/build_routing_bitstream.cpp
index 457b1d004..1e6b8d3c6 100644
--- a/openfpga/src/fpga_bitstream/build_routing_bitstream.cpp
+++ b/openfpga/src/fpga_bitstream/build_routing_bitstream.cpp
@@ -98,13 +98,10 @@ void build_switch_block_mux_bitstream(BitstreamManager& bitstream_manager,
   VTR_ASSERT(mux_bitstream.size() == module_manager.module_port(mux_mem_module, mux_mem_out_port_id).get_width());
 
   /* Add the bistream to the bitstream manager */
-  for (const bool& bit : mux_bitstream) {
-    ConfigBitId config_bit = bitstream_manager.add_bit(bit);
-    /* Link the memory bits to the mux mem block */
-    bitstream_manager.add_bit_to_block(mux_mem_block, config_bit);
-  }
+  bitstream_manager.add_block_bits(mux_mem_block, mux_bitstream);
   /* Record path ids, input and output nets */
   bitstream_manager.add_path_id_to_block(mux_mem_block, path_id);
+  bitstream_manager.reserve_block_input_net_ids(mux_mem_block, input_nets.size());
   for (const ClusterNetId& input_net : input_nets) {
     AtomNetId input_atom_net = atom_ctx.lookup.atom_net(input_net);
     if (true == atom_ctx.nlist.valid_net_id(input_atom_net)) {
@@ -114,6 +111,7 @@ void build_switch_block_mux_bitstream(BitstreamManager& bitstream_manager,
     }
   }
   AtomNetId output_atom_net = atom_ctx.lookup.atom_net(output_net);
+  bitstream_manager.reserve_block_output_net_ids(mux_mem_block, 1);
   if (true == atom_ctx.nlist.valid_net_id(output_atom_net)) {
     bitstream_manager.add_output_net_id_to_block(mux_mem_block, atom_ctx.nlist.net_name(output_atom_net));
   } else {
@@ -289,13 +287,10 @@ void build_connection_block_mux_bitstream(BitstreamManager& bitstream_manager,
   VTR_ASSERT(mux_bitstream.size() == module_manager.module_port(mux_mem_module, mux_mem_out_port_id).get_width());
 
   /* Add the bistream to the bitstream manager */
-  for (const bool& bit : mux_bitstream) {
-    ConfigBitId config_bit = bitstream_manager.add_bit(bit);
-    /* Link the memory bits to the mux mem block */
-    bitstream_manager.add_bit_to_block(mux_mem_block, config_bit);
-  }
+  bitstream_manager.add_block_bits(mux_mem_block, mux_bitstream);
   /* Record path ids, input and output nets */
   bitstream_manager.add_path_id_to_block(mux_mem_block, path_id);
+  bitstream_manager.reserve_block_input_net_ids(mux_mem_block, input_nets.size());
   for (const ClusterNetId& input_net : input_nets) {
     AtomNetId input_atom_net = atom_ctx.lookup.atom_net(input_net);
     if (true == atom_ctx.nlist.valid_net_id(input_atom_net)) {
@@ -305,6 +300,7 @@ void build_connection_block_mux_bitstream(BitstreamManager& bitstream_manager,
     }
   }
   AtomNetId output_atom_net = atom_ctx.lookup.atom_net(output_net);
+  bitstream_manager.reserve_block_output_net_ids(mux_mem_block, 1);
   if (true == atom_ctx.nlist.valid_net_id(output_atom_net)) {
     bitstream_manager.add_output_net_id_to_block(mux_mem_block, atom_ctx.nlist.net_name(output_atom_net));
   } else {
diff --git a/openfpga/src/fpga_bitstream/fabric_bitstream.cpp b/openfpga/src/fpga_bitstream/fabric_bitstream.cpp
index 1e318a530..750cc0296 100644
--- a/openfpga/src/fpga_bitstream/fabric_bitstream.cpp
+++ b/openfpga/src/fpga_bitstream/fabric_bitstream.cpp
@@ -4,17 +4,33 @@
 #include <algorithm>
 
 #include "vtr_assert.h"
+#include "openfpga_decode.h"
 #include "fabric_bitstream.h"
 
 /* begin namespace openfpga */
 namespace openfpga {
 
+/**************************************************
+ * Public Constructor
+ *************************************************/
+FabricBitstream::FabricBitstream() {
+  num_bits_ = 0;
+  invalid_bit_ids_.clear();
+  address_length_ = 0;
+  wl_address_length_ = 0;
+}
+
 /**************************************************
  * Public Accessors : Aggregates
  *************************************************/
+size_t FabricBitstream::num_bits() const {
+  return num_bits_;
+}
+
 /* Find all the configuration bits */
 FabricBitstream::fabric_bit_range FabricBitstream::bits() const {
-  return vtr::make_range(bit_ids_.begin(), bit_ids_.end());
+  return vtr::make_range(fabric_bit_iterator(FabricBitId(0), invalid_bit_ids_),
+                         fabric_bit_iterator(FabricBitId(num_bits_), invalid_bit_ids_));
 }
 
 /******************************************************************************
@@ -27,79 +43,145 @@ ConfigBitId FabricBitstream::config_bit(const FabricBitId& bit_id) const {
   return config_bit_ids_[bit_id];
 }
 
-std::vector<size_t> FabricBitstream::bit_address(const FabricBitId& bit_id) const {
+std::vector<char> FabricBitstream::bit_address(const FabricBitId& bit_id) const {
   /* Ensure a valid id */
   VTR_ASSERT(true == valid_bit_id(bit_id));
+  VTR_ASSERT(true == use_address_);
 
-  return bit_addresses_[bit_id][0];
+  return itobin_charvec(bit_addresses_[bit_id], address_length_);
 }
 
-std::vector<size_t> FabricBitstream::bit_bl_address(const FabricBitId& bit_id) const {
+std::vector<char> FabricBitstream::bit_bl_address(const FabricBitId& bit_id) const {
   return bit_address(bit_id);
 }
 
-std::vector<size_t> FabricBitstream::bit_wl_address(const FabricBitId& bit_id) const {
+std::vector<char> FabricBitstream::bit_wl_address(const FabricBitId& bit_id) const {
   /* Ensure a valid id */
   VTR_ASSERT(true == valid_bit_id(bit_id));
+  VTR_ASSERT(true == use_address_);
+  VTR_ASSERT(true == use_wl_address_);
 
-  return bit_addresses_[bit_id][1];
+  return itobin_charvec(bit_wl_addresses_[bit_id], wl_address_length_);
 }
 
-bool FabricBitstream::bit_din(const FabricBitId& bit_id) const {
+char FabricBitstream::bit_din(const FabricBitId& bit_id) const {
   /* Ensure a valid id */
   VTR_ASSERT(true == valid_bit_id(bit_id));
+  VTR_ASSERT(true == use_address_);
 
   return bit_dins_[bit_id];
 }
 
+bool FabricBitstream::use_address() const {
+  return use_address_;
+}
+
+bool FabricBitstream::use_wl_address() const {
+  return use_wl_address_;
+}
+
 /******************************************************************************
  * Public Mutators
  ******************************************************************************/
+void FabricBitstream::reserve_bits(const size_t& num_bits) {
+  config_bit_ids_.reserve(num_bits);
+ 
+  if (true == use_address_) {
+    bit_addresses_.reserve(num_bits);
+    bit_dins_.reserve(num_bits);
+ 
+    if (true == use_wl_address_) {
+      bit_wl_addresses_.reserve(num_bits);
+    }
+  }
+}
+
 FabricBitId FabricBitstream::add_bit(const ConfigBitId& config_bit_id) {
-  FabricBitId bit = FabricBitId(bit_ids_.size());
+  FabricBitId bit = FabricBitId(num_bits_);
   /* Add a new bit, and allocate associated data structures */
-  bit_ids_.push_back(bit);
+  num_bits_++;
   config_bit_ids_.push_back(config_bit_id);
-  bit_addresses_.emplace_back();
-  bit_dins_.push_back(false);
 
   return bit; 
 }
 
 void FabricBitstream::set_bit_address(const FabricBitId& bit_id,
-                                      const std::vector<size_t>& address) {
+                                      const std::vector<char>& address) {
   VTR_ASSERT(true == valid_bit_id(bit_id));
-  bit_addresses_[bit_id][0] = address;
+  VTR_ASSERT(true == use_address_);
+  VTR_ASSERT(address_length_ == address.size());
+  bit_addresses_[bit_id] = bintoi_charvec(address);
 }
 
 void FabricBitstream::set_bit_bl_address(const FabricBitId& bit_id,
-                                         const std::vector<size_t>& address) {
+                                         const std::vector<char>& address) {
   set_bit_address(bit_id, address);
 }
 
 void FabricBitstream::set_bit_wl_address(const FabricBitId& bit_id,
-                                         const std::vector<size_t>& address) {
+                                         const std::vector<char>& address) {
   VTR_ASSERT(true == valid_bit_id(bit_id));
-  bit_addresses_[bit_id][1] = address;
+  VTR_ASSERT(true == use_address_);
+  VTR_ASSERT(true == use_wl_address_);
+  VTR_ASSERT(wl_address_length_ == address.size());
+  bit_wl_addresses_[bit_id] = bintoi_charvec(address);
 }
 
 void FabricBitstream::set_bit_din(const FabricBitId& bit_id,
-                                  const bool& din) {
+                                  const char& din) {
   VTR_ASSERT(true == valid_bit_id(bit_id));
+  VTR_ASSERT(true == use_address_);
   bit_dins_[bit_id] = din;
 }
 
 void FabricBitstream::reverse() {
   std::reverse(config_bit_ids_.begin(), config_bit_ids_.end());
-  std::reverse(bit_addresses_.begin(), bit_addresses_.end());
-  std::reverse(bit_dins_.begin(), bit_dins_.end());
+
+  if (true == use_address_) {
+    std::reverse(bit_addresses_.begin(), bit_addresses_.end());
+    std::reverse(bit_dins_.begin(), bit_dins_.end());
+
+    if (true == use_wl_address_) {
+      std::reverse(bit_wl_addresses_.begin(), bit_wl_addresses_.end());
+    }
+  }
+}
+
+void FabricBitstream::set_use_address(const bool& enable) {
+  /* Add a lock, only can be modified when num bits are zero*/
+  if (0 == num_bits_) {
+    use_address_ = enable;
+  }
+}
+
+void FabricBitstream::set_address_length(const size_t& length) {
+  if (true == use_address_) {
+    address_length_ = length; 
+  }
+}
+
+void FabricBitstream::set_bl_address_length(const size_t& length) {
+  set_address_length(length);
+}
+
+void FabricBitstream::set_use_wl_address(const bool& enable) {
+  /* Add a lock, only can be modified when num bits are zero*/
+  if (0 == num_bits_) {
+    use_wl_address_ = enable;
+  }
+}
+
+void FabricBitstream::set_wl_address_length(const size_t& length) {
+  if (true == use_address_) {
+    wl_address_length_ = length; 
+  }
 }
 
 /******************************************************************************
  * Public Validators
  ******************************************************************************/
-bool FabricBitstream::valid_bit_id(const FabricBitId& bit_id) const {
-  return (size_t(bit_id) < bit_ids_.size()) && (bit_id == bit_ids_[bit_id]);
+char FabricBitstream::valid_bit_id(const FabricBitId& bit_id) const {
+  return (size_t(bit_id) < num_bits_);
 }
 
 } /* end namespace openfpga */
diff --git a/openfpga/src/fpga_bitstream/fabric_bitstream.h b/openfpga/src/fpga_bitstream/fabric_bitstream.h
index 519330dae..9869fffed 100644
--- a/openfpga/src/fpga_bitstream/fabric_bitstream.h
+++ b/openfpga/src/fpga_bitstream/fabric_bitstream.h
@@ -29,6 +29,8 @@
 #define FABRIC_BITSTREAM_H
 
 #include <vector>
+#include <unordered_set>
+#include <unordered_map>
 #include "vtr_vector.h"
 
 #include "bitstream_manager_fwd.h"
@@ -38,13 +40,68 @@
 namespace openfpga {
 
 class FabricBitstream {
+  public: /* Type implementations */
+    /*
+     * This class (forward delcared above) is a template used to represent a lazily calculated 
+     * iterator of the specified ID type. The key assumption made is that the ID space is 
+     * contiguous and can be walked by incrementing the underlying ID value. To account for 
+     * invalid IDs, it keeps a reference to the invalid ID set and returns ID::INVALID() for
+     * ID values in the set.
+     *
+     * It is used to lazily create an iteration range (e.g. as returned by RRGraph::edges() RRGraph::nodes())
+     * just based on the count of allocated elements (i.e. RRGraph::num_nodes_ or RRGraph::num_edges_),
+     * and the set of any invalid IDs (i.e. RRGraph::invalid_node_ids_, RRGraph::invalid_edge_ids_).
+     */
+    template<class ID>
+    class lazy_id_iterator : public std::iterator<std::bidirectional_iterator_tag, ID> {
+      public:
+        //Since we pass ID as a template to std::iterator we need to use an explicit 'typename'
+        //to bring the value_type and iterator names into scope
+        typedef typename std::iterator<std::bidirectional_iterator_tag, ID>::value_type value_type;
+        typedef typename std::iterator<std::bidirectional_iterator_tag, ID>::iterator iterator;
+
+        lazy_id_iterator(value_type init, const std::unordered_set<ID>& invalid_ids)
+            : value_(init)
+            , invalid_ids_(invalid_ids) {}
+
+        //Advance to the next ID value
+        iterator operator++() {
+            value_ = ID(size_t(value_) + 1);
+            return *this;
+        }
+
+        //Advance to the previous ID value
+        iterator operator--() {
+            value_ = ID(size_t(value_) - 1);
+            return *this;
+        }
+
+        //Dereference the iterator
+        value_type operator*() const { return (invalid_ids_.count(value_)) ? ID::INVALID() : value_; }
+
+        friend bool operator==(const lazy_id_iterator<ID> lhs, const lazy_id_iterator<ID> rhs) { return lhs.value_ == rhs.value_; }
+        friend bool operator!=(const lazy_id_iterator<ID> lhs, const lazy_id_iterator<ID> rhs) { return !(lhs == rhs); }
+
+      private:
+        value_type value_;
+        const std::unordered_set<ID>& invalid_ids_;
+    };
+
   public: /* Types and ranges */
-    typedef vtr::vector<FabricBitId, FabricBitId>::const_iterator fabric_bit_iterator;
+    //Lazy iterator utility forward declaration
+    template<class ID>
+    class lazy_id_iterator;
+
+    typedef lazy_id_iterator<FabricBitId> fabric_bit_iterator;
 
     typedef vtr::Range<fabric_bit_iterator> fabric_bit_range;
 
+  public: /* Public constructor */
+    FabricBitstream();
+
   public: /* Public aggregators */
     /* Find all the configuration bits */
+    size_t num_bits() const;
     fabric_bit_range bits() const;
 
   public:  /* Public Accessors */
@@ -52,52 +109,85 @@ class FabricBitstream {
     ConfigBitId config_bit(const FabricBitId& bit_id) const;
 
     /* Find the address of bitstream */
-    std::vector<size_t> bit_address(const FabricBitId& bit_id) const;
-    std::vector<size_t> bit_bl_address(const FabricBitId& bit_id) const;
-    std::vector<size_t> bit_wl_address(const FabricBitId& bit_id) const;
+    std::vector<char> bit_address(const FabricBitId& bit_id) const;
+    std::vector<char> bit_bl_address(const FabricBitId& bit_id) const;
+    std::vector<char> bit_wl_address(const FabricBitId& bit_id) const;
 
     /* Find the data-in of bitstream */
-    bool bit_din(const FabricBitId& bit_id) const;
+    char bit_din(const FabricBitId& bit_id) const;
+
+    /* Check if address data is accessible or not*/
+    bool use_address() const;
+    bool use_wl_address() const;
 
   public:  /* Public Mutators */
+    /* Reserve config bits */
+    void reserve_bits(const size_t& num_bits);
+
     /* Add a new configuration bit to the bitstream manager */
     FabricBitId add_bit(const ConfigBitId& config_bit_id);
 
     void set_bit_address(const FabricBitId& bit_id,
-                         const std::vector<size_t>& address);
+                         const std::vector<char>& address);
 
     void set_bit_bl_address(const FabricBitId& bit_id,
-                            const std::vector<size_t>& address);
+                            const std::vector<char>& address);
 
     void set_bit_wl_address(const FabricBitId& bit_id,
-                            const std::vector<size_t>& address);
+                            const std::vector<char>& address);
 
     void set_bit_din(const FabricBitId& bit_id,
-                     const bool& din);
+                     const char& din);
 
     /* Reverse bit sequence of the fabric bitstream
      * This is required by configuration chain protocol 
      */
     void reverse();
 
+    /* Enable the use of address-related data 
+     * When this is enabled, data allocation will be applied to these data
+     * and users can access/modify the data
+     * Otherwise, it will NOT be allocated and accessible.
+     *
+     * This function is only applicable before any bits are added
+     */
+    void set_use_address(const bool& enable);
+    void set_address_length(const size_t& length);
+    void set_bl_address_length(const size_t& length);
+
+    /* Enable the use of WL-address related data
+     * Same priniciple as the set_use_address()  
+     */
+    void set_use_wl_address(const bool& enable);
+    void set_wl_address_length(const size_t& length);
+
   public:  /* Public Validators */
-    bool valid_bit_id(const FabricBitId& bit_id) const;
+    char valid_bit_id(const FabricBitId& bit_id) const;
 
   private: /* Internal data */
     /* Unique id of a bit in the Bitstream */
-    vtr::vector<FabricBitId, FabricBitId> bit_ids_; 
+    size_t num_bits_; 
+    std::unordered_set<FabricBitId> invalid_bit_ids_;
     vtr::vector<FabricBitId, ConfigBitId> config_bit_ids_; 
 
+    /* Flags to indicate if the addresses and din should be enabled */
+    bool use_address_;
+    bool use_wl_address_;
+
+    size_t address_length_;
+    size_t wl_address_length_;
+
     /* Address bits: this is designed for memory decoders
      * Here we store the binary format of the address, which can be loaded
      * to the configuration protocol directly 
      *
      * We use a 2-element array, as we may have a BL address and a WL address
      */
-    vtr::vector<FabricBitId, std::array<std::vector<size_t>, 2>> bit_addresses_;
+    vtr::vector<FabricBitId, size_t> bit_addresses_;
+    vtr::vector<FabricBitId, size_t> bit_wl_addresses_;
 
     /* Data input (Din) bits: this is designed for memory decoders */
-    vtr::vector<FabricBitId, bool> bit_dins_;
+    vtr::vector<FabricBitId, char> bit_dins_;
 };
 
 } /* end namespace openfpga */
diff --git a/openfpga/src/fpga_bitstream/fabric_bitstream_writer.cpp b/openfpga/src/fpga_bitstream/fabric_bitstream_writer.cpp
index 6317fd47d..2991dd6a0 100644
--- a/openfpga/src/fpga_bitstream/fabric_bitstream_writer.cpp
+++ b/openfpga/src/fpga_bitstream/fabric_bitstream_writer.cpp
@@ -50,11 +50,11 @@ int write_fabric_config_bit_to_text_file(std::fstream& fp,
     fp << bitstream_manager.bit_value(fabric_bitstream.config_bit(fabric_bit));
     break;
   case CONFIG_MEM_MEMORY_BANK: { 
-    for (const size_t& addr_bit : fabric_bitstream.bit_bl_address(fabric_bit)) {
+    for (const char& addr_bit : fabric_bitstream.bit_bl_address(fabric_bit)) {
       fp << addr_bit;
     }
     write_space_to_file(fp, 1);
-    for (const size_t& addr_bit : fabric_bitstream.bit_wl_address(fabric_bit)) {
+    for (const char& addr_bit : fabric_bitstream.bit_wl_address(fabric_bit)) {
       fp << addr_bit;
     }
     write_space_to_file(fp, 1);
@@ -63,7 +63,7 @@ int write_fabric_config_bit_to_text_file(std::fstream& fp,
     break;
   }
   case CONFIG_MEM_FRAME_BASED: {
-    for (const size_t& addr_bit : fabric_bitstream.bit_address(fabric_bit)) {
+    for (const char& addr_bit : fabric_bitstream.bit_address(fabric_bit)) {
       fp << addr_bit;
     }
     write_space_to_file(fp, 1);
@@ -101,7 +101,7 @@ int write_fabric_bitstream_to_text_file(const BitstreamManager& bitstream_manage
     VTR_LOG_ERROR("Received empty file name to output bitstream!\n\tPlease specify a valid file name.\n");
   }
 
-  std::string timer_message = std::string("Write ") + std::to_string(fabric_bitstream.bits().size()) + std::string(" fabric bitstream into plain text file '") + fname + std::string("'");
+  std::string timer_message = std::string("Write ") + std::to_string(fabric_bitstream.num_bits()) + std::string(" fabric bitstream into plain text file '") + fname + std::string("'");
   vtr::ScopedStartFinishTimer timer(timer_message);
 
   /* Create the file stream */
diff --git a/openfpga/src/fpga_verilog/simulation_info_writer.cpp b/openfpga/src/fpga_verilog/simulation_info_writer.cpp
index de9f5f6af..134b34f0a 100644
--- a/openfpga/src/fpga_verilog/simulation_info_writer.cpp
+++ b/openfpga/src/fpga_verilog/simulation_info_writer.cpp
@@ -78,6 +78,7 @@ void print_verilog_simulation_info(const std::string& ini_fname,
   ini["SIMULATION_DECK"]["VERILOG_PATH "] = std::string(src_dir);
   ini["SIMULATION_DECK"]["VERILOG_FILE1"] = std::string(DEFINES_VERILOG_FILE_NAME);
   ini["SIMULATION_DECK"]["VERILOG_FILE2"] = std::string(circuit_name + std::string(TOP_INCLUDE_NETLIST_FILE_NAME_POSTFIX));
+  ini["SIMULATION_DECK"]["CONFIG_PROTOCOL"] = std::string(CONFIG_PROTOCOL_TYPE_STRING[config_protocol_type]);
 
   /* Information required by UVM */
   if (CONFIG_MEM_FRAME_BASED == config_protocol_type) {
diff --git a/openfpga/src/fpga_verilog/verilog_api.cpp b/openfpga/src/fpga_verilog/verilog_api.cpp
index ff7872999..0e2f84124 100644
--- a/openfpga/src/fpga_verilog/verilog_api.cpp
+++ b/openfpga/src/fpga_verilog/verilog_api.cpp
@@ -234,7 +234,7 @@ namespace openfpga
                                     atom_ctx, place_ctx, io_location_map,
                                     module_manager,
                                     config_protocol_type,
-                                    bitstream_manager.bits().size(),
+                                    bitstream_manager.num_bits(),
                                     simulation_setting.num_clock_cycles(),
                                     simulation_setting.programming_clock_frequency(),
                                     simulation_setting.operating_clock_frequency());
diff --git a/openfpga/src/fpga_verilog/verilog_top_testbench.cpp b/openfpga/src/fpga_verilog/verilog_top_testbench.cpp
index c985c48f0..9e7bde572 100644
--- a/openfpga/src/fpga_verilog/verilog_top_testbench.cpp
+++ b/openfpga/src/fpga_verilog/verilog_top_testbench.cpp
@@ -562,7 +562,7 @@ static
 size_t calculate_num_config_clock_cycles(const e_config_protocol_type& sram_orgz_type,
                                          const bool& fast_configuration,
                                          const FabricBitstream& fabric_bitstream) {
-  size_t num_config_clock_cycles = 1 + fabric_bitstream.bits().size();
+  size_t num_config_clock_cycles = 1 + fabric_bitstream.num_bits();
 
   /* Branch on the type of configuration protocol */
   switch (sram_orgz_type) {
@@ -1223,14 +1223,14 @@ void print_verilog_top_testbench_memory_bank_bitstream(std::fstream& fp,
     fp << "\t\t" << std::string(TOP_TESTBENCH_PROG_TASK_NAME);
     fp << "(" << bl_addr_port.get_width() << "'b";
     VTR_ASSERT(bl_addr_port.get_width() == fabric_bitstream.bit_bl_address(bit_id).size());
-    for (const size_t& addr_bit : fabric_bitstream.bit_bl_address(bit_id)) {
+    for (const char& addr_bit : fabric_bitstream.bit_bl_address(bit_id)) {
       fp << addr_bit;
     }
 
     fp << ", ";
     fp << wl_addr_port.get_width() << "'b";
     VTR_ASSERT(wl_addr_port.get_width() == fabric_bitstream.bit_wl_address(bit_id).size());
-    for (const size_t& addr_bit : fabric_bitstream.bit_wl_address(bit_id)) {
+    for (const char& addr_bit : fabric_bitstream.bit_wl_address(bit_id)) {
       fp << addr_bit;
     }
 
@@ -1319,7 +1319,7 @@ void print_verilog_top_testbench_frame_decoder_bitstream(std::fstream& fp,
     fp << "\t\t" << std::string(TOP_TESTBENCH_PROG_TASK_NAME);
     fp << "(" << addr_port.get_width() << "'b";
     VTR_ASSERT(addr_port.get_width() == fabric_bitstream.bit_address(bit_id).size());
-    for (const size_t& addr_bit : fabric_bitstream.bit_address(bit_id)) {
+    for (const char& addr_bit : fabric_bitstream.bit_address(bit_id)) {
       fp << addr_bit;
     }
     fp << ", ";
diff --git a/openfpga/src/main.cpp b/openfpga/src/main.cpp
index e1f813e9b..9f332263c 100644
--- a/openfpga/src/main.cpp
+++ b/openfpga/src/main.cpp
@@ -25,6 +25,7 @@
  * Main function to start OpenFPGA shell interface
  *******************************************************************/
 int main(int argc, char** argv) {
+
   /* Create the command to launch shell in different modes */
   openfpga::Command start_cmd("OpenFPGA");
   /* Add two options:
@@ -89,13 +90,11 @@ int main(int argc, char** argv) {
     /* Parse succeed. Start a shell */ 
     if (true == start_cmd_context.option_enable(start_cmd, opt_interactive)) {
 
-      vtr::ScopedStartFinishTimer timer("OpenFPGA operating");
       shell.run_interactive_mode(openfpga_context);
       return 0;
     } 
 
     if (true == start_cmd_context.option_enable(start_cmd, opt_script_mode)) {
-      vtr::ScopedStartFinishTimer timer("OpenFPGA operating");
       shell.run_script_mode(start_cmd_context.option_value(start_cmd, opt_script_mode).c_str(),
                             openfpga_context);
       return 0;
diff --git a/openfpga_flow/OpenFPGAShellScripts/generate_bitstream_example_script.openfpga b/openfpga_flow/OpenFPGAShellScripts/generate_bitstream_example_script.openfpga
new file mode 100644
index 000000000..e7c934513
--- /dev/null
+++ b/openfpga_flow/OpenFPGAShellScripts/generate_bitstream_example_script.openfpga
@@ -0,0 +1,47 @@
+# Run VPR for the 'and' design
+#--write_rr_graph example_rr_graph.xml
+vpr ${VPR_ARCH_FILE} ${VPR_TESTBENCH_BLIF} --clock_modeling route
+
+# Read OpenFPGA architecture definition
+read_openfpga_arch -f ${OPENFPGA_ARCH_FILE}
+
+# Read OpenFPGA simulation settings
+read_openfpga_simulation_setting -f ${OPENFPGA_SIM_SETTING_FILE}
+
+# Annotate the OpenFPGA architecture to VPR data base
+# to debug use --verbose options
+link_openfpga_arch --activity_file ${ACTIVITY_FILE} --sort_gsb_chan_node_in_edges
+
+# Check and correct any naming conflicts in the BLIF netlist
+check_netlist_naming_conflict --fix --report ./netlist_renaming.xml
+
+# Apply fix-up to clustering nets based on routing results
+pb_pin_fixup --verbose
+
+# Apply fix-up to Look-Up Table truth tables based on packing results
+lut_truth_table_fixup
+
+# Build the module graph
+#  - Enabled compression on routing architecture modules
+#  - Enabled frame view creation to save runtime and memory
+#    Note that this is turned on when bitstream generation 
+#    is the ONLY purpose of the flow!!!
+build_fabric --compress_routing --frame_view #--verbose
+
+# Repack the netlist to physical pbs
+# This must be done before bitstream generator and testbench generation
+# Strongly recommend it is done after all the fix-up have been applied
+repack #--verbose
+
+# Build the bitstream
+#  - Output the fabric-independent bitstream to a file
+build_architecture_bitstream --verbose --write_file fabric_indepenent_bitstream.xml
+
+# Build fabric-dependent bitstream
+build_fabric_bitstream --verbose
+
+# Finish and exit OpenFPGA
+exit
+
+# Note :
+# To run verification at the end of the flow maintain source in ./SRC directory
diff --git a/openfpga_flow/tasks/openfpga_shell/generate_bitstream/config/task.conf b/openfpga_flow/tasks/openfpga_shell/generate_bitstream/config/task.conf
new file mode 100644
index 000000000..4c12ab08b
--- /dev/null
+++ b/openfpga_flow/tasks/openfpga_shell/generate_bitstream/config/task.conf
@@ -0,0 +1,33 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# Configuration file for running experiments
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# timeout_each_job : FPGA Task script splits fpga flow into multiple jobs
+# Each job execute fpga_flow script on combination of architecture & benchmark
+# timeout_each_job is timeout for each job
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+
+[GENERAL]
+run_engine=openfpga_shell
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/generate_bitstream_example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_40nm_openfpga.xml
+openfpga_sim_setting_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_simulation_settings/auto_sim_openfpga.xml
+external_fabric_key_file=
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and2/and2.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = and2
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and2/and2.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and2/and2.v
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]